compaction.c 16.6 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 36 37 38 39 40
/*
 * 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 */

	/* Account for isolated anon and file pages */
	unsigned long nr_anon;
	unsigned long nr_file;

41 42
	unsigned int order;		/* order a direct compactor needs */
	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
	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;
66
	int nr_scanned = 0, total_isolated = 0;
67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86
	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;
87
		nr_scanned++;
88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106

		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;
		}
	}

107
	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221
	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;

	pfn = cc->free_pfn;
	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
	high_pfn = low_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.
	 */
	spin_lock_irqsave(&zone->lock, flags);
	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;

		/* Found a block suitable for isolating free pages from */
		isolated = isolate_freepages_block(zone, pfn, freelist);
		nr_freepages += isolated;

		/*
		 * 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);
	}
	spin_unlock_irqrestore(&zone->lock, flags);

	/* 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;
	unsigned int count[NR_LRU_LISTS] = { 0, };

	list_for_each_entry(page, &cc->migratepages, lru) {
		int lru = page_lru_base_type(page);
		count[lru]++;
	}

	cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
	cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
	__mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon);
	__mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file);
}

/* Similar to reclaim, but different enough that they don't share logic */
static bool too_many_isolated(struct zone *zone)
{
222
	unsigned long active, inactive, isolated;
223 224 225

	inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
					zone_page_state(zone, NR_INACTIVE_ANON);
226 227
	active = zone_page_state(zone, NR_ACTIVE_FILE) +
					zone_page_state(zone, NR_ACTIVE_ANON);
228 229 230
	isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
					zone_page_state(zone, NR_ISOLATED_ANON);

231
	return isolated > (inactive + active) / 2;
232 233 234 235 236 237 238 239 240 241
}

/*
 * Isolate all pages that can be migrated from the block pointed to by
 * the migrate scanner within compact_control.
 */
static unsigned long isolate_migratepages(struct zone *zone,
					struct compact_control *cc)
{
	unsigned long low_pfn, end_pfn;
242
	unsigned long nr_scanned = 0, nr_isolated = 0;
243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274
	struct list_head *migratelist = &cc->migratepages;

	/* 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;
		return 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))) {
		congestion_wait(BLK_RW_ASYNC, HZ/10);

		if (fatal_signal_pending(current))
			return 0;
	}

	/* Time to isolate some pages for migration */
	spin_lock_irq(&zone->lru_lock);
	for (; low_pfn < end_pfn; low_pfn++) {
		struct page *page;
		if (!pfn_valid_within(low_pfn))
			continue;
275
		nr_scanned++;
276 277 278 279 280 281 282 283 284 285 286 287 288 289

		/* Get the page and skip if free */
		page = pfn_to_page(low_pfn);
		if (PageBuddy(page))
			continue;

		/* Try isolate the page */
		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
			continue;

		/* Successfully isolated */
		del_page_from_lru_list(zone, page, page_lru(page));
		list_add(&page->lru, migratelist);
		cc->nr_migratepages++;
290
		nr_isolated++;
291 292 293 294 295 296 297 298 299 300 301

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

	acct_isolated(zone, cc);

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

302 303
	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);

304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355
	return cc->nr_migratepages;
}

/*
 * 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,
						struct compact_control *cc)
{
356 357 358
	unsigned int order;
	unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order);

359 360 361 362 363 364 365
	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;

366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383
	/* Compaction run is not finished if the watermark is not met */
	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
		return COMPACT_CONTINUE;

	if (cc->order == -1)
		return COMPACT_CONTINUE;

	/* 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;
	}

384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
	return COMPACT_CONTINUE;
}

static int compact_zone(struct zone *zone, struct compact_control *cc)
{
	int ret;

	/* 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;

		if (!isolate_migratepages(zone, cc))
			continue;

		nr_migrate = cc->nr_migratepages;
		migrate_pages(&cc->migratepages, compaction_alloc,
						(unsigned long)cc, 0);
		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);
414 415
		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
						nr_remaining);
416 417 418 419 420 421 422 423 424 425 426 427 428 429 430

		/* Release LRU pages not migrated */
		if (!list_empty(&cc->migratepages)) {
			putback_lru_pages(&cc->migratepages);
			cc->nr_migratepages = 0;
		}

	}

	/* Release free pages and check accounting */
	cc->nr_freepages -= release_freepages(&cc->freepages);
	VM_BUG_ON(cc->nr_freepages != 0);

	return ret;
}
431

432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447
static unsigned long compact_zone_order(struct zone *zone,
						int order, gfp_t gfp_mask)
{
	struct compact_control cc = {
		.nr_freepages = 0,
		.nr_migratepages = 0,
		.order = order,
		.migratetype = allocflags_to_migratetype(gfp_mask),
		.zone = zone,
	};
	INIT_LIST_HEAD(&cc.freepages);
	INIT_LIST_HEAD(&cc.migratepages);

	return compact_zone(zone, &cc);
}

448 449
int sysctl_extfrag_threshold = 500;

450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507
/**
 * 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
 *
 * This is the main entry point for direct page compaction.
 */
unsigned long try_to_compact_pages(struct zonelist *zonelist,
			int order, gfp_t gfp_mask, nodemask_t *nodemask)
{
	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;
	unsigned long watermark;
	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
	 */
	if (order <= PAGE_ALLOC_COSTLY_ORDER || !may_enter_fs || !may_perform_io)
		return rc;

	count_vm_event(COMPACTSTALL);

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

		/*
		 * 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))
			continue;

		/*
		 * fragmentation index determines if allocation failures are
		 * due to low memory or external fragmentation
		 *
		 * index of -1 implies allocations might succeed depending
		 * 	on watermarks
		 * 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);
508
		if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526
			continue;

		if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) {
			rc = COMPACT_PARTIAL;
			break;
		}

		status = compact_zone_order(zone, order, gfp_mask);
		rc = max(status, rc);

		if (zone_watermark_ok(zone, order, watermark, 0, 0))
			break;
	}

	return rc;
}


527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544
/* Compact all zones within a node */
static int compact_node(int nid)
{
	int zoneid;
	pg_data_t *pgdat;
	struct zone *zone;

	if (nid < 0 || nid >= nr_node_ids || !node_online(nid))
		return -EINVAL;
	pgdat = NODE_DATA(nid);

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

	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
		struct compact_control cc = {
			.nr_freepages = 0,
			.nr_migratepages = 0,
545
			.order = -1,
546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587
		};

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

		cc.zone = zone;
		INIT_LIST_HEAD(&cc.freepages);
		INIT_LIST_HEAD(&cc.migratepages);

		compact_zone(zone, &cc);

		VM_BUG_ON(!list_empty(&cc.freepages));
		VM_BUG_ON(!list_empty(&cc.migratepages));
	}

	return 0;
}

/* Compact all nodes in the system */
static int compact_nodes(void)
{
	int nid;

	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;
}
588

589 590 591 592 593 594 595 596
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;
}

597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
ssize_t sysfs_compact_node(struct sys_device *dev,
			struct sysdev_attribute *attr,
			const char *buf, size_t count)
{
	compact_node(dev->id);

	return count;
}
static SYSDEV_ATTR(compact, S_IWUSR, NULL, sysfs_compact_node);

int compaction_register_node(struct node *node)
{
	return sysdev_create_file(&node->sysdev, &attr_compact);
}

void compaction_unregister_node(struct node *node)
{
	return sysdev_remove_file(&node->sysdev, &attr_compact);
}
#endif /* CONFIG_SYSFS && CONFIG_NUMA */