util.c 9.4 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

D
Davi Arnaut 已提交
15
#include <asm/uaccess.h>
16

17 18
#include "internal.h"

19 20 21 22 23 24 25 26 27 28 29 30 31 32
/**
 * 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;
33
	buf = kmalloc_track_caller(len, gfp);
34 35 36 37 38
	if (buf)
		memcpy(buf, s, len);
	return buf;
}
EXPORT_SYMBOL(kstrdup);
D
Davi Arnaut 已提交
39

J
Jeremy Fitzhardinge 已提交
40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63
/**
 * 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
64 65 66 67 68 69 70 71 72 73 74
/**
 * 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;

75
	p = kmalloc_track_caller(len, gfp);
A
Alexey Dobriyan 已提交
76 77 78 79 80 81
	if (p)
		memcpy(p, src, len);
	return p;
}
EXPORT_SYMBOL(kmemdup);

L
Li Zefan 已提交
82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
/**
 * 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
112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129
/*
 * 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
130
	p = memdup_user(s, length);
D
Davi Arnaut 已提交
131

J
Julia Lawall 已提交
132 133
	if (IS_ERR(p))
		return p;
D
Davi Arnaut 已提交
134 135 136 137 138 139

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

	return p;
}
EXPORT_SYMBOL(strndup_user);
A
Andrew Morton 已提交
140

141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162
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;
}

163 164 165 166 167 168 169 170 171 172
/* 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
173 174
 * 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().
175
 */
176 177
struct task_struct *task_of_stack(struct task_struct *task,
				struct vm_area_struct *vma, bool in_group)
178 179
{
	if (vm_is_stack_for_task(task, vma))
180
		return task;
181 182 183 184

	if (in_group) {
		struct task_struct *t;

185
		for_each_thread(task, t) {
186 187
			if (vm_is_stack_for_task(t, vma))
				return t;
188
		}
189 190
	}

191
	return NULL;
192 193
}

194
#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
A
Andrew Morton 已提交
195 196 197 198 199 200
void arch_pick_mmap_layout(struct mm_struct *mm)
{
	mm->mmap_base = TASK_UNMAPPED_BASE;
	mm->get_unmapped_area = arch_get_unmapped_area;
}
#endif
201

202 203 204
/*
 * 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
205
 * If the architecture not support this function, simply return with no
206 207
 * page pinned
 */
208
int __weak __get_user_pages_fast(unsigned long start,
209 210 211 212 213 214
				 int nr_pages, int write, struct page **pages)
{
	return 0;
}
EXPORT_SYMBOL_GPL(__get_user_pages_fast);

A
Andy Grover 已提交
215 216 217 218 219 220 221 222 223 224 225
/**
 * 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.
226 227 228 229 230 231 232 233 234 235 236 237
 *
 * 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
238
 */
239
int __weak get_user_pages_fast(unsigned long start,
240 241 242 243 244 245 246 247 248 249 250 251 252
				int nr_pages, int write, struct page **pages)
{
	struct mm_struct *mm = current->mm;
	int ret;

	down_read(&mm->mmap_sem);
	ret = get_user_pages(current, mm, start, nr_pages,
					write, 0, pages, NULL);
	up_read(&mm->mmap_sem);

	return ret;
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
253

A
Al Viro 已提交
254 255 256 257 258 259
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;
260
	unsigned long populate;
A
Al Viro 已提交
261 262 263 264

	ret = security_mmap_file(file, prot, flag);
	if (!ret) {
		down_write(&mm->mmap_sem);
265 266
		ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
				    &populate);
A
Al Viro 已提交
267
		up_write(&mm->mmap_sem);
268 269
		if (populate)
			mm_populate(ret, populate);
A
Al Viro 已提交
270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286
	}
	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;
	if (unlikely(offset & ~PAGE_MASK))
		return -EINVAL;

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

A
Al Viro 已提交
287 288 289 290 291 292 293 294 295
void kvfree(const void *addr)
{
	if (is_vmalloc_addr(addr))
		vfree(addr);
	else
		kfree(addr);
}
EXPORT_SYMBOL(kvfree);

S
Shaohua Li 已提交
296 297 298 299
struct address_space *page_mapping(struct page *page)
{
	struct address_space *mapping = page->mapping;

300 301 302 303
	/* This happens if someone calls flush_dcache_page on slab page */
	if (unlikely(PageSlab(page)))
		return NULL;

304 305 306 307 308
	if (unlikely(PageSwapCache(page))) {
		swp_entry_t entry;

		entry.val = page_private(page);
		mapping = swap_address_space(entry);
309
	} else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
S
Shaohua Li 已提交
310 311 312 313
		mapping = NULL;
	return mapping;
}

314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337
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;
}

338 339 340 341 342
/*
 * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
 */
unsigned long vm_commit_limit(void)
{
343 344 345 346 347 348 349 350 351 352
	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;
353 354
}

355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402
/**
 * 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);
	if (!mm)
		goto out;
	if (!mm->arg_end)
		goto out_mm;	/* Shh! No looking before we're done */

	len = mm->arg_end - mm->arg_start;

	if (len > buflen)
		len = buflen;

	res = access_process_vm(task, mm->arg_start, buffer, len, 0);

	/*
	 * 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 {
			len = mm->env_end - mm->env_start;
			if (len > buflen - res)
				len = buflen - res;
			res += access_process_vm(task, mm->env_start,
						 buffer+res, len, 0);
			res = strnlen(buffer, res);
		}
	}
out_mm:
	mmput(mm);
out:
	return res;
}