slab_common.c 24.1 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13
/*
 * 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>
14 15
#include <linux/cpu.h>
#include <linux/uaccess.h>
16 17
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
18 19 20
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
21
#include <linux/memcontrol.h>
22 23

#define CREATE_TRACE_POINTS
24
#include <trace/events/kmem.h>
25

26 27 28
#include "slab.h"

enum slab_state slab_state;
29 30
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
31
struct kmem_cache *kmem_cache;
32

33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60
/*
 * Set of flags that will prevent slab merging
 */
#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | SLAB_STORE_USER | \
		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
		SLAB_FAILSLAB)

#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
		SLAB_CACHE_DMA | SLAB_NOTRACK)

/*
 * Merge control. If this is set then no merging of slab caches will occur.
 * (Could be removed. This was introduced to pacify the merge skeptics.)
 */
static int slab_nomerge;

static int __init setup_slab_nomerge(char *str)
{
	slab_nomerge = 1;
	return 1;
}

#ifdef CONFIG_SLUB
__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
#endif

__setup("slab_nomerge", setup_slab_nomerge);

61 62 63 64 65 66 67 68 69
/*
 * 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);

70
#ifdef CONFIG_DEBUG_VM
71
static int kmem_cache_sanity_check(const char *name, size_t size)
72 73 74 75 76
{
	struct kmem_cache *s = NULL;

	if (!name || in_interrupt() || size < sizeof(void *) ||
		size > KMALLOC_MAX_SIZE) {
77 78
		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
		return -EINVAL;
79
	}
80

81 82 83 84 85 86 87 88 89 90 91
	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) {
92
			pr_err("Slab cache with size %d has lost its name\n",
93 94 95 96 97 98
			       s->object_size);
			continue;
		}
	}

	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
99 100 101
	return 0;
}
#else
102
static inline int kmem_cache_sanity_check(const char *name, size_t size)
103 104 105
{
	return 0;
}
106 107
#endif

108
#ifdef CONFIG_MEMCG_KMEM
109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140
static int memcg_alloc_cache_params(struct mem_cgroup *memcg,
		struct kmem_cache *s, struct kmem_cache *root_cache)
{
	size_t size;

	if (!memcg_kmem_enabled())
		return 0;

	if (!memcg) {
		size = offsetof(struct memcg_cache_params, memcg_caches);
		size += memcg_limited_groups_array_size * sizeof(void *);
	} else
		size = sizeof(struct memcg_cache_params);

	s->memcg_params = kzalloc(size, GFP_KERNEL);
	if (!s->memcg_params)
		return -ENOMEM;

	if (memcg) {
		s->memcg_params->memcg = memcg;
		s->memcg_params->root_cache = root_cache;
	} else
		s->memcg_params->is_root_cache = true;

	return 0;
}

static void memcg_free_cache_params(struct kmem_cache *s)
{
	kfree(s->memcg_params);
}

141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167
static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs)
{
	int size;
	struct memcg_cache_params *new_params, *cur_params;

	BUG_ON(!is_root_cache(s));

	size = offsetof(struct memcg_cache_params, memcg_caches);
	size += num_memcgs * sizeof(void *);

	new_params = kzalloc(size, GFP_KERNEL);
	if (!new_params)
		return -ENOMEM;

	cur_params = s->memcg_params;
	memcpy(new_params->memcg_caches, cur_params->memcg_caches,
	       memcg_limited_groups_array_size * sizeof(void *));

	new_params->is_root_cache = true;

	rcu_assign_pointer(s->memcg_params, new_params);
	if (cur_params)
		kfree_rcu(cur_params, rcu_head);

	return 0;
}

168 169 170 171 172 173 174 175 176 177
int memcg_update_all_caches(int num_memcgs)
{
	struct kmem_cache *s;
	int ret = 0;
	mutex_lock(&slab_mutex);

	list_for_each_entry(s, &slab_caches, list) {
		if (!is_root_cache(s))
			continue;

178
		ret = memcg_update_cache_params(s, num_memcgs);
179 180 181 182 183 184 185 186 187 188 189 190 191
		/*
		 * Instead of freeing the memory, we'll just leave the caches
		 * up to this point in an updated state.
		 */
		if (ret)
			goto out;
	}

	memcg_update_array_size(num_memcgs);
out:
	mutex_unlock(&slab_mutex);
	return ret;
}
192 193 194 195 196 197 198 199 200 201 202
#else
static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg,
		struct kmem_cache *s, struct kmem_cache *root_cache)
{
	return 0;
}

static inline void memcg_free_cache_params(struct kmem_cache *s)
{
}
#endif /* CONFIG_MEMCG_KMEM */
203

204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242
/*
 * 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;

	if (slab_nomerge || (flags & SLAB_NEVER_MERGE))
		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);

243
	list_for_each_entry_reverse(s, &slab_caches, list) {
244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261
		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;

262 263 264 265
		if (IS_ENABLED(CONFIG_SLAB) && align &&
			(align > s->align || s->align % align))
			continue;

266 267 268 269 270
		return s;
	}
	return NULL;
}

271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297
/*
 * 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 *));
}

298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336
static struct kmem_cache *
do_kmem_cache_create(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)
{
	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;

	err = memcg_alloc_cache_params(memcg, s, root_cache);
	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);
out:
	if (err)
		return ERR_PTR(err);
	return s;

out_free_cache:
	memcg_free_cache_params(s);
	kfree(s);
	goto out;
}
337

338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361
/*
 * 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.
 */
362
struct kmem_cache *
363 364
kmem_cache_create(const char *name, size_t size, size_t align,
		  unsigned long flags, void (*ctor)(void *))
365
{
366 367
	struct kmem_cache *s;
	char *cache_name;
368
	int err;
369

370
	get_online_cpus();
371 372
	get_online_mems();

373
	mutex_lock(&slab_mutex);
374

375
	err = kmem_cache_sanity_check(name, size);
A
Andrew Morton 已提交
376 377
	if (err) {
		s = NULL;	/* suppress uninit var warning */
378
		goto out_unlock;
A
Andrew Morton 已提交
379
	}
380

381 382 383 384 385 386 387
	/*
	 * 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;
388

389 390
	s = __kmem_cache_alias(name, size, align, flags, ctor);
	if (s)
391
		goto out_unlock;
392

393 394 395 396 397
	cache_name = kstrdup(name, GFP_KERNEL);
	if (!cache_name) {
		err = -ENOMEM;
		goto out_unlock;
	}
398

399 400 401 402 403 404 405
	s = do_kmem_cache_create(cache_name, size, size,
				 calculate_alignment(flags, align, size),
				 flags, ctor, NULL, NULL);
	if (IS_ERR(s)) {
		err = PTR_ERR(s);
		kfree(cache_name);
	}
406 407

out_unlock:
408
	mutex_unlock(&slab_mutex);
409 410

	put_online_mems();
411 412
	put_online_cpus();

413
	if (err) {
414 415 416 417 418 419 420 421 422 423
		if (flags & SLAB_PANIC)
			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
				name, err);
		else {
			printk(KERN_WARNING "kmem_cache_create(%s) failed with error %d",
				name, err);
			dump_stack();
		}
		return NULL;
	}
424 425
	return s;
}
426
EXPORT_SYMBOL(kmem_cache_create);
427

428 429
#ifdef CONFIG_MEMCG_KMEM
/*
430
 * memcg_create_kmem_cache - Create a cache for a memory cgroup.
431 432
 * @memcg: The memory cgroup the new cache is for.
 * @root_cache: The parent of the new cache.
433
 * @memcg_name: The name of the memory cgroup (used for naming the new cache).
434 435 436 437 438
 *
 * 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.
 */
439
struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg,
440 441
					   struct kmem_cache *root_cache,
					   const char *memcg_name)
442
{
443
	struct kmem_cache *s = NULL;
444 445 446
	char *cache_name;

	get_online_cpus();
447 448
	get_online_mems();

449 450
	mutex_lock(&slab_mutex);

451 452
	cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name,
			       memcg_cache_id(memcg), memcg_name);
453 454 455 456 457 458 459
	if (!cache_name)
		goto out_unlock;

	s = do_kmem_cache_create(cache_name, root_cache->object_size,
				 root_cache->size, root_cache->align,
				 root_cache->flags, root_cache->ctor,
				 memcg, root_cache);
460
	if (IS_ERR(s)) {
461
		kfree(cache_name);
462 463
		s = NULL;
	}
464 465 466

out_unlock:
	mutex_unlock(&slab_mutex);
467 468

	put_online_mems();
469
	put_online_cpus();
470 471

	return s;
472
}
473

474
static int memcg_cleanup_cache_params(struct kmem_cache *s)
475 476 477 478 479 480 481 482
{
	int rc;

	if (!s->memcg_params ||
	    !s->memcg_params->is_root_cache)
		return 0;

	mutex_unlock(&slab_mutex);
483
	rc = __memcg_cleanup_cache_params(s);
484 485 486 487 488
	mutex_lock(&slab_mutex);

	return rc;
}
#else
489
static int memcg_cleanup_cache_params(struct kmem_cache *s)
490 491 492
{
	return 0;
}
493
#endif /* CONFIG_MEMCG_KMEM */
494

495 496 497 498 499 500
void slab_kmem_cache_release(struct kmem_cache *s)
{
	kfree(s->name);
	kmem_cache_free(kmem_cache, s);
}

501 502 503
void kmem_cache_destroy(struct kmem_cache *s)
{
	get_online_cpus();
504 505
	get_online_mems();

506
	mutex_lock(&slab_mutex);
507

508
	s->refcount--;
509 510 511
	if (s->refcount)
		goto out_unlock;

512
	if (memcg_cleanup_cache_params(s) != 0)
513 514 515 516 517 518 519
		goto out_unlock;

	if (__kmem_cache_shutdown(s) != 0) {
		printk(KERN_ERR "kmem_cache_destroy %s: "
		       "Slab cache still has objects\n", s->name);
		dump_stack();
		goto out_unlock;
520
	}
521

522 523
	list_del(&s->list);

524 525 526 527 528
	mutex_unlock(&slab_mutex);
	if (s->flags & SLAB_DESTROY_BY_RCU)
		rcu_barrier();

	memcg_free_cache_params(s);
529 530 531 532 533
#ifdef SLAB_SUPPORTS_SYSFS
	sysfs_slab_remove(s);
#else
	slab_kmem_cache_release(s);
#endif
534
	goto out;
535 536 537

out_unlock:
	mutex_unlock(&slab_mutex);
538 539
out:
	put_online_mems();
540 541 542 543
	put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);

544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563
/**
 * 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();
	ret = __kmem_cache_shrink(cachep);
	put_online_mems();
	put_online_cpus();
	return ret;
}
EXPORT_SYMBOL(kmem_cache_shrink);

564 565 566 567
int slab_is_available(void)
{
	return slab_state >= UP;
}
568

569 570 571 572 573 574 575 576 577
#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;
578
	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
579 580 581
	err = __kmem_cache_create(s, flags);

	if (err)
582
		panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601
					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\n", name);

	create_boot_cache(s, name, size, flags);
	list_add(&s->list, &slab_caches);
	s->refcount = 1;
	return s;
}

602 603 604 605 606 607 608 609
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

610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655
/*
 * 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;

656
	if (unlikely(size > KMALLOC_MAX_SIZE)) {
657
		WARN_ON_ONCE(!(flags & __GFP_NOWARN));
658
		return NULL;
659
	}
660

661 662 663 664 665 666 667 668 669
	if (size <= 192) {
		if (!size)
			return ZERO_SIZE_PTR;

		index = size_index[size_index_elem(size)];
	} else
		index = fls(size - 1);

#ifdef CONFIG_ZONE_DMA
670
	if (unlikely((flags & GFP_DMA)))
671 672 673 674 675 676
		return kmalloc_dma_caches[index];

#endif
	return kmalloc_caches[index];
}

677 678 679 680 681 682 683 684 685
/*
 * 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;

686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726
	/*
	 * 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
	 */
	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;
	}
727 728
	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
		if (!kmalloc_caches[i]) {
729 730
			kmalloc_caches[i] = create_kmalloc_cache(NULL,
							1 << i, flags);
731
		}
732

733 734 735 736 737 738 739
		/*
		 * 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
		 */
		if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
			kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
740

741 742
		if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
			kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
743 744
	}

745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775
	/* Kmalloc array is now usable */
	slab_state = UP;

	for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
		struct kmem_cache *s = kmalloc_caches[i];
		char *n;

		if (s) {
			n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));

			BUG_ON(!n);
			s->name = n;
		}
	}

#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
}
776 777
#endif /* !CONFIG_SLOB */

V
Vladimir Davydov 已提交
778 779 780 781 782
/*
 * 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.
 */
V
Vladimir Davydov 已提交
783 784 785 786 787 788 789 790 791 792 793 794 795
void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
{
	void *ret;
	struct page *page;

	flags |= __GFP_COMP;
	page = alloc_kmem_pages(flags, order);
	ret = page ? page_address(page) : NULL;
	kmemleak_alloc(ret, size, 1, flags);
	return ret;
}
EXPORT_SYMBOL(kmalloc_order);

796 797 798 799 800 801 802 803 804
#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
805

806
#ifdef CONFIG_SLABINFO
807 808 809 810 811 812 813

#ifdef CONFIG_SLAB
#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
#else
#define SLABINFO_RIGHTS S_IRUSR
#endif

814
static void print_slabinfo_header(struct seq_file *m)
815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836
{
	/*
	 * 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)\n");
#else
	seq_puts(m, "slabinfo - version: 2.1\n");
#endif
	seq_puts(m, "# name            <active_objs> <num_objs> <objsize> "
		 "<objperslab> <pagesperslab>");
	seq_puts(m, " : tunables <limit> <batchcount> <sharedfactor>");
	seq_puts(m, " : slabdata <active_slabs> <num_slabs> <sharedavail>");
#ifdef CONFIG_DEBUG_SLAB
	seq_puts(m, " : globalstat <listallocs> <maxobjs> <grown> <reaped> "
		 "<error> <maxfreeable> <nodeallocs> <remotefrees> <alienoverflow>");
	seq_puts(m, " : cpustat <allochit> <allocmiss> <freehit> <freemiss>");
#endif
	seq_putc(m, '\n');
}

837
void *slab_start(struct seq_file *m, loff_t *pos)
838 839 840 841 842
{
	mutex_lock(&slab_mutex);
	return seq_list_start(&slab_caches, *pos);
}

843
void *slab_next(struct seq_file *m, void *p, loff_t *pos)
844 845 846 847
{
	return seq_list_next(p, &slab_caches, pos);
}

848
void slab_stop(struct seq_file *m, void *p)
849 850 851 852
{
	mutex_unlock(&slab_mutex);
}

853 854 855 856 857 858 859 860 861 862 863
static void
memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info)
{
	struct kmem_cache *c;
	struct slabinfo sinfo;
	int i;

	if (!is_root_cache(s))
		return;

	for_each_memcg_cache_index(i) {
864
		c = cache_from_memcg_idx(s, i);
865 866 867 868 869 870 871 872 873 874 875 876 877 878
		if (!c)
			continue;

		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;
	}
}

879
static void cache_show(struct kmem_cache *s, struct seq_file *m)
880
{
881 882 883 884 885
	struct slabinfo sinfo;

	memset(&sinfo, 0, sizeof(sinfo));
	get_slabinfo(s, &sinfo);

886 887
	memcg_accumulate_slabinfo(s, &sinfo);

888
	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
889
		   cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
890 891 892 893 894 895 896 897
		   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, '\n');
898 899
}

900
static int slab_show(struct seq_file *m, void *p)
901 902 903
{
	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);

904 905
	if (p == slab_caches.next)
		print_slabinfo_header(m);
906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921
	if (is_root_cache(s))
		cache_show(s, m);
	return 0;
}

#ifdef CONFIG_MEMCG_KMEM
int memcg_slab_show(struct seq_file *m, void *p)
{
	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));

	if (p == slab_caches.next)
		print_slabinfo_header(m);
	if (!is_root_cache(s) && s->memcg_params->memcg == memcg)
		cache_show(s, m);
	return 0;
922
}
923
#endif
924

925 926 927 928 929 930 931 932 933 934 935 936 937 938
/*
 * 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 = {
939
	.start = slab_start,
940 941
	.next = slab_next,
	.stop = slab_stop,
942
	.show = slab_show,
943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959
};

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)
{
960 961
	proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
						&proc_slabinfo_operations);
962 963 964 965
	return 0;
}
module_init(slab_proc_init);
#endif /* CONFIG_SLABINFO */
966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064

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);

	if (ks >= new_size)
		return (void *)p;

	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);