Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: 67d02dc0ea04035e280faad5ec180d459f87b559 (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
/*
 *  mm/mprotect.c
 *
 *  (C) Copyright 1994 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 *
 *  Address space accounting code	<alan@redhat.com>
 *  (C) Copyright 2002 Red Hat Inc, All Rights Reserved
 */

#include <linux/mm.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/fs.h>
#include <linux/highmem.h>
#include <linux/security.h>
#include <linux/mempolicy.h>
#include <linux/personality.h>

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

static inline void
change_pte_range(pmd_t *pmd, unsigned long address,
		unsigned long size, pgprot_t newprot)
{
	pte_t * pte;
	unsigned long end;

	if (pmd_none(*pmd))
		return;
	if (pmd_bad(*pmd)) {
		pmd_ERROR(*pmd);
		pmd_clear(pmd);
		return;
	}
	pte = pte_offset_map(pmd, address);
	address &= ~PMD_MASK;
	end = address + size;
	if (end > PMD_SIZE)
		end = PMD_SIZE;
	do {
		if (pte_present(*pte)) {
			pte_t entry;

			/* Avoid an SMP race with hardware updated dirty/clean
			 * bits by wiping the pte and then setting the new pte
			 * into place.
			 */
			entry = ptep_get_and_clear(pte);
			set_pte(pte, pte_modify(entry, newprot));
		}
		address += PAGE_SIZE;
		pte++;
	} while (address && (address < end));
	pte_unmap(pte - 1);
}

static inline void
change_pmd_range(pgd_t *pgd, unsigned long address,
		unsigned long size, pgprot_t newprot)
{
	pmd_t * pmd;
	unsigned long end;

	if (pgd_none(*pgd))
		return;
	if (pgd_bad(*pgd)) {
		pgd_ERROR(*pgd);
		pgd_clear(pgd);
		return;
	}
	pmd = pmd_offset(pgd, address);
	address &= ~PGDIR_MASK;
	end = address + size;
	if (end > PGDIR_SIZE)
		end = PGDIR_SIZE;
	do {
		change_pte_range(pmd, address, end - address, newprot);
		address = (address + PMD_SIZE) & PMD_MASK;
		pmd++;
	} while (address && (address < end));
}

static void
change_protection(struct vm_area_struct *vma, unsigned long start,
		unsigned long end, pgprot_t newprot)
{
	pgd_t *dir;
	unsigned long beg = start;

	dir = pgd_offset(current->mm, start);
	flush_cache_range(vma, beg, end);
	if (start >= end)
		BUG();
	spin_lock(&current->mm->page_table_lock);
	do {
		change_pmd_range(dir, start, end - start, newprot);
		start = (start + PGDIR_SIZE) & PGDIR_MASK;
		dir++;
	} while (start && (start < end));
	flush_tlb_range(vma, beg, end);
	spin_unlock(&current->mm->page_table_lock);
	return;
}

static int
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
	unsigned long start, unsigned long end, unsigned int newflags)
{
	struct mm_struct * mm = vma->vm_mm;
	unsigned long charged = 0;
	pgprot_t newprot;
	pgoff_t pgoff;
	int error;

	if (newflags == vma->vm_flags) {
		*pprev = vma;
		return 0;
	}

	/*
	 * If we make a private mapping writable we increase our commit;
	 * but (without finer accounting) cannot reduce our commit if we
	 * make it unwritable again.
	 *
	 * FIXME? We haven't defined a VM_NORESERVE flag, so mprotecting
	 * a MAP_NORESERVE private mapping to writable will now reserve.
	 */
	if (newflags & VM_WRITE) {
		if (!(vma->vm_flags & (VM_ACCOUNT|VM_WRITE|VM_SHARED|VM_HUGETLB))) {
			charged = (end - start) >> PAGE_SHIFT;
			if (security_vm_enough_memory(charged))
				return -ENOMEM;
			newflags |= VM_ACCOUNT;
		}
	}

	newprot = protection_map[newflags & 0xf];

	/*
	 * First try to merge with previous and/or next vma.
	 */
	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
	*pprev = vma_merge(mm, *pprev, start, end, newflags,
			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
	if (*pprev) {
		vma = *pprev;
		goto success;
	}

	if (start != vma->vm_start) {
		error = split_vma(mm, vma, start, 1);
		if (error)
			goto fail;
	}
	/*
	 * Unless it returns an error, this function always sets *pprev to
	 * the first vma for which vma->vm_end >= end.
	 */
	*pprev = vma;

	if (end != vma->vm_end) {
		error = split_vma(mm, vma, end, 0);
		if (error)
			goto fail;
	}

success:
	/*
	 * vm_flags and vm_page_prot are protected by the mmap_sem
	 * held in write mode.
	 */
	vm_stat_unaccount(vma);
	vma->vm_flags = newflags;
	vma->vm_page_prot = newprot;
	change_protection(vma, start, end, newprot);
	vm_stat_account(vma);
	return 0;

fail:
	vm_unacct_memory(charged);
	return error;
}

asmlinkage long
sys_mprotect(unsigned long start, size_t len, unsigned long prot)
{
	unsigned long vm_flags, nstart, end, tmp;
	struct vm_area_struct *vma, *prev;
	int error = -EINVAL;
	const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
	prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
	if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
		return -EINVAL;

	if (start & ~PAGE_MASK)
		return -EINVAL;
	len = PAGE_ALIGN(len);
	end = start + len;
	if (end < start)
		return -ENOMEM;
	if (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM))
		return -EINVAL;
	if (end == start)
		return 0;
	/*
	 * Does the application expect PROT_READ to imply PROT_EXEC:
	 */
	if (unlikely((prot & PROT_READ) &&
			(current->personality & READ_IMPLIES_EXEC)))
		prot |= PROT_EXEC;

	vm_flags = calc_vm_prot_bits(prot);

	down_write(&current->mm->mmap_sem);

	vma = find_vma_prev(current->mm, start, &prev);
	error = -ENOMEM;
	if (!vma)
		goto out;
	if (unlikely(grows & PROT_GROWSDOWN)) {
		if (vma->vm_start >= end)
			goto out;
		start = vma->vm_start;
		error = -EINVAL;
		if (!(vma->vm_flags & VM_GROWSDOWN))
			goto out;
	}
	else {
		if (vma->vm_start > start)
			goto out;
		if (unlikely(grows & PROT_GROWSUP)) {
			end = vma->vm_end;
			error = -EINVAL;
			if (!(vma->vm_flags & VM_GROWSUP))
				goto out;
		}
	}
	if (start > vma->vm_start)
		prev = vma;

	for (nstart = start ; ; ) {
		unsigned int newflags;

		/* Here we know that  vma->vm_start <= nstart < vma->vm_end. */

		if (is_vm_hugetlb_page(vma)) {
			error = -EACCES;
			goto out;
		}

		newflags = vm_flags | (vma->vm_flags & ~(VM_READ | VM_WRITE | VM_EXEC));

		if ((newflags & ~(newflags >> 4)) & 0xf) {
			error = -EACCES;
			goto out;
		}

		error = security_file_mprotect(vma, prot);
		if (error)
			goto out;

		tmp = vma->vm_end;
		if (tmp > end)
			tmp = end;
		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
		if (error)
			goto out;
		nstart = tmp;

		if (nstart < prev->vm_end)
			nstart = prev->vm_end;
		if (nstart >= end)
			goto out;

		vma = prev->vm_next;
		if (!vma || vma->vm_start != nstart) {
			error = -ENOMEM;
			goto out;
		}
	}
out:
	up_write(&current->mm->mmap_sem);
	return error;
}