aboutsummaryrefslogtreecommitdiff
path: root/drivers/dma/dmaengine.c
blob: 96598479eece65ecce4e16b7d1f8afe250a9d39b (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
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
/*
 * Copyright(c) 2004 - 2006 Intel Corporation. All rights reserved.
 *
 * 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 option)
 * any later version.
 *
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 59
 * Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 *
 * The full GNU General Public License is included in this distribution in the
 * file called COPYING.
 */

/*
 * This code implements the DMA subsystem. It provides a HW-neutral interface
 * for other kernel code to use asynchronous memory copy capabilities,
 * if present, and allows different HW DMA drivers to register as providing
 * this capability.
 *
 * Due to the fact we are accelerating what is already a relatively fast
 * operation, the code goes to great lengths to avoid additional overhead,
 * such as locking.
 *
 * LOCKING:
 *
 * The subsystem keeps a global list of dma_device structs it is protected by a
 * mutex, dma_list_mutex.
 *
 * A subsystem can get access to a channel by calling dmaengine_get() followed
 * by dma_find_channel(), or if it has need for an exclusive channel it can call
 * dma_request_channel().  Once a channel is allocated a reference is taken
 * against its corresponding driver to disable removal.
 *
 * Each device has a channels list, which runs unlocked but is never modified
 * once the device is registered, it's just setup by the driver.
 *
 * See Documentation/dmaengine.txt for more details
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/mm.h>
#include <linux/device.h>
#include <linux/dmaengine.h>
#include <linux/hardirq.h>
#include <linux/spinlock.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/mutex.h>
#include <linux/jiffies.h>
#include <linux/rculist.h>
#include <linux/idr.h>

static DEFINE_MUTEX(dma_list_mutex);
static LIST_HEAD(dma_device_list);
static long dmaengine_ref_count;
static struct idr dma_idr;

/* --- sysfs implementation --- */

/**
 * dev_to_dma_chan - convert a device pointer to the its sysfs container object
 * @dev - device node
 *
 * Must be called under dma_list_mutex
 */
static struct dma_chan *dev_to_dma_chan(struct device *dev)
{
	struct dma_chan_dev *chan_dev;

	chan_dev = container_of(dev, typeof(*chan_dev), device);
	return chan_dev->chan;
}

static ssize_t show_memcpy_count(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct dma_chan *chan;
	unsigned long count = 0;
	int i;
	int err;

	mutex_lock(&dma_list_mutex);
	chan = dev_to_dma_chan(dev);
	if (chan) {
		for_each_possible_cpu(i)
			count += per_cpu_ptr(chan->local, i)->memcpy_count;
		err = sprintf(buf, "%lu\n", count);
	} else
		err = -ENODEV;
	mutex_unlock(&dma_list_mutex);

	return err;
}

static ssize_t show_bytes_transferred(struct device *dev, struct device_attribute *attr,
				      char *buf)
{
	struct dma_chan *chan;
	unsigned long count = 0;
	int i;
	int err;

	mutex_lock(&dma_list_mutex);
	chan = dev_to_dma_chan(dev);
	if (chan) {
		for_each_possible_cpu(i)
			count += per_cpu_ptr(chan->local, i)->bytes_transferred;
		err = sprintf(buf, "%lu\n", count);
	} else
		err = -ENODEV;
	mutex_unlock(&dma_list_mutex);

	return err;
}

static ssize_t show_in_use(struct device *dev, struct device_attribute *attr, char *buf)
{
	struct dma_chan *chan;
	int err;

	mutex_lock(&dma_list_mutex);
	chan = dev_to_dma_chan(dev);
	if (chan)
		err = sprintf(buf, "%d\n", chan->client_count);
	else
		err = -ENODEV;
	mutex_unlock(&dma_list_mutex);

	return err;
}

static struct device_attribute dma_attrs[] = {
	__ATTR(memcpy_count, S_IRUGO, show_memcpy_count, NULL),
	__ATTR(bytes_transferred, S_IRUGO, show_bytes_transferred, NULL),
	__ATTR(in_use, S_IRUGO, show_in_use, NULL),
	__ATTR_NULL
};

static void chan_dev_release(struct device *dev)
{
	struct dma_chan_dev *chan_dev;

	chan_dev = container_of(dev, typeof(*chan_dev), device);
	if (atomic_dec_and_test(chan_dev->idr_ref)) {
		mutex_lock(&dma_list_mutex);
		idr_remove(&dma_idr, chan_dev->dev_id);
		mutex_unlock(&dma_list_mutex);
		kfree(chan_dev->idr_ref);
	}
	kfree(chan_dev);
}

static struct class dma_devclass = {
	.name		= "dma",
	.dev_attrs	= dma_attrs,
	.dev_release	= chan_dev_release,
};

/* --- client and device registration --- */

#define dma_device_satisfies_mask(device, mask) \
	__dma_device_satisfies_mask((device), &(mask))
static int
__dma_device_satisfies_mask(struct dma_device *device, dma_cap_mask_t *want)
{
	dma_cap_mask_t has;

	bitmap_and(has.bits, want->bits, device->cap_mask.bits,
		DMA_TX_TYPE_END);
	return bitmap_equal(want->bits, has.bits, DMA_TX_TYPE_END);
}

static struct module *dma_chan_to_owner(struct dma_chan *chan)
{
	return chan->device->dev->driver->owner;
}

/**
 * balance_ref_count - catch up the channel reference count
 * @chan - channel to balance ->client_count versus dmaengine_ref_count
 *
 * balance_ref_count must be called under dma_list_mutex
 */
static void balance_ref_count(struct dma_chan *chan)
{
	struct module *owner = dma_chan_to_owner(chan);

	while (chan->client_count < dmaengine_ref_count) {
		__module_get(owner);
		chan->client_count++;
	}
}

/**
 * dma_chan_get - try to grab a dma channel's parent driver module
 * @chan - channel to grab
 *
 * Must be called under dma_list_mutex
 */
static int dma_chan_get(struct dma_chan *chan)
{
	int err = -ENODEV;
	struct module *owner = dma_chan_to_owner(chan);

	if (chan->client_count) {
		__module_get(owner);
		err = 0;
	} else if (try_module_get(owner))
		err = 0;

	if (err == 0)
		chan->client_count++;

	/* allocate upon first client reference */
	if (chan->client_count == 1 && err == 0) {
		int desc_cnt = chan->device->device_alloc_chan_resources(chan);

		if (desc_cnt < 0) {
			err = desc_cnt;
			chan->client_count = 0;
			module_put(owner);
		} else if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask))
			balance_ref_count(chan);
	}

	return err;
}

/**
 * dma_chan_put - drop a reference to a dma channel's parent driver module
 * @chan - channel to release
 *
 * Must be called under dma_list_mutex
 */
static void dma_chan_put(struct dma_chan *chan)
{
	if (!chan->client_count)
		return; /* this channel failed alloc_chan_resources */
	chan->client_count--;
	module_put(dma_chan_to_owner(chan));
	if (chan->client_count == 0)
		chan->device->device_free_chan_resources(chan);
}

enum dma_status dma_sync_wait(struct dma_chan *chan, dma_cookie_t cookie)
{
	enum dma_status status;
	unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);

	dma_async_issue_pending(chan);
	do {
		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
			printk(KERN_ERR "dma_sync_wait_timeout!\n");
			return DMA_ERROR;
		}
	} while (status == DMA_IN_PROGRESS);

	return status;
}
EXPORT_SYMBOL(dma_sync_wait);

/**
 * dma_cap_mask_all - enable iteration over all operation types
 */
static dma_cap_mask_t dma_cap_mask_all;

/**
 * dma_chan_tbl_ent - tracks channel allocations per core/operation
 * @chan - associated channel for this entry
 */
struct dma_chan_tbl_ent {
	struct dma_chan *chan;
};

/**
 * channel_table - percpu lookup table for memory-to-memory offload providers
 */
static struct dma_chan_tbl_ent *channel_table[DMA_TX_TYPE_END];

static int __init dma_channel_table_init(void)
{
	enum dma_transaction_type cap;
	int err = 0;

	bitmap_fill(dma_cap_mask_all.bits, DMA_TX_TYPE_END);

	/* 'interrupt', 'private', and 'slave' are channel capabilities,
	 * but are not associated with an operation so they do not need
	 * an entry in the channel_table
	 */
	clear_bit(DMA_INTERRUPT, dma_cap_mask_all.bits);
	clear_bit(DMA_PRIVATE, dma_cap_mask_all.bits);
	clear_bit(DMA_SLAVE, dma_cap_mask_all.bits);

	for_each_dma_cap_mask(cap, dma_cap_mask_all) {
		channel_table[cap] = alloc_percpu(struct dma_chan_tbl_ent);
		if (!channel_table[cap]) {
			err = -ENOMEM;
			break;
		}
	}

	if (err) {
		pr_err("dmaengine: initialization failure\n");
		for_each_dma_cap_mask(cap, dma_cap_mask_all)
			if (channel_table[cap])
				free_percpu(channel_table[cap]);
	}

	return err;
}
arch_initcall(dma_channel_table_init);

/**
 * dma_find_channel - find a channel to carry out the operation
 * @tx_type: transaction type
 */
struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type)
{
	struct dma_chan *chan;
	int cpu;

	cpu = get_cpu();
	chan = per_cpu_ptr(channel_table[tx_type], cpu)->chan;
	put_cpu();

	return chan;
}
EXPORT_SYMBOL(dma_find_channel);

/**
 * dma_issue_pending_all - flush all pending operations across all channels
 */
void dma_issue_pending_all(void)
{
	struct dma_device *device;
	struct dma_chan *chan;

	rcu_read_lock();
	list_for_each_entry_rcu(device, &dma_device_list, global_node) {
		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
			continue;
		list_for_each_entry(chan, &device->channels, device_node)
			if (chan->client_count)
				device->device_issue_pending(chan);
	}
	rcu_read_unlock();
}
EXPORT_SYMBOL(dma_issue_pending_all);

/**
 * nth_chan - returns the nth channel of the given capability
 * @cap: capability to match
 * @n: nth channel desired
 *
 * Defaults to returning the channel with the desired capability and the
 * lowest reference count when 'n' cannot be satisfied.  Must be called
 * under dma_list_mutex.
 */
static struct dma_chan *nth_chan(enum dma_transaction_type cap, int n)
{
	struct dma_device *device;
	struct dma_chan *chan;
	struct dma_chan *ret = NULL;
	struct dma_chan *min = NULL;

	list_for_each_entry(device, &dma_device_list, global_node) {
		if (!dma_has_cap(cap, device->cap_mask) ||
		    dma_has_cap(DMA_PRIVATE, device->cap_mask))
			continue;
		list_for_each_entry(chan, &device->channels, device_node) {
			if (!chan->client_count)
				continue;
			if (!min)
				min = chan;
			else if (chan->table_count < min->table_count)
				min = chan;

			if (n-- == 0) {
				ret = chan;
				break; /* done */
			}
		}
		if (ret)
			break; /* done */
	}

	if (!ret)
		ret = min;

	if (ret)
		ret->table_count++;

	return ret;
}

/**
 * dma_channel_rebalance - redistribute the available channels
 *
 * Optimize for cpu isolation (each cpu gets a dedicated channel for an
 * operation type) in the SMP case,  and operation isolation (avoid
 * multi-tasking channels) in the non-SMP case.  Must be called under
 * dma_list_mutex.
 */
static void dma_channel_rebalance(void)
{
	struct dma_chan *chan;
	struct dma_device *device;
	int cpu;
	int cap;
	int n;

	/* undo the last distribution */
	for_each_dma_cap_mask(cap, dma_cap_mask_all)
		for_each_possible_cpu(cpu)
			per_cpu_ptr(channel_table[cap], cpu)->chan = NULL;

	list_for_each_entry(device, &dma_device_list, global_node) {
		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
			continue;
		list_for_each_entry(chan, &device->channels, device_node)
			chan->table_count = 0;
	}

	/* don't populate the channel_table if no clients are available */
	if (!dmaengine_ref_count)
		return;

	/* redistribute available channels */
	n = 0;
	for_each_dma_cap_mask(cap, dma_cap_mask_all)
		for_each_online_cpu(cpu) {
			if (num_possible_cpus() > 1)
				chan = nth_chan(cap, n++);
			else
				chan = nth_chan(cap, -1);

			per_cpu_ptr(channel_table[cap], cpu)->chan = chan;
		}
}

static struct dma_chan *private_candidate(dma_cap_mask_t *mask, struct dma_device *dev,
					  dma_filter_fn fn, void *fn_param)
{
	struct dma_chan *chan;

	if (!__dma_device_satisfies_mask(dev, mask)) {
		pr_debug("%s: wrong capabilities\n", __func__);
		return NULL;
	}
	/* devices with multiple channels need special handling as we need to
	 * ensure that all channels are either private or public.
	 */
	if (dev->chancnt > 1 && !dma_has_cap(DMA_PRIVATE, dev->cap_mask))
		list_for_each_entry(chan, &dev->channels, device_node) {
			/* some channels are already publicly allocated */
			if (chan->client_count)
				return NULL;
		}

	list_for_each_entry(chan, &dev->channels, device_node) {
		if (chan->client_count) {
			pr_debug("%s: %s busy\n",
				 __func__, dma_chan_name(chan));
			continue;
		}
		if (fn && !fn(chan, fn_param)) {
			pr_debug("%s: %s filter said false\n",
				 __func__, dma_chan_name(chan));
			continue;
		}
		return chan;
	}

	return NULL;
}

/**
 * dma_request_channel - try to allocate an exclusive channel
 * @mask: capabilities that the channel must satisfy
 * @fn: optional callback to disposition available channels
 * @fn_param: opaque parameter to pass to dma_filter_fn
 */
struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, void *fn_param)
{
	struct dma_device *device, *_d;
	struct dma_chan *chan = NULL;
	int err;

	/* Find a channel */
	mutex_lock(&dma_list_mutex);
	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
		chan = private_candidate(mask, device, fn, fn_param);
		if (chan) {
			/* Found a suitable channel, try to grab, prep, and
			 * return it.  We first set DMA_PRIVATE to disable
			 * balance_ref_count as this channel will not be
			 * published in the general-purpose allocator
			 */
			dma_cap_set(DMA_PRIVATE, device->cap_mask);
			device->privatecnt++;
			err = dma_chan_get(chan);

			if (err == -ENODEV) {
				pr_debug("%s: %s module removed\n", __func__,
					 dma_chan_name(chan));
				list_del_rcu(&device->global_node);
			} else if (err)
				pr_err("dmaengine: failed to get %s: (%d)\n",
				       dma_chan_name(chan), err);
			else
				break;
			if (--device->privatecnt == 0)
				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
			chan->private = NULL;
			chan = NULL;
		}
	}
	mutex_unlock(&dma_list_mutex);

	pr_debug("%s: %s (%s)\n", __func__, chan ? "success" : "fail",
		 chan ? dma_chan_name(chan) : NULL);

	return chan;
}
EXPORT_SYMBOL_GPL(__dma_request_channel);

void dma_release_channel(struct dma_chan *chan)
{
	mutex_lock(&dma_list_mutex);
	WARN_ONCE(chan->client_count != 1,
		  "chan reference count %d != 1\n", chan->client_count);
	dma_chan_put(chan);
	/* drop PRIVATE cap enabled by __dma_request_channel() */
	if (--chan->device->privatecnt == 0)
		dma_cap_clear(DMA_PRIVATE, chan->device->cap_mask);
	chan->private = NULL;
	mutex_unlock(&dma_list_mutex);
}
EXPORT_SYMBOL_GPL(dma_release_channel);

/**
 * dmaengine_get - register interest in dma_channels
 */
void dmaengine_get(void)
{
	struct dma_device *device, *_d;
	struct dma_chan *chan;
	int err;

	mutex_lock(&dma_list_mutex);
	dmaengine_ref_count++;

	/* try to grab channels */
	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
			continue;
		list_for_each_entry(chan, &device->channels, device_node) {
			err = dma_chan_get(chan);
			if (err == -ENODEV) {
				/* module removed before we could use it */
				list_del_rcu(&device->global_node);
				break;
			} else if (err)
				pr_err("dmaengine: failed to get %s: (%d)\n",
				       dma_chan_name(chan), err);
		}
	}

	/* if this is the first reference and there were channels
	 * waiting we need to rebalance to get those channels
	 * incorporated into the channel table
	 */
	if (dmaengine_ref_count == 1)
		dma_channel_rebalance();
	mutex_unlock(&dma_list_mutex);
}
EXPORT_SYMBOL(dmaengine_get);

/**
 * dmaengine_put - let dma drivers be removed when ref_count == 0
 */
void dmaengine_put(void)
{
	struct dma_device *device;
	struct dma_chan *chan;

	mutex_lock(&dma_list_mutex);
	dmaengine_ref_count--;
	BUG_ON(dmaengine_ref_count < 0);
	/* drop channel references */
	list_for_each_entry(device, &dma_device_list, global_node) {
		if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
			continue;
		list_for_each_entry(chan, &device->channels, device_node)
			dma_chan_put(chan);
	}
	mutex_unlock(&dma_list_mutex);
}
EXPORT_SYMBOL(dmaengine_put);

static int get_dma_id(struct dma_device *device)
{
	int rc;

 idr_retry:
	if (!idr_pre_get(&dma_idr, GFP_KERNEL))
		return -ENOMEM;
	mutex_lock(&dma_list_mutex);
	rc = idr_get_new(&dma_idr, NULL, &device->dev_id);
	mutex_unlock(&dma_list_mutex);
	if (rc == -EAGAIN)
		goto idr_retry;
	else if (rc != 0)
		return rc;

	return 0;
}

/**
 * dma_async_device_register - registers DMA devices found
 * @device: &dma_device
 */
int dma_async_device_register(struct dma_device *device)
{
	int chancnt = 0, rc;
	struct dma_chan* chan;
	atomic_t *idr_ref;

	if (!device)
		return -ENODEV;

	/* validate device routines */
	BUG_ON(dma_has_cap(DMA_MEMCPY, device->cap_mask) &&
		!device->device_prep_dma_memcpy);
	BUG_ON(dma_has_cap(DMA_XOR, device->cap_mask) &&
		!device->device_prep_dma_xor);
	BUG_ON(dma_has_cap(DMA_XOR_VAL, device->cap_mask) &&
		!device->device_prep_dma_xor_val);
	BUG_ON(dma_has_cap(DMA_PQ, device->cap_mask) &&
		!device->device_prep_dma_pq);
	BUG_ON(dma_has_cap(DMA_PQ_VAL, device->cap_mask) &&
		!device->device_prep_dma_pq_val);
	BUG_ON(dma_has_cap(DMA_MEMSET, device->cap_mask) &&
		!device->device_prep_dma_memset);
	BUG_ON(dma_has_cap(DMA_INTERRUPT, device->cap_mask) &&
		!device->device_prep_dma_interrupt);
	BUG_ON(dma_has_cap(DMA_SLAVE, device->cap_mask) &&
		!device->device_prep_slave_sg);
	BUG_ON(dma_has_cap(DMA_SLAVE, device->cap_mask) &&
		!device->device_terminate_all);

	BUG_ON(!device->device_alloc_chan_resources);
	BUG_ON(!device->device_free_chan_resources);
	BUG_ON(!device->device_is_tx_complete);
	BUG_ON(!device->device_issue_pending);
	BUG_ON(!device->dev);

	idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
	if (!idr_ref)
		return -ENOMEM;
	rc = get_dma_id(device);
	if (rc != 0) {
		kfree(idr_ref);
		return rc;
	}

	atomic_set(idr_ref, 0);

	/* represent channels in sysfs. Probably want devs too */
	list_for_each_entry(chan, &device->channels, device_node) {
		rc = -ENOMEM;
		chan->local = alloc_percpu(typeof(*chan->local));
		if (chan->local == NULL)
			goto err_out;
		chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL);
		if (chan->dev == NULL) {
			free_percpu(chan->local);
			chan->local = NULL;
			goto err_out;
		}

		chan->chan_id = chancnt++;
		chan->dev->device.class = &dma_devclass;
		chan->dev->device.parent = device->dev;
		chan->dev->chan = chan;
		chan->dev->idr_ref = idr_ref;
		chan->dev->dev_id = device->dev_id;
		atomic_inc(idr_ref);
		dev_set_name(&chan->dev->device, "dma%dchan%d",
			     device->dev_id, chan->chan_id);

		rc = device_register(&chan->dev->device);
		if (rc) {
			free_percpu(chan->local);
			chan->local = NULL;
			kfree(chan->dev);
			atomic_dec(idr_ref);
			goto err_out;
		}
		chan->client_count = 0;
	}
	device->chancnt = chancnt;

	mutex_lock(&dma_list_mutex);
	/* take references on public channels */
	if (dmaengine_ref_count && !dma_has_cap(DMA_PRIVATE, device->cap_mask))
		list_for_each_entry(chan, &device->channels, device_node) {
			/* if clients are already waiting for channels we need
			 * to take references on their behalf
			 */
			if (dma_chan_get(chan) == -ENODEV) {
				/* note we can only get here for the first
				 * channel as the remaining channels are
				 * guaranteed to get a reference
				 */
				rc = -ENODEV;
				mutex_unlock(&dma_list_mutex);
				goto err_out;
			}
		}
	list_add_tail_rcu(&device->global_node, &dma_device_list);
	if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
		device->privatecnt++;	/* Always private */
	dma_channel_rebalance();
	mutex_unlock(&dma_list_mutex);

	return 0;

err_out:
	/* if we never registered a channel just release the idr */
	if (atomic_read(idr_ref) == 0) {
		mutex_lock(&dma_list_mutex);
		idr_remove(&dma_idr, device->dev_id);
		mutex_unlock(&dma_list_mutex);
		kfree(idr_ref);
		return rc;
	}

	list_for_each_entry(chan, &device->channels, device_node) {
		if (chan->local == NULL)
			continue;
		mutex_lock(&dma_list_mutex);
		chan->dev->chan = NULL;
		mutex_unlock(&dma_list_mutex);
		device_unregister(&chan->dev->device);
		free_percpu(chan->local);
	}
	return rc;
}
EXPORT_SYMBOL(dma_async_device_register);

/**
 * dma_async_device_unregister - unregister a DMA device
 * @device: &dma_device
 *
 * This routine is called by dma driver exit routines, dmaengine holds module
 * references to prevent it being called while channels are in use.
 */
void dma_async_device_unregister(struct dma_device *device)
{
	struct dma_chan *chan;

	mutex_lock(&dma_list_mutex);
	list_del_rcu(&device->global_node);
	dma_channel_rebalance();
	mutex_unlock(&dma_list_mutex);

	list_for_each_entry(chan, &device->channels, device_node) {
		WARN_ONCE(chan->client_count,
			  "%s called while %d clients hold a reference\n",
			  __func__, chan->client_count);
		mutex_lock(&dma_list_mutex);
		chan->dev->chan = NULL;
		mutex_unlock(&dma_list_mutex);
		device_unregister(&chan->dev->device);
	}
}
EXPORT_SYMBOL(dma_async_device_unregister);

/**
 * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
 * @chan: DMA channel to offload copy to
 * @dest: destination address (virtual)
 * @src: source address (virtual)
 * @len: length
 *
 * Both @dest and @src must be mappable to a bus address according to the
 * DMA mapping API rules for streaming mappings.
 * Both @dest and @src must stay memory resident (kernel memory or locked
 * user space pages).
 */
dma_cookie_t
dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
			void *src, size_t len)
{
	struct dma_device *dev = chan->device;
	struct dma_async_tx_descriptor *tx;
	dma_addr_t dma_dest, dma_src;
	dma_cookie_t cookie;
	int cpu;
	unsigned long flags;

	dma_src = dma_map_single(dev->dev, src, len, DMA_TO_DEVICE);
	dma_dest = dma_map_single(dev->dev, dest, len, DMA_FROM_DEVICE);
	flags = DMA_CTRL_ACK |
		DMA_COMPL_SRC_UNMAP_SINGLE |
		DMA_COMPL_DEST_UNMAP_SINGLE;
	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);

	if (!tx) {
		dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
		dma_unmap_single(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
		return -ENOMEM;
	}

	tx->callback = NULL;
	cookie = tx->tx_submit(tx);

	cpu = get_cpu();
	per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
	per_cpu_ptr(chan->local, cpu)->memcpy_count++;
	put_cpu();

	return cookie;
}
EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf);

/**
 * dma_async_memcpy_buf_to_pg - offloaded copy from address to page
 * @chan: DMA channel to offload copy to
 * @page: destination page
 * @offset: offset in page to copy to
 * @kdata: source address (virtual)
 * @len: length
 *
 * Both @page/@offset and @kdata must be mappable to a bus address according
 * to the DMA mapping API rules for streaming mappings.
 * Both @page/@offset and @kdata must stay memory resident (kernel memory or
 * locked user space pages)
 */
dma_cookie_t
dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
			unsigned int offset, void *kdata, size_t len)
{
	struct dma_device *dev = chan->device;
	struct dma_async_tx_descriptor *tx;
	dma_addr_t dma_dest, dma_src;
	dma_cookie_t cookie;
	int cpu;
	unsigned long flags;

	dma_src = dma_map_single(dev->dev, kdata, len, DMA_TO_DEVICE);
	dma_dest = dma_map_page(dev->dev, page, offset, len, DMA_FROM_DEVICE);
	flags = DMA_CTRL_ACK | DMA_COMPL_SRC_UNMAP_SINGLE;
	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);

	if (!tx) {
		dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
		dma_unmap_page(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
		return -ENOMEM;
	}

	tx->callback = NULL;
	cookie = tx->tx_submit(tx);

	cpu = get_cpu();
	per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
	per_cpu_ptr(chan->local, cpu)->memcpy_count++;
	put_cpu();

	return cookie;
}
EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg);

/**
 * dma_async_memcpy_pg_to_pg - offloaded copy from page to page
 * @chan: DMA channel to offload copy to
 * @dest_pg: destination page
 * @dest_off: offset in page to copy to
 * @src_pg: source page
 * @src_off: offset in page to copy from
 * @len: length
 *
 * Both @dest_page/@dest_off and @src_page/@src_off must be mappable to a bus
 * address according to the DMA mapping API rules for streaming mappings.
 * Both @dest_page/@dest_off and @src_page/@src_off must stay memory resident
 * (kernel memory or locked user space pages).
 */
dma_cookie_t
dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
	unsigned int dest_off, struct page *src_pg, unsigned int src_off,
	size_t len)
{
	struct dma_device *dev = chan->device;
	struct dma_async_tx_descriptor *tx;
	dma_addr_t dma_dest, dma_src;
	dma_cookie_t cookie;
	int cpu;
	unsigned long flags;

	dma_src = dma_map_page(dev->dev, src_pg, src_off, len, DMA_TO_DEVICE);
	dma_dest = dma_map_page(dev->dev, dest_pg, dest_off, len,
				DMA_FROM_DEVICE);
	flags = DMA_CTRL_ACK;
	tx = dev->device_prep_dma_memcpy(chan, dma_dest, dma_src, len, flags);

	if (!tx) {
		dma_unmap_page(dev->dev, dma_src, len, DMA_TO_DEVICE);
		dma_unmap_page(dev->dev, dma_dest, len, DMA_FROM_DEVICE);
		return -ENOMEM;
	}

	tx->callback = NULL;
	cookie = tx->tx_submit(tx);

	cpu = get_cpu();
	per_cpu_ptr(chan->local, cpu)->bytes_transferred += len;
	per_cpu_ptr(chan->local, cpu)->memcpy_count++;
	put_cpu();

	return cookie;
}
EXPORT_SYMBOL(dma_async_memcpy_pg_to_pg);

void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
	struct dma_chan *chan)
{
	tx->chan = chan;
	spin_lock_init(&tx->lock);
	INIT_LIST_HEAD(&tx->tx_list);
}
EXPORT_SYMBOL(dma_async_tx_descriptor_init);

/* dma_wait_for_async_tx - spin wait for a transaction to complete
 * @tx: in-flight transaction to wait on
 */
enum dma_status
dma_wait_for_async_tx(struct dma_async_tx_descriptor *tx)
{
	unsigned long dma_sync_wait_timeout = jiffies + msecs_to_jiffies(5000);

	if (!tx)
		return DMA_SUCCESS;

	while (tx->cookie == -EBUSY) {
		if (time_after_eq(jiffies, dma_sync_wait_timeout)) {
			pr_err("%s timeout waiting for descriptor submission\n",
				__func__);
			return DMA_ERROR;
		}
		cpu_relax();
	}
	return dma_sync_wait(tx->chan, tx->cookie);
}
EXPORT_SYMBOL_GPL(dma_wait_for_async_tx);

/* dma_run_dependencies - helper routine for dma drivers to process
 *	(start) dependent operations on their target channel
 * @tx: transaction with dependencies
 */
void dma_run_dependencies(struct dma_async_tx_descriptor *tx)
{
	struct dma_async_tx_descriptor *dep = tx->next;
	struct dma_async_tx_descriptor *dep_next;
	struct dma_chan *chan;

	if (!dep)
		return;

	/* we'll submit tx->next now, so clear the link */
	tx->next = NULL;
	chan = dep->chan;

	/* keep submitting up until a channel switch is detected
	 * in that case we will be called again as a result of
	 * processing the interrupt from async_tx_channel_switch
	 */
	for (; dep; dep = dep_next) {
		spin_lock_bh(&dep->lock);
		dep->parent = NULL;
		dep_next = dep->next;
		if (dep_next && dep_next->chan == chan)
			dep->next = NULL; /* ->next will be submitted */
		else
			dep_next = NULL; /* submit current dep and terminate */
		spin_unlock_bh(&dep->lock);

		dep->tx_submit(dep);
	}

	chan->device->device_issue_pending(chan);
}
EXPORT_SYMBOL_GPL(dma_run_dependencies);

static int __init dma_bus_init(void)
{
	idr_init(&dma_idr);
	mutex_init(&dma_list_mutex);
	return class_register(&dma_devclass);
}
arch_initcall(dma_bus_init);