Blame view
mm/util.c
23.9 KB
457c89965 treewide: Add SPD... |
1 |
// SPDX-License-Identifier: GPL-2.0-only |
16d69265b uninline arch_pic... |
2 |
#include <linux/mm.h> |
30992c97a [PATCH] slob: int... |
3 4 |
#include <linux/slab.h> #include <linux/string.h> |
3b32123d7 mm: use macros fr... |
5 |
#include <linux/compiler.h> |
b95f1b31b mm: Map most file... |
6 |
#include <linux/export.h> |
96840aa00 [PATCH] strndup_u... |
7 |
#include <linux/err.h> |
3b8f14b41 mm/util.c must #i... |
8 |
#include <linux/sched.h> |
6e84f3152 sched/headers: Pr... |
9 |
#include <linux/sched/mm.h> |
79eb597cb mm: add account_l... |
10 |
#include <linux/sched/signal.h> |
68db0cf10 sched/headers: Pr... |
11 |
#include <linux/sched/task_stack.h> |
eb36c5873 new helper: vm_mm... |
12 |
#include <linux/security.h> |
9800339b5 mm: don't inline ... |
13 |
#include <linux/swap.h> |
33806f06d swap: make each s... |
14 |
#include <linux/swapops.h> |
00619bcc4 mm: factor commit... |
15 16 |
#include <linux/mman.h> #include <linux/hugetlb.h> |
39f1f78d5 nick kvfree() fro... |
17 |
#include <linux/vmalloc.h> |
897ab3e0c userfaultfd: non-... |
18 |
#include <linux/userfaultfd_k.h> |
649775be6 mm, fs: move rand... |
19 |
#include <linux/elf.h> |
67f3977f8 arm64, mm: move g... |
20 21 |
#include <linux/elf-randomize.h> #include <linux/personality.h> |
649775be6 mm, fs: move rand... |
22 |
#include <linux/random.h> |
67f3977f8 arm64, mm: move g... |
23 24 25 |
#include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> |
00619bcc4 mm: factor commit... |
26 |
|
7c0f6ba68 Replace <asm/uacc... |
27 |
#include <linux/uaccess.h> |
30992c97a [PATCH] slob: int... |
28 |
|
6038def0d mm: nommu: sort m... |
29 |
#include "internal.h" |
a4bb1e43e mm/util: add kstr... |
30 31 32 33 34 35 36 37 38 39 40 41 |
/** * 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); |
30992c97a [PATCH] slob: int... |
42 |
/** |
30992c97a [PATCH] slob: int... |
43 |
* kstrdup - allocate space for and copy an existing string |
30992c97a [PATCH] slob: int... |
44 45 |
* @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory |
a862f68a8 docs/core-api/mm:... |
46 47 |
* * Return: newly allocated copy of @s or %NULL in case of error |
30992c97a [PATCH] slob: int... |
48 49 50 51 52 53 54 55 56 57 |
*/ char *kstrdup(const char *s, gfp_t gfp) { size_t len; char *buf; if (!s) return NULL; len = strlen(s) + 1; |
1d2c8eea6 [PATCH] slab: cle... |
58 |
buf = kmalloc_track_caller(len, gfp); |
30992c97a [PATCH] slob: int... |
59 60 61 62 63 |
if (buf) memcpy(buf, s, len); return buf; } EXPORT_SYMBOL(kstrdup); |
96840aa00 [PATCH] strndup_u... |
64 |
|
1a2f67b45 [PATCH] kmemdup: ... |
65 |
/** |
a4bb1e43e mm/util: add kstr... |
66 67 68 69 |
* 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 * |
295a17302 mm/util.c: update... |
70 71 |
* Note: Strings allocated by kstrdup_const should be freed by kfree_const and * must not be passed to krealloc(). |
a862f68a8 docs/core-api/mm:... |
72 73 74 |
* * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. |
a4bb1e43e mm/util: add kstr... |
75 76 77 78 79 80 81 82 83 84 85 |
*/ 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); /** |
1e66df3ee add kstrndup |
86 87 88 89 |
* 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 |
f35157417 Provide a functio... |
90 91 |
* * Note: Use kmemdup_nul() instead if the size is known exactly. |
a862f68a8 docs/core-api/mm:... |
92 93 |
* * Return: newly allocated copy of @s or %NULL in case of error |
1e66df3ee add kstrndup |
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 |
*/ 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); /** |
1a2f67b45 [PATCH] kmemdup: ... |
114 115 116 117 118 |
* kmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use |
a862f68a8 docs/core-api/mm:... |
119 120 |
* * Return: newly allocated copy of @src or %NULL in case of error |
1a2f67b45 [PATCH] kmemdup: ... |
121 122 123 124 |
*/ void *kmemdup(const void *src, size_t len, gfp_t gfp) { void *p; |
1d2c8eea6 [PATCH] slab: cle... |
125 |
p = kmalloc_track_caller(len, gfp); |
1a2f67b45 [PATCH] kmemdup: ... |
126 127 128 129 130 |
if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kmemdup); |
ef2ad80c7 Slab allocators: ... |
131 |
/** |
f35157417 Provide a functio... |
132 133 134 135 |
* 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 |
a862f68a8 docs/core-api/mm:... |
136 137 138 |
* * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error |
f35157417 Provide a functio... |
139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 |
*/ 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); /** |
610a77e04 memdup_user(): in... |
157 158 159 160 161 |
* memdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * |
a862f68a8 docs/core-api/mm:... |
162 |
* Return: an ERR_PTR() on failure. Result is physically |
50fd2f298 new primitive: vm... |
163 |
* contiguous, to be freed by kfree(). |
610a77e04 memdup_user(): in... |
164 165 166 167 |
*/ void *memdup_user(const void __user *src, size_t len) { void *p; |
6c8fcc096 mm: don't let use... |
168 |
p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); |
610a77e04 memdup_user(): in... |
169 170 171 172 173 174 175 176 177 178 179 |
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); |
50fd2f298 new primitive: vm... |
180 181 182 183 184 185 |
/** * vmemdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * |
a862f68a8 docs/core-api/mm:... |
186 |
* Return: an ERR_PTR() on failure. Result may be not |
50fd2f298 new primitive: vm... |
187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 |
* 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); |
b86181f1a mm/util: make str... |
205 |
/** |
96840aa00 [PATCH] strndup_u... |
206 |
* strndup_user - duplicate an existing string from user space |
96840aa00 [PATCH] strndup_u... |
207 208 |
* @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. |
a862f68a8 docs/core-api/mm:... |
209 |
* |
e91455217 mm/util.c: fix st... |
210 |
* Return: newly allocated copy of @s or an ERR_PTR() in case of error |
96840aa00 [PATCH] strndup_u... |
211 212 213 214 215 216 217 218 219 220 221 222 223 |
*/ 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); |
90d740455 mm: use memdup_user |
224 |
p = memdup_user(s, length); |
96840aa00 [PATCH] strndup_u... |
225 |
|
90d740455 mm: use memdup_user |
226 227 |
if (IS_ERR(p)) return p; |
96840aa00 [PATCH] strndup_u... |
228 229 230 231 232 233 |
p[length - 1] = '\0'; return p; } EXPORT_SYMBOL(strndup_user); |
16d69265b uninline arch_pic... |
234 |
|
e9d408e10 new helper: memdu... |
235 236 237 238 239 240 |
/** * memdup_user_nul - duplicate memory region from user space and NUL-terminate * * @src: source address in user space * @len: number of bytes to copy * |
a862f68a8 docs/core-api/mm:... |
241 |
* Return: an ERR_PTR() on failure. |
e9d408e10 new helper: memdu... |
242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 |
*/ 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); |
6038def0d mm: nommu: sort m... |
265 |
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, |
aba6dfb75 mm/mmap.c: rb_par... |
266 |
struct vm_area_struct *prev) |
6038def0d mm: nommu: sort m... |
267 268 269 270 271 272 273 274 |
{ struct vm_area_struct *next; vma->vm_prev = prev; if (prev) { next = prev->vm_next; prev->vm_next = vma; } else { |
aba6dfb75 mm/mmap.c: rb_par... |
275 |
next = mm->mmap; |
6038def0d mm: nommu: sort m... |
276 |
mm->mmap = vma; |
6038def0d mm: nommu: sort m... |
277 278 279 280 281 |
} vma->vm_next = next; if (next) next->vm_prev = vma; } |
1b9fc5b24 mm/mmap.c: extrac... |
282 283 284 285 286 287 288 289 290 291 292 293 294 |
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; } |
b76437579 procfs: mark thre... |
295 |
/* Check if the vma is being used as a stack by this task */ |
d17af5056 mm: Change vm_is_... |
296 |
int vma_is_stack_for_current(struct vm_area_struct *vma) |
b76437579 procfs: mark thre... |
297 |
{ |
d17af5056 mm: Change vm_is_... |
298 |
struct task_struct * __maybe_unused t = current; |
b76437579 procfs: mark thre... |
299 300 |
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } |
649775be6 mm, fs: move rand... |
301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 |
#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 } |
67f3977f8 arm64, mm: move g... |
320 |
#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT |
e7142bf5d arm64, mm: make r... |
321 322 323 324 325 326 327 328 |
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); } |
67f3977f8 arm64, mm: move g... |
329 330 331 332 333 334 335 336 337 338 339 340 341 |
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; } |
67f3977f8 arm64, mm: move g... |
342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 |
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) |
8f2af155b exec: pass stack ... |
398 |
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) |
16d69265b uninline arch_pic... |
399 400 401 |
{ mm->mmap_base = TASK_UNMAPPED_BASE; mm->get_unmapped_area = arch_get_unmapped_area; |
16d69265b uninline arch_pic... |
402 403 |
} #endif |
912985dce mm: Make generic ... |
404 |
|
79eb597cb mm: add account_l... |
405 406 407 408 409 410 411 412 413 |
/** * __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 |
c1e8d7c6a mmap locking API:... |
414 |
* that mmap_lock is held as writer. |
79eb597cb mm: add account_l... |
415 416 417 418 419 420 421 422 423 424 |
* * 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; |
42fc54140 mmap locking API:... |
425 |
mmap_assert_write_locked(mm); |
79eb597cb mm: add account_l... |
426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 |
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 ", __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; |
d8ed45c5d mmap locking API:... |
469 |
mmap_write_lock(mm); |
79eb597cb mm: add account_l... |
470 471 |
ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); |
d8ed45c5d mmap locking API:... |
472 |
mmap_write_unlock(mm); |
79eb597cb mm: add account_l... |
473 474 475 476 |
return ret; } EXPORT_SYMBOL_GPL(account_locked_vm); |
eb36c5873 new helper: vm_mm... |
477 478 |
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, |
9fbeb5ab5 mm: make vm_mmap ... |
479 |
unsigned long flag, unsigned long pgoff) |
eb36c5873 new helper: vm_mm... |
480 481 482 |
{ unsigned long ret; struct mm_struct *mm = current->mm; |
41badc15c mm: make do_mmap_... |
483 |
unsigned long populate; |
897ab3e0c userfaultfd: non-... |
484 |
LIST_HEAD(uf); |
eb36c5873 new helper: vm_mm... |
485 486 487 |
ret = security_mmap_file(file, prot, flag); if (!ret) { |
d8ed45c5d mmap locking API:... |
488 |
if (mmap_write_lock_killable(mm)) |
9fbeb5ab5 mm: make vm_mmap ... |
489 |
return -EINTR; |
45e55300f mm: remove unnece... |
490 491 |
ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate, &uf); |
d8ed45c5d mmap locking API:... |
492 |
mmap_write_unlock(mm); |
897ab3e0c userfaultfd: non-... |
493 |
userfaultfd_unmap_complete(mm, &uf); |
41badc15c mm: make do_mmap_... |
494 495 |
if (populate) mm_populate(ret, populate); |
eb36c5873 new helper: vm_mm... |
496 497 498 499 500 501 502 503 504 505 |
} 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; |
ea53cde08 mm/util: use offs... |
506 |
if (unlikely(offset_in_page(offset))) |
eb36c5873 new helper: vm_mm... |
507 |
return -EINVAL; |
9fbeb5ab5 mm: make vm_mmap ... |
508 |
return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); |
eb36c5873 new helper: vm_mm... |
509 510 |
} EXPORT_SYMBOL(vm_mmap); |
a7c3e901a mm: introduce kv[... |
511 512 513 514 515 516 517 518 519 520 |
/** * 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. * |
cc965a29d mm: kvmalloc supp... |
521 522 523 |
* Reclaim modifiers - __GFP_NORETRY and __GFP_NOFAIL are not supported. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. |
a7c3e901a mm: introduce kv[... |
524 |
* |
ce91f6ee5 mm: kvmalloc does... |
525 526 |
* Please note that any use of gfp flags outside of GFP_KERNEL is careful to not * fall back to vmalloc. |
a862f68a8 docs/core-api/mm:... |
527 528 |
* * Return: pointer to the allocated memory of %NULL in case of failure |
a7c3e901a mm: introduce kv[... |
529 530 531 532 533 534 535 536 537 538 |
*/ void *kvmalloc_node(size_t size, gfp_t flags, int node) { gfp_t kmalloc_flags = flags; void *ret; /* * vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables) * so the given set of flags has to be compatible. */ |
ce91f6ee5 mm: kvmalloc does... |
539 540 |
if ((flags & GFP_KERNEL) != GFP_KERNEL) return kmalloc_node(size, flags, node); |
a7c3e901a mm: introduce kv[... |
541 542 |
/* |
4f4f2ba9c mm: clarify why w... |
543 544 545 546 547 |
* 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. |
a7c3e901a mm: introduce kv[... |
548 |
*/ |
6c5ab6511 mm: support __GFP... |
549 550 |
if (size > PAGE_SIZE) { kmalloc_flags |= __GFP_NOWARN; |
cc965a29d mm: kvmalloc supp... |
551 |
if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) |
6c5ab6511 mm: support __GFP... |
552 553 |
kmalloc_flags |= __GFP_NORETRY; } |
a7c3e901a mm: introduce kv[... |
554 555 556 557 558 559 560 561 562 |
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; |
2b9059489 mm: remove __vmal... |
563 |
return __vmalloc_node(size, 1, flags, node, |
8594a21cf mm, vmalloc: fix ... |
564 |
__builtin_return_address(0)); |
a7c3e901a mm: introduce kv[... |
565 566 |
} EXPORT_SYMBOL(kvmalloc_node); |
ff4dc7729 mm/util: add kern... |
567 |
/** |
04b8e9460 mm/util.c: improv... |
568 569 |
* kvfree() - Free memory. * @addr: Pointer to allocated memory. |
ff4dc7729 mm/util: add kern... |
570 |
* |
04b8e9460 mm/util.c: improv... |
571 572 573 574 |
* 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. * |
52414d330 kvfree(): fix mis... |
575 |
* Context: Either preemptible task context or not-NMI interrupt. |
ff4dc7729 mm/util: add kern... |
576 |
*/ |
39f1f78d5 nick kvfree() fro... |
577 578 579 580 581 582 583 584 |
void kvfree(const void *addr) { if (is_vmalloc_addr(addr)) vfree(addr); else kfree(addr); } EXPORT_SYMBOL(kvfree); |
d4eaa2837 mm: add kvfree_se... |
585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 |
/** * 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); |
e39155ea1 mm: uninline and ... |
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 |
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); } |
1aa8aea53 mm: uninline page... |
618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 |
/* * Return true if this page is mapped into pagetables. * For compound page it returns true if any subpage of compound page is mapped. */ bool page_mapped(struct page *page) { int i; if (likely(!PageCompound(page))) return atomic_read(&page->_mapcount) >= 0; page = compound_head(page); if (atomic_read(compound_mapcount_ptr(page)) >= 0) return true; if (PageHuge(page)) return false; |
d8c6546b1 mm: introduce com... |
633 |
for (i = 0; i < compound_nr(page); i++) { |
1aa8aea53 mm: uninline page... |
634 635 636 637 638 639 |
if (atomic_read(&page[i]._mapcount) >= 0) return true; } return false; } EXPORT_SYMBOL(page_mapped); |
e39155ea1 mm: uninline and ... |
640 641 642 643 644 645 646 647 648 649 |
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); } |
9800339b5 mm: don't inline ... |
650 651 |
struct address_space *page_mapping(struct page *page) { |
1c290f642 mm: sanitize page... |
652 653 654 |
struct address_space *mapping; page = compound_head(page); |
9800339b5 mm: don't inline ... |
655 |
|
03e5ac2fc mm: fix crash whe... |
656 657 658 |
/* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(PageSlab(page))) return NULL; |
33806f06d swap: make each s... |
659 660 661 662 |
if (unlikely(PageSwapCache(page))) { swp_entry_t entry; entry.val = page_private(page); |
e39155ea1 mm: uninline and ... |
663 664 |
return swap_address_space(entry); } |
1c290f642 mm: sanitize page... |
665 |
mapping = page->mapping; |
bda807d44 mm: migrate: supp... |
666 |
if ((unsigned long)mapping & PAGE_MAPPING_ANON) |
e39155ea1 mm: uninline and ... |
667 |
return NULL; |
bda807d44 mm: migrate: supp... |
668 669 |
return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS); |
9800339b5 mm: don't inline ... |
670 |
} |
bda807d44 mm: migrate: supp... |
671 |
EXPORT_SYMBOL(page_mapping); |
9800339b5 mm: don't inline ... |
672 |
|
cb9f753a3 mm: fix races bet... |
673 674 675 676 677 678 679 680 681 |
/* * For file cache pages, return the address_space, otherwise return NULL */ struct address_space *page_mapping_file(struct page *page) { if (unlikely(PageSwapCache(page))) return NULL; return page_mapping(page); } |
b20ce5e03 mm: prepare page_... |
682 683 684 685 686 687 |
/* Slow path of page_mapcount() for compound pages */ int __page_mapcount(struct page *page) { int ret; ret = atomic_read(&page->_mapcount) + 1; |
dd78fedde rmap: support fil... |
688 689 690 691 692 693 |
/* * 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; |
b20ce5e03 mm: prepare page_... |
694 695 696 697 698 699 700 |
page = compound_head(page); ret += atomic_read(compound_mapcount_ptr(page)) + 1; if (PageDoubleMap(page)) ret--; return ret; } EXPORT_SYMBOL_GPL(__page_mapcount); |
39a1aa8e1 mm: deduplicate m... |
701 702 703 704 705 706 |
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 */ |
32927393d sysctl: pass kern... |
707 708 |
int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) |
49f0ce5f9 mm: add overcommi... |
709 710 711 712 713 714 715 716 |
{ int ret; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_kbytes = 0; return ret; } |
56f3547bf mm: adjust vm_com... |
717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 |
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; int new_policy; 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 * with the strict "NEVER", and to avoid possible race condtion (even * 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); if (ret) 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; } |
32927393d sysctl: pass kern... |
757 758 |
int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) |
49f0ce5f9 mm: add overcommi... |
759 760 761 762 763 764 765 766 |
{ int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_ratio = 0; return ret; } |
00619bcc4 mm: factor commit... |
767 768 769 770 771 |
/* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { |
49f0ce5f9 mm: add overcommi... |
772 773 774 775 776 |
unsigned long allowed; if (sysctl_overcommit_kbytes) allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); else |
ca79b0c21 mm: convert total... |
777 |
allowed = ((totalram_pages() - hugetlb_total_pages()) |
49f0ce5f9 mm: add overcommi... |
778 779 780 781 |
* sysctl_overcommit_ratio / 100); allowed += total_swap_pages; return allowed; |
00619bcc4 mm: factor commit... |
782 |
} |
39a1aa8e1 mm: deduplicate m... |
783 784 785 786 787 788 789 790 791 792 793 794 795 |
/* * 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. |
4e2ee51e8 mm/util.c: make v... |
796 797 798 799 800 |
* * 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. |
39a1aa8e1 mm: deduplicate m... |
801 802 803 |
*/ unsigned long vm_memory_committed(void) { |
4e2ee51e8 mm/util.c: make v... |
804 |
return percpu_counter_sum_positive(&vm_committed_as); |
39a1aa8e1 mm: deduplicate m... |
805 806 807 808 809 810 811 812 813 |
} 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 |
ad56b738c docs/vm: rename d... |
814 |
* vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting.rst |
39a1aa8e1 mm: deduplicate m... |
815 816 817 818 819 820 821 822 823 824 825 |
* * 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) { |
8c7829b04 mm: fix false-pos... |
826 |
long allowed; |
39a1aa8e1 mm: deduplicate m... |
827 |
|
39a1aa8e1 mm: deduplicate m... |
828 829 830 831 832 833 834 835 836 |
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) { |
8c7829b04 mm: fix false-pos... |
837 |
if (pages > totalram_pages() + total_swap_pages) |
39a1aa8e1 mm: deduplicate m... |
838 |
goto error; |
8c7829b04 mm: fix false-pos... |
839 |
return 0; |
39a1aa8e1 mm: deduplicate m... |
840 841 842 843 844 845 846 847 848 849 850 851 852 |
} 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) { |
8c7829b04 mm: fix false-pos... |
853 |
long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); |
39a1aa8e1 mm: deduplicate m... |
854 855 856 857 858 859 860 861 862 863 |
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; } |
a90902531 mm: Create utilit... |
864 865 866 867 868 869 |
/** * 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. |
a862f68a8 docs/core-api/mm:... |
870 871 |
* * Return: the size of the cmdline field copied. Note that the copy does |
a90902531 mm: Create utilit... |
872 873 874 875 876 877 878 |
* 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); |
a3b609ef9 proc read mm's {a... |
879 |
unsigned long arg_start, arg_end, env_start, env_end; |
a90902531 mm: Create utilit... |
880 881 882 883 |
if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ |
bc81426f5 prctl_set_mm: dow... |
884 |
spin_lock(&mm->arg_lock); |
a3b609ef9 proc read mm's {a... |
885 886 887 888 |
arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; |
bc81426f5 prctl_set_mm: dow... |
889 |
spin_unlock(&mm->arg_lock); |
a3b609ef9 proc read mm's {a... |
890 891 |
len = arg_end - arg_start; |
a90902531 mm: Create utilit... |
892 893 894 |
if (len > buflen) len = buflen; |
f307ab6dc mm: replace acces... |
895 |
res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); |
a90902531 mm: Create utilit... |
896 897 898 899 900 901 902 903 904 905 |
/* * 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 { |
a3b609ef9 proc read mm's {a... |
906 |
len = env_end - env_start; |
a90902531 mm: Create utilit... |
907 908 |
if (len > buflen - res) len = buflen - res; |
a3b609ef9 proc read mm's {a... |
909 |
res += access_process_vm(task, env_start, |
f307ab6dc mm: replace acces... |
910 911 |
buffer+res, len, FOLL_FORCE); |
a90902531 mm: Create utilit... |
912 913 914 915 916 917 918 919 |
res = strnlen(buffer, res); } } out_mm: mmput(mm); out: return res; } |
010c164a5 mm: move memcmp_p... |
920 |
|
4d1a8a2dc arm64: mte: Tags-... |
921 |
int __weak memcmp_pages(struct page *page1, struct page *page2) |
010c164a5 mm: move memcmp_p... |
922 923 924 925 926 927 928 929 930 931 932 |
{ 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; } |