mmap.c 70.0 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5
/*
 * mm/mmap.c
 *
 * Written by obz.
 *
A
Alan Cox 已提交
6
 * Address space accounting code	<alan@lxorguk.ukuu.org.uk>
L
Linus Torvalds 已提交
7 8 9
 */

#include <linux/slab.h>
A
Alexey Dobriyan 已提交
10
#include <linux/backing-dev.h>
L
Linus Torvalds 已提交
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>
L
Linus Torvalds 已提交
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>
A
Andrea Arcangeli 已提交
29
#include <linux/mmu_notifier.h>
30
#include <linux/perf_event.h>
A
Al Viro 已提交
31
#include <linux/audit.h>
A
Andrea Arcangeli 已提交
32
#include <linux/khugepaged.h>
L
Linus Torvalds 已提交
33 34 35 36

#include <asm/uaccess.h>
#include <asm/cacheflush.h>
#include <asm/tlb.h>
37
#include <asm/mmu_context.h>
L
Linus Torvalds 已提交
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);

L
Linus Torvalds 已提交
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;
L
Linus Torvalds 已提交
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)
L
Linus Torvalds 已提交
113 114 115 116 117 118 119 120 121 122 123 124 125 126
{
	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;

127
		free = global_page_state(NR_FILE_PAGES);
L
Linus Torvalds 已提交
128 129 130 131 132 133 134 135
		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
		 */
136
		free += global_page_state(NR_SLAB_RECLAIMABLE);
L
Linus Torvalds 已提交
137 138 139 140 141 142 143 144 145 146 147 148 149 150 151

		/*
		 * 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();
152 153 154 155 156 157 158 159 160 161 162 163

		/*
		 * 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
		 */
L
Linus Torvalds 已提交
164 165 166 167 168 169
		if (!cap_sys_admin)
			n -= n / 32;
		free += n;

		if (free > pages)
			return 0;
170 171

		goto error;
L
Linus Torvalds 已提交
172 173 174 175 176 177 178 179 180 181 182 183 184
	}

	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 */
A
Alan Cox 已提交
185 186
	if (mm)
		allowed -= mm->total_vm / 32;
L
Linus Torvalds 已提交
187

188
	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
L
Linus Torvalds 已提交
189
		return 0;
190
error:
L
Linus Torvalds 已提交
191 192 193 194 195 196 197 198 199 200 201 202
	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)
203
		atomic_inc(&file->f_path.dentry->d_inode->i_writecount);
L
Linus Torvalds 已提交
204 205 206 207 208 209 210 211 212 213 214 215
	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);
}

/*
216 217
 * Unlink a file-based vm structure from its prio_tree, to hide
 * vma from rmap and vmtruncate before freeing its page tables.
L
Linus Torvalds 已提交
218
 */
219
void unlink_file_vma(struct vm_area_struct *vma)
L
Linus Torvalds 已提交
220 221 222 223 224 225 226 227 228
{
	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);
	}
229 230 231 232 233 234 235 236 237 238
}

/*
 * 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();
L
Linus Torvalds 已提交
239 240
	if (vma->vm_ops && vma->vm_ops->close)
		vma->vm_ops->close(vma);
M
Matt Helsley 已提交
241
	if (vma->vm_file) {
242
		fput(vma->vm_file);
M
Matt Helsley 已提交
243 244 245
		if (vma->vm_flags & VM_EXECUTABLE)
			removed_exe_file_vma(vma->vm_mm);
	}
246
	mpol_put(vma_policy(vma));
L
Linus Torvalds 已提交
247
	kmem_cache_free(vm_area_cachep, vma);
248
	return next;
L
Linus Torvalds 已提交
249 250
}

251
SYSCALL_DEFINE1(brk, unsigned long, brk)
L
Linus Torvalds 已提交
252 253 254 255
{
	unsigned long rlim, retval;
	unsigned long newbrk, oldbrk;
	struct mm_struct *mm = current->mm;
256
	unsigned long min_brk;
L
Linus Torvalds 已提交
257 258 259

	down_write(&mm->mmap_sem);

260
#ifdef CONFIG_COMPAT_BRK
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
	 */
266
	if (current->brk_randomized)
267 268 269
		min_brk = mm->start_brk;
	else
		min_brk = mm->end_data;
270 271 272 273
#else
	min_brk = mm->start_brk;
#endif
	if (brk < min_brk)
L
Linus Torvalds 已提交
274
		goto out;
R
Ram Gupta 已提交
275 276 277 278 279 280 281

	/*
	 * 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
	 */
J
Jiri Slaby 已提交
282
	rlim = rlimit(RLIMIT_DATA);
J
Jiri Kosina 已提交
283 284
	if (rlim < RLIM_INFINITY && (brk - mm->start_brk) +
			(mm->end_data - mm->start_data) > rlim)
R
Ram Gupta 已提交
285 286
		goto out;

L
Linus Torvalds 已提交
287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331
	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;
D
David Miller 已提交
332 333
		prev = vma->vm_start;
		pend = vma->vm_end;
L
Linus Torvalds 已提交
334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357
	}
	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;
358
	BUG_ON(bug);
L
Linus Torvalds 已提交
359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384
}
#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)
385
				break;
L
Linus Torvalds 已提交
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407
			__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);
}

D
Denys Vlasenko 已提交
408
static void __vma_link_file(struct vm_area_struct *vma)
L
Linus Torvalds 已提交
409
{
Z
ZhenwenXu 已提交
410
	struct file *file;
L
Linus Torvalds 已提交
411 412 413 414 415 416

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

		if (vma->vm_flags & VM_DENYWRITE)
417
			atomic_dec(&file->f_path.dentry->d_inode->i_writecount);
L
Linus Torvalds 已提交
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467
		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.
 */
Z
ZhenwenXu 已提交
468
static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma)
L
Linus Torvalds 已提交
469
{
Z
ZhenwenXu 已提交
470 471
	struct vm_area_struct *__vma, *prev;
	struct rb_node **rb_link, *rb_parent;
L
Linus Torvalds 已提交
472 473

	__vma = find_vma_prepare(mm, vma->vm_start,&prev, &rb_link, &rb_parent);
474
	BUG_ON(__vma && __vma->vm_start < vma->vm_end);
L
Linus Torvalds 已提交
475 476 477 478 479 480 481 482
	__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)
{
483 484 485 486 487
	struct vm_area_struct *next = vma->vm_next;

	prev->vm_next = next;
	if (next)
		next->vm_prev = prev;
L
Linus Torvalds 已提交
488 489 490 491 492 493 494 495 496 497 498 499
	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.
 */
500
int vma_adjust(struct vm_area_struct *vma, unsigned long start,
L
Linus Torvalds 已提交
501 502 503 504 505 506 507
	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;
508
	struct anon_vma *anon_vma = NULL;
L
Linus Torvalds 已提交
509 510 511 512 513
	struct file *file = vma->vm_file;
	long adjust_next = 0;
	int remove_next = 0;

	if (next && !insert) {
514 515
		struct vm_area_struct *exporter = NULL;

L
Linus Torvalds 已提交
516 517 518 519 520 521 522
		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;
523
			exporter = next;
L
Linus Torvalds 已提交
524 525 526 527 528 529 530
			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;
531
			exporter = next;
L
Linus Torvalds 已提交
532 533 534 535 536 537 538 539
			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);
540
			exporter = vma;
L
Linus Torvalds 已提交
541 542 543
			importer = next;
		}

544 545 546 547 548
		/*
		 * 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.
		 */
549 550
		if (exporter && exporter->anon_vma && !importer->anon_vma) {
			if (anon_vma_clone(importer, exporter))
551
				return -ENOMEM;
552
			importer->anon_vma = exporter->anon_vma;
553 554 555
		}
	}

L
Linus Torvalds 已提交
556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580
	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);
		}
	}

581 582
	vma_adjust_trans_huge(vma, start, end, adjust_next);

583 584 585 586 587 588
	/*
	 * 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.
	 */
589
	if (vma->anon_vma && (importer || start != vma->vm_start)) {
590 591 592 593
		anon_vma = vma->anon_vma;
		anon_vma_lock(anon_vma);
	}

L
Linus Torvalds 已提交
594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632
	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);
	}

633 634
	if (anon_vma)
		anon_vma_unlock(anon_vma);
L
Linus Torvalds 已提交
635 636 637 638
	if (mapping)
		spin_unlock(&mapping->i_mmap_lock);

	if (remove_next) {
M
Matt Helsley 已提交
639
		if (file) {
L
Linus Torvalds 已提交
640
			fput(file);
M
Matt Helsley 已提交
641 642 643
			if (next->vm_flags & VM_EXECUTABLE)
				removed_exe_file_vma(mm);
		}
644 645
		if (next->anon_vma)
			anon_vma_merge(vma, next);
L
Linus Torvalds 已提交
646
		mm->map_count--;
647
		mpol_put(vma_policy(next));
L
Linus Torvalds 已提交
648 649 650 651 652 653 654 655 656 657 658 659 660
		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);
661 662

	return 0;
L
Linus Torvalds 已提交
663 664 665 666 667 668 669 670 671
}

/*
 * 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)
{
H
Hugh Dickins 已提交
672 673
	/* VM_CAN_NONLINEAR may get set later by f_op->mmap() */
	if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR)
L
Linus Torvalds 已提交
674 675 676 677 678 679 680 681 682
		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,
S
Shaohua Li 已提交
683 684
					struct anon_vma *anon_vma2,
					struct vm_area_struct *vma)
L
Linus Torvalds 已提交
685
{
S
Shaohua Li 已提交
686 687 688 689 690 691 692 693
	/*
	 * 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;
L
Linus Torvalds 已提交
694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711
}

/*
 * 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) &&
S
Shaohua Li 已提交
712
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
L
Linus Torvalds 已提交
713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730
		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) &&
S
Shaohua Li 已提交
731
	    is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
L
Linus Torvalds 已提交
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
		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;
777
	int err;
L
Linus Torvalds 已提交
778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808

	/*
	 * 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,
S
Shaohua Li 已提交
809
						      next->anon_vma, NULL)) {
L
Linus Torvalds 已提交
810
							/* cases 1, 6 */
811
			err = vma_adjust(prev, prev->vm_start,
L
Linus Torvalds 已提交
812 813
				next->vm_end, prev->vm_pgoff, NULL);
		} else					/* cases 2, 5, 7 */
814
			err = vma_adjust(prev, prev->vm_start,
L
Linus Torvalds 已提交
815
				end, prev->vm_pgoff, NULL);
816 817
		if (err)
			return NULL;
A
Andrea Arcangeli 已提交
818
		khugepaged_enter_vma_merge(prev);
L
Linus Torvalds 已提交
819 820 821 822 823 824 825 826 827 828 829
		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 */
830
			err = vma_adjust(prev, prev->vm_start,
L
Linus Torvalds 已提交
831 832
				addr, prev->vm_pgoff, NULL);
		else					/* cases 3, 8 */
833
			err = vma_adjust(area, addr, next->vm_end,
L
Linus Torvalds 已提交
834
				next->vm_pgoff - pglen, NULL);
835 836
		if (err)
			return NULL;
A
Andrea Arcangeli 已提交
837
		khugepaged_enter_vma_merge(area);
L
Linus Torvalds 已提交
838 839 840 841 842 843
		return area;
	}

	return NULL;
}

844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898
/*
 * 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;
}

L
Linus Torvalds 已提交
899 900 901 902 903 904 905 906 907 908
/*
 * 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)
{
909
	struct anon_vma *anon_vma;
L
Linus Torvalds 已提交
910 911 912 913 914 915
	struct vm_area_struct *near;

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

916 917 918
	anon_vma = reusable_anon_vma(near, vma, near);
	if (anon_vma)
		return anon_vma;
L
Linus Torvalds 已提交
919 920 921 922 923 924 925 926
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.
	 */
927
	BUG_ON(find_vma_prev(vma->vm_mm, vma->vm_start, &near) != vma);
L
Linus Torvalds 已提交
928 929 930
	if (!near)
		goto none;

931 932 933
	anon_vma = reusable_anon_vma(near, near, vma);
	if (anon_vma)
		return anon_vma;
L
Linus Torvalds 已提交
934 935 936 937 938 939 940 941 942 943 944 945 946
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
947
void vm_stat_account(struct mm_struct *mm, unsigned long flags,
L
Linus Torvalds 已提交
948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964
						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 */

/*
965
 * The caller must hold down_write(&current->mm->mmap_sem).
L
Linus Torvalds 已提交
966 967
 */

Z
ZhenwenXu 已提交
968
unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
L
Linus Torvalds 已提交
969 970 971 972 973 974 975
			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;
M
Miklos Szeredi 已提交
976
	unsigned long reqprot = prot;
L
Linus Torvalds 已提交
977 978 979 980 981 982 983 984

	/*
	 * 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))
985
		if (!(file && (file->f_path.mnt->mnt_flags & MNT_NOEXEC)))
L
Linus Torvalds 已提交
986 987 988 989 990
			prot |= PROT_EXEC;

	if (!len)
		return -EINVAL;

991 992 993
	if (!(flags & MAP_FIXED))
		addr = round_hint_to_min(addr);

L
Linus Torvalds 已提交
994 995
	/* Careful about overflows.. */
	len = PAGE_ALIGN(len);
996
	if (!len)
L
Linus Torvalds 已提交
997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020
		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;

H
Huang Shijie 已提交
1021
	if (flags & MAP_LOCKED)
L
Linus Torvalds 已提交
1022 1023
		if (!can_do_mlock())
			return -EPERM;
1024

L
Linus Torvalds 已提交
1025 1026 1027
	/* mlock MCL_FUTURE? */
	if (vm_flags & VM_LOCKED) {
		unsigned long locked, lock_limit;
1028 1029
		locked = len >> PAGE_SHIFT;
		locked += mm->locked_vm;
J
Jiri Slaby 已提交
1030
		lock_limit = rlimit(RLIMIT_MEMLOCK);
1031
		lock_limit >>= PAGE_SHIFT;
L
Linus Torvalds 已提交
1032 1033 1034 1035
		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
			return -EAGAIN;
	}

1036
	inode = file ? file->f_path.dentry->d_inode : NULL;
L
Linus Torvalds 已提交
1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064

	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;
1065
			if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
L
Linus Torvalds 已提交
1066 1067 1068 1069 1070 1071 1072
				if (vm_flags & VM_EXEC)
					return -EPERM;
				vm_flags &= ~VM_MAYEXEC;
			}

			if (!file->f_op || !file->f_op->mmap)
				return -ENODEV;
L
Linus Torvalds 已提交
1073 1074 1075 1076 1077 1078 1079 1080
			break;

		default:
			return -EINVAL;
		}
	} else {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
1081 1082 1083 1084
			/*
			 * Ignore pgoff.
			 */
			pgoff = 0;
L
Linus Torvalds 已提交
1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097
			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;
		}
	}

1098
	error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
L
Linus Torvalds 已提交
1099 1100
	if (error)
		return error;
1101

1102
	return mmap_region(file, addr, len, flags, vm_flags, pgoff);
M
Miklos Szeredi 已提交
1103 1104 1105
}
EXPORT_SYMBOL(do_mmap_pgoff);

H
Hugh Dickins 已提交
1106 1107 1108 1109 1110 1111 1112 1113
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)) {
A
Al Viro 已提交
1114
		audit_mmap_fd(fd, flags);
H
Hugh Dickins 已提交
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146
		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;
}

C
Christoph Hellwig 已提交
1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170
#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 */

A
Alexey Dobriyan 已提交
1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190
/*
 * 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) !=
1191
	    pgprot_val(vm_get_page_prot(vm_flags)))
A
Alexey Dobriyan 已提交
1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202
		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);
}

1203 1204
/*
 * We account for memory if it's a private writeable mapping,
1205
 * not hugepages and VM_NORESERVE wasn't set.
1206
 */
1207
static inline int accountable_mapping(struct file *file, unsigned int vm_flags)
1208
{
1209 1210 1211 1212 1213 1214 1215
	/*
	 * 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;

1216 1217 1218
	return (vm_flags & (VM_NORESERVE | VM_SHARED | VM_WRITE)) == VM_WRITE;
}

M
Miklos Szeredi 已提交
1219 1220
unsigned long mmap_region(struct file *file, unsigned long addr,
			  unsigned long len, unsigned long flags,
1221
			  unsigned int vm_flags, unsigned long pgoff)
M
Miklos Szeredi 已提交
1222 1223 1224 1225 1226 1227 1228 1229 1230
{
	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;

L
Linus Torvalds 已提交
1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241
	/* 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. */
A
akpm@osdl.org 已提交
1242
	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
L
Linus Torvalds 已提交
1243 1244
		return -ENOMEM;

1245 1246
	/*
	 * Set 'VM_NORESERVE' if we should not account for the
1247
	 * memory use of this mapping.
1248
	 */
1249 1250 1251 1252 1253 1254 1255 1256 1257
	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;
	}
1258

1259 1260 1261
	/*
	 * Private writable mapping: check memory availability
	 */
1262
	if (accountable_mapping(file, vm_flags)) {
1263 1264 1265 1266
		charged = len >> PAGE_SHIFT;
		if (security_vm_enough_memory(charged))
			return -ENOMEM;
		vm_flags |= VM_ACCOUNT;
L
Linus Torvalds 已提交
1267 1268 1269
	}

	/*
1270
	 * Can we just expand an old mapping?
L
Linus Torvalds 已提交
1271
	 */
1272 1273 1274
	vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
	if (vma)
		goto out;
L
Linus Torvalds 已提交
1275 1276 1277 1278 1279 1280

	/*
	 * 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.
	 */
P
Pekka Enberg 已提交
1281
	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
1282 1283 1284 1285 1286 1287 1288 1289 1290
	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;
1291
	vma->vm_page_prot = vm_get_page_prot(vm_flags);
L
Linus Torvalds 已提交
1292
	vma->vm_pgoff = pgoff;
1293
	INIT_LIST_HEAD(&vma->anon_vma_chain);
L
Linus Torvalds 已提交
1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309

	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;
M
Matt Helsley 已提交
1310 1311
		if (vm_flags & VM_EXECUTABLE)
			added_exe_file_vma(mm);
1312 1313 1314 1315 1316 1317 1318 1319 1320

		/* 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;
L
Linus Torvalds 已提交
1321 1322 1323 1324 1325 1326
	} else if (vm_flags & VM_SHARED) {
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	}

1327 1328 1329 1330 1331 1332 1333 1334 1335 1336
	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.
		 */
1337
		vma->vm_page_prot = vm_get_page_prot(vm_flags & ~VM_SHARED);
1338 1339 1340
		if (pgprot_val(pprot) == pgprot_val(pgprot_noncached(pprot)))
			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
	}
1341

1342 1343
	vma_link(mm, vma, prev, rb_link, rb_parent);
	file = vma->vm_file;
1344 1345 1346 1347 1348

	/* Once vma denies write, undo our temporary denial count */
	if (correct_wcount)
		atomic_inc(&inode->i_writecount);
out:
1349
	perf_event_mmap(vma);
1350

L
Linus Torvalds 已提交
1351
	mm->total_vm += len >> PAGE_SHIFT;
1352
	vm_stat_account(mm, vm_flags, file, len >> PAGE_SHIFT);
L
Linus Torvalds 已提交
1353
	if (vm_flags & VM_LOCKED) {
1354 1355
		if (!mlock_vma_pages_range(vma, addr, addr + len))
			mm->locked_vm += (len >> PAGE_SHIFT);
1356
	} else if ((flags & MAP_POPULATE) && !(flags & MAP_NONBLOCK))
1357
		make_pages_present(addr, addr + len);
L
Linus Torvalds 已提交
1358 1359 1360 1361 1362 1363 1364 1365 1366
	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. */
1367 1368
	unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end);
	charged = 0;
L
Linus Torvalds 已提交
1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399
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;

1400 1401 1402
	if (flags & MAP_FIXED)
		return addr;

L
Linus Torvalds 已提交
1403 1404 1405 1406 1407 1408 1409
	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
		    (!vma || addr + len <= vma->vm_start))
			return addr;
	}
1410 1411 1412 1413 1414 1415
	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;
	}
L
Linus Torvalds 已提交
1416 1417 1418 1419 1420 1421 1422 1423 1424 1425

full_search:
	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
		/* At this point:  (!vma || addr < vma->vm_end). */
		if (TASK_SIZE - len < addr) {
			/*
			 * Start a new search - just in case we missed
			 * some holes.
			 */
			if (start_addr != TASK_UNMAPPED_BASE) {
1426 1427 1428
				addr = TASK_UNMAPPED_BASE;
			        start_addr = addr;
				mm->cached_hole_size = 0;
L
Linus Torvalds 已提交
1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439
				goto full_search;
			}
			return -ENOMEM;
		}
		if (!vma || addr + len <= vma->vm_start) {
			/*
			 * Remember the place where we stopped the search:
			 */
			mm->free_area_cache = addr + len;
			return addr;
		}
1440 1441
		if (addr + mm->cached_hole_size < vma->vm_start)
		        mm->cached_hole_size = vma->vm_start - addr;
L
Linus Torvalds 已提交
1442 1443 1444 1445 1446
		addr = vma->vm_end;
	}
}
#endif	

1447
void arch_unmap_area(struct mm_struct *mm, unsigned long addr)
L
Linus Torvalds 已提交
1448 1449 1450 1451
{
	/*
	 * Is this a new hole at the lowest possible address?
	 */
1452 1453 1454 1455
	if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) {
		mm->free_area_cache = addr;
		mm->cached_hole_size = ~0UL;
	}
L
Linus Torvalds 已提交
1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475
}

/*
 * This mmap-allocator allocates new areas top-down from below the
 * stack's low limit (the base):
 */
#ifndef HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
unsigned long
arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
			  const unsigned long len, const unsigned long pgoff,
			  const unsigned long flags)
{
	struct vm_area_struct *vma;
	struct mm_struct *mm = current->mm;
	unsigned long addr = addr0;

	/* requested length too big for entire address space */
	if (len > TASK_SIZE)
		return -ENOMEM;

1476 1477 1478
	if (flags & MAP_FIXED)
		return addr;

L
Linus Torvalds 已提交
1479 1480 1481 1482 1483 1484 1485 1486 1487
	/* requesting a specific address */
	if (addr) {
		addr = PAGE_ALIGN(addr);
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
				(!vma || addr + len <= vma->vm_start))
			return addr;
	}

1488 1489 1490 1491 1492 1493
	/* check if free_area_cache is useful for us */
	if (len <= mm->cached_hole_size) {
 	        mm->cached_hole_size = 0;
 		mm->free_area_cache = mm->mmap_base;
 	}

L
Linus Torvalds 已提交
1494 1495 1496 1497
	/* either no address requested or can't fit in requested address hole */
	addr = mm->free_area_cache;

	/* make sure it can fit in the remaining address space */
1498
	if (addr > len) {
L
Linus Torvalds 已提交
1499 1500 1501 1502 1503 1504
		vma = find_vma(mm, addr-len);
		if (!vma || addr <= vma->vm_start)
			/* remember the address as a hint for next time */
			return (mm->free_area_cache = addr-len);
	}

1505 1506 1507
	if (mm->mmap_base < len)
		goto bottomup;

L
Linus Torvalds 已提交
1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520
	addr = mm->mmap_base-len;

	do {
		/*
		 * Lookup failure means no vma is above this address,
		 * else if new region fits below vma->vm_start,
		 * return with success:
		 */
		vma = find_vma(mm, addr);
		if (!vma || addr+len <= vma->vm_start)
			/* remember the address as a hint for next time */
			return (mm->free_area_cache = addr);

1521 1522 1523 1524
 		/* remember the largest hole we saw so far */
 		if (addr + mm->cached_hole_size < vma->vm_start)
 		        mm->cached_hole_size = vma->vm_start - addr;

L
Linus Torvalds 已提交
1525 1526
		/* try just below the current vma->vm_start */
		addr = vma->vm_start-len;
1527
	} while (len < vma->vm_start);
L
Linus Torvalds 已提交
1528

1529
bottomup:
L
Linus Torvalds 已提交
1530 1531 1532 1533 1534 1535
	/*
	 * A failed mmap() very likely causes application failure,
	 * so fall back to the bottom-up function here. This scenario
	 * can happen with large stack limits and large mmap()
	 * allocations.
	 */
1536 1537
	mm->cached_hole_size = ~0UL;
  	mm->free_area_cache = TASK_UNMAPPED_BASE;
L
Linus Torvalds 已提交
1538 1539 1540 1541 1542
	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
	/*
	 * Restore the topdown base:
	 */
	mm->free_area_cache = mm->mmap_base;
1543
	mm->cached_hole_size = ~0UL;
L
Linus Torvalds 已提交
1544 1545 1546 1547 1548

	return addr;
}
#endif

1549
void arch_unmap_area_topdown(struct mm_struct *mm, unsigned long addr)
L
Linus Torvalds 已提交
1550 1551 1552 1553
{
	/*
	 * Is this a new hole at the highest possible address?
	 */
1554 1555
	if (addr > mm->free_area_cache)
		mm->free_area_cache = addr;
L
Linus Torvalds 已提交
1556 1557

	/* dont allow allocations above current base */
1558 1559
	if (mm->free_area_cache > mm->mmap_base)
		mm->free_area_cache = mm->mmap_base;
L
Linus Torvalds 已提交
1560 1561 1562 1563 1564 1565
}

unsigned long
get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
		unsigned long pgoff, unsigned long flags)
{
1566 1567 1568
	unsigned long (*get_area)(struct file *, unsigned long,
				  unsigned long, unsigned long, unsigned long);

1569 1570 1571 1572 1573 1574 1575 1576
	unsigned long error = arch_mmap_check(addr, len, flags);
	if (error)
		return error;

	/* Careful about overflows.. */
	if (len > TASK_SIZE)
		return -ENOMEM;

1577 1578 1579 1580 1581 1582
	get_area = current->mm->get_unmapped_area;
	if (file && file->f_op && file->f_op->get_unmapped_area)
		get_area = file->f_op->get_unmapped_area;
	addr = get_area(file, addr, len, pgoff, flags);
	if (IS_ERR_VALUE(addr))
		return addr;
L
Linus Torvalds 已提交
1583

1584 1585 1586 1587
	if (addr > TASK_SIZE - len)
		return -ENOMEM;
	if (addr & ~PAGE_MASK)
		return -EINVAL;
1588

1589
	return arch_rebalance_pgtables(addr, len);
L
Linus Torvalds 已提交
1590 1591 1592 1593 1594
}

EXPORT_SYMBOL(get_unmapped_area);

/* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
Z
ZhenwenXu 已提交
1595
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
L
Linus Torvalds 已提交
1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637
{
	struct vm_area_struct *vma = NULL;

	if (mm) {
		/* Check the cache first. */
		/* (Cache hit rate is typically around 35%.) */
		vma = mm->mmap_cache;
		if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
			struct rb_node * rb_node;

			rb_node = mm->mm_rb.rb_node;
			vma = NULL;

			while (rb_node) {
				struct vm_area_struct * vma_tmp;

				vma_tmp = rb_entry(rb_node,
						struct vm_area_struct, vm_rb);

				if (vma_tmp->vm_end > addr) {
					vma = vma_tmp;
					if (vma_tmp->vm_start <= addr)
						break;
					rb_node = rb_node->rb_left;
				} else
					rb_node = rb_node->rb_right;
			}
			if (vma)
				mm->mmap_cache = vma;
		}
	}
	return vma;
}

EXPORT_SYMBOL(find_vma);

/* Same as find_vma, but also return a pointer to the previous VMA in *pprev. */
struct vm_area_struct *
find_vma_prev(struct mm_struct *mm, unsigned long addr,
			struct vm_area_struct **pprev)
{
	struct vm_area_struct *vma = NULL, *prev = NULL;
Z
ZhenwenXu 已提交
1638
	struct rb_node *rb_node;
L
Linus Torvalds 已提交
1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671
	if (!mm)
		goto out;

	/* Guard against addr being lower than the first VMA */
	vma = mm->mmap;

	/* Go through the RB tree quickly. */
	rb_node = mm->mm_rb.rb_node;

	while (rb_node) {
		struct vm_area_struct *vma_tmp;
		vma_tmp = rb_entry(rb_node, struct vm_area_struct, vm_rb);

		if (addr < vma_tmp->vm_end) {
			rb_node = rb_node->rb_left;
		} else {
			prev = vma_tmp;
			if (!prev->vm_next || (addr < prev->vm_next->vm_end))
				break;
			rb_node = rb_node->rb_right;
		}
	}

out:
	*pprev = prev;
	return prev ? prev->vm_next : vma;
}

/*
 * Verify that the stack growth is acceptable and
 * update accounting. This is shared with both the
 * grow-up and grow-down cases.
 */
Z
ZhenwenXu 已提交
1672
static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, unsigned long grow)
L
Linus Torvalds 已提交
1673 1674 1675
{
	struct mm_struct *mm = vma->vm_mm;
	struct rlimit *rlim = current->signal->rlim;
1676
	unsigned long new_start;
L
Linus Torvalds 已提交
1677 1678

	/* address space limit tests */
A
akpm@osdl.org 已提交
1679
	if (!may_expand_vm(mm, grow))
L
Linus Torvalds 已提交
1680 1681 1682
		return -ENOMEM;

	/* Stack limit test */
J
Jiri Slaby 已提交
1683
	if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur))
L
Linus Torvalds 已提交
1684 1685 1686 1687 1688 1689 1690
		return -ENOMEM;

	/* mlock limit tests */
	if (vma->vm_flags & VM_LOCKED) {
		unsigned long locked;
		unsigned long limit;
		locked = mm->locked_vm + grow;
J
Jiri Slaby 已提交
1691 1692
		limit = ACCESS_ONCE(rlim[RLIMIT_MEMLOCK].rlim_cur);
		limit >>= PAGE_SHIFT;
L
Linus Torvalds 已提交
1693 1694 1695 1696
		if (locked > limit && !capable(CAP_IPC_LOCK))
			return -ENOMEM;
	}

1697 1698 1699 1700 1701 1702
	/* Check to ensure the stack will not grow into a hugetlb-only region */
	new_start = (vma->vm_flags & VM_GROWSUP) ? vma->vm_start :
			vma->vm_end - size;
	if (is_hugepage_only_range(vma->vm_mm, new_start, size))
		return -EFAULT;

L
Linus Torvalds 已提交
1703 1704 1705 1706
	/*
	 * Overcommit..  This must be the final test, as it will
	 * update security statistics.
	 */
1707
	if (security_vm_enough_memory_mm(mm, grow))
L
Linus Torvalds 已提交
1708 1709 1710 1711 1712 1713
		return -ENOMEM;

	/* Ok, everything looks good - let it rip */
	mm->total_vm += grow;
	if (vma->vm_flags & VM_LOCKED)
		mm->locked_vm += grow;
1714
	vm_stat_account(mm, vma->vm_flags, vma->vm_file, grow);
L
Linus Torvalds 已提交
1715 1716 1717
	return 0;
}

H
Hugh Dickins 已提交
1718
#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64)
L
Linus Torvalds 已提交
1719
/*
H
Hugh Dickins 已提交
1720 1721
 * PA-RISC uses this for its stack; IA64 for its Register Backing Store.
 * vma is the last one with address > vma->vm_end.  Have to extend vma.
L
Linus Torvalds 已提交
1722
 */
H
Hugh Dickins 已提交
1723
int expand_upwards(struct vm_area_struct *vma, unsigned long address)
L
Linus Torvalds 已提交
1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735
{
	int error;

	if (!(vma->vm_flags & VM_GROWSUP))
		return -EFAULT;

	/*
	 * We must make sure the anon_vma is allocated
	 * so that the anon_vma locking is not a noop.
	 */
	if (unlikely(anon_vma_prepare(vma)))
		return -ENOMEM;
1736
	vma_lock_anon_vma(vma);
L
Linus Torvalds 已提交
1737 1738 1739 1740 1741

	/*
	 * vma->vm_start/vm_end cannot change under us because the caller
	 * is required to hold the mmap_sem in read mode.  We need the
	 * anon_vma lock to serialize against concurrent expand_stacks.
1742
	 * Also guard against wrapping around to address 0.
L
Linus Torvalds 已提交
1743
	 */
1744 1745 1746
	if (address < PAGE_ALIGN(address+4))
		address = PAGE_ALIGN(address+4);
	else {
1747
		vma_unlock_anon_vma(vma);
1748 1749
		return -ENOMEM;
	}
L
Linus Torvalds 已提交
1750 1751 1752 1753 1754 1755 1756 1757 1758
	error = 0;

	/* Somebody else might have raced and expanded it already */
	if (address > vma->vm_end) {
		unsigned long size, grow;

		size = address - vma->vm_start;
		grow = (address - vma->vm_end) >> PAGE_SHIFT;

1759 1760 1761 1762 1763 1764 1765
		error = -ENOMEM;
		if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) {
			error = acct_stack_growth(vma, size, grow);
			if (!error) {
				vma->vm_end = address;
				perf_event_mmap(vma);
			}
1766
		}
L
Linus Torvalds 已提交
1767
	}
1768
	vma_unlock_anon_vma(vma);
A
Andrea Arcangeli 已提交
1769
	khugepaged_enter_vma_merge(vma);
L
Linus Torvalds 已提交
1770 1771
	return error;
}
H
Hugh Dickins 已提交
1772 1773
#endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */

L
Linus Torvalds 已提交
1774 1775 1776
/*
 * vma is the first one with address < vma->vm_start.  Have to extend vma.
 */
1777
int expand_downwards(struct vm_area_struct *vma,
1778
				   unsigned long address)
L
Linus Torvalds 已提交
1779 1780 1781 1782 1783 1784 1785 1786 1787
{
	int error;

	/*
	 * We must make sure the anon_vma is allocated
	 * so that the anon_vma locking is not a noop.
	 */
	if (unlikely(anon_vma_prepare(vma)))
		return -ENOMEM;
1788 1789

	address &= PAGE_MASK;
1790
	error = security_file_mmap(NULL, 0, 0, 0, address, 1);
1791 1792 1793
	if (error)
		return error;

1794
	vma_lock_anon_vma(vma);
L
Linus Torvalds 已提交
1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808

	/*
	 * vma->vm_start/vm_end cannot change under us because the caller
	 * is required to hold the mmap_sem in read mode.  We need the
	 * anon_vma lock to serialize against concurrent expand_stacks.
	 */

	/* Somebody else might have raced and expanded it already */
	if (address < vma->vm_start) {
		unsigned long size, grow;

		size = vma->vm_end - address;
		grow = (vma->vm_start - address) >> PAGE_SHIFT;

1809 1810 1811 1812 1813 1814 1815 1816
		error = -ENOMEM;
		if (grow <= vma->vm_pgoff) {
			error = acct_stack_growth(vma, size, grow);
			if (!error) {
				vma->vm_start = address;
				vma->vm_pgoff -= grow;
				perf_event_mmap(vma);
			}
L
Linus Torvalds 已提交
1817 1818
		}
	}
1819
	vma_unlock_anon_vma(vma);
A
Andrea Arcangeli 已提交
1820
	khugepaged_enter_vma_merge(vma);
L
Linus Torvalds 已提交
1821 1822 1823
	return error;
}

1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838
#ifdef CONFIG_STACK_GROWSUP
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
	return expand_upwards(vma, address);
}

struct vm_area_struct *
find_extend_vma(struct mm_struct *mm, unsigned long addr)
{
	struct vm_area_struct *vma, *prev;

	addr &= PAGE_MASK;
	vma = find_vma_prev(mm, addr, &prev);
	if (vma && (vma->vm_start <= addr))
		return vma;
1839
	if (!prev || expand_stack(prev, addr))
1840
		return NULL;
1841
	if (prev->vm_flags & VM_LOCKED) {
1842
		mlock_vma_pages_range(prev, addr, prev->vm_end);
1843
	}
1844 1845 1846 1847 1848 1849 1850 1851
	return prev;
}
#else
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
	return expand_downwards(vma, address);
}

L
Linus Torvalds 已提交
1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868
struct vm_area_struct *
find_extend_vma(struct mm_struct * mm, unsigned long addr)
{
	struct vm_area_struct * vma;
	unsigned long start;

	addr &= PAGE_MASK;
	vma = find_vma(mm,addr);
	if (!vma)
		return NULL;
	if (vma->vm_start <= addr)
		return vma;
	if (!(vma->vm_flags & VM_GROWSDOWN))
		return NULL;
	start = vma->vm_start;
	if (expand_stack(vma, addr))
		return NULL;
1869
	if (vma->vm_flags & VM_LOCKED) {
1870
		mlock_vma_pages_range(vma, addr, start);
1871
	}
L
Linus Torvalds 已提交
1872 1873 1874 1875 1876
	return vma;
}
#endif

/*
1877
 * Ok - we have the memory areas we should free on the vma list,
L
Linus Torvalds 已提交
1878
 * so release them, and do the vma updates.
1879 1880
 *
 * Called with the mm semaphore held.
L
Linus Torvalds 已提交
1881
 */
1882
static void remove_vma_list(struct mm_struct *mm, struct vm_area_struct *vma)
L
Linus Torvalds 已提交
1883
{
1884 1885
	/* Update high watermark before we lower total_vm */
	update_hiwater_vm(mm);
L
Linus Torvalds 已提交
1886
	do {
1887 1888 1889 1890
		long nrpages = vma_pages(vma);

		mm->total_vm -= nrpages;
		vm_stat_account(mm, vma->vm_flags, vma->vm_file, -nrpages);
1891
		vma = remove_vma(vma);
1892
	} while (vma);
L
Linus Torvalds 已提交
1893 1894 1895 1896 1897 1898
	validate_mm(mm);
}

/*
 * Get rid of page table information in the indicated region.
 *
1899
 * Called with the mm semaphore held.
L
Linus Torvalds 已提交
1900 1901
 */
static void unmap_region(struct mm_struct *mm,
1902 1903
		struct vm_area_struct *vma, struct vm_area_struct *prev,
		unsigned long start, unsigned long end)
L
Linus Torvalds 已提交
1904
{
1905
	struct vm_area_struct *next = prev? prev->vm_next: mm->mmap;
L
Linus Torvalds 已提交
1906 1907 1908 1909 1910
	struct mmu_gather *tlb;
	unsigned long nr_accounted = 0;

	lru_add_drain();
	tlb = tlb_gather_mmu(mm, 0);
1911
	update_hiwater_rss(mm);
1912
	unmap_vmas(&tlb, vma, start, end, &nr_accounted, NULL);
L
Linus Torvalds 已提交
1913
	vm_unacct_memory(nr_accounted);
1914
	free_pgtables(tlb, vma, prev? prev->vm_end: FIRST_USER_ADDRESS,
1915
				 next? next->vm_start: 0);
L
Linus Torvalds 已提交
1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928
	tlb_finish_mmu(tlb, start, end);
}

/*
 * Create a list of vma's touched by the unmap, removing them from the mm's
 * vma list as we go..
 */
static void
detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
	struct vm_area_struct *prev, unsigned long end)
{
	struct vm_area_struct **insertion_point;
	struct vm_area_struct *tail_vma = NULL;
1929
	unsigned long addr;
L
Linus Torvalds 已提交
1930 1931

	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
1932
	vma->vm_prev = NULL;
L
Linus Torvalds 已提交
1933 1934 1935 1936 1937 1938 1939
	do {
		rb_erase(&vma->vm_rb, &mm->mm_rb);
		mm->map_count--;
		tail_vma = vma;
		vma = vma->vm_next;
	} while (vma && vma->vm_start < end);
	*insertion_point = vma;
1940 1941
	if (vma)
		vma->vm_prev = prev;
L
Linus Torvalds 已提交
1942
	tail_vma->vm_next = NULL;
1943 1944 1945 1946 1947
	if (mm->unmap_area == arch_unmap_area)
		addr = prev ? prev->vm_end : mm->mmap_base;
	else
		addr = vma ?  vma->vm_start : mm->mmap_base;
	mm->unmap_area(mm, addr);
L
Linus Torvalds 已提交
1948 1949 1950 1951
	mm->mmap_cache = NULL;		/* Kill the cache. */
}

/*
1952 1953
 * __split_vma() bypasses sysctl_max_map_count checking.  We use this on the
 * munmap path where it doesn't make sense to fail.
L
Linus Torvalds 已提交
1954
 */
1955
static int __split_vma(struct mm_struct * mm, struct vm_area_struct * vma,
L
Linus Torvalds 已提交
1956 1957 1958 1959
	      unsigned long addr, int new_below)
{
	struct mempolicy *pol;
	struct vm_area_struct *new;
1960
	int err = -ENOMEM;
L
Linus Torvalds 已提交
1961

1962 1963
	if (is_vm_hugetlb_page(vma) && (addr &
					~(huge_page_mask(hstate_vma(vma)))))
L
Linus Torvalds 已提交
1964 1965
		return -EINVAL;

1966
	new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
1967
	if (!new)
1968
		goto out_err;
L
Linus Torvalds 已提交
1969 1970 1971 1972

	/* most fields are the same, copy all, and then fixup */
	*new = *vma;

1973 1974
	INIT_LIST_HEAD(&new->anon_vma_chain);

L
Linus Torvalds 已提交
1975 1976 1977 1978 1979 1980 1981
	if (new_below)
		new->vm_end = addr;
	else {
		new->vm_start = addr;
		new->vm_pgoff += ((addr - vma->vm_start) >> PAGE_SHIFT);
	}

1982
	pol = mpol_dup(vma_policy(vma));
L
Linus Torvalds 已提交
1983
	if (IS_ERR(pol)) {
1984 1985
		err = PTR_ERR(pol);
		goto out_free_vma;
L
Linus Torvalds 已提交
1986 1987 1988
	}
	vma_set_policy(new, pol);

1989 1990 1991
	if (anon_vma_clone(new, vma))
		goto out_free_mpol;

M
Matt Helsley 已提交
1992
	if (new->vm_file) {
L
Linus Torvalds 已提交
1993
		get_file(new->vm_file);
M
Matt Helsley 已提交
1994 1995 1996
		if (vma->vm_flags & VM_EXECUTABLE)
			added_exe_file_vma(mm);
	}
L
Linus Torvalds 已提交
1997 1998 1999 2000 2001

	if (new->vm_ops && new->vm_ops->open)
		new->vm_ops->open(new);

	if (new_below)
2002
		err = vma_adjust(vma, addr, vma->vm_end, vma->vm_pgoff +
L
Linus Torvalds 已提交
2003 2004
			((addr - new->vm_start) >> PAGE_SHIFT), new);
	else
2005
		err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new);
L
Linus Torvalds 已提交
2006

2007 2008 2009 2010 2011
	/* Success. */
	if (!err)
		return 0;

	/* Clean everything up if vma_adjust failed. */
2012 2013
	if (new->vm_ops && new->vm_ops->close)
		new->vm_ops->close(new);
2014 2015 2016 2017 2018
	if (new->vm_file) {
		if (vma->vm_flags & VM_EXECUTABLE)
			removed_exe_file_vma(mm);
		fput(new->vm_file);
	}
2019
	unlink_anon_vmas(new);
2020 2021 2022 2023 2024 2025
 out_free_mpol:
	mpol_put(pol);
 out_free_vma:
	kmem_cache_free(vm_area_cachep, new);
 out_err:
	return err;
L
Linus Torvalds 已提交
2026 2027
}

2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040
/*
 * Split a vma into two pieces at address 'addr', a new vma is allocated
 * either for the first part or the tail.
 */
int split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
	      unsigned long addr, int new_below)
{
	if (mm->map_count >= sysctl_max_map_count)
		return -ENOMEM;

	return __split_vma(mm, vma, addr, new_below);
}

L
Linus Torvalds 已提交
2041 2042 2043 2044 2045 2046 2047 2048
/* Munmap is split into 2 main parts -- this part which finds
 * what needs doing, and the areas themselves, which do the
 * work.  This now handles partial unmappings.
 * Jeremy Fitzhardinge <jeremy@goop.org>
 */
int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
{
	unsigned long end;
2049
	struct vm_area_struct *vma, *prev, *last;
L
Linus Torvalds 已提交
2050 2051 2052 2053 2054 2055 2056 2057

	if ((start & ~PAGE_MASK) || start > TASK_SIZE || len > TASK_SIZE-start)
		return -EINVAL;

	if ((len = PAGE_ALIGN(len)) == 0)
		return -EINVAL;

	/* Find the first overlapping VMA */
2058 2059
	vma = find_vma_prev(mm, start, &prev);
	if (!vma)
L
Linus Torvalds 已提交
2060
		return 0;
2061
	/* we have  start < vma->vm_end  */
L
Linus Torvalds 已提交
2062 2063 2064

	/* if it doesn't overlap, we have nothing.. */
	end = start + len;
2065
	if (vma->vm_start >= end)
L
Linus Torvalds 已提交
2066 2067 2068 2069 2070 2071 2072 2073 2074
		return 0;

	/*
	 * If we need to split any vma, do it now to save pain later.
	 *
	 * Note: mremap's move_vma VM_ACCOUNT handling assumes a partially
	 * unmapped vm_area_struct will remain in use: so lower split_vma
	 * places tmp vma above, and higher split_vma places tmp vma below.
	 */
2075
	if (start > vma->vm_start) {
2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086
		int error;

		/*
		 * Make sure that map_count on return from munmap() will
		 * not exceed its limit; but let map_count go just above
		 * its limit temporarily, to help free resources as expected.
		 */
		if (end < vma->vm_end && mm->map_count >= sysctl_max_map_count)
			return -ENOMEM;

		error = __split_vma(mm, vma, start, 0);
L
Linus Torvalds 已提交
2087 2088
		if (error)
			return error;
2089
		prev = vma;
L
Linus Torvalds 已提交
2090 2091 2092 2093 2094
	}

	/* Does it split the last one? */
	last = find_vma(mm, end);
	if (last && end > last->vm_start) {
2095
		int error = __split_vma(mm, last, end, 1);
L
Linus Torvalds 已提交
2096 2097 2098
		if (error)
			return error;
	}
2099
	vma = prev? prev->vm_next: mm->mmap;
L
Linus Torvalds 已提交
2100

2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114
	/*
	 * unlock any mlock()ed ranges before detaching vmas
	 */
	if (mm->locked_vm) {
		struct vm_area_struct *tmp = vma;
		while (tmp && tmp->vm_start < end) {
			if (tmp->vm_flags & VM_LOCKED) {
				mm->locked_vm -= vma_pages(tmp);
				munlock_vma_pages_all(tmp);
			}
			tmp = tmp->vm_next;
		}
	}

L
Linus Torvalds 已提交
2115 2116 2117
	/*
	 * Remove the vma's, and unmap the actual pages
	 */
2118 2119
	detach_vmas_to_be_unmapped(mm, vma, prev, end);
	unmap_region(mm, vma, prev, start, end);
L
Linus Torvalds 已提交
2120 2121

	/* Fix up all other VM information */
2122
	remove_vma_list(mm, vma);
L
Linus Torvalds 已提交
2123 2124 2125 2126 2127 2128

	return 0;
}

EXPORT_SYMBOL(do_munmap);

2129
SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len)
L
Linus Torvalds 已提交
2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143
{
	int ret;
	struct mm_struct *mm = current->mm;

	profile_munmap(addr);

	down_write(&mm->mmap_sem);
	ret = do_munmap(mm, addr, len);
	up_write(&mm->mmap_sem);
	return ret;
}

static inline void verify_mm_writelocked(struct mm_struct *mm)
{
2144
#ifdef CONFIG_DEBUG_VM
L
Linus Torvalds 已提交
2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163
	if (unlikely(down_read_trylock(&mm->mmap_sem))) {
		WARN_ON(1);
		up_read(&mm->mmap_sem);
	}
#endif
}

/*
 *  this is really a simplified "do_mmap".  it only handles
 *  anonymous maps.  eventually we may be able to do some
 *  brk-specific accounting here.
 */
unsigned long do_brk(unsigned long addr, unsigned long len)
{
	struct mm_struct * mm = current->mm;
	struct vm_area_struct * vma, * prev;
	unsigned long flags;
	struct rb_node ** rb_link, * rb_parent;
	pgoff_t pgoff = addr >> PAGE_SHIFT;
2164
	int error;
L
Linus Torvalds 已提交
2165 2166 2167 2168 2169

	len = PAGE_ALIGN(len);
	if (!len)
		return addr;

2170
	error = security_file_mmap(NULL, 0, 0, 0, addr, 1);
2171 2172 2173
	if (error)
		return error;

2174 2175
	flags = VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;

A
Al Viro 已提交
2176 2177
	error = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED);
	if (error & ~PAGE_MASK)
2178 2179
		return error;

L
Linus Torvalds 已提交
2180 2181 2182 2183 2184
	/*
	 * mlock MCL_FUTURE?
	 */
	if (mm->def_flags & VM_LOCKED) {
		unsigned long locked, lock_limit;
2185 2186
		locked = len >> PAGE_SHIFT;
		locked += mm->locked_vm;
J
Jiri Slaby 已提交
2187
		lock_limit = rlimit(RLIMIT_MEMLOCK);
2188
		lock_limit >>= PAGE_SHIFT;
L
Linus Torvalds 已提交
2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210
		if (locked > lock_limit && !capable(CAP_IPC_LOCK))
			return -EAGAIN;
	}

	/*
	 * mm->mmap_sem is required to protect against another thread
	 * changing the mappings in case we sleep.
	 */
	verify_mm_writelocked(mm);

	/*
	 * Clear old maps.  this also does some error checking for us
	 */
 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 limits *after* clearing old maps... */
A
akpm@osdl.org 已提交
2211
	if (!may_expand_vm(mm, len >> PAGE_SHIFT))
L
Linus Torvalds 已提交
2212 2213 2214 2215 2216 2217 2218 2219 2220
		return -ENOMEM;

	if (mm->map_count > sysctl_max_map_count)
		return -ENOMEM;

	if (security_vm_enough_memory(len >> PAGE_SHIFT))
		return -ENOMEM;

	/* Can we just expand an old private anonymous mapping? */
2221 2222 2223
	vma = vma_merge(mm, prev, addr, addr + len, flags,
					NULL, NULL, pgoff, NULL);
	if (vma)
L
Linus Torvalds 已提交
2224 2225 2226 2227 2228
		goto out;

	/*
	 * create a vma struct for an anonymous mapping
	 */
P
Pekka Enberg 已提交
2229
	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
2230 2231 2232 2233 2234
	if (!vma) {
		vm_unacct_memory(len >> PAGE_SHIFT);
		return -ENOMEM;
	}

2235
	INIT_LIST_HEAD(&vma->anon_vma_chain);
L
Linus Torvalds 已提交
2236 2237 2238 2239 2240
	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_pgoff = pgoff;
	vma->vm_flags = flags;
2241
	vma->vm_page_prot = vm_get_page_prot(flags);
L
Linus Torvalds 已提交
2242 2243
	vma_link(mm, vma, prev, rb_link, rb_parent);
out:
2244
	perf_event_mmap(vma);
L
Linus Torvalds 已提交
2245 2246
	mm->total_vm += len >> PAGE_SHIFT;
	if (flags & VM_LOCKED) {
2247 2248
		if (!mlock_vma_pages_range(vma, addr, addr + len))
			mm->locked_vm += (len >> PAGE_SHIFT);
L
Linus Torvalds 已提交
2249 2250 2251 2252 2253 2254 2255 2256 2257 2258
	}
	return addr;
}

EXPORT_SYMBOL(do_brk);

/* Release all mmaps. */
void exit_mmap(struct mm_struct *mm)
{
	struct mmu_gather *tlb;
2259
	struct vm_area_struct *vma;
L
Linus Torvalds 已提交
2260
	unsigned long nr_accounted = 0;
2261
	unsigned long end;
L
Linus Torvalds 已提交
2262

2263
	/* mm's last user has gone, and its about to be pulled down */
A
Andrea Arcangeli 已提交
2264
	mmu_notifier_release(mm);
2265

2266 2267 2268 2269 2270 2271 2272 2273
	if (mm->locked_vm) {
		vma = mm->mmap;
		while (vma) {
			if (vma->vm_flags & VM_LOCKED)
				munlock_vma_pages_all(vma);
			vma = vma->vm_next;
		}
	}
2274 2275 2276

	arch_exit_mmap(mm);

2277
	vma = mm->mmap;
2278 2279 2280
	if (!vma)	/* Can happen if dup_mmap() received an OOM */
		return;

L
Linus Torvalds 已提交
2281 2282
	lru_add_drain();
	flush_cache_mm(mm);
2283
	tlb = tlb_gather_mmu(mm, 1);
2284
	/* update_hiwater_rss(mm) here? but nobody should be looking */
2285
	/* Use -1 here to ensure all VMAs in the mm are unmapped */
2286
	end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL);
L
Linus Torvalds 已提交
2287
	vm_unacct_memory(nr_accounted);
H
Hugh Dickins 已提交
2288

2289
	free_pgtables(tlb, vma, FIRST_USER_ADDRESS, 0);
2290
	tlb_finish_mmu(tlb, 0, end);
L
Linus Torvalds 已提交
2291 2292

	/*
2293 2294
	 * Walk the list again, actually closing and freeing it,
	 * with preemption enabled, without holding any MM locks.
L
Linus Torvalds 已提交
2295
	 */
2296 2297
	while (vma)
		vma = remove_vma(vma);
2298

2299
	BUG_ON(mm->nr_ptes > (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT);
L
Linus Torvalds 已提交
2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329
}

/* Insert vm structure into process list sorted by address
 * and into the inode's i_mmap tree.  If vm_file is non-NULL
 * then i_mmap_lock is taken here.
 */
int insert_vm_struct(struct mm_struct * mm, struct vm_area_struct * vma)
{
	struct vm_area_struct * __vma, * prev;
	struct rb_node ** rb_link, * rb_parent;

	/*
	 * The vm_pgoff of a purely anonymous vma should be irrelevant
	 * until its first write fault, when page's anon_vma and index
	 * are set.  But now set the vm_pgoff it will almost certainly
	 * end up with (unless mremap moves it elsewhere before that
	 * first wfault), so /proc/pid/maps tells a consistent story.
	 *
	 * By setting it to reflect the virtual start address of the
	 * vma, merges and splits can happen in a seamless way, just
	 * using the existing file pgoff checks and manipulations.
	 * Similarly in do_mmap_pgoff and in do_brk.
	 */
	if (!vma->vm_file) {
		BUG_ON(vma->anon_vma);
		vma->vm_pgoff = vma->vm_start >> PAGE_SHIFT;
	}
	__vma = find_vma_prepare(mm,vma->vm_start,&prev,&rb_link,&rb_parent);
	if (__vma && __vma->vm_start < vma->vm_end)
		return -ENOMEM;
2330
	if ((vma->vm_flags & VM_ACCOUNT) &&
2331
	     security_vm_enough_memory_mm(mm, vma_pages(vma)))
2332
		return -ENOMEM;
L
Linus Torvalds 已提交
2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368
	vma_link(mm, vma, prev, rb_link, rb_parent);
	return 0;
}

/*
 * Copy the vma structure to a new location in the same mm,
 * prior to moving page table entries, to effect an mremap move.
 */
struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
	unsigned long addr, unsigned long len, pgoff_t pgoff)
{
	struct vm_area_struct *vma = *vmap;
	unsigned long vma_start = vma->vm_start;
	struct mm_struct *mm = vma->vm_mm;
	struct vm_area_struct *new_vma, *prev;
	struct rb_node **rb_link, *rb_parent;
	struct mempolicy *pol;

	/*
	 * If anonymous vma has not yet been faulted, update new pgoff
	 * to match new location, to increase its chance of merging.
	 */
	if (!vma->vm_file && !vma->anon_vma)
		pgoff = addr >> PAGE_SHIFT;

	find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
	new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
	if (new_vma) {
		/*
		 * Source vma may have been merged into new_vma
		 */
		if (vma_start >= new_vma->vm_start &&
		    vma_start < new_vma->vm_end)
			*vmap = new_vma;
	} else {
2369
		new_vma = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
L
Linus Torvalds 已提交
2370 2371
		if (new_vma) {
			*new_vma = *vma;
2372
			pol = mpol_dup(vma_policy(vma));
2373 2374 2375 2376 2377
			if (IS_ERR(pol))
				goto out_free_vma;
			INIT_LIST_HEAD(&new_vma->anon_vma_chain);
			if (anon_vma_clone(new_vma, vma))
				goto out_free_mempol;
L
Linus Torvalds 已提交
2378 2379 2380 2381
			vma_set_policy(new_vma, pol);
			new_vma->vm_start = addr;
			new_vma->vm_end = addr + len;
			new_vma->vm_pgoff = pgoff;
M
Matt Helsley 已提交
2382
			if (new_vma->vm_file) {
L
Linus Torvalds 已提交
2383
				get_file(new_vma->vm_file);
M
Matt Helsley 已提交
2384 2385 2386
				if (vma->vm_flags & VM_EXECUTABLE)
					added_exe_file_vma(mm);
			}
L
Linus Torvalds 已提交
2387 2388 2389 2390 2391 2392
			if (new_vma->vm_ops && new_vma->vm_ops->open)
				new_vma->vm_ops->open(new_vma);
			vma_link(mm, new_vma, prev, rb_link, rb_parent);
		}
	}
	return new_vma;
2393 2394 2395 2396 2397 2398

 out_free_mempol:
	mpol_put(pol);
 out_free_vma:
	kmem_cache_free(vm_area_cachep, new_vma);
	return NULL;
L
Linus Torvalds 已提交
2399
}
A
akpm@osdl.org 已提交
2400 2401 2402 2403 2404 2405 2406 2407 2408 2409

/*
 * Return true if the calling process may expand its vm space by the passed
 * number of pages
 */
int may_expand_vm(struct mm_struct *mm, unsigned long npages)
{
	unsigned long cur = mm->total_vm;	/* pages */
	unsigned long lim;

J
Jiri Slaby 已提交
2410
	lim = rlimit(RLIMIT_AS) >> PAGE_SHIFT;
A
akpm@osdl.org 已提交
2411 2412 2413 2414 2415

	if (cur + npages > lim)
		return 0;
	return 1;
}
2416 2417


N
Nick Piggin 已提交
2418 2419
static int special_mapping_fault(struct vm_area_struct *vma,
				struct vm_fault *vmf)
2420
{
N
Nick Piggin 已提交
2421
	pgoff_t pgoff;
2422 2423
	struct page **pages;

N
Nick Piggin 已提交
2424 2425 2426 2427 2428 2429 2430
	/*
	 * special mappings have no vm_file, and in that case, the mm
	 * uses vm_pgoff internally. So we have to subtract it from here.
	 * We are allowed to do this because we are the mm; do not copy
	 * this code into drivers!
	 */
	pgoff = vmf->pgoff - vma->vm_pgoff;
2431

N
Nick Piggin 已提交
2432 2433
	for (pages = vma->vm_private_data; pgoff && *pages; ++pages)
		pgoff--;
2434 2435 2436 2437

	if (*pages) {
		struct page *page = *pages;
		get_page(page);
N
Nick Piggin 已提交
2438 2439
		vmf->page = page;
		return 0;
2440 2441
	}

N
Nick Piggin 已提交
2442
	return VM_FAULT_SIGBUS;
2443 2444 2445 2446 2447 2448 2449 2450 2451
}

/*
 * Having a close hook prevents vma merging regardless of flags.
 */
static void special_mapping_close(struct vm_area_struct *vma)
{
}

2452
static const struct vm_operations_struct special_mapping_vmops = {
2453
	.close = special_mapping_close,
N
Nick Piggin 已提交
2454
	.fault = special_mapping_fault,
2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469
};

/*
 * Called with mm->mmap_sem held for writing.
 * Insert a new vma covering the given region, with the given flags.
 * Its pages are supplied by the given array of struct page *.
 * The array can be shorter than len >> PAGE_SHIFT if it's null-terminated.
 * The region past the last page supplied will always produce SIGBUS.
 * The array pointer and the pages it points to are assumed to stay alive
 * for as long as this mapping might exist.
 */
int install_special_mapping(struct mm_struct *mm,
			    unsigned long addr, unsigned long len,
			    unsigned long vm_flags, struct page **pages)
{
2470
	int ret;
2471 2472 2473 2474 2475 2476
	struct vm_area_struct *vma;

	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
	if (unlikely(vma == NULL))
		return -ENOMEM;

2477
	INIT_LIST_HEAD(&vma->anon_vma_chain);
2478 2479 2480 2481
	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;

2482
	vma->vm_flags = vm_flags | mm->def_flags | VM_DONTEXPAND;
2483
	vma->vm_page_prot = vm_get_page_prot(vma->vm_flags);
2484 2485 2486 2487

	vma->vm_ops = &special_mapping_vmops;
	vma->vm_private_data = pages;

2488 2489 2490 2491 2492 2493 2494
	ret = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1);
	if (ret)
		goto out;

	ret = insert_vm_struct(mm, vma);
	if (ret)
		goto out;
2495 2496 2497

	mm->total_vm += len >> PAGE_SHIFT;

2498
	perf_event_mmap(vma);
2499

2500
	return 0;
2501 2502 2503 2504

out:
	kmem_cache_free(vm_area_cachep, vma);
	return ret;
2505
}
2506 2507 2508

static DEFINE_MUTEX(mm_all_locks_mutex);

2509
static void vm_lock_anon_vma(struct mm_struct *mm, struct anon_vma *anon_vma)
2510
{
2511
	if (!test_bit(0, (unsigned long *) &anon_vma->root->head.next)) {
2512 2513 2514 2515
		/*
		 * The LSB of head.next can't change from under us
		 * because we hold the mm_all_locks_mutex.
		 */
2516
		spin_lock_nest_lock(&anon_vma->root->lock, &mm->mmap_sem);
2517 2518
		/*
		 * We can safely modify head.next after taking the
2519
		 * anon_vma->root->lock. If some other vma in this mm shares
2520 2521 2522 2523
		 * the same anon_vma we won't take it again.
		 *
		 * No need of atomic instructions here, head.next
		 * can't change from under us thanks to the
2524
		 * anon_vma->root->lock.
2525 2526
		 */
		if (__test_and_set_bit(0, (unsigned long *)
2527
				       &anon_vma->root->head.next))
2528 2529 2530 2531
			BUG();
	}
}

2532
static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping)
2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545
{
	if (!test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
		/*
		 * AS_MM_ALL_LOCKS can't change from under us because
		 * we hold the mm_all_locks_mutex.
		 *
		 * Operations on ->flags have to be atomic because
		 * even if AS_MM_ALL_LOCKS is stable thanks to the
		 * mm_all_locks_mutex, there may be other cpus
		 * changing other bitflags in parallel to us.
		 */
		if (test_and_set_bit(AS_MM_ALL_LOCKS, &mapping->flags))
			BUG();
2546
		spin_lock_nest_lock(&mapping->i_mmap_lock, &mm->mmap_sem);
2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584
	}
}

/*
 * This operation locks against the VM for all pte/vma/mm related
 * operations that could ever happen on a certain mm. This includes
 * vmtruncate, try_to_unmap, and all page faults.
 *
 * The caller must take the mmap_sem in write mode before calling
 * mm_take_all_locks(). The caller isn't allowed to release the
 * mmap_sem until mm_drop_all_locks() returns.
 *
 * mmap_sem in write mode is required in order to block all operations
 * that could modify pagetables and free pages without need of
 * altering the vma layout (for example populate_range() with
 * nonlinear vmas). It's also needed in write mode to avoid new
 * anon_vmas to be associated with existing vmas.
 *
 * A single task can't take more than one mm_take_all_locks() in a row
 * or it would deadlock.
 *
 * The LSB in anon_vma->head.next and the AS_MM_ALL_LOCKS bitflag in
 * mapping->flags avoid to take the same lock twice, if more than one
 * vma in this mm is backed by the same anon_vma or address_space.
 *
 * We can take all the locks in random order because the VM code
 * taking i_mmap_lock or anon_vma->lock outside the mmap_sem never
 * takes more than one of them in a row. Secondly we're protected
 * against a concurrent mm_take_all_locks() by the mm_all_locks_mutex.
 *
 * mm_take_all_locks() and mm_drop_all_locks are expensive operations
 * that may have to take thousand of locks.
 *
 * mm_take_all_locks() can fail if it's interrupted by signals.
 */
int mm_take_all_locks(struct mm_struct *mm)
{
	struct vm_area_struct *vma;
2585
	struct anon_vma_chain *avc;
2586 2587 2588 2589 2590 2591 2592 2593 2594 2595
	int ret = -EINTR;

	BUG_ON(down_read_trylock(&mm->mmap_sem));

	mutex_lock(&mm_all_locks_mutex);

	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (signal_pending(current))
			goto out_unlock;
		if (vma->vm_file && vma->vm_file->f_mapping)
2596
			vm_lock_mapping(mm, vma->vm_file->f_mapping);
2597
	}
2598 2599 2600 2601 2602

	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (signal_pending(current))
			goto out_unlock;
		if (vma->anon_vma)
2603 2604
			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
				vm_lock_anon_vma(mm, avc->anon_vma);
2605
	}
2606

2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617
	ret = 0;

out_unlock:
	if (ret)
		mm_drop_all_locks(mm);

	return ret;
}

static void vm_unlock_anon_vma(struct anon_vma *anon_vma)
{
2618
	if (test_bit(0, (unsigned long *) &anon_vma->root->head.next)) {
2619 2620 2621 2622 2623 2624 2625 2626 2627 2628
		/*
		 * The LSB of head.next can't change to 0 from under
		 * us because we hold the mm_all_locks_mutex.
		 *
		 * We must however clear the bitflag before unlocking
		 * the vma so the users using the anon_vma->head will
		 * never see our bitflag.
		 *
		 * No need of atomic instructions here, head.next
		 * can't change from under us until we release the
2629
		 * anon_vma->root->lock.
2630 2631
		 */
		if (!__test_and_clear_bit(0, (unsigned long *)
2632
					  &anon_vma->root->head.next))
2633
			BUG();
2634
		anon_vma_unlock(anon_vma);
2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658
	}
}

static void vm_unlock_mapping(struct address_space *mapping)
{
	if (test_bit(AS_MM_ALL_LOCKS, &mapping->flags)) {
		/*
		 * AS_MM_ALL_LOCKS can't change to 0 from under us
		 * because we hold the mm_all_locks_mutex.
		 */
		spin_unlock(&mapping->i_mmap_lock);
		if (!test_and_clear_bit(AS_MM_ALL_LOCKS,
					&mapping->flags))
			BUG();
	}
}

/*
 * The mmap_sem cannot be released by the caller until
 * mm_drop_all_locks() returns.
 */
void mm_drop_all_locks(struct mm_struct *mm)
{
	struct vm_area_struct *vma;
2659
	struct anon_vma_chain *avc;
2660 2661 2662 2663 2664 2665

	BUG_ON(down_read_trylock(&mm->mmap_sem));
	BUG_ON(!mutex_is_locked(&mm_all_locks_mutex));

	for (vma = mm->mmap; vma; vma = vma->vm_next) {
		if (vma->anon_vma)
2666 2667
			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
				vm_unlock_anon_vma(avc->anon_vma);
2668 2669 2670 2671 2672 2673
		if (vma->vm_file && vma->vm_file->f_mapping)
			vm_unlock_mapping(vma->vm_file->f_mapping);
	}

	mutex_unlock(&mm_all_locks_mutex);
}
2674 2675 2676 2677 2678 2679

/*
 * initialise the VMA slab
 */
void __init mmap_init(void)
{
2680 2681 2682 2683
	int ret;

	ret = percpu_counter_init(&vm_committed_as, 0);
	VM_BUG_ON(ret);
2684
}