summaryrefslogtreecommitdiff
path: root/drivers/spi/spi-tegra210-quad.c
blob: 904972606bd45bb99a960b028ec5aef4c335c706 (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
// SPDX-License-Identifier: GPL-2.0-only
//
// Copyright (C) 2020 NVIDIA CORPORATION.

#include <linux/clk.h>
#include <linux/completion.h>
#include <linux/delay.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/dmapool.h>
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iopoll.h>
#include <linux/kernel.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/reset.h>
#include <linux/spi/spi.h>
#include <linux/acpi.h>
#include <linux/property.h>

#define QSPI_COMMAND1				0x000
#define QSPI_BIT_LENGTH(x)			(((x) & 0x1f) << 0)
#define QSPI_PACKED				BIT(5)
#define QSPI_INTERFACE_WIDTH_MASK		(0x03 << 7)
#define QSPI_INTERFACE_WIDTH(x)			(((x) & 0x03) << 7)
#define QSPI_INTERFACE_WIDTH_SINGLE		QSPI_INTERFACE_WIDTH(0)
#define QSPI_INTERFACE_WIDTH_DUAL		QSPI_INTERFACE_WIDTH(1)
#define QSPI_INTERFACE_WIDTH_QUAD		QSPI_INTERFACE_WIDTH(2)
#define QSPI_SDR_DDR_SEL			BIT(9)
#define QSPI_TX_EN				BIT(11)
#define QSPI_RX_EN				BIT(12)
#define QSPI_CS_SW_VAL				BIT(20)
#define QSPI_CS_SW_HW				BIT(21)

#define QSPI_CS_POL_INACTIVE(n)			(1 << (22 + (n)))
#define QSPI_CS_POL_INACTIVE_MASK		(0xF << 22)
#define QSPI_CS_SEL_0				(0 << 26)
#define QSPI_CS_SEL_1				(1 << 26)
#define QSPI_CS_SEL_2				(2 << 26)
#define QSPI_CS_SEL_3				(3 << 26)
#define QSPI_CS_SEL_MASK			(3 << 26)
#define QSPI_CS_SEL(x)				(((x) & 0x3) << 26)

#define QSPI_CONTROL_MODE_0			(0 << 28)
#define QSPI_CONTROL_MODE_3			(3 << 28)
#define QSPI_CONTROL_MODE_MASK			(3 << 28)
#define QSPI_M_S				BIT(30)
#define QSPI_PIO				BIT(31)

#define QSPI_COMMAND2				0x004
#define QSPI_TX_TAP_DELAY(x)			(((x) & 0x3f) << 10)
#define QSPI_RX_TAP_DELAY(x)			(((x) & 0xff) << 0)

#define QSPI_CS_TIMING1				0x008
#define QSPI_SETUP_HOLD(setup, hold)		(((setup) << 4) | (hold))

#define QSPI_CS_TIMING2				0x00c
#define CYCLES_BETWEEN_PACKETS_0(x)		(((x) & 0x1f) << 0)
#define CS_ACTIVE_BETWEEN_PACKETS_0		BIT(5)

#define QSPI_TRANS_STATUS			0x010
#define QSPI_BLK_CNT(val)			(((val) >> 0) & 0xffff)
#define QSPI_RDY				BIT(30)

#define QSPI_FIFO_STATUS			0x014
#define QSPI_RX_FIFO_EMPTY			BIT(0)
#define QSPI_RX_FIFO_FULL			BIT(1)
#define QSPI_TX_FIFO_EMPTY			BIT(2)
#define QSPI_TX_FIFO_FULL			BIT(3)
#define QSPI_RX_FIFO_UNF			BIT(4)
#define QSPI_RX_FIFO_OVF			BIT(5)
#define QSPI_TX_FIFO_UNF			BIT(6)
#define QSPI_TX_FIFO_OVF			BIT(7)
#define QSPI_ERR				BIT(8)
#define QSPI_TX_FIFO_FLUSH			BIT(14)
#define QSPI_RX_FIFO_FLUSH			BIT(15)
#define QSPI_TX_FIFO_EMPTY_COUNT(val)		(((val) >> 16) & 0x7f)
#define QSPI_RX_FIFO_FULL_COUNT(val)		(((val) >> 23) & 0x7f)

#define QSPI_FIFO_ERROR				(QSPI_RX_FIFO_UNF | \
						 QSPI_RX_FIFO_OVF | \
						 QSPI_TX_FIFO_UNF | \
						 QSPI_TX_FIFO_OVF)
#define QSPI_FIFO_EMPTY				(QSPI_RX_FIFO_EMPTY | \
						 QSPI_TX_FIFO_EMPTY)

#define QSPI_TX_DATA				0x018
#define QSPI_RX_DATA				0x01c

#define QSPI_DMA_CTL				0x020
#define QSPI_TX_TRIG(n)				(((n) & 0x3) << 15)
#define QSPI_TX_TRIG_1				QSPI_TX_TRIG(0)
#define QSPI_TX_TRIG_4				QSPI_TX_TRIG(1)
#define QSPI_TX_TRIG_8				QSPI_TX_TRIG(2)
#define QSPI_TX_TRIG_16				QSPI_TX_TRIG(3)

#define QSPI_RX_TRIG(n)				(((n) & 0x3) << 19)
#define QSPI_RX_TRIG_1				QSPI_RX_TRIG(0)
#define QSPI_RX_TRIG_4				QSPI_RX_TRIG(1)
#define QSPI_RX_TRIG_8				QSPI_RX_TRIG(2)
#define QSPI_RX_TRIG_16				QSPI_RX_TRIG(3)

#define QSPI_DMA_EN				BIT(31)

#define QSPI_DMA_BLK				0x024
#define QSPI_DMA_BLK_SET(x)			(((x) & 0xffff) << 0)

#define QSPI_TX_FIFO				0x108
#define QSPI_RX_FIFO				0x188

#define QSPI_FIFO_DEPTH				64

#define QSPI_INTR_MASK				0x18c
#define QSPI_INTR_RX_FIFO_UNF_MASK		BIT(25)
#define QSPI_INTR_RX_FIFO_OVF_MASK		BIT(26)
#define QSPI_INTR_TX_FIFO_UNF_MASK		BIT(27)
#define QSPI_INTR_TX_FIFO_OVF_MASK		BIT(28)
#define QSPI_INTR_RDY_MASK			BIT(29)
#define QSPI_INTR_RX_TX_FIFO_ERR		(QSPI_INTR_RX_FIFO_UNF_MASK | \
						 QSPI_INTR_RX_FIFO_OVF_MASK | \
						 QSPI_INTR_TX_FIFO_UNF_MASK | \
						 QSPI_INTR_TX_FIFO_OVF_MASK)

#define QSPI_MISC_REG                           0x194
#define QSPI_NUM_DUMMY_CYCLE(x)			(((x) & 0xff) << 0)
#define QSPI_DUMMY_CYCLES_MAX			0xff

#define QSPI_CMB_SEQ_CMD			0x19c
#define QSPI_COMMAND_VALUE_SET(X)		(((x) & 0xFF) << 0)

#define QSPI_CMB_SEQ_CMD_CFG			0x1a0
#define QSPI_COMMAND_X1_X2_X4(x)		(((x) & 0x3) << 13)
#define QSPI_COMMAND_X1_X2_X4_MASK		(0x03 << 13)
#define QSPI_COMMAND_SDR_DDR			BIT(12)
#define QSPI_COMMAND_SIZE_SET(x)		(((x) & 0xFF) << 0)

#define QSPI_GLOBAL_CONFIG			0X1a4
#define QSPI_CMB_SEQ_EN				BIT(0)

#define QSPI_CMB_SEQ_ADDR			0x1a8
#define QSPI_ADDRESS_VALUE_SET(X)		(((x) & 0xFFFF) << 0)

#define QSPI_CMB_SEQ_ADDR_CFG			0x1ac
#define QSPI_ADDRESS_X1_X2_X4(x)		(((x) & 0x3) << 13)
#define QSPI_ADDRESS_X1_X2_X4_MASK		(0x03 << 13)
#define QSPI_ADDRESS_SDR_DDR			BIT(12)
#define QSPI_ADDRESS_SIZE_SET(x)		(((x) & 0xFF) << 0)

#define DATA_DIR_TX				BIT(0)
#define DATA_DIR_RX				BIT(1)

#define QSPI_DMA_TIMEOUT			(msecs_to_jiffies(1000))
#define DEFAULT_QSPI_DMA_BUF_LEN		(64 * 1024)
#define CMD_TRANSFER				0
#define ADDR_TRANSFER				1
#define DATA_TRANSFER				2

struct tegra_qspi_soc_data {
	bool has_dma;
	bool cmb_xfer_capable;
	unsigned int cs_count;
};

struct tegra_qspi_client_data {
	int tx_clk_tap_delay;
	int rx_clk_tap_delay;
};

struct tegra_qspi {
	struct device				*dev;
	struct spi_master			*master;
	/* lock to protect data accessed by irq */
	spinlock_t				lock;

	struct clk				*clk;
	void __iomem				*base;
	phys_addr_t				phys;
	unsigned int				irq;

	u32					cur_speed;
	unsigned int				cur_pos;
	unsigned int				words_per_32bit;
	unsigned int				bytes_per_word;
	unsigned int				curr_dma_words;
	unsigned int				cur_direction;

	unsigned int				cur_rx_pos;
	unsigned int				cur_tx_pos;

	unsigned int				dma_buf_size;
	unsigned int				max_buf_size;
	bool					is_curr_dma_xfer;

	struct completion			rx_dma_complete;
	struct completion			tx_dma_complete;

	u32					tx_status;
	u32					rx_status;
	u32					status_reg;
	bool					is_packed;
	bool					use_dma;

	u32					command1_reg;
	u32					dma_control_reg;
	u32					def_command1_reg;
	u32					def_command2_reg;
	u32					spi_cs_timing1;
	u32					spi_cs_timing2;
	u8					dummy_cycles;

	struct completion			xfer_completion;
	struct spi_transfer			*curr_xfer;

	struct dma_chan				*rx_dma_chan;
	u32					*rx_dma_buf;
	dma_addr_t				rx_dma_phys;
	struct dma_async_tx_descriptor		*rx_dma_desc;

	struct dma_chan				*tx_dma_chan;
	u32					*tx_dma_buf;
	dma_addr_t				tx_dma_phys;
	struct dma_async_tx_descriptor		*tx_dma_desc;
	const struct tegra_qspi_soc_data	*soc_data;
};

static inline u32 tegra_qspi_readl(struct tegra_qspi *tqspi, unsigned long offset)
{
	return readl(tqspi->base + offset);
}

static inline void tegra_qspi_writel(struct tegra_qspi *tqspi, u32 value, unsigned long offset)
{
	writel(value, tqspi->base + offset);

	/* read back register to make sure that register writes completed */
	if (offset != QSPI_TX_FIFO)
		readl(tqspi->base + QSPI_COMMAND1);
}

static void tegra_qspi_mask_clear_irq(struct tegra_qspi *tqspi)
{
	u32 value;

	/* write 1 to clear status register */
	value = tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS);
	tegra_qspi_writel(tqspi, value, QSPI_TRANS_STATUS);

	value = tegra_qspi_readl(tqspi, QSPI_INTR_MASK);
	if (!(value & QSPI_INTR_RDY_MASK)) {
		value |= (QSPI_INTR_RDY_MASK | QSPI_INTR_RX_TX_FIFO_ERR);
		tegra_qspi_writel(tqspi, value, QSPI_INTR_MASK);
	}

	/* clear fifo status error if any */
	value = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
	if (value & QSPI_ERR)
		tegra_qspi_writel(tqspi, QSPI_ERR | QSPI_FIFO_ERROR, QSPI_FIFO_STATUS);
}

static unsigned int
tegra_qspi_calculate_curr_xfer_param(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	unsigned int max_word, max_len, total_fifo_words;
	unsigned int remain_len = t->len - tqspi->cur_pos;
	unsigned int bits_per_word = t->bits_per_word;

	tqspi->bytes_per_word = DIV_ROUND_UP(bits_per_word, 8);

	/*
	 * Tegra QSPI controller supports packed or unpacked mode transfers.
	 * Packed mode is used for data transfers using 8, 16, or 32 bits per
	 * word with a minimum transfer of 1 word and for all other transfers
	 * unpacked mode will be used.
	 */

	if ((bits_per_word == 8 || bits_per_word == 16 ||
	     bits_per_word == 32) && t->len > 3) {
		tqspi->is_packed = true;
		tqspi->words_per_32bit = 32 / bits_per_word;
	} else {
		tqspi->is_packed = false;
		tqspi->words_per_32bit = 1;
	}

	if (tqspi->is_packed) {
		max_len = min(remain_len, tqspi->max_buf_size);
		tqspi->curr_dma_words = max_len / tqspi->bytes_per_word;
		total_fifo_words = (max_len + 3) / 4;
	} else {
		max_word = (remain_len - 1) / tqspi->bytes_per_word + 1;
		max_word = min(max_word, tqspi->max_buf_size / 4);
		tqspi->curr_dma_words = max_word;
		total_fifo_words = max_word;
	}

	return total_fifo_words;
}

static unsigned int
tegra_qspi_fill_tx_fifo_from_client_txbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	unsigned int written_words, fifo_words_left, count;
	unsigned int len, tx_empty_count, max_n_32bit, i;
	u8 *tx_buf = (u8 *)t->tx_buf + tqspi->cur_tx_pos;
	u32 fifo_status;

	fifo_status = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
	tx_empty_count = QSPI_TX_FIFO_EMPTY_COUNT(fifo_status);

	if (tqspi->is_packed) {
		fifo_words_left = tx_empty_count * tqspi->words_per_32bit;
		written_words = min(fifo_words_left, tqspi->curr_dma_words);
		len = written_words * tqspi->bytes_per_word;
		max_n_32bit = DIV_ROUND_UP(len, 4);
		for (count = 0; count < max_n_32bit; count++) {
			u32 x = 0;

			for (i = 0; (i < 4) && len; i++, len--)
				x |= (u32)(*tx_buf++) << (i * 8);
			tegra_qspi_writel(tqspi, x, QSPI_TX_FIFO);
		}

		tqspi->cur_tx_pos += written_words * tqspi->bytes_per_word;
	} else {
		unsigned int write_bytes;
		u8 bytes_per_word = tqspi->bytes_per_word;

		max_n_32bit = min(tqspi->curr_dma_words, tx_empty_count);
		written_words = max_n_32bit;
		len = written_words * tqspi->bytes_per_word;
		if (len > t->len - tqspi->cur_pos)
			len = t->len - tqspi->cur_pos;
		write_bytes = len;
		for (count = 0; count < max_n_32bit; count++) {
			u32 x = 0;

			for (i = 0; len && (i < bytes_per_word); i++, len--)
				x |= (u32)(*tx_buf++) << (i * 8);
			tegra_qspi_writel(tqspi, x, QSPI_TX_FIFO);
		}

		tqspi->cur_tx_pos += write_bytes;
	}

	return written_words;
}

static unsigned int
tegra_qspi_read_rx_fifo_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	u8 *rx_buf = (u8 *)t->rx_buf + tqspi->cur_rx_pos;
	unsigned int len, rx_full_count, count, i;
	unsigned int read_words = 0;
	u32 fifo_status, x;

	fifo_status = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
	rx_full_count = QSPI_RX_FIFO_FULL_COUNT(fifo_status);
	if (tqspi->is_packed) {
		len = tqspi->curr_dma_words * tqspi->bytes_per_word;
		for (count = 0; count < rx_full_count; count++) {
			x = tegra_qspi_readl(tqspi, QSPI_RX_FIFO);

			for (i = 0; len && (i < 4); i++, len--)
				*rx_buf++ = (x >> i * 8) & 0xff;
		}

		read_words += tqspi->curr_dma_words;
		tqspi->cur_rx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
	} else {
		u32 rx_mask = ((u32)1 << t->bits_per_word) - 1;
		u8 bytes_per_word = tqspi->bytes_per_word;
		unsigned int read_bytes;

		len = rx_full_count * bytes_per_word;
		if (len > t->len - tqspi->cur_pos)
			len = t->len - tqspi->cur_pos;
		read_bytes = len;
		for (count = 0; count < rx_full_count; count++) {
			x = tegra_qspi_readl(tqspi, QSPI_RX_FIFO) & rx_mask;

			for (i = 0; len && (i < bytes_per_word); i++, len--)
				*rx_buf++ = (x >> (i * 8)) & 0xff;
		}

		read_words += rx_full_count;
		tqspi->cur_rx_pos += read_bytes;
	}

	return read_words;
}

static void
tegra_qspi_copy_client_txbuf_to_qspi_txbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	dma_sync_single_for_cpu(tqspi->dev, tqspi->tx_dma_phys,
				tqspi->dma_buf_size, DMA_TO_DEVICE);

	/*
	 * In packed mode, each word in FIFO may contain multiple packets
	 * based on bits per word. So all bytes in each FIFO word are valid.
	 *
	 * In unpacked mode, each word in FIFO contains single packet and
	 * based on bits per word any remaining bits in FIFO word will be
	 * ignored by the hardware and are invalid bits.
	 */
	if (tqspi->is_packed) {
		tqspi->cur_tx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
	} else {
		u8 *tx_buf = (u8 *)t->tx_buf + tqspi->cur_tx_pos;
		unsigned int i, count, consume, write_bytes;

		/*
		 * Fill tx_dma_buf to contain single packet in each word based
		 * on bits per word from SPI core tx_buf.
		 */
		consume = tqspi->curr_dma_words * tqspi->bytes_per_word;
		if (consume > t->len - tqspi->cur_pos)
			consume = t->len - tqspi->cur_pos;
		write_bytes = consume;
		for (count = 0; count < tqspi->curr_dma_words; count++) {
			u32 x = 0;

			for (i = 0; consume && (i < tqspi->bytes_per_word); i++, consume--)
				x |= (u32)(*tx_buf++) << (i * 8);
			tqspi->tx_dma_buf[count] = x;
		}

		tqspi->cur_tx_pos += write_bytes;
	}

	dma_sync_single_for_device(tqspi->dev, tqspi->tx_dma_phys,
				   tqspi->dma_buf_size, DMA_TO_DEVICE);
}

static void
tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	dma_sync_single_for_cpu(tqspi->dev, tqspi->rx_dma_phys,
				tqspi->dma_buf_size, DMA_FROM_DEVICE);

	if (tqspi->is_packed) {
		tqspi->cur_rx_pos += tqspi->curr_dma_words * tqspi->bytes_per_word;
	} else {
		unsigned char *rx_buf = t->rx_buf + tqspi->cur_rx_pos;
		u32 rx_mask = ((u32)1 << t->bits_per_word) - 1;
		unsigned int i, count, consume, read_bytes;

		/*
		 * Each FIFO word contains single data packet.
		 * Skip invalid bits in each FIFO word based on bits per word
		 * and align bytes while filling in SPI core rx_buf.
		 */
		consume = tqspi->curr_dma_words * tqspi->bytes_per_word;
		if (consume > t->len - tqspi->cur_pos)
			consume = t->len - tqspi->cur_pos;
		read_bytes = consume;
		for (count = 0; count < tqspi->curr_dma_words; count++) {
			u32 x = tqspi->rx_dma_buf[count] & rx_mask;

			for (i = 0; consume && (i < tqspi->bytes_per_word); i++, consume--)
				*rx_buf++ = (x >> (i * 8)) & 0xff;
		}

		tqspi->cur_rx_pos += read_bytes;
	}

	dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
				   tqspi->dma_buf_size, DMA_FROM_DEVICE);
}

static void tegra_qspi_dma_complete(void *args)
{
	struct completion *dma_complete = args;

	complete(dma_complete);
}

static int tegra_qspi_start_tx_dma(struct tegra_qspi *tqspi, struct spi_transfer *t, int len)
{
	dma_addr_t tx_dma_phys;

	reinit_completion(&tqspi->tx_dma_complete);

	if (tqspi->is_packed)
		tx_dma_phys = t->tx_dma;
	else
		tx_dma_phys = tqspi->tx_dma_phys;

	tqspi->tx_dma_desc = dmaengine_prep_slave_single(tqspi->tx_dma_chan, tx_dma_phys,
							 len, DMA_MEM_TO_DEV,
							 DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);

	if (!tqspi->tx_dma_desc) {
		dev_err(tqspi->dev, "Unable to get TX descriptor\n");
		return -EIO;
	}

	tqspi->tx_dma_desc->callback = tegra_qspi_dma_complete;
	tqspi->tx_dma_desc->callback_param = &tqspi->tx_dma_complete;
	dmaengine_submit(tqspi->tx_dma_desc);
	dma_async_issue_pending(tqspi->tx_dma_chan);

	return 0;
}

static int tegra_qspi_start_rx_dma(struct tegra_qspi *tqspi, struct spi_transfer *t, int len)
{
	dma_addr_t rx_dma_phys;

	reinit_completion(&tqspi->rx_dma_complete);

	if (tqspi->is_packed)
		rx_dma_phys = t->rx_dma;
	else
		rx_dma_phys = tqspi->rx_dma_phys;

	tqspi->rx_dma_desc = dmaengine_prep_slave_single(tqspi->rx_dma_chan, rx_dma_phys,
							 len, DMA_DEV_TO_MEM,
							 DMA_PREP_INTERRUPT |  DMA_CTRL_ACK);

	if (!tqspi->rx_dma_desc) {
		dev_err(tqspi->dev, "Unable to get RX descriptor\n");
		return -EIO;
	}

	tqspi->rx_dma_desc->callback = tegra_qspi_dma_complete;
	tqspi->rx_dma_desc->callback_param = &tqspi->rx_dma_complete;
	dmaengine_submit(tqspi->rx_dma_desc);
	dma_async_issue_pending(tqspi->rx_dma_chan);

	return 0;
}

static int tegra_qspi_flush_fifos(struct tegra_qspi *tqspi, bool atomic)
{
	void __iomem *addr = tqspi->base + QSPI_FIFO_STATUS;
	u32 val;

	val = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);
	if ((val & QSPI_FIFO_EMPTY) == QSPI_FIFO_EMPTY)
		return 0;

	val |= QSPI_RX_FIFO_FLUSH | QSPI_TX_FIFO_FLUSH;
	tegra_qspi_writel(tqspi, val, QSPI_FIFO_STATUS);

	if (!atomic)
		return readl_relaxed_poll_timeout(addr, val,
						  (val & QSPI_FIFO_EMPTY) == QSPI_FIFO_EMPTY,
						  1000, 1000000);

	return readl_relaxed_poll_timeout_atomic(addr, val,
						 (val & QSPI_FIFO_EMPTY) == QSPI_FIFO_EMPTY,
						 1000, 1000000);
}

static void tegra_qspi_unmask_irq(struct tegra_qspi *tqspi)
{
	u32 intr_mask;

	intr_mask = tegra_qspi_readl(tqspi, QSPI_INTR_MASK);
	intr_mask &= ~(QSPI_INTR_RDY_MASK | QSPI_INTR_RX_TX_FIFO_ERR);
	tegra_qspi_writel(tqspi, intr_mask, QSPI_INTR_MASK);
}

static int tegra_qspi_dma_map_xfer(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	u8 *tx_buf = (u8 *)t->tx_buf + tqspi->cur_tx_pos;
	u8 *rx_buf = (u8 *)t->rx_buf + tqspi->cur_rx_pos;
	unsigned int len;

	len = DIV_ROUND_UP(tqspi->curr_dma_words * tqspi->bytes_per_word, 4) * 4;

	if (t->tx_buf) {
		t->tx_dma = dma_map_single(tqspi->dev, (void *)tx_buf, len, DMA_TO_DEVICE);
		if (dma_mapping_error(tqspi->dev, t->tx_dma))
			return -ENOMEM;
	}

	if (t->rx_buf) {
		t->rx_dma = dma_map_single(tqspi->dev, (void *)rx_buf, len, DMA_FROM_DEVICE);
		if (dma_mapping_error(tqspi->dev, t->rx_dma)) {
			dma_unmap_single(tqspi->dev, t->tx_dma, len, DMA_TO_DEVICE);
			return -ENOMEM;
		}
	}

	return 0;
}

static void tegra_qspi_dma_unmap_xfer(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	unsigned int len;

	len = DIV_ROUND_UP(tqspi->curr_dma_words * tqspi->bytes_per_word, 4) * 4;

	dma_unmap_single(tqspi->dev, t->tx_dma, len, DMA_TO_DEVICE);
	dma_unmap_single(tqspi->dev, t->rx_dma, len, DMA_FROM_DEVICE);
}

static int tegra_qspi_start_dma_based_transfer(struct tegra_qspi *tqspi, struct spi_transfer *t)
{
	struct dma_slave_config dma_sconfig = { 0 };
	unsigned int len;
	u8 dma_burst;
	int ret = 0;
	u32 val;

	if (tqspi->is_packed) {
		ret = tegra_qspi_dma_map_xfer(tqspi, t);
		if (ret < 0)
			return ret;
	}

	val = QSPI_DMA_BLK_SET(tqspi->curr_dma_words - 1);
	tegra_qspi_writel(tqspi, val, QSPI_DMA_BLK);

	tegra_qspi_unmask_irq(tqspi);

	if (tqspi->is_packed)
		len = DIV_ROUND_UP(tqspi->curr_dma_words * tqspi->bytes_per_word, 4) * 4;
	else
		len = tqspi->curr_dma_words * 4;

	/* set attention level based on length of transfer */
	val = 0;
	if (len & 0xf) {
		val |= QSPI_TX_TRIG_1 | QSPI_RX_TRIG_1;
		dma_burst = 1;
	} else if (((len) >> 4) & 0x1) {
		val |= QSPI_TX_TRIG_4 | QSPI_RX_TRIG_4;
		dma_burst = 4;
	} else {
		val |= QSPI_TX_TRIG_8 | QSPI_RX_TRIG_8;
		dma_burst = 8;
	}

	tegra_qspi_writel(tqspi, val, QSPI_DMA_CTL);
	tqspi->dma_control_reg = val;

	dma_sconfig.device_fc = true;
	if (tqspi->cur_direction & DATA_DIR_TX) {
		dma_sconfig.dst_addr = tqspi->phys + QSPI_TX_FIFO;
		dma_sconfig.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
		dma_sconfig.dst_maxburst = dma_burst;
		ret = dmaengine_slave_config(tqspi->tx_dma_chan, &dma_sconfig);
		if (ret < 0) {
			dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
			return ret;
		}

		tegra_qspi_copy_client_txbuf_to_qspi_txbuf(tqspi, t);
		ret = tegra_qspi_start_tx_dma(tqspi, t, len);
		if (ret < 0) {
			dev_err(tqspi->dev, "failed to starting TX DMA: %d\n", ret);
			return ret;
		}
	}

	if (tqspi->cur_direction & DATA_DIR_RX) {
		dma_sconfig.src_addr = tqspi->phys + QSPI_RX_FIFO;
		dma_sconfig.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES;
		dma_sconfig.src_maxburst = dma_burst;
		ret = dmaengine_slave_config(tqspi->rx_dma_chan, &dma_sconfig);
		if (ret < 0) {
			dev_err(tqspi->dev, "failed DMA slave config: %d\n", ret);
			return ret;
		}

		dma_sync_single_for_device(tqspi->dev, tqspi->rx_dma_phys,
					   tqspi->dma_buf_size,
					   DMA_FROM_DEVICE);

		ret = tegra_qspi_start_rx_dma(tqspi, t, len);
		if (ret < 0) {
			dev_err(tqspi->dev, "failed to start RX DMA: %d\n", ret);
			if (tqspi->cur_direction & DATA_DIR_TX)
				dmaengine_terminate_all(tqspi->tx_dma_chan);
			return ret;
		}
	}

	tegra_qspi_writel(tqspi, tqspi->command1_reg, QSPI_COMMAND1);

	tqspi->is_curr_dma_xfer = true;
	tqspi->dma_control_reg = val;
	val |= QSPI_DMA_EN;
	tegra_qspi_writel(tqspi, val, QSPI_DMA_CTL);

	return ret;
}

static int tegra_qspi_start_cpu_based_transfer(struct tegra_qspi *qspi, struct spi_transfer *t)
{
	u32 val;
	unsigned int cur_words;

	if (qspi->cur_direction & DATA_DIR_TX)
		cur_words = tegra_qspi_fill_tx_fifo_from_client_txbuf(qspi, t);
	else
		cur_words = qspi->curr_dma_words;

	val = QSPI_DMA_BLK_SET(cur_words - 1);
	tegra_qspi_writel(qspi, val, QSPI_DMA_BLK);

	tegra_qspi_unmask_irq(qspi);

	qspi->is_curr_dma_xfer = false;
	val = qspi->command1_reg;
	val |= QSPI_PIO;
	tegra_qspi_writel(qspi, val, QSPI_COMMAND1);

	return 0;
}

static void tegra_qspi_deinit_dma(struct tegra_qspi *tqspi)
{
	if (tqspi->tx_dma_buf) {
		dma_free_coherent(tqspi->dev, tqspi->dma_buf_size,
				  tqspi->tx_dma_buf, tqspi->tx_dma_phys);
		tqspi->tx_dma_buf = NULL;
	}

	if (tqspi->tx_dma_chan) {
		dma_release_channel(tqspi->tx_dma_chan);
		tqspi->tx_dma_chan = NULL;
	}

	if (tqspi->rx_dma_buf) {
		dma_free_coherent(tqspi->dev, tqspi->dma_buf_size,
				  tqspi->rx_dma_buf, tqspi->rx_dma_phys);
		tqspi->rx_dma_buf = NULL;
	}

	if (tqspi->rx_dma_chan) {
		dma_release_channel(tqspi->rx_dma_chan);
		tqspi->rx_dma_chan = NULL;
	}
}

static int tegra_qspi_init_dma(struct tegra_qspi *tqspi)
{
	struct dma_chan *dma_chan;
	dma_addr_t dma_phys;
	u32 *dma_buf;
	int err;

	dma_chan = dma_request_chan(tqspi->dev, "rx");
	if (IS_ERR(dma_chan)) {
		err = PTR_ERR(dma_chan);
		goto err_out;
	}

	tqspi->rx_dma_chan = dma_chan;

	dma_buf = dma_alloc_coherent(tqspi->dev, tqspi->dma_buf_size, &dma_phys, GFP_KERNEL);
	if (!dma_buf) {
		err = -ENOMEM;
		goto err_out;
	}

	tqspi->rx_dma_buf = dma_buf;
	tqspi->rx_dma_phys = dma_phys;

	dma_chan = dma_request_chan(tqspi->dev, "tx");
	if (IS_ERR(dma_chan)) {
		err = PTR_ERR(dma_chan);
		goto err_out;
	}

	tqspi->tx_dma_chan = dma_chan;

	dma_buf = dma_alloc_coherent(tqspi->dev, tqspi->dma_buf_size, &dma_phys, GFP_KERNEL);
	if (!dma_buf) {
		err = -ENOMEM;
		goto err_out;
	}

	tqspi->tx_dma_buf = dma_buf;
	tqspi->tx_dma_phys = dma_phys;
	tqspi->use_dma = true;

	return 0;

err_out:
	tegra_qspi_deinit_dma(tqspi);

	if (err != -EPROBE_DEFER) {
		dev_err(tqspi->dev, "cannot use DMA: %d\n", err);
		dev_err(tqspi->dev, "falling back to PIO\n");
		return 0;
	}

	return err;
}

static u32 tegra_qspi_setup_transfer_one(struct spi_device *spi, struct spi_transfer *t,
					 bool is_first_of_msg)
{
	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
	struct tegra_qspi_client_data *cdata = spi->controller_data;
	u32 command1, command2, speed = t->speed_hz;
	u8 bits_per_word = t->bits_per_word;
	u32 tx_tap = 0, rx_tap = 0;
	int req_mode;

	if (!has_acpi_companion(tqspi->dev) && speed != tqspi->cur_speed) {
		clk_set_rate(tqspi->clk, speed);
		tqspi->cur_speed = speed;
	}

	tqspi->cur_pos = 0;
	tqspi->cur_rx_pos = 0;
	tqspi->cur_tx_pos = 0;
	tqspi->curr_xfer = t;

	if (is_first_of_msg) {
		tegra_qspi_mask_clear_irq(tqspi);

		command1 = tqspi->def_command1_reg;
		command1 |= QSPI_CS_SEL(spi->chip_select);
		command1 |= QSPI_BIT_LENGTH(bits_per_word - 1);

		command1 &= ~QSPI_CONTROL_MODE_MASK;
		req_mode = spi->mode & 0x3;
		if (req_mode == SPI_MODE_3)
			command1 |= QSPI_CONTROL_MODE_3;
		else
			command1 |= QSPI_CONTROL_MODE_0;

		if (spi->mode & SPI_CS_HIGH)
			command1 |= QSPI_CS_SW_VAL;
		else
			command1 &= ~QSPI_CS_SW_VAL;
		tegra_qspi_writel(tqspi, command1, QSPI_COMMAND1);

		if (cdata && cdata->tx_clk_tap_delay)
			tx_tap = cdata->tx_clk_tap_delay;

		if (cdata && cdata->rx_clk_tap_delay)
			rx_tap = cdata->rx_clk_tap_delay;

		command2 = QSPI_TX_TAP_DELAY(tx_tap) | QSPI_RX_TAP_DELAY(rx_tap);
		if (command2 != tqspi->def_command2_reg)
			tegra_qspi_writel(tqspi, command2, QSPI_COMMAND2);

	} else {
		command1 = tqspi->command1_reg;
		command1 &= ~QSPI_BIT_LENGTH(~0);
		command1 |= QSPI_BIT_LENGTH(bits_per_word - 1);
	}

	command1 &= ~QSPI_SDR_DDR_SEL;

	return command1;
}

static int tegra_qspi_start_transfer_one(struct spi_device *spi,
					 struct spi_transfer *t, u32 command1)
{
	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
	unsigned int total_fifo_words;
	u8 bus_width = 0;
	int ret;

	total_fifo_words = tegra_qspi_calculate_curr_xfer_param(tqspi, t);

	command1 &= ~QSPI_PACKED;
	if (tqspi->is_packed)
		command1 |= QSPI_PACKED;
	tegra_qspi_writel(tqspi, command1, QSPI_COMMAND1);

	tqspi->cur_direction = 0;

	command1 &= ~(QSPI_TX_EN | QSPI_RX_EN);
	if (t->rx_buf) {
		command1 |= QSPI_RX_EN;
		tqspi->cur_direction |= DATA_DIR_RX;
		bus_width = t->rx_nbits;
	}

	if (t->tx_buf) {
		command1 |= QSPI_TX_EN;
		tqspi->cur_direction |= DATA_DIR_TX;
		bus_width = t->tx_nbits;
	}

	command1 &= ~QSPI_INTERFACE_WIDTH_MASK;

	if (bus_width == SPI_NBITS_QUAD)
		command1 |= QSPI_INTERFACE_WIDTH_QUAD;
	else if (bus_width == SPI_NBITS_DUAL)
		command1 |= QSPI_INTERFACE_WIDTH_DUAL;
	else
		command1 |= QSPI_INTERFACE_WIDTH_SINGLE;

	tqspi->command1_reg = command1;

	tegra_qspi_writel(tqspi, QSPI_NUM_DUMMY_CYCLE(tqspi->dummy_cycles), QSPI_MISC_REG);

	ret = tegra_qspi_flush_fifos(tqspi, false);
	if (ret < 0)
		return ret;

	if (tqspi->use_dma && total_fifo_words > QSPI_FIFO_DEPTH)
		ret = tegra_qspi_start_dma_based_transfer(tqspi, t);
	else
		ret = tegra_qspi_start_cpu_based_transfer(tqspi, t);

	return ret;
}

static struct tegra_qspi_client_data *tegra_qspi_parse_cdata_dt(struct spi_device *spi)
{
	struct tegra_qspi_client_data *cdata;

	cdata = devm_kzalloc(&spi->dev, sizeof(*cdata), GFP_KERNEL);
	if (!cdata)
		return NULL;

	device_property_read_u32(&spi->dev, "nvidia,tx-clk-tap-delay",
				 &cdata->tx_clk_tap_delay);
	device_property_read_u32(&spi->dev, "nvidia,rx-clk-tap-delay",
				 &cdata->rx_clk_tap_delay);

	return cdata;
}

static int tegra_qspi_setup(struct spi_device *spi)
{
	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
	struct tegra_qspi_client_data *cdata = spi->controller_data;
	unsigned long flags;
	u32 val;
	int ret;

	ret = pm_runtime_resume_and_get(tqspi->dev);
	if (ret < 0) {
		dev_err(tqspi->dev, "failed to get runtime PM: %d\n", ret);
		return ret;
	}

	if (!cdata) {
		cdata = tegra_qspi_parse_cdata_dt(spi);
		spi->controller_data = cdata;
	}
	spin_lock_irqsave(&tqspi->lock, flags);

	/* keep default cs state to inactive */
	val = tqspi->def_command1_reg;
	val |= QSPI_CS_SEL(spi->chip_select);
	if (spi->mode & SPI_CS_HIGH)
		val &= ~QSPI_CS_POL_INACTIVE(spi->chip_select);
	else
		val |= QSPI_CS_POL_INACTIVE(spi->chip_select);

	tqspi->def_command1_reg = val;
	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);

	spin_unlock_irqrestore(&tqspi->lock, flags);

	pm_runtime_put(tqspi->dev);

	return 0;
}

static void tegra_qspi_dump_regs(struct tegra_qspi *tqspi)
{
	dev_dbg(tqspi->dev, "============ QSPI REGISTER DUMP ============\n");
	dev_dbg(tqspi->dev, "Command1:    0x%08x | Command2:    0x%08x\n",
		tegra_qspi_readl(tqspi, QSPI_COMMAND1),
		tegra_qspi_readl(tqspi, QSPI_COMMAND2));
	dev_dbg(tqspi->dev, "DMA_CTL:     0x%08x | DMA_BLK:     0x%08x\n",
		tegra_qspi_readl(tqspi, QSPI_DMA_CTL),
		tegra_qspi_readl(tqspi, QSPI_DMA_BLK));
	dev_dbg(tqspi->dev, "INTR_MASK:  0x%08x | MISC: 0x%08x\n",
		tegra_qspi_readl(tqspi, QSPI_INTR_MASK),
		tegra_qspi_readl(tqspi, QSPI_MISC_REG));
	dev_dbg(tqspi->dev, "TRANS_STAT:  0x%08x | FIFO_STATUS: 0x%08x\n",
		tegra_qspi_readl(tqspi, QSPI_TRANS_STATUS),
		tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS));
}

static void tegra_qspi_handle_error(struct tegra_qspi *tqspi)
{
	dev_err(tqspi->dev, "error in transfer, fifo status 0x%08x\n", tqspi->status_reg);
	tegra_qspi_dump_regs(tqspi);
	tegra_qspi_flush_fifos(tqspi, true);
	if (device_reset(tqspi->dev) < 0)
		dev_warn_once(tqspi->dev, "device reset failed\n");
}

static void tegra_qspi_transfer_end(struct spi_device *spi)
{
	struct tegra_qspi *tqspi = spi_master_get_devdata(spi->master);
	int cs_val = (spi->mode & SPI_CS_HIGH) ? 0 : 1;

	if (cs_val)
		tqspi->command1_reg |= QSPI_CS_SW_VAL;
	else
		tqspi->command1_reg &= ~QSPI_CS_SW_VAL;
	tegra_qspi_writel(tqspi, tqspi->command1_reg, QSPI_COMMAND1);
	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);
}

static u32 tegra_qspi_cmd_config(bool is_ddr, u8 bus_width, u8 len)
{
	u32 cmd_config = 0;

	/* Extract Command configuration and value */
	if (is_ddr)
		cmd_config |= QSPI_COMMAND_SDR_DDR;
	else
		cmd_config &= ~QSPI_COMMAND_SDR_DDR;

	cmd_config |= QSPI_COMMAND_X1_X2_X4(bus_width);
	cmd_config |= QSPI_COMMAND_SIZE_SET((len * 8) - 1);

	return cmd_config;
}

static u32 tegra_qspi_addr_config(bool is_ddr, u8 bus_width, u8 len)
{
	u32 addr_config = 0;

	/* Extract Address configuration and value */
	is_ddr = 0; //Only SDR mode supported
	bus_width = 0; //X1 mode

	if (is_ddr)
		addr_config |= QSPI_ADDRESS_SDR_DDR;
	else
		addr_config &= ~QSPI_ADDRESS_SDR_DDR;

	addr_config |= QSPI_ADDRESS_X1_X2_X4(bus_width);
	addr_config |= QSPI_ADDRESS_SIZE_SET((len * 8) - 1);

	return addr_config;
}

static int tegra_qspi_combined_seq_xfer(struct tegra_qspi *tqspi,
					struct spi_message *msg)
{
	bool is_first_msg = true;
	struct spi_transfer *xfer;
	struct spi_device *spi = msg->spi;
	u8 transfer_phase = 0;
	u32 cmd1 = 0, dma_ctl = 0;
	int ret = 0;
	u32 address_value = 0;
	u32 cmd_config = 0, addr_config = 0;
	u8 cmd_value = 0, val = 0;

	/* Enable Combined sequence mode */
	val = tegra_qspi_readl(tqspi, QSPI_GLOBAL_CONFIG);
	val |= QSPI_CMB_SEQ_EN;
	tegra_qspi_writel(tqspi, val, QSPI_GLOBAL_CONFIG);
	/* Process individual transfer list */
	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
		switch (transfer_phase) {
		case CMD_TRANSFER:
			/* X1 SDR mode */
			cmd_config = tegra_qspi_cmd_config(false, 0,
							   xfer->len);
			cmd_value = *((const u8 *)(xfer->tx_buf));
			break;
		case ADDR_TRANSFER:
			/* X1 SDR mode */
			addr_config = tegra_qspi_addr_config(false, 0,
							     xfer->len);
			address_value = *((const u32 *)(xfer->tx_buf));
			break;
		case DATA_TRANSFER:
			/* Program Command, Address value in register */
			tegra_qspi_writel(tqspi, cmd_value, QSPI_CMB_SEQ_CMD);
			tegra_qspi_writel(tqspi, address_value,
					  QSPI_CMB_SEQ_ADDR);
			/* Program Command and Address config in register */
			tegra_qspi_writel(tqspi, cmd_config,
					  QSPI_CMB_SEQ_CMD_CFG);
			tegra_qspi_writel(tqspi, addr_config,
					  QSPI_CMB_SEQ_ADDR_CFG);

			reinit_completion(&tqspi->xfer_completion);
			cmd1 = tegra_qspi_setup_transfer_one(spi, xfer,
							     is_first_msg);
			ret = tegra_qspi_start_transfer_one(spi, xfer,
							    cmd1);

			if (ret < 0) {
				dev_err(tqspi->dev, "Failed to start transfer-one: %d\n",
					ret);
				return ret;
			}

			is_first_msg = false;
			ret = wait_for_completion_timeout
					(&tqspi->xfer_completion,
					QSPI_DMA_TIMEOUT);

			if (WARN_ON(ret == 0)) {
				dev_err(tqspi->dev, "QSPI Transfer failed with timeout: %d\n",
					ret);
				if (tqspi->is_curr_dma_xfer &&
				    (tqspi->cur_direction & DATA_DIR_TX))
					dmaengine_terminate_all
						(tqspi->tx_dma_chan);

				if (tqspi->is_curr_dma_xfer &&
				    (tqspi->cur_direction & DATA_DIR_RX))
					dmaengine_terminate_all
						(tqspi->rx_dma_chan);

				/* Abort transfer by resetting pio/dma bit */
				if (!tqspi->is_curr_dma_xfer) {
					cmd1 = tegra_qspi_readl
							(tqspi,
							 QSPI_COMMAND1);
					cmd1 &= ~QSPI_PIO;
					tegra_qspi_writel
							(tqspi, cmd1,
							 QSPI_COMMAND1);
				} else {
					dma_ctl = tegra_qspi_readl
							(tqspi,
							 QSPI_DMA_CTL);
					dma_ctl &= ~QSPI_DMA_EN;
					tegra_qspi_writel(tqspi, dma_ctl,
							  QSPI_DMA_CTL);
				}

				/* Reset controller if timeout happens */
				if (device_reset(tqspi->dev) < 0)
					dev_warn_once(tqspi->dev,
						      "device reset failed\n");
				ret = -EIO;
				goto exit;
			}

			if (tqspi->tx_status ||  tqspi->rx_status) {
				dev_err(tqspi->dev, "QSPI Transfer failed\n");
				tqspi->tx_status = 0;
				tqspi->rx_status = 0;
				ret = -EIO;
				goto exit;
			}
			break;
		default:
			ret = -EINVAL;
			goto exit;
		}
		msg->actual_length += xfer->len;
		transfer_phase++;
	}
	if (!xfer->cs_change) {
		tegra_qspi_transfer_end(spi);
		spi_transfer_delay_exec(xfer);
	}
	ret = 0;

exit:
	msg->status = ret;

	return ret;
}

static int tegra_qspi_non_combined_seq_xfer(struct tegra_qspi *tqspi,
					    struct spi_message *msg)
{
	struct spi_device *spi = msg->spi;
	struct spi_transfer *transfer;
	bool is_first_msg = true;
	int ret = 0, val = 0;

	msg->status = 0;
	msg->actual_length = 0;
	tqspi->tx_status = 0;
	tqspi->rx_status = 0;

	/* Disable Combined sequence mode */
	val = tegra_qspi_readl(tqspi, QSPI_GLOBAL_CONFIG);
	val &= ~QSPI_CMB_SEQ_EN;
	tegra_qspi_writel(tqspi, val, QSPI_GLOBAL_CONFIG);
	list_for_each_entry(transfer, &msg->transfers, transfer_list) {
		struct spi_transfer *xfer = transfer;
		u8 dummy_bytes = 0;
		u32 cmd1;

		tqspi->dummy_cycles = 0;
		/*
		 * Tegra QSPI hardware supports dummy bytes transfer after actual transfer
		 * bytes based on programmed dummy clock cycles in the QSPI_MISC register.
		 * So, check if the next transfer is dummy data transfer and program dummy
		 * clock cycles along with the current transfer and skip next transfer.
		 */
		if (!list_is_last(&xfer->transfer_list, &msg->transfers)) {
			struct spi_transfer *next_xfer;

			next_xfer = list_next_entry(xfer, transfer_list);
			if (next_xfer->dummy_data) {
				u32 dummy_cycles = next_xfer->len * 8 / next_xfer->tx_nbits;

				if (dummy_cycles <= QSPI_DUMMY_CYCLES_MAX) {
					tqspi->dummy_cycles = dummy_cycles;
					dummy_bytes = next_xfer->len;
					transfer = next_xfer;
				}
			}
		}

		reinit_completion(&tqspi->xfer_completion);

		cmd1 = tegra_qspi_setup_transfer_one(spi, xfer, is_first_msg);

		ret = tegra_qspi_start_transfer_one(spi, xfer, cmd1);
		if (ret < 0) {
			dev_err(tqspi->dev, "failed to start transfer: %d\n", ret);
			goto complete_xfer;
		}

		ret = wait_for_completion_timeout(&tqspi->xfer_completion,
						  QSPI_DMA_TIMEOUT);
		if (WARN_ON(ret == 0)) {
			dev_err(tqspi->dev, "transfer timeout\n");
			if (tqspi->is_curr_dma_xfer && (tqspi->cur_direction & DATA_DIR_TX))
				dmaengine_terminate_all(tqspi->tx_dma_chan);
			if (tqspi->is_curr_dma_xfer && (tqspi->cur_direction & DATA_DIR_RX))
				dmaengine_terminate_all(tqspi->rx_dma_chan);
			tegra_qspi_handle_error(tqspi);
			ret = -EIO;
			goto complete_xfer;
		}

		if (tqspi->tx_status ||  tqspi->rx_status) {
			tegra_qspi_handle_error(tqspi);
			ret = -EIO;
			goto complete_xfer;
		}

		msg->actual_length += xfer->len + dummy_bytes;

complete_xfer:
		if (ret < 0) {
			tegra_qspi_transfer_end(spi);
			spi_transfer_delay_exec(xfer);
			goto exit;
		}

		if (list_is_last(&xfer->transfer_list, &msg->transfers)) {
			/* de-activate CS after last transfer only when cs_change is not set */
			if (!xfer->cs_change) {
				tegra_qspi_transfer_end(spi);
				spi_transfer_delay_exec(xfer);
			}
		} else if (xfer->cs_change) {
			 /* de-activated CS between the transfers only when cs_change is set */
			tegra_qspi_transfer_end(spi);
			spi_transfer_delay_exec(xfer);
		}
	}

	ret = 0;
exit:
	msg->status = ret;

	return ret;
}

static bool tegra_qspi_validate_cmb_seq(struct tegra_qspi *tqspi,
					struct spi_message *msg)
{
	int transfer_count = 0;
	struct spi_transfer *xfer;

	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
		transfer_count++;
	}
	if (!tqspi->soc_data->cmb_xfer_capable || transfer_count != 3)
		return false;
	xfer = list_first_entry(&msg->transfers, typeof(*xfer),
				transfer_list);
	if (xfer->len > 2)
		return false;
	xfer = list_next_entry(xfer, transfer_list);
	if (xfer->len > 4 || xfer->len < 3)
		return false;
	xfer = list_next_entry(xfer, transfer_list);
	if (!tqspi->soc_data->has_dma || xfer->len > (QSPI_FIFO_DEPTH << 2))
		return false;

	return true;
}

static int tegra_qspi_transfer_one_message(struct spi_master *master,
					   struct spi_message *msg)
{
	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
	int ret;

	if (tegra_qspi_validate_cmb_seq(tqspi, msg))
		ret = tegra_qspi_combined_seq_xfer(tqspi, msg);
	else
		ret = tegra_qspi_non_combined_seq_xfer(tqspi, msg);

	spi_finalize_current_message(master);

	return ret;
}

static irqreturn_t handle_cpu_based_xfer(struct tegra_qspi *tqspi)
{
	struct spi_transfer *t = tqspi->curr_xfer;
	unsigned long flags;

	spin_lock_irqsave(&tqspi->lock, flags);

	if (tqspi->tx_status ||  tqspi->rx_status) {
		tegra_qspi_handle_error(tqspi);
		complete(&tqspi->xfer_completion);
		goto exit;
	}

	if (tqspi->cur_direction & DATA_DIR_RX)
		tegra_qspi_read_rx_fifo_to_client_rxbuf(tqspi, t);

	if (tqspi->cur_direction & DATA_DIR_TX)
		tqspi->cur_pos = tqspi->cur_tx_pos;
	else
		tqspi->cur_pos = tqspi->cur_rx_pos;

	if (tqspi->cur_pos == t->len) {
		complete(&tqspi->xfer_completion);
		goto exit;
	}

	tegra_qspi_calculate_curr_xfer_param(tqspi, t);
	tegra_qspi_start_cpu_based_transfer(tqspi, t);
exit:
	spin_unlock_irqrestore(&tqspi->lock, flags);
	return IRQ_HANDLED;
}

static irqreturn_t handle_dma_based_xfer(struct tegra_qspi *tqspi)
{
	struct spi_transfer *t = tqspi->curr_xfer;
	unsigned int total_fifo_words;
	unsigned long flags;
	long wait_status;
	int err = 0;

	if (tqspi->cur_direction & DATA_DIR_TX) {
		if (tqspi->tx_status) {
			dmaengine_terminate_all(tqspi->tx_dma_chan);
			err += 1;
		} else {
			wait_status = wait_for_completion_interruptible_timeout(
				&tqspi->tx_dma_complete, QSPI_DMA_TIMEOUT);
			if (wait_status <= 0) {
				dmaengine_terminate_all(tqspi->tx_dma_chan);
				dev_err(tqspi->dev, "failed TX DMA transfer\n");
				err += 1;
			}
		}
	}

	if (tqspi->cur_direction & DATA_DIR_RX) {
		if (tqspi->rx_status) {
			dmaengine_terminate_all(tqspi->rx_dma_chan);
			err += 2;
		} else {
			wait_status = wait_for_completion_interruptible_timeout(
				&tqspi->rx_dma_complete, QSPI_DMA_TIMEOUT);
			if (wait_status <= 0) {
				dmaengine_terminate_all(tqspi->rx_dma_chan);
				dev_err(tqspi->dev, "failed RX DMA transfer\n");
				err += 2;
			}
		}
	}

	spin_lock_irqsave(&tqspi->lock, flags);

	if (err) {
		tegra_qspi_dma_unmap_xfer(tqspi, t);
		tegra_qspi_handle_error(tqspi);
		complete(&tqspi->xfer_completion);
		goto exit;
	}

	if (tqspi->cur_direction & DATA_DIR_RX)
		tegra_qspi_copy_qspi_rxbuf_to_client_rxbuf(tqspi, t);

	if (tqspi->cur_direction & DATA_DIR_TX)
		tqspi->cur_pos = tqspi->cur_tx_pos;
	else
		tqspi->cur_pos = tqspi->cur_rx_pos;

	if (tqspi->cur_pos == t->len) {
		tegra_qspi_dma_unmap_xfer(tqspi, t);
		complete(&tqspi->xfer_completion);
		goto exit;
	}

	tegra_qspi_dma_unmap_xfer(tqspi, t);

	/* continue transfer in current message */
	total_fifo_words = tegra_qspi_calculate_curr_xfer_param(tqspi, t);
	if (total_fifo_words > QSPI_FIFO_DEPTH)
		err = tegra_qspi_start_dma_based_transfer(tqspi, t);
	else
		err = tegra_qspi_start_cpu_based_transfer(tqspi, t);

exit:
	spin_unlock_irqrestore(&tqspi->lock, flags);
	return IRQ_HANDLED;
}

static irqreturn_t tegra_qspi_isr_thread(int irq, void *context_data)
{
	struct tegra_qspi *tqspi = context_data;

	tqspi->status_reg = tegra_qspi_readl(tqspi, QSPI_FIFO_STATUS);

	if (tqspi->cur_direction & DATA_DIR_TX)
		tqspi->tx_status = tqspi->status_reg & (QSPI_TX_FIFO_UNF | QSPI_TX_FIFO_OVF);

	if (tqspi->cur_direction & DATA_DIR_RX)
		tqspi->rx_status = tqspi->status_reg & (QSPI_RX_FIFO_OVF | QSPI_RX_FIFO_UNF);

	tegra_qspi_mask_clear_irq(tqspi);

	if (!tqspi->is_curr_dma_xfer)
		return handle_cpu_based_xfer(tqspi);

	return handle_dma_based_xfer(tqspi);
}

static struct tegra_qspi_soc_data tegra210_qspi_soc_data = {
	.has_dma = true,
	.cmb_xfer_capable = false,
	.cs_count = 1,
};

static struct tegra_qspi_soc_data tegra186_qspi_soc_data = {
	.has_dma = true,
	.cmb_xfer_capable = true,
	.cs_count = 1,
};

static struct tegra_qspi_soc_data tegra234_qspi_soc_data = {
	.has_dma = false,
	.cmb_xfer_capable = true,
	.cs_count = 1,
};

static struct tegra_qspi_soc_data tegra241_qspi_soc_data = {
	.has_dma = false,
	.cmb_xfer_capable = true,
	.cs_count = 4,
};

static const struct of_device_id tegra_qspi_of_match[] = {
	{
		.compatible = "nvidia,tegra210-qspi",
		.data	    = &tegra210_qspi_soc_data,
	}, {
		.compatible = "nvidia,tegra186-qspi",
		.data	    = &tegra186_qspi_soc_data,
	}, {
		.compatible = "nvidia,tegra194-qspi",
		.data	    = &tegra186_qspi_soc_data,
	}, {
		.compatible = "nvidia,tegra234-qspi",
		.data	    = &tegra234_qspi_soc_data,
	}, {
		.compatible = "nvidia,tegra241-qspi",
		.data	    = &tegra241_qspi_soc_data,
	},
	{}
};

MODULE_DEVICE_TABLE(of, tegra_qspi_of_match);

#ifdef CONFIG_ACPI
static const struct acpi_device_id tegra_qspi_acpi_match[] = {
	{
		.id = "NVDA1213",
		.driver_data = (kernel_ulong_t)&tegra210_qspi_soc_data,
	}, {
		.id = "NVDA1313",
		.driver_data = (kernel_ulong_t)&tegra186_qspi_soc_data,
	}, {
		.id = "NVDA1413",
		.driver_data = (kernel_ulong_t)&tegra234_qspi_soc_data,
	}, {
		.id = "NVDA1513",
		.driver_data = (kernel_ulong_t)&tegra241_qspi_soc_data,
	},
	{}
};

MODULE_DEVICE_TABLE(acpi, tegra_qspi_acpi_match);
#endif

static int tegra_qspi_probe(struct platform_device *pdev)
{
	struct spi_master	*master;
	struct tegra_qspi	*tqspi;
	struct resource		*r;
	int ret, qspi_irq;
	int bus_num;

	master = devm_spi_alloc_master(&pdev->dev, sizeof(*tqspi));
	if (!master)
		return -ENOMEM;

	platform_set_drvdata(pdev, master);
	tqspi = spi_master_get_devdata(master);

	master->mode_bits = SPI_MODE_0 | SPI_MODE_3 | SPI_CS_HIGH |
			    SPI_TX_DUAL | SPI_RX_DUAL | SPI_TX_QUAD | SPI_RX_QUAD;
	master->bits_per_word_mask = SPI_BPW_MASK(32) | SPI_BPW_MASK(16) | SPI_BPW_MASK(8);
	master->setup = tegra_qspi_setup;
	master->transfer_one_message = tegra_qspi_transfer_one_message;
	master->num_chipselect = 1;
	master->auto_runtime_pm = true;

	bus_num = of_alias_get_id(pdev->dev.of_node, "spi");
	if (bus_num >= 0)
		master->bus_num = bus_num;

	tqspi->master = master;
	tqspi->dev = &pdev->dev;
	spin_lock_init(&tqspi->lock);

	tqspi->soc_data = device_get_match_data(&pdev->dev);
	master->num_chipselect = tqspi->soc_data->cs_count;
	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	tqspi->base = devm_ioremap_resource(&pdev->dev, r);
	if (IS_ERR(tqspi->base))
		return PTR_ERR(tqspi->base);

	tqspi->phys = r->start;
	qspi_irq = platform_get_irq(pdev, 0);
	if (qspi_irq < 0)
		return qspi_irq;
	tqspi->irq = qspi_irq;

	if (!has_acpi_companion(tqspi->dev)) {
		tqspi->clk = devm_clk_get(&pdev->dev, "qspi");
		if (IS_ERR(tqspi->clk)) {
			ret = PTR_ERR(tqspi->clk);
			dev_err(&pdev->dev, "failed to get clock: %d\n", ret);
			return ret;
		}

	}

	tqspi->max_buf_size = QSPI_FIFO_DEPTH << 2;
	tqspi->dma_buf_size = DEFAULT_QSPI_DMA_BUF_LEN;

	ret = tegra_qspi_init_dma(tqspi);
	if (ret < 0)
		return ret;

	if (tqspi->use_dma)
		tqspi->max_buf_size = tqspi->dma_buf_size;

	init_completion(&tqspi->tx_dma_complete);
	init_completion(&tqspi->rx_dma_complete);
	init_completion(&tqspi->xfer_completion);

	pm_runtime_enable(&pdev->dev);
	ret = pm_runtime_resume_and_get(&pdev->dev);
	if (ret < 0) {
		dev_err(&pdev->dev, "failed to get runtime PM: %d\n", ret);
		goto exit_pm_disable;
	}

	if (device_reset(tqspi->dev) < 0)
		dev_warn_once(tqspi->dev, "device reset failed\n");

	tqspi->def_command1_reg = QSPI_M_S | QSPI_CS_SW_HW |  QSPI_CS_SW_VAL;
	tegra_qspi_writel(tqspi, tqspi->def_command1_reg, QSPI_COMMAND1);
	tqspi->spi_cs_timing1 = tegra_qspi_readl(tqspi, QSPI_CS_TIMING1);
	tqspi->spi_cs_timing2 = tegra_qspi_readl(tqspi, QSPI_CS_TIMING2);
	tqspi->def_command2_reg = tegra_qspi_readl(tqspi, QSPI_COMMAND2);

	pm_runtime_put(&pdev->dev);

	ret = request_threaded_irq(tqspi->irq, NULL,
				   tegra_qspi_isr_thread, IRQF_ONESHOT,
				   dev_name(&pdev->dev), tqspi);
	if (ret < 0) {
		dev_err(&pdev->dev, "failed to request IRQ#%u: %d\n", tqspi->irq, ret);
		goto exit_pm_disable;
	}

	master->dev.of_node = pdev->dev.of_node;
	ret = spi_register_master(master);
	if (ret < 0) {
		dev_err(&pdev->dev, "failed to register master: %d\n", ret);
		goto exit_free_irq;
	}

	return 0;

exit_free_irq:
	free_irq(qspi_irq, tqspi);
exit_pm_disable:
	pm_runtime_force_suspend(&pdev->dev);
	tegra_qspi_deinit_dma(tqspi);
	return ret;
}

static int tegra_qspi_remove(struct platform_device *pdev)
{
	struct spi_master *master = platform_get_drvdata(pdev);
	struct tegra_qspi *tqspi = spi_master_get_devdata(master);

	spi_unregister_master(master);
	free_irq(tqspi->irq, tqspi);
	pm_runtime_force_suspend(&pdev->dev);
	tegra_qspi_deinit_dma(tqspi);

	return 0;
}

static int __maybe_unused tegra_qspi_suspend(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);

	return spi_master_suspend(master);
}

static int __maybe_unused tegra_qspi_resume(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);
	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
	int ret;

	ret = pm_runtime_resume_and_get(dev);
	if (ret < 0) {
		dev_err(dev, "failed to get runtime PM: %d\n", ret);
		return ret;
	}

	tegra_qspi_writel(tqspi, tqspi->command1_reg, QSPI_COMMAND1);
	tegra_qspi_writel(tqspi, tqspi->def_command2_reg, QSPI_COMMAND2);
	pm_runtime_put(dev);

	return spi_master_resume(master);
}

static int __maybe_unused tegra_qspi_runtime_suspend(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);
	struct tegra_qspi *tqspi = spi_master_get_devdata(master);

	/* Runtime pm disabled with ACPI */
	if (has_acpi_companion(tqspi->dev))
		return 0;
	/* flush all write which are in PPSB queue by reading back */
	tegra_qspi_readl(tqspi, QSPI_COMMAND1);

	clk_disable_unprepare(tqspi->clk);

	return 0;
}

static int __maybe_unused tegra_qspi_runtime_resume(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);
	struct tegra_qspi *tqspi = spi_master_get_devdata(master);
	int ret;

	/* Runtime pm disabled with ACPI */
	if (has_acpi_companion(tqspi->dev))
		return 0;
	ret = clk_prepare_enable(tqspi->clk);
	if (ret < 0)
		dev_err(tqspi->dev, "failed to enable clock: %d\n", ret);

	return ret;
}

static const struct dev_pm_ops tegra_qspi_pm_ops = {
	SET_RUNTIME_PM_OPS(tegra_qspi_runtime_suspend, tegra_qspi_runtime_resume, NULL)
	SET_SYSTEM_SLEEP_PM_OPS(tegra_qspi_suspend, tegra_qspi_resume)
};

static struct platform_driver tegra_qspi_driver = {
	.driver = {
		.name		= "tegra-qspi",
		.pm		= &tegra_qspi_pm_ops,
		.of_match_table	= tegra_qspi_of_match,
		.acpi_match_table = ACPI_PTR(tegra_qspi_acpi_match),
	},
	.probe =	tegra_qspi_probe,
	.remove =	tegra_qspi_remove,
};
module_platform_driver(tegra_qspi_driver);

MODULE_ALIAS("platform:qspi-tegra");
MODULE_DESCRIPTION("NVIDIA Tegra QSPI Controller Driver");
MODULE_AUTHOR("Sowjanya Komatineni <skomatineni@nvidia.com>");
MODULE_LICENSE("GPL v2");