summaryrefslogtreecommitdiff
path: root/drivers/dma/s3c24xx-dma.c
blob: 2f91da3db8361cdba3dbd51e120b299607a42485 (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
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
/*
 * S3C24XX DMA handling
 *
 * Copyright (c) 2013 Heiko Stuebner <heiko@sntech.de>
 *
 * based on amba-pl08x.c
 *
 * Copyright (c) 2006 ARM Ltd.
 * Copyright (c) 2010 ST-Ericsson SA
 *
 * Author: Peter Pearse <peter.pearse@arm.com>
 * Author: Linus Walleij <linus.walleij@stericsson.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License as published by the Free
 * Software Foundation; either version 2 of the License, or (at your option)
 * any later version.
 *
 * The DMA controllers in S3C24XX SoCs have a varying number of DMA signals
 * that can be routed to any of the 4 to 8 hardware-channels.
 *
 * Therefore on these DMA controllers the number of channels
 * and the number of incoming DMA signals are two totally different things.
 * It is usually not possible to theoretically handle all physical signals,
 * so a multiplexing scheme with possible denial of use is necessary.
 *
 * Open items:
 * - bursts
 */

#include <linux/platform_device.h>
#include <linux/types.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/interrupt.h>
#include <linux/clk.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/platform_data/dma-s3c24xx.h>

#include "dmaengine.h"
#include "virt-dma.h"

#define MAX_DMA_CHANNELS	8

#define S3C24XX_DISRC			0x00
#define S3C24XX_DISRCC			0x04
#define S3C24XX_DISRCC_INC_INCREMENT	0
#define S3C24XX_DISRCC_INC_FIXED	BIT(0)
#define S3C24XX_DISRCC_LOC_AHB		0
#define S3C24XX_DISRCC_LOC_APB		BIT(1)

#define S3C24XX_DIDST			0x08
#define S3C24XX_DIDSTC			0x0c
#define S3C24XX_DIDSTC_INC_INCREMENT	0
#define S3C24XX_DIDSTC_INC_FIXED	BIT(0)
#define S3C24XX_DIDSTC_LOC_AHB		0
#define S3C24XX_DIDSTC_LOC_APB		BIT(1)
#define S3C24XX_DIDSTC_INT_TC0		0
#define S3C24XX_DIDSTC_INT_RELOAD	BIT(2)

#define S3C24XX_DCON			0x10

#define S3C24XX_DCON_TC_MASK		0xfffff
#define S3C24XX_DCON_DSZ_BYTE		(0 << 20)
#define S3C24XX_DCON_DSZ_HALFWORD	(1 << 20)
#define S3C24XX_DCON_DSZ_WORD		(2 << 20)
#define S3C24XX_DCON_DSZ_MASK		(3 << 20)
#define S3C24XX_DCON_DSZ_SHIFT		20
#define S3C24XX_DCON_AUTORELOAD		0
#define S3C24XX_DCON_NORELOAD		BIT(22)
#define S3C24XX_DCON_HWTRIG		BIT(23)
#define S3C24XX_DCON_HWSRC_SHIFT	24
#define S3C24XX_DCON_SERV_SINGLE	0
#define S3C24XX_DCON_SERV_WHOLE		BIT(27)
#define S3C24XX_DCON_TSZ_UNIT		0
#define S3C24XX_DCON_TSZ_BURST4		BIT(28)
#define S3C24XX_DCON_INT		BIT(29)
#define S3C24XX_DCON_SYNC_PCLK		0
#define S3C24XX_DCON_SYNC_HCLK		BIT(30)
#define S3C24XX_DCON_DEMAND		0
#define S3C24XX_DCON_HANDSHAKE		BIT(31)

#define S3C24XX_DSTAT			0x14
#define S3C24XX_DSTAT_STAT_BUSY		BIT(20)
#define S3C24XX_DSTAT_CURRTC_MASK	0xfffff

#define S3C24XX_DMASKTRIG		0x20
#define S3C24XX_DMASKTRIG_SWTRIG	BIT(0)
#define S3C24XX_DMASKTRIG_ON		BIT(1)
#define S3C24XX_DMASKTRIG_STOP		BIT(2)

#define S3C24XX_DMAREQSEL		0x24
#define S3C24XX_DMAREQSEL_HW		BIT(0)

/*
 * S3C2410, S3C2440 and S3C2442 SoCs cannot select any physical channel
 * for a DMA source. Instead only specific channels are valid.
 * All of these SoCs have 4 physical channels and the number of request
 * source bits is 3. Additionally we also need 1 bit to mark the channel
 * as valid.
 * Therefore we separate the chansel element of the channel data into 4
 * parts of 4 bits each, to hold the information if the channel is valid
 * and the hw request source to use.
 *
 * Example:
 * SDI is valid on channels 0, 2 and 3 - with varying hw request sources.
 * For it the chansel field would look like
 *
 * ((BIT(3) | 1) << 3 * 4) | // channel 3, with request source 1
 * ((BIT(3) | 2) << 2 * 4) | // channel 2, with request source 2
 * ((BIT(3) | 2) << 0 * 4)   // channel 0, with request source 2
 */
#define S3C24XX_CHANSEL_WIDTH		4
#define S3C24XX_CHANSEL_VALID		BIT(3)
#define S3C24XX_CHANSEL_REQ_MASK	7

/*
 * struct soc_data - vendor-specific config parameters for individual SoCs
 * @stride: spacing between the registers of each channel
 * @has_reqsel: does the controller use the newer requestselection mechanism
 * @has_clocks: are controllable dma-clocks present
 */
struct soc_data {
	int stride;
	bool has_reqsel;
	bool has_clocks;
};

/*
 * enum s3c24xx_dma_chan_state - holds the virtual channel states
 * @S3C24XX_DMA_CHAN_IDLE: the channel is idle
 * @S3C24XX_DMA_CHAN_RUNNING: the channel has allocated a physical transport
 * channel and is running a transfer on it
 * @S3C24XX_DMA_CHAN_WAITING: the channel is waiting for a physical transport
 * channel to become available (only pertains to memcpy channels)
 */
enum s3c24xx_dma_chan_state {
	S3C24XX_DMA_CHAN_IDLE,
	S3C24XX_DMA_CHAN_RUNNING,
	S3C24XX_DMA_CHAN_WAITING,
};

/*
 * struct s3c24xx_sg - structure containing data per sg
 * @src_addr: src address of sg
 * @dst_addr: dst address of sg
 * @len: transfer len in bytes
 * @node: node for txd's dsg_list
 */
struct s3c24xx_sg {
	dma_addr_t src_addr;
	dma_addr_t dst_addr;
	size_t len;
	struct list_head node;
};

/*
 * struct s3c24xx_txd - wrapper for struct dma_async_tx_descriptor
 * @vd: virtual DMA descriptor
 * @dsg_list: list of children sg's
 * @at: sg currently being transfered
 * @width: transfer width
 * @disrcc: value for source control register
 * @didstc: value for destination control register
 * @dcon: base value for dcon register
 * @cyclic: indicate cyclic transfer
 */
struct s3c24xx_txd {
	struct virt_dma_desc vd;
	struct list_head dsg_list;
	struct list_head *at;
	u8 width;
	u32 disrcc;
	u32 didstc;
	u32 dcon;
	bool cyclic;
};

struct s3c24xx_dma_chan;

/*
 * struct s3c24xx_dma_phy - holder for the physical channels
 * @id: physical index to this channel
 * @valid: does the channel have all required elements
 * @base: virtual memory base (remapped) for the this channel
 * @irq: interrupt for this channel
 * @clk: clock for this channel
 * @lock: a lock to use when altering an instance of this struct
 * @serving: virtual channel currently being served by this physicalchannel
 * @host: a pointer to the host (internal use)
 */
struct s3c24xx_dma_phy {
	unsigned int			id;
	bool				valid;
	void __iomem			*base;
	int				irq;
	struct clk			*clk;
	spinlock_t			lock;
	struct s3c24xx_dma_chan		*serving;
	struct s3c24xx_dma_engine	*host;
};

/*
 * struct s3c24xx_dma_chan - this structure wraps a DMA ENGINE channel
 * @id: the id of the channel
 * @name: name of the channel
 * @vc: wrappped virtual channel
 * @phy: the physical channel utilized by this channel, if there is one
 * @runtime_addr: address for RX/TX according to the runtime config
 * @at: active transaction on this channel
 * @lock: a lock for this channel data
 * @host: a pointer to the host (internal use)
 * @state: whether the channel is idle, running etc
 * @slave: whether this channel is a device (slave) or for memcpy
 */
struct s3c24xx_dma_chan {
	int id;
	const char *name;
	struct virt_dma_chan vc;
	struct s3c24xx_dma_phy *phy;
	struct dma_slave_config cfg;
	struct s3c24xx_txd *at;
	struct s3c24xx_dma_engine *host;
	enum s3c24xx_dma_chan_state state;
	bool slave;
};

/*
 * struct s3c24xx_dma_engine - the local state holder for the S3C24XX
 * @pdev: the corresponding platform device
 * @pdata: platform data passed in from the platform/machine
 * @base: virtual memory base (remapped)
 * @slave: slave engine for this instance
 * @memcpy: memcpy engine for this instance
 * @phy_chans: array of data for the physical channels
 */
struct s3c24xx_dma_engine {
	struct platform_device			*pdev;
	const struct s3c24xx_dma_platdata	*pdata;
	struct soc_data				*sdata;
	void __iomem				*base;
	struct dma_device			slave;
	struct dma_device			memcpy;
	struct s3c24xx_dma_phy			*phy_chans;
};

/*
 * Physical channel handling
 */

/*
 * Check whether a certain channel is busy or not.
 */
static int s3c24xx_dma_phy_busy(struct s3c24xx_dma_phy *phy)
{
	unsigned int val = readl(phy->base + S3C24XX_DSTAT);
	return val & S3C24XX_DSTAT_STAT_BUSY;
}

static bool s3c24xx_dma_phy_valid(struct s3c24xx_dma_chan *s3cchan,
				  struct s3c24xx_dma_phy *phy)
{
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
	struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id];
	int phyvalid;

	/* every phy is valid for memcopy channels */
	if (!s3cchan->slave)
		return true;

	/* On newer variants all phys can be used for all virtual channels */
	if (s3cdma->sdata->has_reqsel)
		return true;

	phyvalid = (cdata->chansel >> (phy->id * S3C24XX_CHANSEL_WIDTH));
	return (phyvalid & S3C24XX_CHANSEL_VALID) ? true : false;
}

/*
 * Allocate a physical channel for a virtual channel
 *
 * Try to locate a physical channel to be used for this transfer. If all
 * are taken return NULL and the requester will have to cope by using
 * some fallback PIO mode or retrying later.
 */
static
struct s3c24xx_dma_phy *s3c24xx_dma_get_phy(struct s3c24xx_dma_chan *s3cchan)
{
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
	struct s3c24xx_dma_channel *cdata;
	struct s3c24xx_dma_phy *phy = NULL;
	unsigned long flags;
	int i;
	int ret;

	if (s3cchan->slave)
		cdata = &pdata->channels[s3cchan->id];

	for (i = 0; i < s3cdma->pdata->num_phy_channels; i++) {
		phy = &s3cdma->phy_chans[i];

		if (!phy->valid)
			continue;

		if (!s3c24xx_dma_phy_valid(s3cchan, phy))
			continue;

		spin_lock_irqsave(&phy->lock, flags);

		if (!phy->serving) {
			phy->serving = s3cchan;
			spin_unlock_irqrestore(&phy->lock, flags);
			break;
		}

		spin_unlock_irqrestore(&phy->lock, flags);
	}

	/* No physical channel available, cope with it */
	if (i == s3cdma->pdata->num_phy_channels) {
		dev_warn(&s3cdma->pdev->dev, "no phy channel available\n");
		return NULL;
	}

	/* start the phy clock */
	if (s3cdma->sdata->has_clocks) {
		ret = clk_enable(phy->clk);
		if (ret) {
			dev_err(&s3cdma->pdev->dev, "could not enable clock for channel %d, err %d\n",
				phy->id, ret);
			phy->serving = NULL;
			return NULL;
		}
	}

	return phy;
}

/*
 * Mark the physical channel as free.
 *
 * This drops the link between the physical and virtual channel.
 */
static inline void s3c24xx_dma_put_phy(struct s3c24xx_dma_phy *phy)
{
	struct s3c24xx_dma_engine *s3cdma = phy->host;

	if (s3cdma->sdata->has_clocks)
		clk_disable(phy->clk);

	phy->serving = NULL;
}

/*
 * Stops the channel by writing the stop bit.
 * This should not be used for an on-going transfer, but as a method of
 * shutting down a channel (eg, when it's no longer used) or terminating a
 * transfer.
 */
static void s3c24xx_dma_terminate_phy(struct s3c24xx_dma_phy *phy)
{
	writel(S3C24XX_DMASKTRIG_STOP, phy->base + S3C24XX_DMASKTRIG);
}

/*
 * Virtual channel handling
 */

static inline
struct s3c24xx_dma_chan *to_s3c24xx_dma_chan(struct dma_chan *chan)
{
	return container_of(chan, struct s3c24xx_dma_chan, vc.chan);
}

static u32 s3c24xx_dma_getbytes_chan(struct s3c24xx_dma_chan *s3cchan)
{
	struct s3c24xx_dma_phy *phy = s3cchan->phy;
	struct s3c24xx_txd *txd = s3cchan->at;
	u32 tc = readl(phy->base + S3C24XX_DSTAT) & S3C24XX_DSTAT_CURRTC_MASK;

	return tc * txd->width;
}

static int s3c24xx_dma_set_runtime_config(struct dma_chan *chan,
				  struct dma_slave_config *config)
{
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
	unsigned long flags;
	int ret = 0;

	/* Reject definitely invalid configurations */
	if (config->src_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES ||
	    config->dst_addr_width == DMA_SLAVE_BUSWIDTH_8_BYTES)
		return -EINVAL;

	spin_lock_irqsave(&s3cchan->vc.lock, flags);

	if (!s3cchan->slave) {
		ret = -EINVAL;
		goto out;
	}

	s3cchan->cfg = *config;

out:
	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
	return ret;
}

/*
 * Transfer handling
 */

static inline
struct s3c24xx_txd *to_s3c24xx_txd(struct dma_async_tx_descriptor *tx)
{
	return container_of(tx, struct s3c24xx_txd, vd.tx);
}

static struct s3c24xx_txd *s3c24xx_dma_get_txd(void)
{
	struct s3c24xx_txd *txd = kzalloc(sizeof(*txd), GFP_NOWAIT);

	if (txd) {
		INIT_LIST_HEAD(&txd->dsg_list);
		txd->dcon = S3C24XX_DCON_INT | S3C24XX_DCON_NORELOAD;
	}

	return txd;
}

static void s3c24xx_dma_free_txd(struct s3c24xx_txd *txd)
{
	struct s3c24xx_sg *dsg, *_dsg;

	list_for_each_entry_safe(dsg, _dsg, &txd->dsg_list, node) {
		list_del(&dsg->node);
		kfree(dsg);
	}

	kfree(txd);
}

static void s3c24xx_dma_start_next_sg(struct s3c24xx_dma_chan *s3cchan,
				       struct s3c24xx_txd *txd)
{
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	struct s3c24xx_dma_phy *phy = s3cchan->phy;
	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
	struct s3c24xx_sg *dsg = list_entry(txd->at, struct s3c24xx_sg, node);
	u32 dcon = txd->dcon;
	u32 val;

	/* transfer-size and -count from len and width */
	switch (txd->width) {
	case 1:
		dcon |= S3C24XX_DCON_DSZ_BYTE | dsg->len;
		break;
	case 2:
		dcon |= S3C24XX_DCON_DSZ_HALFWORD | (dsg->len / 2);
		break;
	case 4:
		dcon |= S3C24XX_DCON_DSZ_WORD | (dsg->len / 4);
		break;
	}

	if (s3cchan->slave) {
		struct s3c24xx_dma_channel *cdata =
					&pdata->channels[s3cchan->id];

		if (s3cdma->sdata->has_reqsel) {
			writel_relaxed((cdata->chansel << 1) |
							S3C24XX_DMAREQSEL_HW,
					phy->base + S3C24XX_DMAREQSEL);
		} else {
			int csel = cdata->chansel >> (phy->id *
							S3C24XX_CHANSEL_WIDTH);

			csel &= S3C24XX_CHANSEL_REQ_MASK;
			dcon |= csel << S3C24XX_DCON_HWSRC_SHIFT;
			dcon |= S3C24XX_DCON_HWTRIG;
		}
	} else {
		if (s3cdma->sdata->has_reqsel)
			writel_relaxed(0, phy->base + S3C24XX_DMAREQSEL);
	}

	writel_relaxed(dsg->src_addr, phy->base + S3C24XX_DISRC);
	writel_relaxed(txd->disrcc, phy->base + S3C24XX_DISRCC);
	writel_relaxed(dsg->dst_addr, phy->base + S3C24XX_DIDST);
	writel_relaxed(txd->didstc, phy->base + S3C24XX_DIDSTC);
	writel_relaxed(dcon, phy->base + S3C24XX_DCON);

	val = readl_relaxed(phy->base + S3C24XX_DMASKTRIG);
	val &= ~S3C24XX_DMASKTRIG_STOP;
	val |= S3C24XX_DMASKTRIG_ON;

	/* trigger the dma operation for memcpy transfers */
	if (!s3cchan->slave)
		val |= S3C24XX_DMASKTRIG_SWTRIG;

	writel(val, phy->base + S3C24XX_DMASKTRIG);
}

/*
 * Set the initial DMA register values and start first sg.
 */
static void s3c24xx_dma_start_next_txd(struct s3c24xx_dma_chan *s3cchan)
{
	struct s3c24xx_dma_phy *phy = s3cchan->phy;
	struct virt_dma_desc *vd = vchan_next_desc(&s3cchan->vc);
	struct s3c24xx_txd *txd = to_s3c24xx_txd(&vd->tx);

	list_del(&txd->vd.node);

	s3cchan->at = txd;

	/* Wait for channel inactive */
	while (s3c24xx_dma_phy_busy(phy))
		cpu_relax();

	/* point to the first element of the sg list */
	txd->at = txd->dsg_list.next;
	s3c24xx_dma_start_next_sg(s3cchan, txd);
}

static void s3c24xx_dma_free_txd_list(struct s3c24xx_dma_engine *s3cdma,
				struct s3c24xx_dma_chan *s3cchan)
{
	LIST_HEAD(head);

	vchan_get_all_descriptors(&s3cchan->vc, &head);
	vchan_dma_desc_free_list(&s3cchan->vc, &head);
}

/*
 * Try to allocate a physical channel.  When successful, assign it to
 * this virtual channel, and initiate the next descriptor.  The
 * virtual channel lock must be held at this point.
 */
static void s3c24xx_dma_phy_alloc_and_start(struct s3c24xx_dma_chan *s3cchan)
{
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	struct s3c24xx_dma_phy *phy;

	phy = s3c24xx_dma_get_phy(s3cchan);
	if (!phy) {
		dev_dbg(&s3cdma->pdev->dev, "no physical channel available for xfer on %s\n",
			s3cchan->name);
		s3cchan->state = S3C24XX_DMA_CHAN_WAITING;
		return;
	}

	dev_dbg(&s3cdma->pdev->dev, "allocated physical channel %d for xfer on %s\n",
		phy->id, s3cchan->name);

	s3cchan->phy = phy;
	s3cchan->state = S3C24XX_DMA_CHAN_RUNNING;

	s3c24xx_dma_start_next_txd(s3cchan);
}

static void s3c24xx_dma_phy_reassign_start(struct s3c24xx_dma_phy *phy,
	struct s3c24xx_dma_chan *s3cchan)
{
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;

	dev_dbg(&s3cdma->pdev->dev, "reassigned physical channel %d for xfer on %s\n",
		phy->id, s3cchan->name);

	/*
	 * We do this without taking the lock; we're really only concerned
	 * about whether this pointer is NULL or not, and we're guaranteed
	 * that this will only be called when it _already_ is non-NULL.
	 */
	phy->serving = s3cchan;
	s3cchan->phy = phy;
	s3cchan->state = S3C24XX_DMA_CHAN_RUNNING;
	s3c24xx_dma_start_next_txd(s3cchan);
}

/*
 * Free a physical DMA channel, potentially reallocating it to another
 * virtual channel if we have any pending.
 */
static void s3c24xx_dma_phy_free(struct s3c24xx_dma_chan *s3cchan)
{
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	struct s3c24xx_dma_chan *p, *next;

retry:
	next = NULL;

	/* Find a waiting virtual channel for the next transfer. */
	list_for_each_entry(p, &s3cdma->memcpy.channels, vc.chan.device_node)
		if (p->state == S3C24XX_DMA_CHAN_WAITING) {
			next = p;
			break;
		}

	if (!next) {
		list_for_each_entry(p, &s3cdma->slave.channels,
				    vc.chan.device_node)
			if (p->state == S3C24XX_DMA_CHAN_WAITING &&
				      s3c24xx_dma_phy_valid(p, s3cchan->phy)) {
				next = p;
				break;
			}
	}

	/* Ensure that the physical channel is stopped */
	s3c24xx_dma_terminate_phy(s3cchan->phy);

	if (next) {
		bool success;

		/*
		 * Eww.  We know this isn't going to deadlock
		 * but lockdep probably doesn't.
		 */
		spin_lock(&next->vc.lock);
		/* Re-check the state now that we have the lock */
		success = next->state == S3C24XX_DMA_CHAN_WAITING;
		if (success)
			s3c24xx_dma_phy_reassign_start(s3cchan->phy, next);
		spin_unlock(&next->vc.lock);

		/* If the state changed, try to find another channel */
		if (!success)
			goto retry;
	} else {
		/* No more jobs, so free up the physical channel */
		s3c24xx_dma_put_phy(s3cchan->phy);
	}

	s3cchan->phy = NULL;
	s3cchan->state = S3C24XX_DMA_CHAN_IDLE;
}

static void s3c24xx_dma_desc_free(struct virt_dma_desc *vd)
{
	struct s3c24xx_txd *txd = to_s3c24xx_txd(&vd->tx);
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(vd->tx.chan);

	if (!s3cchan->slave)
		dma_descriptor_unmap(&vd->tx);

	s3c24xx_dma_free_txd(txd);
}

static irqreturn_t s3c24xx_dma_irq(int irq, void *data)
{
	struct s3c24xx_dma_phy *phy = data;
	struct s3c24xx_dma_chan *s3cchan = phy->serving;
	struct s3c24xx_txd *txd;

	dev_dbg(&phy->host->pdev->dev, "interrupt on channel %d\n", phy->id);

	/*
	 * Interrupts happen to notify the completion of a transfer and the
	 * channel should have moved into its stop state already on its own.
	 * Therefore interrupts on channels not bound to a virtual channel
	 * should never happen. Nevertheless send a terminate command to the
	 * channel if the unlikely case happens.
	 */
	if (unlikely(!s3cchan)) {
		dev_err(&phy->host->pdev->dev, "interrupt on unused channel %d\n",
			phy->id);

		s3c24xx_dma_terminate_phy(phy);

		return IRQ_HANDLED;
	}

	spin_lock(&s3cchan->vc.lock);
	txd = s3cchan->at;
	if (txd) {
		/* when more sg's are in this txd, start the next one */
		if (!list_is_last(txd->at, &txd->dsg_list)) {
			txd->at = txd->at->next;
			if (txd->cyclic)
				vchan_cyclic_callback(&txd->vd);
			s3c24xx_dma_start_next_sg(s3cchan, txd);
		} else if (!txd->cyclic) {
			s3cchan->at = NULL;
			vchan_cookie_complete(&txd->vd);

			/*
			 * And start the next descriptor (if any),
			 * otherwise free this channel.
			 */
			if (vchan_next_desc(&s3cchan->vc))
				s3c24xx_dma_start_next_txd(s3cchan);
			else
				s3c24xx_dma_phy_free(s3cchan);
		} else {
			vchan_cyclic_callback(&txd->vd);

			/* Cyclic: reset at beginning */
			txd->at = txd->dsg_list.next;
			s3c24xx_dma_start_next_sg(s3cchan, txd);
		}
	}
	spin_unlock(&s3cchan->vc.lock);

	return IRQ_HANDLED;
}

/*
 * The DMA ENGINE API
 */

static int s3c24xx_dma_terminate_all(struct dma_chan *chan)
{
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	unsigned long flags;
	int ret = 0;

	spin_lock_irqsave(&s3cchan->vc.lock, flags);

	if (!s3cchan->phy && !s3cchan->at) {
		dev_err(&s3cdma->pdev->dev, "trying to terminate already stopped channel %d\n",
			s3cchan->id);
		ret = -EINVAL;
		goto unlock;
	}

	s3cchan->state = S3C24XX_DMA_CHAN_IDLE;

	/* Mark physical channel as free */
	if (s3cchan->phy)
		s3c24xx_dma_phy_free(s3cchan);

	/* Dequeue current job */
	if (s3cchan->at) {
		s3c24xx_dma_desc_free(&s3cchan->at->vd);
		s3cchan->at = NULL;
	}

	/* Dequeue jobs not yet fired as well */
	s3c24xx_dma_free_txd_list(s3cdma, s3cchan);
unlock:
	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);

	return ret;
}

static int s3c24xx_dma_alloc_chan_resources(struct dma_chan *chan)
{
	return 0;
}

static void s3c24xx_dma_free_chan_resources(struct dma_chan *chan)
{
	/* Ensure all queued descriptors are freed */
	vchan_free_chan_resources(to_virt_chan(chan));
}

static enum dma_status s3c24xx_dma_tx_status(struct dma_chan *chan,
		dma_cookie_t cookie, struct dma_tx_state *txstate)
{
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
	struct s3c24xx_txd *txd;
	struct s3c24xx_sg *dsg;
	struct virt_dma_desc *vd;
	unsigned long flags;
	enum dma_status ret;
	size_t bytes = 0;

	spin_lock_irqsave(&s3cchan->vc.lock, flags);
	ret = dma_cookie_status(chan, cookie, txstate);
	if (ret == DMA_COMPLETE) {
		spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
		return ret;
	}

	/*
	 * There's no point calculating the residue if there's
	 * no txstate to store the value.
	 */
	if (!txstate) {
		spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
		return ret;
	}

	vd = vchan_find_desc(&s3cchan->vc, cookie);
	if (vd) {
		/* On the issued list, so hasn't been processed yet */
		txd = to_s3c24xx_txd(&vd->tx);

		list_for_each_entry(dsg, &txd->dsg_list, node)
			bytes += dsg->len;
	} else {
		/*
		 * Currently running, so sum over the pending sg's and
		 * the currently active one.
		 */
		txd = s3cchan->at;

		dsg = list_entry(txd->at, struct s3c24xx_sg, node);
		list_for_each_entry_from(dsg, &txd->dsg_list, node)
			bytes += dsg->len;

		bytes += s3c24xx_dma_getbytes_chan(s3cchan);
	}
	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);

	/*
	 * This cookie not complete yet
	 * Get number of bytes left in the active transactions and queue
	 */
	dma_set_residue(txstate, bytes);

	/* Whether waiting or running, we're in progress */
	return ret;
}

/*
 * Initialize a descriptor to be used by memcpy submit
 */
static struct dma_async_tx_descriptor *s3c24xx_dma_prep_memcpy(
		struct dma_chan *chan, dma_addr_t dest, dma_addr_t src,
		size_t len, unsigned long flags)
{
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	struct s3c24xx_txd *txd;
	struct s3c24xx_sg *dsg;
	int src_mod, dest_mod;

	dev_dbg(&s3cdma->pdev->dev, "prepare memcpy of %d bytes from %s\n",
			len, s3cchan->name);

	if ((len & S3C24XX_DCON_TC_MASK) != len) {
		dev_err(&s3cdma->pdev->dev, "memcpy size %d to large\n", len);
		return NULL;
	}

	txd = s3c24xx_dma_get_txd();
	if (!txd)
		return NULL;

	dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT);
	if (!dsg) {
		s3c24xx_dma_free_txd(txd);
		return NULL;
	}
	list_add_tail(&dsg->node, &txd->dsg_list);

	dsg->src_addr = src;
	dsg->dst_addr = dest;
	dsg->len = len;

	/*
	 * Determine a suitable transfer width.
	 * The DMA controller cannot fetch/store information which is not
	 * naturally aligned on the bus, i.e., a 4 byte fetch must start at
	 * an address divisible by 4 - more generally addr % width must be 0.
	 */
	src_mod = src % 4;
	dest_mod = dest % 4;
	switch (len % 4) {
	case 0:
		txd->width = (src_mod == 0 && dest_mod == 0) ? 4 : 1;
		break;
	case 2:
		txd->width = ((src_mod == 2 || src_mod == 0) &&
			      (dest_mod == 2 || dest_mod == 0)) ? 2 : 1;
		break;
	default:
		txd->width = 1;
		break;
	}

	txd->disrcc = S3C24XX_DISRCC_LOC_AHB | S3C24XX_DISRCC_INC_INCREMENT;
	txd->didstc = S3C24XX_DIDSTC_LOC_AHB | S3C24XX_DIDSTC_INC_INCREMENT;
	txd->dcon |= S3C24XX_DCON_DEMAND | S3C24XX_DCON_SYNC_HCLK |
		     S3C24XX_DCON_SERV_WHOLE;

	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
}

static struct dma_async_tx_descriptor *s3c24xx_dma_prep_dma_cyclic(
	struct dma_chan *chan, dma_addr_t addr, size_t size, size_t period,
	enum dma_transfer_direction direction, unsigned long flags)
{
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
	struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id];
	struct s3c24xx_txd *txd;
	struct s3c24xx_sg *dsg;
	unsigned sg_len;
	dma_addr_t slave_addr;
	u32 hwcfg = 0;
	int i;

	dev_dbg(&s3cdma->pdev->dev,
		"prepare cyclic transaction of %zu bytes with period %zu from %s\n",
		size, period, s3cchan->name);

	if (!is_slave_direction(direction)) {
		dev_err(&s3cdma->pdev->dev,
			"direction %d unsupported\n", direction);
		return NULL;
	}

	txd = s3c24xx_dma_get_txd();
	if (!txd)
		return NULL;

	txd->cyclic = 1;

	if (cdata->handshake)
		txd->dcon |= S3C24XX_DCON_HANDSHAKE;

	switch (cdata->bus) {
	case S3C24XX_DMA_APB:
		txd->dcon |= S3C24XX_DCON_SYNC_PCLK;
		hwcfg |= S3C24XX_DISRCC_LOC_APB;
		break;
	case S3C24XX_DMA_AHB:
		txd->dcon |= S3C24XX_DCON_SYNC_HCLK;
		hwcfg |= S3C24XX_DISRCC_LOC_AHB;
		break;
	}

	/*
	 * Always assume our peripheral desintation is a fixed
	 * address in memory.
	 */
	hwcfg |= S3C24XX_DISRCC_INC_FIXED;

	/*
	 * Individual dma operations are requested by the slave,
	 * so serve only single atomic operations (S3C24XX_DCON_SERV_SINGLE).
	 */
	txd->dcon |= S3C24XX_DCON_SERV_SINGLE;

	if (direction == DMA_MEM_TO_DEV) {
		txd->disrcc = S3C24XX_DISRCC_LOC_AHB |
			      S3C24XX_DISRCC_INC_INCREMENT;
		txd->didstc = hwcfg;
		slave_addr = s3cchan->cfg.dst_addr;
		txd->width = s3cchan->cfg.dst_addr_width;
	} else {
		txd->disrcc = hwcfg;
		txd->didstc = S3C24XX_DIDSTC_LOC_AHB |
			      S3C24XX_DIDSTC_INC_INCREMENT;
		slave_addr = s3cchan->cfg.src_addr;
		txd->width = s3cchan->cfg.src_addr_width;
	}

	sg_len = size / period;

	for (i = 0; i < sg_len; i++) {
		dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT);
		if (!dsg) {
			s3c24xx_dma_free_txd(txd);
			return NULL;
		}
		list_add_tail(&dsg->node, &txd->dsg_list);

		dsg->len = period;
		/* Check last period length */
		if (i == sg_len - 1)
			dsg->len = size - period * i;
		if (direction == DMA_MEM_TO_DEV) {
			dsg->src_addr = addr + period * i;
			dsg->dst_addr = slave_addr;
		} else { /* DMA_DEV_TO_MEM */
			dsg->src_addr = slave_addr;
			dsg->dst_addr = addr + period * i;
		}
	}

	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
}

static struct dma_async_tx_descriptor *s3c24xx_dma_prep_slave_sg(
		struct dma_chan *chan, struct scatterlist *sgl,
		unsigned int sg_len, enum dma_transfer_direction direction,
		unsigned long flags, void *context)
{
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
	struct s3c24xx_dma_engine *s3cdma = s3cchan->host;
	const struct s3c24xx_dma_platdata *pdata = s3cdma->pdata;
	struct s3c24xx_dma_channel *cdata = &pdata->channels[s3cchan->id];
	struct s3c24xx_txd *txd;
	struct s3c24xx_sg *dsg;
	struct scatterlist *sg;
	dma_addr_t slave_addr;
	u32 hwcfg = 0;
	int tmp;

	dev_dbg(&s3cdma->pdev->dev, "prepare transaction of %d bytes from %s\n",
			sg_dma_len(sgl), s3cchan->name);

	txd = s3c24xx_dma_get_txd();
	if (!txd)
		return NULL;

	if (cdata->handshake)
		txd->dcon |= S3C24XX_DCON_HANDSHAKE;

	switch (cdata->bus) {
	case S3C24XX_DMA_APB:
		txd->dcon |= S3C24XX_DCON_SYNC_PCLK;
		hwcfg |= S3C24XX_DISRCC_LOC_APB;
		break;
	case S3C24XX_DMA_AHB:
		txd->dcon |= S3C24XX_DCON_SYNC_HCLK;
		hwcfg |= S3C24XX_DISRCC_LOC_AHB;
		break;
	}

	/*
	 * Always assume our peripheral desintation is a fixed
	 * address in memory.
	 */
	hwcfg |= S3C24XX_DISRCC_INC_FIXED;

	/*
	 * Individual dma operations are requested by the slave,
	 * so serve only single atomic operations (S3C24XX_DCON_SERV_SINGLE).
	 */
	txd->dcon |= S3C24XX_DCON_SERV_SINGLE;

	if (direction == DMA_MEM_TO_DEV) {
		txd->disrcc = S3C24XX_DISRCC_LOC_AHB |
			      S3C24XX_DISRCC_INC_INCREMENT;
		txd->didstc = hwcfg;
		slave_addr = s3cchan->cfg.dst_addr;
		txd->width = s3cchan->cfg.dst_addr_width;
	} else if (direction == DMA_DEV_TO_MEM) {
		txd->disrcc = hwcfg;
		txd->didstc = S3C24XX_DIDSTC_LOC_AHB |
			      S3C24XX_DIDSTC_INC_INCREMENT;
		slave_addr = s3cchan->cfg.src_addr;
		txd->width = s3cchan->cfg.src_addr_width;
	} else {
		s3c24xx_dma_free_txd(txd);
		dev_err(&s3cdma->pdev->dev,
			"direction %d unsupported\n", direction);
		return NULL;
	}

	for_each_sg(sgl, sg, sg_len, tmp) {
		dsg = kzalloc(sizeof(*dsg), GFP_NOWAIT);
		if (!dsg) {
			s3c24xx_dma_free_txd(txd);
			return NULL;
		}
		list_add_tail(&dsg->node, &txd->dsg_list);

		dsg->len = sg_dma_len(sg);
		if (direction == DMA_MEM_TO_DEV) {
			dsg->src_addr = sg_dma_address(sg);
			dsg->dst_addr = slave_addr;
		} else { /* DMA_DEV_TO_MEM */
			dsg->src_addr = slave_addr;
			dsg->dst_addr = sg_dma_address(sg);
		}
	}

	return vchan_tx_prep(&s3cchan->vc, &txd->vd, flags);
}

/*
 * Slave transactions callback to the slave device to allow
 * synchronization of slave DMA signals with the DMAC enable
 */
static void s3c24xx_dma_issue_pending(struct dma_chan *chan)
{
	struct s3c24xx_dma_chan *s3cchan = to_s3c24xx_dma_chan(chan);
	unsigned long flags;

	spin_lock_irqsave(&s3cchan->vc.lock, flags);
	if (vchan_issue_pending(&s3cchan->vc)) {
		if (!s3cchan->phy && s3cchan->state != S3C24XX_DMA_CHAN_WAITING)
			s3c24xx_dma_phy_alloc_and_start(s3cchan);
	}
	spin_unlock_irqrestore(&s3cchan->vc.lock, flags);
}

/*
 * Bringup and teardown
 */

/*
 * Initialise the DMAC memcpy/slave channels.
 * Make a local wrapper to hold required data
 */
static int s3c24xx_dma_init_virtual_channels(struct s3c24xx_dma_engine *s3cdma,
		struct dma_device *dmadev, unsigned int channels, bool slave)
{
	struct s3c24xx_dma_chan *chan;
	int i;

	INIT_LIST_HEAD(&dmadev->channels);

	/*
	 * Register as many many memcpy as we have physical channels,
	 * we won't always be able to use all but the code will have
	 * to cope with that situation.
	 */
	for (i = 0; i < channels; i++) {
		chan = devm_kzalloc(dmadev->dev, sizeof(*chan), GFP_KERNEL);
		if (!chan) {
			dev_err(dmadev->dev,
				"%s no memory for channel\n", __func__);
			return -ENOMEM;
		}

		chan->id = i;
		chan->host = s3cdma;
		chan->state = S3C24XX_DMA_CHAN_IDLE;

		if (slave) {
			chan->slave = true;
			chan->name = kasprintf(GFP_KERNEL, "slave%d", i);
			if (!chan->name)
				return -ENOMEM;
		} else {
			chan->name = kasprintf(GFP_KERNEL, "memcpy%d", i);
			if (!chan->name)
				return -ENOMEM;
		}
		dev_dbg(dmadev->dev,
			 "initialize virtual channel \"%s\"\n",
			 chan->name);

		chan->vc.desc_free = s3c24xx_dma_desc_free;
		vchan_init(&chan->vc, dmadev);
	}
	dev_info(dmadev->dev, "initialized %d virtual %s channels\n",
		 i, slave ? "slave" : "memcpy");
	return i;
}

static void s3c24xx_dma_free_virtual_channels(struct dma_device *dmadev)
{
	struct s3c24xx_dma_chan *chan = NULL;
	struct s3c24xx_dma_chan *next;

	list_for_each_entry_safe(chan,
				 next, &dmadev->channels, vc.chan.device_node)
		list_del(&chan->vc.chan.device_node);
}

/* s3c2410, s3c2440 and s3c2442 have a 0x40 stride without separate clocks */
static struct soc_data soc_s3c2410 = {
	.stride = 0x40,
	.has_reqsel = false,
	.has_clocks = false,
};

/* s3c2412 and s3c2413 have a 0x40 stride and dmareqsel mechanism */
static struct soc_data soc_s3c2412 = {
	.stride = 0x40,
	.has_reqsel = true,
	.has_clocks = true,
};

/* s3c2443 and following have a 0x100 stride and dmareqsel mechanism */
static struct soc_data soc_s3c2443 = {
	.stride = 0x100,
	.has_reqsel = true,
	.has_clocks = true,
};

static struct platform_device_id s3c24xx_dma_driver_ids[] = {
	{
		.name		= "s3c2410-dma",
		.driver_data	= (kernel_ulong_t)&soc_s3c2410,
	}, {
		.name		= "s3c2412-dma",
		.driver_data	= (kernel_ulong_t)&soc_s3c2412,
	}, {
		.name		= "s3c2443-dma",
		.driver_data	= (kernel_ulong_t)&soc_s3c2443,
	},
	{ },
};

static struct soc_data *s3c24xx_dma_get_soc_data(struct platform_device *pdev)
{
	return (struct soc_data *)
			 platform_get_device_id(pdev)->driver_data;
}

static int s3c24xx_dma_probe(struct platform_device *pdev)
{
	const struct s3c24xx_dma_platdata *pdata = dev_get_platdata(&pdev->dev);
	struct s3c24xx_dma_engine *s3cdma;
	struct soc_data *sdata;
	struct resource *res;
	int ret;
	int i;

	if (!pdata) {
		dev_err(&pdev->dev, "platform data missing\n");
		return -ENODEV;
	}

	/* Basic sanity check */
	if (pdata->num_phy_channels > MAX_DMA_CHANNELS) {
		dev_err(&pdev->dev, "to many dma channels %d, max %d\n",
			pdata->num_phy_channels, MAX_DMA_CHANNELS);
		return -EINVAL;
	}

	sdata = s3c24xx_dma_get_soc_data(pdev);
	if (!sdata)
		return -EINVAL;

	s3cdma = devm_kzalloc(&pdev->dev, sizeof(*s3cdma), GFP_KERNEL);
	if (!s3cdma)
		return -ENOMEM;

	s3cdma->pdev = pdev;
	s3cdma->pdata = pdata;
	s3cdma->sdata = sdata;

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	s3cdma->base = devm_ioremap_resource(&pdev->dev, res);
	if (IS_ERR(s3cdma->base))
		return PTR_ERR(s3cdma->base);

	s3cdma->phy_chans = devm_kzalloc(&pdev->dev,
					      sizeof(struct s3c24xx_dma_phy) *
							pdata->num_phy_channels,
					      GFP_KERNEL);
	if (!s3cdma->phy_chans)
		return -ENOMEM;

	/* aquire irqs and clocks for all physical channels */
	for (i = 0; i < pdata->num_phy_channels; i++) {
		struct s3c24xx_dma_phy *phy = &s3cdma->phy_chans[i];
		char clk_name[6];

		phy->id = i;
		phy->base = s3cdma->base + (i * sdata->stride);
		phy->host = s3cdma;

		phy->irq = platform_get_irq(pdev, i);
		if (phy->irq < 0) {
			dev_err(&pdev->dev, "failed to get irq %d, err %d\n",
				i, phy->irq);
			continue;
		}

		ret = devm_request_irq(&pdev->dev, phy->irq, s3c24xx_dma_irq,
				       0, pdev->name, phy);
		if (ret) {
			dev_err(&pdev->dev, "Unable to request irq for channel %d, error %d\n",
				i, ret);
			continue;
		}

		if (sdata->has_clocks) {
			sprintf(clk_name, "dma.%d", i);
			phy->clk = devm_clk_get(&pdev->dev, clk_name);
			if (IS_ERR(phy->clk) && sdata->has_clocks) {
				dev_err(&pdev->dev, "unable to aquire clock for channel %d, error %lu",
					i, PTR_ERR(phy->clk));
				continue;
			}

			ret = clk_prepare(phy->clk);
			if (ret) {
				dev_err(&pdev->dev, "clock for phy %d failed, error %d\n",
					i, ret);
				continue;
			}
		}

		spin_lock_init(&phy->lock);
		phy->valid = true;

		dev_dbg(&pdev->dev, "physical channel %d is %s\n",
			i, s3c24xx_dma_phy_busy(phy) ? "BUSY" : "FREE");
	}

	/* Initialize memcpy engine */
	dma_cap_set(DMA_MEMCPY, s3cdma->memcpy.cap_mask);
	dma_cap_set(DMA_PRIVATE, s3cdma->memcpy.cap_mask);
	s3cdma->memcpy.dev = &pdev->dev;
	s3cdma->memcpy.device_alloc_chan_resources =
					s3c24xx_dma_alloc_chan_resources;
	s3cdma->memcpy.device_free_chan_resources =
					s3c24xx_dma_free_chan_resources;
	s3cdma->memcpy.device_prep_dma_memcpy = s3c24xx_dma_prep_memcpy;
	s3cdma->memcpy.device_tx_status = s3c24xx_dma_tx_status;
	s3cdma->memcpy.device_issue_pending = s3c24xx_dma_issue_pending;
	s3cdma->memcpy.device_config = s3c24xx_dma_set_runtime_config;
	s3cdma->memcpy.device_terminate_all = s3c24xx_dma_terminate_all;

	/* Initialize slave engine for SoC internal dedicated peripherals */
	dma_cap_set(DMA_SLAVE, s3cdma->slave.cap_mask);
	dma_cap_set(DMA_CYCLIC, s3cdma->slave.cap_mask);
	dma_cap_set(DMA_PRIVATE, s3cdma->slave.cap_mask);
	s3cdma->slave.dev = &pdev->dev;
	s3cdma->slave.device_alloc_chan_resources =
					s3c24xx_dma_alloc_chan_resources;
	s3cdma->slave.device_free_chan_resources =
					s3c24xx_dma_free_chan_resources;
	s3cdma->slave.device_tx_status = s3c24xx_dma_tx_status;
	s3cdma->slave.device_issue_pending = s3c24xx_dma_issue_pending;
	s3cdma->slave.device_prep_slave_sg = s3c24xx_dma_prep_slave_sg;
	s3cdma->slave.device_prep_dma_cyclic = s3c24xx_dma_prep_dma_cyclic;
	s3cdma->slave.device_config = s3c24xx_dma_set_runtime_config;
	s3cdma->slave.device_terminate_all = s3c24xx_dma_terminate_all;

	/* Register as many memcpy channels as there are physical channels */
	ret = s3c24xx_dma_init_virtual_channels(s3cdma, &s3cdma->memcpy,
						pdata->num_phy_channels, false);
	if (ret <= 0) {
		dev_warn(&pdev->dev,
			 "%s failed to enumerate memcpy channels - %d\n",
			 __func__, ret);
		goto err_memcpy;
	}

	/* Register slave channels */
	ret = s3c24xx_dma_init_virtual_channels(s3cdma, &s3cdma->slave,
				pdata->num_channels, true);
	if (ret <= 0) {
		dev_warn(&pdev->dev,
			"%s failed to enumerate slave channels - %d\n",
				__func__, ret);
		goto err_slave;
	}

	ret = dma_async_device_register(&s3cdma->memcpy);
	if (ret) {
		dev_warn(&pdev->dev,
			"%s failed to register memcpy as an async device - %d\n",
			__func__, ret);
		goto err_memcpy_reg;
	}

	ret = dma_async_device_register(&s3cdma->slave);
	if (ret) {
		dev_warn(&pdev->dev,
			"%s failed to register slave as an async device - %d\n",
			__func__, ret);
		goto err_slave_reg;
	}

	platform_set_drvdata(pdev, s3cdma);
	dev_info(&pdev->dev, "Loaded dma driver with %d physical channels\n",
		 pdata->num_phy_channels);

	return 0;

err_slave_reg:
	dma_async_device_unregister(&s3cdma->memcpy);
err_memcpy_reg:
	s3c24xx_dma_free_virtual_channels(&s3cdma->slave);
err_slave:
	s3c24xx_dma_free_virtual_channels(&s3cdma->memcpy);
err_memcpy:
	if (sdata->has_clocks)
		for (i = 0; i < pdata->num_phy_channels; i++) {
			struct s3c24xx_dma_phy *phy = &s3cdma->phy_chans[i];
			if (phy->valid)
				clk_unprepare(phy->clk);
		}

	return ret;
}

static int s3c24xx_dma_remove(struct platform_device *pdev)
{
	const struct s3c24xx_dma_platdata *pdata = dev_get_platdata(&pdev->dev);
	struct s3c24xx_dma_engine *s3cdma = platform_get_drvdata(pdev);
	struct soc_data *sdata = s3c24xx_dma_get_soc_data(pdev);
	int i;

	dma_async_device_unregister(&s3cdma->slave);
	dma_async_device_unregister(&s3cdma->memcpy);

	s3c24xx_dma_free_virtual_channels(&s3cdma->slave);
	s3c24xx_dma_free_virtual_channels(&s3cdma->memcpy);

	if (sdata->has_clocks)
		for (i = 0; i < pdata->num_phy_channels; i++) {
			struct s3c24xx_dma_phy *phy = &s3cdma->phy_chans[i];
			if (phy->valid)
				clk_unprepare(phy->clk);
		}

	return 0;
}

static struct platform_driver s3c24xx_dma_driver = {
	.driver		= {
		.name	= "s3c24xx-dma",
	},
	.id_table	= s3c24xx_dma_driver_ids,
	.probe		= s3c24xx_dma_probe,
	.remove		= s3c24xx_dma_remove,
};

module_platform_driver(s3c24xx_dma_driver);

bool s3c24xx_dma_filter(struct dma_chan *chan, void *param)
{
	struct s3c24xx_dma_chan *s3cchan;

	if (chan->device->dev->driver != &s3c24xx_dma_driver.driver)
		return false;

	s3cchan = to_s3c24xx_dma_chan(chan);

	return s3cchan->id == (int)param;
}
EXPORT_SYMBOL(s3c24xx_dma_filter);

MODULE_DESCRIPTION("S3C24XX DMA Driver");
MODULE_AUTHOR("Heiko Stuebner");
MODULE_LICENSE("GPL v2");