aboutsummaryrefslogtreecommitdiff
path: root/drivers/dma/shdma.c
blob: 85ffd5e38c5031690ea125cf5341fa70591bfa58 (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
/*
 * Renesas SuperH DMA Engine support
 *
 * base is drivers/dma/flsdma.c
 *
 * Copyright (C) 2009 Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>
 * Copyright (C) 2009 Renesas Solutions, Inc. All rights reserved.
 * Copyright (C) 2007 Freescale Semiconductor, Inc. All rights reserved.
 *
 * This 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.
 *
 * - DMA of SuperH does not have Hardware DMA chain mode.
 * - MAX DMA size is 16MB.
 *
 */

#include <linux/init.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/dmaengine.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/sh_dma.h>

#include "shdma.h"

/* DMA descriptor control */
enum sh_dmae_desc_status {
	DESC_IDLE,
	DESC_PREPARED,
	DESC_SUBMITTED,
	DESC_COMPLETED,	/* completed, have to call callback */
	DESC_WAITING,	/* callback called, waiting for ack / re-submit */
};

#define NR_DESCS_PER_CHANNEL 32
/* Default MEMCPY transfer size = 2^2 = 4 bytes */
#define LOG2_DEFAULT_XFER_SIZE	2

/* A bitmask with bits enough for enum sh_dmae_slave_chan_id */
static unsigned long sh_dmae_slave_used[BITS_TO_LONGS(SH_DMA_SLAVE_NUMBER)];

static void sh_dmae_chan_ld_cleanup(struct sh_dmae_chan *sh_chan, bool all);

static void sh_dmae_writel(struct sh_dmae_chan *sh_dc, u32 data, u32 reg)
{
	__raw_writel(data, sh_dc->base + reg / sizeof(u32));
}

static u32 sh_dmae_readl(struct sh_dmae_chan *sh_dc, u32 reg)
{
	return __raw_readl(sh_dc->base + reg / sizeof(u32));
}

static u16 dmaor_read(struct sh_dmae_device *shdev)
{
	return __raw_readw(shdev->chan_reg + DMAOR / sizeof(u32));
}

static void dmaor_write(struct sh_dmae_device *shdev, u16 data)
{
	__raw_writew(data, shdev->chan_reg + DMAOR / sizeof(u32));
}

/*
 * Reset DMA controller
 *
 * SH7780 has two DMAOR register
 */
static void sh_dmae_ctl_stop(struct sh_dmae_device *shdev)
{
	unsigned short dmaor = dmaor_read(shdev);

	dmaor_write(shdev, dmaor & ~(DMAOR_NMIF | DMAOR_AE | DMAOR_DME));
}

static int sh_dmae_rst(struct sh_dmae_device *shdev)
{
	unsigned short dmaor;

	sh_dmae_ctl_stop(shdev);
	dmaor = dmaor_read(shdev) | shdev->pdata->dmaor_init;

	dmaor_write(shdev, dmaor);
	if (dmaor_read(shdev) & (DMAOR_AE | DMAOR_NMIF)) {
		pr_warning("dma-sh: Can't initialize DMAOR.\n");
		return -EINVAL;
	}
	return 0;
}

static bool dmae_is_busy(struct sh_dmae_chan *sh_chan)
{
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);

	if ((chcr & (CHCR_DE | CHCR_TE)) == CHCR_DE)
		return true; /* working */

	return false; /* waiting */
}

static unsigned int calc_xmit_shift(struct sh_dmae_chan *sh_chan, u32 chcr)
{
	struct sh_dmae_device *shdev = container_of(sh_chan->common.device,
						struct sh_dmae_device, common);
	struct sh_dmae_pdata *pdata = shdev->pdata;
	int cnt = ((chcr & pdata->ts_low_mask) >> pdata->ts_low_shift) |
		((chcr & pdata->ts_high_mask) >> pdata->ts_high_shift);

	if (cnt >= pdata->ts_shift_num)
		cnt = 0;

	return pdata->ts_shift[cnt];
}

static u32 log2size_to_chcr(struct sh_dmae_chan *sh_chan, int l2size)
{
	struct sh_dmae_device *shdev = container_of(sh_chan->common.device,
						struct sh_dmae_device, common);
	struct sh_dmae_pdata *pdata = shdev->pdata;
	int i;

	for (i = 0; i < pdata->ts_shift_num; i++)
		if (pdata->ts_shift[i] == l2size)
			break;

	if (i == pdata->ts_shift_num)
		i = 0;

	return ((i << pdata->ts_low_shift) & pdata->ts_low_mask) |
		((i << pdata->ts_high_shift) & pdata->ts_high_mask);
}

static void dmae_set_reg(struct sh_dmae_chan *sh_chan, struct sh_dmae_regs *hw)
{
	sh_dmae_writel(sh_chan, hw->sar, SAR);
	sh_dmae_writel(sh_chan, hw->dar, DAR);
	sh_dmae_writel(sh_chan, hw->tcr >> sh_chan->xmit_shift, TCR);
}

static void dmae_start(struct sh_dmae_chan *sh_chan)
{
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);

	chcr |= CHCR_DE | CHCR_IE;
	sh_dmae_writel(sh_chan, chcr & ~CHCR_TE, CHCR);
}

static void dmae_halt(struct sh_dmae_chan *sh_chan)
{
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);

	chcr &= ~(CHCR_DE | CHCR_TE | CHCR_IE);
	sh_dmae_writel(sh_chan, chcr, CHCR);
}

static void dmae_init(struct sh_dmae_chan *sh_chan)
{
	/*
	 * Default configuration for dual address memory-memory transfer.
	 * 0x400 represents auto-request.
	 */
	u32 chcr = DM_INC | SM_INC | 0x400 | log2size_to_chcr(sh_chan,
						   LOG2_DEFAULT_XFER_SIZE);
	sh_chan->xmit_shift = calc_xmit_shift(sh_chan, chcr);
	sh_dmae_writel(sh_chan, chcr, CHCR);
}

static int dmae_set_chcr(struct sh_dmae_chan *sh_chan, u32 val)
{
	/* When DMA was working, can not set data to CHCR */
	if (dmae_is_busy(sh_chan))
		return -EBUSY;

	sh_chan->xmit_shift = calc_xmit_shift(sh_chan, val);
	sh_dmae_writel(sh_chan, val, CHCR);

	return 0;
}

static int dmae_set_dmars(struct sh_dmae_chan *sh_chan, u16 val)
{
	struct sh_dmae_device *shdev = container_of(sh_chan->common.device,
						struct sh_dmae_device, common);
	struct sh_dmae_pdata *pdata = shdev->pdata;
	const struct sh_dmae_channel *chan_pdata = &pdata->channel[sh_chan->id];
	u16 __iomem *addr = shdev->dmars + chan_pdata->dmars / sizeof(u16);
	int shift = chan_pdata->dmars_bit;

	if (dmae_is_busy(sh_chan))
		return -EBUSY;

	__raw_writew((__raw_readw(addr) & (0xff00 >> shift)) | (val << shift),
		     addr);

	return 0;
}

static dma_cookie_t sh_dmae_tx_submit(struct dma_async_tx_descriptor *tx)
{
	struct sh_desc *desc = tx_to_sh_desc(tx), *chunk, *last = desc, *c;
	struct sh_dmae_chan *sh_chan = to_sh_chan(tx->chan);
	dma_async_tx_callback callback = tx->callback;
	dma_cookie_t cookie;

	spin_lock_bh(&sh_chan->desc_lock);

	cookie = sh_chan->common.cookie;
	cookie++;
	if (cookie < 0)
		cookie = 1;

	sh_chan->common.cookie = cookie;
	tx->cookie = cookie;

	/* Mark all chunks of this descriptor as submitted, move to the queue */
	list_for_each_entry_safe(chunk, c, desc->node.prev, node) {
		/*
		 * All chunks are on the global ld_free, so, we have to find
		 * the end of the chain ourselves
		 */
		if (chunk != desc && (chunk->mark == DESC_IDLE ||
				      chunk->async_tx.cookie > 0 ||
				      chunk->async_tx.cookie == -EBUSY ||
				      &chunk->node == &sh_chan->ld_free))
			break;
		chunk->mark = DESC_SUBMITTED;
		/* Callback goes to the last chunk */
		chunk->async_tx.callback = NULL;
		chunk->cookie = cookie;
		list_move_tail(&chunk->node, &sh_chan->ld_queue);
		last = chunk;
	}

	last->async_tx.callback = callback;
	last->async_tx.callback_param = tx->callback_param;

	dev_dbg(sh_chan->dev, "submit #%d@%p on %d: %x[%d] -> %x\n",
		tx->cookie, &last->async_tx, sh_chan->id,
		desc->hw.sar, desc->hw.tcr, desc->hw.dar);

	spin_unlock_bh(&sh_chan->desc_lock);

	return cookie;
}

/* Called with desc_lock held */
static struct sh_desc *sh_dmae_get_desc(struct sh_dmae_chan *sh_chan)
{
	struct sh_desc *desc;

	list_for_each_entry(desc, &sh_chan->ld_free, node)
		if (desc->mark != DESC_PREPARED) {
			BUG_ON(desc->mark != DESC_IDLE);
			list_del(&desc->node);
			return desc;
		}

	return NULL;
}

static const struct sh_dmae_slave_config *sh_dmae_find_slave(
	struct sh_dmae_chan *sh_chan, struct sh_dmae_slave *param)
{
	struct dma_device *dma_dev = sh_chan->common.device;
	struct sh_dmae_device *shdev = container_of(dma_dev,
					struct sh_dmae_device, common);
	struct sh_dmae_pdata *pdata = shdev->pdata;
	int i;

	if (param->slave_id >= SH_DMA_SLAVE_NUMBER)
		return NULL;

	for (i = 0; i < pdata->slave_num; i++)
		if (pdata->slave[i].slave_id == param->slave_id)
			return pdata->slave + i;

	return NULL;
}

static int sh_dmae_alloc_chan_resources(struct dma_chan *chan)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	struct sh_desc *desc;
	struct sh_dmae_slave *param = chan->private;
	int ret;

	pm_runtime_get_sync(sh_chan->dev);

	/*
	 * This relies on the guarantee from dmaengine that alloc_chan_resources
	 * never runs concurrently with itself or free_chan_resources.
	 */
	if (param) {
		const struct sh_dmae_slave_config *cfg;

		cfg = sh_dmae_find_slave(sh_chan, param);
		if (!cfg) {
			ret = -EINVAL;
			goto efindslave;
		}

		if (test_and_set_bit(param->slave_id, sh_dmae_slave_used)) {
			ret = -EBUSY;
			goto etestused;
		}

		param->config = cfg;

		dmae_set_dmars(sh_chan, cfg->mid_rid);
		dmae_set_chcr(sh_chan, cfg->chcr);
	} else if ((sh_dmae_readl(sh_chan, CHCR) & 0xf00) != 0x400) {
		dmae_init(sh_chan);
	}

	spin_lock_bh(&sh_chan->desc_lock);
	while (sh_chan->descs_allocated < NR_DESCS_PER_CHANNEL) {
		spin_unlock_bh(&sh_chan->desc_lock);
		desc = kzalloc(sizeof(struct sh_desc), GFP_KERNEL);
		if (!desc) {
			spin_lock_bh(&sh_chan->desc_lock);
			break;
		}
		dma_async_tx_descriptor_init(&desc->async_tx,
					&sh_chan->common);
		desc->async_tx.tx_submit = sh_dmae_tx_submit;
		desc->mark = DESC_IDLE;

		spin_lock_bh(&sh_chan->desc_lock);
		list_add(&desc->node, &sh_chan->ld_free);
		sh_chan->descs_allocated++;
	}
	spin_unlock_bh(&sh_chan->desc_lock);

	if (!sh_chan->descs_allocated) {
		ret = -ENOMEM;
		goto edescalloc;
	}

	return sh_chan->descs_allocated;

edescalloc:
	if (param)
		clear_bit(param->slave_id, sh_dmae_slave_used);
etestused:
efindslave:
	pm_runtime_put(sh_chan->dev);
	return ret;
}

/*
 * sh_dma_free_chan_resources - Free all resources of the channel.
 */
static void sh_dmae_free_chan_resources(struct dma_chan *chan)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	struct sh_desc *desc, *_desc;
	LIST_HEAD(list);
	int descs = sh_chan->descs_allocated;

	dmae_halt(sh_chan);

	/* Prepared and not submitted descriptors can still be on the queue */
	if (!list_empty(&sh_chan->ld_queue))
		sh_dmae_chan_ld_cleanup(sh_chan, true);

	if (chan->private) {
		/* The caller is holding dma_list_mutex */
		struct sh_dmae_slave *param = chan->private;
		clear_bit(param->slave_id, sh_dmae_slave_used);
	}

	spin_lock_bh(&sh_chan->desc_lock);

	list_splice_init(&sh_chan->ld_free, &list);
	sh_chan->descs_allocated = 0;

	spin_unlock_bh(&sh_chan->desc_lock);

	if (descs > 0)
		pm_runtime_put(sh_chan->dev);

	list_for_each_entry_safe(desc, _desc, &list, node)
		kfree(desc);
}

/**
 * sh_dmae_add_desc - get, set up and return one transfer descriptor
 * @sh_chan:	DMA channel
 * @flags:	DMA transfer flags
 * @dest:	destination DMA address, incremented when direction equals
 *		DMA_FROM_DEVICE or DMA_BIDIRECTIONAL
 * @src:	source DMA address, incremented when direction equals
 *		DMA_TO_DEVICE or DMA_BIDIRECTIONAL
 * @len:	DMA transfer length
 * @first:	if NULL, set to the current descriptor and cookie set to -EBUSY
 * @direction:	needed for slave DMA to decide which address to keep constant,
 *		equals DMA_BIDIRECTIONAL for MEMCPY
 * Returns 0 or an error
 * Locks: called with desc_lock held
 */
static struct sh_desc *sh_dmae_add_desc(struct sh_dmae_chan *sh_chan,
	unsigned long flags, dma_addr_t *dest, dma_addr_t *src, size_t *len,
	struct sh_desc **first, enum dma_data_direction direction)
{
	struct sh_desc *new;
	size_t copy_size;

	if (!*len)
		return NULL;

	/* Allocate the link descriptor from the free list */
	new = sh_dmae_get_desc(sh_chan);
	if (!new) {
		dev_err(sh_chan->dev, "No free link descriptor available\n");
		return NULL;
	}

	copy_size = min(*len, (size_t)SH_DMA_TCR_MAX + 1);

	new->hw.sar = *src;
	new->hw.dar = *dest;
	new->hw.tcr = copy_size;

	if (!*first) {
		/* First desc */
		new->async_tx.cookie = -EBUSY;
		*first = new;
	} else {
		/* Other desc - invisible to the user */
		new->async_tx.cookie = -EINVAL;
	}

	dev_dbg(sh_chan->dev,
		"chaining (%u/%u)@%x -> %x with %p, cookie %d, shift %d\n",
		copy_size, *len, *src, *dest, &new->async_tx,
		new->async_tx.cookie, sh_chan->xmit_shift);

	new->mark = DESC_PREPARED;
	new->async_tx.flags = flags;
	new->direction = direction;

	*len -= copy_size;
	if (direction == DMA_BIDIRECTIONAL || direction == DMA_TO_DEVICE)
		*src += copy_size;
	if (direction == DMA_BIDIRECTIONAL || direction == DMA_FROM_DEVICE)
		*dest += copy_size;

	return new;
}

/*
 * sh_dmae_prep_sg - prepare transfer descriptors from an SG list
 *
 * Common routine for public (MEMCPY) and slave DMA. The MEMCPY case is also
 * converted to scatter-gather to guarantee consistent locking and a correct
 * list manipulation. For slave DMA direction carries the usual meaning, and,
 * logically, the SG list is RAM and the addr variable contains slave address,
 * e.g., the FIFO I/O register. For MEMCPY direction equals DMA_BIDIRECTIONAL
 * and the SG list contains only one element and points at the source buffer.
 */
static struct dma_async_tx_descriptor *sh_dmae_prep_sg(struct sh_dmae_chan *sh_chan,
	struct scatterlist *sgl, unsigned int sg_len, dma_addr_t *addr,
	enum dma_data_direction direction, unsigned long flags)
{
	struct scatterlist *sg;
	struct sh_desc *first = NULL, *new = NULL /* compiler... */;
	LIST_HEAD(tx_list);
	int chunks = 0;
	int i;

	if (!sg_len)
		return NULL;

	for_each_sg(sgl, sg, sg_len, i)
		chunks += (sg_dma_len(sg) + SH_DMA_TCR_MAX) /
			(SH_DMA_TCR_MAX + 1);

	/* Have to lock the whole loop to protect against concurrent release */
	spin_lock_bh(&sh_chan->desc_lock);

	/*
	 * Chaining:
	 * first descriptor is what user is dealing with in all API calls, its
	 *	cookie is at first set to -EBUSY, at tx-submit to a positive
	 *	number
	 * if more than one chunk is needed further chunks have cookie = -EINVAL
	 * the last chunk, if not equal to the first, has cookie = -ENOSPC
	 * all chunks are linked onto the tx_list head with their .node heads
	 *	only during this function, then they are immediately spliced
	 *	back onto the free list in form of a chain
	 */
	for_each_sg(sgl, sg, sg_len, i) {
		dma_addr_t sg_addr = sg_dma_address(sg);
		size_t len = sg_dma_len(sg);

		if (!len)
			goto err_get_desc;

		do {
			dev_dbg(sh_chan->dev, "Add SG #%d@%p[%d], dma %llx\n",
				i, sg, len, (unsigned long long)sg_addr);

			if (direction == DMA_FROM_DEVICE)
				new = sh_dmae_add_desc(sh_chan, flags,
						&sg_addr, addr, &len, &first,
						direction);
			else
				new = sh_dmae_add_desc(sh_chan, flags,
						addr, &sg_addr, &len, &first,
						direction);
			if (!new)
				goto err_get_desc;

			new->chunks = chunks--;
			list_add_tail(&new->node, &tx_list);
		} while (len);
	}

	if (new != first)
		new->async_tx.cookie = -ENOSPC;

	/* Put them back on the free list, so, they don't get lost */
	list_splice_tail(&tx_list, &sh_chan->ld_free);

	spin_unlock_bh(&sh_chan->desc_lock);

	return &first->async_tx;

err_get_desc:
	list_for_each_entry(new, &tx_list, node)
		new->mark = DESC_IDLE;
	list_splice(&tx_list, &sh_chan->ld_free);

	spin_unlock_bh(&sh_chan->desc_lock);

	return NULL;
}

static struct dma_async_tx_descriptor *sh_dmae_prep_memcpy(
	struct dma_chan *chan, dma_addr_t dma_dest, dma_addr_t dma_src,
	size_t len, unsigned long flags)
{
	struct sh_dmae_chan *sh_chan;
	struct scatterlist sg;

	if (!chan || !len)
		return NULL;

	chan->private = NULL;

	sh_chan = to_sh_chan(chan);

	sg_init_table(&sg, 1);
	sg_set_page(&sg, pfn_to_page(PFN_DOWN(dma_src)), len,
		    offset_in_page(dma_src));
	sg_dma_address(&sg) = dma_src;
	sg_dma_len(&sg) = len;

	return sh_dmae_prep_sg(sh_chan, &sg, 1, &dma_dest, DMA_BIDIRECTIONAL,
			       flags);
}

static struct dma_async_tx_descriptor *sh_dmae_prep_slave_sg(
	struct dma_chan *chan, struct scatterlist *sgl, unsigned int sg_len,
	enum dma_data_direction direction, unsigned long flags)
{
	struct sh_dmae_slave *param;
	struct sh_dmae_chan *sh_chan;
	dma_addr_t slave_addr;

	if (!chan)
		return NULL;

	sh_chan = to_sh_chan(chan);
	param = chan->private;

	/* Someone calling slave DMA on a public channel? */
	if (!param || !sg_len) {
		dev_warn(sh_chan->dev, "%s: bad parameter: %p, %d, %d\n",
			 __func__, param, sg_len, param ? param->slave_id : -1);
		return NULL;
	}

	slave_addr = param->config->addr;

	/*
	 * if (param != NULL), this is a successfully requested slave channel,
	 * therefore param->config != NULL too.
	 */
	return sh_dmae_prep_sg(sh_chan, sgl, sg_len, &slave_addr,
			       direction, flags);
}

static int sh_dmae_control(struct dma_chan *chan, enum dma_ctrl_cmd cmd,
			   unsigned long arg)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);

	/* Only supports DMA_TERMINATE_ALL */
	if (cmd != DMA_TERMINATE_ALL)
		return -ENXIO;

	if (!chan)
		return -EINVAL;

	dmae_halt(sh_chan);

	spin_lock_bh(&sh_chan->desc_lock);
	if (!list_empty(&sh_chan->ld_queue)) {
		/* Record partial transfer */
		struct sh_desc *desc = list_entry(sh_chan->ld_queue.next,
						  struct sh_desc, node);
		desc->partial = (desc->hw.tcr - sh_dmae_readl(sh_chan, TCR)) <<
			sh_chan->xmit_shift;

	}
	spin_unlock_bh(&sh_chan->desc_lock);

	sh_dmae_chan_ld_cleanup(sh_chan, true);

	return 0;
}

static dma_async_tx_callback __ld_cleanup(struct sh_dmae_chan *sh_chan, bool all)
{
	struct sh_desc *desc, *_desc;
	/* Is the "exposed" head of a chain acked? */
	bool head_acked = false;
	dma_cookie_t cookie = 0;
	dma_async_tx_callback callback = NULL;
	void *param = NULL;

	spin_lock_bh(&sh_chan->desc_lock);
	list_for_each_entry_safe(desc, _desc, &sh_chan->ld_queue, node) {
		struct dma_async_tx_descriptor *tx = &desc->async_tx;

		BUG_ON(tx->cookie > 0 && tx->cookie != desc->cookie);
		BUG_ON(desc->mark != DESC_SUBMITTED &&
		       desc->mark != DESC_COMPLETED &&
		       desc->mark != DESC_WAITING);

		/*
		 * queue is ordered, and we use this loop to (1) clean up all
		 * completed descriptors, and to (2) update descriptor flags of
		 * any chunks in a (partially) completed chain
		 */
		if (!all && desc->mark == DESC_SUBMITTED &&
		    desc->cookie != cookie)
			break;

		if (tx->cookie > 0)
			cookie = tx->cookie;

		if (desc->mark == DESC_COMPLETED && desc->chunks == 1) {
			if (sh_chan->completed_cookie != desc->cookie - 1)
				dev_dbg(sh_chan->dev,
					"Completing cookie %d, expected %d\n",
					desc->cookie,
					sh_chan->completed_cookie + 1);
			sh_chan->completed_cookie = desc->cookie;
		}

		/* Call callback on the last chunk */
		if (desc->mark == DESC_COMPLETED && tx->callback) {
			desc->mark = DESC_WAITING;
			callback = tx->callback;
			param = tx->callback_param;
			dev_dbg(sh_chan->dev, "descriptor #%d@%p on %d callback\n",
				tx->cookie, tx, sh_chan->id);
			BUG_ON(desc->chunks != 1);
			break;
		}

		if (tx->cookie > 0 || tx->cookie == -EBUSY) {
			if (desc->mark == DESC_COMPLETED) {
				BUG_ON(tx->cookie < 0);
				desc->mark = DESC_WAITING;
			}
			head_acked = async_tx_test_ack(tx);
		} else {
			switch (desc->mark) {
			case DESC_COMPLETED:
				desc->mark = DESC_WAITING;
				/* Fall through */
			case DESC_WAITING:
				if (head_acked)
					async_tx_ack(&desc->async_tx);
			}
		}

		dev_dbg(sh_chan->dev, "descriptor %p #%d completed.\n",
			tx, tx->cookie);

		if (((desc->mark == DESC_COMPLETED ||
		      desc->mark == DESC_WAITING) &&
		     async_tx_test_ack(&desc->async_tx)) || all) {
			/* Remove from ld_queue list */
			desc->mark = DESC_IDLE;
			list_move(&desc->node, &sh_chan->ld_free);
		}
	}
	spin_unlock_bh(&sh_chan->desc_lock);

	if (callback)
		callback(param);

	return callback;
}

/*
 * sh_chan_ld_cleanup - Clean up link descriptors
 *
 * This function cleans up the ld_queue of DMA channel.
 */
static void sh_dmae_chan_ld_cleanup(struct sh_dmae_chan *sh_chan, bool all)
{
	while (__ld_cleanup(sh_chan, all))
		;

	if (all)
		/* Terminating - forgive uncompleted cookies */
		sh_chan->completed_cookie = sh_chan->common.cookie;
}

static void sh_chan_xfer_ld_queue(struct sh_dmae_chan *sh_chan)
{
	struct sh_desc *desc;

	spin_lock_bh(&sh_chan->desc_lock);
	/* DMA work check */
	if (dmae_is_busy(sh_chan)) {
		spin_unlock_bh(&sh_chan->desc_lock);
		return;
	}

	/* Find the first not transferred desciptor */
	list_for_each_entry(desc, &sh_chan->ld_queue, node)
		if (desc->mark == DESC_SUBMITTED) {
			dev_dbg(sh_chan->dev, "Queue #%d to %d: %u@%x -> %x\n",
				desc->async_tx.cookie, sh_chan->id,
				desc->hw.tcr, desc->hw.sar, desc->hw.dar);
			/* Get the ld start address from ld_queue */
			dmae_set_reg(sh_chan, &desc->hw);
			dmae_start(sh_chan);
			break;
		}

	spin_unlock_bh(&sh_chan->desc_lock);
}

static void sh_dmae_memcpy_issue_pending(struct dma_chan *chan)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	sh_chan_xfer_ld_queue(sh_chan);
}

static enum dma_status sh_dmae_tx_status(struct dma_chan *chan,
					dma_cookie_t cookie,
					struct dma_tx_state *txstate)
{
	struct sh_dmae_chan *sh_chan = to_sh_chan(chan);
	dma_cookie_t last_used;
	dma_cookie_t last_complete;
	enum dma_status status;

	sh_dmae_chan_ld_cleanup(sh_chan, false);

	last_used = chan->cookie;
	last_complete = sh_chan->completed_cookie;
	BUG_ON(last_complete < 0);
	dma_set_tx_state(txstate, last_complete, last_used, 0);

	spin_lock_bh(&sh_chan->desc_lock);

	status = dma_async_is_complete(cookie, last_complete, last_used);

	/*
	 * If we don't find cookie on the queue, it has been aborted and we have
	 * to report error
	 */
	if (status != DMA_SUCCESS) {
		struct sh_desc *desc;
		status = DMA_ERROR;
		list_for_each_entry(desc, &sh_chan->ld_queue, node)
			if (desc->cookie == cookie) {
				status = DMA_IN_PROGRESS;
				break;
			}
	}

	spin_unlock_bh(&sh_chan->desc_lock);

	return status;
}

static irqreturn_t sh_dmae_interrupt(int irq, void *data)
{
	irqreturn_t ret = IRQ_NONE;
	struct sh_dmae_chan *sh_chan = (struct sh_dmae_chan *)data;
	u32 chcr = sh_dmae_readl(sh_chan, CHCR);

	if (chcr & CHCR_TE) {
		/* DMA stop */
		dmae_halt(sh_chan);

		ret = IRQ_HANDLED;
		tasklet_schedule(&sh_chan->tasklet);
	}

	return ret;
}

#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
static irqreturn_t sh_dmae_err(int irq, void *data)
{
	struct sh_dmae_device *shdev = (struct sh_dmae_device *)data;
	int i;

	/* halt the dma controller */
	sh_dmae_ctl_stop(shdev);

	/* We cannot detect, which channel caused the error, have to reset all */
	for (i = 0; i < SH_DMAC_MAX_CHANNELS; i++) {
		struct sh_dmae_chan *sh_chan = shdev->chan[i];
		if (sh_chan) {
			struct sh_desc *desc;
			/* Stop the channel */
			dmae_halt(sh_chan);
			/* Complete all  */
			list_for_each_entry(desc, &sh_chan->ld_queue, node) {
				struct dma_async_tx_descriptor *tx = &desc->async_tx;
				desc->mark = DESC_IDLE;
				if (tx->callback)
					tx->callback(tx->callback_param);
			}
			list_splice_init(&sh_chan->ld_queue, &sh_chan->ld_free);
		}
	}
	sh_dmae_rst(shdev);

	return IRQ_HANDLED;
}
#endif

static void dmae_do_tasklet(unsigned long data)
{
	struct sh_dmae_chan *sh_chan = (struct sh_dmae_chan *)data;
	struct sh_desc *desc;
	u32 sar_buf = sh_dmae_readl(sh_chan, SAR);
	u32 dar_buf = sh_dmae_readl(sh_chan, DAR);

	spin_lock(&sh_chan->desc_lock);
	list_for_each_entry(desc, &sh_chan->ld_queue, node) {
		if (desc->mark == DESC_SUBMITTED &&
		    ((desc->direction == DMA_FROM_DEVICE &&
		      (desc->hw.dar + desc->hw.tcr) == dar_buf) ||
		     (desc->hw.sar + desc->hw.tcr) == sar_buf)) {
			dev_dbg(sh_chan->dev, "done #%d@%p dst %u\n",
				desc->async_tx.cookie, &desc->async_tx,
				desc->hw.dar);
			desc->mark = DESC_COMPLETED;
			break;
		}
	}
	spin_unlock(&sh_chan->desc_lock);

	/* Next desc */
	sh_chan_xfer_ld_queue(sh_chan);
	sh_dmae_chan_ld_cleanup(sh_chan, false);
}

static int __devinit sh_dmae_chan_probe(struct sh_dmae_device *shdev, int id,
					int irq, unsigned long flags)
{
	int err;
	const struct sh_dmae_channel *chan_pdata = &shdev->pdata->channel[id];
	struct platform_device *pdev = to_platform_device(shdev->common.dev);
	struct sh_dmae_chan *new_sh_chan;

	/* alloc channel */
	new_sh_chan = kzalloc(sizeof(struct sh_dmae_chan), GFP_KERNEL);
	if (!new_sh_chan) {
		dev_err(shdev->common.dev,
			"No free memory for allocating dma channels!\n");
		return -ENOMEM;
	}

	/* copy struct dma_device */
	new_sh_chan->common.device = &shdev->common;

	new_sh_chan->dev = shdev->common.dev;
	new_sh_chan->id = id;
	new_sh_chan->irq = irq;
	new_sh_chan->base = shdev->chan_reg + chan_pdata->offset / sizeof(u32);

	/* Init DMA tasklet */
	tasklet_init(&new_sh_chan->tasklet, dmae_do_tasklet,
			(unsigned long)new_sh_chan);

	/* Init the channel */
	dmae_init(new_sh_chan);

	spin_lock_init(&new_sh_chan->desc_lock);

	/* Init descripter manage list */
	INIT_LIST_HEAD(&new_sh_chan->ld_queue);
	INIT_LIST_HEAD(&new_sh_chan->ld_free);

	/* Add the channel to DMA device channel list */
	list_add_tail(&new_sh_chan->common.device_node,
			&shdev->common.channels);
	shdev->common.chancnt++;

	if (pdev->id >= 0)
		snprintf(new_sh_chan->dev_id, sizeof(new_sh_chan->dev_id),
			 "sh-dmae%d.%d", pdev->id, new_sh_chan->id);
	else
		snprintf(new_sh_chan->dev_id, sizeof(new_sh_chan->dev_id),
			 "sh-dma%d", new_sh_chan->id);

	/* set up channel irq */
	err = request_irq(irq, &sh_dmae_interrupt, flags,
			  new_sh_chan->dev_id, new_sh_chan);
	if (err) {
		dev_err(shdev->common.dev, "DMA channel %d request_irq error "
			"with return %d\n", id, err);
		goto err_no_irq;
	}

	shdev->chan[id] = new_sh_chan;
	return 0;

err_no_irq:
	/* remove from dmaengine device node */
	list_del(&new_sh_chan->common.device_node);
	kfree(new_sh_chan);
	return err;
}

static void sh_dmae_chan_remove(struct sh_dmae_device *shdev)
{
	int i;

	for (i = shdev->common.chancnt - 1 ; i >= 0 ; i--) {
		if (shdev->chan[i]) {
			struct sh_dmae_chan *sh_chan = shdev->chan[i];

			free_irq(sh_chan->irq, sh_chan);

			list_del(&sh_chan->common.device_node);
			kfree(sh_chan);
			shdev->chan[i] = NULL;
		}
	}
	shdev->common.chancnt = 0;
}

static int __init sh_dmae_probe(struct platform_device *pdev)
{
	struct sh_dmae_pdata *pdata = pdev->dev.platform_data;
	unsigned long irqflags = IRQF_DISABLED,
		chan_flag[SH_DMAC_MAX_CHANNELS] = {};
	int errirq, chan_irq[SH_DMAC_MAX_CHANNELS];
	int err, i, irq_cnt = 0, irqres = 0;
	struct sh_dmae_device *shdev;
	struct resource *chan, *dmars, *errirq_res, *chanirq_res;

	/* get platform data */
	if (!pdata || !pdata->channel_num)
		return -ENODEV;

	chan = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	/* DMARS area is optional, if absent, this controller cannot do slave DMA */
	dmars = platform_get_resource(pdev, IORESOURCE_MEM, 1);
	/*
	 * IRQ resources:
	 * 1. there always must be at least one IRQ IO-resource. On SH4 it is
	 *    the error IRQ, in which case it is the only IRQ in this resource:
	 *    start == end. If it is the only IRQ resource, all channels also
	 *    use the same IRQ.
	 * 2. DMA channel IRQ resources can be specified one per resource or in
	 *    ranges (start != end)
	 * 3. iff all events (channels and, optionally, error) on this
	 *    controller use the same IRQ, only one IRQ resource can be
	 *    specified, otherwise there must be one IRQ per channel, even if
	 *    some of them are equal
	 * 4. if all IRQs on this controller are equal or if some specific IRQs
	 *    specify IORESOURCE_IRQ_SHAREABLE in their resources, they will be
	 *    requested with the IRQF_SHARED flag
	 */
	errirq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
	if (!chan || !errirq_res)
		return -ENODEV;

	if (!request_mem_region(chan->start, resource_size(chan), pdev->name)) {
		dev_err(&pdev->dev, "DMAC register region already claimed\n");
		return -EBUSY;
	}

	if (dmars && !request_mem_region(dmars->start, resource_size(dmars), pdev->name)) {
		dev_err(&pdev->dev, "DMAC DMARS region already claimed\n");
		err = -EBUSY;
		goto ermrdmars;
	}

	err = -ENOMEM;
	shdev = kzalloc(sizeof(struct sh_dmae_device), GFP_KERNEL);
	if (!shdev) {
		dev_err(&pdev->dev, "Not enough memory\n");
		goto ealloc;
	}

	shdev->chan_reg = ioremap(chan->start, resource_size(chan));
	if (!shdev->chan_reg)
		goto emapchan;
	if (dmars) {
		shdev->dmars = ioremap(dmars->start, resource_size(dmars));
		if (!shdev->dmars)
			goto emapdmars;
	}

	/* platform data */
	shdev->pdata = pdata;

	pm_runtime_enable(&pdev->dev);
	pm_runtime_get_sync(&pdev->dev);

	/* reset dma controller */
	err = sh_dmae_rst(shdev);
	if (err)
		goto rst_err;

	INIT_LIST_HEAD(&shdev->common.channels);

	dma_cap_set(DMA_MEMCPY, shdev->common.cap_mask);
	if (dmars)
		dma_cap_set(DMA_SLAVE, shdev->common.cap_mask);

	shdev->common.device_alloc_chan_resources
		= sh_dmae_alloc_chan_resources;
	shdev->common.device_free_chan_resources = sh_dmae_free_chan_resources;
	shdev->common.device_prep_dma_memcpy = sh_dmae_prep_memcpy;
	shdev->common.device_tx_status = sh_dmae_tx_status;
	shdev->common.device_issue_pending = sh_dmae_memcpy_issue_pending;

	/* Compulsory for DMA_SLAVE fields */
	shdev->common.device_prep_slave_sg = sh_dmae_prep_slave_sg;
	shdev->common.device_control = sh_dmae_control;

	shdev->common.dev = &pdev->dev;
	/* Default transfer size of 32 bytes requires 32-byte alignment */
	shdev->common.copy_align = LOG2_DEFAULT_XFER_SIZE;

#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
	chanirq_res = platform_get_resource(pdev, IORESOURCE_IRQ, 1);

	if (!chanirq_res)
		chanirq_res = errirq_res;
	else
		irqres++;

	if (chanirq_res == errirq_res ||
	    (errirq_res->flags & IORESOURCE_BITS) == IORESOURCE_IRQ_SHAREABLE)
		irqflags = IRQF_SHARED;

	errirq = errirq_res->start;

	err = request_irq(errirq, sh_dmae_err, irqflags,
			  "DMAC Address Error", shdev);
	if (err) {
		dev_err(&pdev->dev,
			"DMA failed requesting irq #%d, error %d\n",
			errirq, err);
		goto eirq_err;
	}

#else
	chanirq_res = errirq_res;
#endif /* CONFIG_CPU_SH4 || CONFIG_ARCH_SHMOBILE */

	if (chanirq_res->start == chanirq_res->end &&
	    !platform_get_resource(pdev, IORESOURCE_IRQ, 1)) {
		/* Special case - all multiplexed */
		for (; irq_cnt < pdata->channel_num; irq_cnt++) {
			chan_irq[irq_cnt] = chanirq_res->start;
			chan_flag[irq_cnt] = IRQF_SHARED;
		}
	} else {
		do {
			for (i = chanirq_res->start; i <= chanirq_res->end; i++) {
				if ((errirq_res->flags & IORESOURCE_BITS) ==
				    IORESOURCE_IRQ_SHAREABLE)
					chan_flag[irq_cnt] = IRQF_SHARED;
				else
					chan_flag[irq_cnt] = IRQF_DISABLED;
				dev_dbg(&pdev->dev,
					"Found IRQ %d for channel %d\n",
					i, irq_cnt);
				chan_irq[irq_cnt++] = i;
			}
			chanirq_res = platform_get_resource(pdev,
						IORESOURCE_IRQ, ++irqres);
		} while (irq_cnt < pdata->channel_num && chanirq_res);
	}

	if (irq_cnt < pdata->channel_num)
		goto eirqres;

	/* Create DMA Channel */
	for (i = 0; i < pdata->channel_num; i++) {
		err = sh_dmae_chan_probe(shdev, i, chan_irq[i], chan_flag[i]);
		if (err)
			goto chan_probe_err;
	}

	pm_runtime_put(&pdev->dev);

	platform_set_drvdata(pdev, shdev);
	dma_async_device_register(&shdev->common);

	return err;

chan_probe_err:
	sh_dmae_chan_remove(shdev);
eirqres:
#if defined(CONFIG_CPU_SH4) || defined(CONFIG_ARCH_SHMOBILE)
	free_irq(errirq, shdev);
eirq_err:
#endif
rst_err:
	pm_runtime_put(&pdev->dev);
	if (dmars)
		iounmap(shdev->dmars);
emapdmars:
	iounmap(shdev->chan_reg);
emapchan:
	kfree(shdev);
ealloc:
	if (dmars)
		release_mem_region(dmars->start, resource_size(dmars));
ermrdmars:
	release_mem_region(chan->start, resource_size(chan));

	return err;
}

static int __exit sh_dmae_remove(struct platform_device *pdev)
{
	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
	struct resource *res;
	int errirq = platform_get_irq(pdev, 0);

	dma_async_device_unregister(&shdev->common);

	if (errirq > 0)
		free_irq(errirq, shdev);

	/* channel data remove */
	sh_dmae_chan_remove(shdev);

	pm_runtime_disable(&pdev->dev);

	if (shdev->dmars)
		iounmap(shdev->dmars);
	iounmap(shdev->chan_reg);

	kfree(shdev);

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (res)
		release_mem_region(res->start, resource_size(res));
	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
	if (res)
		release_mem_region(res->start, resource_size(res));

	return 0;
}

static void sh_dmae_shutdown(struct platform_device *pdev)
{
	struct sh_dmae_device *shdev = platform_get_drvdata(pdev);
	sh_dmae_ctl_stop(shdev);
}

static struct platform_driver sh_dmae_driver = {
	.remove		= __exit_p(sh_dmae_remove),
	.shutdown	= sh_dmae_shutdown,
	.driver = {
		.owner	= THIS_MODULE,
		.name	= "sh-dma-engine",
	},
};

static int __init sh_dmae_init(void)
{
	return platform_driver_probe(&sh_dmae_driver, sh_dmae_probe);
}
module_init(sh_dmae_init);

static void __exit sh_dmae_exit(void)
{
	platform_driver_unregister(&sh_dmae_driver);
}
module_exit(sh_dmae_exit);

MODULE_AUTHOR("Nobuhiro Iwamatsu <iwamatsu.nobuhiro@renesas.com>");
MODULE_DESCRIPTION("Renesas SH DMA Engine driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:sh-dma-engine");