summaryrefslogtreecommitdiff
path: root/mm/mincore.c
blob: 9700c230394169a6401b7a886d7bb6abf8869fe4 (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
/*
 *	linux/mm/mincore.c
 *
 * Copyright (C) 1994-2006  Linus Torvalds
 */

/*
 * The mincore() system call.
 */
#include <linux/pagemap.h>
#include <linux/gfp.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/syscalls.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/hugetlb.h>

#include <asm/uaccess.h>
#include <asm/pgtable.h>

static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr,
			unsigned long end, struct mm_walk *walk)
{
#ifdef CONFIG_HUGETLB_PAGE
	unsigned char present;
	unsigned char *vec = walk->private;

	/*
	 * Hugepages under user process are always in RAM and never
	 * swapped out, but theoretically it needs to be checked.
	 */
	present = pte && !huge_pte_none(huge_ptep_get(pte));
	for (; addr != end; vec++, addr += PAGE_SIZE)
		*vec = present;
	walk->private = vec;
#else
	BUG();
#endif
	return 0;
}

/*
 * Later we can get more picky about what "in core" means precisely.
 * For now, simply check to see if the page is in the page cache,
 * and is up to date; i.e. that no page-in operation would be required
 * at this time if an application were to map and access this page.
 */
static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff)
{
	unsigned char present = 0;
	struct page *page;

	/*
	 * When tmpfs swaps out a page from a file, any process mapping that
	 * file will not get a swp_entry_t in its pte, but rather it is like
	 * any other file mapping (ie. marked !present and faulted in with
	 * tmpfs's .fault). So swapped out tmpfs mappings are tested here.
	 */
#ifdef CONFIG_SWAP
	if (shmem_mapping(mapping)) {
		page = find_get_entry(mapping, pgoff);
		/*
		 * shmem/tmpfs may return swap: account for swapcache
		 * page too.
		 */
		if (radix_tree_exceptional_entry(page)) {
			swp_entry_t swp = radix_to_swp_entry(page);
			page = find_get_page(swap_address_space(swp), swp.val);
		}
	} else
		page = find_get_page(mapping, pgoff);
#else
	page = find_get_page(mapping, pgoff);
#endif
	if (page) {
		present = PageUptodate(page);
		page_cache_release(page);
	}

	return present;
}

static int __mincore_unmapped_range(unsigned long addr, unsigned long end,
				struct vm_area_struct *vma, unsigned char *vec)
{
	unsigned long nr = (end - addr) >> PAGE_SHIFT;
	int i;

	if (vma->vm_file) {
		pgoff_t pgoff;

		pgoff = linear_page_index(vma, addr);
		for (i = 0; i < nr; i++, pgoff++)
			vec[i] = mincore_page(vma->vm_file->f_mapping, pgoff);
	} else {
		for (i = 0; i < nr; i++)
			vec[i] = 0;
	}
	return nr;
}

static int mincore_unmapped_range(unsigned long addr, unsigned long end,
				   struct mm_walk *walk)
{
	walk->private += __mincore_unmapped_range(addr, end,
						  walk->vma, walk->private);
	return 0;
}

static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
			struct mm_walk *walk)
{
	spinlock_t *ptl;
	struct vm_area_struct *vma = walk->vma;
	pte_t *ptep;
	unsigned char *vec = walk->private;
	int nr = (end - addr) >> PAGE_SHIFT;

	if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
		memset(vec, 1, nr);
		spin_unlock(ptl);
		goto out;
	}

	if (pmd_trans_unstable(pmd)) {
		__mincore_unmapped_range(addr, end, vma, vec);
		goto out;
	}

	ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl);
	for (; addr != end; ptep++, addr += PAGE_SIZE) {
		pte_t pte = *ptep;

		if (pte_none(pte))
			__mincore_unmapped_range(addr, addr + PAGE_SIZE,
						 vma, vec);
		else if (pte_present(pte))
			*vec = 1;
		else { /* pte is a swap entry */
			swp_entry_t entry = pte_to_swp_entry(pte);

			if (non_swap_entry(entry)) {
				/*
				 * migration or hwpoison entries are always
				 * uptodate
				 */
				*vec = 1;
			} else {
#ifdef CONFIG_SWAP
				*vec = mincore_page(swap_address_space(entry),
					entry.val);
#else
				WARN_ON(1);
				*vec = 1;
#endif
			}
		}
		vec++;
	}
	pte_unmap_unlock(ptep - 1, ptl);
out:
	walk->private += nr;
	cond_resched();
	return 0;
}

static inline bool can_do_mincore(struct vm_area_struct *vma)
{
	if (vma_is_anonymous(vma))
		return true;
	if (!vma->vm_file)
		return false;
	/*
	 * Reveal pagecache information only for non-anonymous mappings that
	 * correspond to the files the calling process could (if tried) open
	 * for writing; otherwise we'd be including shared non-exclusive
	 * mappings, which opens a side channel.
	 */
	return inode_owner_or_capable(file_inode(vma->vm_file)) ||
		inode_permission(file_inode(vma->vm_file), MAY_WRITE) == 0;
}

/*
 * Do a chunk of "sys_mincore()". We've already checked
 * all the arguments, we hold the mmap semaphore: we should
 * just return the amount of info we're asked for.
 */
static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *vec)
{
	struct vm_area_struct *vma;
	unsigned long end;
	int err;
	struct mm_walk mincore_walk = {
		.pmd_entry = mincore_pte_range,
		.pte_hole = mincore_unmapped_range,
		.hugetlb_entry = mincore_hugetlb,
		.private = vec,
	};

	vma = find_vma(current->mm, addr);
	if (!vma || addr < vma->vm_start)
		return -ENOMEM;
	end = min(vma->vm_end, addr + (pages << PAGE_SHIFT));
	if (!can_do_mincore(vma)) {
		unsigned long pages = DIV_ROUND_UP(end - addr, PAGE_SIZE);
		memset(vec, 1, pages);
		return pages;
	}
	mincore_walk.mm = vma->vm_mm;
	err = walk_page_range(addr, end, &mincore_walk);
	if (err < 0)
		return err;
	return (end - addr) >> PAGE_SHIFT;
}

/*
 * The mincore(2) system call.
 *
 * mincore() returns the memory residency status of the pages in the
 * current process's address space specified by [addr, addr + len).
 * The status is returned in a vector of bytes.  The least significant
 * bit of each byte is 1 if the referenced page is in memory, otherwise
 * it is zero.
 *
 * Because the status of a page can change after mincore() checks it
 * but before it returns to the application, the returned vector may
 * contain stale information.  Only locked pages are guaranteed to
 * remain in memory.
 *
 * return values:
 *  zero    - success
 *  -EFAULT - vec points to an illegal address
 *  -EINVAL - addr is not a multiple of PAGE_CACHE_SIZE
 *  -ENOMEM - Addresses in the range [addr, addr + len] are
 *		invalid for the address space of this process, or
 *		specify one or more pages which are not currently
 *		mapped
 *  -EAGAIN - A kernel resource was temporarily unavailable.
 */
SYSCALL_DEFINE3(mincore, unsigned long, start, size_t, len,
		unsigned char __user *, vec)
{
	long retval;
	unsigned long pages;
	unsigned char *tmp;

	/* Check the start address: needs to be page-aligned.. */
 	if (start & ~PAGE_CACHE_MASK)
		return -EINVAL;

	/* ..and we need to be passed a valid user-space range */
	if (!access_ok(VERIFY_READ, (void __user *) start, len))
		return -ENOMEM;

	/* This also avoids any overflows on PAGE_CACHE_ALIGN */
	pages = len >> PAGE_SHIFT;
	pages += (offset_in_page(len)) != 0;

	if (!access_ok(VERIFY_WRITE, vec, pages))
		return -EFAULT;

	tmp = (void *) __get_free_page(GFP_USER);
	if (!tmp)
		return -EAGAIN;

	retval = 0;
	while (pages) {
		/*
		 * Do at most PAGE_SIZE entries per iteration, due to
		 * the temporary buffer size.
		 */
		down_read(&current->mm->mmap_sem);
		retval = do_mincore(start, min(pages, PAGE_SIZE), tmp);
		up_read(&current->mm->mmap_sem);

		if (retval <= 0)
			break;
		if (copy_to_user(vec, tmp, retval)) {
			retval = -EFAULT;
			break;
		}
		pages -= retval;
		vec += retval;
		start += retval << PAGE_SHIFT;
		retval = 0;
	}
	free_page((unsigned long) tmp);
	return retval;
}