slab_common.c 15.4 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
#include <trace/events/kmem.h>
23

24 25 26
#include "slab.h"

enum slab_state slab_state;
27 28
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
29
struct kmem_cache *kmem_cache;
30

31
#ifdef CONFIG_DEBUG_VM
32 33
static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
				   size_t size)
34 35 36 37 38
{
	struct kmem_cache *s = NULL;

	if (!name || in_interrupt() || size < sizeof(void *) ||
		size > KMALLOC_MAX_SIZE) {
39 40
		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
		return -EINVAL;
41
	}
42

43 44 45 46 47 48 49 50 51 52 53
	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) {
54
			pr_err("Slab cache with size %d has lost its name\n",
55 56 57 58
			       s->object_size);
			continue;
		}

59
#if !defined(CONFIG_SLUB) || !defined(CONFIG_SLUB_DEBUG_ON)
60 61 62 63 64 65 66
		/*
		 * For simplicity, we won't check this in the list of memcg
		 * caches. We have control over memcg naming, and if there
		 * aren't duplicates in the global list, there won't be any
		 * duplicates in the memcg lists as well.
		 */
		if (!memcg && !strcmp(s->name, name)) {
67 68
			pr_err("%s (%s): Cache name already exists.\n",
			       __func__, name);
69 70
			dump_stack();
			s = NULL;
71
			return -EINVAL;
72
		}
73
#endif
74 75 76
	}

	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
77 78 79
	return 0;
}
#else
80 81
static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
					  const char *name, size_t size)
82 83 84
{
	return 0;
}
85 86
#endif

87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
#ifdef CONFIG_MEMCG_KMEM
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;

		ret = memcg_update_cache_size(s, num_memcgs);
		/*
		 * See comment in memcontrol.c, memcg_update_cache_size:
		 * 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;
}
#endif

115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142
/*
 * 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 *));
}


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
/*
 * 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.
 */

168 169
struct kmem_cache *
kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
G
Glauber Costa 已提交
170 171
			size_t align, unsigned long flags, void (*ctor)(void *),
			struct kmem_cache *parent_cache)
172 173
{
	struct kmem_cache *s = NULL;
174
	int err = 0;
175

176 177
	get_online_cpus();
	mutex_lock(&slab_mutex);
178

179
	if (!kmem_cache_sanity_check(memcg, name, size) == 0)
180 181
		goto out_locked;

182 183 184 185 186 187 188
	/*
	 * 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;
189

190
	s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
191 192 193
	if (s)
		goto out_locked;

194
	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
195
	if (s) {
196
		s->object_size = s->size = size;
197
		s->align = calculate_alignment(flags, align, size);
198
		s->ctor = ctor;
199

G
Glauber Costa 已提交
200
		if (memcg_register_cache(memcg, s, parent_cache)) {
201 202 203 204 205
			kmem_cache_free(kmem_cache, s);
			err = -ENOMEM;
			goto out_locked;
		}

206 207 208 209 210 211 212 213
		s->name = kstrdup(name, GFP_KERNEL);
		if (!s->name) {
			kmem_cache_free(kmem_cache, s);
			err = -ENOMEM;
			goto out_locked;
		}

		err = __kmem_cache_create(s, flags);
214 215
		if (!err) {
			s->refcount = 1;
216
			list_add(&s->list, &slab_caches);
217
			memcg_cache_list_add(memcg, s);
218
		} else {
219
			kfree(s->name);
220 221
			kmem_cache_free(kmem_cache, s);
		}
222
	} else
223
		err = -ENOMEM;
224

225
out_locked:
226 227 228
	mutex_unlock(&slab_mutex);
	put_online_cpus();

229 230 231 232 233 234 235 236 237 238 239 240 241
	if (err) {

		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;
	}
242 243 244

	return s;
}
245 246 247 248 249

struct kmem_cache *
kmem_cache_create(const char *name, size_t size, size_t align,
		  unsigned long flags, void (*ctor)(void *))
{
G
Glauber Costa 已提交
250
	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
251
}
252
EXPORT_SYMBOL(kmem_cache_create);
253

254 255
void kmem_cache_destroy(struct kmem_cache *s)
{
256 257 258
	/* Destroy all the children caches if we aren't a memcg cache */
	kmem_cache_destroy_memcg_children(s);

259 260 261 262 263 264 265
	get_online_cpus();
	mutex_lock(&slab_mutex);
	s->refcount--;
	if (!s->refcount) {
		list_del(&s->list);

		if (!__kmem_cache_shutdown(s)) {
266
			mutex_unlock(&slab_mutex);
267 268 269
			if (s->flags & SLAB_DESTROY_BY_RCU)
				rcu_barrier();

270
			memcg_release_cache(s);
271
			kfree(s->name);
272
			kmem_cache_free(kmem_cache, s);
273 274
		} else {
			list_add(&s->list, &slab_caches);
275
			mutex_unlock(&slab_mutex);
276 277 278 279
			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
				s->name);
			dump_stack();
		}
280 281
	} else {
		mutex_unlock(&slab_mutex);
282 283 284 285 286
	}
	put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);

287 288 289 290
int slab_is_available(void)
{
	return slab_state >= UP;
}
291

292 293 294 295 296 297 298 299 300
#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;
301
	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
302 303 304
	err = __kmem_cache_create(s, flags);

	if (err)
305
		panic("Creation of kmalloc slab %s size=%zu failed. Reason %d\n",
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324
					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;
}

325 326 327 328 329 330 331 332
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

333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
/*
 * 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;

379
	if (unlikely(size > KMALLOC_MAX_SIZE)) {
380
		WARN_ON_ONCE(!(flags & __GFP_NOWARN));
381
		return NULL;
382
	}
383

384 385 386 387 388 389 390 391 392
	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
393
	if (unlikely((flags & GFP_DMA)))
394 395 396 397 398 399
		return kmalloc_dma_caches[index];

#endif
	return kmalloc_caches[index];
}

400 401 402 403 404 405 406 407 408
/*
 * 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;

409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449
	/*
	 * 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;
	}
450 451
	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
		if (!kmalloc_caches[i]) {
452 453
			kmalloc_caches[i] = create_kmalloc_cache(NULL,
							1 << i, flags);
454
		}
455

456 457 458 459 460 461 462
		/*
		 * 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);
463

464 465
		if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
			kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
466 467
	}

468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498
	/* 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
}
499 500
#endif /* !CONFIG_SLOB */

501 502 503 504 505 506 507 508 509
#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
510

511
#ifdef CONFIG_SLABINFO
512 513 514 515 516 517 518

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

519
void print_slabinfo_header(struct seq_file *m)
520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541
{
	/*
	 * 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');
}

542 543 544 545 546 547 548 549 550 551 552
static void *s_start(struct seq_file *m, loff_t *pos)
{
	loff_t n = *pos;

	mutex_lock(&slab_mutex);
	if (!n)
		print_slabinfo_header(m);

	return seq_list_start(&slab_caches, *pos);
}

553
void *slab_next(struct seq_file *m, void *p, loff_t *pos)
554 555 556 557
{
	return seq_list_next(p, &slab_caches, pos);
}

558
void slab_stop(struct seq_file *m, void *p)
559 560 561 562
{
	mutex_unlock(&slab_mutex);
}

563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589
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) {
		c = cache_from_memcg(s, i);
		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;
	}
}

int cache_show(struct kmem_cache *s, struct seq_file *m)
590
{
591 592 593 594 595
	struct slabinfo sinfo;

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

596 597
	memcg_accumulate_slabinfo(s, &sinfo);

598
	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
599
		   cache_name(s), sinfo.active_objs, sinfo.num_objs, s->size,
600 601 602 603 604 605 606 607 608
		   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');
	return 0;
609 610
}

611 612 613 614 615 616 617 618 619
static int s_show(struct seq_file *m, void *p)
{
	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);

	if (!is_root_cache(s))
		return 0;
	return cache_show(s, m);
}

620 621 622 623 624 625 626 627 628 629 630 631 632 633 634
/*
 * 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 = {
	.start = s_start,
635 636
	.next = slab_next,
	.stop = slab_stop,
637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654
	.show = s_show,
};

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)
{
655 656
	proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
						&proc_slabinfo_operations);
657 658 659 660
	return 0;
}
module_init(slab_proc_init);
#endif /* CONFIG_SLABINFO */