summaryrefslogtreecommitdiff
path: root/mm/page_isolation.c
blob: 9d73dc38e3d75cdc6ec5a1efc3cbc178dbc89464 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
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
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
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
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
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
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
356
357
358
359
360
361
362
363
364
365
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
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
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
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
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
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
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
// SPDX-License-Identifier: GPL-2.0
/*
 * linux/mm/page_isolation.c
 */

#include <linux/mm.h>
#include <linux/page-isolation.h>
#include <linux/pageblock-flags.h>
#include <linux/memory.h>
#include <linux/hugetlb.h>
#include <linux/page_owner.h>
#include <linux/migrate.h>
#include "internal.h"

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

/*
 * This function checks whether the range [start_pfn, end_pfn) includes
 * unmovable pages or not. The range must fall into a single pageblock and
 * consequently belong to a single zone.
 *
 * PageLRU check without isolation or lru_lock could race so that
 * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
 * check without lock_page also may miss some movable non-lru pages at
 * race condition. So you can't expect this function should be exact.
 *
 * Returns a page without holding a reference. If the caller wants to
 * dereference that page (e.g., dumping), it has to make sure that it
 * cannot get removed (e.g., via memory unplug) concurrently.
 *
 */
static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long end_pfn,
				int migratetype, int flags)
{
	struct page *page = pfn_to_page(start_pfn);
	struct zone *zone = page_zone(page);
	unsigned long pfn;

	VM_BUG_ON(ALIGN_DOWN(start_pfn, pageblock_nr_pages) !=
		  ALIGN_DOWN(end_pfn - 1, pageblock_nr_pages));

	if (is_migrate_cma_page(page)) {
		/*
		 * CMA allocations (alloc_contig_range) really need to mark
		 * isolate CMA pageblocks even when they are not movable in fact
		 * so consider them movable here.
		 */
		if (is_migrate_cma(migratetype))
			return NULL;

		return page;
	}

	for (pfn = start_pfn; pfn < end_pfn; pfn++) {
		page = pfn_to_page(pfn);

		/*
		 * Both, bootmem allocations and memory holes are marked
		 * PG_reserved and are unmovable. We can even have unmovable
		 * allocations inside ZONE_MOVABLE, for example when
		 * specifying "movablecore".
		 */
		if (PageReserved(page))
			return page;

		/*
		 * If the zone is movable and we have ruled out all reserved
		 * pages then it should be reasonably safe to assume the rest
		 * is movable.
		 */
		if (zone_idx(zone) == ZONE_MOVABLE)
			continue;

		/*
		 * Hugepages are not in LRU lists, but they're movable.
		 * THPs are on the LRU, but need to be counted as #small pages.
		 * We need not scan over tail pages because we don't
		 * handle each tail page individually in migration.
		 */
		if (PageHuge(page) || PageTransCompound(page)) {
			struct page *head = compound_head(page);
			unsigned int skip_pages;

			if (PageHuge(page)) {
				if (!hugepage_migration_supported(page_hstate(head)))
					return page;
			} else if (!PageLRU(head) && !__PageMovable(head)) {
				return page;
			}

			skip_pages = compound_nr(head) - (page - head);
			pfn += skip_pages - 1;
			continue;
		}

		/*
		 * We can't use page_count without pin a page
		 * because another CPU can free compound page.
		 * This check already skips compound tails of THP
		 * because their page->_refcount is zero at all time.
		 */
		if (!page_ref_count(page)) {
			if (PageBuddy(page))
				pfn += (1 << buddy_order(page)) - 1;
			continue;
		}

		/*
		 * The HWPoisoned page may be not in buddy system, and
		 * page_count() is not 0.
		 */
		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
			continue;

		/*
		 * We treat all PageOffline() pages as movable when offlining
		 * to give drivers a chance to decrement their reference count
		 * in MEM_GOING_OFFLINE in order to indicate that these pages
		 * can be offlined as there are no direct references anymore.
		 * For actually unmovable PageOffline() where the driver does
		 * not support this, we will fail later when trying to actually
		 * move these pages that still have a reference count > 0.
		 * (false negatives in this function only)
		 */
		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
			continue;

		if (__PageMovable(page) || PageLRU(page))
			continue;

		/*
		 * If there are RECLAIMABLE pages, we need to check
		 * it.  But now, memory offline itself doesn't call
		 * shrink_node_slabs() and it still to be fixed.
		 */
		return page;
	}
	return NULL;
}

/*
 * This function set pageblock migratetype to isolate if no unmovable page is
 * present in [start_pfn, end_pfn). The pageblock must intersect with
 * [start_pfn, end_pfn).
 */
static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags,
			unsigned long start_pfn, unsigned long end_pfn)
{
	struct zone *zone = page_zone(page);
	struct page *unmovable;
	unsigned long flags;
	unsigned long check_unmovable_start, check_unmovable_end;

	spin_lock_irqsave(&zone->lock, flags);

	/*
	 * We assume the caller intended to SET migrate type to isolate.
	 * If it is already set, then someone else must have raced and
	 * set it before us.
	 */
	if (is_migrate_isolate_page(page)) {
		spin_unlock_irqrestore(&zone->lock, flags);
		return -EBUSY;
	}

	/*
	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
	 * We just check MOVABLE pages.
	 *
	 * Pass the intersection of [start_pfn, end_pfn) and the page's pageblock
	 * to avoid redundant checks.
	 */
	check_unmovable_start = max(page_to_pfn(page), start_pfn);
	check_unmovable_end = min(ALIGN(page_to_pfn(page) + 1, pageblock_nr_pages),
				  end_pfn);

	unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
			migratetype, isol_flags);
	if (!unmovable) {
		unsigned long nr_pages;
		int mt = get_pageblock_migratetype(page);

		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
		zone->nr_isolate_pageblock++;
		nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE,
									NULL);

		__mod_zone_freepage_state(zone, -nr_pages, mt);
		spin_unlock_irqrestore(&zone->lock, flags);
		return 0;
	}

	spin_unlock_irqrestore(&zone->lock, flags);
	if (isol_flags & REPORT_FAILURE) {
		/*
		 * printk() with zone->lock held will likely trigger a
		 * lockdep splat, so defer it here.
		 */
		dump_page(unmovable, "unmovable page");
	}

	return -EBUSY;
}

static void unset_migratetype_isolate(struct page *page, int migratetype)
{
	struct zone *zone;
	unsigned long flags, nr_pages;
	bool isolated_page = false;
	unsigned int order;
	struct page *buddy;

	zone = page_zone(page);
	spin_lock_irqsave(&zone->lock, flags);
	if (!is_migrate_isolate_page(page))
		goto out;

	/*
	 * Because freepage with more than pageblock_order on isolated
	 * pageblock is restricted to merge due to freepage counting problem,
	 * it is possible that there is free buddy page.
	 * move_freepages_block() doesn't care of merge so we need other
	 * approach in order to merge them. Isolation and free will make
	 * these pages to be merged.
	 */
	if (PageBuddy(page)) {
		order = buddy_order(page);
		if (order >= pageblock_order && order < MAX_ORDER - 1) {
			buddy = find_buddy_page_pfn(page, page_to_pfn(page),
						    order, NULL);
			if (buddy && !is_migrate_isolate_page(buddy)) {
				isolated_page = !!__isolate_free_page(page, order);
				/*
				 * Isolating a free page in an isolated pageblock
				 * is expected to always work as watermarks don't
				 * apply here.
				 */
				VM_WARN_ON(!isolated_page);
			}
		}
	}

	/*
	 * If we isolate freepage with more than pageblock_order, there
	 * should be no freepage in the range, so we could avoid costly
	 * pageblock scanning for freepage moving.
	 *
	 * We didn't actually touch any of the isolated pages, so place them
	 * to the tail of the freelist. This is an optimization for memory
	 * onlining - just onlined memory won't immediately be considered for
	 * allocation.
	 */
	if (!isolated_page) {
		nr_pages = move_freepages_block(zone, page, migratetype, NULL);
		__mod_zone_freepage_state(zone, nr_pages, migratetype);
	}
	set_pageblock_migratetype(page, migratetype);
	if (isolated_page)
		__putback_isolated_page(page, order, migratetype);
	zone->nr_isolate_pageblock--;
out:
	spin_unlock_irqrestore(&zone->lock, flags);
}

static inline struct page *
__first_valid_page(unsigned long pfn, unsigned long nr_pages)
{
	int i;

	for (i = 0; i < nr_pages; i++) {
		struct page *page;

		page = pfn_to_online_page(pfn + i);
		if (!page)
			continue;
		return page;
	}
	return NULL;
}

/**
 * isolate_single_pageblock() -- tries to isolate a pageblock that might be
 * within a free or in-use page.
 * @boundary_pfn:		pageblock-aligned pfn that a page might cross
 * @flags:			isolation flags
 * @gfp_flags:			GFP flags used for migrating pages
 * @isolate_before:	isolate the pageblock before the boundary_pfn
 * @skip_isolation:	the flag to skip the pageblock isolation in second
 *			isolate_single_pageblock()
 *
 * Free and in-use pages can be as big as MAX_ORDER-1 and contain more than one
 * pageblock. When not all pageblocks within a page are isolated at the same
 * time, free page accounting can go wrong. For example, in the case of
 * MAX_ORDER-1 = pageblock_order + 1, a MAX_ORDER-1 page has two pagelbocks.
 * [         MAX_ORDER-1         ]
 * [  pageblock0  |  pageblock1  ]
 * When either pageblock is isolated, if it is a free page, the page is not
 * split into separate migratetype lists, which is supposed to; if it is an
 * in-use page and freed later, __free_one_page() does not split the free page
 * either. The function handles this by splitting the free page or migrating
 * the in-use page then splitting the free page.
 */
static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
			gfp_t gfp_flags, bool isolate_before, bool skip_isolation)
{
	unsigned char saved_mt;
	unsigned long start_pfn;
	unsigned long isolate_pageblock;
	unsigned long pfn;
	struct zone *zone;
	int ret;

	VM_BUG_ON(!IS_ALIGNED(boundary_pfn, pageblock_nr_pages));

	if (isolate_before)
		isolate_pageblock = boundary_pfn - pageblock_nr_pages;
	else
		isolate_pageblock = boundary_pfn;

	/*
	 * scan at the beginning of MAX_ORDER_NR_PAGES aligned range to avoid
	 * only isolating a subset of pageblocks from a bigger than pageblock
	 * free or in-use page. Also make sure all to-be-isolated pageblocks
	 * are within the same zone.
	 */
	zone  = page_zone(pfn_to_page(isolate_pageblock));
	start_pfn  = max(ALIGN_DOWN(isolate_pageblock, MAX_ORDER_NR_PAGES),
				      zone->zone_start_pfn);

	saved_mt = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));

	if (skip_isolation)
		VM_BUG_ON(!is_migrate_isolate(saved_mt));
	else {
		ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt, flags,
				isolate_pageblock, isolate_pageblock + pageblock_nr_pages);

		if (ret)
			return ret;
	}

	/*
	 * Bail out early when the to-be-isolated pageblock does not form
	 * a free or in-use page across boundary_pfn:
	 *
	 * 1. isolate before boundary_pfn: the page after is not online
	 * 2. isolate after boundary_pfn: the page before is not online
	 *
	 * This also ensures correctness. Without it, when isolate after
	 * boundary_pfn and [start_pfn, boundary_pfn) are not online,
	 * __first_valid_page() will return unexpected NULL in the for loop
	 * below.
	 */
	if (isolate_before) {
		if (!pfn_to_online_page(boundary_pfn))
			return 0;
	} else {
		if (!pfn_to_online_page(boundary_pfn - 1))
			return 0;
	}

	for (pfn = start_pfn; pfn < boundary_pfn;) {
		struct page *page = __first_valid_page(pfn, boundary_pfn - pfn);

		VM_BUG_ON(!page);
		pfn = page_to_pfn(page);
		/*
		 * start_pfn is MAX_ORDER_NR_PAGES aligned, if there is any
		 * free pages in [start_pfn, boundary_pfn), its head page will
		 * always be in the range.
		 */
		if (PageBuddy(page)) {
			int order = buddy_order(page);

			if (pfn + (1UL << order) > boundary_pfn) {
				/* free page changed before split, check it again */
				if (split_free_page(page, order, boundary_pfn - pfn))
					continue;
			}

			pfn += 1UL << order;
			continue;
		}
		/*
		 * migrate compound pages then let the free page handling code
		 * above do the rest. If migration is not possible, just fail.
		 */
		if (PageCompound(page)) {
			struct page *head = compound_head(page);
			unsigned long head_pfn = page_to_pfn(head);
			unsigned long nr_pages = compound_nr(head);

			if (head_pfn + nr_pages <= boundary_pfn) {
				pfn = head_pfn + nr_pages;
				continue;
			}
#if defined CONFIG_COMPACTION || defined CONFIG_CMA
			/*
			 * hugetlb, lru compound (THP), and movable compound pages
			 * can be migrated. Otherwise, fail the isolation.
			 */
			if (PageHuge(page) || PageLRU(page) || __PageMovable(page)) {
				int order;
				unsigned long outer_pfn;
				int page_mt = get_pageblock_migratetype(page);
				bool isolate_page = !is_migrate_isolate_page(page);
				struct compact_control cc = {
					.nr_migratepages = 0,
					.order = -1,
					.zone = page_zone(pfn_to_page(head_pfn)),
					.mode = MIGRATE_SYNC,
					.ignore_skip_hint = true,
					.no_set_skip_hint = true,
					.gfp_mask = gfp_flags,
					.alloc_contig = true,
				};
				INIT_LIST_HEAD(&cc.migratepages);

				/*
				 * XXX: mark the page as MIGRATE_ISOLATE so that
				 * no one else can grab the freed page after migration.
				 * Ideally, the page should be freed as two separate
				 * pages to be added into separate migratetype free
				 * lists.
				 */
				if (isolate_page) {
					ret = set_migratetype_isolate(page, page_mt,
						flags, head_pfn, head_pfn + nr_pages);
					if (ret)
						goto failed;
				}

				ret = __alloc_contig_migrate_range(&cc, head_pfn,
							head_pfn + nr_pages);

				/*
				 * restore the page's migratetype so that it can
				 * be split into separate migratetype free lists
				 * later.
				 */
				if (isolate_page)
					unset_migratetype_isolate(page, page_mt);

				if (ret)
					goto failed;
				/*
				 * reset pfn to the head of the free page, so
				 * that the free page handling code above can split
				 * the free page to the right migratetype list.
				 *
				 * head_pfn is not used here as a hugetlb page order
				 * can be bigger than MAX_ORDER-1, but after it is
				 * freed, the free page order is not. Use pfn within
				 * the range to find the head of the free page.
				 */
				order = 0;
				outer_pfn = pfn;
				while (!PageBuddy(pfn_to_page(outer_pfn))) {
					/* stop if we cannot find the free page */
					if (++order >= MAX_ORDER)
						goto failed;
					outer_pfn &= ~0UL << order;
				}
				pfn = outer_pfn;
				continue;
			} else
#endif
				goto failed;
		}

		pfn++;
	}
	return 0;
failed:
	/* restore the original migratetype */
	if (!skip_isolation)
		unset_migratetype_isolate(pfn_to_page(isolate_pageblock), saved_mt);
	return -EBUSY;
}

/**
 * start_isolate_page_range() - make page-allocation-type of range of pages to
 * be MIGRATE_ISOLATE.
 * @start_pfn:		The lower PFN of the range to be isolated.
 * @end_pfn:		The upper PFN of the range to be isolated.
 * @migratetype:	Migrate type to set in error recovery.
 * @flags:		The following flags are allowed (they can be combined in
 *			a bit mask)
 *			MEMORY_OFFLINE - isolate to offline (!allocate) memory
 *					 e.g., skip over PageHWPoison() pages
 *					 and PageOffline() pages.
 *			REPORT_FAILURE - report details about the failure to
 *			isolate the range
 * @gfp_flags:		GFP flags used for migrating pages that sit across the
 *			range boundaries.
 *
 * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
 * the range will never be allocated. Any free pages and pages freed in the
 * future will not be allocated again. If specified range includes migrate types
 * other than MOVABLE or CMA, this will fail with -EBUSY. For isolating all
 * pages in the range finally, the caller have to free all pages in the range.
 * test_page_isolated() can be used for test it.
 *
 * The function first tries to isolate the pageblocks at the beginning and end
 * of the range, since there might be pages across the range boundaries.
 * Afterwards, it isolates the rest of the range.
 *
 * There is no high level synchronization mechanism that prevents two threads
 * from trying to isolate overlapping ranges. If this happens, one thread
 * will notice pageblocks in the overlapping range already set to isolate.
 * This happens in set_migratetype_isolate, and set_migratetype_isolate
 * returns an error. We then clean up by restoring the migration type on
 * pageblocks we may have modified and return -EBUSY to caller. This
 * prevents two threads from simultaneously working on overlapping ranges.
 *
 * Please note that there is no strong synchronization with the page allocator
 * either. Pages might be freed while their page blocks are marked ISOLATED.
 * A call to drain_all_pages() after isolation can flush most of them. However
 * in some cases pages might still end up on pcp lists and that would allow
 * for their allocation even when they are in fact isolated already. Depending
 * on how strong of a guarantee the caller needs, zone_pcp_disable/enable()
 * might be used to flush and disable pcplist before isolation and enable after
 * unisolation.
 *
 * Return: 0 on success and -EBUSY if any part of range cannot be isolated.
 */
int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
			     int migratetype, int flags, gfp_t gfp_flags)
{
	unsigned long pfn;
	struct page *page;
	/* isolation is done at page block granularity */
	unsigned long isolate_start = ALIGN_DOWN(start_pfn, pageblock_nr_pages);
	unsigned long isolate_end = ALIGN(end_pfn, pageblock_nr_pages);
	int ret;
	bool skip_isolation = false;

	/* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */
	ret = isolate_single_pageblock(isolate_start, flags, gfp_flags, false, skip_isolation);
	if (ret)
		return ret;

	if (isolate_start == isolate_end - pageblock_nr_pages)
		skip_isolation = true;

	/* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */
	ret = isolate_single_pageblock(isolate_end, flags, gfp_flags, true, skip_isolation);
	if (ret) {
		unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype);
		return ret;
	}

	/* skip isolated pageblocks at the beginning and end */
	for (pfn = isolate_start + pageblock_nr_pages;
	     pfn < isolate_end - pageblock_nr_pages;
	     pfn += pageblock_nr_pages) {
		page = __first_valid_page(pfn, pageblock_nr_pages);
		if (page && set_migratetype_isolate(page, migratetype, flags,
					start_pfn, end_pfn)) {
			undo_isolate_page_range(isolate_start, pfn, migratetype);
			unset_migratetype_isolate(
				pfn_to_page(isolate_end - pageblock_nr_pages),
				migratetype);
			return -EBUSY;
		}
	}
	return 0;
}

/*
 * Make isolated pages available again.
 */
void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
			    int migratetype)
{
	unsigned long pfn;
	struct page *page;
	unsigned long isolate_start = ALIGN_DOWN(start_pfn, pageblock_nr_pages);
	unsigned long isolate_end = ALIGN(end_pfn, pageblock_nr_pages);


	for (pfn = isolate_start;
	     pfn < isolate_end;
	     pfn += pageblock_nr_pages) {
		page = __first_valid_page(pfn, pageblock_nr_pages);
		if (!page || !is_migrate_isolate_page(page))
			continue;
		unset_migratetype_isolate(page, migratetype);
	}
}
/*
 * Test all pages in the range is free(means isolated) or not.
 * all pages in [start_pfn...end_pfn) must be in the same zone.
 * zone->lock must be held before call this.
 *
 * Returns the last tested pfn.
 */
static unsigned long
__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
				  int flags)
{
	struct page *page;

	while (pfn < end_pfn) {
		page = pfn_to_page(pfn);
		if (PageBuddy(page))
			/*
			 * If the page is on a free list, it has to be on
			 * the correct MIGRATE_ISOLATE freelist. There is no
			 * simple way to verify that as VM_BUG_ON(), though.
			 */
			pfn += 1 << buddy_order(page);
		else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
			/* A HWPoisoned page cannot be also PageBuddy */
			pfn++;
		else if ((flags & MEMORY_OFFLINE) && PageOffline(page) &&
			 !page_count(page))
			/*
			 * The responsible driver agreed to skip PageOffline()
			 * pages when offlining memory by dropping its
			 * reference in MEM_GOING_OFFLINE.
			 */
			pfn++;
		else
			break;
	}

	return pfn;
}

/* Caller should ensure that requested range is in a single zone */
int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
			int isol_flags)
{
	unsigned long pfn, flags;
	struct page *page;
	struct zone *zone;
	int ret;

	/*
	 * Note: pageblock_nr_pages != MAX_ORDER. Then, chunks of free pages
	 * are not aligned to pageblock_nr_pages.
	 * Then we just check migratetype first.
	 */
	for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
		page = __first_valid_page(pfn, pageblock_nr_pages);
		if (page && !is_migrate_isolate_page(page))
			break;
	}
	page = __first_valid_page(start_pfn, end_pfn - start_pfn);
	if ((pfn < end_pfn) || !page) {
		ret = -EBUSY;
		goto out;
	}

	/* Check all pages are free or marked as ISOLATED */
	zone = page_zone(page);
	spin_lock_irqsave(&zone->lock, flags);
	pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, isol_flags);
	spin_unlock_irqrestore(&zone->lock, flags);

	ret = pfn < end_pfn ? -EBUSY : 0;

out:
	trace_test_pages_isolated(start_pfn, end_pfn, pfn);

	return ret;
}