util.c 12.0 KB
Newer Older
A
Andrew Morton 已提交
1
#include <linux/mm.h>
2 3
#include <linux/slab.h>
#include <linux/string.h>
4
#include <linux/compiler.h>
5
#include <linux/export.h>
D
Davi Arnaut 已提交
6
#include <linux/err.h>
7
#include <linux/sched.h>
A
Al Viro 已提交
8
#include <linux/security.h>
S
Shaohua Li 已提交
9
#include <linux/swap.h>
10
#include <linux/swapops.h>
11 12
#include <linux/mman.h>
#include <linux/hugetlb.h>
A
Al Viro 已提交
13
#include <linux/vmalloc.h>
14

A
Andrzej Hajda 已提交
15
#include <asm/sections.h>
D
Davi Arnaut 已提交
16
#include <asm/uaccess.h>
17

18 19
#include "internal.h"

A
Andrzej Hajda 已提交
20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38
static inline int is_kernel_rodata(unsigned long addr)
{
	return addr >= (unsigned long)__start_rodata &&
		addr < (unsigned long)__end_rodata;
}

/**
 * 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);

39 40 41 42 43 44 45 46 47 48 49 50 51 52
/**
 * 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
 */
char *kstrdup(const char *s, gfp_t gfp)
{
	size_t len;
	char *buf;

	if (!s)
		return NULL;

	len = strlen(s) + 1;
53
	buf = kmalloc_track_caller(len, gfp);
54 55 56 57 58
	if (buf)
		memcpy(buf, s, len);
	return buf;
}
EXPORT_SYMBOL(kstrdup);
D
Davi Arnaut 已提交
59

A
Andrzej Hajda 已提交
60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77
/**
 * 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
 *
 * Function returns source string if it is in .rodata section otherwise it
 * fallbacks to kstrdup.
 * Strings allocated by kstrdup_const should be freed by kfree_const.
 */
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);

J
Jeremy Fitzhardinge 已提交
78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101
/**
 * 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
 */
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);

A
Alexey Dobriyan 已提交
102 103 104 105 106 107 108 109 110 111 112
/**
 * kmemdup - duplicate region of memory
 *
 * @src: memory region to duplicate
 * @len: memory region length
 * @gfp: GFP mask to use
 */
void *kmemdup(const void *src, size_t len, gfp_t gfp)
{
	void *p;

113
	p = kmalloc_track_caller(len, gfp);
A
Alexey Dobriyan 已提交
114 115 116 117 118 119
	if (p)
		memcpy(p, src, len);
	return p;
}
EXPORT_SYMBOL(kmemdup);

L
Li Zefan 已提交
120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149
/**
 * memdup_user - duplicate memory region from user space
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
 * Returns an ERR_PTR() on failure.
 */
void *memdup_user(const void __user *src, size_t len)
{
	void *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, GFP_KERNEL);
	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);

D
Davi Arnaut 已提交
150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
/*
 * 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.
 */
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);

J
Julia Lawall 已提交
168
	p = memdup_user(s, length);
D
Davi Arnaut 已提交
169

J
Julia Lawall 已提交
170 171
	if (IS_ERR(p))
		return p;
D
Davi Arnaut 已提交
172 173 174 175 176 177

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

	return p;
}
EXPORT_SYMBOL(strndup_user);
A
Andrew Morton 已提交
178

A
Al Viro 已提交
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209
/**
 * memdup_user_nul - duplicate memory region from user space and NUL-terminate
 *
 * @src: source address in user space
 * @len: number of bytes to copy
 *
 * Returns an ERR_PTR() on failure.
 */
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);

210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
		struct vm_area_struct *prev, struct rb_node *rb_parent)
{
	struct vm_area_struct *next;

	vma->vm_prev = prev;
	if (prev) {
		next = prev->vm_next;
		prev->vm_next = vma;
	} else {
		mm->mmap = vma;
		if (rb_parent)
			next = rb_entry(rb_parent,
					struct vm_area_struct, vm_rb);
		else
			next = NULL;
	}
	vma->vm_next = next;
	if (next)
		next->vm_prev = vma;
}

232 233 234 235 236 237 238 239 240 241
/* Check if the vma is being used as a stack by this task */
static int vm_is_stack_for_task(struct task_struct *t,
				struct vm_area_struct *vma)
{
	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}

/*
 * Check if the vma is being used as a stack.
 * If is_group is non-zero, check in the entire thread group or else
242 243
 * just check in the current task. Returns the task_struct of the task
 * that the vma is stack for. Must be called under rcu_read_lock().
244
 */
245 246
struct task_struct *task_of_stack(struct task_struct *task,
				struct vm_area_struct *vma, bool in_group)
247 248
{
	if (vm_is_stack_for_task(task, vma))
249
		return task;
250 251 252 253

	if (in_group) {
		struct task_struct *t;

254
		for_each_thread(task, t) {
255 256
			if (vm_is_stack_for_task(t, vma))
				return t;
257
		}
258 259
	}

260
	return NULL;
261 262
}

263
#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
A
Andrew Morton 已提交
264 265 266 267 268 269
void arch_pick_mmap_layout(struct mm_struct *mm)
{
	mm->mmap_base = TASK_UNMAPPED_BASE;
	mm->get_unmapped_area = arch_get_unmapped_area;
}
#endif
270

271 272 273
/*
 * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
 * back to the regular GUP.
L
Lucas De Marchi 已提交
274
 * If the architecture not support this function, simply return with no
275 276
 * page pinned
 */
277
int __weak __get_user_pages_fast(unsigned long start,
278 279 280 281 282 283
				 int nr_pages, int write, struct page **pages)
{
	return 0;
}
EXPORT_SYMBOL_GPL(__get_user_pages_fast);

A
Andy Grover 已提交
284 285 286 287 288 289 290 291 292 293 294
/**
 * get_user_pages_fast() - pin user pages in memory
 * @start:	starting user address
 * @nr_pages:	number of pages from start to pin
 * @write:	whether pages will be written to
 * @pages:	array that receives pointers to the pages pinned.
 *		Should be at least nr_pages long.
 *
 * Returns number of pages pinned. This may be fewer than the number
 * requested. If nr_pages is 0 or negative, returns 0. If no pages
 * were pinned, returns -errno.
295 296 297 298 299 300 301 302 303 304 305 306
 *
 * get_user_pages_fast provides equivalent functionality to get_user_pages,
 * operating on current and current->mm, with force=0 and vma=NULL. However
 * unlike get_user_pages, it must be called without mmap_sem held.
 *
 * get_user_pages_fast may take mmap_sem and page table locks, so no
 * assumptions can be made about lack of locking. get_user_pages_fast is to be
 * implemented in a way that is advantageous (vs get_user_pages()) when the
 * user memory area is already faulted in and present in ptes. However if the
 * pages have to be faulted in, it may turn out to be slightly slower so
 * callers need to carefully consider what to use. On many architectures,
 * get_user_pages_fast simply falls back to get_user_pages.
A
Andy Grover 已提交
307
 */
308
int __weak get_user_pages_fast(unsigned long start,
309 310 311
				int nr_pages, int write, struct page **pages)
{
	struct mm_struct *mm = current->mm;
312 313
	return get_user_pages_unlocked(current, mm, start, nr_pages,
				       write, 0, pages);
314 315
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
316

A
Al Viro 已提交
317 318 319 320 321 322
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
	unsigned long len, unsigned long prot,
	unsigned long flag, unsigned long pgoff)
{
	unsigned long ret;
	struct mm_struct *mm = current->mm;
323
	unsigned long populate;
A
Al Viro 已提交
324 325 326 327

	ret = security_mmap_file(file, prot, flag);
	if (!ret) {
		down_write(&mm->mmap_sem);
328 329
		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
				    &populate);
A
Al Viro 已提交
330
		up_write(&mm->mmap_sem);
331 332
		if (populate)
			mm_populate(ret, populate);
A
Al Viro 已提交
333 334 335 336 337 338 339 340 341 342
	}
	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;
343
	if (unlikely(offset_in_page(offset)))
A
Al Viro 已提交
344 345 346 347 348 349
		return -EINVAL;

	return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
}
EXPORT_SYMBOL(vm_mmap);

A
Al Viro 已提交
350 351 352 353 354 355 356 357 358
void kvfree(const void *addr)
{
	if (is_vmalloc_addr(addr))
		vfree(addr);
	else
		kfree(addr);
}
EXPORT_SYMBOL(kvfree);

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
static inline void *__page_rmapping(struct page *page)
{
	unsigned long mapping;

	mapping = (unsigned long)page->mapping;
	mapping &= ~PAGE_MAPPING_FLAGS;

	return (void *)mapping;
}

/* Neutral page->mapping pointer to address_space or anon_vma or other */
void *page_rmapping(struct page *page)
{
	page = compound_head(page);
	return __page_rmapping(page);
}

struct anon_vma *page_anon_vma(struct page *page)
{
	unsigned long mapping;

	page = compound_head(page);
	mapping = (unsigned long)page->mapping;
	if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
		return NULL;
	return __page_rmapping(page);
}

S
Shaohua Li 已提交
387 388
struct address_space *page_mapping(struct page *page)
{
389 390 391
	struct address_space *mapping;

	page = compound_head(page);
S
Shaohua Li 已提交
392

393 394 395 396
	/* This happens if someone calls flush_dcache_page on slab page */
	if (unlikely(PageSlab(page)))
		return NULL;

397 398 399 400
	if (unlikely(PageSwapCache(page))) {
		swp_entry_t entry;

		entry.val = page_private(page);
401 402 403
		return swap_address_space(entry);
	}

404 405
	mapping = page->mapping;
	if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
406
		return NULL;
407
	return mapping;
S
Shaohua Li 已提交
408 409
}

410 411 412 413 414 415 416 417 418 419 420 421 422 423
/* Slow path of page_mapcount() for compound pages */
int __page_mapcount(struct page *page)
{
	int ret;

	ret = atomic_read(&page->_mapcount) + 1;
	page = compound_head(page);
	ret += atomic_read(compound_mapcount_ptr(page)) + 1;
	if (PageDoubleMap(page))
		ret--;
	return ret;
}
EXPORT_SYMBOL_GPL(__page_mapcount);

424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447
int overcommit_ratio_handler(struct ctl_table *table, int write,
			     void __user *buffer, size_t *lenp,
			     loff_t *ppos)
{
	int ret;

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

int overcommit_kbytes_handler(struct ctl_table *table, int write,
			     void __user *buffer, size_t *lenp,
			     loff_t *ppos)
{
	int ret;

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

448 449 450 451 452
/*
 * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
 */
unsigned long vm_commit_limit(void)
{
453 454 455 456 457 458 459 460 461 462
	unsigned long allowed;

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

	return allowed;
463 464
}

465 466 467 468 469 470 471 472 473 474 475 476 477 478
/**
 * 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.
 * Returns the size of the cmdline field copied. Note that the copy does
 * 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);
479
	unsigned long arg_start, arg_end, env_start, env_end;
480 481 482 483 484
	if (!mm)
		goto out;
	if (!mm->arg_end)
		goto out_mm;	/* Shh! No looking before we're done */

485 486 487 488 489 490 491 492
	down_read(&mm->mmap_sem);
	arg_start = mm->arg_start;
	arg_end = mm->arg_end;
	env_start = mm->env_start;
	env_end = mm->env_end;
	up_read(&mm->mmap_sem);

	len = arg_end - arg_start;
493 494 495 496

	if (len > buflen)
		len = buflen;

497
	res = access_process_vm(task, arg_start, buffer, len, 0);
498 499 500 501 502 503 504 505 506 507

	/*
	 * 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 {
508
			len = env_end - env_start;
509 510
			if (len > buflen - res)
				len = buflen - res;
511
			res += access_process_vm(task, env_start,
512 513 514 515 516 517 518 519 520
						 buffer+res, len, 0);
			res = strnlen(buffer, res);
		}
	}
out_mm:
	mmput(mm);
out:
	return res;
}