summaryrefslogtreecommitdiff
path: root/drivers/mmc/host/mmci.c
blob: 771c60ab4a320a3edc222b108c49d14a8e0076b1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
/*
 *  linux/drivers/mmc/host/mmci.c - ARM PrimeCell MMCI PL180/1 driver
 *
 *  Copyright (C) 2003 Deep Blue Solutions, Ltd, All Rights Reserved.
 *  Copyright (C) 2010 ST-Ericsson SA
 *
 * 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/module.h>
#include <linux/moduleparam.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/err.h>
#include <linux/highmem.h>
#include <linux/log2.h>
#include <linux/mmc/pm.h>
#include <linux/mmc/host.h>
#include <linux/mmc/card.h>
#include <linux/amba/bus.h>
#include <linux/clk.h>
#include <linux/scatterlist.h>
#include <linux/gpio.h>
#include <linux/of_gpio.h>
#include <linux/regulator/consumer.h>
#include <linux/dmaengine.h>
#include <linux/dma-mapping.h>
#include <linux/amba/mmci.h>
#include <linux/pm_runtime.h>
#include <linux/types.h>
#include <linux/pinctrl/consumer.h>

#include <asm/div64.h>
#include <asm/io.h>
#include <asm/sizes.h>

#include "mmci.h"

#define DRIVER_NAME "mmci-pl18x"

static unsigned int fmax = 515633;

/**
 * struct variant_data - MMCI variant-specific quirks
 * @clkreg: default value for MCICLOCK register
 * @clkreg_enable: enable value for MMCICLOCK register
 * @datalength_bits: number of bits in the MMCIDATALENGTH register
 * @fifosize: number of bytes that can be written when MMCI_TXFIFOEMPTY
 *	      is asserted (likewise for RX)
 * @fifohalfsize: number of bytes that can be written when MCI_TXFIFOHALFEMPTY
 *		  is asserted (likewise for RX)
 * @sdio: variant supports SDIO
 * @st_clkdiv: true if using a ST-specific clock divider algorithm
 * @blksz_datactrl16: true if Block size is at b16..b30 position in datactrl register
 * @pwrreg_powerup: power up value for MMCIPOWER register
 * @signal_direction: input/out direction of bus signals can be indicated
 * @pwrreg_clkgate: MMCIPOWER register must be used to gate the clock
 * @busy_detect: true if busy detection on dat0 is supported
 * @pwrreg_nopower: bits in MMCIPOWER don't controls ext. power supply
 */
struct variant_data {
	unsigned int		clkreg;
	unsigned int		clkreg_enable;
	unsigned int		datalength_bits;
	unsigned int		fifosize;
	unsigned int		fifohalfsize;
	bool			sdio;
	bool			st_clkdiv;
	bool			blksz_datactrl16;
	u32			pwrreg_powerup;
	bool			signal_direction;
	bool			pwrreg_clkgate;
	bool			busy_detect;
	bool			pwrreg_nopower;
};

static struct variant_data variant_arm = {
	.fifosize		= 16 * 4,
	.fifohalfsize		= 8 * 4,
	.datalength_bits	= 16,
	.pwrreg_powerup		= MCI_PWR_UP,
};

static struct variant_data variant_arm_extended_fifo = {
	.fifosize		= 128 * 4,
	.fifohalfsize		= 64 * 4,
	.datalength_bits	= 16,
	.pwrreg_powerup		= MCI_PWR_UP,
};

static struct variant_data variant_arm_extended_fifo_hwfc = {
	.fifosize		= 128 * 4,
	.fifohalfsize		= 64 * 4,
	.clkreg_enable		= MCI_ARM_HWFCEN,
	.datalength_bits	= 16,
	.pwrreg_powerup		= MCI_PWR_UP,
};

static struct variant_data variant_u300 = {
	.fifosize		= 16 * 4,
	.fifohalfsize		= 8 * 4,
	.clkreg_enable		= MCI_ST_U300_HWFCEN,
	.datalength_bits	= 16,
	.sdio			= true,
	.pwrreg_powerup		= MCI_PWR_ON,
	.signal_direction	= true,
	.pwrreg_clkgate		= true,
	.pwrreg_nopower		= true,
};

static struct variant_data variant_nomadik = {
	.fifosize		= 16 * 4,
	.fifohalfsize		= 8 * 4,
	.clkreg			= MCI_CLK_ENABLE,
	.datalength_bits	= 24,
	.sdio			= true,
	.st_clkdiv		= true,
	.pwrreg_powerup		= MCI_PWR_ON,
	.signal_direction	= true,
	.pwrreg_clkgate		= true,
	.pwrreg_nopower		= true,
};

static struct variant_data variant_ux500 = {
	.fifosize		= 30 * 4,
	.fifohalfsize		= 8 * 4,
	.clkreg			= MCI_CLK_ENABLE,
	.clkreg_enable		= MCI_ST_UX500_HWFCEN,
	.datalength_bits	= 24,
	.sdio			= true,
	.st_clkdiv		= true,
	.pwrreg_powerup		= MCI_PWR_ON,
	.signal_direction	= true,
	.pwrreg_clkgate		= true,
	.busy_detect		= true,
	.pwrreg_nopower		= true,
};

static struct variant_data variant_ux500v2 = {
	.fifosize		= 30 * 4,
	.fifohalfsize		= 8 * 4,
	.clkreg			= MCI_CLK_ENABLE,
	.clkreg_enable		= MCI_ST_UX500_HWFCEN,
	.datalength_bits	= 24,
	.sdio			= true,
	.st_clkdiv		= true,
	.blksz_datactrl16	= true,
	.pwrreg_powerup		= MCI_PWR_ON,
	.signal_direction	= true,
	.pwrreg_clkgate		= true,
	.busy_detect		= true,
	.pwrreg_nopower		= true,
};

static int mmci_card_busy(struct mmc_host *mmc)
{
	struct mmci_host *host = mmc_priv(mmc);
	unsigned long flags;
	int busy = 0;

	pm_runtime_get_sync(mmc_dev(mmc));

	spin_lock_irqsave(&host->lock, flags);
	if (readl(host->base + MMCISTATUS) & MCI_ST_CARDBUSY)
		busy = 1;
	spin_unlock_irqrestore(&host->lock, flags);

	pm_runtime_mark_last_busy(mmc_dev(mmc));
	pm_runtime_put_autosuspend(mmc_dev(mmc));

	return busy;
}

/*
 * Validate mmc prerequisites
 */
static int mmci_validate_data(struct mmci_host *host,
			      struct mmc_data *data)
{
	if (!data)
		return 0;

	if (!is_power_of_2(data->blksz)) {
		dev_err(mmc_dev(host->mmc),
			"unsupported block size (%d bytes)\n", data->blksz);
		return -EINVAL;
	}

	return 0;
}

static void mmci_reg_delay(struct mmci_host *host)
{
	/*
	 * According to the spec, at least three feedback clock cycles
	 * of max 52 MHz must pass between two writes to the MMCICLOCK reg.
	 * Three MCLK clock cycles must pass between two MMCIPOWER reg writes.
	 * Worst delay time during card init is at 100 kHz => 30 us.
	 * Worst delay time when up and running is at 25 MHz => 120 ns.
	 */
	if (host->cclk < 25000000)
		udelay(30);
	else
		ndelay(120);
}

/*
 * This must be called with host->lock held
 */
static void mmci_write_clkreg(struct mmci_host *host, u32 clk)
{
	if (host->clk_reg != clk) {
		host->clk_reg = clk;
		writel(clk, host->base + MMCICLOCK);
	}
}

/*
 * This must be called with host->lock held
 */
static void mmci_write_pwrreg(struct mmci_host *host, u32 pwr)
{
	if (host->pwr_reg != pwr) {
		host->pwr_reg = pwr;
		writel(pwr, host->base + MMCIPOWER);
	}
}

/*
 * This must be called with host->lock held
 */
static void mmci_write_datactrlreg(struct mmci_host *host, u32 datactrl)
{
	/* Keep ST Micro busy mode if enabled */
	datactrl |= host->datactrl_reg & MCI_ST_DPSM_BUSYMODE;

	if (host->datactrl_reg != datactrl) {
		host->datactrl_reg = datactrl;
		writel(datactrl, host->base + MMCIDATACTRL);
	}
}

/*
 * This must be called with host->lock held
 */
static void mmci_set_clkreg(struct mmci_host *host, unsigned int desired)
{
	struct variant_data *variant = host->variant;
	u32 clk = variant->clkreg;

	/* Make sure cclk reflects the current calculated clock */
	host->cclk = 0;

	if (desired) {
		if (desired >= host->mclk) {
			clk = MCI_CLK_BYPASS;
			if (variant->st_clkdiv)
				clk |= MCI_ST_UX500_NEG_EDGE;
			host->cclk = host->mclk;
		} else if (variant->st_clkdiv) {
			/*
			 * DB8500 TRM says f = mclk / (clkdiv + 2)
			 * => clkdiv = (mclk / f) - 2
			 * Round the divider up so we don't exceed the max
			 * frequency
			 */
			clk = DIV_ROUND_UP(host->mclk, desired) - 2;
			if (clk >= 256)
				clk = 255;
			host->cclk = host->mclk / (clk + 2);
		} else {
			/*
			 * PL180 TRM says f = mclk / (2 * (clkdiv + 1))
			 * => clkdiv = mclk / (2 * f) - 1
			 */
			clk = host->mclk / (2 * desired) - 1;
			if (clk >= 256)
				clk = 255;
			host->cclk = host->mclk / (2 * (clk + 1));
		}

		clk |= variant->clkreg_enable;
		clk |= MCI_CLK_ENABLE;
		/* This hasn't proven to be worthwhile */
		/* clk |= MCI_CLK_PWRSAVE; */
	}

	/* Set actual clock for debug */
	host->mmc->actual_clock = host->cclk;

	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_4)
		clk |= MCI_4BIT_BUS;
	if (host->mmc->ios.bus_width == MMC_BUS_WIDTH_8)
		clk |= MCI_ST_8BIT_BUS;

	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50)
		clk |= MCI_ST_UX500_NEG_EDGE;

	mmci_write_clkreg(host, clk);
}

static void
mmci_request_end(struct mmci_host *host, struct mmc_request *mrq)
{
	writel(0, host->base + MMCICOMMAND);

	BUG_ON(host->data);

	host->mrq = NULL;
	host->cmd = NULL;

	mmc_request_done(host->mmc, mrq);

	pm_runtime_mark_last_busy(mmc_dev(host->mmc));
	pm_runtime_put_autosuspend(mmc_dev(host->mmc));
}

static void mmci_set_mask1(struct mmci_host *host, unsigned int mask)
{
	void __iomem *base = host->base;

	if (host->singleirq) {
		unsigned int mask0 = readl(base + MMCIMASK0);

		mask0 &= ~MCI_IRQ1MASK;
		mask0 |= mask;

		writel(mask0, base + MMCIMASK0);
	}

	writel(mask, base + MMCIMASK1);
}

static void mmci_stop_data(struct mmci_host *host)
{
	mmci_write_datactrlreg(host, 0);
	mmci_set_mask1(host, 0);
	host->data = NULL;
}

static void mmci_init_sg(struct mmci_host *host, struct mmc_data *data)
{
	unsigned int flags = SG_MITER_ATOMIC;

	if (data->flags & MMC_DATA_READ)
		flags |= SG_MITER_TO_SG;
	else
		flags |= SG_MITER_FROM_SG;

	sg_miter_start(&host->sg_miter, data->sg, data->sg_len, flags);
}

/*
 * All the DMA operation mode stuff goes inside this ifdef.
 * This assumes that you have a generic DMA device interface,
 * no custom DMA interfaces are supported.
 */
#ifdef CONFIG_DMA_ENGINE
static void mmci_dma_setup(struct mmci_host *host)
{
	struct mmci_platform_data *plat = host->plat;
	const char *rxname, *txname;
	dma_cap_mask_t mask;

	host->dma_rx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "rx");
	host->dma_tx_channel = dma_request_slave_channel(mmc_dev(host->mmc), "tx");

	/* initialize pre request cookie */
	host->next_data.cookie = 1;

	/* Try to acquire a generic DMA engine slave channel */
	dma_cap_zero(mask);
	dma_cap_set(DMA_SLAVE, mask);

	if (plat && plat->dma_filter) {
		if (!host->dma_rx_channel && plat->dma_rx_param) {
			host->dma_rx_channel = dma_request_channel(mask,
							   plat->dma_filter,
							   plat->dma_rx_param);
			/* E.g if no DMA hardware is present */
			if (!host->dma_rx_channel)
				dev_err(mmc_dev(host->mmc), "no RX DMA channel\n");
		}

		if (!host->dma_tx_channel && plat->dma_tx_param) {
			host->dma_tx_channel = dma_request_channel(mask,
							   plat->dma_filter,
							   plat->dma_tx_param);
			if (!host->dma_tx_channel)
				dev_warn(mmc_dev(host->mmc), "no TX DMA channel\n");
		}
	}

	/*
	 * If only an RX channel is specified, the driver will
	 * attempt to use it bidirectionally, however if it is
	 * is specified but cannot be located, DMA will be disabled.
	 */
	if (host->dma_rx_channel && !host->dma_tx_channel)
		host->dma_tx_channel = host->dma_rx_channel;

	if (host->dma_rx_channel)
		rxname = dma_chan_name(host->dma_rx_channel);
	else
		rxname = "none";

	if (host->dma_tx_channel)
		txname = dma_chan_name(host->dma_tx_channel);
	else
		txname = "none";

	dev_info(mmc_dev(host->mmc), "DMA channels RX %s, TX %s\n",
		 rxname, txname);

	/*
	 * Limit the maximum segment size in any SG entry according to
	 * the parameters of the DMA engine device.
	 */
	if (host->dma_tx_channel) {
		struct device *dev = host->dma_tx_channel->device->dev;
		unsigned int max_seg_size = dma_get_max_seg_size(dev);

		if (max_seg_size < host->mmc->max_seg_size)
			host->mmc->max_seg_size = max_seg_size;
	}
	if (host->dma_rx_channel) {
		struct device *dev = host->dma_rx_channel->device->dev;
		unsigned int max_seg_size = dma_get_max_seg_size(dev);

		if (max_seg_size < host->mmc->max_seg_size)
			host->mmc->max_seg_size = max_seg_size;
	}
}

/*
 * This is used in or so inline it
 * so it can be discarded.
 */
static inline void mmci_dma_release(struct mmci_host *host)
{
	struct mmci_platform_data *plat = host->plat;

	if (host->dma_rx_channel)
		dma_release_channel(host->dma_rx_channel);
	if (host->dma_tx_channel && plat->dma_tx_param)
		dma_release_channel(host->dma_tx_channel);
	host->dma_rx_channel = host->dma_tx_channel = NULL;
}

static void mmci_dma_data_error(struct mmci_host *host)
{
	dev_err(mmc_dev(host->mmc), "error during DMA transfer!\n");
	dmaengine_terminate_all(host->dma_current);
	host->dma_current = NULL;
	host->dma_desc_current = NULL;
	host->data->host_cookie = 0;
}

static void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
{
	struct dma_chan *chan;
	enum dma_data_direction dir;

	if (data->flags & MMC_DATA_READ) {
		dir = DMA_FROM_DEVICE;
		chan = host->dma_rx_channel;
	} else {
		dir = DMA_TO_DEVICE;
		chan = host->dma_tx_channel;
	}

	dma_unmap_sg(chan->device->dev, data->sg, data->sg_len, dir);
}

static void mmci_dma_finalize(struct mmci_host *host, struct mmc_data *data)
{
	u32 status;
	int i;

	/* Wait up to 1ms for the DMA to complete */
	for (i = 0; ; i++) {
		status = readl(host->base + MMCISTATUS);
		if (!(status & MCI_RXDATAAVLBLMASK) || i >= 100)
			break;
		udelay(10);
	}

	/*
	 * Check to see whether we still have some data left in the FIFO -
	 * this catches DMA controllers which are unable to monitor the
	 * DMALBREQ and DMALSREQ signals while allowing us to DMA to non-
	 * contiguous buffers.  On TX, we'll get a FIFO underrun error.
	 */
	if (status & MCI_RXDATAAVLBLMASK) {
		mmci_dma_data_error(host);
		if (!data->error)
			data->error = -EIO;
	}

	if (!data->host_cookie)
		mmci_dma_unmap(host, data);

	/*
	 * Use of DMA with scatter-gather is impossible.
	 * Give up with DMA and switch back to PIO mode.
	 */
	if (status & MCI_RXDATAAVLBLMASK) {
		dev_err(mmc_dev(host->mmc), "buggy DMA detected. Taking evasive action.\n");
		mmci_dma_release(host);
	}

	host->dma_current = NULL;
	host->dma_desc_current = NULL;
}

/* prepares DMA channel and DMA descriptor, returns non-zero on failure */
static int __mmci_dma_prep_data(struct mmci_host *host, struct mmc_data *data,
				struct dma_chan **dma_chan,
				struct dma_async_tx_descriptor **dma_desc)
{
	struct variant_data *variant = host->variant;
	struct dma_slave_config conf = {
		.src_addr = host->phybase + MMCIFIFO,
		.dst_addr = host->phybase + MMCIFIFO,
		.src_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
		.dst_addr_width = DMA_SLAVE_BUSWIDTH_4_BYTES,
		.src_maxburst = variant->fifohalfsize >> 2, /* # of words */
		.dst_maxburst = variant->fifohalfsize >> 2, /* # of words */
		.device_fc = false,
	};
	struct dma_chan *chan;
	struct dma_device *device;
	struct dma_async_tx_descriptor *desc;
	enum dma_data_direction buffer_dirn;
	int nr_sg;

	if (data->flags & MMC_DATA_READ) {
		conf.direction = DMA_DEV_TO_MEM;
		buffer_dirn = DMA_FROM_DEVICE;
		chan = host->dma_rx_channel;
	} else {
		conf.direction = DMA_MEM_TO_DEV;
		buffer_dirn = DMA_TO_DEVICE;
		chan = host->dma_tx_channel;
	}

	/* If there's no DMA channel, fall back to PIO */
	if (!chan)
		return -EINVAL;

	/* If less than or equal to the fifo size, don't bother with DMA */
	if (data->blksz * data->blocks <= variant->fifosize)
		return -EINVAL;

	device = chan->device;
	nr_sg = dma_map_sg(device->dev, data->sg, data->sg_len, buffer_dirn);
	if (nr_sg == 0)
		return -EINVAL;

	dmaengine_slave_config(chan, &conf);
	desc = dmaengine_prep_slave_sg(chan, data->sg, nr_sg,
					    conf.direction, DMA_CTRL_ACK);
	if (!desc)
		goto unmap_exit;

	*dma_chan = chan;
	*dma_desc = desc;

	return 0;

 unmap_exit:
	dma_unmap_sg(device->dev, data->sg, data->sg_len, buffer_dirn);
	return -ENOMEM;
}

static inline int mmci_dma_prep_data(struct mmci_host *host,
				     struct mmc_data *data)
{
	/* Check if next job is already prepared. */
	if (host->dma_current && host->dma_desc_current)
		return 0;

	/* No job were prepared thus do it now. */
	return __mmci_dma_prep_data(host, data, &host->dma_current,
				    &host->dma_desc_current);
}

static inline int mmci_dma_prep_next(struct mmci_host *host,
				     struct mmc_data *data)
{
	struct mmci_host_next *nd = &host->next_data;
	return __mmci_dma_prep_data(host, data, &nd->dma_chan, &nd->dma_desc);
}

static int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
{
	int ret;
	struct mmc_data *data = host->data;

	ret = mmci_dma_prep_data(host, host->data);
	if (ret)
		return ret;

	/* Okay, go for it. */
	dev_vdbg(mmc_dev(host->mmc),
		 "Submit MMCI DMA job, sglen %d blksz %04x blks %04x flags %08x\n",
		 data->sg_len, data->blksz, data->blocks, data->flags);
	dmaengine_submit(host->dma_desc_current);
	dma_async_issue_pending(host->dma_current);

	datactrl |= MCI_DPSM_DMAENABLE;

	/* Trigger the DMA transfer */
	mmci_write_datactrlreg(host, datactrl);

	/*
	 * Let the MMCI say when the data is ended and it's time
	 * to fire next DMA request. When that happens, MMCI will
	 * call mmci_data_end()
	 */
	writel(readl(host->base + MMCIMASK0) | MCI_DATAENDMASK,
	       host->base + MMCIMASK0);
	return 0;
}

static void mmci_get_next_data(struct mmci_host *host, struct mmc_data *data)
{
	struct mmci_host_next *next = &host->next_data;

	WARN_ON(data->host_cookie && data->host_cookie != next->cookie);
	WARN_ON(!data->host_cookie && (next->dma_desc || next->dma_chan));

	host->dma_desc_current = next->dma_desc;
	host->dma_current = next->dma_chan;
	next->dma_desc = NULL;
	next->dma_chan = NULL;
}

static void mmci_pre_request(struct mmc_host *mmc, struct mmc_request *mrq,
			     bool is_first_req)
{
	struct mmci_host *host = mmc_priv(mmc);
	struct mmc_data *data = mrq->data;
	struct mmci_host_next *nd = &host->next_data;

	if (!data)
		return;

	BUG_ON(data->host_cookie);

	if (mmci_validate_data(host, data))
		return;

	if (!mmci_dma_prep_next(host, data))
		data->host_cookie = ++nd->cookie < 0 ? 1 : nd->cookie;
}

static void mmci_post_request(struct mmc_host *mmc, struct mmc_request *mrq,
			      int err)
{
	struct mmci_host *host = mmc_priv(mmc);
	struct mmc_data *data = mrq->data;

	if (!data || !data->host_cookie)
		return;

	mmci_dma_unmap(host, data);

	if (err) {
		struct mmci_host_next *next = &host->next_data;
		struct dma_chan *chan;
		if (data->flags & MMC_DATA_READ)
			chan = host->dma_rx_channel;
		else
			chan = host->dma_tx_channel;
		dmaengine_terminate_all(chan);

		next->dma_desc = NULL;
		next->dma_chan = NULL;
	}
}

#else
/* Blank functions if the DMA engine is not available */
static void mmci_get_next_data(struct mmci_host *host, struct mmc_data *data)
{
}
static inline void mmci_dma_setup(struct mmci_host *host)
{
}

static inline void mmci_dma_release(struct mmci_host *host)
{
}

static inline void mmci_dma_unmap(struct mmci_host *host, struct mmc_data *data)
{
}

static inline void mmci_dma_finalize(struct mmci_host *host,
				     struct mmc_data *data)
{
}

static inline void mmci_dma_data_error(struct mmci_host *host)
{
}

static inline int mmci_dma_start_data(struct mmci_host *host, unsigned int datactrl)
{
	return -ENOSYS;
}

#define mmci_pre_request NULL
#define mmci_post_request NULL

#endif

static void mmci_start_data(struct mmci_host *host, struct mmc_data *data)
{
	struct variant_data *variant = host->variant;
	unsigned int datactrl, timeout, irqmask;
	unsigned long long clks;
	void __iomem *base;
	int blksz_bits;

	dev_dbg(mmc_dev(host->mmc), "blksz %04x blks %04x flags %08x\n",
		data->blksz, data->blocks, data->flags);

	host->data = data;
	host->size = data->blksz * data->blocks;
	data->bytes_xfered = 0;

	clks = (unsigned long long)data->timeout_ns * host->cclk;
	do_div(clks, 1000000000UL);

	timeout = data->timeout_clks + (unsigned int)clks;

	base = host->base;
	writel(timeout, base + MMCIDATATIMER);
	writel(host->size, base + MMCIDATALENGTH);

	blksz_bits = ffs(data->blksz) - 1;
	BUG_ON(1 << blksz_bits != data->blksz);

	if (variant->blksz_datactrl16)
		datactrl = MCI_DPSM_ENABLE | (data->blksz << 16);
	else
		datactrl = MCI_DPSM_ENABLE | blksz_bits << 4;

	if (data->flags & MMC_DATA_READ)
		datactrl |= MCI_DPSM_DIRECTION;

	/* The ST Micro variants has a special bit to enable SDIO */
	if (variant->sdio && host->mmc->card)
		if (mmc_card_sdio(host->mmc->card)) {
			/*
			 * The ST Micro variants has a special bit
			 * to enable SDIO.
			 */
			u32 clk;

			datactrl |= MCI_ST_DPSM_SDIOEN;

			/*
			 * The ST Micro variant for SDIO small write transfers
			 * needs to have clock H/W flow control disabled,
			 * otherwise the transfer will not start. The threshold
			 * depends on the rate of MCLK.
			 */
			if (data->flags & MMC_DATA_WRITE &&
			    (host->size < 8 ||
			     (host->size <= 8 && host->mclk > 50000000)))
				clk = host->clk_reg & ~variant->clkreg_enable;
			else
				clk = host->clk_reg | variant->clkreg_enable;

			mmci_write_clkreg(host, clk);
		}

	if (host->mmc->ios.timing == MMC_TIMING_UHS_DDR50)
		datactrl |= MCI_ST_DPSM_DDRMODE;

	/*
	 * Attempt to use DMA operation mode, if this
	 * should fail, fall back to PIO mode
	 */
	if (!mmci_dma_start_data(host, datactrl))
		return;

	/* IRQ mode, map the SG list for CPU reading/writing */
	mmci_init_sg(host, data);

	if (data->flags & MMC_DATA_READ) {
		irqmask = MCI_RXFIFOHALFFULLMASK;

		/*
		 * If we have less than the fifo 'half-full' threshold to
		 * transfer, trigger a PIO interrupt as soon as any data
		 * is available.
		 */
		if (host->size < variant->fifohalfsize)
			irqmask |= MCI_RXDATAAVLBLMASK;
	} else {
		/*
		 * We don't actually need to include "FIFO empty" here
		 * since its implicit in "FIFO half empty".
		 */
		irqmask = MCI_TXFIFOHALFEMPTYMASK;
	}

	mmci_write_datactrlreg(host, datactrl);
	writel(readl(base + MMCIMASK0) & ~MCI_DATAENDMASK, base + MMCIMASK0);
	mmci_set_mask1(host, irqmask);
}

static void
mmci_start_command(struct mmci_host *host, struct mmc_command *cmd, u32 c)
{
	void __iomem *base = host->base;

	dev_dbg(mmc_dev(host->mmc), "op %02x arg %08x flags %08x\n",
	    cmd->opcode, cmd->arg, cmd->flags);

	if (readl(base + MMCICOMMAND) & MCI_CPSM_ENABLE) {
		writel(0, base + MMCICOMMAND);
		udelay(1);
	}

	c |= cmd->opcode | MCI_CPSM_ENABLE;
	if (cmd->flags & MMC_RSP_PRESENT) {
		if (cmd->flags & MMC_RSP_136)
			c |= MCI_CPSM_LONGRSP;
		c |= MCI_CPSM_RESPONSE;
	}
	if (/*interrupt*/0)
		c |= MCI_CPSM_INTERRUPT;

	host->cmd = cmd;

	writel(cmd->arg, base + MMCIARGUMENT);
	writel(c, base + MMCICOMMAND);
}

static void
mmci_data_irq(struct mmci_host *host, struct mmc_data *data,
	      unsigned int status)
{
	/* First check for errors */
	if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR|
		      MCI_TXUNDERRUN|MCI_RXOVERRUN)) {
		u32 remain, success;

		/* Terminate the DMA transfer */
		if (dma_inprogress(host)) {
			mmci_dma_data_error(host);
			mmci_dma_unmap(host, data);
		}

		/*
		 * Calculate how far we are into the transfer.  Note that
		 * the data counter gives the number of bytes transferred
		 * on the MMC bus, not on the host side.  On reads, this
		 * can be as much as a FIFO-worth of data ahead.  This
		 * matters for FIFO overruns only.
		 */
		remain = readl(host->base + MMCIDATACNT);
		success = data->blksz * data->blocks - remain;

		dev_dbg(mmc_dev(host->mmc), "MCI ERROR IRQ, status 0x%08x at 0x%08x\n",
			status, success);
		if (status & MCI_DATACRCFAIL) {
			/* Last block was not successful */
			success -= 1;
			data->error = -EILSEQ;
		} else if (status & MCI_DATATIMEOUT) {
			data->error = -ETIMEDOUT;
		} else if (status & MCI_STARTBITERR) {
			data->error = -ECOMM;
		} else if (status & MCI_TXUNDERRUN) {
			data->error = -EIO;
		} else if (status & MCI_RXOVERRUN) {
			if (success > host->variant->fifosize)
				success -= host->variant->fifosize;
			else
				success = 0;
			data->error = -EIO;
		}
		data->bytes_xfered = round_down(success, data->blksz);
	}

	if (status & MCI_DATABLOCKEND)
		dev_err(mmc_dev(host->mmc), "stray MCI_DATABLOCKEND interrupt\n");

	if (status & MCI_DATAEND || data->error) {
		if (dma_inprogress(host))
			mmci_dma_finalize(host, data);
		mmci_stop_data(host);

		if (!data->error)
			/* The error clause is handled above, success! */
			data->bytes_xfered = data->blksz * data->blocks;

		if (!data->stop || host->mrq->sbc) {
			mmci_request_end(host, data->mrq);
		} else {
			mmci_start_command(host, data->stop, 0);
		}
	}
}

static void
mmci_cmd_irq(struct mmci_host *host, struct mmc_command *cmd,
	     unsigned int status)
{
	void __iomem *base = host->base;
	bool sbc = (cmd == host->mrq->sbc);
	bool busy_resp = host->variant->busy_detect &&
			(cmd->flags & MMC_RSP_BUSY);

	/* Check if we need to wait for busy completion. */
	if (host->busy_status && (status & MCI_ST_CARDBUSY))
		return;

	/* Enable busy completion if needed and supported. */
	if (!host->busy_status && busy_resp &&
		!(status & (MCI_CMDCRCFAIL|MCI_CMDTIMEOUT)) &&
		(readl(base + MMCISTATUS) & MCI_ST_CARDBUSY)) {
		writel(readl(base + MMCIMASK0) | MCI_ST_BUSYEND,
			base + MMCIMASK0);
		host->busy_status = status & (MCI_CMDSENT|MCI_CMDRESPEND);
		return;
	}

	/* At busy completion, mask the IRQ and complete the request. */
	if (host->busy_status) {
		writel(readl(base + MMCIMASK0) & ~MCI_ST_BUSYEND,
			base + MMCIMASK0);
		host->busy_status = 0;
	}

	host->cmd = NULL;

	if (status & MCI_CMDTIMEOUT) {
		cmd->error = -ETIMEDOUT;
	} else if (status & MCI_CMDCRCFAIL && cmd->flags & MMC_RSP_CRC) {
		cmd->error = -EILSEQ;
	} else {
		cmd->resp[0] = readl(base + MMCIRESPONSE0);
		cmd->resp[1] = readl(base + MMCIRESPONSE1);
		cmd->resp[2] = readl(base + MMCIRESPONSE2);
		cmd->resp[3] = readl(base + MMCIRESPONSE3);
	}

	if ((!sbc && !cmd->data) || cmd->error) {
		if (host->data) {
			/* Terminate the DMA transfer */
			if (dma_inprogress(host)) {
				mmci_dma_data_error(host);
				mmci_dma_unmap(host, host->data);
			}
			mmci_stop_data(host);
		}
		mmci_request_end(host, host->mrq);
	} else if (sbc) {
		mmci_start_command(host, host->mrq->cmd, 0);
	} else if (!(cmd->data->flags & MMC_DATA_READ)) {
		mmci_start_data(host, cmd->data);
	}
}

static int mmci_pio_read(struct mmci_host *host, char *buffer, unsigned int remain)
{
	void __iomem *base = host->base;
	char *ptr = buffer;
	u32 status;
	int host_remain = host->size;

	do {
		int count = host_remain - (readl(base + MMCIFIFOCNT) << 2);

		if (count > remain)
			count = remain;

		if (count <= 0)
			break;

		/*
		 * SDIO especially may want to send something that is
		 * not divisible by 4 (as opposed to card sectors
		 * etc). Therefore make sure to always read the last bytes
		 * while only doing full 32-bit reads towards the FIFO.
		 */
		if (unlikely(count & 0x3)) {
			if (count < 4) {
				unsigned char buf[4];
				ioread32_rep(base + MMCIFIFO, buf, 1);
				memcpy(ptr, buf, count);
			} else {
				ioread32_rep(base + MMCIFIFO, ptr, count >> 2);
				count &= ~0x3;
			}
		} else {
			ioread32_rep(base + MMCIFIFO, ptr, count >> 2);
		}

		ptr += count;
		remain -= count;
		host_remain -= count;

		if (remain == 0)
			break;

		status = readl(base + MMCISTATUS);
	} while (status & MCI_RXDATAAVLBL);

	return ptr - buffer;
}

static int mmci_pio_write(struct mmci_host *host, char *buffer, unsigned int remain, u32 status)
{
	struct variant_data *variant = host->variant;
	void __iomem *base = host->base;
	char *ptr = buffer;

	do {
		unsigned int count, maxcnt;

		maxcnt = status & MCI_TXFIFOEMPTY ?
			 variant->fifosize : variant->fifohalfsize;
		count = min(remain, maxcnt);

		/*
		 * SDIO especially may want to send something that is
		 * not divisible by 4 (as opposed to card sectors
		 * etc), and the FIFO only accept full 32-bit writes.
		 * So compensate by adding +3 on the count, a single
		 * byte become a 32bit write, 7 bytes will be two
		 * 32bit writes etc.
		 */
		iowrite32_rep(base + MMCIFIFO, ptr, (count + 3) >> 2);

		ptr += count;
		remain -= count;

		if (remain == 0)
			break;

		status = readl(base + MMCISTATUS);
	} while (status & MCI_TXFIFOHALFEMPTY);

	return ptr - buffer;
}

/*
 * PIO data transfer IRQ handler.
 */
static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
{
	struct mmci_host *host = dev_id;
	struct sg_mapping_iter *sg_miter = &host->sg_miter;
	struct variant_data *variant = host->variant;
	void __iomem *base = host->base;
	unsigned long flags;
	u32 status;

	status = readl(base + MMCISTATUS);

	dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status);

	local_irq_save(flags);

	do {
		unsigned int remain, len;
		char *buffer;

		/*
		 * For write, we only need to test the half-empty flag
		 * here - if the FIFO is completely empty, then by
		 * definition it is more than half empty.
		 *
		 * For read, check for data available.
		 */
		if (!(status & (MCI_TXFIFOHALFEMPTY|MCI_RXDATAAVLBL)))
			break;

		if (!sg_miter_next(sg_miter))
			break;

		buffer = sg_miter->addr;
		remain = sg_miter->length;

		len = 0;
		if (status & MCI_RXACTIVE)
			len = mmci_pio_read(host, buffer, remain);
		if (status & MCI_TXACTIVE)
			len = mmci_pio_write(host, buffer, remain, status);

		sg_miter->consumed = len;

		host->size -= len;
		remain -= len;

		if (remain)
			break;

		status = readl(base + MMCISTATUS);
	} while (1);

	sg_miter_stop(sg_miter);

	local_irq_restore(flags);

	/*
	 * If we have less than the fifo 'half-full' threshold to transfer,
	 * trigger a PIO interrupt as soon as any data is available.
	 */
	if (status & MCI_RXACTIVE && host->size < variant->fifohalfsize)
		mmci_set_mask1(host, MCI_RXDATAAVLBLMASK);

	/*
	 * If we run out of data, disable the data IRQs; this
	 * prevents a race where the FIFO becomes empty before
	 * the chip itself has disabled the data path, and
	 * stops us racing with our data end IRQ.
	 */
	if (host->size == 0) {
		mmci_set_mask1(host, 0);
		writel(readl(base + MMCIMASK0) | MCI_DATAENDMASK, base + MMCIMASK0);
	}

	return IRQ_HANDLED;
}

/*
 * Handle completion of command and data transfers.
 */
static irqreturn_t mmci_irq(int irq, void *dev_id)
{
	struct mmci_host *host = dev_id;
	u32 status;
	int ret = 0;

	spin_lock(&host->lock);

	do {
		struct mmc_command *cmd;
		struct mmc_data *data;

		status = readl(host->base + MMCISTATUS);

		if (host->singleirq) {
			if (status & readl(host->base + MMCIMASK1))
				mmci_pio_irq(irq, dev_id);

			status &= ~MCI_IRQ1MASK;
		}

		/*
		 * We intentionally clear the MCI_ST_CARDBUSY IRQ here (if it's
		 * enabled) since the HW seems to be triggering the IRQ on both
		 * edges while monitoring DAT0 for busy completion.
		 */
		status &= readl(host->base + MMCIMASK0);
		writel(status, host->base + MMCICLEAR);

		dev_dbg(mmc_dev(host->mmc), "irq0 (data+cmd) %08x\n", status);

		cmd = host->cmd;
		if ((status|host->busy_status) & (MCI_CMDCRCFAIL|MCI_CMDTIMEOUT|
			MCI_CMDSENT|MCI_CMDRESPEND) && cmd)
			mmci_cmd_irq(host, cmd, status);

		data = host->data;
		if (status & (MCI_DATACRCFAIL|MCI_DATATIMEOUT|MCI_STARTBITERR|
			      MCI_TXUNDERRUN|MCI_RXOVERRUN|MCI_DATAEND|
			      MCI_DATABLOCKEND) && data)
			mmci_data_irq(host, data, status);

		/* Don't poll for busy completion in irq context. */
		if (host->busy_status)
			status &= ~MCI_ST_CARDBUSY;

		ret = 1;
	} while (status);

	spin_unlock(&host->lock);

	return IRQ_RETVAL(ret);
}

static void mmci_request(struct mmc_host *mmc, struct mmc_request *mrq)
{
	struct mmci_host *host = mmc_priv(mmc);
	unsigned long flags;

	WARN_ON(host->mrq != NULL);

	mrq->cmd->error = mmci_validate_data(host, mrq->data);
	if (mrq->cmd->error) {
		mmc_request_done(mmc, mrq);
		return;
	}

	pm_runtime_get_sync(mmc_dev(mmc));

	spin_lock_irqsave(&host->lock, flags);

	host->mrq = mrq;

	if (mrq->data)
		mmci_get_next_data(host, mrq->data);

	if (mrq->data && mrq->data->flags & MMC_DATA_READ)
		mmci_start_data(host, mrq->data);

	if (mrq->sbc)
		mmci_start_command(host, mrq->sbc, 0);
	else
		mmci_start_command(host, mrq->cmd, 0);

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

static void mmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
{
	struct mmci_host *host = mmc_priv(mmc);
	struct variant_data *variant = host->variant;
	u32 pwr = 0;
	unsigned long flags;
	int ret;

	pm_runtime_get_sync(mmc_dev(mmc));

	if (host->plat->ios_handler &&
		host->plat->ios_handler(mmc_dev(mmc), ios))
			dev_err(mmc_dev(mmc), "platform ios_handler failed\n");

	switch (ios->power_mode) {
	case MMC_POWER_OFF:
		if (!IS_ERR(mmc->supply.vmmc))
			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, 0);

		if (!IS_ERR(mmc->supply.vqmmc) && host->vqmmc_enabled) {
			regulator_disable(mmc->supply.vqmmc);
			host->vqmmc_enabled = false;
		}

		break;
	case MMC_POWER_UP:
		if (!IS_ERR(mmc->supply.vmmc))
			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);

		/*
		 * The ST Micro variant doesn't have the PL180s MCI_PWR_UP
		 * and instead uses MCI_PWR_ON so apply whatever value is
		 * configured in the variant data.
		 */
		pwr |= variant->pwrreg_powerup;

		break;
	case MMC_POWER_ON:
		if (!IS_ERR(mmc->supply.vqmmc) && !host->vqmmc_enabled) {
			ret = regulator_enable(mmc->supply.vqmmc);
			if (ret < 0)
				dev_err(mmc_dev(mmc),
					"failed to enable vqmmc regulator\n");
			else
				host->vqmmc_enabled = true;
		}

		pwr |= MCI_PWR_ON;
		break;
	}

	if (variant->signal_direction && ios->power_mode != MMC_POWER_OFF) {
		/*
		 * The ST Micro variant has some additional bits
		 * indicating signal direction for the signals in
		 * the SD/MMC bus and feedback-clock usage.
		 */
		pwr |= host->plat->sigdir;

		if (ios->bus_width == MMC_BUS_WIDTH_4)
			pwr &= ~MCI_ST_DATA74DIREN;
		else if (ios->bus_width == MMC_BUS_WIDTH_1)
			pwr &= (~MCI_ST_DATA74DIREN &
				~MCI_ST_DATA31DIREN &
				~MCI_ST_DATA2DIREN);
	}

	if (ios->bus_mode == MMC_BUSMODE_OPENDRAIN) {
		if (host->hw_designer != AMBA_VENDOR_ST)
			pwr |= MCI_ROD;
		else {
			/*
			 * The ST Micro variant use the ROD bit for something
			 * else and only has OD (Open Drain).
			 */
			pwr |= MCI_OD;
		}
	}

	/*
	 * If clock = 0 and the variant requires the MMCIPOWER to be used for
	 * gating the clock, the MCI_PWR_ON bit is cleared.
	 */
	if (!ios->clock && variant->pwrreg_clkgate)
		pwr &= ~MCI_PWR_ON;

	spin_lock_irqsave(&host->lock, flags);

	mmci_set_clkreg(host, ios->clock);
	mmci_write_pwrreg(host, pwr);
	mmci_reg_delay(host);

	spin_unlock_irqrestore(&host->lock, flags);

	pm_runtime_mark_last_busy(mmc_dev(mmc));
	pm_runtime_put_autosuspend(mmc_dev(mmc));
}

static int mmci_get_ro(struct mmc_host *mmc)
{
	struct mmci_host *host = mmc_priv(mmc);

	if (host->gpio_wp == -ENOSYS)
		return -ENOSYS;

	return gpio_get_value_cansleep(host->gpio_wp);
}

static int mmci_get_cd(struct mmc_host *mmc)
{
	struct mmci_host *host = mmc_priv(mmc);
	struct mmci_platform_data *plat = host->plat;
	unsigned int status;

	if (host->gpio_cd == -ENOSYS) {
		if (!plat->status)
			return 1; /* Assume always present */

		status = plat->status(mmc_dev(host->mmc));
	} else
		status = !!gpio_get_value_cansleep(host->gpio_cd)
			^ plat->cd_invert;

	/*
	 * Use positive logic throughout - status is zero for no card,
	 * non-zero for card inserted.
	 */
	return status;
}

static int mmci_sig_volt_switch(struct mmc_host *mmc, struct mmc_ios *ios)
{
	int ret = 0;

	if (!IS_ERR(mmc->supply.vqmmc)) {

		pm_runtime_get_sync(mmc_dev(mmc));

		switch (ios->signal_voltage) {
		case MMC_SIGNAL_VOLTAGE_330:
			ret = regulator_set_voltage(mmc->supply.vqmmc,
						2700000, 3600000);
			break;
		case MMC_SIGNAL_VOLTAGE_180:
			ret = regulator_set_voltage(mmc->supply.vqmmc,
						1700000, 1950000);
			break;
		case MMC_SIGNAL_VOLTAGE_120:
			ret = regulator_set_voltage(mmc->supply.vqmmc,
						1100000, 1300000);
			break;
		}

		if (ret)
			dev_warn(mmc_dev(mmc), "Voltage switch failed\n");

		pm_runtime_mark_last_busy(mmc_dev(mmc));
		pm_runtime_put_autosuspend(mmc_dev(mmc));
	}

	return ret;
}

static irqreturn_t mmci_cd_irq(int irq, void *dev_id)
{
	struct mmci_host *host = dev_id;

	mmc_detect_change(host->mmc, msecs_to_jiffies(500));

	return IRQ_HANDLED;
}

static struct mmc_host_ops mmci_ops = {
	.request	= mmci_request,
	.pre_req	= mmci_pre_request,
	.post_req	= mmci_post_request,
	.set_ios	= mmci_set_ios,
	.get_ro		= mmci_get_ro,
	.get_cd		= mmci_get_cd,
	.start_signal_voltage_switch = mmci_sig_volt_switch,
};

#ifdef CONFIG_OF
static void mmci_dt_populate_generic_pdata(struct device_node *np,
					struct mmci_platform_data *pdata)
{
	int bus_width = 0;

	pdata->gpio_wp = of_get_named_gpio(np, "wp-gpios", 0);
	pdata->gpio_cd = of_get_named_gpio(np, "cd-gpios", 0);

	if (of_get_property(np, "cd-inverted", NULL))
		pdata->cd_invert = true;
	else
		pdata->cd_invert = false;

	of_property_read_u32(np, "max-frequency", &pdata->f_max);
	if (!pdata->f_max)
		pr_warn("%s has no 'max-frequency' property\n", np->full_name);

	if (of_get_property(np, "mmc-cap-mmc-highspeed", NULL))
		pdata->capabilities |= MMC_CAP_MMC_HIGHSPEED;
	if (of_get_property(np, "mmc-cap-sd-highspeed", NULL))
		pdata->capabilities |= MMC_CAP_SD_HIGHSPEED;

	of_property_read_u32(np, "bus-width", &bus_width);
	switch (bus_width) {
	case 0 :
		/* No bus-width supplied. */
		break;
	case 4 :
		pdata->capabilities |= MMC_CAP_4_BIT_DATA;
		break;
	case 8 :
		pdata->capabilities |= MMC_CAP_8_BIT_DATA;
		break;
	default :
		pr_warn("%s: Unsupported bus width\n", np->full_name);
	}
}
#else
static void mmci_dt_populate_generic_pdata(struct device_node *np,
					struct mmci_platform_data *pdata)
{
	return;
}
#endif

static int mmci_probe(struct amba_device *dev,
	const struct amba_id *id)
{
	struct mmci_platform_data *plat = dev->dev.platform_data;
	struct device_node *np = dev->dev.of_node;
	struct variant_data *variant = id->data;
	struct mmci_host *host;
	struct mmc_host *mmc;
	int ret;

	/* Must have platform data or Device Tree. */
	if (!plat && !np) {
		dev_err(&dev->dev, "No plat data or DT found\n");
		return -EINVAL;
	}

	if (!plat) {
		plat = devm_kzalloc(&dev->dev, sizeof(*plat), GFP_KERNEL);
		if (!plat)
			return -ENOMEM;
	}

	if (np)
		mmci_dt_populate_generic_pdata(np, plat);

	ret = amba_request_regions(dev, DRIVER_NAME);
	if (ret)
		goto out;

	mmc = mmc_alloc_host(sizeof(struct mmci_host), &dev->dev);
	if (!mmc) {
		ret = -ENOMEM;
		goto rel_regions;
	}

	host = mmc_priv(mmc);
	host->mmc = mmc;

	host->gpio_wp = -ENOSYS;
	host->gpio_cd = -ENOSYS;
	host->gpio_cd_irq = -1;

	host->hw_designer = amba_manf(dev);
	host->hw_revision = amba_rev(dev);
	dev_dbg(mmc_dev(mmc), "designer ID = 0x%02x\n", host->hw_designer);
	dev_dbg(mmc_dev(mmc), "revision = 0x%01x\n", host->hw_revision);

	host->clk = devm_clk_get(&dev->dev, NULL);
	if (IS_ERR(host->clk)) {
		ret = PTR_ERR(host->clk);
		goto host_free;
	}

	ret = clk_prepare_enable(host->clk);
	if (ret)
		goto host_free;

	host->plat = plat;
	host->variant = variant;
	host->mclk = clk_get_rate(host->clk);
	/*
	 * According to the spec, mclk is max 100 MHz,
	 * so we try to adjust the clock down to this,
	 * (if possible).
	 */
	if (host->mclk > 100000000) {
		ret = clk_set_rate(host->clk, 100000000);
		if (ret < 0)
			goto clk_disable;
		host->mclk = clk_get_rate(host->clk);
		dev_dbg(mmc_dev(mmc), "eventual mclk rate: %u Hz\n",
			host->mclk);
	}
	host->phybase = dev->res.start;
	host->base = ioremap(dev->res.start, resource_size(&dev->res));
	if (!host->base) {
		ret = -ENOMEM;
		goto clk_disable;
	}

	/*
	 * The ARM and ST versions of the block have slightly different
	 * clock divider equations which means that the minimum divider
	 * differs too.
	 */
	if (variant->st_clkdiv)
		mmc->f_min = DIV_ROUND_UP(host->mclk, 257);
	else
		mmc->f_min = DIV_ROUND_UP(host->mclk, 512);
	/*
	 * If the platform data supplies a maximum operating
	 * frequency, this takes precedence. Else, we fall back
	 * to using the module parameter, which has a (low)
	 * default value in case it is not specified. Either
	 * value must not exceed the clock rate into the block,
	 * of course.
	 */
	if (plat->f_max)
		mmc->f_max = min(host->mclk, plat->f_max);
	else
		mmc->f_max = min(host->mclk, fmax);
	dev_dbg(mmc_dev(mmc), "clocking block at %u Hz\n", mmc->f_max);

	/* Get regulators and the supported OCR mask */
	mmc_regulator_get_supply(mmc);
	if (!mmc->ocr_avail)
		mmc->ocr_avail = plat->ocr_mask;
	else if (plat->ocr_mask)
		dev_warn(mmc_dev(mmc), "Platform OCR mask is ignored\n");

	mmc->caps = plat->capabilities;
	mmc->caps2 = plat->capabilities2;

	if (variant->busy_detect) {
		mmci_ops.card_busy = mmci_card_busy;
		mmci_write_datactrlreg(host, MCI_ST_DPSM_BUSYMODE);
		mmc->caps |= MMC_CAP_WAIT_WHILE_BUSY;
		mmc->max_busy_timeout = 0;
	}

	mmc->ops = &mmci_ops;

	/* We support these PM capabilities. */
	mmc->pm_caps = MMC_PM_KEEP_POWER;

	/*
	 * We can do SGIO
	 */
	mmc->max_segs = NR_SG;

	/*
	 * Since only a certain number of bits are valid in the data length
	 * register, we must ensure that we don't exceed 2^num-1 bytes in a
	 * single request.
	 */
	mmc->max_req_size = (1 << variant->datalength_bits) - 1;

	/*
	 * Set the maximum segment size.  Since we aren't doing DMA
	 * (yet) we are only limited by the data length register.
	 */
	mmc->max_seg_size = mmc->max_req_size;

	/*
	 * Block size can be up to 2048 bytes, but must be a power of two.
	 */
	mmc->max_blk_size = 1 << 11;

	/*
	 * Limit the number of blocks transferred so that we don't overflow
	 * the maximum request size.
	 */
	mmc->max_blk_count = mmc->max_req_size >> 11;

	spin_lock_init(&host->lock);

	writel(0, host->base + MMCIMASK0);
	writel(0, host->base + MMCIMASK1);
	writel(0xfff, host->base + MMCICLEAR);

	if (plat->gpio_cd == -EPROBE_DEFER) {
		ret = -EPROBE_DEFER;
		goto err_gpio_cd;
	}
	if (gpio_is_valid(plat->gpio_cd)) {
		ret = gpio_request(plat->gpio_cd, DRIVER_NAME " (cd)");
		if (ret == 0)
			ret = gpio_direction_input(plat->gpio_cd);
		if (ret == 0)
			host->gpio_cd = plat->gpio_cd;
		else if (ret != -ENOSYS)
			goto err_gpio_cd;

		/*
		 * A gpio pin that will detect cards when inserted and removed
		 * will most likely want to trigger on the edges if it is
		 * 0 when ejected and 1 when inserted (or mutatis mutandis
		 * for the inverted case) so we request triggers on both
		 * edges.
		 */
		ret = request_any_context_irq(gpio_to_irq(plat->gpio_cd),
				mmci_cd_irq,
				IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
				DRIVER_NAME " (cd)", host);
		if (ret >= 0)
			host->gpio_cd_irq = gpio_to_irq(plat->gpio_cd);
	}
	if (plat->gpio_wp == -EPROBE_DEFER) {
		ret = -EPROBE_DEFER;
		goto err_gpio_wp;
	}
	if (gpio_is_valid(plat->gpio_wp)) {
		ret = gpio_request(plat->gpio_wp, DRIVER_NAME " (wp)");
		if (ret == 0)
			ret = gpio_direction_input(plat->gpio_wp);
		if (ret == 0)
			host->gpio_wp = plat->gpio_wp;
		else if (ret != -ENOSYS)
			goto err_gpio_wp;
	}

	if ((host->plat->status || host->gpio_cd != -ENOSYS)
	    && host->gpio_cd_irq < 0)
		mmc->caps |= MMC_CAP_NEEDS_POLL;

	ret = request_irq(dev->irq[0], mmci_irq, IRQF_SHARED, DRIVER_NAME " (cmd)", host);
	if (ret)
		goto unmap;

	if (!dev->irq[1])
		host->singleirq = true;
	else {
		ret = request_irq(dev->irq[1], mmci_pio_irq, IRQF_SHARED,
				  DRIVER_NAME " (pio)", host);
		if (ret)
			goto irq0_free;
	}

	writel(MCI_IRQENABLE, host->base + MMCIMASK0);

	amba_set_drvdata(dev, mmc);

	dev_info(&dev->dev, "%s: PL%03x manf %x rev%u at 0x%08llx irq %d,%d (pio)\n",
		 mmc_hostname(mmc), amba_part(dev), amba_manf(dev),
		 amba_rev(dev), (unsigned long long)dev->res.start,
		 dev->irq[0], dev->irq[1]);

	mmci_dma_setup(host);

	pm_runtime_set_autosuspend_delay(&dev->dev, 50);
	pm_runtime_use_autosuspend(&dev->dev);
	pm_runtime_put(&dev->dev);

	mmc_add_host(mmc);

	return 0;

 irq0_free:
	free_irq(dev->irq[0], host);
 unmap:
	if (host->gpio_wp != -ENOSYS)
		gpio_free(host->gpio_wp);
 err_gpio_wp:
	if (host->gpio_cd_irq >= 0)
		free_irq(host->gpio_cd_irq, host);
	if (host->gpio_cd != -ENOSYS)
		gpio_free(host->gpio_cd);
 err_gpio_cd:
	iounmap(host->base);
 clk_disable:
	clk_disable_unprepare(host->clk);
 host_free:
	mmc_free_host(mmc);
 rel_regions:
	amba_release_regions(dev);
 out:
	return ret;
}

static int mmci_remove(struct amba_device *dev)
{
	struct mmc_host *mmc = amba_get_drvdata(dev);

	if (mmc) {
		struct mmci_host *host = mmc_priv(mmc);

		/*
		 * Undo pm_runtime_put() in probe.  We use the _sync
		 * version here so that we can access the primecell.
		 */
		pm_runtime_get_sync(&dev->dev);

		mmc_remove_host(mmc);

		writel(0, host->base + MMCIMASK0);
		writel(0, host->base + MMCIMASK1);

		writel(0, host->base + MMCICOMMAND);
		writel(0, host->base + MMCIDATACTRL);

		mmci_dma_release(host);
		free_irq(dev->irq[0], host);
		if (!host->singleirq)
			free_irq(dev->irq[1], host);

		if (host->gpio_wp != -ENOSYS)
			gpio_free(host->gpio_wp);
		if (host->gpio_cd_irq >= 0)
			free_irq(host->gpio_cd_irq, host);
		if (host->gpio_cd != -ENOSYS)
			gpio_free(host->gpio_cd);

		iounmap(host->base);
		clk_disable_unprepare(host->clk);

		mmc_free_host(mmc);

		amba_release_regions(dev);
	}

	return 0;
}

#ifdef CONFIG_SUSPEND
static int mmci_suspend(struct device *dev)
{
	struct amba_device *adev = to_amba_device(dev);
	struct mmc_host *mmc = amba_get_drvdata(adev);

	if (mmc) {
		struct mmci_host *host = mmc_priv(mmc);
		pm_runtime_get_sync(dev);
		writel(0, host->base + MMCIMASK0);
	}

	return 0;
}

static int mmci_resume(struct device *dev)
{
	struct amba_device *adev = to_amba_device(dev);
	struct mmc_host *mmc = amba_get_drvdata(adev);

	if (mmc) {
		struct mmci_host *host = mmc_priv(mmc);
		writel(MCI_IRQENABLE, host->base + MMCIMASK0);
		pm_runtime_put(dev);
	}

	return 0;
}
#endif

#ifdef CONFIG_PM_RUNTIME
static void mmci_save(struct mmci_host *host)
{
	unsigned long flags;

	if (host->variant->pwrreg_nopower) {
		spin_lock_irqsave(&host->lock, flags);

		writel(0, host->base + MMCIMASK0);
		writel(0, host->base + MMCIDATACTRL);
		writel(0, host->base + MMCIPOWER);
		writel(0, host->base + MMCICLOCK);
		mmci_reg_delay(host);

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

}

static void mmci_restore(struct mmci_host *host)
{
	unsigned long flags;

	if (host->variant->pwrreg_nopower) {
		spin_lock_irqsave(&host->lock, flags);

		writel(host->clk_reg, host->base + MMCICLOCK);
		writel(host->datactrl_reg, host->base + MMCIDATACTRL);
		writel(host->pwr_reg, host->base + MMCIPOWER);
		writel(MCI_IRQENABLE, host->base + MMCIMASK0);
		mmci_reg_delay(host);

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

static int mmci_runtime_suspend(struct device *dev)
{
	struct amba_device *adev = to_amba_device(dev);
	struct mmc_host *mmc = amba_get_drvdata(adev);

	if (mmc) {
		struct mmci_host *host = mmc_priv(mmc);
		pinctrl_pm_select_sleep_state(dev);
		mmci_save(host);
		clk_disable_unprepare(host->clk);
	}

	return 0;
}

static int mmci_runtime_resume(struct device *dev)
{
	struct amba_device *adev = to_amba_device(dev);
	struct mmc_host *mmc = amba_get_drvdata(adev);

	if (mmc) {
		struct mmci_host *host = mmc_priv(mmc);
		clk_prepare_enable(host->clk);
		mmci_restore(host);
		pinctrl_pm_select_default_state(dev);
	}

	return 0;
}
#endif

static const struct dev_pm_ops mmci_dev_pm_ops = {
	SET_SYSTEM_SLEEP_PM_OPS(mmci_suspend, mmci_resume)
	SET_RUNTIME_PM_OPS(mmci_runtime_suspend, mmci_runtime_resume, NULL)
};

static struct amba_id mmci_ids[] = {
	{
		.id	= 0x00041180,
		.mask	= 0xff0fffff,
		.data	= &variant_arm,
	},
	{
		.id	= 0x01041180,
		.mask	= 0xff0fffff,
		.data	= &variant_arm_extended_fifo,
	},
	{
		.id	= 0x02041180,
		.mask	= 0xff0fffff,
		.data	= &variant_arm_extended_fifo_hwfc,
	},
	{
		.id	= 0x00041181,
		.mask	= 0x000fffff,
		.data	= &variant_arm,
	},
	/* ST Micro variants */
	{
		.id     = 0x00180180,
		.mask   = 0x00ffffff,
		.data	= &variant_u300,
	},
	{
		.id     = 0x10180180,
		.mask   = 0xf0ffffff,
		.data	= &variant_nomadik,
	},
	{
		.id     = 0x00280180,
		.mask   = 0x00ffffff,
		.data	= &variant_u300,
	},
	{
		.id     = 0x00480180,
		.mask   = 0xf0ffffff,
		.data	= &variant_ux500,
	},
	{
		.id     = 0x10480180,
		.mask   = 0xf0ffffff,
		.data	= &variant_ux500v2,
	},
	{ 0, 0 },
};

MODULE_DEVICE_TABLE(amba, mmci_ids);

static struct amba_driver mmci_driver = {
	.drv		= {
		.name	= DRIVER_NAME,
		.pm	= &mmci_dev_pm_ops,
	},
	.probe		= mmci_probe,
	.remove		= mmci_remove,
	.id_table	= mmci_ids,
};

module_amba_driver(mmci_driver);

module_param(fmax, uint, 0444);

MODULE_DESCRIPTION("ARM PrimeCell PL180/181 Multimedia Card Interface driver");
MODULE_LICENSE("GPL");