compaction.c 21.2 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14
/*
 * 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/swap.h>
#include <linux/migrate.h>
#include <linux/compaction.h>
#include <linux/mm_inline.h>
#include <linux/backing-dev.h>
15
#include <linux/sysctl.h>
16
#include <linux/sysfs.h>
17 18
#include "internal.h"

19 20 21
#define CREATE_TRACE_POINTS
#include <trace/events/compaction.h>

22 23 24 25 26 27 28 29 30 31 32 33 34 35
/*
 * compact_control is used to track pages being migrated and the free pages
 * they are being migrated to during memory compaction. The free_pfn starts
 * at the end of a zone and migrate_pfn begins at the start. Movable pages
 * are moved to the end of a zone during a compaction run and the run
 * completes when free_pfn <= migrate_pfn
 */
struct compact_control {
	struct list_head freepages;	/* List of free pages to migrate to */
	struct list_head migratepages;	/* List of pages being migrated */
	unsigned long nr_freepages;	/* Number of isolated free pages */
	unsigned long nr_migratepages;	/* Number of pages to migrate */
	unsigned long free_pfn;		/* isolate_freepages search base */
	unsigned long migrate_pfn;	/* isolate_migratepages search base */
36
	bool sync;			/* Synchronous migration */
37

38
	int order;			/* order a direct compactor needs */
39
	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
	struct zone *zone;
};

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

	list_for_each_entry_safe(page, next, freelist, lru) {
		list_del(&page->lru);
		__free_page(page);
		count++;
	}

	return count;
}

/* Isolate free pages onto a private freelist. Must hold zone->lock */
static unsigned long isolate_freepages_block(struct zone *zone,
				unsigned long blockpfn,
				struct list_head *freelist)
{
	unsigned long zone_end_pfn, end_pfn;
63
	int nr_scanned = 0, total_isolated = 0;
64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83
	struct page *cursor;

	/* Get the last PFN we should scan for free pages at */
	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
	end_pfn = min(blockpfn + pageblock_nr_pages, zone_end_pfn);

	/* Find the first usable PFN in the block to initialse page cursor */
	for (; blockpfn < end_pfn; blockpfn++) {
		if (pfn_valid_within(blockpfn))
			break;
	}
	cursor = pfn_to_page(blockpfn);

	/* Isolate free pages. This assumes the block is valid */
	for (; blockpfn < end_pfn; blockpfn++, cursor++) {
		int isolated, i;
		struct page *page = cursor;

		if (!pfn_valid_within(blockpfn))
			continue;
84
		nr_scanned++;
85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103

		if (!PageBuddy(page))
			continue;

		/* Found a free page, break it into order-0 pages */
		isolated = split_free_page(page);
		total_isolated += isolated;
		for (i = 0; i < isolated; i++) {
			list_add(&page->lru, freelist);
			page++;
		}

		/* If a page was split, advance to the end of it */
		if (isolated) {
			blockpfn += isolated - 1;
			cursor += isolated - 1;
		}
	}

104
	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142
	return total_isolated;
}

/* Returns true if the page is within a block suitable for migration to */
static bool suitable_migration_target(struct page *page)
{

	int migratetype = get_pageblock_migratetype(page);

	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
		return false;

	/* If the page is a large free page, then allow migration */
	if (PageBuddy(page) && page_order(page) >= pageblock_order)
		return true;

	/* If the block is MIGRATE_MOVABLE, allow migration */
	if (migratetype == MIGRATE_MOVABLE)
		return true;

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

/*
 * 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 zone *zone,
				struct compact_control *cc)
{
	struct page *page;
	unsigned long high_pfn, low_pfn, pfn;
	unsigned long flags;
	int nr_freepages = cc->nr_freepages;
	struct list_head *freelist = &cc->freepages;

143 144 145 146 147
	/*
	 * Initialise the free scanner. The starting point is where we last
	 * scanned from (or the end of the zone if starting). The low point
	 * is the end of the pageblock the migration scanner is using.
	 */
148 149
	pfn = cc->free_pfn;
	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
150 151 152 153 154 155 156

	/*
	 * Take care that if the migration scanner is at the end of the zone
	 * that the free scanner does not accidentally move to the next zone
	 * in the next isolation cycle.
	 */
	high_pfn = min(low_pfn, pfn);
157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184

	/*
	 * 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 (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
					pfn -= pageblock_nr_pages) {
		unsigned long isolated;

		if (!pfn_valid(pfn))
			continue;

		/*
		 * Check for overlapping nodes/zones. 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.
		 */
		page = pfn_to_page(pfn);
		if (page_zone(page) != zone)
			continue;

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

185 186 187 188 189 190 191 192 193 194 195 196 197
		/*
		 * Found a block suitable for isolating free pages from. Now
		 * we disabled interrupts, double check things are ok and
		 * isolate the pages. This is to minimise the time IRQs
		 * are disabled
		 */
		isolated = 0;
		spin_lock_irqsave(&zone->lock, flags);
		if (suitable_migration_target(page)) {
			isolated = isolate_freepages_block(zone, pfn, freelist);
			nr_freepages += isolated;
		}
		spin_unlock_irqrestore(&zone->lock, flags);
198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221

		/*
		 * Record the highest PFN we isolated pages from. When next
		 * looking for free pages, the search will restart here as
		 * page migration may have returned some pages to the allocator
		 */
		if (isolated)
			high_pfn = max(high_pfn, pfn);
	}

	/* split_free_page does not map the pages */
	list_for_each_entry(page, freelist, lru) {
		arch_alloc_page(page, 0);
		kernel_map_pages(page, 1, 1);
	}

	cc->free_pfn = high_pfn;
	cc->nr_freepages = nr_freepages;
}

/* Update the number of anon and file isolated pages in the zone */
static void acct_isolated(struct zone *zone, struct compact_control *cc)
{
	struct page *page;
222
	unsigned int count[2] = { 0, };
223

224 225
	list_for_each_entry(page, &cc->migratepages, lru)
		count[!!page_is_file_cache(page)]++;
226

227 228
	__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
	__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
229 230 231 232 233
}

/* Similar to reclaim, but different enough that they don't share logic */
static bool too_many_isolated(struct zone *zone)
{
234
	unsigned long active, inactive, isolated;
235 236 237

	inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
					zone_page_state(zone, NR_INACTIVE_ANON);
238 239
	active = zone_page_state(zone, NR_ACTIVE_FILE) +
					zone_page_state(zone, NR_ACTIVE_ANON);
240 241 242
	isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
					zone_page_state(zone, NR_ISOLATED_ANON);

243
	return isolated > (inactive + active) / 2;
244 245
}

246 247 248 249 250 251 252
/* 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;

253 254 255 256
/*
 * Isolate all pages that can be migrated from the block pointed to by
 * the migrate scanner within compact_control.
 */
257
static isolate_migrate_t isolate_migratepages(struct zone *zone,
258 259 260
					struct compact_control *cc)
{
	unsigned long low_pfn, end_pfn;
261
	unsigned long last_pageblock_nr = 0, pageblock_nr;
262
	unsigned long nr_scanned = 0, nr_isolated = 0;
263
	struct list_head *migratelist = &cc->migratepages;
264
	isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;
265 266 267 268 269 270 271 272 273 274

	/* Do not scan outside zone boundaries */
	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);

	/* Only scan within a pageblock boundary */
	end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages);

	/* Do not cross the free scanner or scan within a memory hole */
	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
		cc->migrate_pfn = end_pfn;
275
		return ISOLATE_NONE;
276 277 278 279 280 281 282 283
	}

	/*
	 * 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))) {
284 285 286 287
		/* async migration should just abort */
		if (!cc->sync)
			return ISOLATE_ABORT;

288 289 290
		congestion_wait(BLK_RW_ASYNC, HZ/10);

		if (fatal_signal_pending(current))
291
			return ISOLATE_ABORT;
292 293 294
	}

	/* Time to isolate some pages for migration */
295
	cond_resched();
296 297 298
	spin_lock_irq(&zone->lru_lock);
	for (; low_pfn < end_pfn; low_pfn++) {
		struct page *page;
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315
		bool locked = true;

		/* give a chance to irqs before checking need_resched() */
		if (!((low_pfn+1) % SWAP_CLUSTER_MAX)) {
			spin_unlock_irq(&zone->lru_lock);
			locked = false;
		}
		if (need_resched() || spin_is_contended(&zone->lru_lock)) {
			if (locked)
				spin_unlock_irq(&zone->lru_lock);
			cond_resched();
			spin_lock_irq(&zone->lru_lock);
			if (fatal_signal_pending(current))
				break;
		} else if (!locked)
			spin_lock_irq(&zone->lru_lock);

316 317 318 319 320 321 322 323 324 325 326 327 328
		/*
		 * migrate_pfn does not necessarily start aligned to a
		 * pageblock. Ensure that pfn_valid is called when moving
		 * into a new MAX_ORDER_NR_PAGES range in case of large
		 * memory holes within the zone
		 */
		if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
			if (!pfn_valid(low_pfn)) {
				low_pfn += MAX_ORDER_NR_PAGES - 1;
				continue;
			}
		}

329 330
		if (!pfn_valid_within(low_pfn))
			continue;
331
		nr_scanned++;
332

333 334 335 336 337 338
		/*
		 * Get the page and ensure the page is within the same zone.
		 * See the comment in isolate_freepages about overlapping
		 * nodes. It is deliberate that the new zone lock is not taken
		 * as memory compaction should not move pages between nodes.
		 */
339
		page = pfn_to_page(low_pfn);
340 341 342 343
		if (page_zone(page) != zone)
			continue;

		/* Skip if free */
344 345 346
		if (PageBuddy(page))
			continue;

347 348 349 350 351 352 353 354 355 356 357 358 359 360
		/*
		 * For async migration, also only scan in MOVABLE blocks. Async
		 * migration is optimistic to see if the minimum amount of work
		 * satisfies the allocation
		 */
		pageblock_nr = low_pfn >> pageblock_order;
		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
				get_pageblock_migratetype(page) != MIGRATE_MOVABLE) {
			low_pfn += pageblock_nr_pages;
			low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
			last_pageblock_nr = pageblock_nr;
			continue;
		}

361 362 363 364 365 366 367 368 369 370 371 372 373
		if (!PageLRU(page))
			continue;

		/*
		 * PageLRU is set, and lru_lock excludes isolation,
		 * splitting and collapsing (collapsing has already
		 * happened if PageLRU is set).
		 */
		if (PageTransHuge(page)) {
			low_pfn += (1 << compound_order(page)) - 1;
			continue;
		}

374 375 376
		if (!cc->sync)
			mode |= ISOLATE_ASYNC_MIGRATE;

377
		/* Try isolate the page */
378
		if (__isolate_lru_page(page, mode, 0) != 0)
379 380
			continue;

381 382
		VM_BUG_ON(PageTransCompound(page));

383 384 385 386
		/* Successfully isolated */
		del_page_from_lru_list(zone, page, page_lru(page));
		list_add(&page->lru, migratelist);
		cc->nr_migratepages++;
387
		nr_isolated++;
388 389

		/* Avoid isolating too much */
390 391
		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
			++low_pfn;
392
			break;
393
		}
394 395 396 397 398 399 400
	}

	acct_isolated(zone, cc);

	spin_unlock_irq(&zone->lru_lock);
	cc->migrate_pfn = low_pfn;

401 402
	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);

403
	return ISOLATE_SUCCESS;
404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
}

/*
 * 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 */
	if (list_empty(&cc->freepages)) {
		isolate_freepages(cc->zone, 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;
}

/*
 * We cannot control nr_migratepages and nr_freepages fully when migration is
 * running as migrate_pages() has no knowledge of compact_control. When
 * migration is complete, we count the number of pages on the lists by hand.
 */
static void update_nr_listpages(struct compact_control *cc)
{
	int nr_migratepages = 0;
	int nr_freepages = 0;
	struct page *page;

	list_for_each_entry(page, &cc->migratepages, lru)
		nr_migratepages++;
	list_for_each_entry(page, &cc->freepages, lru)
		nr_freepages++;

	cc->nr_migratepages = nr_migratepages;
	cc->nr_freepages = nr_freepages;
}

static int compact_finished(struct zone *zone,
453
			    struct compact_control *cc)
454
{
455
	unsigned int order;
456
	unsigned long watermark;
457

458 459 460 461 462 463 464
	if (fatal_signal_pending(current))
		return COMPACT_PARTIAL;

	/* Compaction run completes if the migrate and free scanner meet */
	if (cc->free_pfn <= cc->migrate_pfn)
		return COMPACT_COMPLETE;

465 466 467 468
	/*
	 * order == -1 is expected when compacting via
	 * /proc/sys/vm/compact_memory
	 */
469 470 471
	if (cc->order == -1)
		return COMPACT_CONTINUE;

472 473 474 475 476 477 478
	/* Compaction run is not finished if the watermark is not met */
	watermark = low_wmark_pages(zone);
	watermark += (1 << cc->order);

	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
		return COMPACT_CONTINUE;

479 480 481 482 483 484 485 486 487 488 489
	/* Direct compactor: Is a suitable page free? */
	for (order = cc->order; order < MAX_ORDER; order++) {
		/* Job done if page is free of the right migratetype */
		if (!list_empty(&zone->free_area[order].free_list[cc->migratetype]))
			return COMPACT_PARTIAL;

		/* Job done if allocation would set block type */
		if (order >= pageblock_order && zone->free_area[order].nr_free)
			return COMPACT_PARTIAL;
	}

490 491 492
	return COMPACT_CONTINUE;
}

493 494 495 496 497 498 499 500 501 502 503 504
/*
 * 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_PARTIAL  - If the allocation would succeed without compaction
 *   COMPACT_CONTINUE - If compaction should run now
 */
unsigned long compaction_suitable(struct zone *zone, int order)
{
	int fragindex;
	unsigned long watermark;

505 506 507 508 509 510 511
	/*
	 * order == -1 is expected when compacting via
	 * /proc/sys/vm/compact_memory
	 */
	if (order == -1)
		return COMPACT_CONTINUE;

512 513 514 515 516 517 518 519 520 521 522 523 524
	/*
	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
	 * This is because during migration, copies of pages need to be
	 * allocated and for a short time, the footprint is higher
	 */
	watermark = low_wmark_pages(zone) + (2UL << order);
	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
		return COMPACT_SKIPPED;

	/*
	 * fragmentation index determines if allocation failures are due to
	 * low memory or external fragmentation
	 *
525 526
	 * index of -1000 implies allocations might succeed depending on
	 * watermarks
527 528 529 530 531 532 533 534 535
	 * index towards 0 implies failure is due to lack of memory
	 * index towards 1000 implies failure is due to fragmentation
	 *
	 * Only compact if a failure would be due to fragmentation.
	 */
	fragindex = fragmentation_index(zone, order);
	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
		return COMPACT_SKIPPED;

536 537
	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
	    0, 0))
538 539 540 541 542
		return COMPACT_PARTIAL;

	return COMPACT_CONTINUE;
}

543 544 545 546
static int compact_zone(struct zone *zone, struct compact_control *cc)
{
	int ret;

547 548 549 550 551 552 553 554 555 556 557
	ret = compaction_suitable(zone, cc->order);
	switch (ret) {
	case COMPACT_PARTIAL:
	case COMPACT_SKIPPED:
		/* Compaction is likely to fail */
		return ret;
	case COMPACT_CONTINUE:
		/* Fall through to compaction */
		;
	}

558 559 560 561 562 563 564 565 566
	/* Setup to move all movable pages to the end of the zone */
	cc->migrate_pfn = zone->zone_start_pfn;
	cc->free_pfn = cc->migrate_pfn + zone->spanned_pages;
	cc->free_pfn &= ~(pageblock_nr_pages-1);

	migrate_prep_local();

	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
		unsigned long nr_migrate, nr_remaining;
567
		int err;
568

569 570 571 572 573
		switch (isolate_migratepages(zone, cc)) {
		case ISOLATE_ABORT:
			ret = COMPACT_PARTIAL;
			goto out;
		case ISOLATE_NONE:
574
			continue;
575 576 577
		case ISOLATE_SUCCESS:
			;
		}
578 579

		nr_migrate = cc->nr_migratepages;
580
		err = migrate_pages(&cc->migratepages, compaction_alloc,
581
				(unsigned long)cc, false,
582
				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
583 584 585 586 587 588 589
		update_nr_listpages(cc);
		nr_remaining = cc->nr_migratepages;

		count_vm_event(COMPACTBLOCKS);
		count_vm_events(COMPACTPAGES, nr_migrate - nr_remaining);
		if (nr_remaining)
			count_vm_events(COMPACTPAGEFAILED, nr_remaining);
590 591
		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
						nr_remaining);
592 593

		/* Release LRU pages not migrated */
594
		if (err) {
595 596 597 598 599 600
			putback_lru_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
		}

	}

601
out:
602 603 604 605 606 607
	/* Release free pages and check accounting */
	cc->nr_freepages -= release_freepages(&cc->freepages);
	VM_BUG_ON(cc->nr_freepages != 0);

	return ret;
}
608

609
static unsigned long compact_zone_order(struct zone *zone,
610
				 int order, gfp_t gfp_mask,
611
				 bool sync)
612 613 614 615 616 617 618
{
	struct compact_control cc = {
		.nr_freepages = 0,
		.nr_migratepages = 0,
		.order = order,
		.migratetype = allocflags_to_migratetype(gfp_mask),
		.zone = zone,
619
		.sync = sync,
620 621 622 623 624 625 626
	};
	INIT_LIST_HEAD(&cc.freepages);
	INIT_LIST_HEAD(&cc.migratepages);

	return compact_zone(zone, &cc);
}

627 628
int sysctl_extfrag_threshold = 500;

629 630 631 632 633 634
/**
 * try_to_compact_pages - Direct compact to satisfy a high-order allocation
 * @zonelist: The zonelist used for the current allocation
 * @order: The order of the current allocation
 * @gfp_mask: The GFP mask of the current allocation
 * @nodemask: The allowed nodes to allocate from
635
 * @sync: Whether migration is synchronous or not
636 637 638 639
 *
 * This is the main entry point for direct page compaction.
 */
unsigned long try_to_compact_pages(struct zonelist *zonelist,
640 641
			int order, gfp_t gfp_mask, nodemask_t *nodemask,
			bool sync)
642 643 644 645 646 647 648 649 650 651 652 653 654
{
	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
	int may_enter_fs = gfp_mask & __GFP_FS;
	int may_perform_io = gfp_mask & __GFP_IO;
	struct zoneref *z;
	struct zone *zone;
	int rc = COMPACT_SKIPPED;

	/*
	 * Check whether it is worth even starting compaction. The order check is
	 * made because an assumption is made that the page allocator can satisfy
	 * the "cheaper" orders without taking special steps
	 */
655
	if (!order || !may_enter_fs || !may_perform_io)
656 657 658 659 660 661 662 663 664
		return rc;

	count_vm_event(COMPACTSTALL);

	/* Compact each zone in the list */
	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
								nodemask) {
		int status;

665
		status = compact_zone_order(zone, order, gfp_mask, sync);
666 667
		rc = max(status, rc);

668 669
		/* If a normal allocation would succeed, stop compacting */
		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
670 671 672 673 674 675 676
			break;
	}

	return rc;
}


677
/* Compact all zones within a node */
678
static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc)
679 680 681 682 683 684 685 686 687 688
{
	int zoneid;
	struct zone *zone;

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {

		zone = &pgdat->node_zones[zoneid];
		if (!populated_zone(zone))
			continue;

689 690 691 692 693
		cc->nr_freepages = 0;
		cc->nr_migratepages = 0;
		cc->zone = zone;
		INIT_LIST_HEAD(&cc->freepages);
		INIT_LIST_HEAD(&cc->migratepages);
694

695
		if (cc->order == -1 || !compaction_deferred(zone, cc->order))
696
			compact_zone(zone, cc);
697

698 699 700 701 702 703 704 705 706 707
		if (cc->order > 0) {
			int ok = zone_watermark_ok(zone, cc->order,
						low_wmark_pages(zone), 0, 0);
			if (ok && cc->order > zone->compact_order_failed)
				zone->compact_order_failed = cc->order + 1;
			/* Currently async compaction is never deferred. */
			else if (!ok && cc->sync)
				defer_compaction(zone, cc->order);
		}

708 709
		VM_BUG_ON(!list_empty(&cc->freepages));
		VM_BUG_ON(!list_empty(&cc->migratepages));
710 711 712 713 714
	}

	return 0;
}

715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731
int compact_pgdat(pg_data_t *pgdat, int order)
{
	struct compact_control cc = {
		.order = order,
		.sync = false,
	};

	return __compact_pgdat(pgdat, &cc);
}

static int compact_node(int nid)
{
	struct compact_control cc = {
		.order = -1,
		.sync = true,
	};

732
	return __compact_pgdat(NODE_DATA(nid), &cc);
733 734
}

735 736 737 738 739
/* Compact all nodes in the system */
static int compact_nodes(void)
{
	int nid;

740 741 742
	/* Flush pending updates to the LRU lists */
	lru_add_drain_all();

743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760
	for_each_online_node(nid)
		compact_node(nid);

	return COMPACT_COMPLETE;
}

/* The written value is actually unused, all memory is compacted */
int sysctl_compact_memory;

/* This is the entry point for compacting all nodes via /proc/sys/vm */
int sysctl_compaction_handler(struct ctl_table *table, int write,
			void __user *buffer, size_t *length, loff_t *ppos)
{
	if (write)
		return compact_nodes();

	return 0;
}
761

762 763 764 765 766 767 768 769
int sysctl_extfrag_handler(struct ctl_table *table, int write,
			void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec_minmax(table, write, buffer, length, ppos);

	return 0;
}

770
#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
771 772
ssize_t sysfs_compact_node(struct device *dev,
			struct device_attribute *attr,
773 774
			const char *buf, size_t count)
{
775 776 777 778 779 780 781 782
	int nid = dev->id;

	if (nid >= 0 && nid < nr_node_ids && node_online(nid)) {
		/* Flush pending updates to the LRU lists */
		lru_add_drain_all();

		compact_node(nid);
	}
783 784 785

	return count;
}
786
static DEVICE_ATTR(compact, S_IWUSR, NULL, sysfs_compact_node);
787 788 789

int compaction_register_node(struct node *node)
{
790
	return device_create_file(&node->dev, &dev_attr_compact);
791 792 793 794
}

void compaction_unregister_node(struct node *node)
{
795
	return device_remove_file(&node->dev, &dev_attr_compact);
796 797
}
#endif /* CONFIG_SYSFS && CONFIG_NUMA */