Blame view
mm/slab_common.c
34.6 KB
b24413180
|
1 |
// SPDX-License-Identifier: GPL-2.0 |
039363f38
|
2 3 4 5 6 7 8 9 10 11 12 13 14 |
/* * Slab allocator functions that are independent of the allocator strategy * * (C) 2012 Christoph Lameter <cl@linux.com> */ #include <linux/slab.h> #include <linux/mm.h> #include <linux/poison.h> #include <linux/interrupt.h> #include <linux/memory.h> #include <linux/compiler.h> #include <linux/module.h> |
20cea9683
|
15 16 |
#include <linux/cpu.h> #include <linux/uaccess.h> |
b7454ad3c
|
17 18 |
#include <linux/seq_file.h> #include <linux/proc_fs.h> |
039363f38
|
19 20 21 |
#include <asm/cacheflush.h> #include <asm/tlbflush.h> #include <asm/page.h> |
2633d7a02
|
22 |
#include <linux/memcontrol.h> |
928cec9cd
|
23 24 |
#define CREATE_TRACE_POINTS |
f1b6eb6e6
|
25 |
#include <trace/events/kmem.h> |
039363f38
|
26 |
|
97d066091
|
27 28 29 |
#include "slab.h" enum slab_state slab_state; |
18004c5d4
|
30 31 |
LIST_HEAD(slab_caches); DEFINE_MUTEX(slab_mutex); |
9b030cb86
|
32 |
struct kmem_cache *kmem_cache; |
97d066091
|
33 |
|
657dc2f97
|
34 35 36 37 |
static LIST_HEAD(slab_caches_to_rcu_destroy); static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work); static DECLARE_WORK(slab_caches_to_rcu_destroy_work, slab_caches_to_rcu_destroy_workfn); |
07f361b2b
|
38 |
/* |
423c929cb
|
39 40 41 |
* Set of flags that will prevent slab merging */ #define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \ |
5f0d5a3ae
|
42 |
SLAB_TRACE | SLAB_TYPESAFE_BY_RCU | SLAB_NOLEAKTRACE | \ |
7ed2f9e66
|
43 |
SLAB_FAILSLAB | SLAB_KASAN) |
423c929cb
|
44 |
|
230e9fc28
|
45 |
#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | \ |
ae63fd26b
|
46 |
SLAB_ACCOUNT) |
423c929cb
|
47 48 49 |
/* * Merge control. If this is set then no merging of slab caches will occur. |
423c929cb
|
50 |
*/ |
7660a6fdd
|
51 |
static bool slab_nomerge = !IS_ENABLED(CONFIG_SLAB_MERGE_DEFAULT); |
423c929cb
|
52 53 54 |
static int __init setup_slab_nomerge(char *str) { |
7660a6fdd
|
55 |
slab_nomerge = true; |
423c929cb
|
56 57 58 59 60 61 62 63 64 65 |
return 1; } #ifdef CONFIG_SLUB __setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0); #endif __setup("slab_nomerge", setup_slab_nomerge); /* |
07f361b2b
|
66 67 68 69 70 71 72 |
* Determine the size of a slab object */ unsigned int kmem_cache_size(struct kmem_cache *s) { return s->object_size; } EXPORT_SYMBOL(kmem_cache_size); |
77be4b136
|
73 |
#ifdef CONFIG_DEBUG_VM |
794b1248b
|
74 |
static int kmem_cache_sanity_check(const char *name, size_t size) |
039363f38
|
75 76 |
{ struct kmem_cache *s = NULL; |
039363f38
|
77 78 |
if (!name || in_interrupt() || size < sizeof(void *) || size > KMALLOC_MAX_SIZE) { |
77be4b136
|
79 80 81 |
pr_err("kmem_cache_create(%s) integrity check failed ", name); return -EINVAL; |
039363f38
|
82 |
} |
b920536aa
|
83 |
|
20cea9683
|
84 85 86 87 88 89 90 91 92 93 94 |
list_for_each_entry(s, &slab_caches, list) { char tmp; int res; /* * This happens when the module gets unloaded and doesn't * destroy its slab cache and no-one else reuses the vmalloc * area of the module. Print a warning. */ res = probe_kernel_address(s->name, tmp); if (res) { |
77be4b136
|
95 96 |
pr_err("Slab cache with size %d has lost its name ", |
20cea9683
|
97 98 99 |
s->object_size); continue; } |
20cea9683
|
100 101 102 |
} WARN_ON(strchr(name, ' ')); /* It confuses parsers */ |
77be4b136
|
103 104 105 |
return 0; } #else |
794b1248b
|
106 |
static inline int kmem_cache_sanity_check(const char *name, size_t size) |
77be4b136
|
107 108 109 |
{ return 0; } |
20cea9683
|
110 |
#endif |
484748f0b
|
111 112 113 |
void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p) { size_t i; |
ca2571955
|
114 115 116 117 118 119 |
for (i = 0; i < nr; i++) { if (s) kmem_cache_free(s, p[i]); else kfree(p[i]); } |
484748f0b
|
120 |
} |
865762a81
|
121 |
int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, |
484748f0b
|
122 123 124 125 126 127 128 129 |
void **p) { size_t i; for (i = 0; i < nr; i++) { void *x = p[i] = kmem_cache_alloc(s, flags); if (!x) { __kmem_cache_free_bulk(s, i, p); |
865762a81
|
130 |
return 0; |
484748f0b
|
131 132 |
} } |
865762a81
|
133 |
return i; |
484748f0b
|
134 |
} |
127424c86
|
135 |
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) |
510ded33e
|
136 137 |
LIST_HEAD(slab_root_caches); |
f7ce3190c
|
138 |
void slab_init_memcg_params(struct kmem_cache *s) |
33a690c45
|
139 |
{ |
9eeadc8b6
|
140 |
s->memcg_params.root_cache = NULL; |
f7ce3190c
|
141 |
RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL); |
9eeadc8b6
|
142 |
INIT_LIST_HEAD(&s->memcg_params.children); |
f7ce3190c
|
143 144 145 146 147 148 |
} static int init_memcg_params(struct kmem_cache *s, struct mem_cgroup *memcg, struct kmem_cache *root_cache) { struct memcg_cache_array *arr; |
33a690c45
|
149 |
|
9eeadc8b6
|
150 |
if (root_cache) { |
f7ce3190c
|
151 |
s->memcg_params.root_cache = root_cache; |
9eeadc8b6
|
152 153 |
s->memcg_params.memcg = memcg; INIT_LIST_HEAD(&s->memcg_params.children_node); |
bc2791f85
|
154 |
INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node); |
33a690c45
|
155 |
return 0; |
f7ce3190c
|
156 |
} |
33a690c45
|
157 |
|
f7ce3190c
|
158 |
slab_init_memcg_params(s); |
33a690c45
|
159 |
|
f7ce3190c
|
160 161 |
if (!memcg_nr_cache_ids) return 0; |
33a690c45
|
162 |
|
f80c7dab9
|
163 164 165 |
arr = kvzalloc(sizeof(struct memcg_cache_array) + memcg_nr_cache_ids * sizeof(void *), GFP_KERNEL); |
f7ce3190c
|
166 167 |
if (!arr) return -ENOMEM; |
33a690c45
|
168 |
|
f7ce3190c
|
169 |
RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr); |
33a690c45
|
170 171 |
return 0; } |
f7ce3190c
|
172 |
static void destroy_memcg_params(struct kmem_cache *s) |
33a690c45
|
173 |
{ |
f7ce3190c
|
174 |
if (is_root_cache(s)) |
f80c7dab9
|
175 176 177 178 179 180 181 182 183 |
kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); } static void free_memcg_params(struct rcu_head *rcu) { struct memcg_cache_array *old; old = container_of(rcu, struct memcg_cache_array, rcu); kvfree(old); |
33a690c45
|
184 |
} |
f7ce3190c
|
185 |
static int update_memcg_params(struct kmem_cache *s, int new_array_size) |
6f817f4cd
|
186 |
{ |
f7ce3190c
|
187 |
struct memcg_cache_array *old, *new; |
6f817f4cd
|
188 |
|
f80c7dab9
|
189 190 |
new = kvzalloc(sizeof(struct memcg_cache_array) + new_array_size * sizeof(void *), GFP_KERNEL); |
f7ce3190c
|
191 |
if (!new) |
6f817f4cd
|
192 |
return -ENOMEM; |
f7ce3190c
|
193 194 195 196 197 |
old = rcu_dereference_protected(s->memcg_params.memcg_caches, lockdep_is_held(&slab_mutex)); if (old) memcpy(new->entries, old->entries, memcg_nr_cache_ids * sizeof(void *)); |
6f817f4cd
|
198 |
|
f7ce3190c
|
199 200 |
rcu_assign_pointer(s->memcg_params.memcg_caches, new); if (old) |
f80c7dab9
|
201 |
call_rcu(&old->rcu, free_memcg_params); |
6f817f4cd
|
202 203 |
return 0; } |
55007d849
|
204 205 206 207 |
int memcg_update_all_caches(int num_memcgs) { struct kmem_cache *s; int ret = 0; |
55007d849
|
208 |
|
05257a1a3
|
209 |
mutex_lock(&slab_mutex); |
510ded33e
|
210 |
list_for_each_entry(s, &slab_root_caches, root_caches_node) { |
f7ce3190c
|
211 |
ret = update_memcg_params(s, num_memcgs); |
55007d849
|
212 |
/* |
55007d849
|
213 214 215 216 |
* Instead of freeing the memory, we'll just leave the caches * up to this point in an updated state. */ if (ret) |
05257a1a3
|
217 |
break; |
55007d849
|
218 |
} |
55007d849
|
219 220 221 |
mutex_unlock(&slab_mutex); return ret; } |
657dc2f97
|
222 |
|
510ded33e
|
223 |
void memcg_link_cache(struct kmem_cache *s) |
657dc2f97
|
224 |
{ |
510ded33e
|
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 |
if (is_root_cache(s)) { list_add(&s->root_caches_node, &slab_root_caches); } else { list_add(&s->memcg_params.children_node, &s->memcg_params.root_cache->memcg_params.children); list_add(&s->memcg_params.kmem_caches_node, &s->memcg_params.memcg->kmem_caches); } } static void memcg_unlink_cache(struct kmem_cache *s) { if (is_root_cache(s)) { list_del(&s->root_caches_node); } else { list_del(&s->memcg_params.children_node); list_del(&s->memcg_params.kmem_caches_node); } |
657dc2f97
|
243 |
} |
33a690c45
|
244 |
#else |
f7ce3190c
|
245 246 |
static inline int init_memcg_params(struct kmem_cache *s, struct mem_cgroup *memcg, struct kmem_cache *root_cache) |
33a690c45
|
247 248 249 |
{ return 0; } |
f7ce3190c
|
250 |
static inline void destroy_memcg_params(struct kmem_cache *s) |
33a690c45
|
251 252 |
{ } |
657dc2f97
|
253 |
|
510ded33e
|
254 |
static inline void memcg_unlink_cache(struct kmem_cache *s) |
657dc2f97
|
255 256 |
{ } |
127424c86
|
257 |
#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ |
55007d849
|
258 |
|
77be4b136
|
259 |
/* |
423c929cb
|
260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 |
* Find a mergeable slab cache */ int slab_unmergeable(struct kmem_cache *s) { if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE)) return 1; if (!is_root_cache(s)) return 1; if (s->ctor) return 1; /* * We may have set a slab to be unmergeable during bootstrap. */ if (s->refcount < 0) return 1; return 0; } struct kmem_cache *find_mergeable(size_t size, size_t align, unsigned long flags, const char *name, void (*ctor)(void *)) { struct kmem_cache *s; |
c6e28895a
|
286 |
if (slab_nomerge) |
423c929cb
|
287 288 289 290 291 292 293 294 295 |
return NULL; if (ctor) return NULL; size = ALIGN(size, sizeof(void *)); align = calculate_alignment(flags, align, size); size = ALIGN(size, align); flags = kmem_cache_flags(size, flags, name, NULL); |
c6e28895a
|
296 297 |
if (flags & SLAB_NEVER_MERGE) return NULL; |
510ded33e
|
298 |
list_for_each_entry_reverse(s, &slab_root_caches, root_caches_node) { |
423c929cb
|
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 |
if (slab_unmergeable(s)) continue; if (size > s->size) continue; if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME)) continue; /* * Check if alignment is compatible. * Courtesy of Adrian Drzewiecki */ if ((s->size & ~(align - 1)) != s->size) continue; if (s->size - size >= sizeof(void *)) continue; |
95069ac8d
|
316 317 318 |
if (IS_ENABLED(CONFIG_SLAB) && align && (align > s->align || s->align % align)) continue; |
423c929cb
|
319 320 321 322 323 324 |
return s; } return NULL; } /* |
459068554
|
325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 |
* Figure out what the alignment of the objects will be given a set of * flags, a user specified alignment and the size of the objects. */ unsigned long calculate_alignment(unsigned long flags, unsigned long align, unsigned long size) { /* * If the user wants hardware cache aligned objects then follow that * suggestion if the object is sufficiently large. * * The hardware cache alignment cannot override the specified * alignment though. If that is greater then use it. */ if (flags & SLAB_HWCACHE_ALIGN) { unsigned long ralign = cache_line_size(); while (size <= ralign / 2) ralign /= 2; align = max(align, ralign); } if (align < ARCH_SLAB_MINALIGN) align = ARCH_SLAB_MINALIGN; return ALIGN(align, sizeof(void *)); } |
c9a77a792
|
350 351 352 353 |
static struct kmem_cache *create_cache(const char *name, size_t object_size, size_t size, size_t align, unsigned long flags, void (*ctor)(void *), struct mem_cgroup *memcg, struct kmem_cache *root_cache) |
794b1248b
|
354 355 356 357 358 359 360 361 362 363 364 365 366 367 |
{ struct kmem_cache *s; int err; err = -ENOMEM; s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL); if (!s) goto out; s->name = name; s->object_size = object_size; s->size = size; s->align = align; s->ctor = ctor; |
f7ce3190c
|
368 |
err = init_memcg_params(s, memcg, root_cache); |
794b1248b
|
369 370 371 372 373 374 375 376 377 |
if (err) goto out_free_cache; err = __kmem_cache_create(s, flags); if (err) goto out_free_cache; s->refcount = 1; list_add(&s->list, &slab_caches); |
510ded33e
|
378 |
memcg_link_cache(s); |
794b1248b
|
379 380 381 382 383 384 |
out: if (err) return ERR_PTR(err); return s; out_free_cache: |
f7ce3190c
|
385 |
destroy_memcg_params(s); |
7c4da061f
|
386 |
kmem_cache_free(kmem_cache, s); |
794b1248b
|
387 388 |
goto out; } |
459068554
|
389 390 |
/* |
77be4b136
|
391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 |
* kmem_cache_create - Create a cache. * @name: A string which is used in /proc/slabinfo to identify this cache. * @size: The size of objects to be created in this cache. * @align: The required alignment for the objects. * @flags: SLAB flags * @ctor: A constructor for the objects. * * Returns a ptr to the cache on success, NULL on failure. * Cannot be called within a interrupt, but can be interrupted. * The @ctor is run when new pages are allocated by the cache. * * The flags are * * %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5) * to catch references to uninitialised memory. * * %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check * for buffer overruns. * * %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware * cacheline. This can be beneficial if you're counting cycles as closely * as davem. */ |
2633d7a02
|
414 |
struct kmem_cache * |
794b1248b
|
415 416 |
kmem_cache_create(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) |
77be4b136
|
417 |
{ |
40911a798
|
418 |
struct kmem_cache *s = NULL; |
3dec16ea3
|
419 |
const char *cache_name; |
3965fc365
|
420 |
int err; |
039363f38
|
421 |
|
77be4b136
|
422 |
get_online_cpus(); |
03afc0e25
|
423 |
get_online_mems(); |
05257a1a3
|
424 |
memcg_get_cache_ids(); |
03afc0e25
|
425 |
|
77be4b136
|
426 |
mutex_lock(&slab_mutex); |
686d550d2
|
427 |
|
794b1248b
|
428 |
err = kmem_cache_sanity_check(name, size); |
3aa24f519
|
429 |
if (err) { |
3965fc365
|
430 |
goto out_unlock; |
3aa24f519
|
431 |
} |
686d550d2
|
432 |
|
e70954fd6
|
433 434 435 436 437 |
/* Refuse requests with allocator specific flags */ if (flags & ~SLAB_FLAGS_PERMITTED) { err = -EINVAL; goto out_unlock; } |
d8843922f
|
438 439 440 441 442 443 444 |
/* * Some allocators will constraint the set of valid flags to a subset * of all flags. We expect them to define CACHE_CREATE_MASK in this * case, and we'll just provide them with a sanitized version of the * passed flags. */ flags &= CACHE_CREATE_MASK; |
686d550d2
|
445 |
|
794b1248b
|
446 447 |
s = __kmem_cache_alias(name, size, align, flags, ctor); if (s) |
3965fc365
|
448 |
goto out_unlock; |
2633d7a02
|
449 |
|
3dec16ea3
|
450 |
cache_name = kstrdup_const(name, GFP_KERNEL); |
794b1248b
|
451 452 453 454 |
if (!cache_name) { err = -ENOMEM; goto out_unlock; } |
7c9adf5a5
|
455 |
|
c9a77a792
|
456 457 458 |
s = create_cache(cache_name, size, size, calculate_alignment(flags, align, size), flags, ctor, NULL, NULL); |
794b1248b
|
459 460 |
if (IS_ERR(s)) { err = PTR_ERR(s); |
3dec16ea3
|
461 |
kfree_const(cache_name); |
794b1248b
|
462 |
} |
3965fc365
|
463 464 |
out_unlock: |
20cea9683
|
465 |
mutex_unlock(&slab_mutex); |
03afc0e25
|
466 |
|
05257a1a3
|
467 |
memcg_put_cache_ids(); |
03afc0e25
|
468 |
put_online_mems(); |
20cea9683
|
469 |
put_online_cpus(); |
ba3253c78
|
470 |
if (err) { |
686d550d2
|
471 472 473 474 475 |
if (flags & SLAB_PANIC) panic("kmem_cache_create: Failed to create slab '%s'. Error %d ", name, err); else { |
1170532bb
|
476 477 |
pr_warn("kmem_cache_create(%s) failed with error %d ", |
686d550d2
|
478 479 480 |
name, err); dump_stack(); } |
686d550d2
|
481 482 |
return NULL; } |
039363f38
|
483 484 |
return s; } |
794b1248b
|
485 |
EXPORT_SYMBOL(kmem_cache_create); |
2633d7a02
|
486 |
|
657dc2f97
|
487 |
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work) |
d5b3cf713
|
488 |
{ |
657dc2f97
|
489 490 |
LIST_HEAD(to_destroy); struct kmem_cache *s, *s2; |
d5b3cf713
|
491 |
|
657dc2f97
|
492 |
/* |
5f0d5a3ae
|
493 |
* On destruction, SLAB_TYPESAFE_BY_RCU kmem_caches are put on the |
657dc2f97
|
494 495 496 497 498 499 500 501 502 503 |
* @slab_caches_to_rcu_destroy list. The slab pages are freed * through RCU and and the associated kmem_cache are dereferenced * while freeing the pages, so the kmem_caches should be freed only * after the pending RCU operations are finished. As rcu_barrier() * is a pretty slow operation, we batch all pending destructions * asynchronously. */ mutex_lock(&slab_mutex); list_splice_init(&slab_caches_to_rcu_destroy, &to_destroy); mutex_unlock(&slab_mutex); |
d5b3cf713
|
504 |
|
657dc2f97
|
505 506 507 508 509 510 511 512 513 514 515 516 |
if (list_empty(&to_destroy)) return; rcu_barrier(); list_for_each_entry_safe(s, s2, &to_destroy, list) { #ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_release(s); #else slab_kmem_cache_release(s); #endif } |
d5b3cf713
|
517 |
} |
657dc2f97
|
518 |
static int shutdown_cache(struct kmem_cache *s) |
d5b3cf713
|
519 |
{ |
f9fa1d919
|
520 521 |
/* free asan quarantined objects */ kasan_cache_shutdown(s); |
657dc2f97
|
522 523 |
if (__kmem_cache_shutdown(s) != 0) return -EBUSY; |
d5b3cf713
|
524 |
|
510ded33e
|
525 |
memcg_unlink_cache(s); |
657dc2f97
|
526 |
list_del(&s->list); |
d5b3cf713
|
527 |
|
5f0d5a3ae
|
528 |
if (s->flags & SLAB_TYPESAFE_BY_RCU) { |
804a0db74
|
529 530 531 |
#ifdef SLAB_SUPPORTS_SYSFS sysfs_slab_unlink(s); #endif |
657dc2f97
|
532 533 534 |
list_add_tail(&s->list, &slab_caches_to_rcu_destroy); schedule_work(&slab_caches_to_rcu_destroy_work); } else { |
d5b3cf713
|
535 |
#ifdef SLAB_SUPPORTS_SYSFS |
804a0db74
|
536 |
sysfs_slab_unlink(s); |
bf5eb3de3
|
537 |
sysfs_slab_release(s); |
d5b3cf713
|
538 539 540 541 |
#else slab_kmem_cache_release(s); #endif } |
657dc2f97
|
542 543 |
return 0; |
d5b3cf713
|
544 |
} |
127424c86
|
545 |
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) |
794b1248b
|
546 |
/* |
776ed0f03
|
547 |
* memcg_create_kmem_cache - Create a cache for a memory cgroup. |
794b1248b
|
548 549 550 551 552 553 554 |
* @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. * * This function attempts to create a kmem cache that will serve allocation * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ |
d5b3cf713
|
555 556 |
void memcg_create_kmem_cache(struct mem_cgroup *memcg, struct kmem_cache *root_cache) |
2633d7a02
|
557 |
{ |
3e0350a36
|
558 |
static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */ |
33398cf2f
|
559 |
struct cgroup_subsys_state *css = &memcg->css; |
f7ce3190c
|
560 |
struct memcg_cache_array *arr; |
bd6731458
|
561 |
struct kmem_cache *s = NULL; |
794b1248b
|
562 |
char *cache_name; |
f7ce3190c
|
563 |
int idx; |
794b1248b
|
564 565 |
get_online_cpus(); |
03afc0e25
|
566 |
get_online_mems(); |
794b1248b
|
567 |
mutex_lock(&slab_mutex); |
2a4db7eb9
|
568 |
/* |
567e9ab2e
|
569 |
* The memory cgroup could have been offlined while the cache |
2a4db7eb9
|
570 571 |
* creation work was pending. */ |
b6ecd2dea
|
572 |
if (memcg->kmem_state != KMEM_ONLINE) |
2a4db7eb9
|
573 |
goto out_unlock; |
f7ce3190c
|
574 575 576 |
idx = memcg_cache_id(memcg); arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches, lockdep_is_held(&slab_mutex)); |
d5b3cf713
|
577 578 579 580 581 |
/* * Since per-memcg caches are created asynchronously on first * allocation (see memcg_kmem_get_cache()), several threads can try to * create the same cache, but only one of them may succeed. */ |
f7ce3190c
|
582 |
if (arr->entries[idx]) |
d5b3cf713
|
583 |
goto out_unlock; |
f1008365b
|
584 |
cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); |
73f576c04
|
585 586 |
cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name, css->serial_nr, memcg_name_buf); |
794b1248b
|
587 588 |
if (!cache_name) goto out_unlock; |
c9a77a792
|
589 590 |
s = create_cache(cache_name, root_cache->object_size, root_cache->size, root_cache->align, |
f773e36de
|
591 592 |
root_cache->flags & CACHE_CREATE_MASK, root_cache->ctor, memcg, root_cache); |
d5b3cf713
|
593 594 595 596 597 |
/* * If we could not create a memcg cache, do not complain, because * that's not critical at all as we can always proceed with the root * cache. */ |
bd6731458
|
598 |
if (IS_ERR(s)) { |
794b1248b
|
599 |
kfree(cache_name); |
d5b3cf713
|
600 |
goto out_unlock; |
bd6731458
|
601 |
} |
794b1248b
|
602 |
|
d5b3cf713
|
603 604 605 606 607 608 |
/* * Since readers won't lock (see cache_from_memcg_idx()), we need a * barrier here to ensure nobody will see the kmem_cache partially * initialized. */ smp_wmb(); |
f7ce3190c
|
609 |
arr->entries[idx] = s; |
d5b3cf713
|
610 |
|
794b1248b
|
611 612 |
out_unlock: mutex_unlock(&slab_mutex); |
03afc0e25
|
613 614 |
put_online_mems(); |
794b1248b
|
615 |
put_online_cpus(); |
2633d7a02
|
616 |
} |
b8529907b
|
617 |
|
01fb58bcb
|
618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 |
static void kmemcg_deactivate_workfn(struct work_struct *work) { struct kmem_cache *s = container_of(work, struct kmem_cache, memcg_params.deact_work); get_online_cpus(); get_online_mems(); mutex_lock(&slab_mutex); s->memcg_params.deact_fn(s); mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); /* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */ css_put(&s->memcg_params.memcg->css); } static void kmemcg_deactivate_rcufn(struct rcu_head *head) { struct kmem_cache *s = container_of(head, struct kmem_cache, memcg_params.deact_rcu_head); /* * We need to grab blocking locks. Bounce to ->deact_work. The * work item shares the space with the RCU head and can't be * initialized eariler. */ INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn); |
17cc4dfed
|
650 |
queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work); |
01fb58bcb
|
651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 |
} /** * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a * sched RCU grace period * @s: target kmem_cache * @deact_fn: deactivation function to call * * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex * held after a sched RCU grace period. The slab is guaranteed to stay * alive until @deact_fn is finished. This is to be used from * __kmemcg_cache_deactivate(). */ void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s, void (*deact_fn)(struct kmem_cache *)) { if (WARN_ON_ONCE(is_root_cache(s)) || WARN_ON_ONCE(s->memcg_params.deact_fn)) return; /* pin memcg so that @s doesn't get destroyed in the middle */ css_get(&s->memcg_params.memcg->css); s->memcg_params.deact_fn = deact_fn; call_rcu_sched(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn); } |
2a4db7eb9
|
677 678 679 680 |
void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) { int idx; struct memcg_cache_array *arr; |
d6e0b7fa1
|
681 |
struct kmem_cache *s, *c; |
2a4db7eb9
|
682 683 |
idx = memcg_cache_id(memcg); |
d6e0b7fa1
|
684 685 |
get_online_cpus(); get_online_mems(); |
2a4db7eb9
|
686 |
mutex_lock(&slab_mutex); |
510ded33e
|
687 |
list_for_each_entry(s, &slab_root_caches, root_caches_node) { |
2a4db7eb9
|
688 689 |
arr = rcu_dereference_protected(s->memcg_params.memcg_caches, lockdep_is_held(&slab_mutex)); |
d6e0b7fa1
|
690 691 692 |
c = arr->entries[idx]; if (!c) continue; |
c9fc58640
|
693 |
__kmemcg_cache_deactivate(c); |
2a4db7eb9
|
694 695 696 |
arr->entries[idx] = NULL; } mutex_unlock(&slab_mutex); |
d6e0b7fa1
|
697 698 699 |
put_online_mems(); put_online_cpus(); |
2a4db7eb9
|
700 |
} |
d5b3cf713
|
701 |
void memcg_destroy_kmem_caches(struct mem_cgroup *memcg) |
b8529907b
|
702 |
{ |
d5b3cf713
|
703 |
struct kmem_cache *s, *s2; |
b8529907b
|
704 |
|
d5b3cf713
|
705 706 |
get_online_cpus(); get_online_mems(); |
b8529907b
|
707 |
|
b8529907b
|
708 |
mutex_lock(&slab_mutex); |
bc2791f85
|
709 710 |
list_for_each_entry_safe(s, s2, &memcg->kmem_caches, memcg_params.kmem_caches_node) { |
d5b3cf713
|
711 712 713 714 |
/* * The cgroup is about to be freed and therefore has no charges * left. Hence, all its caches must be empty by now. */ |
657dc2f97
|
715 |
BUG_ON(shutdown_cache(s)); |
d5b3cf713
|
716 717 |
} mutex_unlock(&slab_mutex); |
b8529907b
|
718 |
|
d5b3cf713
|
719 720 |
put_online_mems(); put_online_cpus(); |
b8529907b
|
721 |
} |
d60fdcc9e
|
722 |
|
657dc2f97
|
723 |
static int shutdown_memcg_caches(struct kmem_cache *s) |
d60fdcc9e
|
724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 |
{ struct memcg_cache_array *arr; struct kmem_cache *c, *c2; LIST_HEAD(busy); int i; BUG_ON(!is_root_cache(s)); /* * First, shutdown active caches, i.e. caches that belong to online * memory cgroups. */ arr = rcu_dereference_protected(s->memcg_params.memcg_caches, lockdep_is_held(&slab_mutex)); for_each_memcg_cache_index(i) { c = arr->entries[i]; if (!c) continue; |
657dc2f97
|
742 |
if (shutdown_cache(c)) |
d60fdcc9e
|
743 744 745 746 747 |
/* * The cache still has objects. Move it to a temporary * list so as not to try to destroy it for a second * time while iterating over inactive caches below. */ |
9eeadc8b6
|
748 |
list_move(&c->memcg_params.children_node, &busy); |
d60fdcc9e
|
749 750 751 752 753 754 755 756 757 758 759 760 761 762 |
else /* * The cache is empty and will be destroyed soon. Clear * the pointer to it in the memcg_caches array so that * it will never be accessed even if the root cache * stays alive. */ arr->entries[i] = NULL; } /* * Second, shutdown all caches left from memory cgroups that are now * offline. */ |
9eeadc8b6
|
763 764 |
list_for_each_entry_safe(c, c2, &s->memcg_params.children, memcg_params.children_node) |
657dc2f97
|
765 |
shutdown_cache(c); |
d60fdcc9e
|
766 |
|
9eeadc8b6
|
767 |
list_splice(&busy, &s->memcg_params.children); |
d60fdcc9e
|
768 769 770 771 772 |
/* * A cache being destroyed must be empty. In particular, this means * that all per memcg caches attached to it must be empty too. */ |
9eeadc8b6
|
773 |
if (!list_empty(&s->memcg_params.children)) |
d60fdcc9e
|
774 775 776 777 |
return -EBUSY; return 0; } #else |
657dc2f97
|
778 |
static inline int shutdown_memcg_caches(struct kmem_cache *s) |
d60fdcc9e
|
779 780 781 |
{ return 0; } |
127424c86
|
782 |
#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ |
97d066091
|
783 |
|
41a212859
|
784 785 |
void slab_kmem_cache_release(struct kmem_cache *s) { |
52b4b950b
|
786 |
__kmem_cache_release(s); |
f7ce3190c
|
787 |
destroy_memcg_params(s); |
3dec16ea3
|
788 |
kfree_const(s->name); |
41a212859
|
789 790 |
kmem_cache_free(kmem_cache, s); } |
945cf2b61
|
791 792 |
void kmem_cache_destroy(struct kmem_cache *s) { |
d60fdcc9e
|
793 |
int err; |
d5b3cf713
|
794 |
|
3942d2991
|
795 796 |
if (unlikely(!s)) return; |
945cf2b61
|
797 |
get_online_cpus(); |
03afc0e25
|
798 |
get_online_mems(); |
945cf2b61
|
799 |
mutex_lock(&slab_mutex); |
b8529907b
|
800 |
|
945cf2b61
|
801 |
s->refcount--; |
b8529907b
|
802 803 |
if (s->refcount) goto out_unlock; |
657dc2f97
|
804 |
err = shutdown_memcg_caches(s); |
d60fdcc9e
|
805 |
if (!err) |
657dc2f97
|
806 |
err = shutdown_cache(s); |
b8529907b
|
807 |
|
cd918c557
|
808 |
if (err) { |
756a025f0
|
809 810 811 |
pr_err("kmem_cache_destroy %s: Slab cache still has objects ", s->name); |
cd918c557
|
812 813 |
dump_stack(); } |
b8529907b
|
814 815 |
out_unlock: mutex_unlock(&slab_mutex); |
d5b3cf713
|
816 |
|
03afc0e25
|
817 |
put_online_mems(); |
945cf2b61
|
818 819 820 |
put_online_cpus(); } EXPORT_SYMBOL(kmem_cache_destroy); |
03afc0e25
|
821 822 823 824 825 826 827 828 829 830 831 832 833 |
/** * kmem_cache_shrink - Shrink a cache. * @cachep: The cache to shrink. * * Releases as many slabs as possible for a cache. * To help debugging, a zero exit status indicates all slabs were released. */ int kmem_cache_shrink(struct kmem_cache *cachep) { int ret; get_online_cpus(); get_online_mems(); |
55834c590
|
834 |
kasan_cache_shrink(cachep); |
c9fc58640
|
835 |
ret = __kmem_cache_shrink(cachep); |
03afc0e25
|
836 837 838 839 840 |
put_online_mems(); put_online_cpus(); return ret; } EXPORT_SYMBOL(kmem_cache_shrink); |
fda901241
|
841 |
bool slab_is_available(void) |
97d066091
|
842 843 844 |
{ return slab_state >= UP; } |
b7454ad3c
|
845 |
|
45530c447
|
846 847 848 849 850 851 852 853 854 |
#ifndef CONFIG_SLOB /* Create a cache during boot when no slab services are available yet */ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t size, unsigned long flags) { int err; s->name = name; s->size = s->object_size = size; |
459068554
|
855 |
s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size); |
f7ce3190c
|
856 857 |
slab_init_memcg_params(s); |
45530c447
|
858 859 860 |
err = __kmem_cache_create(s, flags); if (err) |
31ba7346f
|
861 862 |
panic("Creation of kmalloc slab %s size=%zu failed. Reason %d ", |
45530c447
|
863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 |
name, size, err); s->refcount = -1; /* Exempt from merging for now */ } struct kmem_cache *__init create_kmalloc_cache(const char *name, size_t size, unsigned long flags) { struct kmem_cache *s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT); if (!s) panic("Out of memory when creating slab %s ", name); create_boot_cache(s, name, size, flags); list_add(&s->list, &slab_caches); |
510ded33e
|
879 |
memcg_link_cache(s); |
45530c447
|
880 881 882 |
s->refcount = 1; return s; } |
9425c58e5
|
883 884 885 886 887 888 889 |
struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; EXPORT_SYMBOL(kmalloc_caches); #ifdef CONFIG_ZONE_DMA struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; EXPORT_SYMBOL(kmalloc_dma_caches); #endif |
f97d5f634
|
890 |
/* |
2c59dd654
|
891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 |
* Conversion table for small slabs sizes / 8 to the index in the * kmalloc array. This is necessary for slabs < 192 since we have non power * of two cache sizes there. The size of larger slabs can be determined using * fls. */ static s8 size_index[24] = { 3, /* 8 */ 4, /* 16 */ 5, /* 24 */ 5, /* 32 */ 6, /* 40 */ 6, /* 48 */ 6, /* 56 */ 6, /* 64 */ 1, /* 72 */ 1, /* 80 */ 1, /* 88 */ 1, /* 96 */ 7, /* 104 */ 7, /* 112 */ 7, /* 120 */ 7, /* 128 */ 2, /* 136 */ 2, /* 144 */ 2, /* 152 */ 2, /* 160 */ 2, /* 168 */ 2, /* 176 */ 2, /* 184 */ 2 /* 192 */ }; static inline int size_index_elem(size_t bytes) { return (bytes - 1) / 8; } /* * Find the kmem_cache structure that serves a given size of * allocation */ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) { int index; if (size <= 192) { if (!size) return ZERO_SIZE_PTR; index = size_index[size_index_elem(size)]; |
977640438
|
941 942 943 944 945 |
} else { if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { WARN_ON(1); return NULL; } |
2c59dd654
|
946 |
index = fls(size - 1); |
977640438
|
947 |
} |
2c59dd654
|
948 949 |
#ifdef CONFIG_ZONE_DMA |
b1e054167
|
950 |
if (unlikely((flags & GFP_DMA))) |
2c59dd654
|
951 952 953 954 955 956 957 |
return kmalloc_dma_caches[index]; #endif return kmalloc_caches[index]; } /* |
4066c33d0
|
958 959 960 961 |
* kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time. * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is * kmalloc-67108864. */ |
af3b5f876
|
962 |
const struct kmalloc_info_struct kmalloc_info[] __initconst = { |
4066c33d0
|
963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 |
{NULL, 0}, {"kmalloc-96", 96}, {"kmalloc-192", 192}, {"kmalloc-8", 8}, {"kmalloc-16", 16}, {"kmalloc-32", 32}, {"kmalloc-64", 64}, {"kmalloc-128", 128}, {"kmalloc-256", 256}, {"kmalloc-512", 512}, {"kmalloc-1024", 1024}, {"kmalloc-2048", 2048}, {"kmalloc-4096", 4096}, {"kmalloc-8192", 8192}, {"kmalloc-16384", 16384}, {"kmalloc-32768", 32768}, {"kmalloc-65536", 65536}, {"kmalloc-131072", 131072}, {"kmalloc-262144", 262144}, {"kmalloc-524288", 524288}, {"kmalloc-1048576", 1048576}, {"kmalloc-2097152", 2097152}, {"kmalloc-4194304", 4194304}, {"kmalloc-8388608", 8388608}, {"kmalloc-16777216", 16777216}, {"kmalloc-33554432", 33554432}, {"kmalloc-67108864", 67108864} }; /* |
34cc6990d
|
980 981 982 983 984 985 986 987 988 |
* Patch up the size_index table if we have strange large alignment * requirements for the kmalloc array. This is only the case for * MIPS it seems. The standard arches will not generate any code here. * * Largest permitted alignment is 256 bytes due to the way we * handle the index determination for the smaller caches. * * Make sure that nothing crazy happens if someone starts tinkering * around with ARCH_KMALLOC_MINALIGN |
f97d5f634
|
989 |
*/ |
34cc6990d
|
990 |
void __init setup_kmalloc_cache_index_table(void) |
f97d5f634
|
991 992 |
{ int i; |
2c59dd654
|
993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 |
BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 || (KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1))); for (i = 8; i < KMALLOC_MIN_SIZE; i += 8) { int elem = size_index_elem(i); if (elem >= ARRAY_SIZE(size_index)) break; size_index[elem] = KMALLOC_SHIFT_LOW; } if (KMALLOC_MIN_SIZE >= 64) { /* * The 96 byte size cache is not used if the alignment * is 64 byte. */ for (i = 64 + 8; i <= 96; i += 8) size_index[size_index_elem(i)] = 7; } if (KMALLOC_MIN_SIZE >= 128) { /* * The 192 byte sized cache is not used if the alignment * is 128 byte. Redirect kmalloc to use the 256 byte cache * instead. */ for (i = 128 + 8; i <= 192; i += 8) size_index[size_index_elem(i)] = 8; } |
34cc6990d
|
1023 |
} |
ae6f2462e
|
1024 |
static void __init new_kmalloc_cache(int idx, unsigned long flags) |
a9730fca9
|
1025 1026 1027 1028 |
{ kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name, kmalloc_info[idx].size, flags); } |
34cc6990d
|
1029 1030 1031 1032 1033 1034 1035 1036 |
/* * Create the kmalloc array. Some of the regular kmalloc arrays * may already have been created because they were needed to * enable allocations for slab creation. */ void __init create_kmalloc_caches(unsigned long flags) { int i; |
a9730fca9
|
1037 1038 1039 |
for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { if (!kmalloc_caches[i]) new_kmalloc_cache(i, flags); |
f97d5f634
|
1040 |
|
956e46efb
|
1041 |
/* |
a9730fca9
|
1042 1043 1044 |
* Caches that are not of the two-to-the-power-of size. * These have to be created immediately after the * earlier power of two caches |
956e46efb
|
1045 |
*/ |
a9730fca9
|
1046 1047 1048 1049 |
if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6) new_kmalloc_cache(1, flags); if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7) new_kmalloc_cache(2, flags); |
8a965b3ba
|
1050 |
} |
f97d5f634
|
1051 1052 |
/* Kmalloc array is now usable */ slab_state = UP; |
f97d5f634
|
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 |
#ifdef CONFIG_ZONE_DMA for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { struct kmem_cache *s = kmalloc_caches[i]; if (s) { int size = kmalloc_size(i); char *n = kasprintf(GFP_NOWAIT, "dma-kmalloc-%d", size); BUG_ON(!n); kmalloc_dma_caches[i] = create_kmalloc_cache(n, size, SLAB_CACHE_DMA | flags); } } #endif } |
45530c447
|
1069 |
#endif /* !CONFIG_SLOB */ |
cea371f4f
|
1070 1071 1072 1073 1074 |
/* * To avoid unnecessary overhead, we pass through large allocation requests * directly to the page allocator. We use __GFP_COMP, because we will need to * know the allocation order to free the pages properly in kfree. */ |
52383431b
|
1075 1076 1077 1078 1079 1080 |
void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) { void *ret; struct page *page; flags |= __GFP_COMP; |
4949148ad
|
1081 |
page = alloc_pages(flags, order); |
52383431b
|
1082 1083 |
ret = page ? page_address(page) : NULL; kmemleak_alloc(ret, size, 1, flags); |
505f5dcb1
|
1084 |
kasan_kmalloc_large(ret, size, flags); |
52383431b
|
1085 1086 1087 |
return ret; } EXPORT_SYMBOL(kmalloc_order); |
f1b6eb6e6
|
1088 1089 1090 1091 1092 1093 1094 1095 1096 |
#ifdef CONFIG_TRACING void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order) { void *ret = kmalloc_order(size, flags, order); trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags); return ret; } EXPORT_SYMBOL(kmalloc_order_trace); #endif |
45530c447
|
1097 |
|
7c00fce98
|
1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 |
#ifdef CONFIG_SLAB_FREELIST_RANDOM /* Randomize a generic freelist */ static void freelist_randomize(struct rnd_state *state, unsigned int *list, size_t count) { size_t i; unsigned int rand; for (i = 0; i < count; i++) list[i] = i; /* Fisher-Yates shuffle */ for (i = count - 1; i > 0; i--) { rand = prandom_u32_state(state); rand %= (i + 1); swap(list[i], list[rand]); } } /* Create a random sequence per cache */ int cache_random_seq_create(struct kmem_cache *cachep, unsigned int count, gfp_t gfp) { struct rnd_state state; if (count < 2 || cachep->random_seq) return 0; cachep->random_seq = kcalloc(count, sizeof(unsigned int), gfp); if (!cachep->random_seq) return -ENOMEM; /* Get best entropy at this stage of boot */ prandom_seed_state(&state, get_random_long()); freelist_randomize(&state, cachep->random_seq, count); return 0; } /* Destroy the per-cache random freelist sequence */ void cache_random_seq_destroy(struct kmem_cache *cachep) { kfree(cachep->random_seq); cachep->random_seq = NULL; } #endif /* CONFIG_SLAB_FREELIST_RANDOM */ |
b7454ad3c
|
1144 |
#ifdef CONFIG_SLABINFO |
e9b4db2b8
|
1145 1146 1147 1148 1149 1150 |
#ifdef CONFIG_SLAB #define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR) #else #define SLABINFO_RIGHTS S_IRUSR #endif |
b047501cd
|
1151 |
static void print_slabinfo_header(struct seq_file *m) |
bcee6e2a1
|
1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 |
{ /* * Output format version, so at least we can change it * without _too_ many complaints. */ #ifdef CONFIG_DEBUG_SLAB seq_puts(m, "slabinfo - version: 2.1 (statistics) "); #else seq_puts(m, "slabinfo - version: 2.1 "); #endif |
756a025f0
|
1164 |
seq_puts(m, "# name <active_objs> <num_objs> <objsize> <objperslab> <pagesperslab>"); |
bcee6e2a1
|
1165 1166 1167 |
seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>"); seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>"); #ifdef CONFIG_DEBUG_SLAB |
756a025f0
|
1168 |
seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> <error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>"); |
bcee6e2a1
|
1169 1170 1171 1172 1173 |
seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>"); #endif seq_putc(m, ' '); } |
1df3b26f2
|
1174 |
void *slab_start(struct seq_file *m, loff_t *pos) |
b7454ad3c
|
1175 |
{ |
b7454ad3c
|
1176 |
mutex_lock(&slab_mutex); |
510ded33e
|
1177 |
return seq_list_start(&slab_root_caches, *pos); |
b7454ad3c
|
1178 |
} |
276a2439c
|
1179 |
void *slab_next(struct seq_file *m, void *p, loff_t *pos) |
b7454ad3c
|
1180 |
{ |
510ded33e
|
1181 |
return seq_list_next(p, &slab_root_caches, pos); |
b7454ad3c
|
1182 |
} |
276a2439c
|
1183 |
void slab_stop(struct seq_file *m, void *p) |
b7454ad3c
|
1184 1185 1186 |
{ mutex_unlock(&slab_mutex); } |
749c54151
|
1187 1188 1189 1190 1191 |
static void memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info) { struct kmem_cache *c; struct slabinfo sinfo; |
749c54151
|
1192 1193 1194 |
if (!is_root_cache(s)) return; |
426589f57
|
1195 |
for_each_memcg_cache(c, s) { |
749c54151
|
1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 |
memset(&sinfo, 0, sizeof(sinfo)); get_slabinfo(c, &sinfo); info->active_slabs += sinfo.active_slabs; info->num_slabs += sinfo.num_slabs; info->shared_avail += sinfo.shared_avail; info->active_objs += sinfo.active_objs; info->num_objs += sinfo.num_objs; } } |
b047501cd
|
1206 |
static void cache_show(struct kmem_cache *s, struct seq_file *m) |
b7454ad3c
|
1207 |
{ |
0d7561c61
|
1208 1209 1210 1211 |
struct slabinfo sinfo; memset(&sinfo, 0, sizeof(sinfo)); get_slabinfo(s, &sinfo); |
749c54151
|
1212 |
memcg_accumulate_slabinfo(s, &sinfo); |
0d7561c61
|
1213 |
seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d", |
749c54151
|
1214 |
cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size, |
0d7561c61
|
1215 1216 1217 1218 1219 1220 1221 1222 1223 |
sinfo.objects_per_slab, (1 << sinfo.cache_order)); seq_printf(m, " : tunables %4u %4u %4u", sinfo.limit, sinfo.batchcount, sinfo.shared); seq_printf(m, " : slabdata %6lu %6lu %6lu", sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail); slabinfo_show_stats(m, s); seq_putc(m, ' '); |
b7454ad3c
|
1224 |
} |
1df3b26f2
|
1225 |
static int slab_show(struct seq_file *m, void *p) |
749c54151
|
1226 |
{ |
510ded33e
|
1227 |
struct kmem_cache *s = list_entry(p, struct kmem_cache, root_caches_node); |
749c54151
|
1228 |
|
510ded33e
|
1229 |
if (p == slab_root_caches.next) |
1df3b26f2
|
1230 |
print_slabinfo_header(m); |
510ded33e
|
1231 |
cache_show(s, m); |
b047501cd
|
1232 1233 |
return 0; } |
127424c86
|
1234 |
#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) |
bc2791f85
|
1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 |
void *memcg_slab_start(struct seq_file *m, loff_t *pos) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); mutex_lock(&slab_mutex); return seq_list_start(&memcg->kmem_caches, *pos); } void *memcg_slab_next(struct seq_file *m, void *p, loff_t *pos) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); return seq_list_next(p, &memcg->kmem_caches, pos); } void memcg_slab_stop(struct seq_file *m, void *p) { mutex_unlock(&slab_mutex); } |
b047501cd
|
1254 1255 |
int memcg_slab_show(struct seq_file *m, void *p) { |
bc2791f85
|
1256 1257 |
struct kmem_cache *s = list_entry(p, struct kmem_cache, memcg_params.kmem_caches_node); |
b047501cd
|
1258 |
struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); |
bc2791f85
|
1259 |
if (p == memcg->kmem_caches.next) |
b047501cd
|
1260 |
print_slabinfo_header(m); |
bc2791f85
|
1261 |
cache_show(s, m); |
b047501cd
|
1262 |
return 0; |
749c54151
|
1263 |
} |
b047501cd
|
1264 |
#endif |
749c54151
|
1265 |
|
b7454ad3c
|
1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 |
/* * slabinfo_op - iterator that generates /proc/slabinfo * * Output layout: * cache-name * num-active-objs * total-objs * object size * num-active-slabs * total-slabs * num-pages-per-slab * + further values on SMP and with statistics enabled */ static const struct seq_operations slabinfo_op = { |
1df3b26f2
|
1280 |
.start = slab_start, |
276a2439c
|
1281 1282 |
.next = slab_next, .stop = slab_stop, |
1df3b26f2
|
1283 |
.show = slab_show, |
b7454ad3c
|
1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 |
}; static int slabinfo_open(struct inode *inode, struct file *file) { return seq_open(file, &slabinfo_op); } static const struct file_operations proc_slabinfo_operations = { .open = slabinfo_open, .read = seq_read, .write = slabinfo_write, .llseek = seq_lseek, .release = seq_release, }; static int __init slab_proc_init(void) { |
e9b4db2b8
|
1301 1302 |
proc_create("slabinfo", SLABINFO_RIGHTS, NULL, &proc_slabinfo_operations); |
b7454ad3c
|
1303 1304 1305 1306 |
return 0; } module_init(slab_proc_init); #endif /* CONFIG_SLABINFO */ |
928cec9cd
|
1307 1308 1309 1310 1311 1312 1313 1314 1315 |
static __always_inline void *__do_krealloc(const void *p, size_t new_size, gfp_t flags) { void *ret; size_t ks = 0; if (p) ks = ksize(p); |
0316bec22
|
1316 |
if (ks >= new_size) { |
505f5dcb1
|
1317 |
kasan_krealloc((void *)p, new_size, flags); |
928cec9cd
|
1318 |
return (void *)p; |
0316bec22
|
1319 |
} |
928cec9cd
|
1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 |
ret = kmalloc_track_caller(new_size, flags); if (ret && p) memcpy(ret, p, ks); return ret; } /** * __krealloc - like krealloc() but don't free @p. * @p: object to reallocate memory for. * @new_size: how many bytes of memory are required. * @flags: the type of memory to allocate. * * This function is like krealloc() except it never frees the originally * allocated buffer. Use this if you don't want to free the buffer immediately * like, for example, with RCU. */ void *__krealloc(const void *p, size_t new_size, gfp_t flags) { if (unlikely(!new_size)) return ZERO_SIZE_PTR; return __do_krealloc(p, new_size, flags); } EXPORT_SYMBOL(__krealloc); /** * krealloc - reallocate memory. The contents will remain unchanged. * @p: object to reallocate memory for. * @new_size: how many bytes of memory are required. * @flags: the type of memory to allocate. * * The contents of the object pointed to are preserved up to the * lesser of the new and old sizes. If @p is %NULL, krealloc() * behaves exactly like kmalloc(). If @new_size is 0 and @p is not a * %NULL pointer, the object pointed to is freed. */ void *krealloc(const void *p, size_t new_size, gfp_t flags) { void *ret; if (unlikely(!new_size)) { kfree(p); return ZERO_SIZE_PTR; } ret = __do_krealloc(p, new_size, flags); if (ret && p != ret) kfree(p); return ret; } EXPORT_SYMBOL(krealloc); /** * kzfree - like kfree but zero memory * @p: object to free memory of * * The memory of the object @p points to is zeroed before freed. * If @p is %NULL, kzfree() does nothing. * * Note: this function zeroes the whole allocated buffer which can be a good * deal bigger than the requested buffer size passed to kmalloc(). So be * careful when using this function in performance sensitive code. */ void kzfree(const void *p) { size_t ks; void *mem = (void *)p; if (unlikely(ZERO_OR_NULL_PTR(mem))) return; ks = ksize(mem); memset(mem, 0, ks); kfree(mem); } EXPORT_SYMBOL(kzfree); /* Tracepoints definitions. */ EXPORT_TRACEPOINT_SYMBOL(kmalloc); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc); EXPORT_TRACEPOINT_SYMBOL(kmalloc_node); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node); EXPORT_TRACEPOINT_SYMBOL(kfree); EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free); |