summaryrefslogtreecommitdiff
path: root/drivers/iommu/rockchip-iommu.c
blob: 4054030c32379533eca2e96003016a8a6a51481a (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * IOMMU API for Rockchip
 *
 * Module Authors:	Simon Xue <xxm@rock-chips.com>
 *			Daniel Kurtz <djkurtz@chromium.org>
 */

#include <linux/clk.h>
#include <linux/compiler.h>
#include <linux/delay.h>
#include <linux/device.h>
#include <linux/dma-mapping.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/of.h>
#include <linux/of_platform.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/slab.h>
#include <linux/spinlock.h>

/** MMU register offsets */
#define RK_MMU_DTE_ADDR		0x00	/* Directory table address */
#define RK_MMU_STATUS		0x04
#define RK_MMU_COMMAND		0x08
#define RK_MMU_PAGE_FAULT_ADDR	0x0C	/* IOVA of last page fault */
#define RK_MMU_ZAP_ONE_LINE	0x10	/* Shootdown one IOTLB entry */
#define RK_MMU_INT_RAWSTAT	0x14	/* IRQ status ignoring mask */
#define RK_MMU_INT_CLEAR	0x18	/* Acknowledge and re-arm irq */
#define RK_MMU_INT_MASK		0x1C	/* IRQ enable */
#define RK_MMU_INT_STATUS	0x20	/* IRQ status after masking */
#define RK_MMU_AUTO_GATING	0x24

#define DTE_ADDR_DUMMY		0xCAFEBABE

#define RK_MMU_POLL_PERIOD_US		100
#define RK_MMU_FORCE_RESET_TIMEOUT_US	100000
#define RK_MMU_POLL_TIMEOUT_US		1000

/* RK_MMU_STATUS fields */
#define RK_MMU_STATUS_PAGING_ENABLED       BIT(0)
#define RK_MMU_STATUS_PAGE_FAULT_ACTIVE    BIT(1)
#define RK_MMU_STATUS_STALL_ACTIVE         BIT(2)
#define RK_MMU_STATUS_IDLE                 BIT(3)
#define RK_MMU_STATUS_REPLAY_BUFFER_EMPTY  BIT(4)
#define RK_MMU_STATUS_PAGE_FAULT_IS_WRITE  BIT(5)
#define RK_MMU_STATUS_STALL_NOT_ACTIVE     BIT(31)

/* RK_MMU_COMMAND command values */
#define RK_MMU_CMD_ENABLE_PAGING    0  /* Enable memory translation */
#define RK_MMU_CMD_DISABLE_PAGING   1  /* Disable memory translation */
#define RK_MMU_CMD_ENABLE_STALL     2  /* Stall paging to allow other cmds */
#define RK_MMU_CMD_DISABLE_STALL    3  /* Stop stall re-enables paging */
#define RK_MMU_CMD_ZAP_CACHE        4  /* Shoot down entire IOTLB */
#define RK_MMU_CMD_PAGE_FAULT_DONE  5  /* Clear page fault */
#define RK_MMU_CMD_FORCE_RESET      6  /* Reset all registers */

/* RK_MMU_INT_* register fields */
#define RK_MMU_IRQ_PAGE_FAULT    0x01  /* page fault */
#define RK_MMU_IRQ_BUS_ERROR     0x02  /* bus read error */
#define RK_MMU_IRQ_MASK          (RK_MMU_IRQ_PAGE_FAULT | RK_MMU_IRQ_BUS_ERROR)

#define NUM_DT_ENTRIES 1024
#define NUM_PT_ENTRIES 1024

#define SPAGE_ORDER 12
#define SPAGE_SIZE (1 << SPAGE_ORDER)

 /*
  * Support mapping any size that fits in one page table:
  *   4 KiB to 4 MiB
  */
#define RK_IOMMU_PGSIZE_BITMAP 0x007ff000

struct rk_iommu_domain {
	struct list_head iommus;
	u32 *dt; /* page directory table */
	dma_addr_t dt_dma;
	spinlock_t iommus_lock; /* lock for iommus list */
	spinlock_t dt_lock; /* lock for modifying page directory table */

	struct iommu_domain domain;
};

/* list of clocks required by IOMMU */
static const char * const rk_iommu_clocks[] = {
	"aclk", "iface",
};

struct rk_iommu_ops {
	phys_addr_t (*pt_address)(u32 dte);
	u32 (*mk_dtentries)(dma_addr_t pt_dma);
	u32 (*mk_ptentries)(phys_addr_t page, int prot);
	phys_addr_t (*dte_addr_phys)(u32 addr);
	u32 (*dma_addr_dte)(dma_addr_t dt_dma);
	u64 dma_bit_mask;
};

struct rk_iommu {
	struct device *dev;
	void __iomem **bases;
	int num_mmu;
	int num_irq;
	struct clk_bulk_data *clocks;
	int num_clocks;
	bool reset_disabled;
	struct iommu_device iommu;
	struct list_head node; /* entry in rk_iommu_domain.iommus */
	struct iommu_domain *domain; /* domain to which iommu is attached */
	struct iommu_group *group;
};

struct rk_iommudata {
	struct device_link *link; /* runtime PM link from IOMMU to master */
	struct rk_iommu *iommu;
};

static struct device *dma_dev;
static const struct rk_iommu_ops *rk_ops;
static struct iommu_domain rk_identity_domain;

static inline void rk_table_flush(struct rk_iommu_domain *dom, dma_addr_t dma,
				  unsigned int count)
{
	size_t size = count * sizeof(u32); /* count of u32 entry */

	dma_sync_single_for_device(dma_dev, dma, size, DMA_TO_DEVICE);
}

static struct rk_iommu_domain *to_rk_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct rk_iommu_domain, domain);
}

/*
 * The Rockchip rk3288 iommu uses a 2-level page table.
 * The first level is the "Directory Table" (DT).
 * The DT consists of 1024 4-byte Directory Table Entries (DTEs), each pointing
 * to a "Page Table".
 * The second level is the 1024 Page Tables (PT).
 * Each PT consists of 1024 4-byte Page Table Entries (PTEs), each pointing to
 * a 4 KB page of physical memory.
 *
 * The DT and each PT fits in a single 4 KB page (4-bytes * 1024 entries).
 * Each iommu device has a MMU_DTE_ADDR register that contains the physical
 * address of the start of the DT page.
 *
 * The structure of the page table is as follows:
 *
 *                   DT
 * MMU_DTE_ADDR -> +-----+
 *                 |     |
 *                 +-----+     PT
 *                 | DTE | -> +-----+
 *                 +-----+    |     |     Memory
 *                 |     |    +-----+     Page
 *                 |     |    | PTE | -> +-----+
 *                 +-----+    +-----+    |     |
 *                            |     |    |     |
 *                            |     |    |     |
 *                            +-----+    |     |
 *                                       |     |
 *                                       |     |
 *                                       +-----+
 */

/*
 * Each DTE has a PT address and a valid bit:
 * +---------------------+-----------+-+
 * | PT address          | Reserved  |V|
 * +---------------------+-----------+-+
 *  31:12 - PT address (PTs always starts on a 4 KB boundary)
 *  11: 1 - Reserved
 *      0 - 1 if PT @ PT address is valid
 */
#define RK_DTE_PT_ADDRESS_MASK    0xfffff000
#define RK_DTE_PT_VALID           BIT(0)

static inline phys_addr_t rk_dte_pt_address(u32 dte)
{
	return (phys_addr_t)dte & RK_DTE_PT_ADDRESS_MASK;
}

/*
 * In v2:
 * 31:12 - PT address bit 31:0
 * 11: 8 - PT address bit 35:32
 *  7: 4 - PT address bit 39:36
 *  3: 1 - Reserved
 *     0 - 1 if PT @ PT address is valid
 */
#define RK_DTE_PT_ADDRESS_MASK_V2 GENMASK_ULL(31, 4)
#define DTE_HI_MASK1	GENMASK(11, 8)
#define DTE_HI_MASK2	GENMASK(7, 4)
#define DTE_HI_SHIFT1	24 /* shift bit 8 to bit 32 */
#define DTE_HI_SHIFT2	32 /* shift bit 4 to bit 36 */
#define PAGE_DESC_HI_MASK1	GENMASK_ULL(35, 32)
#define PAGE_DESC_HI_MASK2	GENMASK_ULL(39, 36)

static inline phys_addr_t rk_dte_pt_address_v2(u32 dte)
{
	u64 dte_v2 = dte;

	dte_v2 = ((dte_v2 & DTE_HI_MASK2) << DTE_HI_SHIFT2) |
		 ((dte_v2 & DTE_HI_MASK1) << DTE_HI_SHIFT1) |
		 (dte_v2 & RK_DTE_PT_ADDRESS_MASK);

	return (phys_addr_t)dte_v2;
}

static inline bool rk_dte_is_pt_valid(u32 dte)
{
	return dte & RK_DTE_PT_VALID;
}

static inline u32 rk_mk_dte(dma_addr_t pt_dma)
{
	return (pt_dma & RK_DTE_PT_ADDRESS_MASK) | RK_DTE_PT_VALID;
}

static inline u32 rk_mk_dte_v2(dma_addr_t pt_dma)
{
	pt_dma = (pt_dma & RK_DTE_PT_ADDRESS_MASK) |
		 ((pt_dma & PAGE_DESC_HI_MASK1) >> DTE_HI_SHIFT1) |
		 (pt_dma & PAGE_DESC_HI_MASK2) >> DTE_HI_SHIFT2;

	return (pt_dma & RK_DTE_PT_ADDRESS_MASK_V2) | RK_DTE_PT_VALID;
}

/*
 * Each PTE has a Page address, some flags and a valid bit:
 * +---------------------+---+-------+-+
 * | Page address        |Rsv| Flags |V|
 * +---------------------+---+-------+-+
 *  31:12 - Page address (Pages always start on a 4 KB boundary)
 *  11: 9 - Reserved
 *   8: 1 - Flags
 *      8 - Read allocate - allocate cache space on read misses
 *      7 - Read cache - enable cache & prefetch of data
 *      6 - Write buffer - enable delaying writes on their way to memory
 *      5 - Write allocate - allocate cache space on write misses
 *      4 - Write cache - different writes can be merged together
 *      3 - Override cache attributes
 *          if 1, bits 4-8 control cache attributes
 *          if 0, the system bus defaults are used
 *      2 - Writable
 *      1 - Readable
 *      0 - 1 if Page @ Page address is valid
 */
#define RK_PTE_PAGE_ADDRESS_MASK  0xfffff000
#define RK_PTE_PAGE_FLAGS_MASK    0x000001fe
#define RK_PTE_PAGE_WRITABLE      BIT(2)
#define RK_PTE_PAGE_READABLE      BIT(1)
#define RK_PTE_PAGE_VALID         BIT(0)

static inline bool rk_pte_is_page_valid(u32 pte)
{
	return pte & RK_PTE_PAGE_VALID;
}

/* TODO: set cache flags per prot IOMMU_CACHE */
static u32 rk_mk_pte(phys_addr_t page, int prot)
{
	u32 flags = 0;
	flags |= (prot & IOMMU_READ) ? RK_PTE_PAGE_READABLE : 0;
	flags |= (prot & IOMMU_WRITE) ? RK_PTE_PAGE_WRITABLE : 0;
	page &= RK_PTE_PAGE_ADDRESS_MASK;
	return page | flags | RK_PTE_PAGE_VALID;
}

/*
 * In v2:
 * 31:12 - Page address bit 31:0
 *  11:9 - Page address bit 34:32
 *   8:4 - Page address bit 39:35
 *     3 - Security
 *     2 - Writable
 *     1 - Readable
 *     0 - 1 if Page @ Page address is valid
 */

static u32 rk_mk_pte_v2(phys_addr_t page, int prot)
{
	u32 flags = 0;

	flags |= (prot & IOMMU_READ) ? RK_PTE_PAGE_READABLE : 0;
	flags |= (prot & IOMMU_WRITE) ? RK_PTE_PAGE_WRITABLE : 0;

	return rk_mk_dte_v2(page) | flags;
}

static u32 rk_mk_pte_invalid(u32 pte)
{
	return pte & ~RK_PTE_PAGE_VALID;
}

/*
 * rk3288 iova (IOMMU Virtual Address) format
 *  31       22.21       12.11          0
 * +-----------+-----------+-------------+
 * | DTE index | PTE index | Page offset |
 * +-----------+-----------+-------------+
 *  31:22 - DTE index   - index of DTE in DT
 *  21:12 - PTE index   - index of PTE in PT @ DTE.pt_address
 *  11: 0 - Page offset - offset into page @ PTE.page_address
 */
#define RK_IOVA_DTE_MASK    0xffc00000
#define RK_IOVA_DTE_SHIFT   22
#define RK_IOVA_PTE_MASK    0x003ff000
#define RK_IOVA_PTE_SHIFT   12
#define RK_IOVA_PAGE_MASK   0x00000fff
#define RK_IOVA_PAGE_SHIFT  0

static u32 rk_iova_dte_index(dma_addr_t iova)
{
	return (u32)(iova & RK_IOVA_DTE_MASK) >> RK_IOVA_DTE_SHIFT;
}

static u32 rk_iova_pte_index(dma_addr_t iova)
{
	return (u32)(iova & RK_IOVA_PTE_MASK) >> RK_IOVA_PTE_SHIFT;
}

static u32 rk_iova_page_offset(dma_addr_t iova)
{
	return (u32)(iova & RK_IOVA_PAGE_MASK) >> RK_IOVA_PAGE_SHIFT;
}

static u32 rk_iommu_read(void __iomem *base, u32 offset)
{
	return readl(base + offset);
}

static void rk_iommu_write(void __iomem *base, u32 offset, u32 value)
{
	writel(value, base + offset);
}

static void rk_iommu_command(struct rk_iommu *iommu, u32 command)
{
	int i;

	for (i = 0; i < iommu->num_mmu; i++)
		writel(command, iommu->bases[i] + RK_MMU_COMMAND);
}

static void rk_iommu_base_command(void __iomem *base, u32 command)
{
	writel(command, base + RK_MMU_COMMAND);
}
static void rk_iommu_zap_lines(struct rk_iommu *iommu, dma_addr_t iova_start,
			       size_t size)
{
	int i;
	dma_addr_t iova_end = iova_start + size;
	/*
	 * TODO(djkurtz): Figure out when it is more efficient to shootdown the
	 * entire iotlb rather than iterate over individual iovas.
	 */
	for (i = 0; i < iommu->num_mmu; i++) {
		dma_addr_t iova;

		for (iova = iova_start; iova < iova_end; iova += SPAGE_SIZE)
			rk_iommu_write(iommu->bases[i], RK_MMU_ZAP_ONE_LINE, iova);
	}
}

static bool rk_iommu_is_stall_active(struct rk_iommu *iommu)
{
	bool active = true;
	int i;

	for (i = 0; i < iommu->num_mmu; i++)
		active &= !!(rk_iommu_read(iommu->bases[i], RK_MMU_STATUS) &
					   RK_MMU_STATUS_STALL_ACTIVE);

	return active;
}

static bool rk_iommu_is_paging_enabled(struct rk_iommu *iommu)
{
	bool enable = true;
	int i;

	for (i = 0; i < iommu->num_mmu; i++)
		enable &= !!(rk_iommu_read(iommu->bases[i], RK_MMU_STATUS) &
					   RK_MMU_STATUS_PAGING_ENABLED);

	return enable;
}

static bool rk_iommu_is_reset_done(struct rk_iommu *iommu)
{
	bool done = true;
	int i;

	for (i = 0; i < iommu->num_mmu; i++)
		done &= rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR) == 0;

	return done;
}

static int rk_iommu_enable_stall(struct rk_iommu *iommu)
{
	int ret, i;
	bool val;

	if (rk_iommu_is_stall_active(iommu))
		return 0;

	/* Stall can only be enabled if paging is enabled */
	if (!rk_iommu_is_paging_enabled(iommu))
		return 0;

	rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_STALL);

	ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val,
				 val, RK_MMU_POLL_PERIOD_US,
				 RK_MMU_POLL_TIMEOUT_US);
	if (ret)
		for (i = 0; i < iommu->num_mmu; i++)
			dev_err(iommu->dev, "Enable stall request timed out, status: %#08x\n",
				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));

	return ret;
}

static int rk_iommu_disable_stall(struct rk_iommu *iommu)
{
	int ret, i;
	bool val;

	if (!rk_iommu_is_stall_active(iommu))
		return 0;

	rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_STALL);

	ret = readx_poll_timeout(rk_iommu_is_stall_active, iommu, val,
				 !val, RK_MMU_POLL_PERIOD_US,
				 RK_MMU_POLL_TIMEOUT_US);
	if (ret)
		for (i = 0; i < iommu->num_mmu; i++)
			dev_err(iommu->dev, "Disable stall request timed out, status: %#08x\n",
				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));

	return ret;
}

static int rk_iommu_enable_paging(struct rk_iommu *iommu)
{
	int ret, i;
	bool val;

	if (rk_iommu_is_paging_enabled(iommu))
		return 0;

	rk_iommu_command(iommu, RK_MMU_CMD_ENABLE_PAGING);

	ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val,
				 val, RK_MMU_POLL_PERIOD_US,
				 RK_MMU_POLL_TIMEOUT_US);
	if (ret)
		for (i = 0; i < iommu->num_mmu; i++)
			dev_err(iommu->dev, "Enable paging request timed out, status: %#08x\n",
				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));

	return ret;
}

static int rk_iommu_disable_paging(struct rk_iommu *iommu)
{
	int ret, i;
	bool val;

	if (!rk_iommu_is_paging_enabled(iommu))
		return 0;

	rk_iommu_command(iommu, RK_MMU_CMD_DISABLE_PAGING);

	ret = readx_poll_timeout(rk_iommu_is_paging_enabled, iommu, val,
				 !val, RK_MMU_POLL_PERIOD_US,
				 RK_MMU_POLL_TIMEOUT_US);
	if (ret)
		for (i = 0; i < iommu->num_mmu; i++)
			dev_err(iommu->dev, "Disable paging request timed out, status: %#08x\n",
				rk_iommu_read(iommu->bases[i], RK_MMU_STATUS));

	return ret;
}

static int rk_iommu_force_reset(struct rk_iommu *iommu)
{
	int ret, i;
	u32 dte_addr;
	bool val;

	if (iommu->reset_disabled)
		return 0;

	/*
	 * Check if register DTE_ADDR is working by writing DTE_ADDR_DUMMY
	 * and verifying that upper 5 nybbles are read back.
	 */
	for (i = 0; i < iommu->num_mmu; i++) {
		dte_addr = rk_ops->pt_address(DTE_ADDR_DUMMY);
		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, dte_addr);

		if (dte_addr != rk_iommu_read(iommu->bases[i], RK_MMU_DTE_ADDR)) {
			dev_err(iommu->dev, "Error during raw reset. MMU_DTE_ADDR is not functioning\n");
			return -EFAULT;
		}
	}

	rk_iommu_command(iommu, RK_MMU_CMD_FORCE_RESET);

	ret = readx_poll_timeout(rk_iommu_is_reset_done, iommu, val,
				 val, RK_MMU_FORCE_RESET_TIMEOUT_US,
				 RK_MMU_POLL_TIMEOUT_US);
	if (ret) {
		dev_err(iommu->dev, "FORCE_RESET command timed out\n");
		return ret;
	}

	return 0;
}

static inline phys_addr_t rk_dte_addr_phys(u32 addr)
{
	return (phys_addr_t)addr;
}

static inline u32 rk_dma_addr_dte(dma_addr_t dt_dma)
{
	return dt_dma;
}

#define DT_HI_MASK GENMASK_ULL(39, 32)
#define DTE_BASE_HI_MASK GENMASK(11, 4)
#define DT_SHIFT   28

static inline phys_addr_t rk_dte_addr_phys_v2(u32 addr)
{
	u64 addr64 = addr;
	return (phys_addr_t)(addr64 & RK_DTE_PT_ADDRESS_MASK) |
	       ((addr64 & DTE_BASE_HI_MASK) << DT_SHIFT);
}

static inline u32 rk_dma_addr_dte_v2(dma_addr_t dt_dma)
{
	return (dt_dma & RK_DTE_PT_ADDRESS_MASK) |
	       ((dt_dma & DT_HI_MASK) >> DT_SHIFT);
}

static void log_iova(struct rk_iommu *iommu, int index, dma_addr_t iova)
{
	void __iomem *base = iommu->bases[index];
	u32 dte_index, pte_index, page_offset;
	u32 mmu_dte_addr;
	phys_addr_t mmu_dte_addr_phys, dte_addr_phys;
	u32 *dte_addr;
	u32 dte;
	phys_addr_t pte_addr_phys = 0;
	u32 *pte_addr = NULL;
	u32 pte = 0;
	phys_addr_t page_addr_phys = 0;
	u32 page_flags = 0;

	dte_index = rk_iova_dte_index(iova);
	pte_index = rk_iova_pte_index(iova);
	page_offset = rk_iova_page_offset(iova);

	mmu_dte_addr = rk_iommu_read(base, RK_MMU_DTE_ADDR);
	mmu_dte_addr_phys = rk_ops->dte_addr_phys(mmu_dte_addr);

	dte_addr_phys = mmu_dte_addr_phys + (4 * dte_index);
	dte_addr = phys_to_virt(dte_addr_phys);
	dte = *dte_addr;

	if (!rk_dte_is_pt_valid(dte))
		goto print_it;

	pte_addr_phys = rk_ops->pt_address(dte) + (pte_index * 4);
	pte_addr = phys_to_virt(pte_addr_phys);
	pte = *pte_addr;

	if (!rk_pte_is_page_valid(pte))
		goto print_it;

	page_addr_phys = rk_ops->pt_address(pte) + page_offset;
	page_flags = pte & RK_PTE_PAGE_FLAGS_MASK;

print_it:
	dev_err(iommu->dev, "iova = %pad: dte_index: %#03x pte_index: %#03x page_offset: %#03x\n",
		&iova, dte_index, pte_index, page_offset);
	dev_err(iommu->dev, "mmu_dte_addr: %pa dte@%pa: %#08x valid: %u pte@%pa: %#08x valid: %u page@%pa flags: %#03x\n",
		&mmu_dte_addr_phys, &dte_addr_phys, dte,
		rk_dte_is_pt_valid(dte), &pte_addr_phys, pte,
		rk_pte_is_page_valid(pte), &page_addr_phys, page_flags);
}

static irqreturn_t rk_iommu_irq(int irq, void *dev_id)
{
	struct rk_iommu *iommu = dev_id;
	u32 status;
	u32 int_status;
	dma_addr_t iova;
	irqreturn_t ret = IRQ_NONE;
	int i, err;

	err = pm_runtime_get_if_in_use(iommu->dev);
	if (!err || WARN_ON_ONCE(err < 0))
		return ret;

	if (WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks)))
		goto out;

	for (i = 0; i < iommu->num_mmu; i++) {
		int_status = rk_iommu_read(iommu->bases[i], RK_MMU_INT_STATUS);
		if (int_status == 0)
			continue;

		ret = IRQ_HANDLED;
		iova = rk_iommu_read(iommu->bases[i], RK_MMU_PAGE_FAULT_ADDR);

		if (int_status & RK_MMU_IRQ_PAGE_FAULT) {
			int flags;

			status = rk_iommu_read(iommu->bases[i], RK_MMU_STATUS);
			flags = (status & RK_MMU_STATUS_PAGE_FAULT_IS_WRITE) ?
					IOMMU_FAULT_WRITE : IOMMU_FAULT_READ;

			dev_err(iommu->dev, "Page fault at %pad of type %s\n",
				&iova,
				(flags == IOMMU_FAULT_WRITE) ? "write" : "read");

			log_iova(iommu, i, iova);

			/*
			 * Report page fault to any installed handlers.
			 * Ignore the return code, though, since we always zap cache
			 * and clear the page fault anyway.
			 */
			if (iommu->domain != &rk_identity_domain)
				report_iommu_fault(iommu->domain, iommu->dev, iova,
						   flags);
			else
				dev_err(iommu->dev, "Page fault while iommu not attached to domain?\n");

			rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
			rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_PAGE_FAULT_DONE);
		}

		if (int_status & RK_MMU_IRQ_BUS_ERROR)
			dev_err(iommu->dev, "BUS_ERROR occurred at %pad\n", &iova);

		if (int_status & ~RK_MMU_IRQ_MASK)
			dev_err(iommu->dev, "unexpected int_status: %#08x\n",
				int_status);

		rk_iommu_write(iommu->bases[i], RK_MMU_INT_CLEAR, int_status);
	}

	clk_bulk_disable(iommu->num_clocks, iommu->clocks);

out:
	pm_runtime_put(iommu->dev);
	return ret;
}

static phys_addr_t rk_iommu_iova_to_phys(struct iommu_domain *domain,
					 dma_addr_t iova)
{
	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
	unsigned long flags;
	phys_addr_t pt_phys, phys = 0;
	u32 dte, pte;
	u32 *page_table;

	spin_lock_irqsave(&rk_domain->dt_lock, flags);

	dte = rk_domain->dt[rk_iova_dte_index(iova)];
	if (!rk_dte_is_pt_valid(dte))
		goto out;

	pt_phys = rk_ops->pt_address(dte);
	page_table = (u32 *)phys_to_virt(pt_phys);
	pte = page_table[rk_iova_pte_index(iova)];
	if (!rk_pte_is_page_valid(pte))
		goto out;

	phys = rk_ops->pt_address(pte) + rk_iova_page_offset(iova);
out:
	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);

	return phys;
}

static void rk_iommu_zap_iova(struct rk_iommu_domain *rk_domain,
			      dma_addr_t iova, size_t size)
{
	struct list_head *pos;
	unsigned long flags;

	/* shootdown these iova from all iommus using this domain */
	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
	list_for_each(pos, &rk_domain->iommus) {
		struct rk_iommu *iommu;
		int ret;

		iommu = list_entry(pos, struct rk_iommu, node);

		/* Only zap TLBs of IOMMUs that are powered on. */
		ret = pm_runtime_get_if_in_use(iommu->dev);
		if (WARN_ON_ONCE(ret < 0))
			continue;
		if (ret) {
			WARN_ON(clk_bulk_enable(iommu->num_clocks,
						iommu->clocks));
			rk_iommu_zap_lines(iommu, iova, size);
			clk_bulk_disable(iommu->num_clocks, iommu->clocks);
			pm_runtime_put(iommu->dev);
		}
	}
	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);
}

static void rk_iommu_zap_iova_first_last(struct rk_iommu_domain *rk_domain,
					 dma_addr_t iova, size_t size)
{
	rk_iommu_zap_iova(rk_domain, iova, SPAGE_SIZE);
	if (size > SPAGE_SIZE)
		rk_iommu_zap_iova(rk_domain, iova + size - SPAGE_SIZE,
					SPAGE_SIZE);
}

static u32 *rk_dte_get_page_table(struct rk_iommu_domain *rk_domain,
				  dma_addr_t iova)
{
	u32 *page_table, *dte_addr;
	u32 dte_index, dte;
	phys_addr_t pt_phys;
	dma_addr_t pt_dma;

	assert_spin_locked(&rk_domain->dt_lock);

	dte_index = rk_iova_dte_index(iova);
	dte_addr = &rk_domain->dt[dte_index];
	dte = *dte_addr;
	if (rk_dte_is_pt_valid(dte))
		goto done;

	page_table = (u32 *)get_zeroed_page(GFP_ATOMIC | GFP_DMA32);
	if (!page_table)
		return ERR_PTR(-ENOMEM);

	pt_dma = dma_map_single(dma_dev, page_table, SPAGE_SIZE, DMA_TO_DEVICE);
	if (dma_mapping_error(dma_dev, pt_dma)) {
		dev_err(dma_dev, "DMA mapping error while allocating page table\n");
		free_page((unsigned long)page_table);
		return ERR_PTR(-ENOMEM);
	}

	dte = rk_ops->mk_dtentries(pt_dma);
	*dte_addr = dte;

	rk_table_flush(rk_domain,
		       rk_domain->dt_dma + dte_index * sizeof(u32), 1);
done:
	pt_phys = rk_ops->pt_address(dte);
	return (u32 *)phys_to_virt(pt_phys);
}

static size_t rk_iommu_unmap_iova(struct rk_iommu_domain *rk_domain,
				  u32 *pte_addr, dma_addr_t pte_dma,
				  size_t size)
{
	unsigned int pte_count;
	unsigned int pte_total = size / SPAGE_SIZE;

	assert_spin_locked(&rk_domain->dt_lock);

	for (pte_count = 0; pte_count < pte_total; pte_count++) {
		u32 pte = pte_addr[pte_count];
		if (!rk_pte_is_page_valid(pte))
			break;

		pte_addr[pte_count] = rk_mk_pte_invalid(pte);
	}

	rk_table_flush(rk_domain, pte_dma, pte_count);

	return pte_count * SPAGE_SIZE;
}

static int rk_iommu_map_iova(struct rk_iommu_domain *rk_domain, u32 *pte_addr,
			     dma_addr_t pte_dma, dma_addr_t iova,
			     phys_addr_t paddr, size_t size, int prot)
{
	unsigned int pte_count;
	unsigned int pte_total = size / SPAGE_SIZE;
	phys_addr_t page_phys;

	assert_spin_locked(&rk_domain->dt_lock);

	for (pte_count = 0; pte_count < pte_total; pte_count++) {
		u32 pte = pte_addr[pte_count];

		if (rk_pte_is_page_valid(pte))
			goto unwind;

		pte_addr[pte_count] = rk_ops->mk_ptentries(paddr, prot);

		paddr += SPAGE_SIZE;
	}

	rk_table_flush(rk_domain, pte_dma, pte_total);

	/*
	 * Zap the first and last iova to evict from iotlb any previously
	 * mapped cachelines holding stale values for its dte and pte.
	 * We only zap the first and last iova, since only they could have
	 * dte or pte shared with an existing mapping.
	 */
	rk_iommu_zap_iova_first_last(rk_domain, iova, size);

	return 0;
unwind:
	/* Unmap the range of iovas that we just mapped */
	rk_iommu_unmap_iova(rk_domain, pte_addr, pte_dma,
			    pte_count * SPAGE_SIZE);

	iova += pte_count * SPAGE_SIZE;
	page_phys = rk_ops->pt_address(pte_addr[pte_count]);
	pr_err("iova: %pad already mapped to %pa cannot remap to phys: %pa prot: %#x\n",
	       &iova, &page_phys, &paddr, prot);

	return -EADDRINUSE;
}

static int rk_iommu_map(struct iommu_domain *domain, unsigned long _iova,
			phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
	unsigned long flags;
	dma_addr_t pte_dma, iova = (dma_addr_t)_iova;
	u32 *page_table, *pte_addr;
	u32 dte_index, pte_index;
	int ret;

	spin_lock_irqsave(&rk_domain->dt_lock, flags);

	/*
	 * pgsize_bitmap specifies iova sizes that fit in one page table
	 * (1024 4-KiB pages = 4 MiB).
	 * So, size will always be 4096 <= size <= 4194304.
	 * Since iommu_map() guarantees that both iova and size will be
	 * aligned, we will always only be mapping from a single dte here.
	 */
	page_table = rk_dte_get_page_table(rk_domain, iova);
	if (IS_ERR(page_table)) {
		spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
		return PTR_ERR(page_table);
	}

	dte_index = rk_domain->dt[rk_iova_dte_index(iova)];
	pte_index = rk_iova_pte_index(iova);
	pte_addr = &page_table[pte_index];

	pte_dma = rk_ops->pt_address(dte_index) + pte_index * sizeof(u32);
	ret = rk_iommu_map_iova(rk_domain, pte_addr, pte_dma, iova,
				paddr, size, prot);

	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);

	return ret;
}

static size_t rk_iommu_unmap(struct iommu_domain *domain, unsigned long _iova,
			     size_t size, struct iommu_iotlb_gather *gather)
{
	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
	unsigned long flags;
	dma_addr_t pte_dma, iova = (dma_addr_t)_iova;
	phys_addr_t pt_phys;
	u32 dte;
	u32 *pte_addr;
	size_t unmap_size;

	spin_lock_irqsave(&rk_domain->dt_lock, flags);

	/*
	 * pgsize_bitmap specifies iova sizes that fit in one page table
	 * (1024 4-KiB pages = 4 MiB).
	 * So, size will always be 4096 <= size <= 4194304.
	 * Since iommu_unmap() guarantees that both iova and size will be
	 * aligned, we will always only be unmapping from a single dte here.
	 */
	dte = rk_domain->dt[rk_iova_dte_index(iova)];
	/* Just return 0 if iova is unmapped */
	if (!rk_dte_is_pt_valid(dte)) {
		spin_unlock_irqrestore(&rk_domain->dt_lock, flags);
		return 0;
	}

	pt_phys = rk_ops->pt_address(dte);
	pte_addr = (u32 *)phys_to_virt(pt_phys) + rk_iova_pte_index(iova);
	pte_dma = pt_phys + rk_iova_pte_index(iova) * sizeof(u32);
	unmap_size = rk_iommu_unmap_iova(rk_domain, pte_addr, pte_dma, size);

	spin_unlock_irqrestore(&rk_domain->dt_lock, flags);

	/* Shootdown iotlb entries for iova range that was just unmapped */
	rk_iommu_zap_iova(rk_domain, iova, unmap_size);

	return unmap_size;
}

static struct rk_iommu *rk_iommu_from_dev(struct device *dev)
{
	struct rk_iommudata *data = dev_iommu_priv_get(dev);

	return data ? data->iommu : NULL;
}

/* Must be called with iommu powered on and attached */
static void rk_iommu_disable(struct rk_iommu *iommu)
{
	int i;

	/* Ignore error while disabling, just keep going */
	WARN_ON(clk_bulk_enable(iommu->num_clocks, iommu->clocks));
	rk_iommu_enable_stall(iommu);
	rk_iommu_disable_paging(iommu);
	for (i = 0; i < iommu->num_mmu; i++) {
		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, 0);
		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR, 0);
	}
	rk_iommu_disable_stall(iommu);
	clk_bulk_disable(iommu->num_clocks, iommu->clocks);
}

/* Must be called with iommu powered on and attached */
static int rk_iommu_enable(struct rk_iommu *iommu)
{
	struct iommu_domain *domain = iommu->domain;
	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
	int ret, i;

	ret = clk_bulk_enable(iommu->num_clocks, iommu->clocks);
	if (ret)
		return ret;

	ret = rk_iommu_enable_stall(iommu);
	if (ret)
		goto out_disable_clocks;

	ret = rk_iommu_force_reset(iommu);
	if (ret)
		goto out_disable_stall;

	for (i = 0; i < iommu->num_mmu; i++) {
		rk_iommu_write(iommu->bases[i], RK_MMU_DTE_ADDR,
			       rk_ops->dma_addr_dte(rk_domain->dt_dma));
		rk_iommu_base_command(iommu->bases[i], RK_MMU_CMD_ZAP_CACHE);
		rk_iommu_write(iommu->bases[i], RK_MMU_INT_MASK, RK_MMU_IRQ_MASK);
	}

	ret = rk_iommu_enable_paging(iommu);

out_disable_stall:
	rk_iommu_disable_stall(iommu);
out_disable_clocks:
	clk_bulk_disable(iommu->num_clocks, iommu->clocks);
	return ret;
}

static int rk_iommu_identity_attach(struct iommu_domain *identity_domain,
				    struct device *dev)
{
	struct rk_iommu *iommu;
	struct rk_iommu_domain *rk_domain;
	unsigned long flags;
	int ret;

	/* Allow 'virtual devices' (eg drm) to detach from domain */
	iommu = rk_iommu_from_dev(dev);
	if (!iommu)
		return -ENODEV;

	rk_domain = to_rk_domain(iommu->domain);

	dev_dbg(dev, "Detaching from iommu domain\n");

	if (iommu->domain == identity_domain)
		return 0;

	iommu->domain = identity_domain;

	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
	list_del_init(&iommu->node);
	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);

	ret = pm_runtime_get_if_in_use(iommu->dev);
	WARN_ON_ONCE(ret < 0);
	if (ret > 0) {
		rk_iommu_disable(iommu);
		pm_runtime_put(iommu->dev);
	}

	return 0;
}

static void rk_iommu_identity_free(struct iommu_domain *domain)
{
}

static struct iommu_domain_ops rk_identity_ops = {
	.attach_dev = rk_iommu_identity_attach,
	.free = rk_iommu_identity_free,
};

static struct iommu_domain rk_identity_domain = {
	.type = IOMMU_DOMAIN_IDENTITY,
	.ops = &rk_identity_ops,
};

#ifdef CONFIG_ARM
static void rk_iommu_set_platform_dma(struct device *dev)
{
	WARN_ON(rk_iommu_identity_attach(&rk_identity_domain, dev));
}
#endif

static int rk_iommu_attach_device(struct iommu_domain *domain,
		struct device *dev)
{
	struct rk_iommu *iommu;
	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
	unsigned long flags;
	int ret;

	/*
	 * Allow 'virtual devices' (e.g., drm) to attach to domain.
	 * Such a device does not belong to an iommu group.
	 */
	iommu = rk_iommu_from_dev(dev);
	if (!iommu)
		return 0;

	dev_dbg(dev, "Attaching to iommu domain\n");

	/* iommu already attached */
	if (iommu->domain == domain)
		return 0;

	ret = rk_iommu_identity_attach(&rk_identity_domain, dev);
	if (ret)
		return ret;

	iommu->domain = domain;

	spin_lock_irqsave(&rk_domain->iommus_lock, flags);
	list_add_tail(&iommu->node, &rk_domain->iommus);
	spin_unlock_irqrestore(&rk_domain->iommus_lock, flags);

	ret = pm_runtime_get_if_in_use(iommu->dev);
	if (!ret || WARN_ON_ONCE(ret < 0))
		return 0;

	ret = rk_iommu_enable(iommu);
	if (ret)
		WARN_ON(rk_iommu_identity_attach(&rk_identity_domain, dev));

	pm_runtime_put(iommu->dev);

	return ret;
}

static struct iommu_domain *rk_iommu_domain_alloc(unsigned type)
{
	struct rk_iommu_domain *rk_domain;

	if (type == IOMMU_DOMAIN_IDENTITY)
		return &rk_identity_domain;

	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
		return NULL;

	if (!dma_dev)
		return NULL;

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

	/*
	 * rk32xx iommus use a 2 level pagetable.
	 * Each level1 (dt) and level2 (pt) table has 1024 4-byte entries.
	 * Allocate one 4 KiB page for each table.
	 */
	rk_domain->dt = (u32 *)get_zeroed_page(GFP_KERNEL | GFP_DMA32);
	if (!rk_domain->dt)
		goto err_free_domain;

	rk_domain->dt_dma = dma_map_single(dma_dev, rk_domain->dt,
					   SPAGE_SIZE, DMA_TO_DEVICE);
	if (dma_mapping_error(dma_dev, rk_domain->dt_dma)) {
		dev_err(dma_dev, "DMA map error for DT\n");
		goto err_free_dt;
	}

	spin_lock_init(&rk_domain->iommus_lock);
	spin_lock_init(&rk_domain->dt_lock);
	INIT_LIST_HEAD(&rk_domain->iommus);

	rk_domain->domain.geometry.aperture_start = 0;
	rk_domain->domain.geometry.aperture_end   = DMA_BIT_MASK(32);
	rk_domain->domain.geometry.force_aperture = true;

	return &rk_domain->domain;

err_free_dt:
	free_page((unsigned long)rk_domain->dt);
err_free_domain:
	kfree(rk_domain);

	return NULL;
}

static void rk_iommu_domain_free(struct iommu_domain *domain)
{
	struct rk_iommu_domain *rk_domain = to_rk_domain(domain);
	int i;

	WARN_ON(!list_empty(&rk_domain->iommus));

	for (i = 0; i < NUM_DT_ENTRIES; i++) {
		u32 dte = rk_domain->dt[i];
		if (rk_dte_is_pt_valid(dte)) {
			phys_addr_t pt_phys = rk_ops->pt_address(dte);
			u32 *page_table = phys_to_virt(pt_phys);
			dma_unmap_single(dma_dev, pt_phys,
					 SPAGE_SIZE, DMA_TO_DEVICE);
			free_page((unsigned long)page_table);
		}
	}

	dma_unmap_single(dma_dev, rk_domain->dt_dma,
			 SPAGE_SIZE, DMA_TO_DEVICE);
	free_page((unsigned long)rk_domain->dt);

	kfree(rk_domain);
}

static struct iommu_device *rk_iommu_probe_device(struct device *dev)
{
	struct rk_iommudata *data;
	struct rk_iommu *iommu;

	data = dev_iommu_priv_get(dev);
	if (!data)
		return ERR_PTR(-ENODEV);

	iommu = rk_iommu_from_dev(dev);

	data->link = device_link_add(dev, iommu->dev,
				     DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);

	return &iommu->iommu;
}

static void rk_iommu_release_device(struct device *dev)
{
	struct rk_iommudata *data = dev_iommu_priv_get(dev);

	device_link_del(data->link);
}

static struct iommu_group *rk_iommu_device_group(struct device *dev)
{
	struct rk_iommu *iommu;

	iommu = rk_iommu_from_dev(dev);

	return iommu_group_ref_get(iommu->group);
}

static int rk_iommu_of_xlate(struct device *dev,
			     struct of_phandle_args *args)
{
	struct platform_device *iommu_dev;
	struct rk_iommudata *data;

	data = devm_kzalloc(dma_dev, sizeof(*data), GFP_KERNEL);
	if (!data)
		return -ENOMEM;

	iommu_dev = of_find_device_by_node(args->np);

	data->iommu = platform_get_drvdata(iommu_dev);
	data->iommu->domain = &rk_identity_domain;
	dev_iommu_priv_set(dev, data);

	platform_device_put(iommu_dev);

	return 0;
}

static const struct iommu_ops rk_iommu_ops = {
	.domain_alloc = rk_iommu_domain_alloc,
	.probe_device = rk_iommu_probe_device,
	.release_device = rk_iommu_release_device,
	.device_group = rk_iommu_device_group,
#ifdef CONFIG_ARM
	.set_platform_dma_ops = rk_iommu_set_platform_dma,
#endif
	.pgsize_bitmap = RK_IOMMU_PGSIZE_BITMAP,
	.of_xlate = rk_iommu_of_xlate,
	.default_domain_ops = &(const struct iommu_domain_ops) {
		.attach_dev	= rk_iommu_attach_device,
		.map		= rk_iommu_map,
		.unmap		= rk_iommu_unmap,
		.iova_to_phys	= rk_iommu_iova_to_phys,
		.free		= rk_iommu_domain_free,
	}
};

static int rk_iommu_probe(struct platform_device *pdev)
{
	struct device *dev = &pdev->dev;
	struct rk_iommu *iommu;
	struct resource *res;
	const struct rk_iommu_ops *ops;
	int num_res = pdev->num_resources;
	int err, i;

	iommu = devm_kzalloc(dev, sizeof(*iommu), GFP_KERNEL);
	if (!iommu)
		return -ENOMEM;

	platform_set_drvdata(pdev, iommu);
	iommu->dev = dev;
	iommu->num_mmu = 0;

	ops = of_device_get_match_data(dev);
	if (!rk_ops)
		rk_ops = ops;

	/*
	 * That should not happen unless different versions of the
	 * hardware block are embedded the same SoC
	 */
	if (WARN_ON(rk_ops != ops))
		return -EINVAL;

	iommu->bases = devm_kcalloc(dev, num_res, sizeof(*iommu->bases),
				    GFP_KERNEL);
	if (!iommu->bases)
		return -ENOMEM;

	for (i = 0; i < num_res; i++) {
		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
		if (!res)
			continue;
		iommu->bases[i] = devm_ioremap_resource(&pdev->dev, res);
		if (IS_ERR(iommu->bases[i]))
			continue;
		iommu->num_mmu++;
	}
	if (iommu->num_mmu == 0)
		return PTR_ERR(iommu->bases[0]);

	iommu->num_irq = platform_irq_count(pdev);
	if (iommu->num_irq < 0)
		return iommu->num_irq;

	iommu->reset_disabled = device_property_read_bool(dev,
					"rockchip,disable-mmu-reset");

	iommu->num_clocks = ARRAY_SIZE(rk_iommu_clocks);
	iommu->clocks = devm_kcalloc(iommu->dev, iommu->num_clocks,
				     sizeof(*iommu->clocks), GFP_KERNEL);
	if (!iommu->clocks)
		return -ENOMEM;

	for (i = 0; i < iommu->num_clocks; ++i)
		iommu->clocks[i].id = rk_iommu_clocks[i];

	/*
	 * iommu clocks should be present for all new devices and devicetrees
	 * but there are older devicetrees without clocks out in the wild.
	 * So clocks as optional for the time being.
	 */
	err = devm_clk_bulk_get(iommu->dev, iommu->num_clocks, iommu->clocks);
	if (err == -ENOENT)
		iommu->num_clocks = 0;
	else if (err)
		return err;

	err = clk_bulk_prepare(iommu->num_clocks, iommu->clocks);
	if (err)
		return err;

	iommu->group = iommu_group_alloc();
	if (IS_ERR(iommu->group)) {
		err = PTR_ERR(iommu->group);
		goto err_unprepare_clocks;
	}

	err = iommu_device_sysfs_add(&iommu->iommu, dev, NULL, dev_name(dev));
	if (err)
		goto err_put_group;

	err = iommu_device_register(&iommu->iommu, &rk_iommu_ops, dev);
	if (err)
		goto err_remove_sysfs;

	/*
	 * Use the first registered IOMMU device for domain to use with DMA
	 * API, since a domain might not physically correspond to a single
	 * IOMMU device..
	 */
	if (!dma_dev)
		dma_dev = &pdev->dev;

	pm_runtime_enable(dev);

	for (i = 0; i < iommu->num_irq; i++) {
		int irq = platform_get_irq(pdev, i);

		if (irq < 0) {
			err = irq;
			goto err_pm_disable;
		}

		err = devm_request_irq(iommu->dev, irq, rk_iommu_irq,
				       IRQF_SHARED, dev_name(dev), iommu);
		if (err)
			goto err_pm_disable;
	}

	dma_set_mask_and_coherent(dev, rk_ops->dma_bit_mask);

	return 0;
err_pm_disable:
	pm_runtime_disable(dev);
err_remove_sysfs:
	iommu_device_sysfs_remove(&iommu->iommu);
err_put_group:
	iommu_group_put(iommu->group);
err_unprepare_clocks:
	clk_bulk_unprepare(iommu->num_clocks, iommu->clocks);
	return err;
}

static void rk_iommu_shutdown(struct platform_device *pdev)
{
	struct rk_iommu *iommu = platform_get_drvdata(pdev);
	int i;

	for (i = 0; i < iommu->num_irq; i++) {
		int irq = platform_get_irq(pdev, i);

		devm_free_irq(iommu->dev, irq, iommu);
	}

	pm_runtime_force_suspend(&pdev->dev);
}

static int __maybe_unused rk_iommu_suspend(struct device *dev)
{
	struct rk_iommu *iommu = dev_get_drvdata(dev);

	if (iommu->domain == &rk_identity_domain)
		return 0;

	rk_iommu_disable(iommu);
	return 0;
}

static int __maybe_unused rk_iommu_resume(struct device *dev)
{
	struct rk_iommu *iommu = dev_get_drvdata(dev);

	if (iommu->domain == &rk_identity_domain)
		return 0;

	return rk_iommu_enable(iommu);
}

static const struct dev_pm_ops rk_iommu_pm_ops = {
	SET_RUNTIME_PM_OPS(rk_iommu_suspend, rk_iommu_resume, NULL)
	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
				pm_runtime_force_resume)
};

static struct rk_iommu_ops iommu_data_ops_v1 = {
	.pt_address = &rk_dte_pt_address,
	.mk_dtentries = &rk_mk_dte,
	.mk_ptentries = &rk_mk_pte,
	.dte_addr_phys = &rk_dte_addr_phys,
	.dma_addr_dte = &rk_dma_addr_dte,
	.dma_bit_mask = DMA_BIT_MASK(32),
};

static struct rk_iommu_ops iommu_data_ops_v2 = {
	.pt_address = &rk_dte_pt_address_v2,
	.mk_dtentries = &rk_mk_dte_v2,
	.mk_ptentries = &rk_mk_pte_v2,
	.dte_addr_phys = &rk_dte_addr_phys_v2,
	.dma_addr_dte = &rk_dma_addr_dte_v2,
	.dma_bit_mask = DMA_BIT_MASK(40),
};

static const struct of_device_id rk_iommu_dt_ids[] = {
	{	.compatible = "rockchip,iommu",
		.data = &iommu_data_ops_v1,
	},
	{	.compatible = "rockchip,rk3568-iommu",
		.data = &iommu_data_ops_v2,
	},
	{ /* sentinel */ }
};

static struct platform_driver rk_iommu_driver = {
	.probe = rk_iommu_probe,
	.shutdown = rk_iommu_shutdown,
	.driver = {
		   .name = "rk_iommu",
		   .of_match_table = rk_iommu_dt_ids,
		   .pm = &rk_iommu_pm_ops,
		   .suppress_bind_attrs = true,
	},
};
builtin_platform_driver(rk_iommu_driver);