mmap.c 70.1 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5
/*
 * mm/mmap.c
 *
 * Written by obz.
 *
Alan Cox's avatar
Alan Cox committed
6
 * Address space accounting code	<alan@lxorguk.ukuu.org.uk>
Linus Torvalds's avatar
Linus Torvalds committed
7 8 9
 */

#include <linux/slab.h>
Alexey Dobriyan's avatar
Alexey Dobriyan committed
10
#include <linux/backing-dev.h>
Linus Torvalds's avatar
Linus Torvalds committed
11 12 13 14 15 16
#include <linux/mm.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/syscalls.h>
17
#include <linux/capability.h>
Linus Torvalds's avatar
Linus Torvalds committed
18 19 20 21 22 23 24
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/hugetlb.h>
#include <linux/profile.h>
25
#include <linux/export.h>
Linus Torvalds's avatar
Linus Torvalds committed
26 27 28
#include <linux/mount.h>
#include <linux/mempolicy.h>
#include <linux/rmap.h>
Andrea Arcangeli's avatar
Andrea Arcangeli committed
29
#include <linux/mmu_notifier.h>
30
#include <linux/perf_event.h>
Al Viro's avatar
Al Viro committed
31
#include <linux/audit.h>
Andrea Arcangeli's avatar
Andrea Arcangeli committed
32
#include <linux/khugepaged.h>
Linus Torvalds's avatar
Linus Torvalds committed
33 34 35 36

#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlb.h>
37
#include <asm/mmu_context.h>
Linus Torvalds's avatar
Linus Torvalds committed
38

39 40
#include "internal.h"

41 42 43 44
#ifndef arch_mmap_check
#define arch_mmap_check(addr, len, flags)	(0)
#endif

45 46 47 48
#ifndef arch_rebalance_pgtables
#define arch_rebalance_pgtables(addr, len)		(addr)
#endif

49 50 51 52
static void unmap_region(struct mm_struct *mm,
		struct vm_area_struct *vma, struct vm_area_struct *prev,
		unsigned long start, unsigned long end);

Linus Torvalds's avatar
Linus Torvalds committed
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
/*
 * WARNING: the debugging will use recursive algorithms so never enable this
 * unless you know what you are doing.
 */
#undef DEBUG_MM_RB

/* description of effects of mapping type and prot in current implementation.
 * this is due to the limited x86 page protection hardware.  The expected
 * behavior is in parens:
 *
 * map_type	prot
 *		PROT_NONE	PROT_READ	PROT_WRITE	PROT_EXEC
 * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *		
 * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *
 */
pgprot_t protection_map[16] = {
	__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};

79 80
pgprot_t vm_get_page_prot(unsigned long vm_flags)
{
81 82 83
	return __pgprot(pgprot_val(protection_map[vm_flags &
				(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]) |
			pgprot_val(arch_vm_get_page_prot(vm_flags)));
84 85 86
}
EXPORT_SYMBOL(vm_get_page_prot);

87 88
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;  /* heuristic overcommit */
int sysctl_overcommit_ratio __read_mostly = 50;	/* default is 50% */
89
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
90 91 92 93 94
/*
 * Make sure vm_committed_as in one cacheline and not cacheline shared with
 * other variables. It can be updated by several CPUs frequently.
 */
struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
Linus Torvalds's avatar
Linus Torvalds committed
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111

/*
 * Check that a process has enough memory to allocate a new virtual
 * mapping. 0 means there is enough memory for the allocation to
 * succeed and -ENOMEM implies there is not.
 *
 * We currently support three overcommit policies, which are set via the
 * vm.overcommit_memory sysctl.  See Documentation/vm/overcommit-accounting
 *
 * Strict overcommit modes added 2002 Feb 26 by Alan Cox.
 * Additional code 2002 Jul 20 by Robert Love.
 *
 * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
 *
 * Note this is a helper function intended to be used by LSMs which
 * wish to use this logic.
 */
112
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
Linus Torvalds's avatar
Linus Torvalds committed
113 114 115 116 117 118 119 120 121 122 123 124
{
	unsigned long free, allowed;

	vm_acct_memory(pages);

	/*
	 * Sometimes we want to use more memory than we have
	 */
	if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
		return 0;

	if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
125 126 127 128 129 130 131 132 133 134
		free = global_page_state(NR_FREE_PAGES);
		free += global_page_state(NR_FILE_PAGES);

		/*
		 * shmem pages shouldn't be counted as free in this
		 * case, they can't be purged, only swapped out, and
		 * that won't affect the overall amount of available
		 * memory in the system.
		 */
		free -= global_page_state(NR_SHMEM);
Linus Torvalds's avatar
Linus Torvalds committed
135 136 137 138 139 140 141 142 143

		free += nr_swap_pages;

		/*
		 * Any slabs which are created with the
		 * SLAB_RECLAIM_ACCOUNT flag claim to have contents
		 * which are reclaimable, under pressure.  The dentry
		 * cache and most inode caches should fall into this
		 */
144
		free += global_page_state(NR_SLAB_RECLAIMABLE);
Linus Torvalds's avatar
Linus Torvalds committed
145

146 147 148
		/*
		 * Leave reserved pages. The pages are not for anonymous pages.
		 */
149
		if (free <= totalreserve_pages)
150 151
			goto error;
		else
152
			free -= totalreserve_pages;
153 154 155 156

		/*
		 * Leave the last 3% for root
		 */
Linus Torvalds's avatar
Linus Torvalds committed
157
		if (!cap_sys_admin)
158
			free -= free / 32;
Linus Torvalds's avatar
Linus Torvalds committed
159 160 161

		if (free > pages)
			return 0;
162 163

		goto error;
Linus Torvalds's avatar
Linus Torvalds committed
164 165 166 167 168 169 170 171 172 173 174 175 176
	}

	allowed = (totalram_pages - hugetlb_total_pages())
	       	* sysctl_overcommit_ratio / 100;
	/*
	 * Leave the last 3% for root
	 */
	if (!cap_sys_admin)
		allowed -= allowed / 32;
	allowed += total_swap_pages;

	/* Don't let a single process grow too big:
	   leave 3% of the size of this process for other processes */
Alan Cox's avatar
Alan Cox committed
177 178
	if (mm)
		allowed -= mm->total_vm / 32;
Linus Torvalds's avatar
Linus Torvalds committed
179

180
	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
Linus Torvalds's avatar
Linus Torvalds committed
181
		return 0;
182
error:
Linus Torvalds's avatar
Linus Torvalds committed
183 184 185 186 187 188
	vm_unacct_memory(pages);

	return -ENOMEM;
}

/*
189
 * Requires inode->i_mapping->i_mmap_mutex
Linus Torvalds's avatar
Linus Torvalds committed
190 191 192 193 194
 */
static void __remove_shared_vm_struct(struct vm_area_struct *vma,
		struct file *file, struct address_space *mapping)
{
	if (vma->vm_flags & VM_DENYWRITE)
195
		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
Linus Torvalds's avatar
Linus Torvalds committed
196 197 198 199 200 201 202 203 204 205 206 207
	if (vma->vm_flags & VM_SHARED)
		mapping->i_mmap_writable--;

	flush_dcache_mmap_lock(mapping);
	if (unlikely(vma->vm_flags & VM_NONLINEAR))
		list_del_init(&vma->shared.vm_set.list);
	else
		vma_prio_tree_remove(vma, &mapping->i_mmap);
	flush_dcache_mmap_unlock(mapping);
}

/*
208 209
 * Unlink a file-based vm structure from its prio_tree, to hide
 * vma from rmap and vmtruncate before freeing its page tables.
Linus Torvalds's avatar
Linus Torvalds committed
210
 */
211
void unlink_file_vma(struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
212 213 214 215 216
{
	struct file *file = vma->vm_file;

	if (file) {
		struct address_space *mapping = file->f_mapping;
217
		mutex_lock(&mapping->i_mmap_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
218
		__remove_shared_vm_struct(vma, file, mapping);
219
		mutex_unlock(&mapping->i_mmap_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
220
	}
221 222 223 224 225 226 227 228 229 230
}

/*
 * Close a vm structure and free it, returning the next.
 */
static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
{
	struct vm_area_struct *next = vma->vm_next;

	might_sleep();
Linus Torvalds's avatar
Linus Torvalds committed
231 232
	if (vma->vm_ops && vma->vm_ops->close)
		vma->vm_ops->close(vma);
Matt Helsley's avatar
Matt Helsley committed
233
	if (vma->vm_file) {
234
		fput(vma->vm_file);
Matt Helsley's avatar
Matt Helsley committed
235 236 237
		if (vma->vm_flags & VM_EXECUTABLE)
			removed_exe_file_vma(vma->vm_mm);
	}
238
	mpol_put(vma_policy(vma));
Linus Torvalds's avatar
Linus Torvalds committed
239
	kmem_cache_free(vm_area_cachep, vma);
240
	return next;
Linus Torvalds's avatar
Linus Torvalds committed
241 242
}

243
SYSCALL_DEFINE1(brk, unsigned long, brk)
Linus Torvalds's avatar
Linus Torvalds committed
244 245 246 247
{
	unsigned long rlim, retval;
	unsigned long newbrk, oldbrk;
	struct mm_struct *mm = current->mm;
248
	unsigned long min_brk;
Linus Torvalds's avatar
Linus Torvalds committed
249 250 251

	down_write(&mm->mmap_sem);

252
#ifdef CONFIG_COMPAT_BRK
253 254 255 256 257
	/*
	 * CONFIG_COMPAT_BRK can still be overridden by setting
	 * randomize_va_space to 2, which will still cause mm->start_brk
	 * to be arbitrarily shifted
	 */
258
	if (current->brk_randomized)
259 260 261
		min_brk = mm->start_brk;
	else
		min_brk = mm->end_data;
262 263 264 265
#else
	min_brk = mm->start_brk;
#endif
	if (brk < min_brk)
Linus Torvalds's avatar
Linus Torvalds committed
266
		goto out;
Ram Gupta's avatar
Ram Gupta committed
267 268 269 270 271 272 273

	/*
	 * Check against rlimit here. If this check is done later after the test
	 * of oldbrk with newbrk then it can escape the test and let the data
	 * segment grow beyond its set limit the in case where the limit is
	 * not page aligned -Ram Gupta
	 */
Jiri Slaby's avatar
Jiri Slaby committed
274
	rlim = rlimit(RLIMIT_DATA);
Jiri Kosina's avatar
Jiri Kosina committed
275 276
	if (rlim < RLIM_INFINITY && (brk - mm->start_brk) +
			(mm->end_data - mm->start_data) > rlim)
Ram Gupta's avatar
Ram Gupta committed
277 278
		goto out;

Linus Torvalds's avatar
Linus Torvalds committed
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
	newbrk = PAGE_ALIGN(brk);
	oldbrk = PAGE_ALIGN(mm->brk);
	if (oldbrk == newbrk)
		goto set_brk;

	/* Always allow shrinking brk. */
	if (brk <= mm->brk) {
		if (!do_munmap(mm, newbrk, oldbrk-newbrk))
			goto set_brk;
		goto out;
	}

	/* Check against existing mmap mappings. */
	if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
		goto out;

	/* Ok, looks good - let it rip. */
	if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
		goto out;
set_brk:
	mm->brk = brk;
out:
	retval = mm->brk;
	up_write(&mm->mmap_sem);
	return retval;
}

#ifdef DEBUG_MM_RB
static int browse_rb(struct rb_root *root)
{
	int i = 0, j;
	struct rb_node *nd, *pn = NULL;
	unsigned long prev = 0, pend = 0;

	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
		struct vm_area_struct *vma;
		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
		if (vma->vm_start < prev)
			printk("vm_start %lx prev %lx\n", vma->vm_start, prev), i = -1;
		if (vma->vm_start < pend)
			printk("vm_start %lx pend %lx\n", vma->vm_start, pend);
		if (vma->vm_start > vma->vm_end)
			printk("vm_end %lx < vm_start %lx\n", vma->vm_end, vma->vm_start);
		i++;
		pn = nd;
David Miller's avatar
David Miller committed
324 325
		prev = vma->vm_start;
		pend = vma->vm_end;
Linus Torvalds's avatar
Linus Torvalds committed
326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349
	}
	j = 0;
	for (nd = pn; nd; nd = rb_prev(nd)) {
		j++;
	}
	if (i != j)
		printk("backwards %d, forwards %d\n", j, i), i = 0;
	return i;
}

void validate_mm(struct mm_struct *mm)
{
	int bug = 0;
	int i = 0;
	struct vm_area_struct *tmp = mm->mmap;
	while (tmp) {
		tmp = tmp->vm_next;
		i++;
	}
	if (i != mm->map_count)
		printk("map_count %d vm_next %d\n", mm->map_count, i), bug = 1;
	i = browse_rb(&mm->mm_rb);
	if (i != mm->map_count)
		printk("map_count %d rb %d\n", mm->map_count, i), bug = 1;
350
	BUG_ON(bug);
Linus Torvalds's avatar
Linus Torvalds committed
351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376
}
#else
#define validate_mm(mm) do { } while (0)
#endif

static struct vm_area_struct *
find_vma_prepare(struct mm_struct *mm, unsigned long addr,
		struct vm_area_struct **pprev, struct rb_node ***rb_link,
		struct rb_node ** rb_parent)
{
	struct vm_area_struct * vma;
	struct rb_node ** __rb_link, * __rb_parent, * rb_prev;

	__rb_link = &mm->mm_rb.rb_node;
	rb_prev = __rb_parent = NULL;
	vma = NULL;

	while (*__rb_link) {
		struct vm_area_struct *vma_tmp;

		__rb_parent = *__rb_link;
		vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb);

		if (vma_tmp->vm_end > addr) {
			vma = vma_tmp;
			if (vma_tmp->vm_start <= addr)
377
				break;
Linus Torvalds's avatar
Linus Torvalds committed
378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399
			__rb_link = &__rb_parent->rb_left;
		} else {
			rb_prev = __rb_parent;
			__rb_link = &__rb_parent->rb_right;
		}
	}

	*pprev = NULL;
	if (rb_prev)
		*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
	*rb_link = __rb_link;
	*rb_parent = __rb_parent;
	return vma;
}

void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
		struct rb_node **rb_link, struct rb_node *rb_parent)
{
	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
}

400
static void __vma_link_file(struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
401
{
ZhenwenXu's avatar
ZhenwenXu committed
402
	struct file *file;
Linus Torvalds's avatar
Linus Torvalds committed
403 404 405 406 407 408

	file = vma->vm_file;
	if (file) {
		struct address_space *mapping = file->f_mapping;

		if (vma->vm_flags & VM_DENYWRITE)
409
			atomic_dec(&file->f_path.dentry->d_inode->i_writecount);
Linus Torvalds's avatar
Linus Torvalds committed
410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439
		if (vma->vm_flags & VM_SHARED)
			mapping->i_mmap_writable++;

		flush_dcache_mmap_lock(mapping);
		if (unlikely(vma->vm_flags & VM_NONLINEAR))
			vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear);
		else
			vma_prio_tree_insert(vma, &mapping->i_mmap);
		flush_dcache_mmap_unlock(mapping);
	}
}

static void
__vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
	struct vm_area_struct *prev, struct rb_node **rb_link,
	struct rb_node *rb_parent)
{
	__vma_link_list(mm, vma, prev, rb_parent);
	__vma_link_rb(mm, vma, rb_link, rb_parent);
}

static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma,
			struct vm_area_struct *prev, struct rb_node **rb_link,
			struct rb_node *rb_parent)
{
	struct address_space *mapping = NULL;

	if (vma->vm_file)
		mapping = vma->vm_file->f_mapping;

440
	if (mapping)
441
		mutex_lock(&mapping->i_mmap_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
442 443 444 445 446

	__vma_link(mm, vma, prev, rb_link, rb_parent);
	__vma_link_file(vma);

	if (mapping)
447
		mutex_unlock(&mapping->i_mmap_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
448 449 450 451 452 453

	mm->map_count++;
	validate_mm(mm);
}

/*
454 455
 * Helper for vma_adjust() in the split_vma insert case: insert a vma into the
 * mm's list and rbtree.  It has already been inserted into the prio_tree.
Linus Torvalds's avatar
Linus Torvalds committed
456
 */
ZhenwenXu's avatar
ZhenwenXu committed
457
static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
458
{
ZhenwenXu's avatar
ZhenwenXu committed
459 460
	struct vm_area_struct *__vma, *prev;
	struct rb_node **rb_link, *rb_parent;
Linus Torvalds's avatar
Linus Torvalds committed
461 462

	__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent);
463
	BUG_ON(__vma && __vma->vm_start < vma->vm_end);
Linus Torvalds's avatar
Linus Torvalds committed
464 465 466 467 468 469 470 471
	__vma_link(mm, vma, prev, rb_link, rb_parent);
	mm->map_count++;
}

static inline void
__vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
		struct vm_area_struct *prev)
{
472 473 474 475 476
	struct vm_area_struct *next = vma->vm_next;

	prev->vm_next = next;
	if (next)
		next->vm_prev = prev;
Linus Torvalds's avatar
Linus Torvalds committed
477 478 479 480 481 482 483 484 485 486 487 488
	rb_erase(&vma->vm_rb, &mm->mm_rb);
	if (mm->mmap_cache == vma)
		mm->mmap_cache = prev;
}

/*
 * We cannot adjust vm_start, vm_end, vm_pgoff fields of a vma that
 * is already present in an i_mmap tree without adjusting the tree.
 * The following helper function should be used when such adjustments
 * are necessary.  The "insert" vma (if any) is to be inserted
 * before we drop the necessary locks.
 */
489
int vma_adjust(struct vm_area_struct *vma, unsigned long start,
Linus Torvalds's avatar
Linus Torvalds committed
490 491 492 493 494 495 496
	unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert)
{
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *next = vma->vm_next;
	struct vm_area_struct *importer = NULL;
	struct address_space *mapping = NULL;
	struct prio_tree_root *root = NULL;
497
	struct anon_vma *anon_vma = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
498 499 500 501 502
	struct file *file = vma->vm_file;
	long adjust_next = 0;
	int remove_next = 0;

	if (next && !insert) {
503 504
		struct vm_area_struct *exporter = NULL;

Linus Torvalds's avatar
Linus Torvalds committed
505 506 507 508 509 510 511
		if (end >= next->vm_end) {
			/*
			 * vma expands, overlapping all the next, and
			 * perhaps the one after too (mprotect case 6).
			 */
again:			remove_next = 1 + (end > next->vm_end);
			end = next->vm_end;
512
			exporter = next;
Linus Torvalds's avatar
Linus Torvalds committed
513 514 515 516 517 518 519
			importer = vma;
		} else if (end > next->vm_start) {
			/*
			 * vma expands, overlapping part of the next:
			 * mprotect case 5 shifting the boundary up.
			 */
			adjust_next = (end - next->vm_start) >> PAGE_SHIFT;
520
			exporter = next;
Linus Torvalds's avatar
Linus Torvalds committed
521 522 523 524 525 526 527 528
			importer = vma;
		} else if (end < vma->vm_end) {
			/*
			 * vma shrinks, and !insert tells it's not
			 * split_vma inserting another: so it must be
			 * mprotect case 4 shifting the boundary down.
			 */
			adjust_next = - ((vma->vm_end - end) >> PAGE_SHIFT);
529
			exporter = vma;
Linus Torvalds's avatar
Linus Torvalds committed
530 531 532
			importer = next;
		}

533 534 535 536 537
		/*
		 * Easily overlooked: when mprotect shifts the boundary,
		 * make sure the expanding vma has anon_vma set if the
		 * shrinking vma had, to cover any anon pages imported.
		 */
538 539
		if (exporter && exporter->anon_vma && !importer->anon_vma) {
			if (anon_vma_clone(importer, exporter))
540
				return -ENOMEM;
541
			importer->anon_vma = exporter->anon_vma;
542 543 544
		}
	}

Linus Torvalds's avatar
Linus Torvalds committed
545 546 547 548
	if (file) {
		mapping = file->f_mapping;
		if (!(vma->vm_flags & VM_NONLINEAR))
			root = &mapping->i_mmap;
549
		mutex_lock(&mapping->i_mmap_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
550 551 552 553 554 555 556 557 558 559 560
		if (insert) {
			/*
			 * Put into prio_tree now, so instantiated pages
			 * are visible to arm/parisc __flush_dcache_page
			 * throughout; but we cannot insert into address
			 * space until vma start or end is updated.
			 */
			__vma_link_file(insert);
		}
	}

561 562
	vma_adjust_trans_huge(vma, start, end, adjust_next);

563 564 565 566 567 568
	/*
	 * When changing only vma->vm_end, we don't really need anon_vma
	 * lock. This is a fairly rare case by itself, but the anon_vma
	 * lock may be shared between many sibling processes.  Skipping
	 * the lock for brk adjustments makes a difference sometimes.
	 */
569
	if (vma->anon_vma && (importer || start != vma->vm_start)) {
570 571 572 573
		anon_vma = vma->anon_vma;
		anon_vma_lock(anon_vma);
	}

Linus Torvalds's avatar
Linus Torvalds committed
574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612
	if (root) {
		flush_dcache_mmap_lock(mapping);
		vma_prio_tree_remove(vma, root);
		if (adjust_next)
			vma_prio_tree_remove(next, root);
	}

	vma->vm_start = start;
	vma->vm_end = end;
	vma->vm_pgoff = pgoff;
	if (adjust_next) {
		next->vm_start += adjust_next << PAGE_SHIFT;
		next->vm_pgoff += adjust_next;
	}

	if (root) {
		if (adjust_next)
			vma_prio_tree_insert(next, root);
		vma_prio_tree_insert(vma, root);
		flush_dcache_mmap_unlock(mapping);
	}

	if (remove_next) {
		/*
		 * vma_merge has merged next into vma, and needs
		 * us to remove next before dropping the locks.
		 */
		__vma_unlink(mm, next, vma);
		if (file)
			__remove_shared_vm_struct(next, file, mapping);
	} else if (insert) {
		/*
		 * split_vma has split insert from vma, and needs
		 * us to insert it before dropping the locks
		 * (it may either follow vma or precede it).
		 */
		__insert_vm_struct(mm, insert);
	}

613 614
	if (anon_vma)
		anon_vma_unlock(anon_vma);
Linus Torvalds's avatar
Linus Torvalds committed
615
	if (mapping)
616
		mutex_unlock(&mapping->i_mmap_mutex);
Linus Torvalds's avatar
Linus Torvalds committed
617 618

	if (remove_next) {
Matt Helsley's avatar
Matt Helsley committed
619
		if (file) {
Linus Torvalds's avatar
Linus Torvalds committed
620
			fput(file);
Matt Helsley's avatar
Matt Helsley committed
621 622 623
			if (next->vm_flags & VM_EXECUTABLE)
				removed_exe_file_vma(mm);
		}
624 625
		if (next->anon_vma)
			anon_vma_merge(vma, next);
Linus Torvalds's avatar
Linus Torvalds committed
626
		mm->map_count--;
627
		mpol_put(vma_policy(next));
Linus Torvalds's avatar
Linus Torvalds committed
628 629 630 631 632 633 634 635 636 637 638 639 640
		kmem_cache_free(vm_area_cachep, next);
		/*
		 * In mprotect's case 6 (see comments on vma_merge),
		 * we must remove another next too. It would clutter
		 * up the code too much to do both in one go.
		 */
		if (remove_next == 2) {
			next = vma->vm_next;
			goto again;
		}
	}

	validate_mm(mm);
641 642

	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
643 644 645 646 647 648 649 650 651
}

/*
 * If the vma has a ->close operation then the driver probably needs to release
 * per-vma resources, so we don't attempt to merge those.
 */
static inline int is_mergeable_vma(struct vm_area_struct *vma,
			struct file *file, unsigned long vm_flags)
{
Hugh Dickins's avatar
Hugh Dickins committed
652 653
	/* VM_CAN_NONLINEAR may get set later by f_op->mmap() */
	if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR)
Linus Torvalds's avatar
Linus Torvalds committed
654 655 656 657 658 659 660 661 662
		return 0;
	if (vma->vm_file != file)
		return 0;
	if (vma->vm_ops && vma->vm_ops->close)
		return 0;
	return 1;
}

static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1,
Shaohua Li's avatar
Shaohua Li committed
663 664
					struct anon_vma *anon_vma2,
					struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
665
{
Shaohua Li's avatar
Shaohua Li committed
666 667 668 669 670 671 672 673
	/*
	 * The list_is_singular() test is to avoid merging VMA cloned from
	 * parents. This can improve scalability caused by anon_vma lock.
	 */
	if ((!anon_vma1 || !anon_vma2) && (!vma ||
		list_is_singular(&vma->anon_vma_chain)))
		return 1;
	return anon_vma1 == anon_vma2;
Linus Torvalds's avatar
Linus Torvalds committed
674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691
}

/*
 * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
 * in front of (at a lower virtual address and file offset than) the vma.
 *
 * We cannot merge two vmas if they have differently assigned (non-NULL)
 * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
 *
 * We don't check here for the merged mmap wrapping around the end of pagecache
 * indices (16TB on ia32) because do_mmap_pgoff() does not permit mmap's which
 * wrap, nor mmaps which cover the final page at index -1UL.
 */
static int
can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
{
	if (is_mergeable_vma(vma, file, vm_flags) &&
Shaohua Li's avatar
Shaohua Li committed
692
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
Linus Torvalds's avatar
Linus Torvalds committed
693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710
		if (vma->vm_pgoff == vm_pgoff)
			return 1;
	}
	return 0;
}

/*
 * Return true if we can merge this (vm_flags,anon_vma,file,vm_pgoff)
 * beyond (at a higher virtual address and file offset than) the vma.
 *
 * We cannot merge two vmas if they have differently assigned (non-NULL)
 * anon_vmas, nor if same anon_vma is assigned but offsets incompatible.
 */
static int
can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
	struct anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff)
{
	if (is_mergeable_vma(vma, file, vm_flags) &&
Shaohua Li's avatar
Shaohua Li committed
711
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
Linus Torvalds's avatar
Linus Torvalds committed
712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756
		pgoff_t vm_pglen;
		vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
		if (vma->vm_pgoff + vm_pglen == vm_pgoff)
			return 1;
	}
	return 0;
}

/*
 * Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
 * whether that can be merged with its predecessor or its successor.
 * Or both (it neatly fills a hole).
 *
 * In most cases - when called for mmap, brk or mremap - [addr,end) is
 * certain not to be mapped by the time vma_merge is called; but when
 * called for mprotect, it is certain to be already mapped (either at
 * an offset within prev, or at the start of next), and the flags of
 * this area are about to be changed to vm_flags - and the no-change
 * case has already been eliminated.
 *
 * The following mprotect cases have to be considered, where AAAA is
 * the area passed down from mprotect_fixup, never extending beyond one
 * vma, PPPPPP is the prev vma specified, and NNNNNN the next vma after:
 *
 *     AAAA             AAAA                AAAA          AAAA
 *    PPPPPPNNNNNN    PPPPPPNNNNNN    PPPPPPNNNNNN    PPPPNNNNXXXX
 *    cannot merge    might become    might become    might become
 *                    PPNNNNNNNNNN    PPPPPPPPPPNN    PPPPPPPPPPPP 6 or
 *    mmap, brk or    case 4 below    case 5 below    PPPPPPPPXXXX 7 or
 *    mremap move:                                    PPPPNNNNNNNN 8
 *        AAAA
 *    PPPP    NNNN    PPPPPPPPPPPP    PPPPPPPPNNNN    PPPPNNNNNNNN
 *    might become    case 1 below    case 2 below    case 3 below
 *
 * Odd one out? Case 8, because it extends NNNN but needs flags of XXXX:
 * mprotect_fixup updates vm_flags & vm_page_prot on successful return.
 */
struct vm_area_struct *vma_merge(struct mm_struct *mm,
			struct vm_area_struct *prev, unsigned long addr,
			unsigned long end, unsigned long vm_flags,
		     	struct anon_vma *anon_vma, struct file *file,
			pgoff_t pgoff, struct mempolicy *policy)
{
	pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
	struct vm_area_struct *area, *next;
757
	int err;
Linus Torvalds's avatar
Linus Torvalds committed
758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788

	/*
	 * We later require that vma->vm_flags == vm_flags,
	 * so this tests vma->vm_flags & VM_SPECIAL, too.
	 */
	if (vm_flags & VM_SPECIAL)
		return NULL;

	if (prev)
		next = prev->vm_next;
	else
		next = mm->mmap;
	area = next;
	if (next && next->vm_end == end)		/* cases 6, 7, 8 */
		next = next->vm_next;

	/*
	 * Can it merge with the predecessor?
	 */
	if (prev && prev->vm_end == addr &&
  			mpol_equal(vma_policy(prev), policy) &&
			can_vma_merge_after(prev, vm_flags,
						anon_vma, file, pgoff)) {
		/*
		 * OK, it can.  Can we now merge in the successor as well?
		 */
		if (next && end == next->vm_start &&
				mpol_equal(policy, vma_policy(next)) &&
				can_vma_merge_before(next, vm_flags,
					anon_vma, file, pgoff+pglen) &&
				is_mergeable_anon_vma(prev->anon_vma,
Shaohua Li's avatar
Shaohua Li committed
789
						      next->anon_vma, NULL)) {
Linus Torvalds's avatar
Linus Torvalds committed
790
							/* cases 1, 6 */
791
			err = vma_adjust(prev, prev->vm_start,
Linus Torvalds's avatar
Linus Torvalds committed
792 793
				next->vm_end, prev->vm_pgoff, NULL);
		} else					/* cases 2, 5, 7 */
794
			err = vma_adjust(prev, prev->vm_start,
Linus Torvalds's avatar
Linus Torvalds committed
795
				end, prev->vm_pgoff, NULL);
796 797
		if (err)
			return NULL;
Andrea Arcangeli's avatar
Andrea Arcangeli committed
798
		khugepaged_enter_vma_merge(prev);
Linus Torvalds's avatar
Linus Torvalds committed
799 800 801 802 803 804 805 806 807 808 809
		return prev;
	}

	/*
	 * Can this new request be merged in front of next?
	 */
	if (next && end == next->vm_start &&
 			mpol_equal(policy, vma_policy(next)) &&
			can_vma_merge_before(next, vm_flags,
					anon_vma, file, pgoff+pglen)) {
		if (prev && addr < prev->vm_end)	/* case 4 */
810
			err = vma_adjust(prev, prev->vm_start,
Linus Torvalds's avatar
Linus Torvalds committed
811 812
				addr, prev->vm_pgoff, NULL);
		else					/* cases 3, 8 */
813
			err = vma_adjust(area, addr, next->vm_end,
Linus Torvalds's avatar
Linus Torvalds committed
814
				next->vm_pgoff - pglen, NULL);
815 816
		if (err)
			return NULL;
Andrea Arcangeli's avatar
Andrea Arcangeli committed
817
		khugepaged_enter_vma_merge(area);
Linus Torvalds's avatar
Linus Torvalds committed
818 819 820 821 822 823
		return area;
	}

	return NULL;
}

824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878
/*
 * Rough compatbility check to quickly see if it's even worth looking
 * at sharing an anon_vma.
 *
 * They need to have the same vm_file, and the flags can only differ
 * in things that mprotect may change.
 *
 * NOTE! The fact that we share an anon_vma doesn't _have_ to mean that
 * we can merge the two vma's. For example, we refuse to merge a vma if
 * there is a vm_ops->close() function, because that indicates that the
 * driver is doing some kind of reference counting. But that doesn't
 * really matter for the anon_vma sharing case.
 */
static int anon_vma_compatible(struct vm_area_struct *a, struct vm_area_struct *b)
{
	return a->vm_end == b->vm_start &&
		mpol_equal(vma_policy(a), vma_policy(b)) &&
		a->vm_file == b->vm_file &&
		!((a->vm_flags ^ b->vm_flags) & ~(VM_READ|VM_WRITE|VM_EXEC)) &&
		b->vm_pgoff == a->vm_pgoff + ((b->vm_start - a->vm_start) >> PAGE_SHIFT);
}

/*
 * Do some basic sanity checking to see if we can re-use the anon_vma
 * from 'old'. The 'a'/'b' vma's are in VM order - one of them will be
 * the same as 'old', the other will be the new one that is trying
 * to share the anon_vma.
 *
 * NOTE! This runs with mm_sem held for reading, so it is possible that
 * the anon_vma of 'old' is concurrently in the process of being set up
 * by another page fault trying to merge _that_. But that's ok: if it
 * is being set up, that automatically means that it will be a singleton
 * acceptable for merging, so we can do all of this optimistically. But
 * we do that ACCESS_ONCE() to make sure that we never re-load the pointer.
 *
 * IOW: that the "list_is_singular()" test on the anon_vma_chain only
 * matters for the 'stable anon_vma' case (ie the thing we want to avoid
 * is to return an anon_vma that is "complex" due to having gone through
 * a fork).
 *
 * We also make sure that the two vma's are compatible (adjacent,
 * and with the same memory policies). That's all stable, even with just
 * a read lock on the mm_sem.
 */
static struct anon_vma *reusable_anon_vma(struct vm_area_struct *old, struct vm_area_struct *a, struct vm_area_struct *b)
{
	if (anon_vma_compatible(a, b)) {
		struct anon_vma *anon_vma = ACCESS_ONCE(old->anon_vma);

		if (anon_vma && list_is_singular(&old->anon_vma_chain))
			return anon_vma;
	}
	return NULL;
}

Linus Torvalds's avatar
Linus Torvalds committed
879 880 881 882 883 884 885 886 887 888
/*
 * find_mergeable_anon_vma is used by anon_vma_prepare, to check
 * neighbouring vmas for a suitable anon_vma, before it goes off
 * to allocate a new anon_vma.  It checks because a repetitive
 * sequence of mprotects and faults may otherwise lead to distinct
 * anon_vmas being allocated, preventing vma merge in subsequent
 * mprotect.
 */
struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *vma)
{
889
	struct anon_vma *anon_vma;
Linus Torvalds's avatar
Linus Torvalds committed
890 891 892 893 894 895
	struct vm_area_struct *near;

	near = vma->vm_next;
	if (!near)
		goto try_prev;

896 897 898
	anon_vma = reusable_anon_vma(near, vma, near);
	if (anon_vma)
		return anon_vma;
Linus Torvalds's avatar
Linus Torvalds committed
899
try_prev:
900
	near = vma->vm_prev;
Linus Torvalds's avatar
Linus Torvalds committed
901 902 903
	if (!near)
		goto none;

904 905 906
	anon_vma = reusable_anon_vma(near, near, vma);
	if (anon_vma)
		return anon_vma;
Linus Torvalds's avatar
Linus Torvalds committed
907 908 909 910 911 912 913 914 915 916 917 918 919
none:
	/*
	 * There's no absolute need to look only at touching neighbours:
	 * we could search further afield for "compatible" anon_vmas.
	 * But it would probably just be a waste of time searching,
	 * or lead to too many vmas hanging off the same anon_vma.
	 * We're trying to allow mprotect remerging later on,
	 * not trying to minimize memory used for anon_vmas.
	 */
	return NULL;
}

#ifdef CONFIG_PROC_FS
920
void vm_stat_account(struct mm_struct *mm, unsigned long flags,
Linus Torvalds's avatar
Linus Torvalds committed
921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936
						struct file *file, long pages)
{
	const unsigned long stack_flags
		= VM_STACK_FLAGS & (VM_GROWSUP|VM_GROWSDOWN);

	if (file) {
		mm->shared_vm += pages;
		if ((flags & (VM_EXEC|VM_WRITE)) == VM_EXEC)
			mm->exec_vm += pages;
	} else if (flags & stack_flags)
		mm->stack_vm += pages;
	if (flags & (VM_RESERVED|VM_IO))
		mm->reserved_vm += pages;
}
#endif /* CONFIG_PROC_FS */

Al Viro's avatar
Al Viro committed
937 938 939 940 941 942 943 944 945 946 947 948 949
/*
 * If a hint addr is less than mmap_min_addr change hint to be as
 * low as possible but still greater than mmap_min_addr
 */
static inline unsigned long round_hint_to_min(unsigned long hint)
{
	hint &= PAGE_MASK;
	if (((void *)hint != NULL) &&
	    (hint < mmap_min_addr))
		return PAGE_ALIGN(mmap_min_addr);
	return hint;
}

Linus Torvalds's avatar
Linus Torvalds committed
950
/*
951
 * The caller must hold down_write(&current->mm->mmap_sem).
Linus Torvalds's avatar
Linus Torvalds committed
952 953
 */

ZhenwenXu's avatar
ZhenwenXu committed
954
unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
Linus Torvalds's avatar
Linus Torvalds committed
955 956 957 958 959
			unsigned long len, unsigned long prot,
			unsigned long flags, unsigned long pgoff)
{
	struct mm_struct * mm = current->mm;
	struct inode *inode;
960
	vm_flags_t vm_flags;
Linus Torvalds's avatar
Linus Torvalds committed
961
	int error;
Miklos Szeredi's avatar
Miklos Szeredi committed
962
	unsigned long reqprot = prot;
Linus Torvalds's avatar
Linus Torvalds committed
963 964 965 966 967 968 969 970

	/*
	 * Does the application expect PROT_READ to imply PROT_EXEC?
	 *
	 * (the exception is when the underlying filesystem is noexec
	 *  mounted, in which case we dont add PROT_EXEC.)
	 */
	if ((prot & PROT_READ) && (current->personality & READ_IMPLIES_EXEC))
971
		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
Linus Torvalds's avatar
Linus Torvalds committed
972 973 974 975 976
			prot |= PROT_EXEC;

	if (!len)
		return -EINVAL;

977 978 979
	if (!(flags & MAP_FIXED))
		addr = round_hint_to_min(addr);

Linus Torvalds's avatar
Linus Torvalds committed
980 981
	/* Careful about overflows.. */
	len = PAGE_ALIGN(len);
982
	if (!len)
Linus Torvalds's avatar
Linus Torvalds committed
983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006
		return -ENOMEM;

	/* offset overflow? */
	if ((pgoff + (len >> PAGE_SHIFT)) < pgoff)
               return -EOVERFLOW;

	/* Too many mappings? */
	if (mm->map_count > sysctl_max_map_count)
		return -ENOMEM;

	/* Obtain the address to map to. we verify (or select) it and ensure
	 * that it represents a valid section of the address space.
	 */
	addr = get_unmapped_area(file, addr, len, pgoff, flags);
	if (addr & ~PAGE_MASK)
		return addr;

	/* Do simple checking here so the lower-level routines won't have
	 * to. we assume access permissions have been handled by the open
	 * of the memory object, so we don't do any here.
	 */
	vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags) |
			mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;

Huang Shijie's avatar
Huang Shijie committed
1007
	if (flags & MAP_LOCKED)
Linus Torvalds's avatar
Linus Torvalds committed
1008 1009
		if (!can_do_mlock())
			return -EPERM;
1010

Linus Torvalds's avatar
Linus Torvalds committed
1011 1012 1013
	/* mlock MCL_FUTURE? */
	if (vm_flags & VM_LOCKED) {
		unsigned long locked, lock_limit;
1014 1015
		locked = len >> PAGE_SHIFT;
		locked += mm->locked_vm;
Jiri Slaby's avatar
Jiri Slaby committed
1016
		lock_limit = rlimit(RLIMIT_MEMLOCK);
1017
		lock_limit >>= PAGE_SHIFT;
Linus Torvalds's avatar
Linus Torvalds committed
1018 1019 1020 1021
		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
			return -EAGAIN;
	}

1022
	inode = file ? file->f_path.dentry->d_inode : NULL;
Linus Torvalds's avatar
Linus Torvalds committed
1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050

	if (file) {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
				return -EACCES;

			/*
			 * Make sure we don't allow writing to an append-only
			 * file..
			 */
			if (IS_APPEND(inode) && (file->f_mode & FMODE_WRITE))
				return -EACCES;

			/*
			 * Make sure there are no mandatory locks on the file.
			 */
			if (locks_verify_locked(inode))
				return -EAGAIN;

			vm_flags |= VM_SHARED | VM_MAYSHARE;
			if (!(file->f_mode & FMODE_WRITE))
				vm_flags &= ~(VM_MAYWRITE | VM_SHARED);

			/* fall through */
		case MAP_PRIVATE:
			if (!(file->f_mode & FMODE_READ))
				return -EACCES;
1051
			if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
Linus Torvalds's avatar
Linus Torvalds committed
1052 1053 1054 1055 1056 1057 1058
				if (vm_flags & VM_EXEC)
					return -EPERM;
				vm_flags &= ~VM_MAYEXEC;
			}

			if (!file->f_op || !file->f_op->mmap)
				return -ENODEV;
Linus Torvalds's avatar
Linus Torvalds committed
1059 1060 1061 1062 1063 1064 1065 1066
			break;

		default:
			return -EINVAL;
		}
	} else {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
1067 1068 1069 1070
			/*
			 * Ignore pgoff.
			 */
			pgoff = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083
			vm_flags |= VM_SHARED | VM_MAYSHARE;
			break;
		case MAP_PRIVATE:
			/*
			 * Set pgoff according to addr for anon_vma.
			 */
			pgoff = addr >> PAGE_SHIFT;
			break;
		default:
			return -EINVAL;
		}
	}

1084
	error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1085 1086
	if (error)
		return error;
1087

1088
	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
Miklos Szeredi's avatar
Miklos Szeredi committed
1089 1090 1091
}
EXPORT_SYMBOL(do_mmap_pgoff);

1092 1093 1094 1095 1096 1097 1098 1099
SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
		unsigned long, prot, unsigned long, flags,
		unsigned long, fd, unsigned long, pgoff)
{
	struct file *file = NULL;
	unsigned long retval = -EBADF;

	if (!(flags & MAP_ANONYMOUS)) {
Al Viro's avatar
Al Viro committed
1100
		audit_mmap_fd(fd, flags);
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113
		if (unlikely(flags & MAP_HUGETLB))
			return -EINVAL;
		file = fget(fd);
		if (!file)
			goto out;
	} else if (flags & MAP_HUGETLB) {
		struct user_struct *user = NULL;
		/*
		 * VM_NORESERVE is used because the reservations will be
		 * taken when vm_ops->mmap() is called
		 * A dummy user value is used because we are not locking
		 * memory so no accounting is necessary
		 */
1114 1115 1116
		file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
						VM_NORESERVE, &user,
						HUGETLB_ANONHUGE_INODE);
1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132
		if (IS_ERR(file))
			return PTR_ERR(file);
	}

	flags &= ~(MAP_EXECUTABLE | MAP_DENYWRITE);

	down_write(&current->mm->mmap_sem);
	retval = do_mmap_pgoff(file, addr, len, prot, flags, pgoff);
	up_write(&current->mm->mmap_sem);

	if (file)
		fput(file);
out:
	return retval;
}

Christoph Hellwig's avatar
Christoph Hellwig committed
1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
#ifdef __ARCH_WANT_SYS_OLD_MMAP
struct mmap_arg_struct {
	unsigned long addr;
	unsigned long len;
	unsigned long prot;
	unsigned long flags;
	unsigned long fd;
	unsigned long offset;
};

SYSCALL_DEFINE1(old_mmap, struct mmap_arg_struct __user *, arg)
{
	struct mmap_arg_struct a;

	if (copy_from_user(&a, arg, sizeof(a)))
		return -EFAULT;
	if (a.offset & ~PAGE_MASK)
		return -EINVAL;

	return sys_mmap_pgoff(a.addr, a.len, a.prot, a.flags, a.fd,
			      a.offset >> PAGE_SHIFT);
}
#endif /* __ARCH_WANT_SYS_OLD_MMAP */

Alexey Dobriyan's avatar
Alexey Dobriyan committed
1157 1158 1159 1160 1161 1162 1163 1164
/*
 * Some shared mappigns will want the pages marked read-only
 * to track write events. If so, we'll downgrade vm_page_prot
 * to the private version (using protection_map[] without the
 * VM_SHARED bit).
 */
int vma_wants_writenotify(struct vm_area_struct *vma)
{
1165
	vm_flags_t vm_flags = vma->vm_flags;
Alexey Dobriyan's avatar
Alexey Dobriyan committed
1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176

	/* If it was private or non-writable, the write bit is already clear */
	if ((vm_flags & (VM_WRITE|VM_SHARED)) != ((VM_WRITE|VM_SHARED)))
		return 0;

	/* The backer wishes to know when pages are first written to? */
	if (vma->vm_ops && vma->vm_ops->page_mkwrite)
		return 1;

	/* The open routine did something to the protections already? */
	if (pgprot_val(vma->vm_page_prot) !=
1177
	    pgprot_val(vm_get_page_prot(vm_flags)))
Alexey Dobriyan's avatar
Alexey Dobriyan committed
1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188
		return 0;

	/* Specialty mapping? */
	if (vm_flags & (VM_PFNMAP|VM_INSERTPAGE))
		return 0;

	/* Can the mapping track the dirty pages? */
	return vma->vm_file && vma->vm_file->f_mapping &&
		mapping_cap_account_dirty(vma->vm_file->f_mapping);
}

1189 1190
/*
 * We account for memory if it's a private writeable mapping,
1191
 * not hugepages and VM_NORESERVE wasn't set.
1192
 */
1193
static inline int accountable_mapping(struct file *file, vm_flags_t vm_flags)
1194
{
1195 1196 1197 1198 1199 1200 1201
	/*
	 * hugetlb has its own accounting separate from the core VM
	 * VM_HUGETLB may not be set yet so we cannot check for that flag.
	 */
	if (file && is_file_hugepages(file))
		return 0;

1202 1203 1204
	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
}

Miklos Szeredi's avatar
Miklos Szeredi committed
1205 1206
unsigned long mmap_region(struct file *file, unsigned long addr,
			  unsigned long len, unsigned long flags,
1207
			  vm_flags_t vm_flags, unsigned long pgoff)
Miklos Szeredi's avatar
Miklos Szeredi committed
1208 1209 1210 1211 1212 1213 1214 1215 1216
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma, *prev;
	int correct_wcount = 0;
	int error;
	struct rb_node **rb_link, *rb_parent;
	unsigned long charged = 0;
	struct inode *inode =  file ? file->f_path.dentry->d_inode : NULL;

Linus Torvalds's avatar
Linus Torvalds committed
1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227
	/* Clear old maps */
	error = -ENOMEM;
munmap_back:
	vma = find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
	if (vma && vma->vm_start < addr + len) {
		if (do_munmap(mm, addr, len))
			return -ENOMEM;
		goto munmap_back;
	}

	/* Check against address space limit. */
akpm@osdl.org's avatar
akpm@osdl.org committed
1228
	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
Linus Torvalds's avatar
Linus Torvalds committed
1229 1230
		return -ENOMEM;

1231 1232
	/*
	 * Set 'VM_NORESERVE' if we should not account for the
1233
	 * memory use of this mapping.
1234
	 */
1235 1236 1237 1238 1239 1240 1241 1242 1243
	if ((flags & MAP_NORESERVE)) {
		/* We honor MAP_NORESERVE if allowed to overcommit */
		if (sysctl_overcommit_memory != OVERCOMMIT_NEVER)
			vm_flags |= VM_NORESERVE;

		/* hugetlb applies strict overcommit unless MAP_NORESERVE */
		if (file && is_file_hugepages(file))
			vm_flags |= VM_NORESERVE;
	}
1244

1245 1246 1247
	/*
	 * Private writable mapping: check memory availability
	 */
1248
	if (accountable_mapping(file, vm_flags)) {
1249
		charged = len >> PAGE_SHIFT;
1250
		if (security_vm_enough_memory_mm(mm, charged))
1251 1252
			return -ENOMEM;
		vm_flags |= VM_ACCOUNT;
Linus Torvalds's avatar
Linus Torvalds committed
1253 1254 1255
	}

	/*
1256
	 * Can we just expand an old mapping?
Linus Torvalds's avatar
Linus Torvalds committed
1257
	 */
1258 1259 1260
	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
	if (vma)
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed
1261 1262 1263 1264 1265 1266

	/*
	 * Determine the object being mapped and call the appropriate
	 * specific mapper. the address has already been validated, but
	 * not unmapped, but the maps are removed from the list.
	 */
1267
	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
Linus Torvalds's avatar
Linus Torvalds committed
1268 1269 1270 1271 1272 1273 1274 1275 1276
	if (!vma) {
		error = -ENOMEM;
		goto unacct_error;
	}

	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_flags = vm_flags;
1277
	vma->vm_page_prot = vm_get_page_prot(vm_flags);
Linus Torvalds's avatar
Linus Torvalds committed
1278
	vma->vm_pgoff = pgoff;
1279
	INIT_LIST_HEAD(&vma->anon_vma_chain);
Linus Torvalds's avatar
Linus Torvalds committed
1280

1281 1282
	error = -EINVAL;	/* when rejecting VM_GROWSDOWN|VM_GROWSUP */

Linus Torvalds's avatar
Linus Torvalds committed
1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296
	if (file) {
		if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
			goto free_vma;
		if (vm_flags & VM_DENYWRITE) {
			error = deny_write_access(file);
			if (error)
				goto free_vma;
			correct_wcount = 1;
		}
		vma->vm_file = file;
		get_file(file);
		error = file->f_op->mmap(file, vma);
		if (error)
			goto unmap_and_free_vma;
Matt Helsley's avatar
Matt Helsley committed
1297 1298
		if (vm_flags & VM_EXECUTABLE)
			added_exe_file_vma(mm);
1299 1300 1301 1302 1303 1304 1305 1306 1307

		/* Can addr have changed??
		 *
		 * Answer: Yes, several device drivers can do it in their
		 *         f_op->mmap method. -DaveM
		 */
		addr = vma->vm_start;
		pgoff = vma->vm_pgoff;
		vm_flags = vma->vm_flags;
Linus Torvalds's avatar
Linus Torvalds committed
1308
	} else if (vm_flags & VM_SHARED) {
1309 1310
		if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP)))
			goto free_vma;
Linus Torvalds's avatar
Linus Torvalds committed
1311 1312 1313 1314 1315
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	}

1316 1317 1318 1319 1320 1321 1322 1323 1324 1325
	if (vma_wants_writenotify(vma)) {
		pgprot_t pprot = vma->vm_page_prot;

		/* Can vma->vm_page_prot have changed??
		 *
		 * Answer: Yes, drivers may have changed it in their
		 *         f_op->mmap method.
		 *
		 * Ensures that vmas marked as uncached stay that way.
		 */
1326
		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
1327 1328 1329
		if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
	}
1330

1331 1332
	vma_link(mm, vma, prev, rb_link, rb_parent);
	file = vma->vm_file;
1333 1334 1335 1336 1337

	/* Once vma denies write, undo our temporary denial count */
	if (correct_wcount)
		atomic_inc(&inode->i_writecount);
out:
1338
	perf_event_mmap(vma);
Peter Zijlstra's avatar