slab_common.c 9.7 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 24 25
#include "slab.h"

enum slab_state slab_state;
26 27
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
28
struct kmem_cache *kmem_cache;
29

30
#ifdef CONFIG_DEBUG_VM
31 32
static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
				   size_t size)
33 34 35 36 37
{
	struct kmem_cache *s = NULL;

	if (!name || in_interrupt() || size < sizeof(void *) ||
		size > KMALLOC_MAX_SIZE) {
38 39
		pr_err("kmem_cache_create(%s) integrity check failed\n", name);
		return -EINVAL;
40
	}
41

42 43 44 45 46 47 48 49 50 51 52
	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) {
53
			pr_err("Slab cache with size %d has lost its name\n",
54 55 56 57
			       s->object_size);
			continue;
		}

58 59 60 61 62 63 64
		/*
		 * 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)) {
65 66
			pr_err("%s (%s): Cache name already exists.\n",
			       __func__, name);
67 68
			dump_stack();
			s = NULL;
69
			return -EINVAL;
70 71 72 73
		}
	}

	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
74 75 76
	return 0;
}
#else
77 78
static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
					  const char *name, size_t size)
79 80 81
{
	return 0;
}
82 83
#endif

84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111
/*
 * 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 *));
}


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
/*
 * 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.
 */

137 138 139
struct kmem_cache *
kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
			size_t align, unsigned long flags, void (*ctor)(void *))
140 141
{
	struct kmem_cache *s = NULL;
142
	int err = 0;
143

144 145
	get_online_cpus();
	mutex_lock(&slab_mutex);
146

147
	if (!kmem_cache_sanity_check(memcg, name, size) == 0)
148 149
		goto out_locked;

150 151 152 153 154 155 156
	/*
	 * 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;
157

158
	s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
159 160 161
	if (s)
		goto out_locked;

162
	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
163
	if (s) {
164
		s->object_size = s->size = size;
165
		s->align = calculate_alignment(flags, align, size);
166
		s->ctor = ctor;
167 168 169 170 171 172 173

		if (memcg_register_cache(memcg, s)) {
			kmem_cache_free(kmem_cache, s);
			err = -ENOMEM;
			goto out_locked;
		}

174 175 176 177 178 179 180 181
		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);
182 183
		if (!err) {
			s->refcount = 1;
184
			list_add(&s->list, &slab_caches);
185
			memcg_cache_list_add(memcg, s);
186
		} else {
187
			kfree(s->name);
188 189
			kmem_cache_free(kmem_cache, s);
		}
190
	} else
191
		err = -ENOMEM;
192

193
out_locked:
194 195 196
	mutex_unlock(&slab_mutex);
	put_online_cpus();

197 198 199 200 201 202 203 204 205 206 207 208 209
	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;
	}
210 211 212

	return s;
}
213 214 215 216 217 218 219

struct kmem_cache *
kmem_cache_create(const char *name, size_t size, size_t align,
		  unsigned long flags, void (*ctor)(void *))
{
	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor);
}
220
EXPORT_SYMBOL(kmem_cache_create);
221

222 223 224 225 226 227 228 229 230
void kmem_cache_destroy(struct kmem_cache *s)
{
	get_online_cpus();
	mutex_lock(&slab_mutex);
	s->refcount--;
	if (!s->refcount) {
		list_del(&s->list);

		if (!__kmem_cache_shutdown(s)) {
231
			mutex_unlock(&slab_mutex);
232 233 234
			if (s->flags & SLAB_DESTROY_BY_RCU)
				rcu_barrier();

235
			memcg_release_cache(s);
236
			kfree(s->name);
237
			kmem_cache_free(kmem_cache, s);
238 239
		} else {
			list_add(&s->list, &slab_caches);
240
			mutex_unlock(&slab_mutex);
241 242 243 244
			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
				s->name);
			dump_stack();
		}
245 246
	} else {
		mutex_unlock(&slab_mutex);
247 248 249 250 251
	}
	put_online_cpus();
}
EXPORT_SYMBOL(kmem_cache_destroy);

252 253 254 255
int slab_is_available(void)
{
	return slab_state >= UP;
}
256

257 258 259 260 261 262 263 264 265
#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;
266
	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
	err = __kmem_cache_create(s, flags);

	if (err)
		panic("Creation of kmalloc slab %s size=%zd failed. Reason %d\n",
					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;
}

#endif /* !CONFIG_SLOB */


293
#ifdef CONFIG_SLABINFO
294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
static void print_slabinfo_header(struct seq_file *m)
{
	/*
	 * 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');
}

317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339
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);
}

static void *s_next(struct seq_file *m, void *p, loff_t *pos)
{
	return seq_list_next(p, &slab_caches, pos);
}

static void s_stop(struct seq_file *m, void *p)
{
	mutex_unlock(&slab_mutex);
}

static int s_show(struct seq_file *m, void *p)
{
340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356
	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
	struct slabinfo sinfo;

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

	seq_printf(m, "%-17s %6lu %6lu %6u %4u %4d",
		   s->name, sinfo.active_objs, sinfo.num_objs, s->size,
		   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;
357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
}

/*
 * 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,
	.next = s_next,
	.stop = s_stop,
	.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)
{
	proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations);
	return 0;
}
module_init(slab_proc_init);
#endif /* CONFIG_SLABINFO */