summaryrefslogtreecommitdiff
path: root/lib/genalloc.c
blob: ca208a92628c1b49a6f5c1fece1a81592a65ecaa (plain)
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
296
297
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
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
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
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
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
/*
 * Basic general purpose allocator for managing special purpose
 * memory, for example, memory that is not managed by the regular
 * kmalloc/kfree interface.  Uses for this includes on-device special
 * memory, uncached memory etc.
 *
 * It is safe to use the allocator in NMI handlers and other special
 * unblockable contexts that could otherwise deadlock on locks.  This
 * is implemented by using atomic operations and retries on any
 * conflicts.  The disadvantage is that there may be livelocks in
 * extreme cases.  For better scalability, one allocator can be used
 * for each CPU.
 *
 * The lockless operation only works if there is enough memory
 * available.  If new memory is added to the pool a lock has to be
 * still taken.  So any user relying on locklessness has to ensure
 * that sufficient memory is preallocated.
 *
 * The basic atomic operation of this allocator is cmpxchg on long.
 * On architectures that don't have NMI-safe cmpxchg implementation,
 * the allocator can NOT be used in NMI handler.  So code uses the
 * allocator in NMI handler should depend on
 * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
 *
 * Copyright 2005 (C) Jes Sorensen <jes@trained-monkey.org>
 *
 * This source code is licensed under the GNU General Public License,
 * Version 2.  See the file COPYING for more details.
 */

#include <linux/slab.h>
#include <linux/export.h>
#include <linux/bitmap.h>
#include <linux/rculist.h>
#include <linux/interrupt.h>
#include <linux/genalloc.h>

static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
{
	unsigned long val, nval;

	nval = *addr;
	do {
		val = nval;
		if (val & mask_to_set)
			return -EBUSY;
		cpu_relax();
	} while ((nval = cmpxchg(addr, val, val | mask_to_set)) != val);

	return 0;
}

static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
{
	unsigned long val, nval;

	nval = *addr;
	do {
		val = nval;
		if ((val & mask_to_clear) != mask_to_clear)
			return -EBUSY;
		cpu_relax();
	} while ((nval = cmpxchg(addr, val, val & ~mask_to_clear)) != val);

	return 0;
}

/*
 * bitmap_set_ll - set the specified number of bits at the specified position
 * @map: pointer to a bitmap
 * @start: a bit position in @map
 * @nr: number of bits to set
 *
 * Set @nr bits start from @start in @map lock-lessly. Several users
 * can set/clear the same bitmap simultaneously without lock. If two
 * users set the same bit, one user will return remain bits, otherwise
 * return 0.
 */
static int bitmap_set_ll(unsigned long *map, int start, int nr)
{
	unsigned long *p = map + BIT_WORD(start);
	const int size = start + nr;
	int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
	unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);

	while (nr - bits_to_set >= 0) {
		if (set_bits_ll(p, mask_to_set))
			return nr;
		nr -= bits_to_set;
		bits_to_set = BITS_PER_LONG;
		mask_to_set = ~0UL;
		p++;
	}
	if (nr) {
		mask_to_set &= BITMAP_LAST_WORD_MASK(size);
		if (set_bits_ll(p, mask_to_set))
			return nr;
	}

	return 0;
}

/*
 * bitmap_clear_ll - clear the specified number of bits at the specified position
 * @map: pointer to a bitmap
 * @start: a bit position in @map
 * @nr: number of bits to set
 *
 * Clear @nr bits start from @start in @map lock-lessly. Several users
 * can set/clear the same bitmap simultaneously without lock. If two
 * users clear the same bit, one user will return remain bits,
 * otherwise return 0.
 */
static int bitmap_clear_ll(unsigned long *map, int start, int nr)
{
	unsigned long *p = map + BIT_WORD(start);
	const int size = start + nr;
	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);

	while (nr - bits_to_clear >= 0) {
		if (clear_bits_ll(p, mask_to_clear))
			return nr;
		nr -= bits_to_clear;
		bits_to_clear = BITS_PER_LONG;
		mask_to_clear = ~0UL;
		p++;
	}
	if (nr) {
		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
		if (clear_bits_ll(p, mask_to_clear))
			return nr;
	}

	return 0;
}

/**
 * gen_pool_create - create a new special memory pool
 * @min_alloc_order: log base 2 of number of bytes each bitmap bit represents
 * @nid: node id of the node the pool structure should be allocated on, or -1
 *
 * Create a new special memory pool that can be used to manage special purpose
 * memory not managed by the regular kmalloc/kfree interface.
 */
struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
{
	struct gen_pool *pool;

	pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid);
	if (pool != NULL) {
		spin_lock_init(&pool->lock);
		INIT_LIST_HEAD(&pool->chunks);
		pool->min_alloc_order = min_alloc_order;
		pool->algo = gen_pool_first_fit;
		pool->data = NULL;
	}
	return pool;
}
EXPORT_SYMBOL(gen_pool_create);

/**
 * gen_pool_add_virt - add a new chunk of special memory to the pool
 * @pool: pool to add new memory chunk to
 * @virt: virtual starting address of memory chunk to add to pool
 * @phys: physical starting address of memory chunk to add to pool
 * @size: size in bytes of the memory chunk to add to pool
 * @nid: node id of the node the chunk structure and bitmap should be
 *       allocated on, or -1
 *
 * Add a new chunk of special memory to the specified pool.
 *
 * Returns 0 on success or a -ve errno on failure.
 */
int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
		 size_t size, int nid)
{
	struct gen_pool_chunk *chunk;
	int nbits = size >> pool->min_alloc_order;
	int nbytes = sizeof(struct gen_pool_chunk) +
				(nbits + BITS_PER_BYTE - 1) / BITS_PER_BYTE;

	chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
	if (unlikely(chunk == NULL))
		return -ENOMEM;

	chunk->phys_addr = phys;
	chunk->start_addr = virt;
	chunk->end_addr = virt + size;
	atomic_set(&chunk->avail, size);

	spin_lock(&pool->lock);
	list_add_rcu(&chunk->next_chunk, &pool->chunks);
	spin_unlock(&pool->lock);

	return 0;
}
EXPORT_SYMBOL(gen_pool_add_virt);

/**
 * gen_pool_virt_to_phys - return the physical address of memory
 * @pool: pool to allocate from
 * @addr: starting address of memory
 *
 * Returns the physical address on success, or -1 on error.
 */
phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
{
	struct gen_pool_chunk *chunk;
	phys_addr_t paddr = -1;

	rcu_read_lock();
	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
			paddr = chunk->phys_addr + (addr - chunk->start_addr);
			break;
		}
	}
	rcu_read_unlock();

	return paddr;
}
EXPORT_SYMBOL(gen_pool_virt_to_phys);

/**
 * gen_pool_destroy - destroy a special memory pool
 * @pool: pool to destroy
 *
 * Destroy the specified special memory pool. Verifies that there are no
 * outstanding allocations.
 */
void gen_pool_destroy(struct gen_pool *pool)
{
	struct list_head *_chunk, *_next_chunk;
	struct gen_pool_chunk *chunk;
	int order = pool->min_alloc_order;
	int bit, end_bit;

	list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
		list_del(&chunk->next_chunk);

		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
		bit = find_next_bit(chunk->bits, end_bit, 0);
		BUG_ON(bit < end_bit);

		kfree(chunk);
	}
	kfree(pool);
	return;
}
EXPORT_SYMBOL(gen_pool_destroy);

/**
 * gen_pool_alloc - allocate special memory from the pool
 * @pool: pool to allocate from
 * @size: number of bytes to allocate from the pool
 *
 * Allocate the requested number of bytes from the specified pool.
 * Uses the pool allocation function (with first-fit algorithm by default).
 * Can not be used in NMI handler on architectures without
 * NMI-safe cmpxchg implementation.
 */
unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
{
	struct gen_pool_chunk *chunk;
	unsigned long addr = 0;
	int order = pool->min_alloc_order;
	int nbits, start_bit = 0, end_bit, remain;

#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
	BUG_ON(in_nmi());
#endif

	if (size == 0)
		return 0;

	nbits = (size + (1UL << order) - 1) >> order;
	rcu_read_lock();
	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
		if (size > atomic_read(&chunk->avail))
			continue;

		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
retry:
		start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
				pool->data);
		if (start_bit >= end_bit)
			continue;
		remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
		if (remain) {
			remain = bitmap_clear_ll(chunk->bits, start_bit,
						 nbits - remain);
			BUG_ON(remain);
			goto retry;
		}

		addr = chunk->start_addr + ((unsigned long)start_bit << order);
		size = nbits << order;
		atomic_sub(size, &chunk->avail);
		break;
	}
	rcu_read_unlock();
	return addr;
}
EXPORT_SYMBOL(gen_pool_alloc);

/**
 * gen_pool_free - free allocated special memory back to the pool
 * @pool: pool to free to
 * @addr: starting address of memory to free back to pool
 * @size: size in bytes of memory to free
 *
 * Free previously allocated special memory back to the specified
 * pool.  Can not be used in NMI handler on architectures without
 * NMI-safe cmpxchg implementation.
 */
void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
{
	struct gen_pool_chunk *chunk;
	int order = pool->min_alloc_order;
	int start_bit, nbits, remain;

#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
	BUG_ON(in_nmi());
#endif

	nbits = (size + (1UL << order) - 1) >> order;
	rcu_read_lock();
	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
			BUG_ON(addr + size > chunk->end_addr);
			start_bit = (addr - chunk->start_addr) >> order;
			remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
			BUG_ON(remain);
			size = nbits << order;
			atomic_add(size, &chunk->avail);
			rcu_read_unlock();
			return;
		}
	}
	rcu_read_unlock();
	BUG();
}
EXPORT_SYMBOL(gen_pool_free);

/**
 * gen_pool_for_each_chunk - call func for every chunk of generic memory pool
 * @pool:	the generic memory pool
 * @func:	func to call
 * @data:	additional data used by @func
 *
 * Call @func for every chunk of generic memory pool.  The @func is
 * called with rcu_read_lock held.
 */
void gen_pool_for_each_chunk(struct gen_pool *pool,
	void (*func)(struct gen_pool *pool, struct gen_pool_chunk *chunk, void *data),
	void *data)
{
	struct gen_pool_chunk *chunk;

	rcu_read_lock();
	list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk)
		func(pool, chunk, data);
	rcu_read_unlock();
}
EXPORT_SYMBOL(gen_pool_for_each_chunk);

/**
 * gen_pool_avail - get available free space of the pool
 * @pool: pool to get available free space
 *
 * Return available free space of the specified pool.
 */
size_t gen_pool_avail(struct gen_pool *pool)
{
	struct gen_pool_chunk *chunk;
	size_t avail = 0;

	rcu_read_lock();
	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
		avail += atomic_read(&chunk->avail);
	rcu_read_unlock();
	return avail;
}
EXPORT_SYMBOL_GPL(gen_pool_avail);

/**
 * gen_pool_size - get size in bytes of memory managed by the pool
 * @pool: pool to get size
 *
 * Return size in bytes of memory managed by the pool.
 */
size_t gen_pool_size(struct gen_pool *pool)
{
	struct gen_pool_chunk *chunk;
	size_t size = 0;

	rcu_read_lock();
	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
		size += chunk->end_addr - chunk->start_addr;
	rcu_read_unlock();
	return size;
}
EXPORT_SYMBOL_GPL(gen_pool_size);

/**
 * gen_pool_set_algo - set the allocation algorithm
 * @pool: pool to change allocation algorithm
 * @algo: custom algorithm function
 * @data: additional data used by @algo
 *
 * Call @algo for each memory allocation in the pool.
 * If @algo is NULL use gen_pool_first_fit as default
 * memory allocation function.
 */
void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo, void *data)
{
	rcu_read_lock();

	pool->algo = algo;
	if (!pool->algo)
		pool->algo = gen_pool_first_fit;

	pool->data = data;

	rcu_read_unlock();
}
EXPORT_SYMBOL(gen_pool_set_algo);

/**
 * gen_pool_first_fit - find the first available region
 * of memory matching the size requirement (no alignment constraint)
 * @map: The address to base the search on
 * @size: The bitmap size in bits
 * @start: The bitnumber to start searching at
 * @nr: The number of zeroed bits we're looking for
 * @data: additional data - unused
 */
unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
		unsigned long start, unsigned int nr, void *data)
{
	return bitmap_find_next_zero_area(map, size, start, nr, 0);
}
EXPORT_SYMBOL(gen_pool_first_fit);

/**
 * gen_pool_best_fit - find the best fitting region of memory
 * macthing the size requirement (no alignment constraint)
 * @map: The address to base the search on
 * @size: The bitmap size in bits
 * @start: The bitnumber to start searching at
 * @nr: The number of zeroed bits we're looking for
 * @data: additional data - unused
 *
 * Iterate over the bitmap to find the smallest free region
 * which we can allocate the memory.
 */
unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
		unsigned long start, unsigned int nr, void *data)
{
	unsigned long start_bit = size;
	unsigned long len = size + 1;
	unsigned long index;

	index = bitmap_find_next_zero_area(map, size, start, nr, 0);

	while (index < size) {
		int next_bit = find_next_bit(map, size, index + nr);
		if ((next_bit - index) < len) {
			len = next_bit - index;
			start_bit = index;
			if (len == nr)
				return start_bit;
		}
		index = bitmap_find_next_zero_area(map, size,
						   next_bit + 1, nr, 0);
	}

	return start_bit;
}
EXPORT_SYMBOL(gen_pool_best_fit);