summaryrefslogtreecommitdiffstats
path: root/arch/arm/common/dmabounce.c
blob: 301281645d086690f1935af86c99711b629e59d6 (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
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
/*
 *  arch/arm/common/dmabounce.c
 *
 *  Special dma_{map/unmap/dma_sync}_* routines for systems that have
 *  limited DMA windows. These functions utilize bounce buffers to
 *  copy data to/from buffers located outside the DMA region. This
 *  only works for systems in which DMA memory is at the bottom of
 *  RAM, the remainder of memory is at the top and the DMA memory
 *  can be marked as ZONE_DMA. Anything beyond that such as discontiguous
 *  DMA windows will require custom implementations that reserve memory
 *  areas at early bootup.
 *
 *  Original version by Brad Parker (brad@heeltoe.com)
 *  Re-written by Christopher Hoover <ch@murgatroid.com>
 *  Made generic by Deepak Saxena <dsaxena@plexity.net>
 *
 *  Copyright (C) 2002 Hewlett Packard Company.
 *  Copyright (C) 2004 MontaVista Software, Inc.
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License
 *  version 2 as published by the Free Software Foundation.
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/page-flags.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/dmapool.h>
#include <linux/list.h>
#include <linux/scatterlist.h>

#include <asm/cacheflush.h>

#undef STATS

#ifdef STATS
#define DO_STATS(X) do { X ; } while (0)
#else
#define DO_STATS(X) do { } while (0)
#endif

/* ************************************************** */

struct safe_buffer {
	struct list_head node;

	/* original request */
	void		*ptr;
	size_t		size;
	int		direction;

	/* safe buffer info */
	struct dmabounce_pool *pool;
	void		*safe;
	dma_addr_t	safe_dma_addr;
};

struct dmabounce_pool {
	unsigned long	size;
	struct dma_pool	*pool;
#ifdef STATS
	unsigned long	allocs;
#endif
};

struct dmabounce_device_info {
	struct device *dev;
	struct list_head safe_buffers;
#ifdef STATS
	unsigned long total_allocs;
	unsigned long map_op_count;
	unsigned long bounce_count;
	int attr_res;
#endif
	struct dmabounce_pool	small;
	struct dmabounce_pool	large;

	rwlock_t lock;

	int (*needs_bounce)(struct device *, dma_addr_t, size_t);
};

#ifdef STATS
static ssize_t dmabounce_show(struct device *dev, struct device_attribute *attr,
			      char *buf)
{
	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
	return sprintf(buf, "%lu %lu %lu %lu %lu %lu\n",
		device_info->small.allocs,
		device_info->large.allocs,
		device_info->total_allocs - device_info->small.allocs -
			device_info->large.allocs,
		device_info->total_allocs,
		device_info->map_op_count,
		device_info->bounce_count);
}

static DEVICE_ATTR(dmabounce_stats, 0400, dmabounce_show, NULL);
#endif


/* allocate a 'safe' buffer and keep track of it */
static inline struct safe_buffer *
alloc_safe_buffer(struct dmabounce_device_info *device_info, void *ptr,
		  size_t size, enum dma_data_direction dir)
{
	struct safe_buffer *buf;
	struct dmabounce_pool *pool;
	struct device *dev = device_info->dev;
	unsigned long flags;

	dev_dbg(dev, "%s(ptr=%p, size=%d, dir=%d)\n",
		__func__, ptr, size, dir);

	if (size <= device_info->small.size) {
		pool = &device_info->small;
	} else if (size <= device_info->large.size) {
		pool = &device_info->large;
	} else {
		pool = NULL;
	}

	buf = kmalloc(sizeof(struct safe_buffer), GFP_ATOMIC);
	if (buf == NULL) {
		dev_warn(dev, "%s: kmalloc failed\n", __func__);
		return NULL;
	}

	buf->ptr = ptr;
	buf->size = size;
	buf->direction = dir;
	buf->pool = pool;

	if (pool) {
		buf->safe = dma_pool_alloc(pool->pool, GFP_ATOMIC,
					   &buf->safe_dma_addr);
	} else {
		buf->safe = dma_alloc_coherent(dev, size, &buf->safe_dma_addr,
					       GFP_ATOMIC);
	}

	if (buf->safe == NULL) {
		dev_warn(dev,
			 "%s: could not alloc dma memory (size=%d)\n",
			 __func__, size);
		kfree(buf);
		return NULL;
	}

#ifdef STATS
	if (pool)
		pool->allocs++;
	device_info->total_allocs++;
#endif

	write_lock_irqsave(&device_info->lock, flags);
	list_add(&buf->node, &device_info->safe_buffers);
	write_unlock_irqrestore(&device_info->lock, flags);

	return buf;
}

/* determine if a buffer is from our "safe" pool */
static inline struct safe_buffer *
find_safe_buffer(struct dmabounce_device_info *device_info, dma_addr_t safe_dma_addr)
{
	struct safe_buffer *b, *rb = NULL;
	unsigned long flags;

	read_lock_irqsave(&device_info->lock, flags);

	list_for_each_entry(b, &device_info->safe_buffers, node)
		if (b->safe_dma_addr <= safe_dma_addr &&
		    b->safe_dma_addr + b->size > safe_dma_addr) {
			rb = b;
			break;
		}

	read_unlock_irqrestore(&device_info->lock, flags);
	return rb;
}

static inline void
free_safe_buffer(struct dmabounce_device_info *device_info, struct safe_buffer *buf)
{
	unsigned long flags;

	dev_dbg(device_info->dev, "%s(buf=%p)\n", __func__, buf);

	write_lock_irqsave(&device_info->lock, flags);

	list_del(&buf->node);

	write_unlock_irqrestore(&device_info->lock, flags);

	if (buf->pool)
		dma_pool_free(buf->pool->pool, buf->safe, buf->safe_dma_addr);
	else
		dma_free_coherent(device_info->dev, buf->size, buf->safe,
				    buf->safe_dma_addr);

	kfree(buf);
}

/* ************************************************** */

static struct safe_buffer *find_safe_buffer_dev(struct device *dev,
		dma_addr_t dma_addr, const char *where)
{
	if (!dev || !dev->archdata.dmabounce)
		return NULL;
	if (dma_mapping_error(dev, dma_addr)) {
		dev_err(dev, "Trying to %s invalid mapping\n", where);
		return NULL;
	}
	return find_safe_buffer(dev->archdata.dmabounce, dma_addr);
}

static int needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
{
	if (!dev || !dev->archdata.dmabounce)
		return 0;

	if (dev->dma_mask) {
		unsigned long limit, mask = *dev->dma_mask;

		limit = (mask + 1) & ~mask;
		if (limit && size > limit) {
			dev_err(dev, "DMA mapping too big (requested %#x "
				"mask %#Lx)\n", size, *dev->dma_mask);
			return -E2BIG;
		}

		/* Figure out if we need to bounce from the DMA mask. */
		if ((dma_addr | (dma_addr + size - 1)) & ~mask)
			return 1;
	}

	return !!dev->archdata.dmabounce->needs_bounce(dev, dma_addr, size);
}

static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
		enum dma_data_direction dir)
{
	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
	struct safe_buffer *buf;

	if (device_info)
		DO_STATS ( device_info->map_op_count++ );

	buf = alloc_safe_buffer(device_info, ptr, size, dir);
	if (buf == NULL) {
		dev_err(dev, "%s: unable to map unsafe buffer %p!\n",
		       __func__, ptr);
		return DMA_ERROR_CODE;
	}

	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
		buf->safe, buf->safe_dma_addr);

	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
		dev_dbg(dev, "%s: copy unsafe %p to safe %p, size %d\n",
			__func__, ptr, buf->safe, size);
		memcpy(buf->safe, ptr, size);
	}

	return buf->safe_dma_addr;
}

static inline void unmap_single(struct device *dev, struct safe_buffer *buf,
		size_t size, enum dma_data_direction dir)
{
	BUG_ON(buf->size != size);
	BUG_ON(buf->direction != dir);

	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
		buf->safe, buf->safe_dma_addr);

	DO_STATS(dev->archdata.dmabounce->bounce_count++);

	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
		void *ptr = buf->ptr;

		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
			__func__, buf->safe, ptr, size);
		memcpy(ptr, buf->safe, size);

		/*
		 * Since we may have written to a page cache page,
		 * we need to ensure that the data will be coherent
		 * with user mappings.
		 */
		__cpuc_flush_dcache_area(ptr, size);
	}
	free_safe_buffer(dev->archdata.dmabounce, buf);
}

/* ************************************************** */

/*
 * see if a buffer address is in an 'unsafe' range.  if it is
 * allocate a 'safe' buffer and copy the unsafe buffer into it.
 * substitute the safe buffer for the unsafe one.
 * (basically move the buffer from an unsafe area to a safe one)
 */
static dma_addr_t dmabounce_map_page(struct device *dev, struct page *page,
		unsigned long offset, size_t size, enum dma_data_direction dir,
		unsigned long attrs)
{
	dma_addr_t dma_addr;
	int ret;

	dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
		__func__, page, offset, size, dir);

	dma_addr = pfn_to_dma(dev, page_to_pfn(page)) + offset;

	ret = needs_bounce(dev, dma_addr, size);
	if (ret < 0)
		return DMA_ERROR_CODE;

	if (ret == 0) {
		arm_dma_ops.sync_single_for_device(dev, dma_addr, size, dir);
		return dma_addr;
	}

	if (PageHighMem(page)) {
		dev_err(dev, "DMA buffer bouncing of HIGHMEM pages is not supported\n");
		return DMA_ERROR_CODE;
	}

	return map_single(dev, page_address(page) + offset, size, dir);
}

/*
 * see if a mapped address was really a "safe" buffer and if so, copy
 * the data from the safe buffer back to the unsafe buffer and free up
 * the safe buffer.  (basically return things back to the way they
 * should be)
 */
static void dmabounce_unmap_page(struct device *dev, dma_addr_t dma_addr, size_t size,
		enum dma_data_direction dir, unsigned long attrs)
{
	struct safe_buffer *buf;

	dev_dbg(dev, "%s(dma=%#x,size=%d,dir=%x)\n",
		__func__, dma_addr, size, dir);

	buf = find_safe_buffer_dev(dev, dma_addr, __func__);
	if (!buf) {
		arm_dma_ops.sync_single_for_cpu(dev, dma_addr, size, dir);
		return;
	}

	unmap_single(dev, buf, size, dir);
}

static int __dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
		size_t sz, enum dma_data_direction dir)
{
	struct safe_buffer *buf;
	unsigned long off;

	dev_dbg(dev, "%s(dma=%#x,sz=%zx,dir=%x)\n",
		__func__, addr, sz, dir);

	buf = find_safe_buffer_dev(dev, addr, __func__);
	if (!buf)
		return 1;

	off = addr - buf->safe_dma_addr;

	BUG_ON(buf->direction != dir);

	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x off=%#lx) mapped to %p (dma=%#x)\n",
		__func__, buf->ptr, virt_to_dma(dev, buf->ptr), off,
		buf->safe, buf->safe_dma_addr);

	DO_STATS(dev->archdata.dmabounce->bounce_count++);

	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
			__func__, buf->safe + off, buf->ptr + off, sz);
		memcpy(buf->ptr + off, buf->safe + off, sz);
	}
	return 0;
}

static void dmabounce_sync_for_cpu(struct device *dev,
		dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
	if (!__dmabounce_sync_for_cpu(dev, handle, size, dir))
		return;

	arm_dma_ops.sync_single_for_cpu(dev, handle, size, dir);
}

static int __dmabounce_sync_for_device(struct device *dev, dma_addr_t addr,
		size_t sz, enum dma_data_direction dir)
{
	struct safe_buffer *buf;
	unsigned long off;

	dev_dbg(dev, "%s(dma=%#x,sz=%zx,dir=%x)\n",
		__func__, addr, sz, dir);

	buf = find_safe_buffer_dev(dev, addr, __func__);
	if (!buf)
		return 1;

	off = addr - buf->safe_dma_addr;

	BUG_ON(buf->direction != dir);

	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x off=%#lx) mapped to %p (dma=%#x)\n",
		__func__, buf->ptr, virt_to_dma(dev, buf->ptr), off,
		buf->safe, buf->safe_dma_addr);

	DO_STATS(dev->archdata.dmabounce->bounce_count++);

	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
		dev_dbg(dev, "%s: copy out unsafe %p to safe %p, size %d\n",
			__func__,buf->ptr + off, buf->safe + off, sz);
		memcpy(buf->safe + off, buf->ptr + off, sz);
	}
	return 0;
}

static void dmabounce_sync_for_device(struct device *dev,
		dma_addr_t handle, size_t size, enum dma_data_direction dir)
{
	if (!__dmabounce_sync_for_device(dev, handle, size, dir))
		return;

	arm_dma_ops.sync_single_for_device(dev, handle, size, dir);
}

static int dmabounce_set_mask(struct device *dev, u64 dma_mask)
{
	if (dev->archdata.dmabounce)
		return 0;

	return arm_dma_ops.set_dma_mask(dev, dma_mask);
}

static struct dma_map_ops dmabounce_ops = {
	.alloc			= arm_dma_alloc,
	.free			= arm_dma_free,
	.mmap			= arm_dma_mmap,
	.get_sgtable		= arm_dma_get_sgtable,
	.map_page		= dmabounce_map_page,
	.unmap_page		= dmabounce_unmap_page,
	.sync_single_for_cpu	= dmabounce_sync_for_cpu,
	.sync_single_for_device	= dmabounce_sync_for_device,
	.map_sg			= arm_dma_map_sg,
	.unmap_sg		= arm_dma_unmap_sg,
	.sync_sg_for_cpu	= arm_dma_sync_sg_for_cpu,
	.sync_sg_for_device	= arm_dma_sync_sg_for_device,
	.set_dma_mask		= dmabounce_set_mask,
};

static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
		const char *name, unsigned long size)
{
	pool->size = size;
	DO_STATS(pool->allocs = 0);
	pool->pool = dma_pool_create(name, dev, size,
				     0 /* byte alignment */,
				     0 /* no page-crossing issues */);

	return pool->pool ? 0 : -ENOMEM;
}

int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
		unsigned long large_buffer_size,
		int (*needs_bounce_fn)(struct device *, dma_addr_t, size_t))
{
	struct dmabounce_device_info *device_info;
	int ret;

	device_info = kmalloc(sizeof(struct dmabounce_device_info), GFP_ATOMIC);
	if (!device_info) {
		dev_err(dev,
			"Could not allocated dmabounce_device_info\n");
		return -ENOMEM;
	}

	ret = dmabounce_init_pool(&device_info->small, dev,
				  "small_dmabounce_pool", small_buffer_size);
	if (ret) {
		dev_err(dev,
			"dmabounce: could not allocate DMA pool for %ld byte objects\n",
			small_buffer_size);
		goto err_free;
	}

	if (large_buffer_size) {
		ret = dmabounce_init_pool(&device_info->large, dev,
					  "large_dmabounce_pool",
					  large_buffer_size);
		if (ret) {
			dev_err(dev,
				"dmabounce: could not allocate DMA pool for %ld byte objects\n",
				large_buffer_size);
			goto err_destroy;
		}
	}

	device_info->dev = dev;
	INIT_LIST_HEAD(&device_info->safe_buffers);
	rwlock_init(&device_info->lock);
	device_info->needs_bounce = needs_bounce_fn;

#ifdef STATS
	device_info->total_allocs = 0;
	device_info->map_op_count = 0;
	device_info->bounce_count = 0;
	device_info->attr_res = device_create_file(dev, &dev_attr_dmabounce_stats);
#endif

	dev->archdata.dmabounce = device_info;
	set_dma_ops(dev, &dmabounce_ops);

	dev_info(dev, "dmabounce: registered device\n");

	return 0;

 err_destroy:
	dma_pool_destroy(device_info->small.pool);
 err_free:
	kfree(device_info);
	return ret;
}
EXPORT_SYMBOL(dmabounce_register_dev);

void dmabounce_unregister_dev(struct device *dev)
{
	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;

	dev->archdata.dmabounce = NULL;
	set_dma_ops(dev, NULL);

	if (!device_info) {
		dev_warn(dev,
			 "Never registered with dmabounce but attempting"
			 "to unregister!\n");
		return;
	}

	if (!list_empty(&device_info->safe_buffers)) {
		dev_err(dev,
			"Removing from dmabounce with pending buffers!\n");
		BUG();
	}

	if (device_info->small.pool)
		dma_pool_destroy(device_info->small.pool);
	if (device_info->large.pool)
		dma_pool_destroy(device_info->large.pool);

#ifdef STATS
	if (device_info->attr_res == 0)
		device_remove_file(dev, &dev_attr_dmabounce_stats);
#endif

	kfree(device_info);

	dev_info(dev, "dmabounce: device unregistered\n");
}
EXPORT_SYMBOL(dmabounce_unregister_dev);

MODULE_AUTHOR("Christopher Hoover <ch@hpl.hp.com>, Deepak Saxena <dsaxena@plexity.net>");
MODULE_DESCRIPTION("Special dma_{map/unmap/dma_sync}_* routines for systems with limited DMA windows");
MODULE_LICENSE("GPL");
OpenPOWER on IntegriCloud