summaryrefslogtreecommitdiff
path: root/mm/page_isolation.c
blob: bddf788f45bff8cb2f1768dc3930a24355566658 (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
// 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>

static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags)
{
	struct zone *zone = page_zone(page);
	struct page *unmovable;
	unsigned long flags;

	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.
	 */
	unmovable = has_unmovable_pages(zone, page, 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, unsigned migratetype)
{
	struct zone *zone;
	unsigned long flags, nr_pages;
	bool isolated_page = false;
	unsigned int order;
	unsigned long pfn, buddy_pfn;
	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) {
			pfn = page_to_pfn(page);
			buddy_pfn = __find_buddy_pfn(pfn, order);
			buddy = page + (buddy_pfn - pfn);

			if (pfn_valid_within(buddy_pfn) &&
			    !is_migrate_isolate_page(buddy)) {
				__isolate_free_page(page, order);
				isolated_page = true;
			}
		}
	}

	/*
	 * 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;
}

/**
 * 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.
 *			start_pfn/end_pfn must be aligned to pageblock_order.
 * @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
 *
 * 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.
 *
 * 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,
			     unsigned migratetype, int flags)
{
	unsigned long pfn;
	unsigned long undo_pfn;
	struct page *page;

	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));

	for (pfn = start_pfn;
	     pfn < end_pfn;
	     pfn += pageblock_nr_pages) {
		page = __first_valid_page(pfn, pageblock_nr_pages);
		if (page) {
			if (set_migratetype_isolate(page, migratetype, flags)) {
				undo_pfn = pfn;
				goto undo;
			}
		}
	}
	return 0;
undo:
	for (pfn = start_pfn;
	     pfn < undo_pfn;
	     pfn += pageblock_nr_pages) {
		struct page *page = pfn_to_online_page(pfn);
		if (!page)
			continue;
		unset_migratetype_isolate(page, migratetype);
	}

	return -EBUSY;
}

/*
 * Make isolated pages available again.
 */
void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
			    unsigned migratetype)
{
	unsigned long pfn;
	struct page *page;

	BUG_ON(!IS_ALIGNED(start_pfn, pageblock_nr_pages));
	BUG_ON(!IS_ALIGNED(end_pfn, pageblock_nr_pages));

	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))
			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) {
		if (!pfn_valid_within(pfn)) {
			pfn++;
			continue;
		}
		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;

	/*
	 * 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)
		return -EBUSY;
	/* 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);

	trace_test_pages_isolated(start_pfn, end_pfn, pfn);

	return pfn < end_pfn ? -EBUSY : 0;
}