summaryrefslogtreecommitdiff
path: root/include/linux/rmap.h
blob: 17230c458341ee5f975d41ca9c7691b249a09f94 (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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_RMAP_H
#define _LINUX_RMAP_H
/*
 * Declarations for Reverse Mapping functions in mm/rmap.c
 */

#include <linux/list.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/rwsem.h>
#include <linux/memcontrol.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>

/*
 * The anon_vma heads a list of private "related" vmas, to scan if
 * an anonymous page pointing to this anon_vma needs to be unmapped:
 * the vmas on the list will be related by forking, or by splitting.
 *
 * Since vmas come and go as they are split and merged (particularly
 * in mprotect), the mapping field of an anonymous page cannot point
 * directly to a vma: instead it points to an anon_vma, on whose list
 * the related vmas can be easily linked or unlinked.
 *
 * After unlinking the last vma on the list, we must garbage collect
 * the anon_vma object itself: we're guaranteed no page can be
 * pointing to this anon_vma once its vma list is empty.
 */
struct anon_vma {
	struct anon_vma *root;		/* Root of this anon_vma tree */
	struct rw_semaphore rwsem;	/* W: modification, R: walking the list */
	/*
	 * The refcount is taken on an anon_vma when there is no
	 * guarantee that the vma of page tables will exist for
	 * the duration of the operation. A caller that takes
	 * the reference is responsible for clearing up the
	 * anon_vma if they are the last user on release
	 */
	atomic_t refcount;

	/*
	 * Count of child anon_vmas and VMAs which points to this anon_vma.
	 *
	 * This counter is used for making decision about reusing anon_vma
	 * instead of forking new one. See comments in function anon_vma_clone.
	 */
	unsigned degree;

	struct anon_vma *parent;	/* Parent of this anon_vma */

	/*
	 * NOTE: the LSB of the rb_root.rb_node is set by
	 * mm_take_all_locks() _after_ taking the above lock. So the
	 * rb_root must only be read/written after taking the above lock
	 * to be sure to see a valid next pointer. The LSB bit itself
	 * is serialized by a system wide lock only visible to
	 * mm_take_all_locks() (mm_all_locks_mutex).
	 */

	/* Interval tree of private "related" vmas */
	struct rb_root_cached rb_root;
};

/*
 * The copy-on-write semantics of fork mean that an anon_vma
 * can become associated with multiple processes. Furthermore,
 * each child process will have its own anon_vma, where new
 * pages for that process are instantiated.
 *
 * This structure allows us to find the anon_vmas associated
 * with a VMA, or the VMAs associated with an anon_vma.
 * The "same_vma" list contains the anon_vma_chains linking
 * all the anon_vmas associated with this VMA.
 * The "rb" field indexes on an interval tree the anon_vma_chains
 * which link all the VMAs associated with this anon_vma.
 */
struct anon_vma_chain {
	struct vm_area_struct *vma;
	struct anon_vma *anon_vma;
	struct list_head same_vma;   /* locked by mmap_lock & page_table_lock */
	struct rb_node rb;			/* locked by anon_vma->rwsem */
	unsigned long rb_subtree_last;
#ifdef CONFIG_DEBUG_VM_RB
	unsigned long cached_vma_start, cached_vma_last;
#endif
};

enum ttu_flags {
	TTU_SPLIT_HUGE_PMD	= 0x4,	/* split huge PMD if any */
	TTU_IGNORE_MLOCK	= 0x8,	/* ignore mlock */
	TTU_SYNC		= 0x10,	/* avoid racy checks with PVMW_SYNC */
	TTU_IGNORE_HWPOISON	= 0x20,	/* corrupted page is recoverable */
	TTU_BATCH_FLUSH		= 0x40,	/* Batch TLB flushes where possible
					 * and caller guarantees they will
					 * do a final flush if necessary */
	TTU_RMAP_LOCKED		= 0x80,	/* do not grab rmap lock:
					 * caller holds it */
};

#ifdef CONFIG_MMU
static inline void get_anon_vma(struct anon_vma *anon_vma)
{
	atomic_inc(&anon_vma->refcount);
}

void __put_anon_vma(struct anon_vma *anon_vma);

static inline void put_anon_vma(struct anon_vma *anon_vma)
{
	if (atomic_dec_and_test(&anon_vma->refcount))
		__put_anon_vma(anon_vma);
}

static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
{
	down_write(&anon_vma->root->rwsem);
}

static inline void anon_vma_unlock_write(struct anon_vma *anon_vma)
{
	up_write(&anon_vma->root->rwsem);
}

static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
{
	down_read(&anon_vma->root->rwsem);
}

static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
{
	up_read(&anon_vma->root->rwsem);
}


/*
 * anon_vma helper functions.
 */
void anon_vma_init(void);	/* create anon_vma_cachep */
int  __anon_vma_prepare(struct vm_area_struct *);
void unlink_anon_vmas(struct vm_area_struct *);
int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);

static inline int anon_vma_prepare(struct vm_area_struct *vma)
{
	if (likely(vma->anon_vma))
		return 0;

	return __anon_vma_prepare(vma);
}

static inline void anon_vma_merge(struct vm_area_struct *vma,
				  struct vm_area_struct *next)
{
	VM_BUG_ON_VMA(vma->anon_vma != next->anon_vma, vma);
	unlink_anon_vmas(next);
}

struct anon_vma *page_get_anon_vma(struct page *page);

/* bitflags for do_page_add_anon_rmap() */
#define RMAP_EXCLUSIVE 0x01
#define RMAP_COMPOUND 0x02

/*
 * rmap interfaces called when adding or removing pte of page
 */
void page_move_anon_rmap(struct page *, struct vm_area_struct *);
void page_add_anon_rmap(struct page *, struct vm_area_struct *,
		unsigned long address, bool compound);
void do_page_add_anon_rmap(struct page *, struct vm_area_struct *,
		unsigned long address, int flags);
void page_add_new_anon_rmap(struct page *, struct vm_area_struct *,
		unsigned long address, bool compound);
void page_add_file_rmap(struct page *, struct vm_area_struct *,
		bool compound);
void page_remove_rmap(struct page *, struct vm_area_struct *,
		bool compound);
void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
		unsigned long address);
void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *,
		unsigned long address);

static inline void page_dup_rmap(struct page *page, bool compound)
{
	atomic_inc(compound ? compound_mapcount_ptr(page) : &page->_mapcount);
}

/*
 * Called from mm/vmscan.c to handle paging out
 */
int folio_referenced(struct folio *, int is_locked,
			struct mem_cgroup *memcg, unsigned long *vm_flags);

void try_to_migrate(struct folio *folio, enum ttu_flags flags);
void try_to_unmap(struct folio *, enum ttu_flags flags);

int make_device_exclusive_range(struct mm_struct *mm, unsigned long start,
				unsigned long end, struct page **pages,
				void *arg);

/* Avoid racy checks */
#define PVMW_SYNC		(1 << 0)
/* Look for migration entries rather than present PTEs */
#define PVMW_MIGRATION		(1 << 1)

struct page_vma_mapped_walk {
	unsigned long pfn;
	unsigned long nr_pages;
	pgoff_t pgoff;
	struct vm_area_struct *vma;
	unsigned long address;
	pmd_t *pmd;
	pte_t *pte;
	spinlock_t *ptl;
	unsigned int flags;
};

#define DEFINE_PAGE_VMA_WALK(name, _page, _vma, _address, _flags)	\
	struct page_vma_mapped_walk name = {				\
		.pfn = page_to_pfn(_page),				\
		.nr_pages = compound_nr(page),				\
		.pgoff = page_to_pgoff(page),				\
		.vma = _vma,						\
		.address = _address,					\
		.flags = _flags,					\
	}

#define DEFINE_FOLIO_VMA_WALK(name, _folio, _vma, _address, _flags)	\
	struct page_vma_mapped_walk name = {				\
		.pfn = folio_pfn(_folio),				\
		.nr_pages = folio_nr_pages(_folio),			\
		.pgoff = folio_pgoff(_folio),				\
		.vma = _vma,						\
		.address = _address,					\
		.flags = _flags,					\
	}

static inline void page_vma_mapped_walk_done(struct page_vma_mapped_walk *pvmw)
{
	/* HugeTLB pte is set to the relevant page table entry without pte_mapped. */
	if (pvmw->pte && !is_vm_hugetlb_page(pvmw->vma))
		pte_unmap(pvmw->pte);
	if (pvmw->ptl)
		spin_unlock(pvmw->ptl);
}

bool page_vma_mapped_walk(struct page_vma_mapped_walk *pvmw);

/*
 * Used by swapoff to help locate where page is expected in vma.
 */
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);

/*
 * Cleans the PTEs of shared mappings.
 * (and since clean PTEs should also be readonly, write protects them too)
 *
 * returns the number of cleaned PTEs.
 */
int folio_mkclean(struct folio *);

void remove_migration_ptes(struct folio *src, struct folio *dst, bool locked);

/*
 * Called by memory-failure.c to kill processes.
 */
struct anon_vma *folio_lock_anon_vma_read(struct folio *folio);
void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);

/*
 * rmap_walk_control: To control rmap traversing for specific needs
 *
 * arg: passed to rmap_one() and invalid_vma()
 * rmap_one: executed on each vma where page is mapped
 * done: for checking traversing termination condition
 * anon_lock: for getting anon_lock by optimized way rather than default
 * invalid_vma: for skipping uninterested vma
 */
struct rmap_walk_control {
	void *arg;
	/*
	 * Return false if page table scanning in rmap_walk should be stopped.
	 * Otherwise, return true.
	 */
	bool (*rmap_one)(struct folio *folio, struct vm_area_struct *vma,
					unsigned long addr, void *arg);
	int (*done)(struct folio *folio);
	struct anon_vma *(*anon_lock)(struct folio *folio);
	bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
};

void rmap_walk(struct folio *folio, const struct rmap_walk_control *rwc);
void rmap_walk_locked(struct folio *folio, const struct rmap_walk_control *rwc);

#else	/* !CONFIG_MMU */

#define anon_vma_init()		do {} while (0)
#define anon_vma_prepare(vma)	(0)
#define anon_vma_link(vma)	do {} while (0)

static inline int folio_referenced(struct folio *folio, int is_locked,
				  struct mem_cgroup *memcg,
				  unsigned long *vm_flags)
{
	*vm_flags = 0;
	return 0;
}

static inline void try_to_unmap(struct folio *folio, enum ttu_flags flags)
{
}

static inline int folio_mkclean(struct folio *folio)
{
	return 0;
}
#endif	/* CONFIG_MMU */

static inline int page_mkclean(struct page *page)
{
	return folio_mkclean(page_folio(page));
}
#endif	/* _LINUX_RMAP_H */