mprotect.c 7.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6
/*
 *  mm/mprotect.c
 *
 *  (C) Copyright 1994 Linus Torvalds
 *  (C) Copyright 2002 Christoph Hellwig
 *
A
Alan Cox 已提交
7
 *  Address space accounting code	<alan@lxorguk.ukuu.org.uk>
L
Linus Torvalds 已提交
8 9 10 11 12 13 14 15 16 17 18 19 20
 *  (C) Copyright 2002 Red Hat Inc, All Rights Reserved
 */

#include <linux/mm.h>
#include <linux/hugetlb.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 <linux/syscalls.h>
21 22
#include <linux/swap.h>
#include <linux/swapops.h>
A
Andrea Arcangeli 已提交
23
#include <linux/mmu_notifier.h>
24
#include <linux/migrate.h>
25
#include <linux/perf_event.h>
L
Linus Torvalds 已提交
26 27 28 29 30
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>

31 32 33 34 35 36 37
#ifndef pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
	return newprot;
}
#endif

L
Linus Torvalds 已提交
38
static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
39 40
		unsigned long addr, unsigned long end, pgprot_t newprot,
		int dirty_accountable)
L
Linus Torvalds 已提交
41
{
42
	pte_t *pte, oldpte;
43
	spinlock_t *ptl;
L
Linus Torvalds 已提交
44

45
	pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
46
	arch_enter_lazy_mmu_mode();
L
Linus Torvalds 已提交
47
	do {
48 49
		oldpte = *pte;
		if (pte_present(oldpte)) {
L
Linus Torvalds 已提交
50 51
			pte_t ptent;

52
			ptent = ptep_modify_prot_start(mm, addr, pte);
53
			ptent = pte_modify(ptent, newprot);
54

55 56 57 58 59 60
			/*
			 * Avoid taking write faults for pages we know to be
			 * dirty.
			 */
			if (dirty_accountable && pte_dirty(ptent))
				ptent = pte_mkwrite(ptent);
61 62

			ptep_modify_prot_commit(mm, addr, pte, ptent);
63
		} else if (PAGE_MIGRATION && !pte_file(oldpte)) {
64 65 66 67 68 69 70 71 72 73 74
			swp_entry_t entry = pte_to_swp_entry(oldpte);

			if (is_write_migration_entry(entry)) {
				/*
				 * A protection check is difficult so
				 * just be safe and disable write
				 */
				make_migration_entry_read(&entry);
				set_pte_at(mm, addr, pte,
					swp_entry_to_pte(entry));
			}
L
Linus Torvalds 已提交
75 76
		}
	} while (pte++, addr += PAGE_SIZE, addr != end);
77
	arch_leave_lazy_mmu_mode();
78
	pte_unmap_unlock(pte - 1, ptl);
L
Linus Torvalds 已提交
79 80
}

81
static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
82 83
		unsigned long addr, unsigned long end, pgprot_t newprot,
		int dirty_accountable)
L
Linus Torvalds 已提交
84 85 86 87 88 89 90
{
	pmd_t *pmd;
	unsigned long next;

	pmd = pmd_offset(pud, addr);
	do {
		next = pmd_addr_end(addr, end);
91 92 93 94 95 96 97
		if (pmd_trans_huge(*pmd)) {
			if (next - addr != HPAGE_PMD_SIZE)
				split_huge_page_pmd(vma->vm_mm, pmd);
			else if (change_huge_pmd(vma, pmd, addr, newprot))
				continue;
			/* fall through */
		}
L
Linus Torvalds 已提交
98 99
		if (pmd_none_or_clear_bad(pmd))
			continue;
100 101
		change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
				 dirty_accountable);
L
Linus Torvalds 已提交
102 103 104
	} while (pmd++, addr = next, addr != end);
}

105
static inline void change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
106 107
		unsigned long addr, unsigned long end, pgprot_t newprot,
		int dirty_accountable)
L
Linus Torvalds 已提交
108 109 110 111 112 113 114 115 116
{
	pud_t *pud;
	unsigned long next;

	pud = pud_offset(pgd, addr);
	do {
		next = pud_addr_end(addr, end);
		if (pud_none_or_clear_bad(pud))
			continue;
117 118
		change_pmd_range(vma, pud, addr, next, newprot,
				 dirty_accountable);
L
Linus Torvalds 已提交
119 120 121 122
	} while (pud++, addr = next, addr != end);
}

static void change_protection(struct vm_area_struct *vma,
123 124
		unsigned long addr, unsigned long end, pgprot_t newprot,
		int dirty_accountable)
L
Linus Torvalds 已提交
125 126 127 128 129 130 131 132 133 134 135 136 137
{
	struct mm_struct *mm = vma->vm_mm;
	pgd_t *pgd;
	unsigned long next;
	unsigned long start = addr;

	BUG_ON(addr >= end);
	pgd = pgd_offset(mm, addr);
	flush_cache_range(vma, addr, end);
	do {
		next = pgd_addr_end(addr, end);
		if (pgd_none_or_clear_bad(pgd))
			continue;
138 139
		change_pud_range(vma, pgd, addr, next, newprot,
				 dirty_accountable);
L
Linus Torvalds 已提交
140 141 142 143
	} while (pgd++, addr = next, addr != end);
	flush_tlb_range(vma, start, end);
}

144
int
L
Linus Torvalds 已提交
145 146 147 148 149 150 151 152 153
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
	unsigned long start, unsigned long end, unsigned long newflags)
{
	struct mm_struct *mm = vma->vm_mm;
	unsigned long oldflags = vma->vm_flags;
	long nrpages = (end - start) >> PAGE_SHIFT;
	unsigned long charged = 0;
	pgoff_t pgoff;
	int error;
154
	int dirty_accountable = 0;
L
Linus Torvalds 已提交
155 156 157 158 159 160 161 162 163

	if (newflags == oldflags) {
		*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
164 165
	 * make it unwritable again. hugetlb mapping were accounted for
	 * even if read-only so there is no need to account for them here
L
Linus Torvalds 已提交
166 167
	 */
	if (newflags & VM_WRITE) {
168
		if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
169
						VM_SHARED|VM_NORESERVE))) {
L
Linus Torvalds 已提交
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
			charged = nrpages;
			if (security_vm_enough_memory(charged))
				return -ENOMEM;
			newflags |= VM_ACCOUNT;
		}
	}

	/*
	 * 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;
	}

	*pprev = vma;

	if (start != vma->vm_start) {
		error = split_vma(mm, vma, start, 1);
		if (error)
			goto fail;
	}

	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.
	 */
	vma->vm_flags = newflags;
208 209 210
	vma->vm_page_prot = pgprot_modify(vma->vm_page_prot,
					  vm_get_page_prot(newflags));

211
	if (vma_wants_writenotify(vma)) {
212
		vma->vm_page_prot = vm_get_page_prot(newflags & ~VM_SHARED);
213 214
		dirty_accountable = 1;
	}
215

A
Andrea Arcangeli 已提交
216
	mmu_notifier_invalidate_range_start(mm, start, end);
217
	if (is_vm_hugetlb_page(vma))
218
		hugetlb_change_protection(vma, start, end, vma->vm_page_prot);
219
	else
220
		change_protection(vma, start, end, vma->vm_page_prot, dirty_accountable);
A
Andrea Arcangeli 已提交
221
	mmu_notifier_invalidate_range_end(mm, start, end);
222 223
	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
224
	perf_event_mmap(vma);
L
Linus Torvalds 已提交
225 226 227 228 229 230 231
	return 0;

fail:
	vm_unacct_memory(charged);
	return error;
}

232 233
SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
		unsigned long, prot)
L
Linus Torvalds 已提交
234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250
{
	unsigned long vm_flags, nstart, end, tmp, reqprot;
	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;
	if (!len)
		return 0;
	len = PAGE_ALIGN(len);
	end = start + len;
	if (end <= start)
		return -ENOMEM;
251
	if (!arch_validate_prot(prot))
L
Linus Torvalds 已提交
252 253 254 255 256 257
		return -EINVAL;

	reqprot = prot;
	/*
	 * Does the application expect PROT_READ to imply PROT_EXEC:
	 */
258
	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
L
Linus Torvalds 已提交
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
		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 long newflags;

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

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

297 298
		/* newflags >> 4 shift VM_MAY% in place of VM_% */
		if ((newflags & ~(newflags >> 4)) & (VM_READ | VM_WRITE | VM_EXEC)) {
L
Linus Torvalds 已提交
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
			error = -EACCES;
			goto out;
		}

		error = security_file_mprotect(vma, reqprot, 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;
}