util.c 28.1 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-only
2
#include <linux/mm.h>
3 4
#include <linux/slab.h>
#include <linux/string.h>
5
#include <linux/compiler.h>
6
#include <linux/export.h>
Davi Arnaut's avatar
Davi Arnaut committed
7
#include <linux/err.h>
8
#include <linux/sched.h>
9
#include <linux/sched/mm.h>
10
#include <linux/sched/signal.h>
11
#include <linux/sched/task_stack.h>
Al Viro's avatar
Al Viro committed
12
#include <linux/security.h>
Shaohua Li's avatar
Shaohua Li committed
13
#include <linux/swap.h>
14
#include <linux/swapops.h>
15 16
#include <linux/mman.h>
#include <linux/hugetlb.h>
Al Viro's avatar
Al Viro committed
17
#include <linux/vmalloc.h>
18
#include <linux/userfaultfd_k.h>
19
#include <linux/elf.h>
20 21
#include <linux/elf-randomize.h>
#include <linux/personality.h>
22
#include <linux/random.h>
23 24 25
#include <linux/processor.h>
#include <linux/sizes.h>
#include <linux/compat.h>
26

27
#include <linux/uaccess.h>
28

29 30
#include "internal.h"

Andrzej Hajda's avatar
Andrzej Hajda committed
31 32 33 34 35 36 37 38 39 40 41 42 43
/**
 * kfree_const - conditionally free memory
 * @x: pointer to the memory
 *
 * Function calls kfree only if @x is not in .rodata section.
 */
void kfree_const(const void *x)
{
	if (!is_kernel_rodata((unsigned long)x))
		kfree(x);
}
EXPORT_SYMBOL(kfree_const);

44 45 46 47
/**
 * kstrdup - allocate space for and copy an existing string
 * @s: the string to duplicate
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
48 49
 *
 * Return: newly allocated copy of @s or %NULL in case of error
50 51 52 53 54 55 56 57 58 59
 */
char *kstrdup(const char *s, gfp_t gfp)
{
	size_t len;
	char *buf;

	if (!s)
		return NULL;

	len = strlen(s) + 1;
60
	buf = kmalloc_track_caller(len, gfp);
61 62 63 64 65
	if (buf)
		memcpy(buf, s, len);
	return buf;
}
EXPORT_SYMBOL(kstrdup);
Davi Arnaut's avatar
Davi Arnaut committed
66

Andrzej Hajda's avatar
Andrzej Hajda committed
67 68 69 70 71
/**
 * kstrdup_const - conditionally duplicate an existing const string
 * @s: the string to duplicate
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
 *
72 73
 * Note: Strings allocated by kstrdup_const should be freed by kfree_const and
 * must not be passed to krealloc().
74 75 76
 *
 * Return: source string if it is in .rodata section otherwise
 * fallback to kstrdup.
Andrzej Hajda's avatar
Andrzej Hajda committed
77 78 79 80 81 82 83 84 85 86
 */
const char *kstrdup_const(const char *s, gfp_t gfp)
{
	if (is_kernel_rodata((unsigned long)s))
		return s;

	return kstrdup(s, gfp);
}
EXPORT_SYMBOL(kstrdup_const);

Jeremy Fitzhardinge's avatar
Jeremy Fitzhardinge committed
87 88 89 90 91
/**
 * kstrndup - allocate space for and copy an existing string
 * @s: the string to duplicate
 * @max: read at most @max chars from @s
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
92 93
 *
 * Note: Use kmemdup_nul() instead if the size is known exactly.
94 95
 *
 * Return: newly allocated copy of @s or %NULL in case of error
Jeremy Fitzhardinge's avatar
Jeremy Fitzhardinge committed
96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
 */
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{
	size_t len;
	char *buf;

	if (!s)
		return NULL;

	len = strnlen(s, max);
	buf = kmalloc_track_caller(len+1, gfp);
	if (buf) {
		memcpy(buf, s, len);
		buf[len] = '\0';
	}
	return buf;
}
EXPORT_SYMBOL(kstrndup);

Alexey Dobriyan's avatar
Alexey Dobriyan committed
115 116 117 118 119 120
/**
 * kmemdup - duplicate region of memory
 *
 * @src: memory region to duplicate
 * @len: memory region length
 * @gfp: GFP mask to use
121 122
 *
 * Return: newly allocated copy of @src or %NULL in case of error
Alexey Dobriyan's avatar
Alexey Dobriyan committed
123 124 125 126 127
 */
void *kmemdup(const void *src, size_t len, gfp_t gfp)
{
	void *p;

128
	p = kmalloc_track_caller(len, gfp);
Alexey Dobriyan's avatar
Alexey Dobriyan committed
129 130 131 132 133 134
	if (p)
		memcpy(p, src, len);
	return p;
}
EXPORT_SYMBOL(kmemdup);

135 136 137 138 139
/**
 * kmemdup_nul - Create a NUL-terminated string from unterminated data
 * @s: The data to stringify
 * @len: The size of the data
 * @gfp: the GFP mask used in the kmalloc() call when allocating memory
140 141 142
 *
 * Return: newly allocated copy of @s with NUL-termination or %NULL in
 * case of error
143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159
 */
char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
{
	char *buf;

	if (!s)
		return NULL;

	buf = kmalloc_track_caller(len + 1, gfp);
	if (buf) {
		memcpy(buf, s, len);
		buf[len] = '\0';
	}
	return buf;
}
EXPORT_SYMBOL(kmemdup_nul);

Li Zefan's avatar
Li Zefan committed
160 161 162 163 164 165
/**
 * memdup_user - duplicate memory region from user space
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
166
 * Return: an ERR_PTR() on failure.  Result is physically
Al Viro's avatar
Al Viro committed
167
 * contiguous, to be freed by kfree().
Li Zefan's avatar
Li Zefan committed
168 169 170 171 172
 */
void *memdup_user(const void __user *src, size_t len)
{
	void *p;

173
	p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN);
Li Zefan's avatar
Li Zefan committed
174 175 176 177 178 179 180 181 182 183 184 185
	if (!p)
		return ERR_PTR(-ENOMEM);

	if (copy_from_user(p, src, len)) {
		kfree(p);
		return ERR_PTR(-EFAULT);
	}

	return p;
}
EXPORT_SYMBOL(memdup_user);

Al Viro's avatar
Al Viro committed
186 187 188 189 190 191
/**
 * vmemdup_user - duplicate memory region from user space
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
192
 * Return: an ERR_PTR() on failure.  Result may be not
Al Viro's avatar
Al Viro committed
193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211
 * physically contiguous.  Use kvfree() to free.
 */
void *vmemdup_user(const void __user *src, size_t len)
{
	void *p;

	p = kvmalloc(len, GFP_USER);
	if (!p)
		return ERR_PTR(-ENOMEM);

	if (copy_from_user(p, src, len)) {
		kvfree(p);
		return ERR_PTR(-EFAULT);
	}

	return p;
}
EXPORT_SYMBOL(vmemdup_user);

212
/**
Davi Arnaut's avatar
Davi Arnaut committed
213 214 215
 * strndup_user - duplicate an existing string from user space
 * @s: The string to duplicate
 * @n: Maximum number of bytes to copy, including the trailing NUL.
216
 *
217
 * Return: newly allocated copy of @s or an ERR_PTR() in case of error
Davi Arnaut's avatar
Davi Arnaut committed
218 219 220 221 222 223 224 225 226 227 228 229 230 231
 */
char *strndup_user(const char __user *s, long n)
{
	char *p;
	long length;

	length = strnlen_user(s, n);

	if (!length)
		return ERR_PTR(-EFAULT);

	if (length > n)
		return ERR_PTR(-EINVAL);

Julia Lawall's avatar
Julia Lawall committed
232
	p = memdup_user(s, length);
Davi Arnaut's avatar
Davi Arnaut committed
233

Julia Lawall's avatar
Julia Lawall committed
234 235
	if (IS_ERR(p))
		return p;
Davi Arnaut's avatar
Davi Arnaut committed
236 237 238 239 240 241

	p[length - 1] = '\0';

	return p;
}
EXPORT_SYMBOL(strndup_user);
242

Al Viro's avatar
Al Viro committed
243 244 245 246 247 248
/**
 * memdup_user_nul - duplicate memory region from user space and NUL-terminate
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
249
 * Return: an ERR_PTR() on failure.
Al Viro's avatar
Al Viro committed
250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273
 */
void *memdup_user_nul(const void __user *src, size_t len)
{
	char *p;

	/*
	 * Always use GFP_KERNEL, since copy_from_user() can sleep and
	 * cause pagefault, which makes it pointless to use GFP_NOFS
	 * or GFP_ATOMIC.
	 */
	p = kmalloc_track_caller(len + 1, GFP_KERNEL);
	if (!p)
		return ERR_PTR(-ENOMEM);

	if (copy_from_user(p, src, len)) {
		kfree(p);
		return ERR_PTR(-EFAULT);
	}
	p[len] = '\0';

	return p;
}
EXPORT_SYMBOL(memdup_user_nul);

274
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
275
		struct vm_area_struct *prev)
276 277 278 279 280 281 282 283
{
	struct vm_area_struct *next;

	vma->vm_prev = prev;
	if (prev) {
		next = prev->vm_next;
		prev->vm_next = vma;
	} else {
284
		next = mm->mmap;
285 286 287 288 289 290 291
		mm->mmap = vma;
	}
	vma->vm_next = next;
	if (next)
		next->vm_prev = vma;
}

292 293 294 295 296 297 298 299 300 301 302 303 304 305
void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma)
{
	struct vm_area_struct *prev, *next;

	next = vma->vm_next;
	prev = vma->vm_prev;
	if (prev)
		prev->vm_next = next;
	else
		mm->mmap = next;
	if (next)
		next->vm_prev = prev;
}

306
/* Check if the vma is being used as a stack by this task */
307
int vma_is_stack_for_current(struct vm_area_struct *vma)
308
{
309 310
	struct task_struct * __maybe_unused t = current;

311 312 313
	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}

314 315 316 317 318 319 320 321 322 323 324 325
/*
 * Change backing file, only valid to use during initial VMA setup.
 */
void vma_set_file(struct vm_area_struct *vma, struct file *file)
{
	/* Changing an anonymous vma with this is illegal */
	get_file(file);
	swap(vma->vm_file, file);
	fput(file);
}
EXPORT_SYMBOL(vma_set_file);

326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345
#ifndef STACK_RND_MASK
#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12))     /* 8MB of VA */
#endif

unsigned long randomize_stack_top(unsigned long stack_top)
{
	unsigned long random_variable = 0;

	if (current->flags & PF_RANDOMIZE) {
		random_variable = get_random_long();
		random_variable &= STACK_RND_MASK;
		random_variable <<= PAGE_SHIFT;
	}
#ifdef CONFIG_STACK_GROWSUP
	return PAGE_ALIGN(stack_top) + random_variable;
#else
	return PAGE_ALIGN(stack_top) - random_variable;
#endif
}

346
#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
347 348 349 350 351 352 353 354 355
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
	/* Is the current task 32bit ? */
	if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task())
		return randomize_page(mm->brk, SZ_32M);

	return randomize_page(mm->brk, SZ_1G);
}

356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424
unsigned long arch_mmap_rnd(void)
{
	unsigned long rnd;

#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
	if (is_compat_task())
		rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
	else
#endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */
		rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);

	return rnd << PAGE_SHIFT;
}

static int mmap_is_legacy(struct rlimit *rlim_stack)
{
	if (current->personality & ADDR_COMPAT_LAYOUT)
		return 1;

	if (rlim_stack->rlim_cur == RLIM_INFINITY)
		return 1;

	return sysctl_legacy_va_layout;
}

/*
 * Leave enough space between the mmap area and the stack to honour ulimit in
 * the face of randomisation.
 */
#define MIN_GAP		(SZ_128M)
#define MAX_GAP		(STACK_TOP / 6 * 5)

static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
{
	unsigned long gap = rlim_stack->rlim_cur;
	unsigned long pad = stack_guard_gap;

	/* Account for stack randomization if necessary */
	if (current->flags & PF_RANDOMIZE)
		pad += (STACK_RND_MASK << PAGE_SHIFT);

	/* Values close to RLIM_INFINITY can overflow. */
	if (gap + pad > gap)
		gap += pad;

	if (gap < MIN_GAP)
		gap = MIN_GAP;
	else if (gap > MAX_GAP)
		gap = MAX_GAP;

	return PAGE_ALIGN(STACK_TOP - gap - rnd);
}

void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
	unsigned long random_factor = 0UL;

	if (current->flags & PF_RANDOMIZE)
		random_factor = arch_mmap_rnd();

	if (mmap_is_legacy(rlim_stack)) {
		mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
		mm->get_unmapped_area = arch_get_unmapped_area;
	} else {
		mm->mmap_base = mmap_base(random_factor, rlim_stack);
		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
	}
}
#elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
425
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
426 427 428 429 430
{
	mm->mmap_base = TASK_UNMAPPED_BASE;
	mm->get_unmapped_area = arch_get_unmapped_area;
}
#endif
431

432 433 434 435 436 437 438 439 440
/**
 * __account_locked_vm - account locked pages to an mm's locked_vm
 * @mm:          mm to account against
 * @pages:       number of pages to account
 * @inc:         %true if @pages should be considered positive, %false if not
 * @task:        task used to check RLIMIT_MEMLOCK
 * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
 *
 * Assumes @task and @mm are valid (i.e. at least one reference on each), and
441
 * that mmap_lock is held as writer.
442 443 444 445 446 447 448 449 450 451 452
 *
 * Return:
 * * 0       on success
 * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
 */
int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
			struct task_struct *task, bool bypass_rlim)
{
	unsigned long locked_vm, limit;
	int ret = 0;

453
	mmap_assert_write_locked(mm);
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496

	locked_vm = mm->locked_vm;
	if (inc) {
		if (!bypass_rlim) {
			limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
			if (locked_vm + pages > limit)
				ret = -ENOMEM;
		}
		if (!ret)
			mm->locked_vm = locked_vm + pages;
	} else {
		WARN_ON_ONCE(pages > locked_vm);
		mm->locked_vm = locked_vm - pages;
	}

	pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid,
		 (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT,
		 locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK),
		 ret ? " - exceeded" : "");

	return ret;
}
EXPORT_SYMBOL_GPL(__account_locked_vm);

/**
 * account_locked_vm - account locked pages to an mm's locked_vm
 * @mm:          mm to account against, may be NULL
 * @pages:       number of pages to account
 * @inc:         %true if @pages should be considered positive, %false if not
 *
 * Assumes a non-NULL @mm is valid (i.e. at least one reference on it).
 *
 * Return:
 * * 0       on success, or if mm is NULL
 * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
 */
int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc)
{
	int ret;

	if (pages == 0 || !mm)
		return 0;

497
	mmap_write_lock(mm);
498 499
	ret = __account_locked_vm(mm, pages, inc, current,
				  capable(CAP_IPC_LOCK));
500
	mmap_write_unlock(mm);
501 502 503 504 505

	return ret;
}
EXPORT_SYMBOL_GPL(account_locked_vm);

Al Viro's avatar
Al Viro committed
506 507
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
Michal Hocko's avatar
Michal Hocko committed
508
	unsigned long flag, unsigned long pgoff)
Al Viro's avatar
Al Viro committed
509 510 511
{
	unsigned long ret;
	struct mm_struct *mm = current->mm;
512
	unsigned long populate;
513
	LIST_HEAD(uf);
Al Viro's avatar
Al Viro committed
514 515 516

	ret = security_mmap_file(file, prot, flag);
	if (!ret) {
517
		if (mmap_write_lock_killable(mm))
Michal Hocko's avatar
Michal Hocko committed
518
			return -EINTR;
519 520
		ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate,
			      &uf);
521
		mmap_write_unlock(mm);
522
		userfaultfd_unmap_complete(mm, &uf);
523 524
		if (populate)
			mm_populate(ret, populate);
Al Viro's avatar
Al Viro committed
525 526 527 528 529 530 531 532 533 534
	}
	return ret;
}

unsigned long vm_mmap(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long offset)
{
	if (unlikely(offset + PAGE_ALIGN(len) < offset))
		return -EINVAL;
535
	if (unlikely(offset_in_page(offset)))
Al Viro's avatar
Al Viro committed
536 537
		return -EINVAL;

Michal Hocko's avatar
Michal Hocko committed
538
	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
Al Viro's avatar
Al Viro committed
539 540 541
}
EXPORT_SYMBOL(vm_mmap);

542 543 544 545 546 547 548 549 550 551
/**
 * kvmalloc_node - attempt to allocate physically contiguous memory, but upon
 * failure, fall back to non-contiguous (vmalloc) allocation.
 * @size: size of the request.
 * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL.
 * @node: numa node to allocate from
 *
 * Uses kmalloc to get the memory but if the allocation fails then falls back
 * to the vmalloc allocator. Use kvfree for freeing the memory.
 *
552
 * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier.
553 554
 * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is
 * preferable to the vmalloc fallback, due to visible performance drawbacks.
555
 *
556
 * Return: pointer to the allocated memory of %NULL in case of failure
557 558 559 560 561 562 563
 */
void *kvmalloc_node(size_t size, gfp_t flags, int node)
{
	gfp_t kmalloc_flags = flags;
	void *ret;

	/*
564 565 566 567 568
	 * We want to attempt a large physically contiguous block first because
	 * it is less likely to fragment multiple larger blocks and therefore
	 * contribute to a long term fragmentation less than vmalloc fallback.
	 * However make sure that larger requests are not too disruptive - no
	 * OOM killer and no allocation failure warnings as we have a fallback.
569
	 */
570 571 572
	if (size > PAGE_SIZE) {
		kmalloc_flags |= __GFP_NOWARN;

573
		if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL))
574
			kmalloc_flags |= __GFP_NORETRY;
575 576 577

		/* nofail semantic is implemented by the vmalloc fallback */
		kmalloc_flags &= ~__GFP_NOFAIL;
578
	}
579 580 581 582 583 584 585 586 587 588

	ret = kmalloc_node(size, kmalloc_flags, node);

	/*
	 * It doesn't really make sense to fallback to vmalloc for sub page
	 * requests
	 */
	if (ret || size <= PAGE_SIZE)
		return ret;

589 590 591 592
	/* Don't even allow crazy sizes */
	if (WARN_ON_ONCE(size > INT_MAX))
		return NULL;

593
	return __vmalloc_node(size, 1, flags, node,
594
			__builtin_return_address(0));
595 596 597
}
EXPORT_SYMBOL(kvmalloc_node);

598
/**
599 600
 * kvfree() - Free memory.
 * @addr: Pointer to allocated memory.
601
 *
602 603 604 605
 * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc().
 * It is slightly more efficient to use kfree() or vfree() if you are certain
 * that you know which one to use.
 *
606
 * Context: Either preemptible task context or not-NMI interrupt.
607
 */
Al Viro's avatar
Al Viro committed
608 609 610 611 612 613 614 615 616
void kvfree(const void *addr)
{
	if (is_vmalloc_addr(addr))
		vfree(addr);
	else
		kfree(addr);
}
EXPORT_SYMBOL(kvfree);

617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634
/**
 * kvfree_sensitive - Free a data object containing sensitive information.
 * @addr: address of the data object to be freed.
 * @len: length of the data object.
 *
 * Use the special memzero_explicit() function to clear the content of a
 * kvmalloc'ed object containing sensitive data to make sure that the
 * compiler won't optimize out the data clearing.
 */
void kvfree_sensitive(const void *addr, size_t len)
{
	if (likely(!ZERO_OR_NULL_PTR(addr))) {
		memzero_explicit((void *)addr, len);
		kvfree(addr);
	}
}
EXPORT_SYMBOL(kvfree_sensitive);

Dave Chinner's avatar
Dave Chinner committed
635 636 637 638 639 640 641 642 643 644 645 646 647 648 649
void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
{
	void *newp;

	if (oldsize >= newsize)
		return (void *)p;
	newp = kvmalloc(newsize, flags);
	if (!newp)
		return NULL;
	memcpy(newp, p, oldsize);
	kvfree(p);
	return newp;
}
EXPORT_SYMBOL(kvrealloc);

650 651 652
/* Neutral page->mapping pointer to address_space or anon_vma or other */
void *page_rmapping(struct page *page)
{
653
	return folio_raw_mapping(page_folio(page));
654 655
}

656 657 658 659 660
/**
 * folio_mapped - Is this folio mapped into userspace?
 * @folio: The folio.
 *
 * Return: True if any page in this folio is referenced by user page tables.
Andrew Morton's avatar
Andrew Morton committed
661
 */
662
bool folio_mapped(struct folio *folio)
Andrew Morton's avatar
Andrew Morton committed
663
{
664
	long i, nr;
Andrew Morton's avatar
Andrew Morton committed
665

666
	if (!folio_test_large(folio))
667 668
		return atomic_read(&folio->_mapcount) >= 0;
	if (atomic_read(folio_mapcount_ptr(folio)) >= 0)
Andrew Morton's avatar
Andrew Morton committed
669
		return true;
670
	if (folio_test_hugetlb(folio))
Andrew Morton's avatar
Andrew Morton committed
671
		return false;
672 673 674 675

	nr = folio_nr_pages(folio);
	for (i = 0; i < nr; i++) {
		if (atomic_read(&folio_page(folio, i)->_mapcount) >= 0)
Andrew Morton's avatar
Andrew Morton committed
676 677 678 679
			return true;
	}
	return false;
}
680
EXPORT_SYMBOL(folio_mapped);
Andrew Morton's avatar
Andrew Morton committed
681

682
struct anon_vma *folio_anon_vma(struct folio *folio)
683
{
684
	unsigned long mapping = (unsigned long)folio->mapping;
685 686 687

	if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
		return NULL;
688
	return (void *)(mapping - PAGE_MAPPING_ANON);
689 690
}

691 692 693 694 695 696 697 698 699 700 701 702 703
/**
 * folio_mapping - Find the mapping where this folio is stored.
 * @folio: The folio.
 *
 * For folios which are in the page cache, return the mapping that this
 * page belongs to.  Folios in the swap cache return the swap mapping
 * this page is stored in (which is different from the mapping for the
 * swap file or swap device where the data is stored).
 *
 * You can call this for folios which aren't in the swap cache or page
 * cache and it will return NULL.
 */
struct address_space *folio_mapping(struct folio *folio)
Shaohua Li's avatar
Shaohua Li committed
704
{
705 706
	struct address_space *mapping;

707
	/* This happens if someone calls flush_dcache_page on slab page */
708
	if (unlikely(folio_test_slab(folio)))
709 710
		return NULL;

711 712
	if (unlikely(folio_test_swapcache(folio)))
		return swap_address_space(folio_swap_entry(folio));
713

714
	mapping = folio->mapping;
715
	if ((unsigned long)mapping & PAGE_MAPPING_ANON)
716
		return NULL;
717 718

	return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS);
Shaohua Li's avatar
Shaohua Li committed
719
}
720
EXPORT_SYMBOL(folio_mapping);
Shaohua Li's avatar
Shaohua Li committed
721

722 723 724 725 726 727
/* Slow path of page_mapcount() for compound pages */
int __page_mapcount(struct page *page)
{
	int ret;

	ret = atomic_read(&page->_mapcount) + 1;
728 729 730 731 732 733
	/*
	 * For file THP page->_mapcount contains total number of mapping
	 * of the page: no need to look into compound_mapcount.
	 */
	if (!PageAnon(page) && !PageHuge(page))
		return ret;
734 735 736 737 738 739 740 741
	page = compound_head(page);
	ret += atomic_read(compound_mapcount_ptr(page)) + 1;
	if (PageDoubleMap(page))
		ret--;
	return ret;
}
EXPORT_SYMBOL_GPL(__page_mapcount);

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
/**
 * folio_mapcount() - Calculate the number of mappings of this folio.
 * @folio: The folio.
 *
 * A large folio tracks both how many times the entire folio is mapped,
 * and how many times each individual page in the folio is mapped.
 * This function calculates the total number of times the folio is
 * mapped.
 *
 * Return: The number of times this folio is mapped.
 */
int folio_mapcount(struct folio *folio)
{
	int i, compound, nr, ret;

	if (likely(!folio_test_large(folio)))
		return atomic_read(&folio->_mapcount) + 1;

	compound = folio_entire_mapcount(folio);
	nr = folio_nr_pages(folio);
	if (folio_test_hugetlb(folio))
		return compound;
	ret = compound;
	for (i = 0; i < nr; i++)
		ret += atomic_read(&folio_page(folio, i)->_mapcount) + 1;
	/* File pages has compound_mapcount included in _mapcount */
	if (!folio_test_anon(folio))
		return ret - compound * nr;
	if (folio_test_double_map(folio))
		ret -= nr;
	return ret;
}

775 776 777 778 779 780 781 782 783 784 785
/**
 * folio_copy - Copy the contents of one folio to another.
 * @dst: Folio to copy to.
 * @src: Folio to copy from.
 *
 * The bytes in the folio represented by @src are copied to @dst.
 * Assumes the caller has validated that @dst is at least as large as @src.
 * Can be called in atomic context for order-0 folios, but if the folio is
 * larger, it may sleep.
 */
void folio_copy(struct folio *dst, struct folio *src)
786
{
787 788
	long i = 0;
	long nr = folio_nr_pages(src);
789

790 791 792 793
	for (;;) {
		copy_highpage(folio_page(dst, i), folio_page(src, i));
		if (++i == nr)
			break;
794 795 796 797
		cond_resched();
	}
}

798 799 800 801 802 803 804
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
int sysctl_overcommit_ratio __read_mostly = 50;
unsigned long sysctl_overcommit_kbytes __read_mostly;
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */

805 806
int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
		size_t *lenp, loff_t *ppos)
807 808 809 810 811 812 813 814 815
{
	int ret;

	ret = proc_dointvec(table, write, buffer, lenp, ppos);
	if (ret == 0 && write)
		sysctl_overcommit_kbytes = 0;
	return ret;
}

816 817 818 819 820 821 822 823 824
static void sync_overcommit_as(struct work_struct *dummy)
{
	percpu_counter_sync(&vm_committed_as);
}

int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
		size_t *lenp, loff_t *ppos)
{
	struct ctl_table t;
825
	int new_policy = -1;
826 827 828 829 830 831
	int ret;

	/*
	 * The deviation of sync_overcommit_as could be big with loose policy
	 * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to
	 * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply
Bhaskar Chowdhury's avatar
Bhaskar Chowdhury committed
832
	 * with the strict "NEVER", and to avoid possible race condition (even
833 834 835 836 837 838 839 840 841 842
	 * though user usually won't too frequently do the switching to policy
	 * OVERCOMMIT_NEVER), the switch is done in the following order:
	 *	1. changing the batch
	 *	2. sync percpu count on each CPU
	 *	3. switch the policy
	 */
	if (write) {
		t = *table;
		t.data = &new_policy;
		ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
843
		if (ret || new_policy == -1)
844 845 846 847 848 849 850 851 852 853 854 855 856
			return ret;

		mm_compute_batch(new_policy);
		if (new_policy == OVERCOMMIT_NEVER)
			schedule_on_each_cpu(sync_overcommit_as);
		sysctl_overcommit_memory = new_policy;
	} else {
		ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
	}

	return ret;
}

857 858
int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer,
		size_t *lenp, loff_t *ppos)
859 860 861 862 863 864 865 866 867
{
	int ret;

	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
	if (ret == 0 && write)
		sysctl_overcommit_ratio = 0;
	return ret;
}

868 869 870 871 872
/*
 * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
 */
unsigned long vm_commit_limit(void)
{
873 874 875 876 877
	unsigned long allowed;

	if (sysctl_overcommit_kbytes)
		allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
	else
878
		allowed = ((totalram_pages() - hugetlb_total_pages())
879 880 881 882
			   * sysctl_overcommit_ratio / 100);
	allowed += total_swap_pages;

	return allowed;
883 884
}

885 886 887 888 889 890 891 892 893 894 895 896 897
/*
 * 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;

/*
 * The global memory commitment made in the system can be a metric
 * that can be used to drive ballooning decisions when Linux is hosted
 * as a guest. On Hyper-V, the host implements a policy engine for dynamically
 * balancing memory across competing virtual machines that are hosted.
 * Several metrics drive this policy engine including the guest reported
 * memory commitment.
898 899 900 901 902
 *
 * The time cost of this is very low for small platforms, and for big
 * platform like a 2S/36C/72T Skylake server, in worst case where
 * vm_committed_as's spinlock is under severe contention, the time cost
 * could be about 30~40 microseconds.
903 904 905
 */
unsigned long vm_memory_committed(void)
{
906
	return percpu_counter_sum_positive(&vm_committed_as);
907 908 909 910 911 912 913 914 915
}
EXPORT_SYMBOL_GPL(vm_memory_committed);

/*
 * 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
916
 * vm.overcommit_memory sysctl.  See Documentation/vm/overcommit-accounting.rst
917 918 919 920 921 922 923 924 925 926 927
 *
 * 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.
 */
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
928
	long allowed;
929 930 931 932 933 934 935 936 937 938

	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) {
939
		if (pages > totalram_pages() + total_swap_pages)
940
			goto error;
941
		return 0;
942 943 944 945 946 947 948 949 950 951 952 953 954
	}

	allowed = vm_commit_limit();
	/*
	 * Reserve some for root
	 */
	if (!cap_sys_admin)
		allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);

	/*
	 * Don't let a single process grow so big a user can't recover
	 */
	if (mm) {
955 956
		long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);

957 958 959 960 961 962 963 964 965 966 967
		allowed -= min_t(long, mm->total_vm / 32, reserve);
	}

	if (percpu_counter_read_positive(&vm_committed_as) < allowed)
		return 0;
error:
	vm_unacct_memory(pages);

	return -ENOMEM;
}

968 969 970 971 972 973
/**
 * get_cmdline() - copy the cmdline value to a buffer.
 * @task:     the task whose cmdline value to copy.
 * @buffer:   the buffer to copy to.
 * @buflen:   the length of the buffer. Larger cmdline values are truncated
 *            to this length.
974 975
 *
 * Return: the size of the cmdline field copied. Note that the copy does
976 977 978 979 980 981 982
 * not guarantee an ending NULL byte.
 */
int get_cmdline(struct task_struct *task, char *buffer, int buflen)
{
	int res = 0;
	unsigned int len;
	struct mm_struct *mm = get_task_mm(task);
983
	unsigned long arg_start, arg_end, env_start, env_end;
984 985 986 987 988
	if (!mm)
		goto out;
	if (!mm->arg_end)
		goto out_mm;	/* Shh! No looking before we're done */

989
	spin_lock(&mm->arg_lock);
990 991 992 993
	arg_start = mm->arg_start;
	arg_end = mm->arg_end;
	env_start = mm->env_start;
	env_end = mm->env_end;
994
	spin_unlock(&mm->arg_lock);
995 996

	len = arg_end - arg_start;
997 998 999 1000

	if (len > buflen)
		len = buflen;

1001
	res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE);
1002 1003 1004 1005 1006 1007 1008 1009 1010 1011

	/*
	 * If the nul at the end of args has been overwritten, then
	 * assume application is using setproctitle(3).
	 */
	if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
		len = strnlen(buffer, res);
		if (len < res) {
			res = len;
		} else {
1012
			len = env_end - env_start;
1013 1014
			if (len > buflen - res)
				len = buflen - res;
1015
			res += access_process_vm(task, env_start,
1016 1017
						 buffer+res, len,
						 FOLL_FORCE);
1018 1019 1020 1021 1022 1023 1024 1025
			res = strnlen(buffer, res);
		}
	}
out_mm:
	mmput(mm);
out:
	return res;
}
1026

1027
int __weak memcmp_pages(struct page *page1, struct page *page2)
1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
{
	char *addr1, *addr2;
	int ret;

	addr1 = kmap_atomic(page1);
	addr2 = kmap_atomic(page2);
	ret = memcmp(addr1, addr2, PAGE_SIZE);
	kunmap_atomic(addr2);
	kunmap_atomic(addr1);
	return ret;
}
1039

1040
#ifdef CONFIG_PRINTK
1041 1042 1043 1044 1045 1046 1047 1048 1049
/**
 * mem_dump_obj - Print available provenance information
 * @object: object for which to find provenance information.
 *
 * This function uses pr_cont(), so that the caller is expected to have
 * printed out whatever preamble is appropriate.  The provenance information
 * depends on the type of object and on how much debugging is enabled.
 * For example, for a slab-cache object, the slab name is printed, and,
 * if available, the return address and stack trace from the allocation
1050
 * and last free path of that object.
1051 1052 1053
 */
void mem_dump_obj(void *object)
{
1054 1055
	const char *type;

1056 1057 1058 1059
	if (kmem_valid_obj(object)) {
		kmem_dump_obj(object);
		return;
	}
1060

1061 1062
	if (vmalloc_dump_obj(object))
		return;
1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073

	if (virt_addr_valid(object))
		type = "non-slab/vmalloc memory";
	else if (object == NULL)
		type = "NULL pointer";
	else if (object == ZERO_SIZE_PTR)
		type = "zero-size pointer";
	else
		type = "non-paged memory";

	pr_cont(" %s\n", type);
1074
}
1075
EXPORT_SYMBOL_GPL(mem_dump_obj);
1076
#endif
1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116

/*
 * A driver might set a page logically offline -- PageOffline() -- and
 * turn the page inaccessible in the hypervisor; after that, access to page
 * content can be fatal.
 *
 * Some special PFN walkers -- i.e., /proc/kcore -- read content of random
 * pages after checking PageOffline(); however, these PFN walkers can race
 * with drivers that set PageOffline().
 *
 * page_offline_freeze()/page_offline_thaw() allows for a subsystem to
 * synchronize with such drivers, achieving that a page cannot be set
 * PageOffline() while frozen.
 *
 * page_offline_begin()/page_offline_end() is used by drivers that care about
 * such races when setting a page PageOffline().
 */
static DECLARE_RWSEM(page_offline_rwsem);

void page_offline_freeze(void)
{
	down_read(&page_offline_rwsem);
}

void page_offline_thaw(void)
{
	up_read(&page_offline_rwsem);
}

void page_offline_begin(void)
{
	down_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_begin);

void page_offline_end(void)
{
	up_write(&page_offline_rwsem);
}
EXPORT_SYMBOL(page_offline_end);
1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127

#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
void flush_dcache_folio(struct folio *folio)
{
	long i, nr = folio_nr_pages(folio);

	for (i = 0; i < nr; i++)
		flush_dcache_page(folio_page(folio, i));
}
EXPORT_SYMBOL(flush_dcache_folio);
#endif