aboutsummaryrefslogtreecommitdiff
path: root/mm/pagewalk.c
blob: 207244489a681d10f16c318c0a6ff0423b5fe30b (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
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/sched.h>
#include <linux/hugetlb.h>

static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pte_t *pte;
	int err = 0;

	pte = pte_offset_map(pmd, addr);
	for (;;) {
		err = walk->pte_entry(pte, addr, addr + PAGE_SIZE, walk);
		if (err)
		       break;
		addr += PAGE_SIZE;
		if (addr == end)
			break;
		pte++;
	}

	pte_unmap(pte);
	return err;
}

static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pmd_t *pmd;
	unsigned long next;
	int err = 0;

	pmd = pmd_offset(pud, addr);
	do {
again:
		next = pmd_addr_end(addr, end);
		if (pmd_none(*pmd) || !walk->vma) {
			if (walk->pte_hole)
				err = walk->pte_hole(addr, next, walk);
			if (err)
				break;
			continue;
		}
		/*
		 * This implies that each ->pmd_entry() handler
		 * needs to know about pmd_trans_huge() pmds
		 */
		if (walk->pmd_entry)
			err = walk->pmd_entry(pmd, addr, next, walk);
		if (err)
			break;

		/*
		 * Check this here so we only break down trans_huge
		 * pages when we _need_ to
		 */
		if (!walk->pte_entry)
			continue;

		split_huge_pmd(walk->vma, pmd, addr);
		if (pmd_trans_unstable(pmd))
			goto again;
		err = walk_pte_range(pmd, addr, next, walk);
		if (err)
			break;
	} while (pmd++, addr = next, addr != end);

	return err;
}

static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pud_t *pud;
	unsigned long next;
	int err = 0;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud)) {
			if (walk->pte_hole)
				err = walk->pte_hole(addr, next, walk);
			if (err)
				break;
			continue;
		}
		if (walk->pmd_entry || walk->pte_entry)
			err = walk_pmd_range(pud, addr, next, walk);
		if (err)
			break;
	} while (pud++, addr = next, addr != end);

	return err;
}

static int walk_pgd_range(unsigned long addr, unsigned long end,
			  struct mm_walk *walk)
{
	pgd_t *pgd;
	unsigned long next;
	int err = 0;

	pgd = pgd_offset(walk->mm, addr);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd)) {
			if (walk->pte_hole)
				err = walk->pte_hole(addr, next, walk);
			if (err)
				break;
			continue;
		}
		if (walk->pmd_entry || walk->pte_entry)
			err = walk_pud_range(pgd, addr, next, walk);
		if (err)
			break;
	} while (pgd++, addr = next, addr != end);

	return err;
}

#ifdef CONFIG_HUGETLB_PAGE
static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr,
				       unsigned long end)
{
	unsigned long boundary = (addr & huge_page_mask(h)) + huge_page_size(h);
	return boundary < end ? boundary : end;
}

static int walk_hugetlb_range(unsigned long addr, unsigned long end,
			      struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->vma;
	struct hstate *h = hstate_vma(vma);
	unsigned long next;
	unsigned long hmask = huge_page_mask(h);
	pte_t *pte;
	int err = 0;

	do {
		next = hugetlb_entry_end(h, addr, end);
		pte = huge_pte_offset(walk->mm, addr & hmask);
		if (pte && walk->hugetlb_entry)
			err = walk->hugetlb_entry(pte, hmask, addr, next, walk);
		if (err)
			break;
	} while (addr = next, addr != end);

	return err;
}

#else /* CONFIG_HUGETLB_PAGE */
static int walk_hugetlb_range(unsigned long addr, unsigned long end,
			      struct mm_walk *walk)
{
	return 0;
}

#endif /* CONFIG_HUGETLB_PAGE */

/*
 * Decide whether we really walk over the current vma on [@start, @end)
 * or skip it via the returned value. Return 0 if we do walk over the
 * current vma, and return 1 if we skip the vma. Negative values means
 * error, where we abort the current walk.
 */
static int walk_page_test(unsigned long start, unsigned long end,
			struct mm_walk *walk)
{
	struct vm_area_struct *vma = walk->vma;

	if (walk->test_walk)
		return walk->test_walk(start, end, walk);

	/*
	 * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP
	 * range, so we don't walk over it as we do for normal vmas. However,
	 * Some callers are interested in handling hole range and they don't
	 * want to just ignore any single address range. Such users certainly
	 * define their ->pte_hole() callbacks, so let's delegate them to handle
	 * vma(VM_PFNMAP).
	 */
	if (vma->vm_flags & VM_PFNMAP) {
		int err = 1;
		if (walk->pte_hole)
			err = walk->pte_hole(start, end, walk);
		return err ? err : 1;
	}
	return 0;
}

static int __walk_page_range(unsigned long start, unsigned long end,
			struct mm_walk *walk)
{
	int err = 0;
	struct vm_area_struct *vma = walk->vma;

	if (vma && is_vm_hugetlb_page(vma)) {
		if (walk->hugetlb_entry)
			err = walk_hugetlb_range(start, end, walk);
	} else
		err = walk_pgd_range(start, end, walk);

	return err;
}

/**
 * walk_page_range - walk page table with caller specific callbacks
 *
 * Recursively walk the page table tree of the process represented by @walk->mm
 * within the virtual address range [@start, @end). During walking, we can do
 * some caller-specific works for each entry, by setting up pmd_entry(),
 * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these
 * callbacks, the associated entries/pages are just ignored.
 * The return values of these callbacks are commonly defined like below:
 *  - 0  : succeeded to handle the current entry, and if you don't reach the
 *         end address yet, continue to walk.
 *  - >0 : succeeded to handle the current entry, and return to the caller
 *         with caller specific value.
 *  - <0 : failed to handle the current entry, and return to the caller
 *         with error code.
 *
 * Before starting to walk page table, some callers want to check whether
 * they really want to walk over the current vma, typically by checking
 * its vm_flags. walk_page_test() and @walk->test_walk() are used for this
 * purpose.
 *
 * struct mm_walk keeps current values of some common data like vma and pmd,
 * which are useful for the access from callbacks. If you want to pass some
 * caller-specific data to callbacks, @walk->private should be helpful.
 *
 * Locking:
 *   Callers of walk_page_range() and walk_page_vma() should hold
 *   @walk->mm->mmap_sem, because these function traverse vma list and/or
 *   access to vma's data.
 */
int walk_page_range(unsigned long start, unsigned long end,
		    struct mm_walk *walk)
{
	int err = 0;
	unsigned long next;
	struct vm_area_struct *vma;

	if (start >= end)
		return -EINVAL;

	if (!walk->mm)
		return -EINVAL;

	VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm);

	vma = find_vma(walk->mm, start);
	do {
		if (!vma) { /* after the last vma */
			walk->vma = NULL;
			next = end;
		} else if (start < vma->vm_start) { /* outside vma */
			walk->vma = NULL;
			next = min(end, vma->vm_start);
		} else { /* inside vma */
			walk->vma = vma;
			next = min(end, vma->vm_end);
			vma = vma->vm_next;

			err = walk_page_test(start, next, walk);
			if (err > 0) {
				/*
				 * positive return values are purely for
				 * controlling the pagewalk, so should never
				 * be passed to the callers.
				 */
				err = 0;
				continue;
			}
			if (err < 0)
				break;
		}
		if (walk->vma || walk->pte_hole)
			err = __walk_page_range(start, next, walk);
		if (err)
			break;
	} while (start = next, start < end);
	return err;
}

int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk)
{
	int err;

	if (!walk->mm)
		return -EINVAL;

	VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem));
	VM_BUG_ON(!vma);
	walk->vma = vma;
	err = walk_page_test(vma->vm_start, vma->vm_end, walk);
	if (err > 0)
		return 0;
	if (err < 0)
		return err;
	return __walk_page_range(vma->vm_start, vma->vm_end, walk);
}