mmap.c 70 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 25 26 27 28
#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>
#include <linux/module.h>
#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);

Linus Torvalds's avatar
Linus Torvalds committed
87 88
int sysctl_overcommit_memory = OVERCOMMIT_GUESS;  /* heuristic overcommit */
int sysctl_overcommit_ratio = 50;	/* default is 50% */
89
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
90
struct percpu_counter vm_committed_as;
Linus Torvalds's avatar
Linus Torvalds committed
91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107

/*
 * 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.
 */
108
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
Linus Torvalds's avatar
Linus Torvalds committed
109 110 111 112 113 114 115 116 117 118 119 120 121 122
{
	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) {
		unsigned long n;

123
		free = global_page_state(NR_FILE_PAGES);
Linus Torvalds's avatar
Linus Torvalds committed
124 125 126 127 128 129 130 131
		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
		 */
132
		free += global_page_state(NR_SLAB_RECLAIMABLE);
Linus Torvalds's avatar
Linus Torvalds committed
133 134 135 136 137 138 139 140 141 142 143 144 145 146 147

		/*
		 * Leave the last 3% for root
		 */
		if (!cap_sys_admin)
			free -= free / 32;

		if (free > pages)
			return 0;

		/*
		 * nr_free_pages() is very expensive on large systems,
		 * only call if we're about to fail.
		 */
		n = nr_free_pages();
148 149 150 151 152 153 154 155 156 157 158 159

		/*
		 * Leave reserved pages. The pages are not for anonymous pages.
		 */
		if (n <= totalreserve_pages)
			goto error;
		else
			n -= totalreserve_pages;

		/*
		 * Leave the last 3% for root
		 */
Linus Torvalds's avatar
Linus Torvalds committed
160 161 162 163 164 165
		if (!cap_sys_admin)
			n -= n / 32;
		free += n;

		if (free > pages)
			return 0;
166 167

		goto error;
Linus Torvalds's avatar
Linus Torvalds committed
168 169 170 171 172 173 174 175 176 177 178 179 180
	}

	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
181 182
	if (mm)
		allowed -= mm->total_vm / 32;
Linus Torvalds's avatar
Linus Torvalds committed
183

184
	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
Linus Torvalds's avatar
Linus Torvalds committed
185
		return 0;
186
error:
Linus Torvalds's avatar
Linus Torvalds committed
187 188 189 190 191 192 193 194 195 196 197 198
	vm_unacct_memory(pages);

	return -ENOMEM;
}

/*
 * Requires inode->i_mapping->i_mmap_lock
 */
static void __remove_shared_vm_struct(struct vm_area_struct *vma,
		struct file *file, struct address_space *mapping)
{
	if (vma->vm_flags & VM_DENYWRITE)
199
		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
Linus Torvalds's avatar
Linus Torvalds committed
200 201 202 203 204 205 206 207 208 209 210 211
	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);
}

/*
212 213
 * 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
214
 */
215
void unlink_file_vma(struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
216 217 218 219 220 221 222 223 224
{
	struct file *file = vma->vm_file;

	if (file) {
		struct address_space *mapping = file->f_mapping;
		spin_lock(&mapping->i_mmap_lock);
		__remove_shared_vm_struct(vma, file, mapping);
		spin_unlock(&mapping->i_mmap_lock);
	}
225 226 227 228 229 230 231 232 233 234
}

/*
 * 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
235 236
	if (vma->vm_ops && vma->vm_ops->close)
		vma->vm_ops->close(vma);
Matt Helsley's avatar
Matt Helsley committed
237
	if (vma->vm_file) {
238
		fput(vma->vm_file);
Matt Helsley's avatar
Matt Helsley committed
239 240 241
		if (vma->vm_flags & VM_EXECUTABLE)
			removed_exe_file_vma(vma->vm_mm);
	}
242
	mpol_put(vma_policy(vma));
Linus Torvalds's avatar
Linus Torvalds committed
243
	kmem_cache_free(vm_area_cachep, vma);
244
	return next;
Linus Torvalds's avatar
Linus Torvalds committed
245 246
}

247
SYSCALL_DEFINE1(brk, unsigned long, brk)
Linus Torvalds's avatar
Linus Torvalds committed
248 249 250 251
{
	unsigned long rlim, retval;
	unsigned long newbrk, oldbrk;
	struct mm_struct *mm = current->mm;
252
	unsigned long min_brk;
Linus Torvalds's avatar
Linus Torvalds committed
253 254 255

	down_write(&mm->mmap_sem);

256
#ifdef CONFIG_COMPAT_BRK
257 258 259 260 261 262 263 264 265
	/*
	 * 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
	 */
	if (mm->start_brk > PAGE_ALIGN(mm->end_data))
		min_brk = mm->start_brk;
	else
		min_brk = mm->end_data;
266 267 268 269
#else
	min_brk = mm->start_brk;
#endif
	if (brk < min_brk)
Linus Torvalds's avatar
Linus Torvalds committed
270
		goto out;
Ram Gupta's avatar
Ram Gupta committed
271 272 273 274 275 276 277

	/*
	 * 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
278
	rlim = rlimit(RLIMIT_DATA);
Jiri Kosina's avatar
Jiri Kosina committed
279 280
	if (rlim < RLIM_INFINITY && (brk - mm->start_brk) +
			(mm->end_data - mm->start_data) > rlim)
Ram Gupta's avatar
Ram Gupta committed
281 282
		goto out;

Linus Torvalds's avatar
Linus Torvalds committed
283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327
	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
328 329
		prev = vma->vm_start;
		pend = vma->vm_end;
Linus Torvalds's avatar
Linus Torvalds committed
330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353
	}
	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;
354
	BUG_ON(bug);
Linus Torvalds's avatar
Linus Torvalds committed
355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380
}
#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)
381
				break;
Linus Torvalds's avatar
Linus Torvalds committed
382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400
			__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;
}

static inline void
__vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
		struct vm_area_struct *prev, struct rb_node *rb_parent)
{
401 402 403
	struct vm_area_struct *next;

	vma->vm_prev = prev;
Linus Torvalds's avatar
Linus Torvalds committed
404
	if (prev) {
405
		next = prev->vm_next;
Linus Torvalds's avatar
Linus Torvalds committed
406 407 408 409
		prev->vm_next = vma;
	} else {
		mm->mmap = vma;
		if (rb_parent)
410
			next = rb_entry(rb_parent,
Linus Torvalds's avatar
Linus Torvalds committed
411 412
					struct vm_area_struct, vm_rb);
		else
413
			next = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
414
	}
415 416 417
	vma->vm_next = next;
	if (next)
		next->vm_prev = vma;
Linus Torvalds's avatar
Linus Torvalds committed
418 419 420 421 422 423 424 425 426
}

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);
}

427
static void __vma_link_file(struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
428
{
ZhenwenXu's avatar
ZhenwenXu committed
429
	struct file *file;
Linus Torvalds's avatar
Linus Torvalds committed
430 431 432 433 434 435

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

		if (vma->vm_flags & VM_DENYWRITE)
436
			atomic_dec(&file->f_path.dentry->d_inode->i_writecount);
Linus Torvalds's avatar
Linus Torvalds committed
437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486
		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;

	if (mapping) {
		spin_lock(&mapping->i_mmap_lock);
		vma->vm_truncate_count = mapping->truncate_count;
	}

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

	if (mapping)
		spin_unlock(&mapping->i_mmap_lock);

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

/*
 * Helper for vma_adjust in the split_vma insert case:
 * insert vm structure into list and rbtree and anon_vma,
 * but it has already been inserted into prio_tree earlier.
 */
ZhenwenXu's avatar
ZhenwenXu committed
487
static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
Linus Torvalds's avatar
Linus Torvalds committed
488
{
ZhenwenXu's avatar
ZhenwenXu committed
489 490
	struct vm_area_struct *__vma, *prev;
	struct rb_node **rb_link, *rb_parent;
Linus Torvalds's avatar
Linus Torvalds committed
491 492

	__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent);
493
	BUG_ON(__vma && __vma->vm_start < vma->vm_end);
Linus Torvalds's avatar
Linus Torvalds committed
494 495 496 497 498 499 500 501
	__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)
{
502 503 504 505 506
	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
507 508 509 510 511 512 513 514 515 516 517 518
	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.
 */
519
int vma_adjust(struct vm_area_struct *vma, unsigned long start,
Linus Torvalds's avatar
Linus Torvalds committed
520 521 522 523 524 525 526
	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;
527
	struct anon_vma *anon_vma = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
528 529 530 531 532
	struct file *file = vma->vm_file;
	long adjust_next = 0;
	int remove_next = 0;

	if (next && !insert) {
533 534
		struct vm_area_struct *exporter = NULL;

Linus Torvalds's avatar
Linus Torvalds committed
535 536 537 538 539 540 541
		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;
542
			exporter = next;
Linus Torvalds's avatar
Linus Torvalds committed
543 544 545 546 547 548 549
			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;
550
			exporter = next;
Linus Torvalds's avatar
Linus Torvalds committed
551 552 553 554 555 556 557 558
			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);
559
			exporter = vma;
Linus Torvalds's avatar
Linus Torvalds committed
560 561 562
			importer = next;
		}

563 564 565 566 567
		/*
		 * 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.
		 */
568 569
		if (exporter && exporter->anon_vma && !importer->anon_vma) {
			if (anon_vma_clone(importer, exporter))
570
				return -ENOMEM;
571
			importer->anon_vma = exporter->anon_vma;
572 573 574
		}
	}

Linus Torvalds's avatar
Linus Torvalds committed
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
	if (file) {
		mapping = file->f_mapping;
		if (!(vma->vm_flags & VM_NONLINEAR))
			root = &mapping->i_mmap;
		spin_lock(&mapping->i_mmap_lock);
		if (importer &&
		    vma->vm_truncate_count != next->vm_truncate_count) {
			/*
			 * unmap_mapping_range might be in progress:
			 * ensure that the expanding vma is rescanned.
			 */
			importer->vm_truncate_count = 0;
		}
		if (insert) {
			insert->vm_truncate_count = vma->vm_truncate_count;
			/*
			 * 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);
		}
	}

600 601
	vma_adjust_trans_huge(vma, start, end, adjust_next);

602 603 604 605 606 607 608 609 610 611 612
	/*
	 * 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.
	 */
	if (vma->anon_vma && (insert || importer || start != vma->vm_start)) {
		anon_vma = vma->anon_vma;
		anon_vma_lock(anon_vma);
	}

Linus Torvalds's avatar
Linus Torvalds committed
613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651
	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);
	}

652 653
	if (anon_vma)
		anon_vma_unlock(anon_vma);
Linus Torvalds's avatar
Linus Torvalds committed
654 655 656 657
	if (mapping)
		spin_unlock(&mapping->i_mmap_lock);

	if (remove_next) {
Matt Helsley's avatar
Matt Helsley committed
658
		if (file) {
Linus Torvalds's avatar
Linus Torvalds committed
659
			fput(file);
Matt Helsley's avatar
Matt Helsley committed
660 661 662
			if (next->vm_flags & VM_EXECUTABLE)
				removed_exe_file_vma(mm);
		}
663 664
		if (next->anon_vma)
			anon_vma_merge(vma, next);
Linus Torvalds's avatar
Linus Torvalds committed
665
		mm->map_count--;
666
		mpol_put(vma_policy(next));
Linus Torvalds's avatar
Linus Torvalds committed
667 668 669 670 671 672 673 674 675 676 677 678 679
		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);
680 681

	return 0;
Linus Torvalds's avatar
Linus Torvalds committed
682 683 684 685 686 687 688 689 690
}

/*
 * 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
691 692
	/* 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
693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787
		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,
					struct anon_vma *anon_vma2)
{
	return !anon_vma1 || !anon_vma2 || (anon_vma1 == anon_vma2);
}

/*
 * 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) &&
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
		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) &&
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma)) {
		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;
788
	int err;
Linus Torvalds's avatar
Linus Torvalds committed
789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821

	/*
	 * 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,
						      next->anon_vma)) {
							/* cases 1, 6 */
822
			err = vma_adjust(prev, prev->vm_start,
Linus Torvalds's avatar
Linus Torvalds committed
823 824
				next->vm_end, prev->vm_pgoff, NULL);
		} else					/* cases 2, 5, 7 */
825
			err = vma_adjust(prev, prev->vm_start,
Linus Torvalds's avatar
Linus Torvalds committed
826
				end, prev->vm_pgoff, NULL);
827 828
		if (err)
			return NULL;
Andrea Arcangeli's avatar
Andrea Arcangeli committed
829
		khugepaged_enter_vma_merge(prev);
Linus Torvalds's avatar
Linus Torvalds committed
830 831 832 833 834 835 836 837 838 839 840
		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 */
841
			err = vma_adjust(prev, prev->vm_start,
Linus Torvalds's avatar
Linus Torvalds committed
842 843
				addr, prev->vm_pgoff, NULL);
		else					/* cases 3, 8 */
844
			err = vma_adjust(area, addr, next->vm_end,
Linus Torvalds's avatar
Linus Torvalds committed
845
				next->vm_pgoff - pglen, NULL);
846 847
		if (err)
			return NULL;
Andrea Arcangeli's avatar
Andrea Arcangeli committed
848
		khugepaged_enter_vma_merge(area);
Linus Torvalds's avatar
Linus Torvalds committed
849 850 851 852 853 854
		return area;
	}

	return NULL;
}

855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909
/*
 * 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
910 911 912 913 914 915 916 917 918 919
/*
 * 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)
{
920
	struct anon_vma *anon_vma;
Linus Torvalds's avatar
Linus Torvalds committed
921 922 923 924 925 926
	struct vm_area_struct *near;

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

927 928 929
	anon_vma = reusable_anon_vma(near, vma, near);
	if (anon_vma)
		return anon_vma;
Linus Torvalds's avatar
Linus Torvalds committed
930 931 932 933 934 935 936 937
try_prev:
	/*
	 * It is potentially slow to have to call find_vma_prev here.
	 * But it's only on the first write fault on the vma, not
	 * every time, and we could devise a way to avoid it later
	 * (e.g. stash info in next's anon_vma_node when assigning
	 * an anon_vma, or when trying vma_merge).  Another time.
	 */
938
	BUG_ON(find_vma_prev(vma->vm_mm, vma->vm_start, &near) != vma);
Linus Torvalds's avatar
Linus Torvalds committed
939 940 941
	if (!near)
		goto none;

942 943 944
	anon_vma = reusable_anon_vma(near, near, vma);
	if (anon_vma)
		return anon_vma;
Linus Torvalds's avatar
Linus Torvalds committed
945 946 947 948 949 950 951 952 953 954 955 956 957
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
958
void vm_stat_account(struct mm_struct *mm, unsigned long flags,
Linus Torvalds's avatar
Linus Torvalds committed
959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975
						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 */

/*
976
 * The caller must hold down_write(&current->mm->mmap_sem).
Linus Torvalds's avatar
Linus Torvalds committed
977 978
 */

ZhenwenXu's avatar
ZhenwenXu committed
979
unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
Linus Torvalds's avatar
Linus Torvalds committed
980 981 982 983 984 985 986
			unsigned long len, unsigned long prot,
			unsigned long flags, unsigned long pgoff)
{
	struct mm_struct * mm = current->mm;
	struct inode *inode;
	unsigned int vm_flags;
	int error;
Miklos Szeredi's avatar
Miklos Szeredi committed
987
	unsigned long reqprot = prot;
Linus Torvalds's avatar
Linus Torvalds committed
988 989 990 991 992 993 994 995

	/*
	 * 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))
996
		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
Linus Torvalds's avatar
Linus Torvalds committed
997 998 999 1000 1001
			prot |= PROT_EXEC;

	if (!len)
		return -EINVAL;

1002 1003 1004
	if (!(flags & MAP_FIXED))
		addr = round_hint_to_min(addr);

Linus Torvalds's avatar
Linus Torvalds committed
1005 1006
	/* Careful about overflows.. */
	len = PAGE_ALIGN(len);
1007
	if (!len)
Linus Torvalds's avatar
Linus Torvalds committed
1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031
		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
1032
	if (flags & MAP_LOCKED)
Linus Torvalds's avatar
Linus Torvalds committed
1033 1034
		if (!can_do_mlock())
			return -EPERM;
1035

Linus Torvalds's avatar
Linus Torvalds committed
1036 1037 1038
	/* mlock MCL_FUTURE? */
	if (vm_flags & VM_LOCKED) {
		unsigned long locked, lock_limit;
1039 1040
		locked = len >> PAGE_SHIFT;
		locked += mm->locked_vm;
Jiri Slaby's avatar
Jiri Slaby committed
1041
		lock_limit = rlimit(RLIMIT_MEMLOCK);
1042
		lock_limit >>= PAGE_SHIFT;
Linus Torvalds's avatar
Linus Torvalds committed
1043 1044 1045 1046
		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
			return -EAGAIN;
	}

1047
	inode = file ? file->f_path.dentry->d_inode : NULL;
Linus Torvalds's avatar
Linus Torvalds committed
1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075

	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;
1076
			if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
Linus Torvalds's avatar
Linus Torvalds committed
1077 1078 1079 1080 1081 1082 1083
				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
1084 1085 1086 1087 1088 1089 1090 1091
			break;

		default:
			return -EINVAL;
		}
	} else {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
1092 1093 1094 1095
			/*
			 * Ignore pgoff.
			 */
			pgoff = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108
			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;
		}
	}

1109
	error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1110 1111
	if (error)
		return error;
1112

1113
	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
Miklos Szeredi's avatar
Miklos Szeredi committed
1114 1115 1116
}
EXPORT_SYMBOL(do_mmap_pgoff);

1117 1118 1119 1120 1121 1122 1123 1124
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
1125
		audit_mmap_fd(fd, flags);
1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157
		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
		 */
		len = ALIGN(len, huge_page_size(&default_hstate));
		file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE,
						&user, HUGETLB_ANONHUGE_INODE);
		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
1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181
#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
1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201
/*
 * 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)
{
	unsigned int vm_flags = vma->vm_flags;

	/* 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) !=
1202
	    pgprot_val(vm_get_page_prot(vm_flags)))
Alexey Dobriyan's avatar
Alexey Dobriyan committed
1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213
		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);
}

1214 1215
/*
 * We account for memory if it's a private writeable mapping,
1216
 * not hugepages and VM_NORESERVE wasn't set.
1217
 */
1218
static inline int accountable_mapping(struct file *file, unsigned int vm_flags)
1219
{
1220 1221 1222 1223 1224 1225 1226
	/*
	 * 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;

1227 1228 1229
	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
}

Miklos Szeredi's avatar
Miklos Szeredi committed
1230 1231
unsigned long mmap_region(struct file *file, unsigned long addr,
			  unsigned long len, unsigned long flags,
1232
			  unsigned int vm_flags, unsigned long pgoff)
Miklos Szeredi's avatar
Miklos Szeredi committed
1233 1234 1235 1236 1237 1238 1239 1240 1241
{
	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
1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
	/* 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
1253
	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
Linus Torvalds's avatar
Linus Torvalds committed
1254 1255
		return -ENOMEM;

1256 1257
	/*
	 * Set 'VM_NORESERVE' if we should not account for the
1258
	 * memory use of this mapping.
1259
	 */
1260 1261 1262 1263 1264 1265 1266 1267 1268
	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;
	}
1269

1270 1271 1272
	/*
	 * Private writable mapping: check memory availability
	 */
1273
	if (accountable_mapping(file, vm_flags)) {
1274 1275 1276 1277
		charged = len >> PAGE_SHIFT;
		if (security_vm_enough_memory(charged))
			return -ENOMEM;
		vm_flags |= VM_ACCOUNT;
Linus Torvalds's avatar
Linus Torvalds committed
1278 1279 1280
	}

	/*
1281
	 * Can we just expand an old mapping?
Linus Torvalds's avatar
Linus Torvalds committed
1282
	 */
1283 1284 1285
	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
1286 1287 1288 1289 1290 1291

	/*
	 * 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.
	 */
1292
	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
Linus Torvalds's avatar
Linus Torvalds committed
1293 1294 1295 1296 1297 1298 1299 1300 1301
	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;
1302
	vma->vm_page_prot = vm_get_page_prot(vm_flags);
Linus Torvalds's avatar
Linus Torvalds committed
1303
	vma->vm_pgoff = pgoff;
1304
	INIT_LIST_HEAD(&vma->anon_vma_chain);
Linus Torvalds's avatar
Linus Torvalds committed
1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320

	if (file) {
		error = -EINVAL;
		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
1321 1322
		if (vm_flags & VM_EXECUTABLE)
			added_exe_file_vma(mm);
1323 1324 1325 1326 1327 1328 1329 1330 1331

		/* 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
1332 1333 1334 1335 1336 1337
	} else if (vm_flags & VM_SHARED) {
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	}

1338 1339 1340 1341 1342 1343 1344 1345 1346 1347
	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.
		 */
1348
		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
1349 1350 1351
		if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
	}
1352

1353 1354
	vma_link(mm, vma, prev, rb_link, rb_parent);
	file = vma->vm_file;
1355 1356 1357 1358 1359

	/* Once vma denies write, undo our temporary denial count */
	if (correct_wcount)
		atomic_inc(&inode->i_writecount);
out:
1360
	perf_event_mmap(vma);
1361

Linus Torvalds's avatar
Linus Torvalds committed
1362
	mm->total_vm += len >> PAGE_SHIFT;
1363
	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
Linus Torvalds's avatar
Linus Torvalds committed
1364
	if (vm_flags & VM_LOCKED) {
1365 1366
		if (!mlock_vma_pages_range(vma, addr, addr + len))
			mm->locked_vm += (len >> PAGE_SHIFT);
1367
	} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
1368
		make_pages_present(addr, addr + len);
Linus Torvalds's avatar
Linus Torvalds committed
1369 1370 1371 1372 1373 1374 1375 1376 1377
	return addr;

unmap_and_free_vma:
	if (correct_wcount)
		atomic_inc(&inode->i_writecount);
	vma->vm_file = NULL;
	fput(file);

	/* Undo any partial mapping done by a device driver. */
1378 1379
	unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
	charged = 0;
Linus Torvalds's avatar
Linus Torvalds committed
1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410
free_vma:
	kmem_cache_free(vm_area_cachep, vma);
unacct_error:
	if (charged)
		vm_unacct_memory(charged);
	return error;
}

/* Get an address range which is currently unmapped.
 * For shmat() with addr=0.
 *
 * Ugly calling convention alert:
 * Return value with the low bits set means error value,
 * ie
 *	if (ret & ~PAGE_MASK)
 *		error = ret;
 *
 * This function "knows" that -ENOMEM has the bits set.
 */
#ifndef HAVE_ARCH_UNMAPPED_AREA
unsigned long
arch_get_unmapped_area(struct file *filp, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long start_addr;

	if (len > TASK_SIZE)
		return -ENOMEM;

1411 1412 1413
	if (flags & MAP_FIXED)
		return addr;

Linus Torvalds's avatar
Linus Torvalds committed
1414 1415 1416 1417 1418 1419 1420
	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
		    (!vma || addr + len <= vma->vm_start))
			return addr;
	}
1421 1422 1423 1424 1425 1426
	if (len > mm->cached_hole_size) {
	        start_addr = addr = mm->free_area_cache;
	} else {
	        start_addr = addr = TASK_UNMAPPED_BASE;
	        mm->cached_hole_size = 0