slob.c 7.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 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 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295
/*
 * SLOB Allocator: Simple List Of Blocks
 *
 * Matt Mackall <mpm@selenic.com> 12/30/03
 *
 * How SLOB works:
 *
 * The core of SLOB is a traditional K&R style heap allocator, with
 * support for returning aligned objects. The granularity of this
 * allocator is 8 bytes on x86, though it's perhaps possible to reduce
 * this to 4 if it's deemed worth the effort. The slob heap is a
 * singly-linked list of pages from __get_free_page, grown on demand
 * and allocation from the heap is currently first-fit.
 *
 * Above this is an implementation of kmalloc/kfree. Blocks returned
 * from kmalloc are 8-byte aligned and prepended with a 8-byte header.
 * If kmalloc is asked for objects of PAGE_SIZE or larger, it calls
 * __get_free_pages directly so that it can return page-aligned blocks
 * and keeps a linked list of such pages and their orders. These
 * objects are detected in kfree() by their page alignment.
 *
 * SLAB is emulated on top of SLOB by simply calling constructors and
 * destructors for every SLAB allocation. Objects are returned with
 * the 8-byte alignment unless the SLAB_MUST_HWCACHE_ALIGN flag is
 * set, in which case the low-level allocator will fragment blocks to
 * create the proper alignment. Again, objects of page-size or greater
 * are allocated by calling __get_free_pages. As SLAB objects know
 * their size, no separate size bookkeeping is necessary and there is
 * essentially no allocation space overhead.
 */

#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/timer.h>

struct slob_block {
	int units;
	struct slob_block *next;
};
typedef struct slob_block slob_t;

#define SLOB_UNIT sizeof(slob_t)
#define SLOB_UNITS(size) (((size) + SLOB_UNIT - 1)/SLOB_UNIT)
#define SLOB_ALIGN L1_CACHE_BYTES

struct bigblock {
	int order;
	void *pages;
	struct bigblock *next;
};
typedef struct bigblock bigblock_t;

static slob_t arena = { .next = &arena, .units = 1 };
static slob_t *slobfree = &arena;
static bigblock_t *bigblocks;
static DEFINE_SPINLOCK(slob_lock);
static DEFINE_SPINLOCK(block_lock);

static void slob_free(void *b, int size);

static void *slob_alloc(size_t size, gfp_t gfp, int align)
{
	slob_t *prev, *cur, *aligned = 0;
	int delta = 0, units = SLOB_UNITS(size);
	unsigned long flags;

	spin_lock_irqsave(&slob_lock, flags);
	prev = slobfree;
	for (cur = prev->next; ; prev = cur, cur = cur->next) {
		if (align) {
			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
			delta = aligned - cur;
		}
		if (cur->units >= units + delta) { /* room enough? */
			if (delta) { /* need to fragment head to align? */
				aligned->units = cur->units - delta;
				aligned->next = cur->next;
				cur->next = aligned;
				cur->units = delta;
				prev = cur;
				cur = aligned;
			}

			if (cur->units == units) /* exact fit? */
				prev->next = cur->next; /* unlink */
			else { /* fragment */
				prev->next = cur + units;
				prev->next->units = cur->units - units;
				prev->next->next = cur->next;
				cur->units = units;
			}

			slobfree = prev;
			spin_unlock_irqrestore(&slob_lock, flags);
			return cur;
		}
		if (cur == slobfree) {
			spin_unlock_irqrestore(&slob_lock, flags);

			if (size == PAGE_SIZE) /* trying to shrink arena? */
				return 0;

			cur = (slob_t *)__get_free_page(gfp);
			if (!cur)
				return 0;

			slob_free(cur, PAGE_SIZE);
			spin_lock_irqsave(&slob_lock, flags);
			cur = slobfree;
		}
	}
}

static void slob_free(void *block, int size)
{
	slob_t *cur, *b = (slob_t *)block;
	unsigned long flags;

	if (!block)
		return;

	if (size)
		b->units = SLOB_UNITS(size);

	/* Find reinsertion point */
	spin_lock_irqsave(&slob_lock, flags);
	for (cur = slobfree; !(b > cur && b < cur->next); cur = cur->next)
		if (cur >= cur->next && (b > cur || b < cur->next))
			break;

	if (b + b->units == cur->next) {
		b->units += cur->next->units;
		b->next = cur->next->next;
	} else
		b->next = cur->next;

	if (cur + cur->units == b) {
		cur->units += b->units;
		cur->next = b->next;
	} else
		cur->next = b;

	slobfree = cur;

	spin_unlock_irqrestore(&slob_lock, flags);
}

static int FASTCALL(find_order(int size));
static int fastcall find_order(int size)
{
	int order = 0;
	for ( ; size > 4096 ; size >>=1)
		order++;
	return order;
}

void *kmalloc(size_t size, gfp_t gfp)
{
	slob_t *m;
	bigblock_t *bb;
	unsigned long flags;

	if (size < PAGE_SIZE - SLOB_UNIT) {
		m = slob_alloc(size + SLOB_UNIT, gfp, 0);
		return m ? (void *)(m + 1) : 0;
	}

	bb = slob_alloc(sizeof(bigblock_t), gfp, 0);
	if (!bb)
		return 0;

	bb->order = find_order(size);
	bb->pages = (void *)__get_free_pages(gfp, bb->order);

	if (bb->pages) {
		spin_lock_irqsave(&block_lock, flags);
		bb->next = bigblocks;
		bigblocks = bb;
		spin_unlock_irqrestore(&block_lock, flags);
		return bb->pages;
	}

	slob_free(bb, sizeof(bigblock_t));
	return 0;
}

EXPORT_SYMBOL(kmalloc);

void kfree(const void *block)
{
	bigblock_t *bb, **last = &bigblocks;
	unsigned long flags;

	if (!block)
		return;

	if (!((unsigned long)block & (PAGE_SIZE-1))) {
		/* might be on the big block list */
		spin_lock_irqsave(&block_lock, flags);
		for (bb = bigblocks; bb; last = &bb->next, bb = bb->next) {
			if (bb->pages == block) {
				*last = bb->next;
				spin_unlock_irqrestore(&block_lock, flags);
				free_pages((unsigned long)block, bb->order);
				slob_free(bb, sizeof(bigblock_t));
				return;
			}
		}
		spin_unlock_irqrestore(&block_lock, flags);
	}

	slob_free((slob_t *)block - 1, 0);
	return;
}

EXPORT_SYMBOL(kfree);

unsigned int ksize(const void *block)
{
	bigblock_t *bb;
	unsigned long flags;

	if (!block)
		return 0;

	if (!((unsigned long)block & (PAGE_SIZE-1))) {
		spin_lock_irqsave(&block_lock, flags);
		for (bb = bigblocks; bb; bb = bb->next)
			if (bb->pages == block) {
				spin_unlock_irqrestore(&slob_lock, flags);
				return PAGE_SIZE << bb->order;
			}
		spin_unlock_irqrestore(&block_lock, flags);
	}

	return ((slob_t *)block - 1)->units * SLOB_UNIT;
}

struct kmem_cache {
	unsigned int size, align;
	const char *name;
	void (*ctor)(void *, struct kmem_cache *, unsigned long);
	void (*dtor)(void *, struct kmem_cache *, unsigned long);
};

struct kmem_cache *kmem_cache_create(const char *name, size_t size,
	size_t align, unsigned long flags,
	void (*ctor)(void*, struct kmem_cache *, unsigned long),
	void (*dtor)(void*, struct kmem_cache *, unsigned long))
{
	struct kmem_cache *c;

	c = slob_alloc(sizeof(struct kmem_cache), flags, 0);

	if (c) {
		c->name = name;
		c->size = size;
		c->ctor = ctor;
		c->dtor = dtor;
		/* ignore alignment unless it's forced */
		c->align = (flags & SLAB_MUST_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
		if (c->align < align)
			c->align = align;
	}

	return c;
}
EXPORT_SYMBOL(kmem_cache_create);

int kmem_cache_destroy(struct kmem_cache *c)
{
	slob_free(c, sizeof(struct kmem_cache));
	return 0;
}
EXPORT_SYMBOL(kmem_cache_destroy);

void *kmem_cache_alloc(struct kmem_cache *c, gfp_t flags)
{
	void *b;

	if (c->size < PAGE_SIZE)
		b = slob_alloc(c->size, flags, c->align);
	else
		b = (void *)__get_free_pages(flags, find_order(c->size));

	if (c->ctor)
		c->ctor(b, c, SLAB_CTOR_CONSTRUCTOR);

	return b;
}
EXPORT_SYMBOL(kmem_cache_alloc);

296 297 298 299 300 301 302 303 304 305
void *kmem_cache_zalloc(struct kmem_cache *c, gfp_t flags)
{
	void *ret = kmem_cache_alloc(c, flags);
	if (ret)
		memset(ret, 0, c->size);

	return ret;
}
EXPORT_SYMBOL(kmem_cache_zalloc);

306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341
void kmem_cache_free(struct kmem_cache *c, void *b)
{
	if (c->dtor)
		c->dtor(b, c, 0);

	if (c->size < PAGE_SIZE)
		slob_free(b, c->size);
	else
		free_pages((unsigned long)b, find_order(c->size));
}
EXPORT_SYMBOL(kmem_cache_free);

unsigned int kmem_cache_size(struct kmem_cache *c)
{
	return c->size;
}
EXPORT_SYMBOL(kmem_cache_size);

const char *kmem_cache_name(struct kmem_cache *c)
{
	return c->name;
}
EXPORT_SYMBOL(kmem_cache_name);

static struct timer_list slob_timer = TIMER_INITIALIZER(
	(void (*)(unsigned long))kmem_cache_init, 0, 0);

void kmem_cache_init(void)
{
	void *p = slob_alloc(PAGE_SIZE, 0, PAGE_SIZE-1);

	if (p)
		free_page((unsigned long)p);

	mod_timer(&slob_timer, jiffies + HZ);
}