summaryrefslogtreecommitdiffstats
path: root/drivers/iommu/omap-iommu.c
blob: af4a8e7fcd27453f160788c93c660f7cf39ff3ab (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
/*
 * omap iommu: tlb and pagetable primitives
 *
 * Copyright (C) 2008-2010 Nokia Corporation
 * Copyright (C) 2013-2017 Texas Instruments Incorporated - http://www.ti.com/
 *
 * Written by Hiroshi DOYU <Hiroshi.DOYU@nokia.com>,
 *		Paul Mundt and Toshihiro Kobayashi
 *
 * 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/dma-mapping.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/ioport.h>
#include <linux/platform_device.h>
#include <linux/iommu.h>
#include <linux/omap-iommu.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
#include <linux/io.h>
#include <linux/pm_runtime.h>
#include <linux/of.h>
#include <linux/of_iommu.h>
#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <linux/regmap.h>
#include <linux/mfd/syscon.h>

#include <linux/platform_data/iommu-omap.h>

#include "omap-iopgtable.h"
#include "omap-iommu.h"

static const struct iommu_ops omap_iommu_ops;

#define to_iommu(dev)							\
	((struct omap_iommu *)platform_get_drvdata(to_platform_device(dev)))

/* bitmap of the page sizes currently supported */
#define OMAP_IOMMU_PGSIZES	(SZ_4K | SZ_64K | SZ_1M | SZ_16M)

#define MMU_LOCK_BASE_SHIFT	10
#define MMU_LOCK_BASE_MASK	(0x1f << MMU_LOCK_BASE_SHIFT)
#define MMU_LOCK_BASE(x)	\
	((x & MMU_LOCK_BASE_MASK) >> MMU_LOCK_BASE_SHIFT)

#define MMU_LOCK_VICT_SHIFT	4
#define MMU_LOCK_VICT_MASK	(0x1f << MMU_LOCK_VICT_SHIFT)
#define MMU_LOCK_VICT(x)	\
	((x & MMU_LOCK_VICT_MASK) >> MMU_LOCK_VICT_SHIFT)

static struct platform_driver omap_iommu_driver;
static struct kmem_cache *iopte_cachep;

/**
 * to_omap_domain - Get struct omap_iommu_domain from generic iommu_domain
 * @dom:	generic iommu domain handle
 **/
static struct omap_iommu_domain *to_omap_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct omap_iommu_domain, domain);
}

/**
 * omap_iommu_save_ctx - Save registers for pm off-mode support
 * @dev:	client device
 **/
void omap_iommu_save_ctx(struct device *dev)
{
	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
	struct omap_iommu *obj;
	u32 *p;
	int i;

	if (!arch_data)
		return;

	while (arch_data->iommu_dev) {
		obj = arch_data->iommu_dev;
		p = obj->ctx;
		for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
			p[i] = iommu_read_reg(obj, i * sizeof(u32));
			dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i,
				p[i]);
		}
		arch_data++;
	}
}
EXPORT_SYMBOL_GPL(omap_iommu_save_ctx);

/**
 * omap_iommu_restore_ctx - Restore registers for pm off-mode support
 * @dev:	client device
 **/
void omap_iommu_restore_ctx(struct device *dev)
{
	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
	struct omap_iommu *obj;
	u32 *p;
	int i;

	if (!arch_data)
		return;

	while (arch_data->iommu_dev) {
		obj = arch_data->iommu_dev;
		p = obj->ctx;
		for (i = 0; i < (MMU_REG_SIZE / sizeof(u32)); i++) {
			iommu_write_reg(obj, p[i], i * sizeof(u32));
			dev_dbg(obj->dev, "%s\t[%02d] %08x\n", __func__, i,
				p[i]);
		}
		arch_data++;
	}
}
EXPORT_SYMBOL_GPL(omap_iommu_restore_ctx);

static void dra7_cfg_dspsys_mmu(struct omap_iommu *obj, bool enable)
{
	u32 val, mask;

	if (!obj->syscfg)
		return;

	mask = (1 << (obj->id * DSP_SYS_MMU_CONFIG_EN_SHIFT));
	val = enable ? mask : 0;
	regmap_update_bits(obj->syscfg, DSP_SYS_MMU_CONFIG, mask, val);
}

static void __iommu_set_twl(struct omap_iommu *obj, bool on)
{
	u32 l = iommu_read_reg(obj, MMU_CNTL);

	if (on)
		iommu_write_reg(obj, MMU_IRQ_TWL_MASK, MMU_IRQENABLE);
	else
		iommu_write_reg(obj, MMU_IRQ_TLB_MISS_MASK, MMU_IRQENABLE);

	l &= ~MMU_CNTL_MASK;
	if (on)
		l |= (MMU_CNTL_MMU_EN | MMU_CNTL_TWL_EN);
	else
		l |= (MMU_CNTL_MMU_EN);

	iommu_write_reg(obj, l, MMU_CNTL);
}

static int omap2_iommu_enable(struct omap_iommu *obj)
{
	u32 l, pa;

	if (!obj->iopgd || !IS_ALIGNED((u32)obj->iopgd,  SZ_16K))
		return -EINVAL;

	pa = virt_to_phys(obj->iopgd);
	if (!IS_ALIGNED(pa, SZ_16K))
		return -EINVAL;

	l = iommu_read_reg(obj, MMU_REVISION);
	dev_info(obj->dev, "%s: version %d.%d\n", obj->name,
		 (l >> 4) & 0xf, l & 0xf);

	iommu_write_reg(obj, pa, MMU_TTB);

	dra7_cfg_dspsys_mmu(obj, true);

	if (obj->has_bus_err_back)
		iommu_write_reg(obj, MMU_GP_REG_BUS_ERR_BACK_EN, MMU_GP_REG);

	__iommu_set_twl(obj, true);

	return 0;
}

static void omap2_iommu_disable(struct omap_iommu *obj)
{
	u32 l = iommu_read_reg(obj, MMU_CNTL);

	l &= ~MMU_CNTL_MASK;
	iommu_write_reg(obj, l, MMU_CNTL);
	dra7_cfg_dspsys_mmu(obj, false);

	dev_dbg(obj->dev, "%s is shutting down\n", obj->name);
}

static int iommu_enable(struct omap_iommu *obj)
{
	int err;
	struct platform_device *pdev = to_platform_device(obj->dev);
	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);

	if (pdata && pdata->deassert_reset) {
		err = pdata->deassert_reset(pdev, pdata->reset_name);
		if (err) {
			dev_err(obj->dev, "deassert_reset failed: %d\n", err);
			return err;
		}
	}

	pm_runtime_get_sync(obj->dev);

	err = omap2_iommu_enable(obj);

	return err;
}

static void iommu_disable(struct omap_iommu *obj)
{
	struct platform_device *pdev = to_platform_device(obj->dev);
	struct iommu_platform_data *pdata = dev_get_platdata(&pdev->dev);

	omap2_iommu_disable(obj);

	pm_runtime_put_sync(obj->dev);

	if (pdata && pdata->assert_reset)
		pdata->assert_reset(pdev, pdata->reset_name);
}

/*
 *	TLB operations
 */
static u32 iotlb_cr_to_virt(struct cr_regs *cr)
{
	u32 page_size = cr->cam & MMU_CAM_PGSZ_MASK;
	u32 mask = get_cam_va_mask(cr->cam & page_size);

	return cr->cam & mask;
}

static u32 get_iopte_attr(struct iotlb_entry *e)
{
	u32 attr;

	attr = e->mixed << 5;
	attr |= e->endian;
	attr |= e->elsz >> 3;
	attr <<= (((e->pgsz == MMU_CAM_PGSZ_4K) ||
			(e->pgsz == MMU_CAM_PGSZ_64K)) ? 0 : 6);
	return attr;
}

static u32 iommu_report_fault(struct omap_iommu *obj, u32 *da)
{
	u32 status, fault_addr;

	status = iommu_read_reg(obj, MMU_IRQSTATUS);
	status &= MMU_IRQ_MASK;
	if (!status) {
		*da = 0;
		return 0;
	}

	fault_addr = iommu_read_reg(obj, MMU_FAULT_AD);
	*da = fault_addr;

	iommu_write_reg(obj, status, MMU_IRQSTATUS);

	return status;
}

void iotlb_lock_get(struct omap_iommu *obj, struct iotlb_lock *l)
{
	u32 val;

	val = iommu_read_reg(obj, MMU_LOCK);

	l->base = MMU_LOCK_BASE(val);
	l->vict = MMU_LOCK_VICT(val);
}

void iotlb_lock_set(struct omap_iommu *obj, struct iotlb_lock *l)
{
	u32 val;

	val = (l->base << MMU_LOCK_BASE_SHIFT);
	val |= (l->vict << MMU_LOCK_VICT_SHIFT);

	iommu_write_reg(obj, val, MMU_LOCK);
}

static void iotlb_read_cr(struct omap_iommu *obj, struct cr_regs *cr)
{
	cr->cam = iommu_read_reg(obj, MMU_READ_CAM);
	cr->ram = iommu_read_reg(obj, MMU_READ_RAM);
}

static void iotlb_load_cr(struct omap_iommu *obj, struct cr_regs *cr)
{
	iommu_write_reg(obj, cr->cam | MMU_CAM_V, MMU_CAM);
	iommu_write_reg(obj, cr->ram, MMU_RAM);

	iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY);
	iommu_write_reg(obj, 1, MMU_LD_TLB);
}

/* only used in iotlb iteration for-loop */
struct cr_regs __iotlb_read_cr(struct omap_iommu *obj, int n)
{
	struct cr_regs cr;
	struct iotlb_lock l;

	iotlb_lock_get(obj, &l);
	l.vict = n;
	iotlb_lock_set(obj, &l);
	iotlb_read_cr(obj, &cr);

	return cr;
}

#ifdef PREFETCH_IOTLB
static struct cr_regs *iotlb_alloc_cr(struct omap_iommu *obj,
				      struct iotlb_entry *e)
{
	struct cr_regs *cr;

	if (!e)
		return NULL;

	if (e->da & ~(get_cam_va_mask(e->pgsz))) {
		dev_err(obj->dev, "%s:\twrong alignment: %08x\n", __func__,
			e->da);
		return ERR_PTR(-EINVAL);
	}

	cr = kmalloc(sizeof(*cr), GFP_KERNEL);
	if (!cr)
		return ERR_PTR(-ENOMEM);

	cr->cam = (e->da & MMU_CAM_VATAG_MASK) | e->prsvd | e->pgsz | e->valid;
	cr->ram = e->pa | e->endian | e->elsz | e->mixed;

	return cr;
}

/**
 * load_iotlb_entry - Set an iommu tlb entry
 * @obj:	target iommu
 * @e:		an iommu tlb entry info
 **/
static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
{
	int err = 0;
	struct iotlb_lock l;
	struct cr_regs *cr;

	if (!obj || !obj->nr_tlb_entries || !e)
		return -EINVAL;

	pm_runtime_get_sync(obj->dev);

	iotlb_lock_get(obj, &l);
	if (l.base == obj->nr_tlb_entries) {
		dev_warn(obj->dev, "%s: preserve entries full\n", __func__);
		err = -EBUSY;
		goto out;
	}
	if (!e->prsvd) {
		int i;
		struct cr_regs tmp;

		for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, tmp)
			if (!iotlb_cr_valid(&tmp))
				break;

		if (i == obj->nr_tlb_entries) {
			dev_dbg(obj->dev, "%s: full: no entry\n", __func__);
			err = -EBUSY;
			goto out;
		}

		iotlb_lock_get(obj, &l);
	} else {
		l.vict = l.base;
		iotlb_lock_set(obj, &l);
	}

	cr = iotlb_alloc_cr(obj, e);
	if (IS_ERR(cr)) {
		pm_runtime_put_sync(obj->dev);
		return PTR_ERR(cr);
	}

	iotlb_load_cr(obj, cr);
	kfree(cr);

	if (e->prsvd)
		l.base++;
	/* increment victim for next tlb load */
	if (++l.vict == obj->nr_tlb_entries)
		l.vict = l.base;
	iotlb_lock_set(obj, &l);
out:
	pm_runtime_put_sync(obj->dev);
	return err;
}

#else /* !PREFETCH_IOTLB */

static int load_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
{
	return 0;
}

#endif /* !PREFETCH_IOTLB */

static int prefetch_iotlb_entry(struct omap_iommu *obj, struct iotlb_entry *e)
{
	return load_iotlb_entry(obj, e);
}

/**
 * flush_iotlb_page - Clear an iommu tlb entry
 * @obj:	target iommu
 * @da:		iommu device virtual address
 *
 * Clear an iommu tlb entry which includes 'da' address.
 **/
static void flush_iotlb_page(struct omap_iommu *obj, u32 da)
{
	int i;
	struct cr_regs cr;

	pm_runtime_get_sync(obj->dev);

	for_each_iotlb_cr(obj, obj->nr_tlb_entries, i, cr) {
		u32 start;
		size_t bytes;

		if (!iotlb_cr_valid(&cr))
			continue;

		start = iotlb_cr_to_virt(&cr);
		bytes = iopgsz_to_bytes(cr.cam & 3);

		if ((start <= da) && (da < start + bytes)) {
			dev_dbg(obj->dev, "%s: %08x<=%08x(%x)\n",
				__func__, start, da, bytes);
			iotlb_load_cr(obj, &cr);
			iommu_write_reg(obj, 1, MMU_FLUSH_ENTRY);
			break;
		}
	}
	pm_runtime_put_sync(obj->dev);

	if (i == obj->nr_tlb_entries)
		dev_dbg(obj->dev, "%s: no page for %08x\n", __func__, da);
}

/**
 * flush_iotlb_all - Clear all iommu tlb entries
 * @obj:	target iommu
 **/
static void flush_iotlb_all(struct omap_iommu *obj)
{
	struct iotlb_lock l;

	pm_runtime_get_sync(obj->dev);

	l.base = 0;
	l.vict = 0;
	iotlb_lock_set(obj, &l);

	iommu_write_reg(obj, 1, MMU_GFLUSH);

	pm_runtime_put_sync(obj->dev);
}

/*
 *	H/W pagetable operations
 */
static void flush_iopte_range(struct device *dev, dma_addr_t dma,
			      unsigned long offset, int num_entries)
{
	size_t size = num_entries * sizeof(u32);

	dma_sync_single_range_for_device(dev, dma, offset, size, DMA_TO_DEVICE);
}

static void iopte_free(struct omap_iommu *obj, u32 *iopte, bool dma_valid)
{
	dma_addr_t pt_dma;

	/* Note: freed iopte's must be clean ready for re-use */
	if (iopte) {
		if (dma_valid) {
			pt_dma = virt_to_phys(iopte);
			dma_unmap_single(obj->dev, pt_dma, IOPTE_TABLE_SIZE,
					 DMA_TO_DEVICE);
		}

		kmem_cache_free(iopte_cachep, iopte);
	}
}

static u32 *iopte_alloc(struct omap_iommu *obj, u32 *iopgd,
			dma_addr_t *pt_dma, u32 da)
{
	u32 *iopte;
	unsigned long offset = iopgd_index(da) * sizeof(da);

	/* a table has already existed */
	if (*iopgd)
		goto pte_ready;

	/*
	 * do the allocation outside the page table lock
	 */
	spin_unlock(&obj->page_table_lock);
	iopte = kmem_cache_zalloc(iopte_cachep, GFP_KERNEL);
	spin_lock(&obj->page_table_lock);

	if (!*iopgd) {
		if (!iopte)
			return ERR_PTR(-ENOMEM);

		*pt_dma = dma_map_single(obj->dev, iopte, IOPTE_TABLE_SIZE,
					 DMA_TO_DEVICE);
		if (dma_mapping_error(obj->dev, *pt_dma)) {
			dev_err(obj->dev, "DMA map error for L2 table\n");
			iopte_free(obj, iopte, false);
			return ERR_PTR(-ENOMEM);
		}

		/*
		 * we rely on dma address and the physical address to be
		 * the same for mapping the L2 table
		 */
		if (WARN_ON(*pt_dma != virt_to_phys(iopte))) {
			dev_err(obj->dev, "DMA translation error for L2 table\n");
			dma_unmap_single(obj->dev, *pt_dma, IOPTE_TABLE_SIZE,
					 DMA_TO_DEVICE);
			iopte_free(obj, iopte, false);
			return ERR_PTR(-ENOMEM);
		}

		*iopgd = virt_to_phys(iopte) | IOPGD_TABLE;

		flush_iopte_range(obj->dev, obj->pd_dma, offset, 1);
		dev_vdbg(obj->dev, "%s: a new pte:%p\n", __func__, iopte);
	} else {
		/* We raced, free the reduniovant table */
		iopte_free(obj, iopte, false);
	}

pte_ready:
	iopte = iopte_offset(iopgd, da);
	*pt_dma = virt_to_phys(iopte);
	dev_vdbg(obj->dev,
		 "%s: da:%08x pgd:%p *pgd:%08x pte:%p *pte:%08x\n",
		 __func__, da, iopgd, *iopgd, iopte, *iopte);

	return iopte;
}

static int iopgd_alloc_section(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
{
	u32 *iopgd = iopgd_offset(obj, da);
	unsigned long offset = iopgd_index(da) * sizeof(da);

	if ((da | pa) & ~IOSECTION_MASK) {
		dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n",
			__func__, da, pa, IOSECTION_SIZE);
		return -EINVAL;
	}

	*iopgd = (pa & IOSECTION_MASK) | prot | IOPGD_SECTION;
	flush_iopte_range(obj->dev, obj->pd_dma, offset, 1);
	return 0;
}

static int iopgd_alloc_super(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
{
	u32 *iopgd = iopgd_offset(obj, da);
	unsigned long offset = iopgd_index(da) * sizeof(da);
	int i;

	if ((da | pa) & ~IOSUPER_MASK) {
		dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n",
			__func__, da, pa, IOSUPER_SIZE);
		return -EINVAL;
	}

	for (i = 0; i < 16; i++)
		*(iopgd + i) = (pa & IOSUPER_MASK) | prot | IOPGD_SUPER;
	flush_iopte_range(obj->dev, obj->pd_dma, offset, 16);
	return 0;
}

static int iopte_alloc_page(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
{
	u32 *iopgd = iopgd_offset(obj, da);
	dma_addr_t pt_dma;
	u32 *iopte = iopte_alloc(obj, iopgd, &pt_dma, da);
	unsigned long offset = iopte_index(da) * sizeof(da);

	if (IS_ERR(iopte))
		return PTR_ERR(iopte);

	*iopte = (pa & IOPAGE_MASK) | prot | IOPTE_SMALL;
	flush_iopte_range(obj->dev, pt_dma, offset, 1);

	dev_vdbg(obj->dev, "%s: da:%08x pa:%08x pte:%p *pte:%08x\n",
		 __func__, da, pa, iopte, *iopte);

	return 0;
}

static int iopte_alloc_large(struct omap_iommu *obj, u32 da, u32 pa, u32 prot)
{
	u32 *iopgd = iopgd_offset(obj, da);
	dma_addr_t pt_dma;
	u32 *iopte = iopte_alloc(obj, iopgd, &pt_dma, da);
	unsigned long offset = iopte_index(da) * sizeof(da);
	int i;

	if ((da | pa) & ~IOLARGE_MASK) {
		dev_err(obj->dev, "%s: %08x:%08x should aligned on %08lx\n",
			__func__, da, pa, IOLARGE_SIZE);
		return -EINVAL;
	}

	if (IS_ERR(iopte))
		return PTR_ERR(iopte);

	for (i = 0; i < 16; i++)
		*(iopte + i) = (pa & IOLARGE_MASK) | prot | IOPTE_LARGE;
	flush_iopte_range(obj->dev, pt_dma, offset, 16);
	return 0;
}

static int
iopgtable_store_entry_core(struct omap_iommu *obj, struct iotlb_entry *e)
{
	int (*fn)(struct omap_iommu *, u32, u32, u32);
	u32 prot;
	int err;

	if (!obj || !e)
		return -EINVAL;

	switch (e->pgsz) {
	case MMU_CAM_PGSZ_16M:
		fn = iopgd_alloc_super;
		break;
	case MMU_CAM_PGSZ_1M:
		fn = iopgd_alloc_section;
		break;
	case MMU_CAM_PGSZ_64K:
		fn = iopte_alloc_large;
		break;
	case MMU_CAM_PGSZ_4K:
		fn = iopte_alloc_page;
		break;
	default:
		fn = NULL;
		break;
	}

	if (WARN_ON(!fn))
		return -EINVAL;

	prot = get_iopte_attr(e);

	spin_lock(&obj->page_table_lock);
	err = fn(obj, e->da, e->pa, prot);
	spin_unlock(&obj->page_table_lock);

	return err;
}

/**
 * omap_iopgtable_store_entry - Make an iommu pte entry
 * @obj:	target iommu
 * @e:		an iommu tlb entry info
 **/
static int
omap_iopgtable_store_entry(struct omap_iommu *obj, struct iotlb_entry *e)
{
	int err;

	flush_iotlb_page(obj, e->da);
	err = iopgtable_store_entry_core(obj, e);
	if (!err)
		prefetch_iotlb_entry(obj, e);
	return err;
}

/**
 * iopgtable_lookup_entry - Lookup an iommu pte entry
 * @obj:	target iommu
 * @da:		iommu device virtual address
 * @ppgd:	iommu pgd entry pointer to be returned
 * @ppte:	iommu pte entry pointer to be returned
 **/
static void
iopgtable_lookup_entry(struct omap_iommu *obj, u32 da, u32 **ppgd, u32 **ppte)
{
	u32 *iopgd, *iopte = NULL;

	iopgd = iopgd_offset(obj, da);
	if (!*iopgd)
		goto out;

	if (iopgd_is_table(*iopgd))
		iopte = iopte_offset(iopgd, da);
out:
	*ppgd = iopgd;
	*ppte = iopte;
}

static size_t iopgtable_clear_entry_core(struct omap_iommu *obj, u32 da)
{
	size_t bytes;
	u32 *iopgd = iopgd_offset(obj, da);
	int nent = 1;
	dma_addr_t pt_dma;
	unsigned long pd_offset = iopgd_index(da) * sizeof(da);
	unsigned long pt_offset = iopte_index(da) * sizeof(da);

	if (!*iopgd)
		return 0;

	if (iopgd_is_table(*iopgd)) {
		int i;
		u32 *iopte = iopte_offset(iopgd, da);

		bytes = IOPTE_SIZE;
		if (*iopte & IOPTE_LARGE) {
			nent *= 16;
			/* rewind to the 1st entry */
			iopte = iopte_offset(iopgd, (da & IOLARGE_MASK));
		}
		bytes *= nent;
		memset(iopte, 0, nent * sizeof(*iopte));
		pt_dma = virt_to_phys(iopte);
		flush_iopte_range(obj->dev, pt_dma, pt_offset, nent);

		/*
		 * do table walk to check if this table is necessary or not
		 */
		iopte = iopte_offset(iopgd, 0);
		for (i = 0; i < PTRS_PER_IOPTE; i++)
			if (iopte[i])
				goto out;

		iopte_free(obj, iopte, true);
		nent = 1; /* for the next L1 entry */
	} else {
		bytes = IOPGD_SIZE;
		if ((*iopgd & IOPGD_SUPER) == IOPGD_SUPER) {
			nent *= 16;
			/* rewind to the 1st entry */
			iopgd = iopgd_offset(obj, (da & IOSUPER_MASK));
		}
		bytes *= nent;
	}
	memset(iopgd, 0, nent * sizeof(*iopgd));
	flush_iopte_range(obj->dev, obj->pd_dma, pd_offset, nent);
out:
	return bytes;
}

/**
 * iopgtable_clear_entry - Remove an iommu pte entry
 * @obj:	target iommu
 * @da:		iommu device virtual address
 **/
static size_t iopgtable_clear_entry(struct omap_iommu *obj, u32 da)
{
	size_t bytes;

	spin_lock(&obj->page_table_lock);

	bytes = iopgtable_clear_entry_core(obj, da);
	flush_iotlb_page(obj, da);

	spin_unlock(&obj->page_table_lock);

	return bytes;
}

static void iopgtable_clear_entry_all(struct omap_iommu *obj)
{
	unsigned long offset;
	int i;

	spin_lock(&obj->page_table_lock);

	for (i = 0; i < PTRS_PER_IOPGD; i++) {
		u32 da;
		u32 *iopgd;

		da = i << IOPGD_SHIFT;
		iopgd = iopgd_offset(obj, da);
		offset = iopgd_index(da) * sizeof(da);

		if (!*iopgd)
			continue;

		if (iopgd_is_table(*iopgd))
			iopte_free(obj, iopte_offset(iopgd, 0), true);

		*iopgd = 0;
		flush_iopte_range(obj->dev, obj->pd_dma, offset, 1);
	}

	flush_iotlb_all(obj);

	spin_unlock(&obj->page_table_lock);
}

/*
 *	Device IOMMU generic operations
 */
static irqreturn_t iommu_fault_handler(int irq, void *data)
{
	u32 da, errs;
	u32 *iopgd, *iopte;
	struct omap_iommu *obj = data;
	struct iommu_domain *domain = obj->domain;
	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);

	if (!omap_domain->dev)
		return IRQ_NONE;

	errs = iommu_report_fault(obj, &da);
	if (errs == 0)
		return IRQ_HANDLED;

	/* Fault callback or TLB/PTE Dynamic loading */
	if (!report_iommu_fault(domain, obj->dev, da, 0))
		return IRQ_HANDLED;

	iommu_write_reg(obj, 0, MMU_IRQENABLE);

	iopgd = iopgd_offset(obj, da);

	if (!iopgd_is_table(*iopgd)) {
		dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:px%08x\n",
			obj->name, errs, da, iopgd, *iopgd);
		return IRQ_NONE;
	}

	iopte = iopte_offset(iopgd, da);

	dev_err(obj->dev, "%s: errs:0x%08x da:0x%08x pgd:0x%p *pgd:0x%08x pte:0x%p *pte:0x%08x\n",
		obj->name, errs, da, iopgd, *iopgd, iopte, *iopte);

	return IRQ_NONE;
}

/**
 * omap_iommu_attach() - attach iommu device to an iommu domain
 * @obj:	target omap iommu device
 * @iopgd:	page table
 **/
static int omap_iommu_attach(struct omap_iommu *obj, u32 *iopgd)
{
	int err;

	spin_lock(&obj->iommu_lock);

	obj->pd_dma = dma_map_single(obj->dev, iopgd, IOPGD_TABLE_SIZE,
				     DMA_TO_DEVICE);
	if (dma_mapping_error(obj->dev, obj->pd_dma)) {
		dev_err(obj->dev, "DMA map error for L1 table\n");
		err = -ENOMEM;
		goto out_err;
	}

	obj->iopgd = iopgd;
	err = iommu_enable(obj);
	if (err)
		goto out_err;
	flush_iotlb_all(obj);

	spin_unlock(&obj->iommu_lock);

	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);

	return 0;

out_err:
	spin_unlock(&obj->iommu_lock);

	return err;
}

/**
 * omap_iommu_detach - release iommu device
 * @obj:	target iommu
 **/
static void omap_iommu_detach(struct omap_iommu *obj)
{
	if (!obj || IS_ERR(obj))
		return;

	spin_lock(&obj->iommu_lock);

	dma_unmap_single(obj->dev, obj->pd_dma, IOPGD_TABLE_SIZE,
			 DMA_TO_DEVICE);
	iommu_disable(obj);
	obj->pd_dma = 0;
	obj->iopgd = NULL;

	spin_unlock(&obj->iommu_lock);

	dev_dbg(obj->dev, "%s: %s\n", __func__, obj->name);
}

static bool omap_iommu_can_register(struct platform_device *pdev)
{
	struct device_node *np = pdev->dev.of_node;

	if (!of_device_is_compatible(np, "ti,dra7-dsp-iommu"))
		return true;

	/*
	 * restrict IOMMU core registration only for processor-port MDMA MMUs
	 * on DRA7 DSPs
	 */
	if ((!strcmp(dev_name(&pdev->dev), "40d01000.mmu")) ||
	    (!strcmp(dev_name(&pdev->dev), "41501000.mmu")))
		return true;

	return false;
}

static int omap_iommu_dra7_get_dsp_system_cfg(struct platform_device *pdev,
					      struct omap_iommu *obj)
{
	struct device_node *np = pdev->dev.of_node;
	int ret;

	if (!of_device_is_compatible(np, "ti,dra7-dsp-iommu"))
		return 0;

	if (!of_property_read_bool(np, "ti,syscon-mmuconfig")) {
		dev_err(&pdev->dev, "ti,syscon-mmuconfig property is missing\n");
		return -EINVAL;
	}

	obj->syscfg =
		syscon_regmap_lookup_by_phandle(np, "ti,syscon-mmuconfig");
	if (IS_ERR(obj->syscfg)) {
		/* can fail with -EPROBE_DEFER */
		ret = PTR_ERR(obj->syscfg);
		return ret;
	}

	if (of_property_read_u32_index(np, "ti,syscon-mmuconfig", 1,
				       &obj->id)) {
		dev_err(&pdev->dev, "couldn't get the IOMMU instance id within subsystem\n");
		return -EINVAL;
	}

	if (obj->id != 0 && obj->id != 1) {
		dev_err(&pdev->dev, "invalid IOMMU instance id\n");
		return -EINVAL;
	}

	return 0;
}

/*
 *	OMAP Device MMU(IOMMU) detection
 */
static int omap_iommu_probe(struct platform_device *pdev)
{
	int err = -ENODEV;
	int irq;
	struct omap_iommu *obj;
	struct resource *res;
	struct device_node *of = pdev->dev.of_node;

	if (!of) {
		pr_err("%s: only DT-based devices are supported\n", __func__);
		return -ENODEV;
	}

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

	obj->name = dev_name(&pdev->dev);
	obj->nr_tlb_entries = 32;
	err = of_property_read_u32(of, "ti,#tlb-entries", &obj->nr_tlb_entries);
	if (err && err != -EINVAL)
		return err;
	if (obj->nr_tlb_entries != 32 && obj->nr_tlb_entries != 8)
		return -EINVAL;
	if (of_find_property(of, "ti,iommu-bus-err-back", NULL))
		obj->has_bus_err_back = MMU_GP_REG_BUS_ERR_BACK_EN;

	obj->dev = &pdev->dev;
	obj->ctx = (void *)obj + sizeof(*obj);

	spin_lock_init(&obj->iommu_lock);
	spin_lock_init(&obj->page_table_lock);

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	obj->regbase = devm_ioremap_resource(obj->dev, res);
	if (IS_ERR(obj->regbase))
		return PTR_ERR(obj->regbase);

	err = omap_iommu_dra7_get_dsp_system_cfg(pdev, obj);
	if (err)
		return err;

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

	err = devm_request_irq(obj->dev, irq, iommu_fault_handler, IRQF_SHARED,
			       dev_name(obj->dev), obj);
	if (err < 0)
		return err;
	platform_set_drvdata(pdev, obj);

	if (omap_iommu_can_register(pdev)) {
		obj->group = iommu_group_alloc();
		if (IS_ERR(obj->group))
			return PTR_ERR(obj->group);

		err = iommu_device_sysfs_add(&obj->iommu, obj->dev, NULL,
					     obj->name);
		if (err)
			goto out_group;

		iommu_device_set_ops(&obj->iommu, &omap_iommu_ops);

		err = iommu_device_register(&obj->iommu);
		if (err)
			goto out_sysfs;
	}

	pm_runtime_irq_safe(obj->dev);
	pm_runtime_enable(obj->dev);

	omap_iommu_debugfs_add(obj);

	dev_info(&pdev->dev, "%s registered\n", obj->name);

	return 0;

out_sysfs:
	iommu_device_sysfs_remove(&obj->iommu);
out_group:
	iommu_group_put(obj->group);
	return err;
}

static int omap_iommu_remove(struct platform_device *pdev)
{
	struct omap_iommu *obj = platform_get_drvdata(pdev);

	if (obj->group) {
		iommu_group_put(obj->group);
		obj->group = NULL;

		iommu_device_sysfs_remove(&obj->iommu);
		iommu_device_unregister(&obj->iommu);
	}

	omap_iommu_debugfs_remove(obj);

	pm_runtime_disable(obj->dev);

	dev_info(&pdev->dev, "%s removed\n", obj->name);
	return 0;
}

static const struct of_device_id omap_iommu_of_match[] = {
	{ .compatible = "ti,omap2-iommu" },
	{ .compatible = "ti,omap4-iommu" },
	{ .compatible = "ti,dra7-iommu"	},
	{ .compatible = "ti,dra7-dsp-iommu" },
	{},
};

static struct platform_driver omap_iommu_driver = {
	.probe	= omap_iommu_probe,
	.remove	= omap_iommu_remove,
	.driver	= {
		.name	= "omap-iommu",
		.of_match_table = of_match_ptr(omap_iommu_of_match),
	},
};

static u32 iotlb_init_entry(struct iotlb_entry *e, u32 da, u32 pa, int pgsz)
{
	memset(e, 0, sizeof(*e));

	e->da		= da;
	e->pa		= pa;
	e->valid	= MMU_CAM_V;
	e->pgsz		= pgsz;
	e->endian	= MMU_RAM_ENDIAN_LITTLE;
	e->elsz		= MMU_RAM_ELSZ_8;
	e->mixed	= 0;

	return iopgsz_to_bytes(e->pgsz);
}

static int omap_iommu_map(struct iommu_domain *domain, unsigned long da,
			  phys_addr_t pa, size_t bytes, int prot)
{
	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
	struct device *dev = omap_domain->dev;
	struct omap_iommu_device *iommu;
	struct omap_iommu *oiommu;
	struct iotlb_entry e;
	int omap_pgsz;
	u32 ret = -EINVAL;
	int i;

	omap_pgsz = bytes_to_iopgsz(bytes);
	if (omap_pgsz < 0) {
		dev_err(dev, "invalid size to map: %d\n", bytes);
		return -EINVAL;
	}

	dev_dbg(dev, "mapping da 0x%lx to pa %pa size 0x%x\n", da, &pa, bytes);

	iotlb_init_entry(&e, da, pa, omap_pgsz);

	iommu = omap_domain->iommus;
	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
		oiommu = iommu->iommu_dev;
		ret = omap_iopgtable_store_entry(oiommu, &e);
		if (ret) {
			dev_err(dev, "omap_iopgtable_store_entry failed: %d\n",
				ret);
			break;
		}
	}

	if (ret) {
		while (i--) {
			iommu--;
			oiommu = iommu->iommu_dev;
			iopgtable_clear_entry(oiommu, da);
		}
	}

	return ret;
}

static size_t omap_iommu_unmap(struct iommu_domain *domain, unsigned long da,
			       size_t size)
{
	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
	struct device *dev = omap_domain->dev;
	struct omap_iommu_device *iommu;
	struct omap_iommu *oiommu;
	bool error = false;
	size_t bytes = 0;
	int i;

	dev_dbg(dev, "unmapping da 0x%lx size %u\n", da, size);

	iommu = omap_domain->iommus;
	for (i = 0; i < omap_domain->num_iommus; i++, iommu++) {
		oiommu = iommu->iommu_dev;
		bytes = iopgtable_clear_entry(oiommu, da);
		if (!bytes)
			error = true;
	}

	/*
	 * simplify return - we are only checking if any of the iommus
	 * reported an error, but not if all of them are unmapping the
	 * same number of entries. This should not occur due to the
	 * mirror programming.
	 */
	return error ? 0 : bytes;
}

static int omap_iommu_count(struct device *dev)
{
	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
	int count = 0;

	while (arch_data->iommu_dev) {
		count++;
		arch_data++;
	}

	return count;
}

/* caller should call cleanup if this function fails */
static int omap_iommu_attach_init(struct device *dev,
				  struct omap_iommu_domain *odomain)
{
	struct omap_iommu_device *iommu;
	int i;

	odomain->num_iommus = omap_iommu_count(dev);
	if (!odomain->num_iommus)
		return -EINVAL;

	odomain->iommus = kcalloc(odomain->num_iommus, sizeof(*iommu),
				  GFP_ATOMIC);
	if (!odomain->iommus)
		return -ENOMEM;

	iommu = odomain->iommus;
	for (i = 0; i < odomain->num_iommus; i++, iommu++) {
		iommu->pgtable = kzalloc(IOPGD_TABLE_SIZE, GFP_ATOMIC);
		if (!iommu->pgtable)
			return -ENOMEM;

		/*
		 * should never fail, but please keep this around to ensure
		 * we keep the hardware happy
		 */
		if (WARN_ON(!IS_ALIGNED((long)iommu->pgtable,
					IOPGD_TABLE_SIZE)))
			return -EINVAL;
	}

	return 0;
}

static void omap_iommu_detach_fini(struct omap_iommu_domain *odomain)
{
	int i;
	struct omap_iommu_device *iommu = odomain->iommus;

	for (i = 0; iommu && i < odomain->num_iommus; i++, iommu++)
		kfree(iommu->pgtable);

	kfree(odomain->iommus);
	odomain->num_iommus = 0;
	odomain->iommus = NULL;
}

static int
omap_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
	struct omap_iommu_device *iommu;
	struct omap_iommu *oiommu;
	int ret = 0;
	int i;

	if (!arch_data || !arch_data->iommu_dev) {
		dev_err(dev, "device doesn't have an associated iommu\n");
		return -EINVAL;
	}

	spin_lock(&omap_domain->lock);

	/* only a single client device can be attached to a domain */
	if (omap_domain->dev) {
		dev_err(dev, "iommu domain is already attached\n");
		ret = -EBUSY;
		goto out;
	}

	ret = omap_iommu_attach_init(dev, omap_domain);
	if (ret) {
		dev_err(dev, "failed to allocate required iommu data %d\n",
			ret);
		goto init_fail;
	}

	iommu = omap_domain->iommus;
	for (i = 0; i < omap_domain->num_iommus; i++, iommu++, arch_data++) {
		/* configure and enable the omap iommu */
		oiommu = arch_data->iommu_dev;
		ret = omap_iommu_attach(oiommu, iommu->pgtable);
		if (ret) {
			dev_err(dev, "can't get omap iommu: %d\n", ret);
			goto attach_fail;
		}

		oiommu->domain = domain;
		iommu->iommu_dev = oiommu;
	}

	omap_domain->dev = dev;

	goto out;

attach_fail:
	while (i--) {
		iommu--;
		arch_data--;
		oiommu = iommu->iommu_dev;
		omap_iommu_detach(oiommu);
		iommu->iommu_dev = NULL;
		oiommu->domain = NULL;
	}
init_fail:
	omap_iommu_detach_fini(omap_domain);
out:
	spin_unlock(&omap_domain->lock);
	return ret;
}

static void _omap_iommu_detach_dev(struct omap_iommu_domain *omap_domain,
				   struct device *dev)
{
	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
	struct omap_iommu_device *iommu = omap_domain->iommus;
	struct omap_iommu *oiommu;
	int i;

	if (!omap_domain->dev) {
		dev_err(dev, "domain has no attached device\n");
		return;
	}

	/* only a single device is supported per domain for now */
	if (omap_domain->dev != dev) {
		dev_err(dev, "invalid attached device\n");
		return;
	}

	/*
	 * cleanup in the reverse order of attachment - this addresses
	 * any h/w dependencies between multiple instances, if any
	 */
	iommu += (omap_domain->num_iommus - 1);
	arch_data += (omap_domain->num_iommus - 1);
	for (i = 0; i < omap_domain->num_iommus; i++, iommu--, arch_data--) {
		oiommu = iommu->iommu_dev;
		iopgtable_clear_entry_all(oiommu);

		omap_iommu_detach(oiommu);
		iommu->iommu_dev = NULL;
		oiommu->domain = NULL;
	}

	omap_iommu_detach_fini(omap_domain);

	omap_domain->dev = NULL;
}

static void omap_iommu_detach_dev(struct iommu_domain *domain,
				  struct device *dev)
{
	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);

	spin_lock(&omap_domain->lock);
	_omap_iommu_detach_dev(omap_domain, dev);
	spin_unlock(&omap_domain->lock);
}

static struct iommu_domain *omap_iommu_domain_alloc(unsigned type)
{
	struct omap_iommu_domain *omap_domain;

	if (type != IOMMU_DOMAIN_UNMANAGED)
		return NULL;

	omap_domain = kzalloc(sizeof(*omap_domain), GFP_KERNEL);
	if (!omap_domain)
		return NULL;

	spin_lock_init(&omap_domain->lock);

	omap_domain->domain.geometry.aperture_start = 0;
	omap_domain->domain.geometry.aperture_end   = (1ULL << 32) - 1;
	omap_domain->domain.geometry.force_aperture = true;

	return &omap_domain->domain;
}

static void omap_iommu_domain_free(struct iommu_domain *domain)
{
	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);

	/*
	 * An iommu device is still attached
	 * (currently, only one device can be attached) ?
	 */
	if (omap_domain->dev)
		_omap_iommu_detach_dev(omap_domain, omap_domain->dev);

	kfree(omap_domain);
}

static phys_addr_t omap_iommu_iova_to_phys(struct iommu_domain *domain,
					   dma_addr_t da)
{
	struct omap_iommu_domain *omap_domain = to_omap_domain(domain);
	struct omap_iommu_device *iommu = omap_domain->iommus;
	struct omap_iommu *oiommu = iommu->iommu_dev;
	struct device *dev = oiommu->dev;
	u32 *pgd, *pte;
	phys_addr_t ret = 0;

	/*
	 * all the iommus within the domain will have identical programming,
	 * so perform the lookup using just the first iommu
	 */
	iopgtable_lookup_entry(oiommu, da, &pgd, &pte);

	if (pte) {
		if (iopte_is_small(*pte))
			ret = omap_iommu_translate(*pte, da, IOPTE_MASK);
		else if (iopte_is_large(*pte))
			ret = omap_iommu_translate(*pte, da, IOLARGE_MASK);
		else
			dev_err(dev, "bogus pte 0x%x, da 0x%llx", *pte,
				(unsigned long long)da);
	} else {
		if (iopgd_is_section(*pgd))
			ret = omap_iommu_translate(*pgd, da, IOSECTION_MASK);
		else if (iopgd_is_super(*pgd))
			ret = omap_iommu_translate(*pgd, da, IOSUPER_MASK);
		else
			dev_err(dev, "bogus pgd 0x%x, da 0x%llx", *pgd,
				(unsigned long long)da);
	}

	return ret;
}

static int omap_iommu_add_device(struct device *dev)
{
	struct omap_iommu_arch_data *arch_data, *tmp;
	struct omap_iommu *oiommu;
	struct iommu_group *group;
	struct device_node *np;
	struct platform_device *pdev;
	int num_iommus, i;
	int ret;

	/*
	 * Allocate the archdata iommu structure for DT-based devices.
	 *
	 * TODO: Simplify this when removing non-DT support completely from the
	 * IOMMU users.
	 */
	if (!dev->of_node)
		return 0;

	/*
	 * retrieve the count of IOMMU nodes using phandle size as element size
	 * since #iommu-cells = 0 for OMAP
	 */
	num_iommus = of_property_count_elems_of_size(dev->of_node, "iommus",
						     sizeof(phandle));
	if (num_iommus < 0)
		return 0;

	arch_data = kcalloc(num_iommus + 1, sizeof(*arch_data), GFP_KERNEL);
	if (!arch_data)
		return -ENOMEM;

	for (i = 0, tmp = arch_data; i < num_iommus; i++, tmp++) {
		np = of_parse_phandle(dev->of_node, "iommus", i);
		if (!np) {
			kfree(arch_data);
			return -EINVAL;
		}

		pdev = of_find_device_by_node(np);
		if (WARN_ON(!pdev)) {
			of_node_put(np);
			kfree(arch_data);
			return -EINVAL;
		}

		oiommu = platform_get_drvdata(pdev);
		if (!oiommu) {
			of_node_put(np);
			kfree(arch_data);
			return -EINVAL;
		}

		tmp->iommu_dev = oiommu;

		of_node_put(np);
	}

	/*
	 * use the first IOMMU alone for the sysfs device linking.
	 * TODO: Evaluate if a single iommu_group needs to be
	 * maintained for both IOMMUs
	 */
	oiommu = arch_data->iommu_dev;
	ret = iommu_device_link(&oiommu->iommu, dev);
	if (ret) {
		kfree(arch_data);
		return ret;
	}

	dev->archdata.iommu = arch_data;

	/*
	 * IOMMU group initialization calls into omap_iommu_device_group, which
	 * needs a valid dev->archdata.iommu pointer
	 */
	group = iommu_group_get_for_dev(dev);
	if (IS_ERR(group)) {
		iommu_device_unlink(&oiommu->iommu, dev);
		dev->archdata.iommu = NULL;
		kfree(arch_data);
		return PTR_ERR(group);
	}
	iommu_group_put(group);

	return 0;
}

static void omap_iommu_remove_device(struct device *dev)
{
	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;

	if (!dev->of_node || !arch_data)
		return;

	iommu_device_unlink(&arch_data->iommu_dev->iommu, dev);
	iommu_group_remove_device(dev);

	dev->archdata.iommu = NULL;
	kfree(arch_data);

}

static struct iommu_group *omap_iommu_device_group(struct device *dev)
{
	struct omap_iommu_arch_data *arch_data = dev->archdata.iommu;
	struct iommu_group *group = ERR_PTR(-EINVAL);

	if (arch_data->iommu_dev)
		group = iommu_group_ref_get(arch_data->iommu_dev->group);

	return group;
}

static const struct iommu_ops omap_iommu_ops = {
	.domain_alloc	= omap_iommu_domain_alloc,
	.domain_free	= omap_iommu_domain_free,
	.attach_dev	= omap_iommu_attach_dev,
	.detach_dev	= omap_iommu_detach_dev,
	.map		= omap_iommu_map,
	.unmap		= omap_iommu_unmap,
	.map_sg		= default_iommu_map_sg,
	.iova_to_phys	= omap_iommu_iova_to_phys,
	.add_device	= omap_iommu_add_device,
	.remove_device	= omap_iommu_remove_device,
	.device_group	= omap_iommu_device_group,
	.pgsize_bitmap	= OMAP_IOMMU_PGSIZES,
};

static int __init omap_iommu_init(void)
{
	struct kmem_cache *p;
	const unsigned long flags = SLAB_HWCACHE_ALIGN;
	size_t align = 1 << 10; /* L2 pagetable alignement */
	struct device_node *np;
	int ret;

	np = of_find_matching_node(NULL, omap_iommu_of_match);
	if (!np)
		return 0;

	of_node_put(np);

	p = kmem_cache_create("iopte_cache", IOPTE_TABLE_SIZE, align, flags,
			      NULL);
	if (!p)
		return -ENOMEM;
	iopte_cachep = p;

	omap_iommu_debugfs_init();

	ret = platform_driver_register(&omap_iommu_driver);
	if (ret) {
		pr_err("%s: failed to register driver\n", __func__);
		goto fail_driver;
	}

	ret = bus_set_iommu(&platform_bus_type, &omap_iommu_ops);
	if (ret)
		goto fail_bus;

	return 0;

fail_bus:
	platform_driver_unregister(&omap_iommu_driver);
fail_driver:
	kmem_cache_destroy(iopte_cachep);
	return ret;
}
subsys_initcall(omap_iommu_init);
/* must be ready before omap3isp is probed */