summaryrefslogtreecommitdiff
path: root/include/linux/swapops.h
blob: 291c4b53465819293aaa9c25bbed1b932f449f1f (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
#ifndef _LINUX_SWAPOPS_H
#define _LINUX_SWAPOPS_H

#include <linux/radix-tree.h>
#include <linux/bug.h>

/*
 * swapcache pages are stored in the swapper_space radix tree.  We want to
 * get good packing density in that tree, so the index should be dense in
 * the low-order bits.
 *
 * We arrange the `type' and `offset' fields so that `type' is at the seven
 * high-order bits of the swp_entry_t and `offset' is right-aligned in the
 * remaining bits.  Although `type' itself needs only five bits, we allow for
 * shmem/tmpfs to shift it all up a further two bits: see swp_to_radix_entry().
 *
 * swp_entry_t's are *never* stored anywhere in their arch-dependent format.
 */
#define SWP_TYPE_SHIFT(e)	((sizeof(e.val) * 8) - \
			(MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT))
#define SWP_OFFSET_MASK(e)	((1UL << SWP_TYPE_SHIFT(e)) - 1)

/*
 * Store a type+offset into a swp_entry_t in an arch-independent format
 */
static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset)
{
	swp_entry_t ret;

	ret.val = (type << SWP_TYPE_SHIFT(ret)) |
			(offset & SWP_OFFSET_MASK(ret));
	return ret;
}

/*
 * Extract the `type' field from a swp_entry_t.  The swp_entry_t is in
 * arch-independent format
 */
static inline unsigned swp_type(swp_entry_t entry)
{
	return (entry.val >> SWP_TYPE_SHIFT(entry));
}

/*
 * Extract the `offset' field from a swp_entry_t.  The swp_entry_t is in
 * arch-independent format
 */
static inline pgoff_t swp_offset(swp_entry_t entry)
{
	return entry.val & SWP_OFFSET_MASK(entry);
}

#ifdef CONFIG_MMU
/* check whether a pte points to a swap entry */
static inline int is_swap_pte(pte_t pte)
{
	return !pte_none(pte) && !pte_present(pte);
}
#endif

/*
 * Convert the arch-dependent pte representation of a swp_entry_t into an
 * arch-independent swp_entry_t.
 */
static inline swp_entry_t pte_to_swp_entry(pte_t pte)
{
	swp_entry_t arch_entry;

	if (pte_swp_soft_dirty(pte))
		pte = pte_swp_clear_soft_dirty(pte);
	arch_entry = __pte_to_swp_entry(pte);
	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}

/*
 * Convert the arch-independent representation of a swp_entry_t into the
 * arch-dependent pte representation.
 */
static inline pte_t swp_entry_to_pte(swp_entry_t entry)
{
	swp_entry_t arch_entry;

	arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
	return __swp_entry_to_pte(arch_entry);
}

static inline swp_entry_t radix_to_swp_entry(void *arg)
{
	swp_entry_t entry;

	entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT;
	return entry;
}

static inline void *swp_to_radix_entry(swp_entry_t entry)
{
	unsigned long value;

	value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT;
	return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY);
}

#if IS_ENABLED(CONFIG_DEVICE_PRIVATE)
static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
{
	return swp_entry(write ? SWP_DEVICE_WRITE : SWP_DEVICE_READ,
			 page_to_pfn(page));
}

static inline bool is_device_private_entry(swp_entry_t entry)
{
	int type = swp_type(entry);
	return type == SWP_DEVICE_READ || type == SWP_DEVICE_WRITE;
}

static inline void make_device_private_entry_read(swp_entry_t *entry)
{
	*entry = swp_entry(SWP_DEVICE_READ, swp_offset(*entry));
}

static inline bool is_write_device_private_entry(swp_entry_t entry)
{
	return unlikely(swp_type(entry) == SWP_DEVICE_WRITE);
}

static inline struct page *device_private_entry_to_page(swp_entry_t entry)
{
	return pfn_to_page(swp_offset(entry));
}

int device_private_entry_fault(struct vm_area_struct *vma,
		       unsigned long addr,
		       swp_entry_t entry,
		       unsigned int flags,
		       pmd_t *pmdp);
#else /* CONFIG_DEVICE_PRIVATE */
static inline swp_entry_t make_device_private_entry(struct page *page, bool write)
{
	return swp_entry(0, 0);
}

static inline void make_device_private_entry_read(swp_entry_t *entry)
{
}

static inline bool is_device_private_entry(swp_entry_t entry)
{
	return false;
}

static inline bool is_write_device_private_entry(swp_entry_t entry)
{
	return false;
}

static inline struct page *device_private_entry_to_page(swp_entry_t entry)
{
	return NULL;
}

static inline int device_private_entry_fault(struct vm_area_struct *vma,
				     unsigned long addr,
				     swp_entry_t entry,
				     unsigned int flags,
				     pmd_t *pmdp)
{
	return VM_FAULT_SIGBUS;
}
#endif /* CONFIG_DEVICE_PRIVATE */

#ifdef CONFIG_MIGRATION
static inline swp_entry_t make_migration_entry(struct page *page, int write)
{
	BUG_ON(!PageLocked(compound_head(page)));

	return swp_entry(write ? SWP_MIGRATION_WRITE : SWP_MIGRATION_READ,
			page_to_pfn(page));
}

static inline int is_migration_entry(swp_entry_t entry)
{
	return unlikely(swp_type(entry) == SWP_MIGRATION_READ ||
			swp_type(entry) == SWP_MIGRATION_WRITE);
}

static inline int is_write_migration_entry(swp_entry_t entry)
{
	return unlikely(swp_type(entry) == SWP_MIGRATION_WRITE);
}

static inline struct page *migration_entry_to_page(swp_entry_t entry)
{
	struct page *p = pfn_to_page(swp_offset(entry));
	/*
	 * Any use of migration entries may only occur while the
	 * corresponding page is locked
	 */
	BUG_ON(!PageLocked(compound_head(p)));
	return p;
}

static inline void make_migration_entry_read(swp_entry_t *entry)
{
	*entry = swp_entry(SWP_MIGRATION_READ, swp_offset(*entry));
}

extern void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
					spinlock_t *ptl);
extern void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
					unsigned long address);
extern void migration_entry_wait_huge(struct vm_area_struct *vma,
		struct mm_struct *mm, pte_t *pte);
#else

#define make_migration_entry(page, write) swp_entry(0, 0)
static inline int is_migration_entry(swp_entry_t swp)
{
	return 0;
}
static inline struct page *migration_entry_to_page(swp_entry_t entry)
{
	return NULL;
}

static inline void make_migration_entry_read(swp_entry_t *entryp) { }
static inline void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
					spinlock_t *ptl) { }
static inline void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
					 unsigned long address) { }
static inline void migration_entry_wait_huge(struct vm_area_struct *vma,
		struct mm_struct *mm, pte_t *pte) { }
static inline int is_write_migration_entry(swp_entry_t entry)
{
	return 0;
}

#endif

struct page_vma_mapped_walk;

#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
extern void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
		struct page *page);

extern void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
		struct page *new);

extern void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd);

static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)
{
	swp_entry_t arch_entry;

	if (pmd_swp_soft_dirty(pmd))
		pmd = pmd_swp_clear_soft_dirty(pmd);
	arch_entry = __pmd_to_swp_entry(pmd);
	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
}

static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
{
	swp_entry_t arch_entry;

	arch_entry = __swp_entry(swp_type(entry), swp_offset(entry));
	return __swp_entry_to_pmd(arch_entry);
}

static inline int is_pmd_migration_entry(pmd_t pmd)
{
	return !pmd_present(pmd) && is_migration_entry(pmd_to_swp_entry(pmd));
}
#else
static inline void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
		struct page *page)
{
	BUILD_BUG();
}

static inline void remove_migration_pmd(struct page_vma_mapped_walk *pvmw,
		struct page *new)
{
	BUILD_BUG();
}

static inline void pmd_migration_entry_wait(struct mm_struct *m, pmd_t *p) { }

static inline swp_entry_t pmd_to_swp_entry(pmd_t pmd)
{
	return swp_entry(0, 0);
}

static inline pmd_t swp_entry_to_pmd(swp_entry_t entry)
{
	return __pmd(0);
}

static inline int is_pmd_migration_entry(pmd_t pmd)
{
	return 0;
}
#endif

#ifdef CONFIG_MEMORY_FAILURE

extern atomic_long_t num_poisoned_pages __read_mostly;

/*
 * Support for hardware poisoned pages
 */
static inline swp_entry_t make_hwpoison_entry(struct page *page)
{
	BUG_ON(!PageLocked(page));
	return swp_entry(SWP_HWPOISON, page_to_pfn(page));
}

static inline int is_hwpoison_entry(swp_entry_t entry)
{
	return swp_type(entry) == SWP_HWPOISON;
}

static inline bool test_set_page_hwpoison(struct page *page)
{
	return TestSetPageHWPoison(page);
}

static inline void num_poisoned_pages_inc(void)
{
	atomic_long_inc(&num_poisoned_pages);
}

static inline void num_poisoned_pages_dec(void)
{
	atomic_long_dec(&num_poisoned_pages);
}

#else

static inline swp_entry_t make_hwpoison_entry(struct page *page)
{
	return swp_entry(0, 0);
}

static inline int is_hwpoison_entry(swp_entry_t swp)
{
	return 0;
}

static inline bool test_set_page_hwpoison(struct page *page)
{
	return false;
}

static inline void num_poisoned_pages_inc(void)
{
}
#endif

#if defined(CONFIG_MEMORY_FAILURE) || defined(CONFIG_MIGRATION)
static inline int non_swap_entry(swp_entry_t entry)
{
	return swp_type(entry) >= MAX_SWAPFILES;
}
#else
static inline int non_swap_entry(swp_entry_t entry)
{
	return 0;
}
#endif

#endif /* _LINUX_SWAPOPS_H */