summaryrefslogtreecommitdiff
path: root/drivers/base/dma-contiguous.c
blob: ad8a85bf852f911229ed13e678e7ab38b0063ba0 (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
/*
 * Contiguous Memory Allocator for DMA mapping framework
 * Copyright (c) 2010-2011 by Samsung Electronics.
 * Written by:
 *	Marek Szyprowski <m.szyprowski@samsung.com>
 *	Michal Nazarewicz <mina86@mina86.com>
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation; either version 2 of the
 * License or (at your optional) any later version of the license.
 */

#define pr_fmt(fmt) "cma: " fmt

#ifdef CONFIG_CMA_DEBUG
#ifndef DEBUG
#  define DEBUG
#endif
#endif

#include <asm/page.h>
#include <asm/dma-contiguous.h>

#include <linux/memblock.h>
#include <linux/err.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/page-isolation.h>
#include <linux/sizes.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/mm_types.h>
#include <linux/dma-contiguous.h>
#include <linux/log2.h>

struct cma {
	unsigned long	base_pfn;
	unsigned long	count;
	unsigned long	*bitmap;
	unsigned int order_per_bit; /* Order of pages represented by one bit */
	struct mutex	lock;
};

struct cma *dma_contiguous_default_area;

#ifdef CONFIG_CMA_SIZE_MBYTES
#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
#else
#define CMA_SIZE_MBYTES 0
#endif

/*
 * Default global CMA area size can be defined in kernel's .config.
 * This is useful mainly for distro maintainers to create a kernel
 * that works correctly for most supported systems.
 * The size can be set in bytes or as a percentage of the total memory
 * in the system.
 *
 * Users, who want to set the size of global CMA area for their system
 * should use cma= kernel parameter.
 */
static const phys_addr_t size_bytes = CMA_SIZE_MBYTES * SZ_1M;
static phys_addr_t size_cmdline = -1;
static phys_addr_t base_cmdline;
static phys_addr_t limit_cmdline;

static int __init early_cma(char *p)
{
	pr_debug("%s(%s)\n", __func__, p);
	size_cmdline = memparse(p, &p);
	if (*p != '@')
		return 0;
	base_cmdline = memparse(p + 1, &p);
	if (*p != '-') {
		limit_cmdline = base_cmdline + size_cmdline;
		return 0;
	}
	limit_cmdline = memparse(p + 1, &p);

	return 0;
}
early_param("cma", early_cma);

#ifdef CONFIG_CMA_SIZE_PERCENTAGE

static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
{
	struct memblock_region *reg;
	unsigned long total_pages = 0;

	/*
	 * We cannot use memblock_phys_mem_size() here, because
	 * memblock_analyze() has not been called yet.
	 */
	for_each_memblock(memory, reg)
		total_pages += memblock_region_memory_end_pfn(reg) -
			       memblock_region_memory_base_pfn(reg);

	return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
}

#else

static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
{
	return 0;
}

#endif

/**
 * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
 * @limit: End address of the reserved memory (optional, 0 for any).
 *
 * This function reserves memory from early allocator. It should be
 * called by arch specific code once the early allocator (memblock or bootmem)
 * has been activated and all other subsystems have already allocated/reserved
 * memory.
 */
void __init dma_contiguous_reserve(phys_addr_t limit)
{
	phys_addr_t selected_size = 0;
	phys_addr_t selected_base = 0;
	phys_addr_t selected_limit = limit;
	bool fixed = false;

	pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);

	if (size_cmdline != -1) {
		selected_size = size_cmdline;
		selected_base = base_cmdline;
		selected_limit = min_not_zero(limit_cmdline, limit);
		if (base_cmdline + size_cmdline == limit_cmdline)
			fixed = true;
	} else {
#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
		selected_size = size_bytes;
#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
		selected_size = cma_early_percent_memory();
#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
		selected_size = min(size_bytes, cma_early_percent_memory());
#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
		selected_size = max(size_bytes, cma_early_percent_memory());
#endif
	}

	if (selected_size && !dma_contiguous_default_area) {
		pr_debug("%s: reserving %ld MiB for global area\n", __func__,
			 (unsigned long)selected_size / SZ_1M);

		dma_contiguous_reserve_area(selected_size, selected_base,
					    selected_limit,
					    &dma_contiguous_default_area,
					    fixed);
	}
}

static DEFINE_MUTEX(cma_mutex);

static unsigned long cma_bitmap_aligned_mask(struct cma *cma, int align_order)
{
	return (1UL << (align_order >> cma->order_per_bit)) - 1;
}

static unsigned long cma_bitmap_maxno(struct cma *cma)
{
	return cma->count >> cma->order_per_bit;
}

static unsigned long cma_bitmap_pages_to_bits(struct cma *cma,
						unsigned long pages)
{
	return ALIGN(pages, 1UL << cma->order_per_bit) >> cma->order_per_bit;
}

static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, int count)
{
	unsigned long bitmap_no, bitmap_count;

	bitmap_no = (pfn - cma->base_pfn) >> cma->order_per_bit;
	bitmap_count = cma_bitmap_pages_to_bits(cma, count);

	mutex_lock(&cma->lock);
	bitmap_clear(cma->bitmap, bitmap_no, bitmap_count);
	mutex_unlock(&cma->lock);
}

static int __init cma_activate_area(struct cma *cma)
{
	int bitmap_size = BITS_TO_LONGS(cma_bitmap_maxno(cma)) * sizeof(long);
	unsigned long base_pfn = cma->base_pfn, pfn = base_pfn;
	unsigned i = cma->count >> pageblock_order;
	struct zone *zone;

	cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL);

	if (!cma->bitmap)
		return -ENOMEM;

	WARN_ON_ONCE(!pfn_valid(pfn));
	zone = page_zone(pfn_to_page(pfn));

	do {
		unsigned j;
		base_pfn = pfn;
		for (j = pageblock_nr_pages; j; --j, pfn++) {
			WARN_ON_ONCE(!pfn_valid(pfn));
			/*
			 * alloc_contig_range requires the pfn range
			 * specified to be in the same zone. Make this
			 * simple by forcing the entire CMA resv range
			 * to be in the same zone.
			 */
			if (page_zone(pfn_to_page(pfn)) != zone)
				goto err;
		}
		init_cma_reserved_pageblock(pfn_to_page(base_pfn));
	} while (--i);

	mutex_init(&cma->lock);
	return 0;

err:
	kfree(cma->bitmap);
	return -EINVAL;
}

static struct cma cma_areas[MAX_CMA_AREAS];
static unsigned cma_area_count;

static int __init cma_init_reserved_areas(void)
{
	int i;

	for (i = 0; i < cma_area_count; i++) {
		int ret = cma_activate_area(&cma_areas[i]);
		if (ret)
			return ret;
	}

	return 0;
}
core_initcall(cma_init_reserved_areas);

static int __init __dma_contiguous_reserve_area(phys_addr_t size,
			phys_addr_t base, phys_addr_t limit,
			phys_addr_t alignment, unsigned int order_per_bit,
			struct cma **res_cma, bool fixed)
{
	struct cma *cma = &cma_areas[cma_area_count];
	int ret = 0;

	pr_debug("%s(size %lx, base %08lx, limit %08lx alignment %08lx)\n",
		__func__, (unsigned long)size, (unsigned long)base,
		(unsigned long)limit, (unsigned long)alignment);

	if (cma_area_count == ARRAY_SIZE(cma_areas)) {
		pr_err("Not enough slots for CMA reserved regions!\n");
		return -ENOSPC;
	}

	if (!size)
		return -EINVAL;

	if (alignment && !is_power_of_2(alignment))
		return -EINVAL;

	/*
	 * Sanitise input arguments.
	 * Pages both ends in CMA area could be merged into adjacent unmovable
	 * migratetype page by page allocator's buddy algorithm. In the case,
	 * you couldn't get a contiguous memory, which is not what we want.
	 */
	alignment = max(alignment,
		(phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order));
	base = ALIGN(base, alignment);
	size = ALIGN(size, alignment);
	limit &= ~(alignment - 1);

	/* size should be aligned with order_per_bit */
	if (!IS_ALIGNED(size >> PAGE_SHIFT, 1 << order_per_bit))
		return -EINVAL;

	/* Reserve memory */
	if (base && fixed) {
		if (memblock_is_region_reserved(base, size) ||
		    memblock_reserve(base, size) < 0) {
			ret = -EBUSY;
			goto err;
		}
	} else {
		phys_addr_t addr = memblock_alloc_range(size, alignment, base,
							limit);
		if (!addr) {
			ret = -ENOMEM;
			goto err;
		} else {
			base = addr;
		}
	}

	/*
	 * Each reserved area must be initialised later, when more kernel
	 * subsystems (like slab allocator) are available.
	 */
	cma->base_pfn = PFN_DOWN(base);
	cma->count = size >> PAGE_SHIFT;
	cma->order_per_bit = order_per_bit;
	*res_cma = cma;
	cma_area_count++;

	pr_info("CMA: reserved %ld MiB at %08lx\n", (unsigned long)size / SZ_1M,
		(unsigned long)base);
	return 0;

err:
	pr_err("CMA: failed to reserve %ld MiB\n", (unsigned long)size / SZ_1M);
	return ret;
}

/**
 * dma_contiguous_reserve_area() - reserve custom contiguous area
 * @size: Size of the reserved area (in bytes),
 * @base: Base address of the reserved area optional, use 0 for any
 * @limit: End address of the reserved memory (optional, 0 for any).
 * @res_cma: Pointer to store the created cma region.
 * @fixed: hint about where to place the reserved area
 *
 * This function reserves memory from early allocator. It should be
 * called by arch specific code once the early allocator (memblock or bootmem)
 * has been activated and all other subsystems have already allocated/reserved
 * memory. This function allows to create custom reserved areas for specific
 * devices.
 *
 * If @fixed is true, reserve contiguous area at exactly @base.  If false,
 * reserve in range from @base to @limit.
 */
int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
				       phys_addr_t limit, struct cma **res_cma,
				       bool fixed)
{
	int ret;

	ret = __dma_contiguous_reserve_area(size, base, limit, 0, 0,
						res_cma, fixed);
	if (ret)
		return ret;

	/* Architecture specific contiguous memory fixup. */
	dma_contiguous_early_fixup(PFN_PHYS((*res_cma)->base_pfn),
				(*res_cma)->count << PAGE_SHIFT);

	return 0;
}

static struct page *__dma_alloc_from_contiguous(struct cma *cma, int count,
				       unsigned int align)
{
	unsigned long mask, pfn, start = 0;
	unsigned long bitmap_maxno, bitmap_no, bitmap_count;
	struct page *page = NULL;
	int ret;

	if (!cma || !cma->count)
		return NULL;

	pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma,
		 count, align);

	if (!count)
		return NULL;

	mask = cma_bitmap_aligned_mask(cma, align);
	bitmap_maxno = cma_bitmap_maxno(cma);
	bitmap_count = cma_bitmap_pages_to_bits(cma, count);

	for (;;) {
		mutex_lock(&cma->lock);
		bitmap_no = bitmap_find_next_zero_area(cma->bitmap,
				bitmap_maxno, start, bitmap_count, mask);
		if (bitmap_no >= bitmap_maxno) {
			mutex_unlock(&cma->lock);
			break;
		}
		bitmap_set(cma->bitmap, bitmap_no, bitmap_count);
		/*
		 * It's safe to drop the lock here. We've marked this region for
		 * our exclusive use. If the migration fails we will take the
		 * lock again and unmark it.
		 */
		mutex_unlock(&cma->lock);

		pfn = cma->base_pfn + (bitmap_no << cma->order_per_bit);
		mutex_lock(&cma_mutex);
		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA);
		mutex_unlock(&cma_mutex);
		if (ret == 0) {
			page = pfn_to_page(pfn);
			break;
		} else if (ret != -EBUSY) {
			cma_clear_bitmap(cma, pfn, count);
			break;
		}
		cma_clear_bitmap(cma, pfn, count);
		pr_debug("%s(): memory range at %p is busy, retrying\n",
			 __func__, pfn_to_page(pfn));
		/* try again with a bit different memory target */
		start = bitmap_no + mask + 1;
	}

	pr_debug("%s(): returned %p\n", __func__, page);
	return page;
}

/**
 * dma_alloc_from_contiguous() - allocate pages from contiguous area
 * @dev:   Pointer to device for which the allocation is performed.
 * @count: Requested number of pages.
 * @align: Requested alignment of pages (in PAGE_SIZE order).
 *
 * This function allocates memory buffer for specified device. It uses
 * device specific contiguous memory area if available or the default
 * global one. Requires architecture specific dev_get_cma_area() helper
 * function.
 */
struct page *dma_alloc_from_contiguous(struct device *dev, int count,
				       unsigned int align)
{
	struct cma *cma = dev_get_cma_area(dev);

	if (align > CONFIG_CMA_ALIGNMENT)
		align = CONFIG_CMA_ALIGNMENT;

	return __dma_alloc_from_contiguous(cma, count, align);
}

static bool __dma_release_from_contiguous(struct cma *cma, struct page *pages,
				 int count)
{
	unsigned long pfn;

	if (!cma || !pages)
		return false;

	pr_debug("%s(page %p)\n", __func__, (void *)pages);

	pfn = page_to_pfn(pages);

	if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count)
		return false;

	VM_BUG_ON(pfn + count > cma->base_pfn + cma->count);

	free_contig_range(pfn, count);
	cma_clear_bitmap(cma, pfn, count);

	return true;
}

/**
 * dma_release_from_contiguous() - release allocated pages
 * @dev:   Pointer to device for which the pages were allocated.
 * @pages: Allocated pages.
 * @count: Number of allocated pages.
 *
 * This function releases memory allocated by dma_alloc_from_contiguous().
 * It returns false when provided pages do not belong to contiguous area and
 * true otherwise.
 */
bool dma_release_from_contiguous(struct device *dev, struct page *pages,
				 int count)
{
	struct cma *cma = dev_get_cma_area(dev);

	return __dma_release_from_contiguous(cma, pages, count);
}