aboutsummaryrefslogtreecommitdiff
path: root/drivers/dma/sh/rcar-dmac.c
blob: 6885b3dcd7a973f25ae92340a9f03cd455fbf5cc (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
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
// SPDX-License-Identifier: GPL-2.0
/*
 * Renesas R-Car Gen2/Gen3 DMA Controller Driver
 *
 * Copyright (C) 2014-2019 Renesas Electronics Inc.
 *
 * Author: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 */

#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/dmaengine.h>
#include <linux/interrupt.h>
#include <linux/list.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_dma.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/spinlock.h>

#include "../dmaengine.h"

/*
 * struct rcar_dmac_xfer_chunk - Descriptor for a hardware transfer
 * @node: entry in the parent's chunks list
 * @src_addr: device source address
 * @dst_addr: device destination address
 * @size: transfer size in bytes
 */
struct rcar_dmac_xfer_chunk {
	struct list_head node;

	dma_addr_t src_addr;
	dma_addr_t dst_addr;
	u32 size;
};

/*
 * struct rcar_dmac_hw_desc - Hardware descriptor for a transfer chunk
 * @sar: value of the SAR register (source address)
 * @dar: value of the DAR register (destination address)
 * @tcr: value of the TCR register (transfer count)
 */
struct rcar_dmac_hw_desc {
	u32 sar;
	u32 dar;
	u32 tcr;
	u32 reserved;
} __attribute__((__packed__));

/*
 * struct rcar_dmac_desc - R-Car Gen2 DMA Transfer Descriptor
 * @async_tx: base DMA asynchronous transaction descriptor
 * @direction: direction of the DMA transfer
 * @xfer_shift: log2 of the transfer size
 * @chcr: value of the channel configuration register for this transfer
 * @node: entry in the channel's descriptors lists
 * @chunks: list of transfer chunks for this transfer
 * @running: the transfer chunk being currently processed
 * @nchunks: number of transfer chunks for this transfer
 * @hwdescs.use: whether the transfer descriptor uses hardware descriptors
 * @hwdescs.mem: hardware descriptors memory for the transfer
 * @hwdescs.dma: device address of the hardware descriptors memory
 * @hwdescs.size: size of the hardware descriptors in bytes
 * @size: transfer size in bytes
 * @cyclic: when set indicates that the DMA transfer is cyclic
 */
struct rcar_dmac_desc {
	struct dma_async_tx_descriptor async_tx;
	enum dma_transfer_direction direction;
	unsigned int xfer_shift;
	u32 chcr;

	struct list_head node;
	struct list_head chunks;
	struct rcar_dmac_xfer_chunk *running;
	unsigned int nchunks;

	struct {
		bool use;
		struct rcar_dmac_hw_desc *mem;
		dma_addr_t dma;
		size_t size;
	} hwdescs;

	unsigned int size;
	bool cyclic;
};

#define to_rcar_dmac_desc(d)	container_of(d, struct rcar_dmac_desc, async_tx)

/*
 * struct rcar_dmac_desc_page - One page worth of descriptors
 * @node: entry in the channel's pages list
 * @descs: array of DMA descriptors
 * @chunks: array of transfer chunk descriptors
 */
struct rcar_dmac_desc_page {
	struct list_head node;

	union {
		struct rcar_dmac_desc descs[0];
		struct rcar_dmac_xfer_chunk chunks[0];
	};
};

#define RCAR_DMAC_DESCS_PER_PAGE					\
	((PAGE_SIZE - offsetof(struct rcar_dmac_desc_page, descs)) /	\
	sizeof(struct rcar_dmac_desc))
#define RCAR_DMAC_XFER_CHUNKS_PER_PAGE					\
	((PAGE_SIZE - offsetof(struct rcar_dmac_desc_page, chunks)) /	\
	sizeof(struct rcar_dmac_xfer_chunk))

/*
 * struct rcar_dmac_chan_slave - Slave configuration
 * @slave_addr: slave memory address
 * @xfer_size: size (in bytes) of hardware transfers
 */
struct rcar_dmac_chan_slave {
	phys_addr_t slave_addr;
	unsigned int xfer_size;
};

/*
 * struct rcar_dmac_chan_map - Map of slave device phys to dma address
 * @addr: slave dma address
 * @dir: direction of mapping
 * @slave: slave configuration that is mapped
 */
struct rcar_dmac_chan_map {
	dma_addr_t addr;
	enum dma_data_direction dir;
	struct rcar_dmac_chan_slave slave;
};

/*
 * struct rcar_dmac_chan - R-Car Gen2 DMA Controller Channel
 * @chan: base DMA channel object
 * @iomem: channel I/O memory base
 * @index: index of this channel in the controller
 * @irq: channel IRQ
 * @src: slave memory address and size on the source side
 * @dst: slave memory address and size on the destination side
 * @mid_rid: hardware MID/RID for the DMA client using this channel
 * @lock: protects the channel CHCR register and the desc members
 * @desc.free: list of free descriptors
 * @desc.pending: list of pending descriptors (submitted with tx_submit)
 * @desc.active: list of active descriptors (activated with issue_pending)
 * @desc.done: list of completed descriptors
 * @desc.wait: list of descriptors waiting for an ack
 * @desc.running: the descriptor being processed (a member of the active list)
 * @desc.chunks_free: list of free transfer chunk descriptors
 * @desc.pages: list of pages used by allocated descriptors
 */
struct rcar_dmac_chan {
	struct dma_chan chan;
	void __iomem *iomem;
	unsigned int index;
	int irq;

	struct rcar_dmac_chan_slave src;
	struct rcar_dmac_chan_slave dst;
	struct rcar_dmac_chan_map map;
	int mid_rid;

	spinlock_t lock;

	struct {
		struct list_head free;
		struct list_head pending;
		struct list_head active;
		struct list_head done;
		struct list_head wait;
		struct rcar_dmac_desc *running;

		struct list_head chunks_free;

		struct list_head pages;
	} desc;
};

#define to_rcar_dmac_chan(c)	container_of(c, struct rcar_dmac_chan, chan)

/*
 * struct rcar_dmac - R-Car Gen2 DMA Controller
 * @engine: base DMA engine object
 * @dev: the hardware device
 * @dmac_base: remapped base register block
 * @chan_base: remapped channel register block (optional)
 * @n_channels: number of available channels
 * @channels: array of DMAC channels
 * @channels_mask: bitfield of which DMA channels are managed by this driver
 * @modules: bitmask of client modules in use
 */
struct rcar_dmac {
	struct dma_device engine;
	struct device *dev;
	void __iomem *dmac_base;
	void __iomem *chan_base;

	unsigned int n_channels;
	struct rcar_dmac_chan *channels;
	u32 channels_mask;

	DECLARE_BITMAP(modules, 256);
};

#define to_rcar_dmac(d)		container_of(d, struct rcar_dmac, engine)

#define for_each_rcar_dmac_chan(i, dmac, chan)						\
	for (i = 0, chan = &(dmac)->channels[0]; i < (dmac)->n_channels; i++, chan++)	\
		if (!((dmac)->channels_mask & BIT(i))) continue; else

/*
 * struct rcar_dmac_of_data - This driver's OF data
 * @chan_offset_base: DMAC channels base offset
 * @chan_offset_stride: DMAC channels offset stride
 */
struct rcar_dmac_of_data {
	u32 chan_offset_base;
	u32 chan_offset_stride;
};

/* -----------------------------------------------------------------------------
 * Registers
 */

#define RCAR_DMAISTA			0x0020
#define RCAR_DMASEC			0x0030
#define RCAR_DMAOR			0x0060
#define RCAR_DMAOR_PRI_FIXED		(0 << 8)
#define RCAR_DMAOR_PRI_ROUND_ROBIN	(3 << 8)
#define RCAR_DMAOR_AE			(1 << 2)
#define RCAR_DMAOR_DME			(1 << 0)
#define RCAR_DMACHCLR			0x0080	/* Not on R-Car V3U */
#define RCAR_DMADPSEC			0x00a0

#define RCAR_DMASAR			0x0000
#define RCAR_DMADAR			0x0004
#define RCAR_DMATCR			0x0008
#define RCAR_DMATCR_MASK		0x00ffffff
#define RCAR_DMATSR			0x0028
#define RCAR_DMACHCR			0x000c
#define RCAR_DMACHCR_CAE		(1 << 31)
#define RCAR_DMACHCR_CAIE		(1 << 30)
#define RCAR_DMACHCR_DPM_DISABLED	(0 << 28)
#define RCAR_DMACHCR_DPM_ENABLED	(1 << 28)
#define RCAR_DMACHCR_DPM_REPEAT		(2 << 28)
#define RCAR_DMACHCR_DPM_INFINITE	(3 << 28)
#define RCAR_DMACHCR_RPT_SAR		(1 << 27)
#define RCAR_DMACHCR_RPT_DAR		(1 << 26)
#define RCAR_DMACHCR_RPT_TCR		(1 << 25)
#define RCAR_DMACHCR_DPB		(1 << 22)
#define RCAR_DMACHCR_DSE		(1 << 19)
#define RCAR_DMACHCR_DSIE		(1 << 18)
#define RCAR_DMACHCR_TS_1B		((0 << 20) | (0 << 3))
#define RCAR_DMACHCR_TS_2B		((0 << 20) | (1 << 3))
#define RCAR_DMACHCR_TS_4B		((0 << 20) | (2 << 3))
#define RCAR_DMACHCR_TS_16B		((0 << 20) | (3 << 3))
#define RCAR_DMACHCR_TS_32B		((1 << 20) | (0 << 3))
#define RCAR_DMACHCR_TS_64B		((1 << 20) | (1 << 3))
#define RCAR_DMACHCR_TS_8B		((1 << 20) | (3 << 3))
#define RCAR_DMACHCR_DM_FIXED		(0 << 14)
#define RCAR_DMACHCR_DM_INC		(1 << 14)
#define RCAR_DMACHCR_DM_DEC		(2 << 14)
#define RCAR_DMACHCR_SM_FIXED		(0 << 12)
#define RCAR_DMACHCR_SM_INC		(1 << 12)
#define RCAR_DMACHCR_SM_DEC		(2 << 12)
#define RCAR_DMACHCR_RS_AUTO		(4 << 8)
#define RCAR_DMACHCR_RS_DMARS		(8 << 8)
#define RCAR_DMACHCR_IE			(1 << 2)
#define RCAR_DMACHCR_TE			(1 << 1)
#define RCAR_DMACHCR_DE			(1 << 0)
#define RCAR_DMATCRB			0x0018
#define RCAR_DMATSRB			0x0038
#define RCAR_DMACHCRB			0x001c
#define RCAR_DMACHCRB_DCNT(n)		((n) << 24)
#define RCAR_DMACHCRB_DPTR_MASK		(0xff << 16)
#define RCAR_DMACHCRB_DPTR_SHIFT	16
#define RCAR_DMACHCRB_DRST		(1 << 15)
#define RCAR_DMACHCRB_DTS		(1 << 8)
#define RCAR_DMACHCRB_SLM_NORMAL	(0 << 4)
#define RCAR_DMACHCRB_SLM_CLK(n)	((8 | (n)) << 4)
#define RCAR_DMACHCRB_PRI(n)		((n) << 0)
#define RCAR_DMARS			0x0040
#define RCAR_DMABUFCR			0x0048
#define RCAR_DMABUFCR_MBU(n)		((n) << 16)
#define RCAR_DMABUFCR_ULB(n)		((n) << 0)
#define RCAR_DMADPBASE			0x0050
#define RCAR_DMADPBASE_MASK		0xfffffff0
#define RCAR_DMADPBASE_SEL		(1 << 0)
#define RCAR_DMADPCR			0x0054
#define RCAR_DMADPCR_DIPT(n)		((n) << 24)
#define RCAR_DMAFIXSAR			0x0010
#define RCAR_DMAFIXDAR			0x0014
#define RCAR_DMAFIXDPBASE		0x0060

/* For R-Car V3U */
#define RCAR_V3U_DMACHCLR		0x0100

/* Hardcode the MEMCPY transfer size to 4 bytes. */
#define RCAR_DMAC_MEMCPY_XFER_SIZE	4

/* -----------------------------------------------------------------------------
 * Device access
 */

static void rcar_dmac_write(struct rcar_dmac *dmac, u32 reg, u32 data)
{
	if (reg == RCAR_DMAOR)
		writew(data, dmac->dmac_base + reg);
	else
		writel(data, dmac->dmac_base + reg);
}

static u32 rcar_dmac_read(struct rcar_dmac *dmac, u32 reg)
{
	if (reg == RCAR_DMAOR)
		return readw(dmac->dmac_base + reg);
	else
		return readl(dmac->dmac_base + reg);
}

static u32 rcar_dmac_chan_read(struct rcar_dmac_chan *chan, u32 reg)
{
	if (reg == RCAR_DMARS)
		return readw(chan->iomem + reg);
	else
		return readl(chan->iomem + reg);
}

static void rcar_dmac_chan_write(struct rcar_dmac_chan *chan, u32 reg, u32 data)
{
	if (reg == RCAR_DMARS)
		writew(data, chan->iomem + reg);
	else
		writel(data, chan->iomem + reg);
}

static void rcar_dmac_chan_clear(struct rcar_dmac *dmac,
				 struct rcar_dmac_chan *chan)
{
	if (dmac->chan_base)
		rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
	else
		rcar_dmac_write(dmac, RCAR_DMACHCLR, BIT(chan->index));
}

static void rcar_dmac_chan_clear_all(struct rcar_dmac *dmac)
{
	struct rcar_dmac_chan *chan;
	unsigned int i;

	if (dmac->chan_base) {
		for_each_rcar_dmac_chan(i, dmac, chan)
			rcar_dmac_chan_write(chan, RCAR_V3U_DMACHCLR, 1);
	} else {
		rcar_dmac_write(dmac, RCAR_DMACHCLR, dmac->channels_mask);
	}
}

/* -----------------------------------------------------------------------------
 * Initialization and configuration
 */

static bool rcar_dmac_chan_is_busy(struct rcar_dmac_chan *chan)
{
	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);

	return !!(chcr & (RCAR_DMACHCR_DE | RCAR_DMACHCR_TE));
}

static void rcar_dmac_chan_start_xfer(struct rcar_dmac_chan *chan)
{
	struct rcar_dmac_desc *desc = chan->desc.running;
	u32 chcr = desc->chcr;

	WARN_ON_ONCE(rcar_dmac_chan_is_busy(chan));

	if (chan->mid_rid >= 0)
		rcar_dmac_chan_write(chan, RCAR_DMARS, chan->mid_rid);

	if (desc->hwdescs.use) {
		struct rcar_dmac_xfer_chunk *chunk =
			list_first_entry(&desc->chunks,
					 struct rcar_dmac_xfer_chunk, node);

		dev_dbg(chan->chan.device->dev,
			"chan%u: queue desc %p: %u@%pad\n",
			chan->index, desc, desc->nchunks, &desc->hwdescs.dma);

#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
		rcar_dmac_chan_write(chan, RCAR_DMAFIXSAR,
				     chunk->src_addr >> 32);
		rcar_dmac_chan_write(chan, RCAR_DMAFIXDAR,
				     chunk->dst_addr >> 32);
		rcar_dmac_chan_write(chan, RCAR_DMAFIXDPBASE,
				     desc->hwdescs.dma >> 32);
#endif
		rcar_dmac_chan_write(chan, RCAR_DMADPBASE,
				     (desc->hwdescs.dma & 0xfffffff0) |
				     RCAR_DMADPBASE_SEL);
		rcar_dmac_chan_write(chan, RCAR_DMACHCRB,
				     RCAR_DMACHCRB_DCNT(desc->nchunks - 1) |
				     RCAR_DMACHCRB_DRST);

		/*
		 * Errata: When descriptor memory is accessed through an IOMMU
		 * the DMADAR register isn't initialized automatically from the
		 * first descriptor at beginning of transfer by the DMAC like it
		 * should. Initialize it manually with the destination address
		 * of the first chunk.
		 */
		rcar_dmac_chan_write(chan, RCAR_DMADAR,
				     chunk->dst_addr & 0xffffffff);

		/*
		 * Program the descriptor stage interrupt to occur after the end
		 * of the first stage.
		 */
		rcar_dmac_chan_write(chan, RCAR_DMADPCR, RCAR_DMADPCR_DIPT(1));

		chcr |= RCAR_DMACHCR_RPT_SAR | RCAR_DMACHCR_RPT_DAR
		     |  RCAR_DMACHCR_RPT_TCR | RCAR_DMACHCR_DPB;

		/*
		 * If the descriptor isn't cyclic enable normal descriptor mode
		 * and the transfer completion interrupt.
		 */
		if (!desc->cyclic)
			chcr |= RCAR_DMACHCR_DPM_ENABLED | RCAR_DMACHCR_IE;
		/*
		 * If the descriptor is cyclic and has a callback enable the
		 * descriptor stage interrupt in infinite repeat mode.
		 */
		else if (desc->async_tx.callback)
			chcr |= RCAR_DMACHCR_DPM_INFINITE | RCAR_DMACHCR_DSIE;
		/*
		 * Otherwise just select infinite repeat mode without any
		 * interrupt.
		 */
		else
			chcr |= RCAR_DMACHCR_DPM_INFINITE;
	} else {
		struct rcar_dmac_xfer_chunk *chunk = desc->running;

		dev_dbg(chan->chan.device->dev,
			"chan%u: queue chunk %p: %u@%pad -> %pad\n",
			chan->index, chunk, chunk->size, &chunk->src_addr,
			&chunk->dst_addr);

#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
		rcar_dmac_chan_write(chan, RCAR_DMAFIXSAR,
				     chunk->src_addr >> 32);
		rcar_dmac_chan_write(chan, RCAR_DMAFIXDAR,
				     chunk->dst_addr >> 32);
#endif
		rcar_dmac_chan_write(chan, RCAR_DMASAR,
				     chunk->src_addr & 0xffffffff);
		rcar_dmac_chan_write(chan, RCAR_DMADAR,
				     chunk->dst_addr & 0xffffffff);
		rcar_dmac_chan_write(chan, RCAR_DMATCR,
				     chunk->size >> desc->xfer_shift);

		chcr |= RCAR_DMACHCR_DPM_DISABLED | RCAR_DMACHCR_IE;
	}

	rcar_dmac_chan_write(chan, RCAR_DMACHCR,
			     chcr | RCAR_DMACHCR_DE | RCAR_DMACHCR_CAIE);
}

static int rcar_dmac_init(struct rcar_dmac *dmac)
{
	u16 dmaor;

	/* Clear all channels and enable the DMAC globally. */
	rcar_dmac_chan_clear_all(dmac);
	rcar_dmac_write(dmac, RCAR_DMAOR,
			RCAR_DMAOR_PRI_FIXED | RCAR_DMAOR_DME);

	dmaor = rcar_dmac_read(dmac, RCAR_DMAOR);
	if ((dmaor & (RCAR_DMAOR_AE | RCAR_DMAOR_DME)) != RCAR_DMAOR_DME) {
		dev_warn(dmac->dev, "DMAOR initialization failed.\n");
		return -EIO;
	}

	return 0;
}

/* -----------------------------------------------------------------------------
 * Descriptors submission
 */

static dma_cookie_t rcar_dmac_tx_submit(struct dma_async_tx_descriptor *tx)
{
	struct rcar_dmac_chan *chan = to_rcar_dmac_chan(tx->chan);
	struct rcar_dmac_desc *desc = to_rcar_dmac_desc(tx);
	unsigned long flags;
	dma_cookie_t cookie;

	spin_lock_irqsave(&chan->lock, flags);

	cookie = dma_cookie_assign(tx);

	dev_dbg(chan->chan.device->dev, "chan%u: submit #%d@%p\n",
		chan->index, tx->cookie, desc);

	list_add_tail(&desc->node, &chan->desc.pending);
	desc->running = list_first_entry(&desc->chunks,
					 struct rcar_dmac_xfer_chunk, node);

	spin_unlock_irqrestore(&chan->lock, flags);

	return cookie;
}

/* -----------------------------------------------------------------------------
 * Descriptors allocation and free
 */

/*
 * rcar_dmac_desc_alloc - Allocate a page worth of DMA descriptors
 * @chan: the DMA channel
 * @gfp: allocation flags
 */
static int rcar_dmac_desc_alloc(struct rcar_dmac_chan *chan, gfp_t gfp)
{
	struct rcar_dmac_desc_page *page;
	unsigned long flags;
	LIST_HEAD(list);
	unsigned int i;

	page = (void *)get_zeroed_page(gfp);
	if (!page)
		return -ENOMEM;

	for (i = 0; i < RCAR_DMAC_DESCS_PER_PAGE; ++i) {
		struct rcar_dmac_desc *desc = &page->descs[i];

		dma_async_tx_descriptor_init(&desc->async_tx, &chan->chan);
		desc->async_tx.tx_submit = rcar_dmac_tx_submit;
		INIT_LIST_HEAD(&desc->chunks);

		list_add_tail(&desc->node, &list);
	}

	spin_lock_irqsave(&chan->lock, flags);
	list_splice_tail(&list, &chan->desc.free);
	list_add_tail(&page->node, &chan->desc.pages);
	spin_unlock_irqrestore(&chan->lock, flags);

	return 0;
}

/*
 * rcar_dmac_desc_put - Release a DMA transfer descriptor
 * @chan: the DMA channel
 * @desc: the descriptor
 *
 * Put the descriptor and its transfer chunk descriptors back in the channel's
 * free descriptors lists. The descriptor's chunks list will be reinitialized to
 * an empty list as a result.
 *
 * The descriptor must have been removed from the channel's lists before calling
 * this function.
 */
static void rcar_dmac_desc_put(struct rcar_dmac_chan *chan,
			       struct rcar_dmac_desc *desc)
{
	unsigned long flags;

	spin_lock_irqsave(&chan->lock, flags);
	list_splice_tail_init(&desc->chunks, &chan->desc.chunks_free);
	list_add(&desc->node, &chan->desc.free);
	spin_unlock_irqrestore(&chan->lock, flags);
}

static void rcar_dmac_desc_recycle_acked(struct rcar_dmac_chan *chan)
{
	struct rcar_dmac_desc *desc, *_desc;
	unsigned long flags;
	LIST_HEAD(list);

	/*
	 * We have to temporarily move all descriptors from the wait list to a
	 * local list as iterating over the wait list, even with
	 * list_for_each_entry_safe, isn't safe if we release the channel lock
	 * around the rcar_dmac_desc_put() call.
	 */
	spin_lock_irqsave(&chan->lock, flags);
	list_splice_init(&chan->desc.wait, &list);
	spin_unlock_irqrestore(&chan->lock, flags);

	list_for_each_entry_safe(desc, _desc, &list, node) {
		if (async_tx_test_ack(&desc->async_tx)) {
			list_del(&desc->node);
			rcar_dmac_desc_put(chan, desc);
		}
	}

	if (list_empty(&list))
		return;

	/* Put the remaining descriptors back in the wait list. */
	spin_lock_irqsave(&chan->lock, flags);
	list_splice(&list, &chan->desc.wait);
	spin_unlock_irqrestore(&chan->lock, flags);
}

/*
 * rcar_dmac_desc_get - Allocate a descriptor for a DMA transfer
 * @chan: the DMA channel
 *
 * Locking: This function must be called in a non-atomic context.
 *
 * Return: A pointer to the allocated descriptor or NULL if no descriptor can
 * be allocated.
 */
static struct rcar_dmac_desc *rcar_dmac_desc_get(struct rcar_dmac_chan *chan)
{
	struct rcar_dmac_desc *desc;
	unsigned long flags;
	int ret;

	/* Recycle acked descriptors before attempting allocation. */
	rcar_dmac_desc_recycle_acked(chan);

	spin_lock_irqsave(&chan->lock, flags);

	while (list_empty(&chan->desc.free)) {
		/*
		 * No free descriptors, allocate a page worth of them and try
		 * again, as someone else could race us to get the newly
		 * allocated descriptors. If the allocation fails return an
		 * error.
		 */
		spin_unlock_irqrestore(&chan->lock, flags);
		ret = rcar_dmac_desc_alloc(chan, GFP_NOWAIT);
		if (ret < 0)
			return NULL;
		spin_lock_irqsave(&chan->lock, flags);
	}

	desc = list_first_entry(&chan->desc.free, struct rcar_dmac_desc, node);
	list_del(&desc->node);

	spin_unlock_irqrestore(&chan->lock, flags);

	return desc;
}

/*
 * rcar_dmac_xfer_chunk_alloc - Allocate a page worth of transfer chunks
 * @chan: the DMA channel
 * @gfp: allocation flags
 */
static int rcar_dmac_xfer_chunk_alloc(struct rcar_dmac_chan *chan, gfp_t gfp)
{
	struct rcar_dmac_desc_page *page;
	unsigned long flags;
	LIST_HEAD(list);
	unsigned int i;

	page = (void *)get_zeroed_page(gfp);
	if (!page)
		return -ENOMEM;

	for (i = 0; i < RCAR_DMAC_XFER_CHUNKS_PER_PAGE; ++i) {
		struct rcar_dmac_xfer_chunk *chunk = &page->chunks[i];

		list_add_tail(&chunk->node, &list);
	}

	spin_lock_irqsave(&chan->lock, flags);
	list_splice_tail(&list, &chan->desc.chunks_free);
	list_add_tail(&page->node, &chan->desc.pages);
	spin_unlock_irqrestore(&chan->lock, flags);

	return 0;
}

/*
 * rcar_dmac_xfer_chunk_get - Allocate a transfer chunk for a DMA transfer
 * @chan: the DMA channel
 *
 * Locking: This function must be called in a non-atomic context.
 *
 * Return: A pointer to the allocated transfer chunk descriptor or NULL if no
 * descriptor can be allocated.
 */
static struct rcar_dmac_xfer_chunk *
rcar_dmac_xfer_chunk_get(struct rcar_dmac_chan *chan)
{
	struct rcar_dmac_xfer_chunk *chunk;
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&chan->lock, flags);

	while (list_empty(&chan->desc.chunks_free)) {
		/*
		 * No free descriptors, allocate a page worth of them and try
		 * again, as someone else could race us to get the newly
		 * allocated descriptors. If the allocation fails return an
		 * error.
		 */
		spin_unlock_irqrestore(&chan->lock, flags);
		ret = rcar_dmac_xfer_chunk_alloc(chan, GFP_NOWAIT);
		if (ret < 0)
			return NULL;
		spin_lock_irqsave(&chan->lock, flags);
	}

	chunk = list_first_entry(&chan->desc.chunks_free,
				 struct rcar_dmac_xfer_chunk, node);
	list_del(&chunk->node);

	spin_unlock_irqrestore(&chan->lock, flags);

	return chunk;
}

static void rcar_dmac_realloc_hwdesc(struct rcar_dmac_chan *chan,
				     struct rcar_dmac_desc *desc, size_t size)
{
	/*
	 * dma_alloc_coherent() allocates memory in page size increments. To
	 * avoid reallocating the hardware descriptors when the allocated size
	 * wouldn't change align the requested size to a multiple of the page
	 * size.
	 */
	size = PAGE_ALIGN(size);

	if (desc->hwdescs.size == size)
		return;

	if (desc->hwdescs.mem) {
		dma_free_coherent(chan->chan.device->dev, desc->hwdescs.size,
				  desc->hwdescs.mem, desc->hwdescs.dma);
		desc->hwdescs.mem = NULL;
		desc->hwdescs.size = 0;
	}

	if (!size)
		return;

	desc->hwdescs.mem = dma_alloc_coherent(chan->chan.device->dev, size,
					       &desc->hwdescs.dma, GFP_NOWAIT);
	if (!desc->hwdescs.mem)
		return;

	desc->hwdescs.size = size;
}

static int rcar_dmac_fill_hwdesc(struct rcar_dmac_chan *chan,
				 struct rcar_dmac_desc *desc)
{
	struct rcar_dmac_xfer_chunk *chunk;
	struct rcar_dmac_hw_desc *hwdesc;

	rcar_dmac_realloc_hwdesc(chan, desc, desc->nchunks * sizeof(*hwdesc));

	hwdesc = desc->hwdescs.mem;
	if (!hwdesc)
		return -ENOMEM;

	list_for_each_entry(chunk, &desc->chunks, node) {
		hwdesc->sar = chunk->src_addr;
		hwdesc->dar = chunk->dst_addr;
		hwdesc->tcr = chunk->size >> desc->xfer_shift;
		hwdesc++;
	}

	return 0;
}

/* -----------------------------------------------------------------------------
 * Stop and reset
 */
static void rcar_dmac_chcr_de_barrier(struct rcar_dmac_chan *chan)
{
	u32 chcr;
	unsigned int i;

	/*
	 * Ensure that the setting of the DE bit is actually 0 after
	 * clearing it.
	 */
	for (i = 0; i < 1024; i++) {
		chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
		if (!(chcr & RCAR_DMACHCR_DE))
			return;
		udelay(1);
	}

	dev_err(chan->chan.device->dev, "CHCR DE check error\n");
}

static void rcar_dmac_clear_chcr_de(struct rcar_dmac_chan *chan)
{
	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);

	/* set DE=0 and flush remaining data */
	rcar_dmac_chan_write(chan, RCAR_DMACHCR, (chcr & ~RCAR_DMACHCR_DE));

	/* make sure all remaining data was flushed */
	rcar_dmac_chcr_de_barrier(chan);
}

static void rcar_dmac_chan_halt(struct rcar_dmac_chan *chan)
{
	u32 chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);

	chcr &= ~(RCAR_DMACHCR_DSE | RCAR_DMACHCR_DSIE | RCAR_DMACHCR_IE |
		  RCAR_DMACHCR_TE | RCAR_DMACHCR_DE |
		  RCAR_DMACHCR_CAE | RCAR_DMACHCR_CAIE);
	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr);
	rcar_dmac_chcr_de_barrier(chan);
}

static void rcar_dmac_chan_reinit(struct rcar_dmac_chan *chan)
{
	struct rcar_dmac_desc *desc, *_desc;
	unsigned long flags;
	LIST_HEAD(descs);

	spin_lock_irqsave(&chan->lock, flags);

	/* Move all non-free descriptors to the local lists. */
	list_splice_init(&chan->desc.pending, &descs);
	list_splice_init(&chan->desc.active, &descs);
	list_splice_init(&chan->desc.done, &descs);
	list_splice_init(&chan->desc.wait, &descs);

	chan->desc.running = NULL;

	spin_unlock_irqrestore(&chan->lock, flags);

	list_for_each_entry_safe(desc, _desc, &descs, node) {
		list_del(&desc->node);
		rcar_dmac_desc_put(chan, desc);
	}
}

static void rcar_dmac_stop_all_chan(struct rcar_dmac *dmac)
{
	struct rcar_dmac_chan *chan;
	unsigned int i;

	/* Stop all channels. */
	for_each_rcar_dmac_chan(i, dmac, chan) {
		/* Stop and reinitialize the channel. */
		spin_lock_irq(&chan->lock);
		rcar_dmac_chan_halt(chan);
		spin_unlock_irq(&chan->lock);
	}
}

static int rcar_dmac_chan_pause(struct dma_chan *chan)
{
	unsigned long flags;
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);

	spin_lock_irqsave(&rchan->lock, flags);
	rcar_dmac_clear_chcr_de(rchan);
	spin_unlock_irqrestore(&rchan->lock, flags);

	return 0;
}

/* -----------------------------------------------------------------------------
 * Descriptors preparation
 */

static void rcar_dmac_chan_configure_desc(struct rcar_dmac_chan *chan,
					  struct rcar_dmac_desc *desc)
{
	static const u32 chcr_ts[] = {
		RCAR_DMACHCR_TS_1B, RCAR_DMACHCR_TS_2B,
		RCAR_DMACHCR_TS_4B, RCAR_DMACHCR_TS_8B,
		RCAR_DMACHCR_TS_16B, RCAR_DMACHCR_TS_32B,
		RCAR_DMACHCR_TS_64B,
	};

	unsigned int xfer_size;
	u32 chcr;

	switch (desc->direction) {
	case DMA_DEV_TO_MEM:
		chcr = RCAR_DMACHCR_DM_INC | RCAR_DMACHCR_SM_FIXED
		     | RCAR_DMACHCR_RS_DMARS;
		xfer_size = chan->src.xfer_size;
		break;

	case DMA_MEM_TO_DEV:
		chcr = RCAR_DMACHCR_DM_FIXED | RCAR_DMACHCR_SM_INC
		     | RCAR_DMACHCR_RS_DMARS;
		xfer_size = chan->dst.xfer_size;
		break;

	case DMA_MEM_TO_MEM:
	default:
		chcr = RCAR_DMACHCR_DM_INC | RCAR_DMACHCR_SM_INC
		     | RCAR_DMACHCR_RS_AUTO;
		xfer_size = RCAR_DMAC_MEMCPY_XFER_SIZE;
		break;
	}

	desc->xfer_shift = ilog2(xfer_size);
	desc->chcr = chcr | chcr_ts[desc->xfer_shift];
}

/*
 * rcar_dmac_chan_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_MEM_TO_MEM
 * and the SG list contains only one element and points at the source buffer.
 */
static struct dma_async_tx_descriptor *
rcar_dmac_chan_prep_sg(struct rcar_dmac_chan *chan, struct scatterlist *sgl,
		       unsigned int sg_len, dma_addr_t dev_addr,
		       enum dma_transfer_direction dir, unsigned long dma_flags,
		       bool cyclic)
{
	struct rcar_dmac_xfer_chunk *chunk;
	struct rcar_dmac_desc *desc;
	struct scatterlist *sg;
	unsigned int nchunks = 0;
	unsigned int max_chunk_size;
	unsigned int full_size = 0;
	bool cross_boundary = false;
	unsigned int i;
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
	u32 high_dev_addr;
	u32 high_mem_addr;
#endif

	desc = rcar_dmac_desc_get(chan);
	if (!desc)
		return NULL;

	desc->async_tx.flags = dma_flags;
	desc->async_tx.cookie = -EBUSY;

	desc->cyclic = cyclic;
	desc->direction = dir;

	rcar_dmac_chan_configure_desc(chan, desc);

	max_chunk_size = RCAR_DMATCR_MASK << desc->xfer_shift;

	/*
	 * Allocate and fill the transfer chunk descriptors. We own the only
	 * reference to the DMA descriptor, there's no need for locking.
	 */
	for_each_sg(sgl, sg, sg_len, i) {
		dma_addr_t mem_addr = sg_dma_address(sg);
		unsigned int len = sg_dma_len(sg);

		full_size += len;

#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
		if (i == 0) {
			high_dev_addr = dev_addr >> 32;
			high_mem_addr = mem_addr >> 32;
		}

		if ((dev_addr >> 32 != high_dev_addr) ||
		    (mem_addr >> 32 != high_mem_addr))
			cross_boundary = true;
#endif
		while (len) {
			unsigned int size = min(len, max_chunk_size);

#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
			/*
			 * Prevent individual transfers from crossing 4GB
			 * boundaries.
			 */
			if (dev_addr >> 32 != (dev_addr + size - 1) >> 32) {
				size = ALIGN(dev_addr, 1ULL << 32) - dev_addr;
				cross_boundary = true;
			}
			if (mem_addr >> 32 != (mem_addr + size - 1) >> 32) {
				size = ALIGN(mem_addr, 1ULL << 32) - mem_addr;
				cross_boundary = true;
			}
#endif

			chunk = rcar_dmac_xfer_chunk_get(chan);
			if (!chunk) {
				rcar_dmac_desc_put(chan, desc);
				return NULL;
			}

			if (dir == DMA_DEV_TO_MEM) {
				chunk->src_addr = dev_addr;
				chunk->dst_addr = mem_addr;
			} else {
				chunk->src_addr = mem_addr;
				chunk->dst_addr = dev_addr;
			}

			chunk->size = size;

			dev_dbg(chan->chan.device->dev,
				"chan%u: chunk %p/%p sgl %u@%p, %u/%u %pad -> %pad\n",
				chan->index, chunk, desc, i, sg, size, len,
				&chunk->src_addr, &chunk->dst_addr);

			mem_addr += size;
			if (dir == DMA_MEM_TO_MEM)
				dev_addr += size;

			len -= size;

			list_add_tail(&chunk->node, &desc->chunks);
			nchunks++;
		}
	}

	desc->nchunks = nchunks;
	desc->size = full_size;

	/*
	 * Use hardware descriptor lists if possible when more than one chunk
	 * needs to be transferred (otherwise they don't make much sense).
	 *
	 * Source/Destination address should be located in same 4GiB region
	 * in the 40bit address space when it uses Hardware descriptor,
	 * and cross_boundary is checking it.
	 */
	desc->hwdescs.use = !cross_boundary && nchunks > 1;
	if (desc->hwdescs.use) {
		if (rcar_dmac_fill_hwdesc(chan, desc) < 0)
			desc->hwdescs.use = false;
	}

	return &desc->async_tx;
}

/* -----------------------------------------------------------------------------
 * DMA engine operations
 */

static int rcar_dmac_alloc_chan_resources(struct dma_chan *chan)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	int ret;

	INIT_LIST_HEAD(&rchan->desc.chunks_free);
	INIT_LIST_HEAD(&rchan->desc.pages);

	/* Preallocate descriptors. */
	ret = rcar_dmac_xfer_chunk_alloc(rchan, GFP_KERNEL);
	if (ret < 0)
		return -ENOMEM;

	ret = rcar_dmac_desc_alloc(rchan, GFP_KERNEL);
	if (ret < 0)
		return -ENOMEM;

	return pm_runtime_get_sync(chan->device->dev);
}

static void rcar_dmac_free_chan_resources(struct dma_chan *chan)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	struct rcar_dmac *dmac = to_rcar_dmac(chan->device);
	struct rcar_dmac_chan_map *map = &rchan->map;
	struct rcar_dmac_desc_page *page, *_page;
	struct rcar_dmac_desc *desc;
	LIST_HEAD(list);

	/* Protect against ISR */
	spin_lock_irq(&rchan->lock);
	rcar_dmac_chan_halt(rchan);
	spin_unlock_irq(&rchan->lock);

	/*
	 * Now no new interrupts will occur, but one might already be
	 * running. Wait for it to finish before freeing resources.
	 */
	synchronize_irq(rchan->irq);

	if (rchan->mid_rid >= 0) {
		/* The caller is holding dma_list_mutex */
		clear_bit(rchan->mid_rid, dmac->modules);
		rchan->mid_rid = -EINVAL;
	}

	list_splice_init(&rchan->desc.free, &list);
	list_splice_init(&rchan->desc.pending, &list);
	list_splice_init(&rchan->desc.active, &list);
	list_splice_init(&rchan->desc.done, &list);
	list_splice_init(&rchan->desc.wait, &list);

	rchan->desc.running = NULL;

	list_for_each_entry(desc, &list, node)
		rcar_dmac_realloc_hwdesc(rchan, desc, 0);

	list_for_each_entry_safe(page, _page, &rchan->desc.pages, node) {
		list_del(&page->node);
		free_page((unsigned long)page);
	}

	/* Remove slave mapping if present. */
	if (map->slave.xfer_size) {
		dma_unmap_resource(chan->device->dev, map->addr,
				   map->slave.xfer_size, map->dir, 0);
		map->slave.xfer_size = 0;
	}

	pm_runtime_put(chan->device->dev);
}

static struct dma_async_tx_descriptor *
rcar_dmac_prep_dma_memcpy(struct dma_chan *chan, dma_addr_t dma_dest,
			  dma_addr_t dma_src, size_t len, unsigned long flags)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	struct scatterlist sgl;

	if (!len)
		return NULL;

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

	return rcar_dmac_chan_prep_sg(rchan, &sgl, 1, dma_dest,
				      DMA_MEM_TO_MEM, flags, false);
}

static int rcar_dmac_map_slave_addr(struct dma_chan *chan,
				    enum dma_transfer_direction dir)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	struct rcar_dmac_chan_map *map = &rchan->map;
	phys_addr_t dev_addr;
	size_t dev_size;
	enum dma_data_direction dev_dir;

	if (dir == DMA_DEV_TO_MEM) {
		dev_addr = rchan->src.slave_addr;
		dev_size = rchan->src.xfer_size;
		dev_dir = DMA_TO_DEVICE;
	} else {
		dev_addr = rchan->dst.slave_addr;
		dev_size = rchan->dst.xfer_size;
		dev_dir = DMA_FROM_DEVICE;
	}

	/* Reuse current map if possible. */
	if (dev_addr == map->slave.slave_addr &&
	    dev_size == map->slave.xfer_size &&
	    dev_dir == map->dir)
		return 0;

	/* Remove old mapping if present. */
	if (map->slave.xfer_size)
		dma_unmap_resource(chan->device->dev, map->addr,
				   map->slave.xfer_size, map->dir, 0);
	map->slave.xfer_size = 0;

	/* Create new slave address map. */
	map->addr = dma_map_resource(chan->device->dev, dev_addr, dev_size,
				     dev_dir, 0);

	if (dma_mapping_error(chan->device->dev, map->addr)) {
		dev_err(chan->device->dev,
			"chan%u: failed to map %zx@%pap", rchan->index,
			dev_size, &dev_addr);
		return -EIO;
	}

	dev_dbg(chan->device->dev, "chan%u: map %zx@%pap to %pad dir: %s\n",
		rchan->index, dev_size, &dev_addr, &map->addr,
		dev_dir == DMA_TO_DEVICE ? "DMA_TO_DEVICE" : "DMA_FROM_DEVICE");

	map->slave.slave_addr = dev_addr;
	map->slave.xfer_size = dev_size;
	map->dir = dev_dir;

	return 0;
}

static struct dma_async_tx_descriptor *
rcar_dmac_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
			unsigned int sg_len, enum dma_transfer_direction dir,
			unsigned long flags, void *context)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);

	/* Someone calling slave DMA on a generic channel? */
	if (rchan->mid_rid < 0 || !sg_len || !sg_dma_len(sgl)) {
		dev_warn(chan->device->dev,
			 "%s: bad parameter: len=%d, id=%d\n",
			 __func__, sg_len, rchan->mid_rid);
		return NULL;
	}

	if (rcar_dmac_map_slave_addr(chan, dir))
		return NULL;

	return rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
				      dir, flags, false);
}

#define RCAR_DMAC_MAX_SG_LEN	32

static struct dma_async_tx_descriptor *
rcar_dmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
			  size_t buf_len, size_t period_len,
			  enum dma_transfer_direction dir, unsigned long flags)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	struct dma_async_tx_descriptor *desc;
	struct scatterlist *sgl;
	unsigned int sg_len;
	unsigned int i;

	/* Someone calling slave DMA on a generic channel? */
	if (rchan->mid_rid < 0 || buf_len < period_len) {
		dev_warn(chan->device->dev,
			"%s: bad parameter: buf_len=%zu, period_len=%zu, id=%d\n",
			__func__, buf_len, period_len, rchan->mid_rid);
		return NULL;
	}

	if (rcar_dmac_map_slave_addr(chan, dir))
		return NULL;

	sg_len = buf_len / period_len;
	if (sg_len > RCAR_DMAC_MAX_SG_LEN) {
		dev_err(chan->device->dev,
			"chan%u: sg length %d exceeds limit %d",
			rchan->index, sg_len, RCAR_DMAC_MAX_SG_LEN);
		return NULL;
	}

	/*
	 * Allocate the sg list dynamically as it would consume too much stack
	 * space.
	 */
	sgl = kmalloc_array(sg_len, sizeof(*sgl), GFP_NOWAIT);
	if (!sgl)
		return NULL;

	sg_init_table(sgl, sg_len);

	for (i = 0; i < sg_len; ++i) {
		dma_addr_t src = buf_addr + (period_len * i);

		sg_set_page(&sgl[i], pfn_to_page(PFN_DOWN(src)), period_len,
			    offset_in_page(src));
		sg_dma_address(&sgl[i]) = src;
		sg_dma_len(&sgl[i]) = period_len;
	}

	desc = rcar_dmac_chan_prep_sg(rchan, sgl, sg_len, rchan->map.addr,
				      dir, flags, true);

	kfree(sgl);
	return desc;
}

static int rcar_dmac_device_config(struct dma_chan *chan,
				   struct dma_slave_config *cfg)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);

	/*
	 * We could lock this, but you shouldn't be configuring the
	 * channel, while using it...
	 */
	rchan->src.slave_addr = cfg->src_addr;
	rchan->dst.slave_addr = cfg->dst_addr;
	rchan->src.xfer_size = cfg->src_addr_width;
	rchan->dst.xfer_size = cfg->dst_addr_width;

	return 0;
}

static int rcar_dmac_chan_terminate_all(struct dma_chan *chan)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	unsigned long flags;

	spin_lock_irqsave(&rchan->lock, flags);
	rcar_dmac_chan_halt(rchan);
	spin_unlock_irqrestore(&rchan->lock, flags);

	/*
	 * FIXME: No new interrupt can occur now, but the IRQ thread might still
	 * be running.
	 */

	rcar_dmac_chan_reinit(rchan);

	return 0;
}

static unsigned int rcar_dmac_chan_get_residue(struct rcar_dmac_chan *chan,
					       dma_cookie_t cookie)
{
	struct rcar_dmac_desc *desc = chan->desc.running;
	struct rcar_dmac_xfer_chunk *running = NULL;
	struct rcar_dmac_xfer_chunk *chunk;
	enum dma_status status;
	unsigned int residue = 0;
	unsigned int dptr = 0;
	unsigned int chcrb;
	unsigned int tcrb;
	unsigned int i;

	if (!desc)
		return 0;

	/*
	 * If the cookie corresponds to a descriptor that has been completed
	 * there is no residue. The same check has already been performed by the
	 * caller but without holding the channel lock, so the descriptor could
	 * now be complete.
	 */
	status = dma_cookie_status(&chan->chan, cookie, NULL);
	if (status == DMA_COMPLETE)
		return 0;

	/*
	 * If the cookie doesn't correspond to the currently running transfer
	 * then the descriptor hasn't been processed yet, and the residue is
	 * equal to the full descriptor size.
	 * Also, a client driver is possible to call this function before
	 * rcar_dmac_isr_channel_thread() runs. In this case, the "desc.running"
	 * will be the next descriptor, and the done list will appear. So, if
	 * the argument cookie matches the done list's cookie, we can assume
	 * the residue is zero.
	 */
	if (cookie != desc->async_tx.cookie) {
		list_for_each_entry(desc, &chan->desc.done, node) {
			if (cookie == desc->async_tx.cookie)
				return 0;
		}
		list_for_each_entry(desc, &chan->desc.pending, node) {
			if (cookie == desc->async_tx.cookie)
				return desc->size;
		}
		list_for_each_entry(desc, &chan->desc.active, node) {
			if (cookie == desc->async_tx.cookie)
				return desc->size;
		}

		/*
		 * No descriptor found for the cookie, there's thus no residue.
		 * This shouldn't happen if the calling driver passes a correct
		 * cookie value.
		 */
		WARN(1, "No descriptor for cookie!");
		return 0;
	}

	/*
	 * We need to read two registers.
	 * Make sure the control register does not skip to next chunk
	 * while reading the counter.
	 * Trying it 3 times should be enough: Initial read, retry, retry
	 * for the paranoid.
	 */
	for (i = 0; i < 3; i++) {
		chcrb = rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
					    RCAR_DMACHCRB_DPTR_MASK;
		tcrb = rcar_dmac_chan_read(chan, RCAR_DMATCRB);
		/* Still the same? */
		if (chcrb == (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
			      RCAR_DMACHCRB_DPTR_MASK))
			break;
	}
	WARN_ONCE(i >= 3, "residue might be not continuous!");

	/*
	 * In descriptor mode the descriptor running pointer is not maintained
	 * by the interrupt handler, find the running descriptor from the
	 * descriptor pointer field in the CHCRB register. In non-descriptor
	 * mode just use the running descriptor pointer.
	 */
	if (desc->hwdescs.use) {
		dptr = chcrb >> RCAR_DMACHCRB_DPTR_SHIFT;
		if (dptr == 0)
			dptr = desc->nchunks;
		dptr--;
		WARN_ON(dptr >= desc->nchunks);
	} else {
		running = desc->running;
	}

	/* Compute the size of all chunks still to be transferred. */
	list_for_each_entry_reverse(chunk, &desc->chunks, node) {
		if (chunk == running || ++dptr == desc->nchunks)
			break;

		residue += chunk->size;
	}

	/* Add the residue for the current chunk. */
	residue += tcrb << desc->xfer_shift;

	return residue;
}

static enum dma_status rcar_dmac_tx_status(struct dma_chan *chan,
					   dma_cookie_t cookie,
					   struct dma_tx_state *txstate)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	enum dma_status status;
	unsigned long flags;
	unsigned int residue;
	bool cyclic;

	status = dma_cookie_status(chan, cookie, txstate);
	if (status == DMA_COMPLETE || !txstate)
		return status;

	spin_lock_irqsave(&rchan->lock, flags);
	residue = rcar_dmac_chan_get_residue(rchan, cookie);
	cyclic = rchan->desc.running ? rchan->desc.running->cyclic : false;
	spin_unlock_irqrestore(&rchan->lock, flags);

	/* if there's no residue, the cookie is complete */
	if (!residue && !cyclic)
		return DMA_COMPLETE;

	dma_set_residue(txstate, residue);

	return status;
}

static void rcar_dmac_issue_pending(struct dma_chan *chan)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);
	unsigned long flags;

	spin_lock_irqsave(&rchan->lock, flags);

	if (list_empty(&rchan->desc.pending))
		goto done;

	/* Append the pending list to the active list. */
	list_splice_tail_init(&rchan->desc.pending, &rchan->desc.active);

	/*
	 * If no transfer is running pick the first descriptor from the active
	 * list and start the transfer.
	 */
	if (!rchan->desc.running) {
		struct rcar_dmac_desc *desc;

		desc = list_first_entry(&rchan->desc.active,
					struct rcar_dmac_desc, node);
		rchan->desc.running = desc;

		rcar_dmac_chan_start_xfer(rchan);
	}

done:
	spin_unlock_irqrestore(&rchan->lock, flags);
}

static void rcar_dmac_device_synchronize(struct dma_chan *chan)
{
	struct rcar_dmac_chan *rchan = to_rcar_dmac_chan(chan);

	synchronize_irq(rchan->irq);
}

/* -----------------------------------------------------------------------------
 * IRQ handling
 */

static irqreturn_t rcar_dmac_isr_desc_stage_end(struct rcar_dmac_chan *chan)
{
	struct rcar_dmac_desc *desc = chan->desc.running;
	unsigned int stage;

	if (WARN_ON(!desc || !desc->cyclic)) {
		/*
		 * This should never happen, there should always be a running
		 * cyclic descriptor when a descriptor stage end interrupt is
		 * triggered. Warn and return.
		 */
		return IRQ_NONE;
	}

	/* Program the interrupt pointer to the next stage. */
	stage = (rcar_dmac_chan_read(chan, RCAR_DMACHCRB) &
		 RCAR_DMACHCRB_DPTR_MASK) >> RCAR_DMACHCRB_DPTR_SHIFT;
	rcar_dmac_chan_write(chan, RCAR_DMADPCR, RCAR_DMADPCR_DIPT(stage));

	return IRQ_WAKE_THREAD;
}

static irqreturn_t rcar_dmac_isr_transfer_end(struct rcar_dmac_chan *chan)
{
	struct rcar_dmac_desc *desc = chan->desc.running;
	irqreturn_t ret = IRQ_WAKE_THREAD;

	if (WARN_ON_ONCE(!desc)) {
		/*
		 * This should never happen, there should always be a running
		 * descriptor when a transfer end interrupt is triggered. Warn
		 * and return.
		 */
		return IRQ_NONE;
	}

	/*
	 * The transfer end interrupt isn't generated for each chunk when using
	 * descriptor mode. Only update the running chunk pointer in
	 * non-descriptor mode.
	 */
	if (!desc->hwdescs.use) {
		/*
		 * If we haven't completed the last transfer chunk simply move
		 * to the next one. Only wake the IRQ thread if the transfer is
		 * cyclic.
		 */
		if (!list_is_last(&desc->running->node, &desc->chunks)) {
			desc->running = list_next_entry(desc->running, node);
			if (!desc->cyclic)
				ret = IRQ_HANDLED;
			goto done;
		}

		/*
		 * We've completed the last transfer chunk. If the transfer is
		 * cyclic, move back to the first one.
		 */
		if (desc->cyclic) {
			desc->running =
				list_first_entry(&desc->chunks,
						 struct rcar_dmac_xfer_chunk,
						 node);
			goto done;
		}
	}

	/* The descriptor is complete, move it to the done list. */
	list_move_tail(&desc->node, &chan->desc.done);

	/* Queue the next descriptor, if any. */
	if (!list_empty(&chan->desc.active))
		chan->desc.running = list_first_entry(&chan->desc.active,
						      struct rcar_dmac_desc,
						      node);
	else
		chan->desc.running = NULL;

done:
	if (chan->desc.running)
		rcar_dmac_chan_start_xfer(chan);

	return ret;
}

static irqreturn_t rcar_dmac_isr_channel(int irq, void *dev)
{
	u32 mask = RCAR_DMACHCR_DSE | RCAR_DMACHCR_TE;
	struct rcar_dmac_chan *chan = dev;
	irqreturn_t ret = IRQ_NONE;
	bool reinit = false;
	u32 chcr;

	spin_lock(&chan->lock);

	chcr = rcar_dmac_chan_read(chan, RCAR_DMACHCR);
	if (chcr & RCAR_DMACHCR_CAE) {
		struct rcar_dmac *dmac = to_rcar_dmac(chan->chan.device);

		/*
		 * We don't need to call rcar_dmac_chan_halt()
		 * because channel is already stopped in error case.
		 * We need to clear register and check DE bit as recovery.
		 */
		rcar_dmac_chan_clear(dmac, chan);
		rcar_dmac_chcr_de_barrier(chan);
		reinit = true;
		goto spin_lock_end;
	}

	if (chcr & RCAR_DMACHCR_TE)
		mask |= RCAR_DMACHCR_DE;
	rcar_dmac_chan_write(chan, RCAR_DMACHCR, chcr & ~mask);
	if (mask & RCAR_DMACHCR_DE)
		rcar_dmac_chcr_de_barrier(chan);

	if (chcr & RCAR_DMACHCR_DSE)
		ret |= rcar_dmac_isr_desc_stage_end(chan);

	if (chcr & RCAR_DMACHCR_TE)
		ret |= rcar_dmac_isr_transfer_end(chan);

spin_lock_end:
	spin_unlock(&chan->lock);

	if (reinit) {
		dev_err(chan->chan.device->dev, "Channel Address Error\n");

		rcar_dmac_chan_reinit(chan);
		ret = IRQ_HANDLED;
	}

	return ret;
}

static irqreturn_t rcar_dmac_isr_channel_thread(int irq, void *dev)
{
	struct rcar_dmac_chan *chan = dev;
	struct rcar_dmac_desc *desc;
	struct dmaengine_desc_callback cb;

	spin_lock_irq(&chan->lock);

	/* For cyclic transfers notify the user after every chunk. */
	if (chan->desc.running && chan->desc.running->cyclic) {
		desc = chan->desc.running;
		dmaengine_desc_get_callback(&desc->async_tx, &cb);

		if (dmaengine_desc_callback_valid(&cb)) {
			spin_unlock_irq(&chan->lock);
			dmaengine_desc_callback_invoke(&cb, NULL);
			spin_lock_irq(&chan->lock);
		}
	}

	/*
	 * Call the callback function for all descriptors on the done list and
	 * move them to the ack wait list.
	 */
	while (!list_empty(&chan->desc.done)) {
		desc = list_first_entry(&chan->desc.done, struct rcar_dmac_desc,
					node);
		dma_cookie_complete(&desc->async_tx);
		list_del(&desc->node);

		dmaengine_desc_get_callback(&desc->async_tx, &cb);
		if (dmaengine_desc_callback_valid(&cb)) {
			spin_unlock_irq(&chan->lock);
			/*
			 * We own the only reference to this descriptor, we can
			 * safely dereference it without holding the channel
			 * lock.
			 */
			dmaengine_desc_callback_invoke(&cb, NULL);
			spin_lock_irq(&chan->lock);
		}

		list_add_tail(&desc->node, &chan->desc.wait);
	}

	spin_unlock_irq(&chan->lock);

	/* Recycle all acked descriptors. */
	rcar_dmac_desc_recycle_acked(chan);

	return IRQ_HANDLED;
}

/* -----------------------------------------------------------------------------
 * OF xlate and channel filter
 */

static bool rcar_dmac_chan_filter(struct dma_chan *chan, void *arg)
{
	struct rcar_dmac *dmac = to_rcar_dmac(chan->device);
	struct of_phandle_args *dma_spec = arg;

	/*
	 * FIXME: Using a filter on OF platforms is a nonsense. The OF xlate
	 * function knows from which device it wants to allocate a channel from,
	 * and would be perfectly capable of selecting the channel it wants.
	 * Forcing it to call dma_request_channel() and iterate through all
	 * channels from all controllers is just pointless.
	 */
	if (chan->device->device_config != rcar_dmac_device_config)
		return false;

	return !test_and_set_bit(dma_spec->args[0], dmac->modules);
}

static struct dma_chan *rcar_dmac_of_xlate(struct of_phandle_args *dma_spec,
					   struct of_dma *ofdma)
{
	struct rcar_dmac_chan *rchan;
	struct dma_chan *chan;
	dma_cap_mask_t mask;

	if (dma_spec->args_count != 1)
		return NULL;

	/* Only slave DMA channels can be allocated via DT */
	dma_cap_zero(mask);
	dma_cap_set(DMA_SLAVE, mask);

	chan = __dma_request_channel(&mask, rcar_dmac_chan_filter, dma_spec,
				     ofdma->of_node);
	if (!chan)
		return NULL;

	rchan = to_rcar_dmac_chan(chan);
	rchan->mid_rid = dma_spec->args[0];

	return chan;
}

/* -----------------------------------------------------------------------------
 * Power management
 */

#ifdef CONFIG_PM
static int rcar_dmac_runtime_suspend(struct device *dev)
{
	return 0;
}

static int rcar_dmac_runtime_resume(struct device *dev)
{
	struct rcar_dmac *dmac = dev_get_drvdata(dev);

	return rcar_dmac_init(dmac);
}
#endif

static const struct dev_pm_ops rcar_dmac_pm = {
	/*
	 * TODO for system sleep/resume:
	 *   - Wait for the current transfer to complete and stop the device,
	 *   - Resume transfers, if any.
	 */
	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
				      pm_runtime_force_resume)
	SET_RUNTIME_PM_OPS(rcar_dmac_runtime_suspend, rcar_dmac_runtime_resume,
			   NULL)
};

/* -----------------------------------------------------------------------------
 * Probe and remove
 */

static int rcar_dmac_chan_probe(struct rcar_dmac *dmac,
				struct rcar_dmac_chan *rchan)
{
	struct platform_device *pdev = to_platform_device(dmac->dev);
	struct dma_chan *chan = &rchan->chan;
	char pdev_irqname[5];
	char *irqname;
	int ret;

	rchan->mid_rid = -EINVAL;

	spin_lock_init(&rchan->lock);

	INIT_LIST_HEAD(&rchan->desc.free);
	INIT_LIST_HEAD(&rchan->desc.pending);
	INIT_LIST_HEAD(&rchan->desc.active);
	INIT_LIST_HEAD(&rchan->desc.done);
	INIT_LIST_HEAD(&rchan->desc.wait);

	/* Request the channel interrupt. */
	sprintf(pdev_irqname, "ch%u", rchan->index);
	rchan->irq = platform_get_irq_byname(pdev, pdev_irqname);
	if (rchan->irq < 0)
		return -ENODEV;

	irqname = devm_kasprintf(dmac->dev, GFP_KERNEL, "%s:%u",
				 dev_name(dmac->dev), rchan->index);
	if (!irqname)
		return -ENOMEM;

	/*
	 * Initialize the DMA engine channel and add it to the DMA engine
	 * channels list.
	 */
	chan->device = &dmac->engine;
	dma_cookie_init(chan);

	list_add_tail(&chan->device_node, &dmac->engine.channels);

	ret = devm_request_threaded_irq(dmac->dev, rchan->irq,
					rcar_dmac_isr_channel,
					rcar_dmac_isr_channel_thread, 0,
					irqname, rchan);
	if (ret) {
		dev_err(dmac->dev, "failed to request IRQ %u (%d)\n",
			rchan->irq, ret);
		return ret;
	}

	return 0;
}

#define RCAR_DMAC_MAX_CHANNELS	32

static int rcar_dmac_parse_of(struct device *dev, struct rcar_dmac *dmac)
{
	struct device_node *np = dev->of_node;
	int ret;

	ret = of_property_read_u32(np, "dma-channels", &dmac->n_channels);
	if (ret < 0) {
		dev_err(dev, "unable to read dma-channels property\n");
		return ret;
	}

	/* The hardware and driver don't support more than 32 bits in CHCLR */
	if (dmac->n_channels <= 0 ||
	    dmac->n_channels >= RCAR_DMAC_MAX_CHANNELS) {
		dev_err(dev, "invalid number of channels %u\n",
			dmac->n_channels);
		return -EINVAL;
	}

	/*
	 * If the driver is unable to read dma-channel-mask property,
	 * the driver assumes that it can use all channels.
	 */
	dmac->channels_mask = GENMASK(dmac->n_channels - 1, 0);
	of_property_read_u32(np, "dma-channel-mask", &dmac->channels_mask);

	/* If the property has out-of-channel mask, this driver clears it */
	dmac->channels_mask &= GENMASK(dmac->n_channels - 1, 0);

	return 0;
}

static int rcar_dmac_probe(struct platform_device *pdev)
{
	const enum dma_slave_buswidth widths = DMA_SLAVE_BUSWIDTH_1_BYTE |
		DMA_SLAVE_BUSWIDTH_2_BYTES | DMA_SLAVE_BUSWIDTH_4_BYTES |
		DMA_SLAVE_BUSWIDTH_8_BYTES | DMA_SLAVE_BUSWIDTH_16_BYTES |
		DMA_SLAVE_BUSWIDTH_32_BYTES | DMA_SLAVE_BUSWIDTH_64_BYTES;
	const struct rcar_dmac_of_data *data;
	struct rcar_dmac_chan *chan;
	struct dma_device *engine;
	void __iomem *chan_base;
	struct rcar_dmac *dmac;
	unsigned int i;
	int ret;

	data = of_device_get_match_data(&pdev->dev);
	if (!data)
		return -EINVAL;

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

	dmac->dev = &pdev->dev;
	platform_set_drvdata(pdev, dmac);
	dma_set_max_seg_size(dmac->dev, RCAR_DMATCR_MASK);
	dma_set_mask_and_coherent(dmac->dev, DMA_BIT_MASK(40));

	ret = rcar_dmac_parse_of(&pdev->dev, dmac);
	if (ret < 0)
		return ret;

	/*
	 * A still unconfirmed hardware bug prevents the IPMMU microTLB 0 to be
	 * flushed correctly, resulting in memory corruption. DMAC 0 channel 0
	 * is connected to microTLB 0 on currently supported platforms, so we
	 * can't use it with the IPMMU. As the IOMMU API operates at the device
	 * level we can't disable it selectively, so ignore channel 0 for now if
	 * the device is part of an IOMMU group.
	 */
	if (device_iommu_mapped(&pdev->dev))
		dmac->channels_mask &= ~BIT(0);

	dmac->channels = devm_kcalloc(&pdev->dev, dmac->n_channels,
				      sizeof(*dmac->channels), GFP_KERNEL);
	if (!dmac->channels)
		return -ENOMEM;

	/* Request resources. */
	dmac->dmac_base = devm_platform_ioremap_resource(pdev, 0);
	if (IS_ERR(dmac->dmac_base))
		return PTR_ERR(dmac->dmac_base);

	if (!data->chan_offset_base) {
		dmac->chan_base = devm_platform_ioremap_resource(pdev, 1);
		if (IS_ERR(dmac->chan_base))
			return PTR_ERR(dmac->chan_base);

		chan_base = dmac->chan_base;
	} else {
		chan_base = dmac->dmac_base + data->chan_offset_base;
	}

	for_each_rcar_dmac_chan(i, dmac, chan) {
		chan->index = i;
		chan->iomem = chan_base + i * data->chan_offset_stride;
	}

	/* Enable runtime PM and initialize the device. */
	pm_runtime_enable(&pdev->dev);
	ret = pm_runtime_resume_and_get(&pdev->dev);
	if (ret < 0) {
		dev_err(&pdev->dev, "runtime PM get sync failed (%d)\n", ret);
		return ret;
	}

	ret = rcar_dmac_init(dmac);
	pm_runtime_put(&pdev->dev);

	if (ret) {
		dev_err(&pdev->dev, "failed to reset device\n");
		goto error;
	}

	/* Initialize engine */
	engine = &dmac->engine;

	dma_cap_set(DMA_MEMCPY, engine->cap_mask);
	dma_cap_set(DMA_SLAVE, engine->cap_mask);

	engine->dev		= &pdev->dev;
	engine->copy_align	= ilog2(RCAR_DMAC_MEMCPY_XFER_SIZE);

	engine->src_addr_widths	= widths;
	engine->dst_addr_widths	= widths;
	engine->directions	= BIT(DMA_MEM_TO_DEV) | BIT(DMA_DEV_TO_MEM);
	engine->residue_granularity = DMA_RESIDUE_GRANULARITY_BURST;

	engine->device_alloc_chan_resources	= rcar_dmac_alloc_chan_resources;
	engine->device_free_chan_resources	= rcar_dmac_free_chan_resources;
	engine->device_prep_dma_memcpy		= rcar_dmac_prep_dma_memcpy;
	engine->device_prep_slave_sg		= rcar_dmac_prep_slave_sg;
	engine->device_prep_dma_cyclic		= rcar_dmac_prep_dma_cyclic;
	engine->device_config			= rcar_dmac_device_config;
	engine->device_pause			= rcar_dmac_chan_pause;
	engine->device_terminate_all		= rcar_dmac_chan_terminate_all;
	engine->device_tx_status		= rcar_dmac_tx_status;
	engine->device_issue_pending		= rcar_dmac_issue_pending;
	engine->device_synchronize		= rcar_dmac_device_synchronize;

	INIT_LIST_HEAD(&engine->channels);

	for_each_rcar_dmac_chan(i, dmac, chan) {
		ret = rcar_dmac_chan_probe(dmac, chan);
		if (ret < 0)
			goto error;
	}

	/* Register the DMAC as a DMA provider for DT. */
	ret = of_dma_controller_register(pdev->dev.of_node, rcar_dmac_of_xlate,
					 NULL);
	if (ret < 0)
		goto error;

	/*
	 * Register the DMA engine device.
	 *
	 * Default transfer size of 32 bytes requires 32-byte alignment.
	 */
	ret = dma_async_device_register(engine);
	if (ret < 0)
		goto error;

	return 0;

error:
	of_dma_controller_free(pdev->dev.of_node);
	pm_runtime_disable(&pdev->dev);
	return ret;
}

static int rcar_dmac_remove(struct platform_device *pdev)
{
	struct rcar_dmac *dmac = platform_get_drvdata(pdev);

	of_dma_controller_free(pdev->dev.of_node);
	dma_async_device_unregister(&dmac->engine);

	pm_runtime_disable(&pdev->dev);

	return 0;
}

static void rcar_dmac_shutdown(struct platform_device *pdev)
{
	struct rcar_dmac *dmac = platform_get_drvdata(pdev);

	rcar_dmac_stop_all_chan(dmac);
}

static const struct rcar_dmac_of_data rcar_dmac_data = {
	.chan_offset_base	= 0x8000,
	.chan_offset_stride	= 0x80,
};

static const struct rcar_dmac_of_data rcar_v3u_dmac_data = {
	.chan_offset_base	= 0x0,
	.chan_offset_stride	= 0x1000,
};

static const struct of_device_id rcar_dmac_of_ids[] = {
	{
		.compatible = "renesas,rcar-dmac",
		.data = &rcar_dmac_data,
	}, {
		.compatible = "renesas,dmac-r8a779a0",
		.data = &rcar_v3u_dmac_data,
	},
	{ /* Sentinel */ }
};
MODULE_DEVICE_TABLE(of, rcar_dmac_of_ids);

static struct platform_driver rcar_dmac_driver = {
	.driver		= {
		.pm	= &rcar_dmac_pm,
		.name	= "rcar-dmac",
		.of_match_table = rcar_dmac_of_ids,
	},
	.probe		= rcar_dmac_probe,
	.remove		= rcar_dmac_remove,
	.shutdown	= rcar_dmac_shutdown,
};

module_platform_driver(rcar_dmac_driver);

MODULE_DESCRIPTION("R-Car Gen2 DMA Controller Driver");
MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
MODULE_LICENSE("GPL v2");