Blame view

mm/compaction.c 20 KB
748446bb6   Mel Gorman   mm: compaction: m...
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>
76ab0f530   Mel Gorman   mm: compaction: a...
15
  #include <linux/sysctl.h>
ed4a6d7f0   Mel Gorman   mm: compaction: a...
16
  #include <linux/sysfs.h>
748446bb6   Mel Gorman   mm: compaction: m...
17
  #include "internal.h"
b7aba6984   Mel Gorman   mm: compaction: a...
18
19
  #define CREATE_TRACE_POINTS
  #include <trace/events/compaction.h>
748446bb6   Mel Gorman   mm: compaction: m...
20
21
22
23
24
25
26
27
28
29
30
31
32
33
  /*
   * 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 */
77f1fe6b0   Mel Gorman   mm: migration: al...
34
  	bool sync;			/* Synchronous migration */
748446bb6   Mel Gorman   mm: compaction: m...
35
36
37
38
  
  	/* Account for isolated anon and file pages */
  	unsigned long nr_anon;
  	unsigned long nr_file;
56de7263f   Mel Gorman   mm: compaction: d...
39
40
  	unsigned int order;		/* order a direct compactor needs */
  	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
748446bb6   Mel Gorman   mm: compaction: m...
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
  	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;
b7aba6984   Mel Gorman   mm: compaction: a...
64
  	int nr_scanned = 0, total_isolated = 0;
748446bb6   Mel Gorman   mm: compaction: m...
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
  	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;
b7aba6984   Mel Gorman   mm: compaction: a...
85
  		nr_scanned++;
748446bb6   Mel Gorman   mm: compaction: m...
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;
  		}
  	}
b7aba6984   Mel Gorman   mm: compaction: a...
104
  	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
748446bb6   Mel Gorman   mm: compaction: m...
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
  	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;
7454f4ba4   Mel Gorman   mm: compaction: e...
142
143
144
145
146
  	/*
  	 * 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.
  	 */
748446bb6   Mel Gorman   mm: compaction: m...
147
148
  	pfn = cc->free_pfn;
  	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
7454f4ba4   Mel Gorman   mm: compaction: e...
149
150
151
152
153
154
155
  
  	/*
  	 * 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);
748446bb6   Mel Gorman   mm: compaction: m...
156
157
158
159
160
161
  
  	/*
  	 * 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.
  	 */
748446bb6   Mel Gorman   mm: compaction: m...
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
  	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;
602605a42   Mel Gorman   mm: compaction: m...
183
184
185
186
187
188
189
190
191
192
193
194
195
  		/*
  		 * 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);
748446bb6   Mel Gorman   mm: compaction: m...
196
197
198
199
200
201
202
203
204
  
  		/*
  		 * 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);
  	}
748446bb6   Mel Gorman   mm: compaction: m...
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
  
  	/* 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)
  {
bc6930457   Minchan Kim   mm: compaction: h...
236
  	unsigned long active, inactive, isolated;
748446bb6   Mel Gorman   mm: compaction: m...
237
238
239
  
  	inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
  					zone_page_state(zone, NR_INACTIVE_ANON);
bc6930457   Minchan Kim   mm: compaction: h...
240
241
  	active = zone_page_state(zone, NR_ACTIVE_FILE) +
  					zone_page_state(zone, NR_ACTIVE_ANON);
748446bb6   Mel Gorman   mm: compaction: m...
242
243
  	isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
  					zone_page_state(zone, NR_ISOLATED_ANON);
bc6930457   Minchan Kim   mm: compaction: h...
244
  	return isolated > (inactive + active) / 2;
748446bb6   Mel Gorman   mm: compaction: m...
245
  }
f9e35b3b4   Mel Gorman   mm: compaction: a...
246
247
248
249
250
251
  /* 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;
748446bb6   Mel Gorman   mm: compaction: m...
252
253
254
255
  /*
   * Isolate all pages that can be migrated from the block pointed to by
   * the migrate scanner within compact_control.
   */
f9e35b3b4   Mel Gorman   mm: compaction: a...
256
  static isolate_migrate_t isolate_migratepages(struct zone *zone,
748446bb6   Mel Gorman   mm: compaction: m...
257
258
259
  					struct compact_control *cc)
  {
  	unsigned long low_pfn, end_pfn;
9927af740   Mel Gorman   mm: compaction: p...
260
  	unsigned long last_pageblock_nr = 0, pageblock_nr;
b7aba6984   Mel Gorman   mm: compaction: a...
261
  	unsigned long nr_scanned = 0, nr_isolated = 0;
748446bb6   Mel Gorman   mm: compaction: m...
262
263
264
265
266
267
268
269
270
271
272
  	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;
f9e35b3b4   Mel Gorman   mm: compaction: a...
273
  		return ISOLATE_NONE;
748446bb6   Mel Gorman   mm: compaction: m...
274
275
276
277
278
279
280
281
  	}
  
  	/*
  	 * 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))) {
f9e35b3b4   Mel Gorman   mm: compaction: a...
282
283
284
  		/* async migration should just abort */
  		if (!cc->sync)
  			return ISOLATE_ABORT;
748446bb6   Mel Gorman   mm: compaction: m...
285
286
287
  		congestion_wait(BLK_RW_ASYNC, HZ/10);
  
  		if (fatal_signal_pending(current))
f9e35b3b4   Mel Gorman   mm: compaction: a...
288
  			return ISOLATE_ABORT;
748446bb6   Mel Gorman   mm: compaction: m...
289
290
291
  	}
  
  	/* Time to isolate some pages for migration */
b2eef8c0d   Andrea Arcangeli   mm: compaction: m...
292
  	cond_resched();
748446bb6   Mel Gorman   mm: compaction: m...
293
294
295
  	spin_lock_irq(&zone->lru_lock);
  	for (; low_pfn < end_pfn; low_pfn++) {
  		struct page *page;
b2eef8c0d   Andrea Arcangeli   mm: compaction: m...
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
  		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);
748446bb6   Mel Gorman   mm: compaction: m...
312
313
  		if (!pfn_valid_within(low_pfn))
  			continue;
b7aba6984   Mel Gorman   mm: compaction: a...
314
  		nr_scanned++;
748446bb6   Mel Gorman   mm: compaction: m...
315
316
317
318
319
  
  		/* Get the page and skip if free */
  		page = pfn_to_page(low_pfn);
  		if (PageBuddy(page))
  			continue;
9927af740   Mel Gorman   mm: compaction: p...
320
321
322
323
324
325
326
327
328
329
330
331
332
  		/*
  		 * 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;
  		}
bc835011a   Andrea Arcangeli   thp: transhuge is...
333
334
335
336
337
338
339
340
341
342
343
344
  		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;
  		}
748446bb6   Mel Gorman   mm: compaction: m...
345
346
347
  		/* Try isolate the page */
  		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
  			continue;
bc835011a   Andrea Arcangeli   thp: transhuge is...
348
  		VM_BUG_ON(PageTransCompound(page));
748446bb6   Mel Gorman   mm: compaction: m...
349
350
351
  		/* Successfully isolated */
  		del_page_from_lru_list(zone, page, page_lru(page));
  		list_add(&page->lru, migratelist);
748446bb6   Mel Gorman   mm: compaction: m...
352
  		cc->nr_migratepages++;
b7aba6984   Mel Gorman   mm: compaction: a...
353
  		nr_isolated++;
748446bb6   Mel Gorman   mm: compaction: m...
354
355
356
357
358
359
360
361
362
363
  
  		/* 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;
b7aba6984   Mel Gorman   mm: compaction: a...
364
  	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
f9e35b3b4   Mel Gorman   mm: compaction: a...
365
  	return ISOLATE_SUCCESS;
748446bb6   Mel Gorman   mm: compaction: m...
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
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
414
  }
  
  /*
   * 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,
5a03b051e   Andrea Arcangeli   thp: use compacti...
415
  			    struct compact_control *cc)
748446bb6   Mel Gorman   mm: compaction: m...
416
  {
56de7263f   Mel Gorman   mm: compaction: d...
417
  	unsigned int order;
5a03b051e   Andrea Arcangeli   thp: use compacti...
418
  	unsigned long watermark;
56de7263f   Mel Gorman   mm: compaction: d...
419

748446bb6   Mel Gorman   mm: compaction: m...
420
421
422
423
424
425
  	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;
82478fb7b   Johannes Weiner   mm: compaction: p...
426
427
428
429
  	/*
  	 * order == -1 is expected when compacting via
  	 * /proc/sys/vm/compact_memory
  	 */
56de7263f   Mel Gorman   mm: compaction: d...
430
431
  	if (cc->order == -1)
  		return COMPACT_CONTINUE;
3957c7768   Michal Hocko   mm: compaction: f...
432
433
434
435
436
437
  	/* 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;
56de7263f   Mel Gorman   mm: compaction: d...
438
439
440
441
442
443
444
445
446
447
  	/* 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;
  	}
748446bb6   Mel Gorman   mm: compaction: m...
448
449
  	return COMPACT_CONTINUE;
  }
3e7d34497   Mel Gorman   mm: vmscan: recla...
450
451
452
453
454
455
456
457
458
459
460
461
462
  /*
   * 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;
  
  	/*
3957c7768   Michal Hocko   mm: compaction: f...
463
464
465
466
467
468
469
  	 * order == -1 is expected when compacting via
  	 * /proc/sys/vm/compact_memory
  	 */
  	if (order == -1)
  		return COMPACT_CONTINUE;
  
  	/*
3e7d34497   Mel Gorman   mm: vmscan: recla...
470
471
472
473
474
475
476
477
478
479
480
481
  	 * 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
  	 *
a582a738c   Shaohua Li   compaction: check...
482
483
  	 * index of -1000 implies allocations might succeed depending on
  	 * watermarks
3e7d34497   Mel Gorman   mm: vmscan: recla...
484
485
486
487
488
489
490
491
  	 * 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;
a582a738c   Shaohua Li   compaction: check...
492
493
  	if (fragindex == -1000 && zone_watermark_ok(zone, order, watermark,
  	    0, 0))
3e7d34497   Mel Gorman   mm: vmscan: recla...
494
495
496
497
  		return COMPACT_PARTIAL;
  
  	return COMPACT_CONTINUE;
  }
748446bb6   Mel Gorman   mm: compaction: m...
498
499
500
  static int compact_zone(struct zone *zone, struct compact_control *cc)
  {
  	int ret;
3e7d34497   Mel Gorman   mm: vmscan: recla...
501
502
503
504
505
506
507
508
509
510
  	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 */
  		;
  	}
748446bb6   Mel Gorman   mm: compaction: m...
511
512
513
514
515
516
517
518
519
  	/* 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;
9d502c1c8   Minchan Kim   mm/compaction: ch...
520
  		int err;
748446bb6   Mel Gorman   mm: compaction: m...
521

f9e35b3b4   Mel Gorman   mm: compaction: a...
522
523
524
525
526
  		switch (isolate_migratepages(zone, cc)) {
  		case ISOLATE_ABORT:
  			ret = COMPACT_PARTIAL;
  			goto out;
  		case ISOLATE_NONE:
748446bb6   Mel Gorman   mm: compaction: m...
527
  			continue;
f9e35b3b4   Mel Gorman   mm: compaction: a...
528
529
530
  		case ISOLATE_SUCCESS:
  			;
  		}
748446bb6   Mel Gorman   mm: compaction: m...
531
532
  
  		nr_migrate = cc->nr_migratepages;
9d502c1c8   Minchan Kim   mm/compaction: ch...
533
  		err = migrate_pages(&cc->migratepages, compaction_alloc,
7f0f24967   Mel Gorman   mm: migration: cl...
534
  				(unsigned long)cc, false,
77f1fe6b0   Mel Gorman   mm: migration: al...
535
  				cc->sync);
748446bb6   Mel Gorman   mm: compaction: m...
536
537
538
539
540
541
542
  		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);
b7aba6984   Mel Gorman   mm: compaction: a...
543
544
  		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
  						nr_remaining);
748446bb6   Mel Gorman   mm: compaction: m...
545
546
  
  		/* Release LRU pages not migrated */
9d502c1c8   Minchan Kim   mm/compaction: ch...
547
  		if (err) {
748446bb6   Mel Gorman   mm: compaction: m...
548
549
550
551
552
  			putback_lru_pages(&cc->migratepages);
  			cc->nr_migratepages = 0;
  		}
  
  	}
f9e35b3b4   Mel Gorman   mm: compaction: a...
553
  out:
748446bb6   Mel Gorman   mm: compaction: m...
554
555
556
557
558
559
  	/* Release free pages and check accounting */
  	cc->nr_freepages -= release_freepages(&cc->freepages);
  	VM_BUG_ON(cc->nr_freepages != 0);
  
  	return ret;
  }
76ab0f530   Mel Gorman   mm: compaction: a...
560

3e7d34497   Mel Gorman   mm: vmscan: recla...
561
  unsigned long compact_zone_order(struct zone *zone,
5a03b051e   Andrea Arcangeli   thp: use compacti...
562
  				 int order, gfp_t gfp_mask,
d527caf22   Andrea Arcangeli   mm: compaction: p...
563
  				 bool sync)
56de7263f   Mel Gorman   mm: compaction: d...
564
565
566
567
568
569
570
  {
  	struct compact_control cc = {
  		.nr_freepages = 0,
  		.nr_migratepages = 0,
  		.order = order,
  		.migratetype = allocflags_to_migratetype(gfp_mask),
  		.zone = zone,
77f1fe6b0   Mel Gorman   mm: migration: al...
571
  		.sync = sync,
56de7263f   Mel Gorman   mm: compaction: d...
572
573
574
575
576
577
  	};
  	INIT_LIST_HEAD(&cc.freepages);
  	INIT_LIST_HEAD(&cc.migratepages);
  
  	return compact_zone(zone, &cc);
  }
5e7719058   Mel Gorman   mm: compaction: a...
578
  int sysctl_extfrag_threshold = 500;
56de7263f   Mel Gorman   mm: compaction: d...
579
580
581
582
583
584
  /**
   * 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
77f1fe6b0   Mel Gorman   mm: migration: al...
585
   * @sync: Whether migration is synchronous or not
56de7263f   Mel Gorman   mm: compaction: d...
586
587
588
589
   *
   * This is the main entry point for direct page compaction.
   */
  unsigned long try_to_compact_pages(struct zonelist *zonelist,
77f1fe6b0   Mel Gorman   mm: migration: al...
590
591
  			int order, gfp_t gfp_mask, nodemask_t *nodemask,
  			bool sync)
56de7263f   Mel Gorman   mm: compaction: d...
592
593
594
595
  {
  	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;
56de7263f   Mel Gorman   mm: compaction: d...
596
597
598
599
600
601
602
603
604
  	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
  	 */
c5a73c3d5   Andrea Arcangeli   thp: use compacti...
605
  	if (!order || !may_enter_fs || !may_perform_io)
56de7263f   Mel Gorman   mm: compaction: d...
606
607
608
609
610
611
612
  		return rc;
  
  	count_vm_event(COMPACTSTALL);
  
  	/* Compact each zone in the list */
  	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
  								nodemask) {
56de7263f   Mel Gorman   mm: compaction: d...
613
  		int status;
d527caf22   Andrea Arcangeli   mm: compaction: p...
614
  		status = compact_zone_order(zone, order, gfp_mask, sync);
56de7263f   Mel Gorman   mm: compaction: d...
615
  		rc = max(status, rc);
3e7d34497   Mel Gorman   mm: vmscan: recla...
616
617
  		/* If a normal allocation would succeed, stop compacting */
  		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
56de7263f   Mel Gorman   mm: compaction: d...
618
619
620
621
622
  			break;
  	}
  
  	return rc;
  }
76ab0f530   Mel Gorman   mm: compaction: a...
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
  /* 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,
56de7263f   Mel Gorman   mm: compaction: d...
641
  			.order = -1,
76ab0f530   Mel Gorman   mm: compaction: a...
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
  		};
  
  		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;
  }
ed4a6d7f0   Mel Gorman   mm: compaction: a...
684

5e7719058   Mel Gorman   mm: compaction: a...
685
686
687
688
689
690
691
  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;
  }
ed4a6d7f0   Mel Gorman   mm: compaction: a...
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
  #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 */