Free Electrons

Embedded Linux Experts

   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
/*
 * Driver for Atmel AT32 and AT91 SPI Controllers
 *
 * Copyright (C) 2006 Atmel Corporation
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#include <linux/kernel.h>
#include <linux/clk.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/delay.h>
#include <linux/dma-mapping.h>
#include <linux/dmaengine.h>
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/spi/spi.h>
#include <linux/slab.h>
#include <linux/platform_data/dma-atmel.h>
#include <linux/of.h>

#include <linux/io.h>
#include <linux/gpio.h>
#include <linux/of_gpio.h>
#include <linux/pinctrl/consumer.h>
#include <linux/pm_runtime.h>

/* SPI register offsets */
#define SPI_CR					0x0000
#define SPI_MR					0x0004
#define SPI_RDR					0x0008
#define SPI_TDR					0x000c
#define SPI_SR					0x0010
#define SPI_IER					0x0014
#define SPI_IDR					0x0018
#define SPI_IMR					0x001c
#define SPI_CSR0				0x0030
#define SPI_CSR1				0x0034
#define SPI_CSR2				0x0038
#define SPI_CSR3				0x003c
#define SPI_FMR					0x0040
#define SPI_FLR					0x0044
#define SPI_VERSION				0x00fc
#define SPI_RPR					0x0100
#define SPI_RCR					0x0104
#define SPI_TPR					0x0108
#define SPI_TCR					0x010c
#define SPI_RNPR				0x0110
#define SPI_RNCR				0x0114
#define SPI_TNPR				0x0118
#define SPI_TNCR				0x011c
#define SPI_PTCR				0x0120
#define SPI_PTSR				0x0124

/* Bitfields in CR */
#define SPI_SPIEN_OFFSET			0
#define SPI_SPIEN_SIZE				1
#define SPI_SPIDIS_OFFSET			1
#define SPI_SPIDIS_SIZE				1
#define SPI_SWRST_OFFSET			7
#define SPI_SWRST_SIZE				1
#define SPI_LASTXFER_OFFSET			24
#define SPI_LASTXFER_SIZE			1
#define SPI_TXFCLR_OFFSET			16
#define SPI_TXFCLR_SIZE				1
#define SPI_RXFCLR_OFFSET			17
#define SPI_RXFCLR_SIZE				1
#define SPI_FIFOEN_OFFSET			30
#define SPI_FIFOEN_SIZE				1
#define SPI_FIFODIS_OFFSET			31
#define SPI_FIFODIS_SIZE			1

/* Bitfields in MR */
#define SPI_MSTR_OFFSET				0
#define SPI_MSTR_SIZE				1
#define SPI_PS_OFFSET				1
#define SPI_PS_SIZE				1
#define SPI_PCSDEC_OFFSET			2
#define SPI_PCSDEC_SIZE				1
#define SPI_FDIV_OFFSET				3
#define SPI_FDIV_SIZE				1
#define SPI_MODFDIS_OFFSET			4
#define SPI_MODFDIS_SIZE			1
#define SPI_WDRBT_OFFSET			5
#define SPI_WDRBT_SIZE				1
#define SPI_LLB_OFFSET				7
#define SPI_LLB_SIZE				1
#define SPI_PCS_OFFSET				16
#define SPI_PCS_SIZE				4
#define SPI_DLYBCS_OFFSET			24
#define SPI_DLYBCS_SIZE				8

/* Bitfields in RDR */
#define SPI_RD_OFFSET				0
#define SPI_RD_SIZE				16

/* Bitfields in TDR */
#define SPI_TD_OFFSET				0
#define SPI_TD_SIZE				16

/* Bitfields in SR */
#define SPI_RDRF_OFFSET				0
#define SPI_RDRF_SIZE				1
#define SPI_TDRE_OFFSET				1
#define SPI_TDRE_SIZE				1
#define SPI_MODF_OFFSET				2
#define SPI_MODF_SIZE				1
#define SPI_OVRES_OFFSET			3
#define SPI_OVRES_SIZE				1
#define SPI_ENDRX_OFFSET			4
#define SPI_ENDRX_SIZE				1
#define SPI_ENDTX_OFFSET			5
#define SPI_ENDTX_SIZE				1
#define SPI_RXBUFF_OFFSET			6
#define SPI_RXBUFF_SIZE				1
#define SPI_TXBUFE_OFFSET			7
#define SPI_TXBUFE_SIZE				1
#define SPI_NSSR_OFFSET				8
#define SPI_NSSR_SIZE				1
#define SPI_TXEMPTY_OFFSET			9
#define SPI_TXEMPTY_SIZE			1
#define SPI_SPIENS_OFFSET			16
#define SPI_SPIENS_SIZE				1
#define SPI_TXFEF_OFFSET			24
#define SPI_TXFEF_SIZE				1
#define SPI_TXFFF_OFFSET			25
#define SPI_TXFFF_SIZE				1
#define SPI_TXFTHF_OFFSET			26
#define SPI_TXFTHF_SIZE				1
#define SPI_RXFEF_OFFSET			27
#define SPI_RXFEF_SIZE				1
#define SPI_RXFFF_OFFSET			28
#define SPI_RXFFF_SIZE				1
#define SPI_RXFTHF_OFFSET			29
#define SPI_RXFTHF_SIZE				1
#define SPI_TXFPTEF_OFFSET			30
#define SPI_TXFPTEF_SIZE			1
#define SPI_RXFPTEF_OFFSET			31
#define SPI_RXFPTEF_SIZE			1

/* Bitfields in CSR0 */
#define SPI_CPOL_OFFSET				0
#define SPI_CPOL_SIZE				1
#define SPI_NCPHA_OFFSET			1
#define SPI_NCPHA_SIZE				1
#define SPI_CSAAT_OFFSET			3
#define SPI_CSAAT_SIZE				1
#define SPI_BITS_OFFSET				4
#define SPI_BITS_SIZE				4
#define SPI_SCBR_OFFSET				8
#define SPI_SCBR_SIZE				8
#define SPI_DLYBS_OFFSET			16
#define SPI_DLYBS_SIZE				8
#define SPI_DLYBCT_OFFSET			24
#define SPI_DLYBCT_SIZE				8

/* Bitfields in RCR */
#define SPI_RXCTR_OFFSET			0
#define SPI_RXCTR_SIZE				16

/* Bitfields in TCR */
#define SPI_TXCTR_OFFSET			0
#define SPI_TXCTR_SIZE				16

/* Bitfields in RNCR */
#define SPI_RXNCR_OFFSET			0
#define SPI_RXNCR_SIZE				16

/* Bitfields in TNCR */
#define SPI_TXNCR_OFFSET			0
#define SPI_TXNCR_SIZE				16

/* Bitfields in PTCR */
#define SPI_RXTEN_OFFSET			0
#define SPI_RXTEN_SIZE				1
#define SPI_RXTDIS_OFFSET			1
#define SPI_RXTDIS_SIZE				1
#define SPI_TXTEN_OFFSET			8
#define SPI_TXTEN_SIZE				1
#define SPI_TXTDIS_OFFSET			9
#define SPI_TXTDIS_SIZE				1

/* Bitfields in FMR */
#define SPI_TXRDYM_OFFSET			0
#define SPI_TXRDYM_SIZE				2
#define SPI_RXRDYM_OFFSET			4
#define SPI_RXRDYM_SIZE				2
#define SPI_TXFTHRES_OFFSET			16
#define SPI_TXFTHRES_SIZE			6
#define SPI_RXFTHRES_OFFSET			24
#define SPI_RXFTHRES_SIZE			6

/* Bitfields in FLR */
#define SPI_TXFL_OFFSET				0
#define SPI_TXFL_SIZE				6
#define SPI_RXFL_OFFSET				16
#define SPI_RXFL_SIZE				6

/* Constants for BITS */
#define SPI_BITS_8_BPT				0
#define SPI_BITS_9_BPT				1
#define SPI_BITS_10_BPT				2
#define SPI_BITS_11_BPT				3
#define SPI_BITS_12_BPT				4
#define SPI_BITS_13_BPT				5
#define SPI_BITS_14_BPT				6
#define SPI_BITS_15_BPT				7
#define SPI_BITS_16_BPT				8
#define SPI_ONE_DATA				0
#define SPI_TWO_DATA				1
#define SPI_FOUR_DATA				2

/* Bit manipulation macros */
#define SPI_BIT(name) \
	(1 << SPI_##name##_OFFSET)
#define SPI_BF(name, value) \
	(((value) & ((1 << SPI_##name##_SIZE) - 1)) << SPI_##name##_OFFSET)
#define SPI_BFEXT(name, value) \
	(((value) >> SPI_##name##_OFFSET) & ((1 << SPI_##name##_SIZE) - 1))
#define SPI_BFINS(name, value, old) \
	(((old) & ~(((1 << SPI_##name##_SIZE) - 1) << SPI_##name##_OFFSET)) \
	  | SPI_BF(name, value))

/* Register access macros */
#ifdef CONFIG_AVR32
#define spi_readl(port, reg) \
	__raw_readl((port)->regs + SPI_##reg)
#define spi_writel(port, reg, value) \
	__raw_writel((value), (port)->regs + SPI_##reg)

#define spi_readw(port, reg) \
	__raw_readw((port)->regs + SPI_##reg)
#define spi_writew(port, reg, value) \
	__raw_writew((value), (port)->regs + SPI_##reg)

#define spi_readb(port, reg) \
	__raw_readb((port)->regs + SPI_##reg)
#define spi_writeb(port, reg, value) \
	__raw_writeb((value), (port)->regs + SPI_##reg)
#else
#define spi_readl(port, reg) \
	readl_relaxed((port)->regs + SPI_##reg)
#define spi_writel(port, reg, value) \
	writel_relaxed((value), (port)->regs + SPI_##reg)

#define spi_readw(port, reg) \
	readw_relaxed((port)->regs + SPI_##reg)
#define spi_writew(port, reg, value) \
	writew_relaxed((value), (port)->regs + SPI_##reg)

#define spi_readb(port, reg) \
	readb_relaxed((port)->regs + SPI_##reg)
#define spi_writeb(port, reg, value) \
	writeb_relaxed((value), (port)->regs + SPI_##reg)
#endif
/* use PIO for small transfers, avoiding DMA setup/teardown overhead and
 * cache operations; better heuristics consider wordsize and bitrate.
 */
#define DMA_MIN_BYTES	16

#define SPI_DMA_TIMEOUT		(msecs_to_jiffies(1000))

#define AUTOSUSPEND_TIMEOUT	2000

struct atmel_spi_caps {
	bool	is_spi2;
	bool	has_wdrbt;
	bool	has_dma_support;
};

/*
 * The core SPI transfer engine just talks to a register bank to set up
 * DMA transfers; transfer queue progress is driven by IRQs.  The clock
 * framework provides the base clock, subdivided for each spi_device.
 */
struct atmel_spi {
	spinlock_t		lock;
	unsigned long		flags;

	phys_addr_t		phybase;
	void __iomem		*regs;
	int			irq;
	struct clk		*clk;
	struct platform_device	*pdev;
	unsigned long		spi_clk;

	struct spi_transfer	*current_transfer;
	int			current_remaining_bytes;
	int			done_status;

	struct completion	xfer_completion;

	struct atmel_spi_caps	caps;

	bool			use_dma;
	bool			use_pdc;
	bool			use_cs_gpios;

	bool			keep_cs;
	bool			cs_active;

	u32			fifo_size;
};

/* Controller-specific per-slave state */
struct atmel_spi_device {
	unsigned int		npcs_pin;
	u32			csr;
};

#define SPI_MAX_DMA_XFER	65535 /* true for both PDC and DMA */
#define INVALID_DMA_ADDRESS	0xffffffff

/*
 * Version 2 of the SPI controller has
 *  - CR.LASTXFER
 *  - SPI_MR.DIV32 may become FDIV or must-be-zero (here: always zero)
 *  - SPI_SR.TXEMPTY, SPI_SR.NSSR (and corresponding irqs)
 *  - SPI_CSRx.CSAAT
 *  - SPI_CSRx.SBCR allows faster clocking
 */
static bool atmel_spi_is_v2(struct atmel_spi *as)
{
	return as->caps.is_spi2;
}

/*
 * Earlier SPI controllers (e.g. on at91rm9200) have a design bug whereby
 * they assume that spi slave device state will not change on deselect, so
 * that automagic deselection is OK.  ("NPCSx rises if no data is to be
 * transmitted")  Not so!  Workaround uses nCSx pins as GPIOs; or newer
 * controllers have CSAAT and friends.
 *
 * Since the CSAAT functionality is a bit weird on newer controllers as
 * well, we use GPIO to control nCSx pins on all controllers, updating
 * MR.PCS to avoid confusing the controller.  Using GPIOs also lets us
 * support active-high chipselects despite the controller's belief that
 * only active-low devices/systems exists.
 *
 * However, at91rm9200 has a second erratum whereby nCS0 doesn't work
 * right when driven with GPIO.  ("Mode Fault does not allow more than one
 * Master on Chip Select 0.")  No workaround exists for that ... so for
 * nCS0 on that chip, we (a) don't use the GPIO, (b) can't support CS_HIGH,
 * and (c) will trigger that first erratum in some cases.
 */

static void cs_activate(struct atmel_spi *as, struct spi_device *spi)
{
	struct atmel_spi_device *asd = spi->controller_state;
	unsigned active = spi->mode & SPI_CS_HIGH;
	u32 mr;

	if (atmel_spi_is_v2(as)) {
		spi_writel(as, CSR0 + 4 * spi->chip_select, asd->csr);
		/* For the low SPI version, there is a issue that PDC transfer
		 * on CS1,2,3 needs SPI_CSR0.BITS config as SPI_CSR1,2,3.BITS
		 */
		spi_writel(as, CSR0, asd->csr);
		if (as->caps.has_wdrbt) {
			spi_writel(as, MR,
					SPI_BF(PCS, ~(0x01 << spi->chip_select))
					| SPI_BIT(WDRBT)
					| SPI_BIT(MODFDIS)
					| SPI_BIT(MSTR));
		} else {
			spi_writel(as, MR,
					SPI_BF(PCS, ~(0x01 << spi->chip_select))
					| SPI_BIT(MODFDIS)
					| SPI_BIT(MSTR));
		}

		mr = spi_readl(as, MR);
		if (as->use_cs_gpios)
			gpio_set_value(asd->npcs_pin, active);
	} else {
		u32 cpol = (spi->mode & SPI_CPOL) ? SPI_BIT(CPOL) : 0;
		int i;
		u32 csr;

		/* Make sure clock polarity is correct */
		for (i = 0; i < spi->master->num_chipselect; i++) {
			csr = spi_readl(as, CSR0 + 4 * i);
			if ((csr ^ cpol) & SPI_BIT(CPOL))
				spi_writel(as, CSR0 + 4 * i,
						csr ^ SPI_BIT(CPOL));
		}

		mr = spi_readl(as, MR);
		mr = SPI_BFINS(PCS, ~(1 << spi->chip_select), mr);
		if (as->use_cs_gpios && spi->chip_select != 0)
			gpio_set_value(asd->npcs_pin, active);
		spi_writel(as, MR, mr);
	}

	dev_dbg(&spi->dev, "activate %u%s, mr %08x\n",
			asd->npcs_pin, active ? " (high)" : "",
			mr);
}

static void cs_deactivate(struct atmel_spi *as, struct spi_device *spi)
{
	struct atmel_spi_device *asd = spi->controller_state;
	unsigned active = spi->mode & SPI_CS_HIGH;
	u32 mr;

	/* only deactivate *this* device; sometimes transfers to
	 * another device may be active when this routine is called.
	 */
	mr = spi_readl(as, MR);
	if (~SPI_BFEXT(PCS, mr) & (1 << spi->chip_select)) {
		mr = SPI_BFINS(PCS, 0xf, mr);
		spi_writel(as, MR, mr);
	}

	dev_dbg(&spi->dev, "DEactivate %u%s, mr %08x\n",
			asd->npcs_pin, active ? " (low)" : "",
			mr);

	if (!as->use_cs_gpios)
		spi_writel(as, CR, SPI_BIT(LASTXFER));
	else if (atmel_spi_is_v2(as) || spi->chip_select != 0)
		gpio_set_value(asd->npcs_pin, !active);
}

static void atmel_spi_lock(struct atmel_spi *as) __acquires(&as->lock)
{
	spin_lock_irqsave(&as->lock, as->flags);
}

static void atmel_spi_unlock(struct atmel_spi *as) __releases(&as->lock)
{
	spin_unlock_irqrestore(&as->lock, as->flags);
}

static inline bool atmel_spi_use_dma(struct atmel_spi *as,
				struct spi_transfer *xfer)
{
	return as->use_dma && xfer->len >= DMA_MIN_BYTES;
}

static bool atmel_spi_can_dma(struct spi_master *master,
			      struct spi_device *spi,
			      struct spi_transfer *xfer)
{
	struct atmel_spi *as = spi_master_get_devdata(master);

	return atmel_spi_use_dma(as, xfer);
}

static int atmel_spi_dma_slave_config(struct atmel_spi *as,
				struct dma_slave_config *slave_config,
				u8 bits_per_word)
{
	struct spi_master *master = platform_get_drvdata(as->pdev);
	int err = 0;

	if (bits_per_word > 8) {
		slave_config->dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
		slave_config->src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
	} else {
		slave_config->dst_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
		slave_config->src_addr_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
	}

	slave_config->dst_addr = (dma_addr_t)as->phybase + SPI_TDR;
	slave_config->src_addr = (dma_addr_t)as->phybase + SPI_RDR;
	slave_config->src_maxburst = 1;
	slave_config->dst_maxburst = 1;
	slave_config->device_fc = false;

	/*
	 * This driver uses fixed peripheral select mode (PS bit set to '0' in
	 * the Mode Register).
	 * So according to the datasheet, when FIFOs are available (and
	 * enabled), the Transmit FIFO operates in Multiple Data Mode.
	 * In this mode, up to 2 data, not 4, can be written into the Transmit
	 * Data Register in a single access.
	 * However, the first data has to be written into the lowest 16 bits and
	 * the second data into the highest 16 bits of the Transmit
	 * Data Register. For 8bit data (the most frequent case), it would
	 * require to rework tx_buf so each data would actualy fit 16 bits.
	 * So we'd rather write only one data at the time. Hence the transmit
	 * path works the same whether FIFOs are available (and enabled) or not.
	 */
	slave_config->direction = DMA_MEM_TO_DEV;
	if (dmaengine_slave_config(master->dma_tx, slave_config)) {
		dev_err(&as->pdev->dev,
			"failed to configure tx dma channel\n");
		err = -EINVAL;
	}

	/*
	 * This driver configures the spi controller for master mode (MSTR bit
	 * set to '1' in the Mode Register).
	 * So according to the datasheet, when FIFOs are available (and
	 * enabled), the Receive FIFO operates in Single Data Mode.
	 * So the receive path works the same whether FIFOs are available (and
	 * enabled) or not.
	 */
	slave_config->direction = DMA_DEV_TO_MEM;
	if (dmaengine_slave_config(master->dma_rx, slave_config)) {
		dev_err(&as->pdev->dev,
			"failed to configure rx dma channel\n");
		err = -EINVAL;
	}

	return err;
}

static int atmel_spi_configure_dma(struct spi_master *master,
				   struct atmel_spi *as)
{
	struct dma_slave_config	slave_config;
	struct device *dev = &as->pdev->dev;
	int err;

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

	master->dma_tx = dma_request_slave_channel_reason(dev, "tx");
	if (IS_ERR(master->dma_tx)) {
		err = PTR_ERR(master->dma_tx);
		if (err == -EPROBE_DEFER) {
			dev_warn(dev, "no DMA channel available at the moment\n");
			goto error_clear;
		}
		dev_err(dev,
			"DMA TX channel not available, SPI unable to use DMA\n");
		err = -EBUSY;
		goto error_clear;
	}

	/*
	 * No reason to check EPROBE_DEFER here since we have already requested
	 * tx channel. If it fails here, it's for another reason.
	 */
	master->dma_rx = dma_request_slave_channel(dev, "rx");

	if (!master->dma_rx) {
		dev_err(dev,
			"DMA RX channel not available, SPI unable to use DMA\n");
		err = -EBUSY;
		goto error;
	}

	err = atmel_spi_dma_slave_config(as, &slave_config, 8);
	if (err)
		goto error;

	dev_info(&as->pdev->dev,
			"Using %s (tx) and %s (rx) for DMA transfers\n",
			dma_chan_name(master->dma_tx),
			dma_chan_name(master->dma_rx));

	return 0;
error:
	if (master->dma_rx)
		dma_release_channel(master->dma_rx);
	if (!IS_ERR(master->dma_tx))
		dma_release_channel(master->dma_tx);
error_clear:
	master->dma_tx = master->dma_rx = NULL;
	return err;
}

static void atmel_spi_stop_dma(struct spi_master *master)
{
	if (master->dma_rx)
		dmaengine_terminate_all(master->dma_rx);
	if (master->dma_tx)
		dmaengine_terminate_all(master->dma_tx);
}

static void atmel_spi_release_dma(struct spi_master *master)
{
	if (master->dma_rx) {
		dma_release_channel(master->dma_rx);
		master->dma_rx = NULL;
	}
	if (master->dma_tx) {
		dma_release_channel(master->dma_tx);
		master->dma_tx = NULL;
	}
}

/* This function is called by the DMA driver from tasklet context */
static void dma_callback(void *data)
{
	struct spi_master	*master = data;
	struct atmel_spi	*as = spi_master_get_devdata(master);

	complete(&as->xfer_completion);
}

/*
 * Next transfer using PIO without FIFO.
 */
static void atmel_spi_next_xfer_single(struct spi_master *master,
				       struct spi_transfer *xfer)
{
	struct atmel_spi	*as = spi_master_get_devdata(master);
	unsigned long xfer_pos = xfer->len - as->current_remaining_bytes;

	dev_vdbg(master->dev.parent, "atmel_spi_next_xfer_pio\n");

	/* Make sure data is not remaining in RDR */
	spi_readl(as, RDR);
	while (spi_readl(as, SR) & SPI_BIT(RDRF)) {
		spi_readl(as, RDR);
		cpu_relax();
	}

	if (xfer->bits_per_word > 8)
		spi_writel(as, TDR, *(u16 *)(xfer->tx_buf + xfer_pos));
	else
		spi_writel(as, TDR, *(u8 *)(xfer->tx_buf + xfer_pos));

	dev_dbg(master->dev.parent,
		"  start pio xfer %p: len %u tx %p rx %p bitpw %d\n",
		xfer, xfer->len, xfer->tx_buf, xfer->rx_buf,
		xfer->bits_per_word);

	/* Enable relevant interrupts */
	spi_writel(as, IER, SPI_BIT(RDRF) | SPI_BIT(OVRES));
}

/*
 * Next transfer using PIO with FIFO.
 */
static void atmel_spi_next_xfer_fifo(struct spi_master *master,
				     struct spi_transfer *xfer)
{
	struct atmel_spi *as = spi_master_get_devdata(master);
	u32 current_remaining_data, num_data;
	u32 offset = xfer->len - as->current_remaining_bytes;
	const u16 *words = (const u16 *)((u8 *)xfer->tx_buf + offset);
	const u8  *bytes = (const u8  *)((u8 *)xfer->tx_buf + offset);
	u16 td0, td1;
	u32 fifomr;

	dev_vdbg(master->dev.parent, "atmel_spi_next_xfer_fifo\n");

	/* Compute the number of data to transfer in the current iteration */
	current_remaining_data = ((xfer->bits_per_word > 8) ?
				  ((u32)as->current_remaining_bytes >> 1) :
				  (u32)as->current_remaining_bytes);
	num_data = min(current_remaining_data, as->fifo_size);

	/* Flush RX and TX FIFOs */
	spi_writel(as, CR, SPI_BIT(RXFCLR) | SPI_BIT(TXFCLR));
	while (spi_readl(as, FLR))
		cpu_relax();

	/* Set RX FIFO Threshold to the number of data to transfer */
	fifomr = spi_readl(as, FMR);
	spi_writel(as, FMR, SPI_BFINS(RXFTHRES, num_data, fifomr));

	/* Clear FIFO flags in the Status Register, especially RXFTHF */
	(void)spi_readl(as, SR);

	/* Fill TX FIFO */
	while (num_data >= 2) {
		if (xfer->bits_per_word > 8) {
			td0 = *words++;
			td1 = *words++;
		} else {
			td0 = *bytes++;
			td1 = *bytes++;
		}

		spi_writel(as, TDR, (td1 << 16) | td0);
		num_data -= 2;
	}

	if (num_data) {
		if (xfer->bits_per_word > 8)
			td0 = *words++;
		else
			td0 = *bytes++;

		spi_writew(as, TDR, td0);
		num_data--;
	}

	dev_dbg(master->dev.parent,
		"  start fifo xfer %p: len %u tx %p rx %p bitpw %d\n",
		xfer, xfer->len, xfer->tx_buf, xfer->rx_buf,
		xfer->bits_per_word);

	/*
	 * Enable RX FIFO Threshold Flag interrupt to be notified about
	 * transfer completion.
	 */
	spi_writel(as, IER, SPI_BIT(RXFTHF) | SPI_BIT(OVRES));
}

/*
 * Next transfer using PIO.
 */
static void atmel_spi_next_xfer_pio(struct spi_master *master,
				    struct spi_transfer *xfer)
{
	struct atmel_spi *as = spi_master_get_devdata(master);

	if (as->fifo_size)
		atmel_spi_next_xfer_fifo(master, xfer);
	else
		atmel_spi_next_xfer_single(master, xfer);
}

/*
 * Submit next transfer for DMA.
 */
static int atmel_spi_next_xfer_dma_submit(struct spi_master *master,
				struct spi_transfer *xfer,
				u32 *plen)
{
	struct atmel_spi	*as = spi_master_get_devdata(master);
	struct dma_chan		*rxchan = master->dma_rx;
	struct dma_chan		*txchan = master->dma_tx;
	struct dma_async_tx_descriptor *rxdesc;
	struct dma_async_tx_descriptor *txdesc;
	struct dma_slave_config	slave_config;
	dma_cookie_t		cookie;

	dev_vdbg(master->dev.parent, "atmel_spi_next_xfer_dma_submit\n");

	/* Check that the channels are available */
	if (!rxchan || !txchan)
		return -ENODEV;

	/* release lock for DMA operations */
	atmel_spi_unlock(as);

	*plen = xfer->len;

	if (atmel_spi_dma_slave_config(as, &slave_config,
				       xfer->bits_per_word))
		goto err_exit;

	/* Send both scatterlists */
	rxdesc = dmaengine_prep_slave_sg(rxchan,
					 xfer->rx_sg.sgl, xfer->rx_sg.nents,
					 DMA_FROM_DEVICE,
					 DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
	if (!rxdesc)
		goto err_dma;

	txdesc = dmaengine_prep_slave_sg(txchan,
					 xfer->tx_sg.sgl, xfer->tx_sg.nents,
					 DMA_TO_DEVICE,
					 DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
	if (!txdesc)
		goto err_dma;

	dev_dbg(master->dev.parent,
		"  start dma xfer %p: len %u tx %p/%08llx rx %p/%08llx\n",
		xfer, xfer->len, xfer->tx_buf, (unsigned long long)xfer->tx_dma,
		xfer->rx_buf, (unsigned long long)xfer->rx_dma);

	/* Enable relevant interrupts */
	spi_writel(as, IER, SPI_BIT(OVRES));

	/* Put the callback on the RX transfer only, that should finish last */
	rxdesc->callback = dma_callback;
	rxdesc->callback_param = master;

	/* Submit and fire RX and TX with TX last so we're ready to read! */
	cookie = rxdesc->tx_submit(rxdesc);
	if (dma_submit_error(cookie))
		goto err_dma;
	cookie = txdesc->tx_submit(txdesc);
	if (dma_submit_error(cookie))
		goto err_dma;
	rxchan->device->device_issue_pending(rxchan);
	txchan->device->device_issue_pending(txchan);

	/* take back lock */
	atmel_spi_lock(as);
	return 0;

err_dma:
	spi_writel(as, IDR, SPI_BIT(OVRES));
	atmel_spi_stop_dma(master);
err_exit:
	atmel_spi_lock(as);
	return -ENOMEM;
}

static void atmel_spi_next_xfer_data(struct spi_master *master,
				struct spi_transfer *xfer,
				dma_addr_t *tx_dma,
				dma_addr_t *rx_dma,
				u32 *plen)
{
	*rx_dma = xfer->rx_dma + xfer->len - *plen;
	*tx_dma = xfer->tx_dma + xfer->len - *plen;
	if (*plen > master->max_dma_len)
		*plen = master->max_dma_len;
}

static int atmel_spi_set_xfer_speed(struct atmel_spi *as,
				    struct spi_device *spi,
				    struct spi_transfer *xfer)
{
	u32			scbr, csr;
	unsigned long		bus_hz;

	/* v1 chips start out at half the peripheral bus speed. */
	bus_hz = as->spi_clk;
	if (!atmel_spi_is_v2(as))
		bus_hz /= 2;

	/*
	 * Calculate the lowest divider that satisfies the
	 * constraint, assuming div32/fdiv/mbz == 0.
	 */
	scbr = DIV_ROUND_UP(bus_hz, xfer->speed_hz);

	/*
	 * If the resulting divider doesn't fit into the
	 * register bitfield, we can't satisfy the constraint.
	 */
	if (scbr >= (1 << SPI_SCBR_SIZE)) {
		dev_err(&spi->dev,
			"setup: %d Hz too slow, scbr %u; min %ld Hz\n",
			xfer->speed_hz, scbr, bus_hz/255);
		return -EINVAL;
	}
	if (scbr == 0) {
		dev_err(&spi->dev,
			"setup: %d Hz too high, scbr %u; max %ld Hz\n",
			xfer->speed_hz, scbr, bus_hz);
		return -EINVAL;
	}
	csr = spi_readl(as, CSR0 + 4 * spi->chip_select);
	csr = SPI_BFINS(SCBR, scbr, csr);
	spi_writel(as, CSR0 + 4 * spi->chip_select, csr);

	return 0;
}

/*
 * Submit next transfer for PDC.
 * lock is held, spi irq is blocked
 */
static void atmel_spi_pdc_next_xfer(struct spi_master *master,
					struct spi_message *msg,
					struct spi_transfer *xfer)
{
	struct atmel_spi	*as = spi_master_get_devdata(master);
	u32			len;
	dma_addr_t		tx_dma, rx_dma;

	spi_writel(as, PTCR, SPI_BIT(RXTDIS) | SPI_BIT(TXTDIS));

	len = as->current_remaining_bytes;
	atmel_spi_next_xfer_data(master, xfer, &tx_dma, &rx_dma, &len);
	as->current_remaining_bytes -= len;

	spi_writel(as, RPR, rx_dma);
	spi_writel(as, TPR, tx_dma);

	if (msg->spi->bits_per_word > 8)
		len >>= 1;
	spi_writel(as, RCR, len);
	spi_writel(as, TCR, len);

	dev_dbg(&msg->spi->dev,
		"  start xfer %p: len %u tx %p/%08llx rx %p/%08llx\n",
		xfer, xfer->len, xfer->tx_buf,
		(unsigned long long)xfer->tx_dma, xfer->rx_buf,
		(unsigned long long)xfer->rx_dma);

	if (as->current_remaining_bytes) {
		len = as->current_remaining_bytes;
		atmel_spi_next_xfer_data(master, xfer, &tx_dma, &rx_dma, &len);
		as->current_remaining_bytes -= len;

		spi_writel(as, RNPR, rx_dma);
		spi_writel(as, TNPR, tx_dma);

		if (msg->spi->bits_per_word > 8)
			len >>= 1;
		spi_writel(as, RNCR, len);
		spi_writel(as, TNCR, len);

		dev_dbg(&msg->spi->dev,
			"  next xfer %p: len %u tx %p/%08llx rx %p/%08llx\n",
			xfer, xfer->len, xfer->tx_buf,
			(unsigned long long)xfer->tx_dma, xfer->rx_buf,
			(unsigned long long)xfer->rx_dma);
	}

	/* REVISIT: We're waiting for RXBUFF before we start the next
	 * transfer because we need to handle some difficult timing
	 * issues otherwise. If we wait for TXBUFE in one transfer and
	 * then starts waiting for RXBUFF in the next, it's difficult
	 * to tell the difference between the RXBUFF interrupt we're
	 * actually waiting for and the RXBUFF interrupt of the
	 * previous transfer.
	 *
	 * It should be doable, though. Just not now...
	 */
	spi_writel(as, IER, SPI_BIT(RXBUFF) | SPI_BIT(OVRES));
	spi_writel(as, PTCR, SPI_BIT(TXTEN) | SPI_BIT(RXTEN));
}

/*
 * For DMA, tx_buf/tx_dma have the same relationship as rx_buf/rx_dma:
 *  - The buffer is either valid for CPU access, else NULL
 *  - If the buffer is valid, so is its DMA address
 *
 * This driver manages the dma address unless message->is_dma_mapped.
 */
static int
atmel_spi_dma_map_xfer(struct atmel_spi *as, struct spi_transfer *xfer)
{
	struct device	*dev = &as->pdev->dev;

	xfer->tx_dma = xfer->rx_dma = INVALID_DMA_ADDRESS;
	if (xfer->tx_buf) {
		/* tx_buf is a const void* where we need a void * for the dma
		 * mapping */
		void *nonconst_tx = (void *)xfer->tx_buf;

		xfer->tx_dma = dma_map_single(dev,
				nonconst_tx, xfer->len,
				DMA_TO_DEVICE);
		if (dma_mapping_error(dev, xfer->tx_dma))
			return -ENOMEM;
	}
	if (xfer->rx_buf) {
		xfer->rx_dma = dma_map_single(dev,
				xfer->rx_buf, xfer->len,
				DMA_FROM_DEVICE);
		if (dma_mapping_error(dev, xfer->rx_dma)) {
			if (xfer->tx_buf)
				dma_unmap_single(dev,
						xfer->tx_dma, xfer->len,
						DMA_TO_DEVICE);
			return -ENOMEM;
		}
	}
	return 0;
}

static void atmel_spi_dma_unmap_xfer(struct spi_master *master,
				     struct spi_transfer *xfer)
{
	if (xfer->tx_dma != INVALID_DMA_ADDRESS)
		dma_unmap_single(master->dev.parent, xfer->tx_dma,
				 xfer->len, DMA_TO_DEVICE);
	if (xfer->rx_dma != INVALID_DMA_ADDRESS)
		dma_unmap_single(master->dev.parent, xfer->rx_dma,
				 xfer->len, DMA_FROM_DEVICE);
}

static void atmel_spi_disable_pdc_transfer(struct atmel_spi *as)
{
	spi_writel(as, PTCR, SPI_BIT(RXTDIS) | SPI_BIT(TXTDIS));
}

static void
atmel_spi_pump_single_data(struct atmel_spi *as, struct spi_transfer *xfer)
{
	u8		*rxp;
	u16		*rxp16;
	unsigned long	xfer_pos = xfer->len - as->current_remaining_bytes;

	if (xfer->bits_per_word > 8) {
		rxp16 = (u16 *)(((u8 *)xfer->rx_buf) + xfer_pos);
		*rxp16 = spi_readl(as, RDR);
	} else {
		rxp = ((u8 *)xfer->rx_buf) + xfer_pos;
		*rxp = spi_readl(as, RDR);
	}
	if (xfer->bits_per_word > 8) {
		if (as->current_remaining_bytes > 2)
			as->current_remaining_bytes -= 2;
		else
			as->current_remaining_bytes = 0;
	} else {
		as->current_remaining_bytes--;
	}
}

static void
atmel_spi_pump_fifo_data(struct atmel_spi *as, struct spi_transfer *xfer)
{
	u32 fifolr = spi_readl(as, FLR);
	u32 num_bytes, num_data = SPI_BFEXT(RXFL, fifolr);
	u32 offset = xfer->len - as->current_remaining_bytes;
	u16 *words = (u16 *)((u8 *)xfer->rx_buf + offset);
	u8  *bytes = (u8  *)((u8 *)xfer->rx_buf + offset);
	u16 rd; /* RD field is the lowest 16 bits of RDR */

	/* Update the number of remaining bytes to transfer */
	num_bytes = ((xfer->bits_per_word > 8) ?
		     (num_data << 1) :
		     num_data);

	if (as->current_remaining_bytes > num_bytes)
		as->current_remaining_bytes -= num_bytes;
	else
		as->current_remaining_bytes = 0;

	/* Handle odd number of bytes when data are more than 8bit width */
	if (xfer->bits_per_word > 8)
		as->current_remaining_bytes &= ~0x1;

	/* Read data */
	while (num_data) {
		rd = spi_readl(as, RDR);
		if (xfer->bits_per_word > 8)
			*words++ = rd;
		else
			*bytes++ = rd;
		num_data--;
	}
}

/* Called from IRQ
 *
 * Must update "current_remaining_bytes" to keep track of data
 * to transfer.
 */
static void
atmel_spi_pump_pio_data(struct atmel_spi *as, struct spi_transfer *xfer)
{
	if (as->fifo_size)
		atmel_spi_pump_fifo_data(as, xfer);
	else
		atmel_spi_pump_single_data(as, xfer);
}

/* Interrupt
 *
 * No need for locking in this Interrupt handler: done_status is the
 * only information modified.
 */
static irqreturn_t
atmel_spi_pio_interrupt(int irq, void *dev_id)
{
	struct spi_master	*master = dev_id;
	struct atmel_spi	*as = spi_master_get_devdata(master);
	u32			status, pending, imr;
	struct spi_transfer	*xfer;
	int			ret = IRQ_NONE;

	imr = spi_readl(as, IMR);
	status = spi_readl(as, SR);
	pending = status & imr;

	if (pending & SPI_BIT(OVRES)) {
		ret = IRQ_HANDLED;
		spi_writel(as, IDR, SPI_BIT(OVRES));
		dev_warn(master->dev.parent, "overrun\n");

		/*
		 * When we get an overrun, we disregard the current
		 * transfer. Data will not be copied back from any
		 * bounce buffer and msg->actual_len will not be
		 * updated with the last xfer.
		 *
		 * We will also not process any remaning transfers in
		 * the message.
		 */
		as->done_status = -EIO;
		smp_wmb();

		/* Clear any overrun happening while cleaning up */
		spi_readl(as, SR);

		complete(&as->xfer_completion);

	} else if (pending & (SPI_BIT(RDRF) | SPI_BIT(RXFTHF))) {
		atmel_spi_lock(as);

		if (as->current_remaining_bytes) {
			ret = IRQ_HANDLED;
			xfer = as->current_transfer;
			atmel_spi_pump_pio_data(as, xfer);
			if (!as->current_remaining_bytes)
				spi_writel(as, IDR, pending);

			complete(&as->xfer_completion);
		}

		atmel_spi_unlock(as);
	} else {
		WARN_ONCE(pending, "IRQ not handled, pending = %x\n", pending);
		ret = IRQ_HANDLED;
		spi_writel(as, IDR, pending);
	}

	return ret;
}

static irqreturn_t
atmel_spi_pdc_interrupt(int irq, void *dev_id)
{
	struct spi_master	*master = dev_id;
	struct atmel_spi	*as = spi_master_get_devdata(master);
	u32			status, pending, imr;
	int			ret = IRQ_NONE;

	imr = spi_readl(as, IMR);
	status = spi_readl(as, SR);
	pending = status & imr;

	if (pending & SPI_BIT(OVRES)) {

		ret = IRQ_HANDLED;

		spi_writel(as, IDR, (SPI_BIT(RXBUFF) | SPI_BIT(ENDRX)
				     | SPI_BIT(OVRES)));

		/* Clear any overrun happening while cleaning up */
		spi_readl(as, SR);

		as->done_status = -EIO;

		complete(&as->xfer_completion);

	} else if (pending & (SPI_BIT(RXBUFF) | SPI_BIT(ENDRX))) {
		ret = IRQ_HANDLED;

		spi_writel(as, IDR, pending);

		complete(&as->xfer_completion);
	}

	return ret;
}

static int atmel_spi_setup(struct spi_device *spi)
{
	struct atmel_spi	*as;
	struct atmel_spi_device	*asd;
	u32			csr;
	unsigned int		bits = spi->bits_per_word;
	unsigned int		npcs_pin;

	as = spi_master_get_devdata(spi->master);

	/* see notes above re chipselect */
	if (!atmel_spi_is_v2(as)
			&& spi->chip_select == 0
			&& (spi->mode & SPI_CS_HIGH)) {
		dev_dbg(&spi->dev, "setup: can't be active-high\n");
		return -EINVAL;
	}

	csr = SPI_BF(BITS, bits - 8);
	if (spi->mode & SPI_CPOL)
		csr |= SPI_BIT(CPOL);
	if (!(spi->mode & SPI_CPHA))
		csr |= SPI_BIT(NCPHA);
	if (!as->use_cs_gpios)
		csr |= SPI_BIT(CSAAT);

	/* DLYBS is mostly irrelevant since we manage chipselect using GPIOs.
	 *
	 * DLYBCT would add delays between words, slowing down transfers.
	 * It could potentially be useful to cope with DMA bottlenecks, but
	 * in those cases it's probably best to just use a lower bitrate.
	 */
	csr |= SPI_BF(DLYBS, 0);
	csr |= SPI_BF(DLYBCT, 0);

	/* chipselect must have been muxed as GPIO (e.g. in board setup) */
	npcs_pin = (unsigned long)spi->controller_data;

	if (!as->use_cs_gpios)
		npcs_pin = spi->chip_select;
	else if (gpio_is_valid(spi->cs_gpio))
		npcs_pin = spi->cs_gpio;

	asd = spi->controller_state;
	if (!asd) {
		asd = kzalloc(sizeof(struct atmel_spi_device), GFP_KERNEL);
		if (!asd)
			return -ENOMEM;

		if (as->use_cs_gpios)
			gpio_direction_output(npcs_pin,
					      !(spi->mode & SPI_CS_HIGH));

		asd->npcs_pin = npcs_pin;
		spi->controller_state = asd;
	}

	asd->csr = csr;

	dev_dbg(&spi->dev,
		"setup: bpw %u mode 0x%x -> csr%d %08x\n",
		bits, spi->mode, spi->chip_select, csr);

	if (!atmel_spi_is_v2(as))
		spi_writel(as, CSR0 + 4 * spi->chip_select, csr);

	return 0;
}

static int atmel_spi_one_transfer(struct spi_master *master,
					struct spi_message *msg,
					struct spi_transfer *xfer)
{
	struct atmel_spi	*as;
	struct spi_device	*spi = msg->spi;
	u8			bits;
	u32			len;
	struct atmel_spi_device	*asd;
	int			timeout;
	int			ret;
	unsigned long		dma_timeout;

	as = spi_master_get_devdata(master);

	if (!(xfer->tx_buf || xfer->rx_buf) && xfer->len) {
		dev_dbg(&spi->dev, "missing rx or tx buf\n");
		return -EINVAL;
	}

	asd = spi->controller_state;
	bits = (asd->csr >> 4) & 0xf;
	if (bits != xfer->bits_per_word - 8) {
		dev_dbg(&spi->dev,
			"you can't yet change bits_per_word in transfers\n");
		return -ENOPROTOOPT;
	}

	/*
	 * DMA map early, for performance (empties dcache ASAP) and
	 * better fault reporting.
	 */
	if ((!msg->is_dma_mapped)
		&& as->use_pdc) {
		if (atmel_spi_dma_map_xfer(as, xfer) < 0)
			return -ENOMEM;
	}

	atmel_spi_set_xfer_speed(as, msg->spi, xfer);

	as->done_status = 0;
	as->current_transfer = xfer;
	as->current_remaining_bytes = xfer->len;
	while (as->current_remaining_bytes) {
		reinit_completion(&as->xfer_completion);

		if (as->use_pdc) {
			atmel_spi_pdc_next_xfer(master, msg, xfer);
		} else if (atmel_spi_use_dma(as, xfer)) {
			len = as->current_remaining_bytes;
			ret = atmel_spi_next_xfer_dma_submit(master,
								xfer, &len);
			if (ret) {
				dev_err(&spi->dev,
					"unable to use DMA, fallback to PIO\n");
				atmel_spi_next_xfer_pio(master, xfer);
			} else {
				as->current_remaining_bytes -= len;
				if (as->current_remaining_bytes < 0)
					as->current_remaining_bytes = 0;
			}
		} else {
			atmel_spi_next_xfer_pio(master, xfer);
		}

		/* interrupts are disabled, so free the lock for schedule */
		atmel_spi_unlock(as);
		dma_timeout = wait_for_completion_timeout(&as->xfer_completion,
							  SPI_DMA_TIMEOUT);
		atmel_spi_lock(as);
		if (WARN_ON(dma_timeout == 0)) {
			dev_err(&spi->dev, "spi transfer timeout\n");
			as->done_status = -EIO;
		}

		if (as->done_status)
			break;
	}

	if (as->done_status) {
		if (as->use_pdc) {
			dev_warn(master->dev.parent,
				"overrun (%u/%u remaining)\n",
				spi_readl(as, TCR), spi_readl(as, RCR));

			/*
			 * Clean up DMA registers and make sure the data
			 * registers are empty.
			 */
			spi_writel(as, RNCR, 0);
			spi_writel(as, TNCR, 0);
			spi_writel(as, RCR, 0);
			spi_writel(as, TCR, 0);
			for (timeout = 1000; timeout; timeout--)
				if (spi_readl(as, SR) & SPI_BIT(TXEMPTY))
					break;
			if (!timeout)
				dev_warn(master->dev.parent,
					 "timeout waiting for TXEMPTY");
			while (spi_readl(as, SR) & SPI_BIT(RDRF))
				spi_readl(as, RDR);

			/* Clear any overrun happening while cleaning up */
			spi_readl(as, SR);

		} else if (atmel_spi_use_dma(as, xfer)) {
			atmel_spi_stop_dma(master);
		}

		if (!msg->is_dma_mapped
			&& as->use_pdc)
			atmel_spi_dma_unmap_xfer(master, xfer);

		return 0;

	} else {
		/* only update length if no error */
		msg->actual_length += xfer->len;
	}

	if (!msg->is_dma_mapped
		&& as->use_pdc)
		atmel_spi_dma_unmap_xfer(master, xfer);

	if (xfer->delay_usecs)
		udelay(xfer->delay_usecs);

	if (xfer->cs_change) {
		if (list_is_last(&xfer->transfer_list,
				 &msg->transfers)) {
			as->keep_cs = true;
		} else {
			as->cs_active = !as->cs_active;
			if (as->cs_active)
				cs_activate(as, msg->spi);
			else
				cs_deactivate(as, msg->spi);
		}
	}

	return 0;
}

static int atmel_spi_transfer_one_message(struct spi_master *master,
						struct spi_message *msg)
{
	struct atmel_spi *as;
	struct spi_transfer *xfer;
	struct spi_device *spi = msg->spi;
	int ret = 0;

	as = spi_master_get_devdata(master);

	dev_dbg(&spi->dev, "new message %p submitted for %s\n",
					msg, dev_name(&spi->dev));

	atmel_spi_lock(as);
	cs_activate(as, spi);

	as->cs_active = true;
	as->keep_cs = false;

	msg->status = 0;
	msg->actual_length = 0;

	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
		ret = atmel_spi_one_transfer(master, msg, xfer);
		if (ret)
			goto msg_done;
	}

	if (as->use_pdc)
		atmel_spi_disable_pdc_transfer(as);

	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
		dev_dbg(&spi->dev,
			"  xfer %p: len %u tx %p/%pad rx %p/%pad\n",
			xfer, xfer->len,
			xfer->tx_buf, &xfer->tx_dma,
			xfer->rx_buf, &xfer->rx_dma);
	}

msg_done:
	if (!as->keep_cs)
		cs_deactivate(as, msg->spi);

	atmel_spi_unlock(as);

	msg->status = as->done_status;
	spi_finalize_current_message(spi->master);

	return ret;
}

static void atmel_spi_cleanup(struct spi_device *spi)
{
	struct atmel_spi_device	*asd = spi->controller_state;

	if (!asd)
		return;

	spi->controller_state = NULL;
	kfree(asd);
}

static inline unsigned int atmel_get_version(struct atmel_spi *as)
{
	return spi_readl(as, VERSION) & 0x00000fff;
}

static void atmel_get_caps(struct atmel_spi *as)
{
	unsigned int version;

	version = atmel_get_version(as);
	dev_info(&as->pdev->dev, "version: 0x%x\n", version);

	as->caps.is_spi2 = version > 0x121;
	as->caps.has_wdrbt = version >= 0x210;
	as->caps.has_dma_support = version >= 0x212;
}

/*-------------------------------------------------------------------------*/
static int atmel_spi_gpio_cs(struct platform_device *pdev)
{
	struct spi_master	*master = platform_get_drvdata(pdev);
	struct atmel_spi	*as = spi_master_get_devdata(master);
	struct device_node	*np = master->dev.of_node;
	int			i;
	int			ret = 0;
	int			nb = 0;

	if (!as->use_cs_gpios)
		return 0;

	if (!np)
		return 0;

	nb = of_gpio_named_count(np, "cs-gpios");
	for (i = 0; i < nb; i++) {
		int cs_gpio = of_get_named_gpio(pdev->dev.of_node,
						"cs-gpios", i);

		if (cs_gpio == -EPROBE_DEFER)
			return cs_gpio;

		if (gpio_is_valid(cs_gpio)) {
			ret = devm_gpio_request(&pdev->dev, cs_gpio,
						dev_name(&pdev->dev));
			if (ret)
				return ret;
		}
	}

	return 0;
}

static void atmel_spi_init(struct atmel_spi *as)
{
	spi_writel(as, CR, SPI_BIT(SWRST));
	spi_writel(as, CR, SPI_BIT(SWRST)); /* AT91SAM9263 Rev B workaround */
	if (as->caps.has_wdrbt) {
		spi_writel(as, MR, SPI_BIT(WDRBT) | SPI_BIT(MODFDIS)
				| SPI_BIT(MSTR));
	} else {
		spi_writel(as, MR, SPI_BIT(MSTR) | SPI_BIT(MODFDIS));
	}

	if (as->use_pdc)
		spi_writel(as, PTCR, SPI_BIT(RXTDIS) | SPI_BIT(TXTDIS));
	spi_writel(as, CR, SPI_BIT(SPIEN));

	if (as->fifo_size)
		spi_writel(as, CR, SPI_BIT(FIFOEN));
}

static int atmel_spi_probe(struct platform_device *pdev)
{
	struct resource		*regs;
	int			irq;
	struct clk		*clk;
	int			ret;
	struct spi_master	*master;
	struct atmel_spi	*as;

	/* Select default pin state */
	pinctrl_pm_select_default_state(&pdev->dev);

	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (!regs)
		return -ENXIO;

	irq = platform_get_irq(pdev, 0);
	if (irq < 0)
		return irq;

	clk = devm_clk_get(&pdev->dev, "spi_clk");
	if (IS_ERR(clk))
		return PTR_ERR(clk);

	/* setup spi core then atmel-specific driver state */
	ret = -ENOMEM;
	master = spi_alloc_master(&pdev->dev, sizeof(*as));
	if (!master)
		goto out_free;

	/* the spi->mode bits understood by this driver: */
	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(8, 16);
	master->dev.of_node = pdev->dev.of_node;
	master->bus_num = pdev->id;
	master->num_chipselect = master->dev.of_node ? 0 : 4;
	master->setup = atmel_spi_setup;
	master->flags = (SPI_MASTER_MUST_RX | SPI_MASTER_MUST_TX);
	master->transfer_one_message = atmel_spi_transfer_one_message;
	master->cleanup = atmel_spi_cleanup;
	master->auto_runtime_pm = true;
	master->max_dma_len = SPI_MAX_DMA_XFER;
	master->can_dma = atmel_spi_can_dma;
	platform_set_drvdata(pdev, master);

	as = spi_master_get_devdata(master);

	spin_lock_init(&as->lock);

	as->pdev = pdev;
	as->regs = devm_ioremap_resource(&pdev->dev, regs);
	if (IS_ERR(as->regs)) {
		ret = PTR_ERR(as->regs);
		goto out_unmap_regs;
	}
	as->phybase = regs->start;
	as->irq = irq;
	as->clk = clk;

	init_completion(&as->xfer_completion);

	atmel_get_caps(as);

	as->use_cs_gpios = true;
	if (atmel_spi_is_v2(as) &&
	    pdev->dev.of_node &&
	    !of_get_property(pdev->dev.of_node, "cs-gpios", NULL)) {
		as->use_cs_gpios = false;
		master->num_chipselect = 4;
	}

	ret = atmel_spi_gpio_cs(pdev);
	if (ret)
		goto out_unmap_regs;

	as->use_dma = false;
	as->use_pdc = false;
	if (as->caps.has_dma_support) {
		ret = atmel_spi_configure_dma(master, as);
		if (ret == 0) {
			as->use_dma = true;
		} else if (ret == -EPROBE_DEFER) {
			return ret;
		}
	} else {
		as->use_pdc = true;
	}

	if (as->caps.has_dma_support && !as->use_dma)
		dev_info(&pdev->dev, "Atmel SPI Controller using PIO only\n");

	if (as->use_pdc) {
		ret = devm_request_irq(&pdev->dev, irq, atmel_spi_pdc_interrupt,
					0, dev_name(&pdev->dev), master);
	} else {
		ret = devm_request_irq(&pdev->dev, irq, atmel_spi_pio_interrupt,
					0, dev_name(&pdev->dev), master);
	}
	if (ret)
		goto out_unmap_regs;

	/* Initialize the hardware */
	ret = clk_prepare_enable(clk);
	if (ret)
		goto out_free_irq;

	as->spi_clk = clk_get_rate(clk);

	as->fifo_size = 0;
	if (!of_property_read_u32(pdev->dev.of_node, "atmel,fifo-size",
				  &as->fifo_size)) {
		dev_info(&pdev->dev, "Using FIFO (%u data)\n", as->fifo_size);
	}

	atmel_spi_init(as);

	pm_runtime_set_autosuspend_delay(&pdev->dev, AUTOSUSPEND_TIMEOUT);
	pm_runtime_use_autosuspend(&pdev->dev);
	pm_runtime_set_active(&pdev->dev);
	pm_runtime_enable(&pdev->dev);

	ret = devm_spi_register_master(&pdev->dev, master);
	if (ret)
		goto out_free_dma;

	/* go! */
	dev_info(&pdev->dev, "Atmel SPI Controller at 0x%08lx (irq %d)\n",
			(unsigned long)regs->start, irq);

	return 0;

out_free_dma:
	pm_runtime_disable(&pdev->dev);
	pm_runtime_set_suspended(&pdev->dev);

	if (as->use_dma)
		atmel_spi_release_dma(master);

	spi_writel(as, CR, SPI_BIT(SWRST));
	spi_writel(as, CR, SPI_BIT(SWRST)); /* AT91SAM9263 Rev B workaround */
	clk_disable_unprepare(clk);
out_free_irq:
out_unmap_regs:
out_free:
	spi_master_put(master);
	return ret;
}

static int atmel_spi_remove(struct platform_device *pdev)
{
	struct spi_master	*master = platform_get_drvdata(pdev);
	struct atmel_spi	*as = spi_master_get_devdata(master);

	pm_runtime_get_sync(&pdev->dev);

	/* reset the hardware and block queue progress */
	spin_lock_irq(&as->lock);
	if (as->use_dma) {
		atmel_spi_stop_dma(master);
		atmel_spi_release_dma(master);
	}

	spi_writel(as, CR, SPI_BIT(SWRST));
	spi_writel(as, CR, SPI_BIT(SWRST)); /* AT91SAM9263 Rev B workaround */
	spi_readl(as, SR);
	spin_unlock_irq(&as->lock);

	clk_disable_unprepare(as->clk);

	pm_runtime_put_noidle(&pdev->dev);
	pm_runtime_disable(&pdev->dev);

	return 0;
}

#ifdef CONFIG_PM
static int atmel_spi_runtime_suspend(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);
	struct atmel_spi *as = spi_master_get_devdata(master);

	clk_disable_unprepare(as->clk);
	pinctrl_pm_select_sleep_state(dev);

	return 0;
}

static int atmel_spi_runtime_resume(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);
	struct atmel_spi *as = spi_master_get_devdata(master);

	pinctrl_pm_select_default_state(dev);

	return clk_prepare_enable(as->clk);
}

#ifdef CONFIG_PM_SLEEP
static int atmel_spi_suspend(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);
	int ret;

	/* Stop the queue running */
	ret = spi_master_suspend(master);
	if (ret) {
		dev_warn(dev, "cannot suspend master\n");
		return ret;
	}

	if (!pm_runtime_suspended(dev))
		atmel_spi_runtime_suspend(dev);

	return 0;
}

static int atmel_spi_resume(struct device *dev)
{
	struct spi_master *master = dev_get_drvdata(dev);
	struct atmel_spi *as = spi_master_get_devdata(master);
	int ret;

	ret = clk_prepare_enable(as->clk);
	if (ret)
		return ret;

	atmel_spi_init(as);

	clk_disable_unprepare(as->clk);

	if (!pm_runtime_suspended(dev)) {
		ret = atmel_spi_runtime_resume(dev);
		if (ret)
			return ret;
	}

	/* Start the queue running */
	ret = spi_master_resume(master);
	if (ret)
		dev_err(dev, "problem starting queue (%d)\n", ret);

	return ret;
}
#endif

static const struct dev_pm_ops atmel_spi_pm_ops = {
	SET_SYSTEM_SLEEP_PM_OPS(atmel_spi_suspend, atmel_spi_resume)
	SET_RUNTIME_PM_OPS(atmel_spi_runtime_suspend,
			   atmel_spi_runtime_resume, NULL)
};
#define ATMEL_SPI_PM_OPS	(&atmel_spi_pm_ops)
#else
#define ATMEL_SPI_PM_OPS	NULL
#endif

#if defined(CONFIG_OF)
static const struct of_device_id atmel_spi_dt_ids[] = {
	{ .compatible = "atmel,at91rm9200-spi" },
	{ /* sentinel */ }
};

MODULE_DEVICE_TABLE(of, atmel_spi_dt_ids);
#endif

static struct platform_driver atmel_spi_driver = {
	.driver		= {
		.name	= "atmel_spi",
		.pm	= ATMEL_SPI_PM_OPS,
		.of_match_table	= of_match_ptr(atmel_spi_dt_ids),
	},
	.probe		= atmel_spi_probe,
	.remove		= atmel_spi_remove,
};
module_platform_driver(atmel_spi_driver);

MODULE_DESCRIPTION("Atmel AT32/AT91 SPI Controller driver");
MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
MODULE_LICENSE("GPL");
MODULE_ALIAS("platform:atmel_spi");