aboutsummaryrefslogtreecommitdiff
path: root/drivers/dma/dmaengine.c
blob: 0cb259c59916ac0cadd4a3c3f7e5d4ae7fa2a1d8 (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
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
/*
 * 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.
 *
 * 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
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/platform_device.h>
#include <linux/dma-mapping.h>
#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>
#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/acpi_dma.h>
#include <linux/of_dma.h>
#include <linux/mempool.h>

static DEFINE_MUTEX(dma_list_mutex);
static DEFINE_IDR(dma_idr);
static LIST_HEAD(dma_device_list);
static long dmaengine_ref_count;

/* --- 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 memcpy_count_show(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 DEVICE_ATTR_RO(memcpy_count);

static ssize_t bytes_transferred_show(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 DEVICE_ATTR_RO(bytes_transferred);

static ssize_t in_use_show(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 DEVICE_ATTR_RO(in_use);

static struct attribute *dma_dev_attrs[] = {
	&dev_attr_memcpy_count.attr,
	&dev_attr_bytes_transferred.attr,
	&dev_attr_in_use.attr,
	NULL,
};
ATTRIBUTE_GROUPS(dma_dev);

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_groups	= dma_dev_groups,
	.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,
			    const 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)
{
	struct module *owner = dma_chan_to_owner(chan);
	int ret;

	/* The channel is already in use, update client count */
	if (chan->client_count) {
		__module_get(owner);
		goto out;
	}

	if (!try_module_get(owner))
		return -ENODEV;

	/* allocate upon first client reference */
	if (chan->device->device_alloc_chan_resources) {
		ret = chan->device->device_alloc_chan_resources(chan);
		if (ret < 0)
			goto err_out;
	}

	if (!dma_has_cap(DMA_PRIVATE, chan->device->cap_mask))
		balance_ref_count(chan);

out:
	chan->client_count++;
	return 0;

err_out:
	module_put(owner);
	return ret;
}

/**
 * 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)
{
	/* This channel is not in use, bail out */
	if (!chan->client_count)
		return;

	chan->client_count--;
	module_put(dma_chan_to_owner(chan));

	/* This channel is not in use anymore, free it */
	if (!chan->client_count && chan->device->device_free_chan_resources) {
		/* Make sure all operations have completed */
		dmaengine_synchronize(chan);
		chan->device->device_free_chan_resources(chan);
	}

	/* If the channel is used via a DMA request router, free the mapping */
	if (chan->router && chan->router->route_free) {
		chan->router->route_free(chan->router->dev, chan->route_data);
		chan->router = NULL;
		chan->route_data = NULL;
	}
}

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)) {
			pr_err("%s: timeout!\n", __func__);
			return DMA_ERROR;
		}
		if (status != DMA_IN_PROGRESS)
			break;
		cpu_relax();
	} while (1);

	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 __percpu *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("initialization failure\n");
		for_each_dma_cap_mask(cap, dma_cap_mask_all)
			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)
{
	return this_cpu_read(channel_table[tx_type]->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);

/**
 * dma_chan_is_local - returns true if the channel is in the same numa-node as the cpu
 */
static bool dma_chan_is_local(struct dma_chan *chan, int cpu)
{
	int node = dev_to_node(chan->device->dev);
	return node == -1 || cpumask_test_cpu(cpu, cpumask_of_node(node));
}

/**
 * min_chan - returns the channel with min count and in the same numa-node as the cpu
 * @cap: capability to match
 * @cpu: cpu index which the channel should be close to
 *
 * If some channels are close to the given cpu, the one with the lowest
 * reference count is returned. Otherwise, cpu is ignored and only the
 * reference count is taken into account.
 * Must be called under dma_list_mutex.
 */
static struct dma_chan *min_chan(enum dma_transaction_type cap, int cpu)
{
	struct dma_device *device;
	struct dma_chan *chan;
	struct dma_chan *min = NULL;
	struct dma_chan *localmin = 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 || chan->table_count < min->table_count)
				min = chan;

			if (dma_chan_is_local(chan, cpu))
				if (!localmin ||
				    chan->table_count < localmin->table_count)
					localmin = chan;
		}
	}

	chan = localmin ? localmin : min;

	if (chan)
		chan->table_count++;

	return chan;
}

/**
 * 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;

	/* 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 */
	for_each_dma_cap_mask(cap, dma_cap_mask_all)
		for_each_online_cpu(cpu) {
			chan = min_chan(cap, cpu);
			per_cpu_ptr(channel_table[cap], cpu)->chan = chan;
		}
}

int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps)
{
	struct dma_device *device;

	if (!chan || !caps)
		return -EINVAL;

	device = chan->device;

	/* check if the channel supports slave transactions */
	if (!test_bit(DMA_SLAVE, device->cap_mask.bits))
		return -ENXIO;

	/*
	 * Check whether it reports it uses the generic slave
	 * capabilities, if not, that means it doesn't support any
	 * kind of slave capabilities reporting.
	 */
	if (!device->directions)
		return -ENXIO;

	caps->src_addr_widths = device->src_addr_widths;
	caps->dst_addr_widths = device->dst_addr_widths;
	caps->directions = device->directions;
	caps->max_burst = device->max_burst;
	caps->residue_granularity = device->residue_granularity;
	caps->descriptor_reuse = device->descriptor_reuse;

	/*
	 * Some devices implement only pause (e.g. to get residuum) but no
	 * resume. However cmd_pause is advertised as pause AND resume.
	 */
	caps->cmd_pause = !!(device->device_pause && device->device_resume);
	caps->cmd_terminate = !!device->device_terminate_all;

	return 0;
}
EXPORT_SYMBOL_GPL(dma_get_slave_caps);

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

	if (mask && !__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;
}

static struct dma_chan *find_candidate(struct dma_device *device,
				       const dma_cap_mask_t *mask,
				       dma_filter_fn fn, void *fn_param)
{
	struct dma_chan *chan = private_candidate(mask, device, fn, fn_param);
	int err;

	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) {
			if (err == -ENODEV) {
				pr_debug("%s: %s module removed\n", __func__,
					 dma_chan_name(chan));
				list_del_rcu(&device->global_node);
			} else
				pr_debug("%s: failed to get %s: (%d)\n",
					 __func__, dma_chan_name(chan), err);

			if (--device->privatecnt == 0)
				dma_cap_clear(DMA_PRIVATE, device->cap_mask);

			chan = ERR_PTR(err);
		}
	}

	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
}

/**
 * dma_get_slave_channel - try to get specific channel exclusively
 * @chan: target channel
 */
struct dma_chan *dma_get_slave_channel(struct dma_chan *chan)
{
	int err = -EBUSY;

	/* lock against __dma_request_channel */
	mutex_lock(&dma_list_mutex);

	if (chan->client_count == 0) {
		struct dma_device *device = chan->device;

		dma_cap_set(DMA_PRIVATE, device->cap_mask);
		device->privatecnt++;
		err = dma_chan_get(chan);
		if (err) {
			pr_debug("%s: failed to get %s: (%d)\n",
				__func__, dma_chan_name(chan), err);
			chan = NULL;
			if (--device->privatecnt == 0)
				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
		}
	} else
		chan = NULL;

	mutex_unlock(&dma_list_mutex);


	return chan;
}
EXPORT_SYMBOL_GPL(dma_get_slave_channel);

struct dma_chan *dma_get_any_slave_channel(struct dma_device *device)
{
	dma_cap_mask_t mask;
	struct dma_chan *chan;

	dma_cap_zero(mask);
	dma_cap_set(DMA_SLAVE, mask);

	/* lock against __dma_request_channel */
	mutex_lock(&dma_list_mutex);

	chan = find_candidate(device, &mask, NULL, NULL);

	mutex_unlock(&dma_list_mutex);

	return IS_ERR(chan) ? NULL : chan;
}
EXPORT_SYMBOL_GPL(dma_get_any_slave_channel);

/**
 * __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
 *
 * Returns pointer to appropriate DMA channel on success or NULL.
 */
struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
				       dma_filter_fn fn, void *fn_param)
{
	struct dma_device *device, *_d;
	struct dma_chan *chan = NULL;

	/* Find a channel */
	mutex_lock(&dma_list_mutex);
	list_for_each_entry_safe(device, _d, &dma_device_list, global_node) {
		chan = find_candidate(device, mask, fn, fn_param);
		if (!IS_ERR(chan))
			break;

		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);

static const struct dma_slave_map *dma_filter_match(struct dma_device *device,
						    const char *name,
						    struct device *dev)
{
	int i;

	if (!device->filter.mapcnt)
		return NULL;

	for (i = 0; i < device->filter.mapcnt; i++) {
		const struct dma_slave_map *map = &device->filter.map[i];

		if (!strcmp(map->devname, dev_name(dev)) &&
		    !strcmp(map->slave, name))
			return map;
	}

	return NULL;
}

/**
 * dma_request_chan - try to allocate an exclusive slave channel
 * @dev:	pointer to client device structure
 * @name:	slave channel name
 *
 * Returns pointer to appropriate DMA channel on success or an error pointer.
 */
struct dma_chan *dma_request_chan(struct device *dev, const char *name)
{
	struct dma_device *d, *_d;
	struct dma_chan *chan = NULL;

	/* If device-tree is present get slave info from here */
	if (dev->of_node)
		chan = of_dma_request_slave_channel(dev->of_node, name);

	/* If device was enumerated by ACPI get slave info from here */
	if (has_acpi_companion(dev) && !chan)
		chan = acpi_dma_request_slave_chan_by_name(dev, name);

	if (chan) {
		/* Valid channel found or requester need to be deferred */
		if (!IS_ERR(chan) || PTR_ERR(chan) == -EPROBE_DEFER)
			return chan;
	}

	/* Try to find the channel via the DMA filter map(s) */
	mutex_lock(&dma_list_mutex);
	list_for_each_entry_safe(d, _d, &dma_device_list, global_node) {
		dma_cap_mask_t mask;
		const struct dma_slave_map *map = dma_filter_match(d, name, dev);

		if (!map)
			continue;

		dma_cap_zero(mask);
		dma_cap_set(DMA_SLAVE, mask);

		chan = find_candidate(d, &mask, d->filter.fn, map->param);
		if (!IS_ERR(chan))
			break;
	}
	mutex_unlock(&dma_list_mutex);

	return chan ? chan : ERR_PTR(-EPROBE_DEFER);
}
EXPORT_SYMBOL_GPL(dma_request_chan);

/**
 * dma_request_slave_channel - try to allocate an exclusive slave channel
 * @dev:	pointer to client device structure
 * @name:	slave channel name
 *
 * Returns pointer to appropriate DMA channel on success or NULL.
 */
struct dma_chan *dma_request_slave_channel(struct device *dev,
					   const char *name)
{
	struct dma_chan *ch = dma_request_chan(dev, name);
	if (IS_ERR(ch))
		return NULL;

	return ch;
}
EXPORT_SYMBOL_GPL(dma_request_slave_channel);

/**
 * dma_request_chan_by_mask - allocate a channel satisfying certain capabilities
 * @mask: capabilities that the channel must satisfy
 *
 * Returns pointer to appropriate DMA channel on success or an error pointer.
 */
struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask)
{
	struct dma_chan *chan;

	if (!mask)
		return ERR_PTR(-ENODEV);

	chan = __dma_request_channel(mask, NULL, NULL);
	if (!chan)
		chan = ERR_PTR(-ENODEV);

	return chan;
}
EXPORT_SYMBOL_GPL(dma_request_chan_by_mask);

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);
	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_debug("%s: failed to get %s: (%d)\n",
				       __func__, 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 bool device_has_all_tx_types(struct dma_device *device)
{
	/* A device that satisfies this test has channels that will never cause
	 * an async_tx channel switch event as all possible operation types can
	 * be handled.
	 */
	#ifdef CONFIG_ASYNC_TX_DMA
	if (!dma_has_cap(DMA_INTERRUPT, device->cap_mask))
		return false;
	#endif

	#if defined(CONFIG_ASYNC_MEMCPY) || defined(CONFIG_ASYNC_MEMCPY_MODULE)
	if (!dma_has_cap(DMA_MEMCPY, device->cap_mask))
		return false;
	#endif

	#if defined(CONFIG_ASYNC_XOR) || defined(CONFIG_ASYNC_XOR_MODULE)
	if (!dma_has_cap(DMA_XOR, device->cap_mask))
		return false;

	#ifndef CONFIG_ASYNC_TX_DISABLE_XOR_VAL_DMA
	if (!dma_has_cap(DMA_XOR_VAL, device->cap_mask))
		return false;
	#endif
	#endif

	#if defined(CONFIG_ASYNC_PQ) || defined(CONFIG_ASYNC_PQ_MODULE)
	if (!dma_has_cap(DMA_PQ, device->cap_mask))
		return false;

	#ifndef CONFIG_ASYNC_TX_DISABLE_PQ_VAL_DMA
	if (!dma_has_cap(DMA_PQ_VAL, device->cap_mask))
		return false;
	#endif
	#endif

	return true;
}

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

	mutex_lock(&dma_list_mutex);

	rc = idr_alloc(&dma_idr, NULL, 0, 0, GFP_KERNEL);
	if (rc >= 0)
		device->dev_id = rc;

	mutex_unlock(&dma_list_mutex);
	return rc < 0 ? rc : 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_SG, device->cap_mask) &&
		!device->device_prep_dma_sg);
	BUG_ON(dma_has_cap(DMA_CYCLIC, device->cap_mask) &&
		!device->device_prep_dma_cyclic);
	BUG_ON(dma_has_cap(DMA_INTERLEAVE, device->cap_mask) &&
		!device->device_prep_interleaved_dma);

	BUG_ON(!device->device_tx_status);
	BUG_ON(!device->device_issue_pending);
	BUG_ON(!device->dev);

	/* note: this only matters in the
	 * CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH=n case
	 */
	if (device_has_all_tx_types(device))
		dma_cap_set(DMA_ASYNC_TX, device->cap_mask);

	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);
		free_percpu(chan->local);
	}
}
EXPORT_SYMBOL(dma_async_device_unregister);

struct dmaengine_unmap_pool {
	struct kmem_cache *cache;
	const char *name;
	mempool_t *pool;
	size_t size;
};

#define __UNMAP_POOL(x) { .size = x, .name = "dmaengine-unmap-" __stringify(x) }
static struct dmaengine_unmap_pool unmap_pool[] = {
	__UNMAP_POOL(2),
	#if IS_ENABLED(CONFIG_DMA_ENGINE_RAID)
	__UNMAP_POOL(16),
	__UNMAP_POOL(128),
	__UNMAP_POOL(256),
	#endif
};

static struct dmaengine_unmap_pool *__get_unmap_pool(int nr)
{
	int order = get_count_order(nr);

	switch (order) {
	case 0 ... 1:
		return &unmap_pool[0];
	case 2 ... 4:
		return &unmap_pool[1];
	case 5 ... 7:
		return &unmap_pool[2];
	case 8:
		return &unmap_pool[3];
	default:
		BUG();
		return NULL;
	}
}

static void dmaengine_unmap(struct kref *kref)
{
	struct dmaengine_unmap_data *unmap = container_of(kref, typeof(*unmap), kref);
	struct device *dev = unmap->dev;
	int cnt, i;

	cnt = unmap->to_cnt;
	for (i = 0; i < cnt; i++)
		dma_unmap_page(dev, unmap->addr[i], unmap->len,
			       DMA_TO_DEVICE);
	cnt += unmap->from_cnt;
	for (; i < cnt; i++)
		dma_unmap_page(dev, unmap->addr[i], unmap->len,
			       DMA_FROM_DEVICE);
	cnt += unmap->bidi_cnt;
	for (; i < cnt; i++) {
		if (unmap->addr[i] == 0)
			continue;
		dma_unmap_page(dev, unmap->addr[i], unmap->len,
			       DMA_BIDIRECTIONAL);
	}
	cnt = unmap->map_cnt;
	mempool_free(unmap, __get_unmap_pool(cnt)->pool);
}

void dmaengine_unmap_put(struct dmaengine_unmap_data *unmap)
{
	if (unmap)
		kref_put(&unmap->kref, dmaengine_unmap);
}
EXPORT_SYMBOL_GPL(dmaengine_unmap_put);

static void dmaengine_destroy_unmap_pool(void)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
		struct dmaengine_unmap_pool *p = &unmap_pool[i];

		mempool_destroy(p->pool);
		p->pool = NULL;
		kmem_cache_destroy(p->cache);
		p->cache = NULL;
	}
}

static int __init dmaengine_init_unmap_pool(void)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(unmap_pool); i++) {
		struct dmaengine_unmap_pool *p = &unmap_pool[i];
		size_t size;

		size = sizeof(struct dmaengine_unmap_data) +
		       sizeof(dma_addr_t) * p->size;

		p->cache = kmem_cache_create(p->name, size, 0,
					     SLAB_HWCACHE_ALIGN, NULL);
		if (!p->cache)
			break;
		p->pool = mempool_create_slab_pool(1, p->cache);
		if (!p->pool)
			break;
	}

	if (i == ARRAY_SIZE(unmap_pool))
		return 0;

	dmaengine_destroy_unmap_pool();
	return -ENOMEM;
}

struct dmaengine_unmap_data *
dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
{
	struct dmaengine_unmap_data *unmap;

	unmap = mempool_alloc(__get_unmap_pool(nr)->pool, flags);
	if (!unmap)
		return NULL;

	memset(unmap, 0, sizeof(*unmap));
	kref_init(&unmap->kref);
	unmap->dev = dev;
	unmap->map_cnt = nr;

	return unmap;
}
EXPORT_SYMBOL(dmaengine_get_unmap_data);

void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
	struct dma_chan *chan)
{
	tx->chan = chan;
	#ifdef CONFIG_ASYNC_TX_ENABLE_CHANNEL_SWITCH
	spin_lock_init(&tx->lock);
	#endif
}
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_COMPLETE;

	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 = txd_next(tx);
	struct dma_async_tx_descriptor *dep_next;
	struct dma_chan *chan;

	if (!dep)
		return;

	/* we'll submit tx->next now, so clear the link */
	txd_clear_next(tx);
	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) {
		txd_lock(dep);
		txd_clear_parent(dep);
		dep_next = txd_next(dep);
		if (dep_next && dep_next->chan == chan)
			txd_clear_next(dep); /* ->next will be submitted */
		else
			dep_next = NULL; /* submit current dep and terminate */
		txd_unlock(dep);

		dep->tx_submit(dep);
	}

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

static int __init dma_bus_init(void)
{
	int err = dmaengine_init_unmap_pool();

	if (err)
		return err;
	return class_register(&dma_devclass);
}
arch_initcall(dma_bus_init);