summaryrefslogtreecommitdiff
path: root/drivers/iommu/mtk_iommu.c
blob: 7383a5df602174b6d8d91ceb7b1d464f8fd88069 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (c) 2015-2016 MediaTek Inc.
 * Author: Yong Wu <yong.wu@mediatek.com>
 */
#include <linux/bitfield.h>
#include <linux/bug.h>
#include <linux/clk.h>
#include <linux/component.h>
#include <linux/device.h>
#include <linux/dma-direct.h>
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/list.h>
#include <linux/mfd/syscon.h>
#include <linux/module.h>
#include <linux/of_address.h>
#include <linux/of_irq.h>
#include <linux/of_platform.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
#include <linux/regmap.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/soc/mediatek/infracfg.h>
#include <asm/barrier.h>
#include <soc/mediatek/smi.h>

#include "mtk_iommu.h"

#define REG_MMU_PT_BASE_ADDR			0x000
#define MMU_PT_ADDR_MASK			GENMASK(31, 7)

#define REG_MMU_INVALIDATE			0x020
#define F_ALL_INVLD				0x2
#define F_MMU_INV_RANGE				0x1

#define REG_MMU_INVLD_START_A			0x024
#define REG_MMU_INVLD_END_A			0x028

#define REG_MMU_INV_SEL_GEN2			0x02c
#define REG_MMU_INV_SEL_GEN1			0x038
#define F_INVLD_EN0				BIT(0)
#define F_INVLD_EN1				BIT(1)

#define REG_MMU_MISC_CTRL			0x048
#define F_MMU_IN_ORDER_WR_EN_MASK		(BIT(1) | BIT(17))
#define F_MMU_STANDARD_AXI_MODE_MASK		(BIT(3) | BIT(19))

#define REG_MMU_DCM_DIS				0x050
#define F_MMU_DCM				BIT(8)

#define REG_MMU_WR_LEN_CTRL			0x054
#define F_MMU_WR_THROT_DIS_MASK			(BIT(5) | BIT(21))

#define REG_MMU_CTRL_REG			0x110
#define F_MMU_TF_PROT_TO_PROGRAM_ADDR		(2 << 4)
#define F_MMU_PREFETCH_RT_REPLACE_MOD		BIT(4)
#define F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173	(2 << 5)

#define REG_MMU_IVRP_PADDR			0x114

#define REG_MMU_VLD_PA_RNG			0x118
#define F_MMU_VLD_PA_RNG(EA, SA)		(((EA) << 8) | (SA))

#define REG_MMU_INT_CONTROL0			0x120
#define F_L2_MULIT_HIT_EN			BIT(0)
#define F_TABLE_WALK_FAULT_INT_EN		BIT(1)
#define F_PREETCH_FIFO_OVERFLOW_INT_EN		BIT(2)
#define F_MISS_FIFO_OVERFLOW_INT_EN		BIT(3)
#define F_PREFETCH_FIFO_ERR_INT_EN		BIT(5)
#define F_MISS_FIFO_ERR_INT_EN			BIT(6)
#define F_INT_CLR_BIT				BIT(12)

#define REG_MMU_INT_MAIN_CONTROL		0x124
						/* mmu0 | mmu1 */
#define F_INT_TRANSLATION_FAULT			(BIT(0) | BIT(7))
#define F_INT_MAIN_MULTI_HIT_FAULT		(BIT(1) | BIT(8))
#define F_INT_INVALID_PA_FAULT			(BIT(2) | BIT(9))
#define F_INT_ENTRY_REPLACEMENT_FAULT		(BIT(3) | BIT(10))
#define F_INT_TLB_MISS_FAULT			(BIT(4) | BIT(11))
#define F_INT_MISS_TRANSACTION_FIFO_FAULT	(BIT(5) | BIT(12))
#define F_INT_PRETETCH_TRANSATION_FIFO_FAULT	(BIT(6) | BIT(13))

#define REG_MMU_CPE_DONE			0x12C

#define REG_MMU_FAULT_ST1			0x134
#define F_REG_MMU0_FAULT_MASK			GENMASK(6, 0)
#define F_REG_MMU1_FAULT_MASK			GENMASK(13, 7)

#define REG_MMU0_FAULT_VA			0x13c
#define F_MMU_INVAL_VA_31_12_MASK		GENMASK(31, 12)
#define F_MMU_INVAL_VA_34_32_MASK		GENMASK(11, 9)
#define F_MMU_INVAL_PA_34_32_MASK		GENMASK(8, 6)
#define F_MMU_FAULT_VA_WRITE_BIT		BIT(1)
#define F_MMU_FAULT_VA_LAYER_BIT		BIT(0)

#define REG_MMU0_INVLD_PA			0x140
#define REG_MMU1_FAULT_VA			0x144
#define REG_MMU1_INVLD_PA			0x148
#define REG_MMU0_INT_ID				0x150
#define REG_MMU1_INT_ID				0x154
#define F_MMU_INT_ID_COMM_ID(a)			(((a) >> 9) & 0x7)
#define F_MMU_INT_ID_SUB_COMM_ID(a)		(((a) >> 7) & 0x3)
#define F_MMU_INT_ID_COMM_ID_EXT(a)		(((a) >> 10) & 0x7)
#define F_MMU_INT_ID_SUB_COMM_ID_EXT(a)		(((a) >> 7) & 0x7)
#define F_MMU_INT_ID_LARB_ID(a)			(((a) >> 7) & 0x7)
#define F_MMU_INT_ID_PORT_ID(a)			(((a) >> 2) & 0x1f)

#define MTK_PROTECT_PA_ALIGN			256

#define PERICFG_IOMMU_1				0x714

#define HAS_4GB_MODE			BIT(0)
/* HW will use the EMI clock if there isn't the "bclk". */
#define HAS_BCLK			BIT(1)
#define HAS_VLD_PA_RNG			BIT(2)
#define RESET_AXI			BIT(3)
#define OUT_ORDER_WR_EN			BIT(4)
#define HAS_SUB_COMM_2BITS		BIT(5)
#define HAS_SUB_COMM_3BITS		BIT(6)
#define WR_THROT_EN			BIT(7)
#define HAS_LEGACY_IVRP_PADDR		BIT(8)
#define IOVA_34_EN			BIT(9)
#define SHARE_PGTABLE			BIT(10) /* 2 HW share pgtable */
#define DCM_DISABLE			BIT(11)
#define STD_AXI_MODE			BIT(12) /* For non MM iommu */
/* 2 bits: iommu type */
#define MTK_IOMMU_TYPE_MM		(0x0 << 13)
#define MTK_IOMMU_TYPE_INFRA		(0x1 << 13)
#define MTK_IOMMU_TYPE_MASK		(0x3 << 13)
/* PM and clock always on. e.g. infra iommu */
#define PM_CLK_AO			BIT(15)
#define IFA_IOMMU_PCIE_SUPPORT		BIT(16)

#define MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, mask)	\
				((((pdata)->flags) & (mask)) == (_x))

#define MTK_IOMMU_HAS_FLAG(pdata, _x)	MTK_IOMMU_HAS_FLAG_MASK(pdata, _x, _x)
#define MTK_IOMMU_IS_TYPE(pdata, _x)	MTK_IOMMU_HAS_FLAG_MASK(pdata, _x,\
							MTK_IOMMU_TYPE_MASK)

#define MTK_INVALID_LARBID		MTK_LARB_NR_MAX

#define MTK_LARB_COM_MAX	8
#define MTK_LARB_SUBCOM_MAX	8

#define MTK_IOMMU_GROUP_MAX	8

enum mtk_iommu_plat {
	M4U_MT2712,
	M4U_MT6779,
	M4U_MT8167,
	M4U_MT8173,
	M4U_MT8183,
	M4U_MT8192,
	M4U_MT8195,
};

struct mtk_iommu_iova_region {
	dma_addr_t		iova_base;
	unsigned long long	size;
};

struct mtk_iommu_plat_data {
	enum mtk_iommu_plat	m4u_plat;
	u32			flags;
	u32			inv_sel_reg;

	char			*pericfg_comp_str;
	struct list_head	*hw_list;
	unsigned int		iova_region_nr;
	const struct mtk_iommu_iova_region	*iova_region;
	unsigned char       larbid_remap[MTK_LARB_COM_MAX][MTK_LARB_SUBCOM_MAX];
};

struct mtk_iommu_data {
	void __iomem			*base;
	int				irq;
	struct device			*dev;
	struct clk			*bclk;
	phys_addr_t			protect_base; /* protect memory base */
	struct mtk_iommu_suspend_reg	reg;
	struct mtk_iommu_domain		*m4u_dom;
	struct iommu_group		*m4u_group[MTK_IOMMU_GROUP_MAX];
	bool                            enable_4GB;
	spinlock_t			tlb_lock; /* lock for tlb range flush */

	struct iommu_device		iommu;
	const struct mtk_iommu_plat_data *plat_data;
	struct device			*smicomm_dev;

	struct dma_iommu_mapping	*mapping; /* For mtk_iommu_v1.c */
	struct regmap			*pericfg;

	struct mutex			mutex; /* Protect m4u_group/m4u_dom above */

	/*
	 * In the sharing pgtable case, list data->list to the global list like m4ulist.
	 * In the non-sharing pgtable case, list data->list to the itself hw_list_head.
	 */
	struct list_head		*hw_list;
	struct list_head		hw_list_head;
	struct list_head		list;
	struct mtk_smi_larb_iommu	larb_imu[MTK_LARB_NR_MAX];
};

struct mtk_iommu_domain {
	struct io_pgtable_cfg		cfg;
	struct io_pgtable_ops		*iop;

	struct mtk_iommu_data		*data;
	struct iommu_domain		domain;

	struct mutex			mutex; /* Protect "data" in this structure */
};

static int mtk_iommu_bind(struct device *dev)
{
	struct mtk_iommu_data *data = dev_get_drvdata(dev);

	return component_bind_all(dev, &data->larb_imu);
}

static void mtk_iommu_unbind(struct device *dev)
{
	struct mtk_iommu_data *data = dev_get_drvdata(dev);

	component_unbind_all(dev, &data->larb_imu);
}

static const struct iommu_ops mtk_iommu_ops;

static int mtk_iommu_hw_init(const struct mtk_iommu_data *data);

#define MTK_IOMMU_TLB_ADDR(iova) ({					\
	dma_addr_t _addr = iova;					\
	((lower_32_bits(_addr) & GENMASK(31, 12)) | upper_32_bits(_addr));\
})

/*
 * In M4U 4GB mode, the physical address is remapped as below:
 *
 * CPU Physical address:
 * ====================
 *
 * 0      1G       2G     3G       4G     5G
 * |---A---|---B---|---C---|---D---|---E---|
 * +--I/O--+------------Memory-------------+
 *
 * IOMMU output physical address:
 *  =============================
 *
 *                                 4G      5G     6G      7G      8G
 *                                 |---E---|---B---|---C---|---D---|
 *                                 +------------Memory-------------+
 *
 * The Region 'A'(I/O) can NOT be mapped by M4U; For Region 'B'/'C'/'D', the
 * bit32 of the CPU physical address always is needed to set, and for Region
 * 'E', the CPU physical address keep as is.
 * Additionally, The iommu consumers always use the CPU phyiscal address.
 */
#define MTK_IOMMU_4GB_MODE_REMAP_BASE	 0x140000000UL

static LIST_HEAD(m4ulist);	/* List all the M4U HWs */

#define for_each_m4u(data, head)  list_for_each_entry(data, head, list)

static const struct mtk_iommu_iova_region single_domain[] = {
	{.iova_base = 0,		.size = SZ_4G},
};

static const struct mtk_iommu_iova_region mt8192_multi_dom[] = {
	{ .iova_base = 0x0,		.size = SZ_4G},		/* 0 ~ 4G */
	#if IS_ENABLED(CONFIG_ARCH_DMA_ADDR_T_64BIT)
	{ .iova_base = SZ_4G,		.size = SZ_4G},		/* 4G ~ 8G */
	{ .iova_base = SZ_4G * 2,	.size = SZ_4G},		/* 8G ~ 12G */
	{ .iova_base = SZ_4G * 3,	.size = SZ_4G},		/* 12G ~ 16G */

	{ .iova_base = 0x240000000ULL,	.size = 0x4000000},	/* CCU0 */
	{ .iova_base = 0x244000000ULL,	.size = 0x4000000},	/* CCU1 */
	#endif
};

/* If 2 M4U share a domain(use the same hwlist), Put the corresponding info in first data.*/
static struct mtk_iommu_data *mtk_iommu_get_frst_data(struct list_head *hwlist)
{
	return list_first_entry(hwlist, struct mtk_iommu_data, list);
}

static struct mtk_iommu_domain *to_mtk_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct mtk_iommu_domain, domain);
}

static void mtk_iommu_tlb_flush_all(struct mtk_iommu_data *data)
{
	void __iomem *base = data->base;
	unsigned long flags;

	spin_lock_irqsave(&data->tlb_lock, flags);
	writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0, base + data->plat_data->inv_sel_reg);
	writel_relaxed(F_ALL_INVLD, base + REG_MMU_INVALIDATE);
	wmb(); /* Make sure the tlb flush all done */
	spin_unlock_irqrestore(&data->tlb_lock, flags);
}

static void mtk_iommu_tlb_flush_range_sync(unsigned long iova, size_t size,
					   struct mtk_iommu_data *data)
{
	struct list_head *head = data->hw_list;
	bool check_pm_status;
	unsigned long flags;
	void __iomem *base;
	int ret;
	u32 tmp;

	for_each_m4u(data, head) {
		/*
		 * To avoid resume the iommu device frequently when the iommu device
		 * is not active, it doesn't always call pm_runtime_get here, then tlb
		 * flush depends on the tlb flush all in the runtime resume.
		 *
		 * There are 2 special cases:
		 *
		 * Case1: The iommu dev doesn't have power domain but has bclk. This case
		 * should also avoid the tlb flush while the dev is not active to mute
		 * the tlb timeout log. like mt8173.
		 *
		 * Case2: The power/clock of infra iommu is always on, and it doesn't
		 * have the device link with the master devices. This case should avoid
		 * the PM status check.
		 */
		check_pm_status = !MTK_IOMMU_HAS_FLAG(data->plat_data, PM_CLK_AO);

		if (check_pm_status) {
			if (pm_runtime_get_if_in_use(data->dev) <= 0)
				continue;
		}

		base = data->base;

		spin_lock_irqsave(&data->tlb_lock, flags);
		writel_relaxed(F_INVLD_EN1 | F_INVLD_EN0,
			       base + data->plat_data->inv_sel_reg);

		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova), base + REG_MMU_INVLD_START_A);
		writel_relaxed(MTK_IOMMU_TLB_ADDR(iova + size - 1),
			       base + REG_MMU_INVLD_END_A);
		writel_relaxed(F_MMU_INV_RANGE, base + REG_MMU_INVALIDATE);

		/* tlb sync */
		ret = readl_poll_timeout_atomic(base + REG_MMU_CPE_DONE,
						tmp, tmp != 0, 10, 1000);

		/* Clear the CPE status */
		writel_relaxed(0, base + REG_MMU_CPE_DONE);
		spin_unlock_irqrestore(&data->tlb_lock, flags);

		if (ret) {
			dev_warn(data->dev,
				 "Partial TLB flush timed out, falling back to full flush\n");
			mtk_iommu_tlb_flush_all(data);
		}

		if (check_pm_status)
			pm_runtime_put(data->dev);
	}
}

static irqreturn_t mtk_iommu_isr(int irq, void *dev_id)
{
	struct mtk_iommu_data *data = dev_id;
	struct mtk_iommu_domain *dom = data->m4u_dom;
	unsigned int fault_larb = MTK_INVALID_LARBID, fault_port = 0, sub_comm = 0;
	u32 int_state, regval, va34_32, pa34_32;
	const struct mtk_iommu_plat_data *plat_data = data->plat_data;
	void __iomem *base = data->base;
	u64 fault_iova, fault_pa;
	bool layer, write;

	/* Read error info from registers */
	int_state = readl_relaxed(base + REG_MMU_FAULT_ST1);
	if (int_state & F_REG_MMU0_FAULT_MASK) {
		regval = readl_relaxed(base + REG_MMU0_INT_ID);
		fault_iova = readl_relaxed(base + REG_MMU0_FAULT_VA);
		fault_pa = readl_relaxed(base + REG_MMU0_INVLD_PA);
	} else {
		regval = readl_relaxed(base + REG_MMU1_INT_ID);
		fault_iova = readl_relaxed(base + REG_MMU1_FAULT_VA);
		fault_pa = readl_relaxed(base + REG_MMU1_INVLD_PA);
	}
	layer = fault_iova & F_MMU_FAULT_VA_LAYER_BIT;
	write = fault_iova & F_MMU_FAULT_VA_WRITE_BIT;
	if (MTK_IOMMU_HAS_FLAG(plat_data, IOVA_34_EN)) {
		va34_32 = FIELD_GET(F_MMU_INVAL_VA_34_32_MASK, fault_iova);
		fault_iova = fault_iova & F_MMU_INVAL_VA_31_12_MASK;
		fault_iova |= (u64)va34_32 << 32;
	}
	pa34_32 = FIELD_GET(F_MMU_INVAL_PA_34_32_MASK, fault_iova);
	fault_pa |= (u64)pa34_32 << 32;

	if (MTK_IOMMU_IS_TYPE(plat_data, MTK_IOMMU_TYPE_MM)) {
		fault_port = F_MMU_INT_ID_PORT_ID(regval);
		if (MTK_IOMMU_HAS_FLAG(plat_data, HAS_SUB_COMM_2BITS)) {
			fault_larb = F_MMU_INT_ID_COMM_ID(regval);
			sub_comm = F_MMU_INT_ID_SUB_COMM_ID(regval);
		} else if (MTK_IOMMU_HAS_FLAG(plat_data, HAS_SUB_COMM_3BITS)) {
			fault_larb = F_MMU_INT_ID_COMM_ID_EXT(regval);
			sub_comm = F_MMU_INT_ID_SUB_COMM_ID_EXT(regval);
		} else {
			fault_larb = F_MMU_INT_ID_LARB_ID(regval);
		}
		fault_larb = data->plat_data->larbid_remap[fault_larb][sub_comm];
	}

	if (report_iommu_fault(&dom->domain, data->dev, fault_iova,
			       write ? IOMMU_FAULT_WRITE : IOMMU_FAULT_READ)) {
		dev_err_ratelimited(
			data->dev,
			"fault type=0x%x iova=0x%llx pa=0x%llx master=0x%x(larb=%d port=%d) layer=%d %s\n",
			int_state, fault_iova, fault_pa, regval, fault_larb, fault_port,
			layer, write ? "write" : "read");
	}

	/* Interrupt clear */
	regval = readl_relaxed(base + REG_MMU_INT_CONTROL0);
	regval |= F_INT_CLR_BIT;
	writel_relaxed(regval, base + REG_MMU_INT_CONTROL0);

	mtk_iommu_tlb_flush_all(data);

	return IRQ_HANDLED;
}

static int mtk_iommu_get_domain_id(struct device *dev,
				   const struct mtk_iommu_plat_data *plat_data)
{
	const struct mtk_iommu_iova_region *rgn = plat_data->iova_region;
	const struct bus_dma_region *dma_rgn = dev->dma_range_map;
	int i, candidate = -1;
	dma_addr_t dma_end;

	if (!dma_rgn || plat_data->iova_region_nr == 1)
		return 0;

	dma_end = dma_rgn->dma_start + dma_rgn->size - 1;
	for (i = 0; i < plat_data->iova_region_nr; i++, rgn++) {
		/* Best fit. */
		if (dma_rgn->dma_start == rgn->iova_base &&
		    dma_end == rgn->iova_base + rgn->size - 1)
			return i;
		/* ok if it is inside this region. */
		if (dma_rgn->dma_start >= rgn->iova_base &&
		    dma_end < rgn->iova_base + rgn->size)
			candidate = i;
	}

	if (candidate >= 0)
		return candidate;
	dev_err(dev, "Can NOT find the iommu domain id(%pad 0x%llx).\n",
		&dma_rgn->dma_start, dma_rgn->size);
	return -EINVAL;
}

static int mtk_iommu_config(struct mtk_iommu_data *data, struct device *dev,
			    bool enable, unsigned int domid)
{
	struct mtk_smi_larb_iommu    *larb_mmu;
	unsigned int                 larbid, portid;
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	const struct mtk_iommu_iova_region *region;
	u32 peri_mmuen, peri_mmuen_msk;
	int i, ret = 0;

	for (i = 0; i < fwspec->num_ids; ++i) {
		larbid = MTK_M4U_TO_LARB(fwspec->ids[i]);
		portid = MTK_M4U_TO_PORT(fwspec->ids[i]);

		if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
			larb_mmu = &data->larb_imu[larbid];

			region = data->plat_data->iova_region + domid;
			larb_mmu->bank[portid] = upper_32_bits(region->iova_base);

			dev_dbg(dev, "%s iommu for larb(%s) port %d dom %d bank %d.\n",
				enable ? "enable" : "disable", dev_name(larb_mmu->dev),
				portid, domid, larb_mmu->bank[portid]);

			if (enable)
				larb_mmu->mmu |= MTK_SMI_MMU_EN(portid);
			else
				larb_mmu->mmu &= ~MTK_SMI_MMU_EN(portid);
		} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA)) {
			peri_mmuen_msk = BIT(portid);
			/* PCI dev has only one output id, enable the next writing bit for PCIe */
			if (dev_is_pci(dev))
				peri_mmuen_msk |= BIT(portid + 1);

			peri_mmuen = enable ? peri_mmuen_msk : 0;
			ret = regmap_update_bits(data->pericfg, PERICFG_IOMMU_1,
						 peri_mmuen_msk, peri_mmuen);
			if (ret)
				dev_err(dev, "%s iommu(%s) inframaster 0x%x fail(%d).\n",
					enable ? "enable" : "disable",
					dev_name(data->dev), peri_mmuen_msk, ret);
		}
	}
	return ret;
}

static int mtk_iommu_domain_finalise(struct mtk_iommu_domain *dom,
				     struct mtk_iommu_data *data,
				     unsigned int domid)
{
	const struct mtk_iommu_iova_region *region;

	/* Use the exist domain as there is only one pgtable here. */
	if (data->m4u_dom) {
		dom->iop = data->m4u_dom->iop;
		dom->cfg = data->m4u_dom->cfg;
		dom->domain.pgsize_bitmap = data->m4u_dom->cfg.pgsize_bitmap;
		goto update_iova_region;
	}

	dom->cfg = (struct io_pgtable_cfg) {
		.quirks = IO_PGTABLE_QUIRK_ARM_NS |
			IO_PGTABLE_QUIRK_NO_PERMS |
			IO_PGTABLE_QUIRK_ARM_MTK_EXT,
		.pgsize_bitmap = mtk_iommu_ops.pgsize_bitmap,
		.ias = MTK_IOMMU_HAS_FLAG(data->plat_data, IOVA_34_EN) ? 34 : 32,
		.iommu_dev = data->dev,
	};

	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE))
		dom->cfg.oas = data->enable_4GB ? 33 : 32;
	else
		dom->cfg.oas = 35;

	dom->iop = alloc_io_pgtable_ops(ARM_V7S, &dom->cfg, data);
	if (!dom->iop) {
		dev_err(data->dev, "Failed to alloc io pgtable\n");
		return -EINVAL;
	}

	/* Update our support page sizes bitmap */
	dom->domain.pgsize_bitmap = dom->cfg.pgsize_bitmap;

update_iova_region:
	/* Update the iova region for this domain */
	region = data->plat_data->iova_region + domid;
	dom->domain.geometry.aperture_start = region->iova_base;
	dom->domain.geometry.aperture_end = region->iova_base + region->size - 1;
	dom->domain.geometry.force_aperture = true;
	return 0;
}

static struct iommu_domain *mtk_iommu_domain_alloc(unsigned type)
{
	struct mtk_iommu_domain *dom;

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

	dom = kzalloc(sizeof(*dom), GFP_KERNEL);
	if (!dom)
		return NULL;
	mutex_init(&dom->mutex);

	return &dom->domain;
}

static void mtk_iommu_domain_free(struct iommu_domain *domain)
{
	kfree(to_mtk_domain(domain));
}

static int mtk_iommu_attach_device(struct iommu_domain *domain,
				   struct device *dev)
{
	struct mtk_iommu_data *data = dev_iommu_priv_get(dev), *frstdata;
	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
	struct list_head *hw_list = data->hw_list;
	struct device *m4udev = data->dev;
	int ret, domid;

	domid = mtk_iommu_get_domain_id(dev, data->plat_data);
	if (domid < 0)
		return domid;

	mutex_lock(&dom->mutex);
	if (!dom->data) {
		/* Data is in the frstdata in sharing pgtable case. */
		frstdata = mtk_iommu_get_frst_data(hw_list);

		ret = mtk_iommu_domain_finalise(dom, frstdata, domid);
		if (ret) {
			mutex_unlock(&dom->mutex);
			return -ENODEV;
		}
		dom->data = data;
	}
	mutex_unlock(&dom->mutex);

	mutex_lock(&data->mutex);
	if (!data->m4u_dom) { /* Initialize the M4U HW */
		ret = pm_runtime_resume_and_get(m4udev);
		if (ret < 0)
			goto err_unlock;

		ret = mtk_iommu_hw_init(data);
		if (ret) {
			pm_runtime_put(m4udev);
			goto err_unlock;
		}
		data->m4u_dom = dom;
		writel(dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK,
		       data->base + REG_MMU_PT_BASE_ADDR);

		pm_runtime_put(m4udev);
	}
	mutex_unlock(&data->mutex);

	return mtk_iommu_config(data, dev, true, domid);

err_unlock:
	mutex_unlock(&data->mutex);
	return ret;
}

static void mtk_iommu_detach_device(struct iommu_domain *domain,
				    struct device *dev)
{
	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);

	mtk_iommu_config(data, dev, false, 0);
}

static int mtk_iommu_map(struct iommu_domain *domain, unsigned long iova,
			 phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
	struct mtk_iommu_domain *dom = to_mtk_domain(domain);

	/* The "4GB mode" M4U physically can not use the lower remap of Dram. */
	if (dom->data->enable_4GB)
		paddr |= BIT_ULL(32);

	/* Synchronize with the tlb_lock */
	return dom->iop->map(dom->iop, iova, paddr, size, prot, gfp);
}

static size_t mtk_iommu_unmap(struct iommu_domain *domain,
			      unsigned long iova, size_t size,
			      struct iommu_iotlb_gather *gather)
{
	struct mtk_iommu_domain *dom = to_mtk_domain(domain);

	iommu_iotlb_gather_add_range(gather, iova, size);
	return dom->iop->unmap(dom->iop, iova, size, gather);
}

static void mtk_iommu_flush_iotlb_all(struct iommu_domain *domain)
{
	struct mtk_iommu_domain *dom = to_mtk_domain(domain);

	mtk_iommu_tlb_flush_all(dom->data);
}

static void mtk_iommu_iotlb_sync(struct iommu_domain *domain,
				 struct iommu_iotlb_gather *gather)
{
	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
	size_t length = gather->end - gather->start + 1;

	mtk_iommu_tlb_flush_range_sync(gather->start, length, dom->data);
}

static void mtk_iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
			       size_t size)
{
	struct mtk_iommu_domain *dom = to_mtk_domain(domain);

	mtk_iommu_tlb_flush_range_sync(iova, size, dom->data);
}

static phys_addr_t mtk_iommu_iova_to_phys(struct iommu_domain *domain,
					  dma_addr_t iova)
{
	struct mtk_iommu_domain *dom = to_mtk_domain(domain);
	phys_addr_t pa;

	pa = dom->iop->iova_to_phys(dom->iop, iova);
	if (IS_ENABLED(CONFIG_PHYS_ADDR_T_64BIT) &&
	    dom->data->enable_4GB &&
	    pa >= MTK_IOMMU_4GB_MODE_REMAP_BASE)
		pa &= ~BIT_ULL(32);

	return pa;
}

static struct iommu_device *mtk_iommu_probe_device(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	struct mtk_iommu_data *data;
	struct device_link *link;
	struct device *larbdev;
	unsigned int larbid, larbidx, i;

	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
		return ERR_PTR(-ENODEV); /* Not a iommu client device */

	data = dev_iommu_priv_get(dev);

	if (!MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
		return &data->iommu;

	/*
	 * Link the consumer device with the smi-larb device(supplier).
	 * The device that connects with each a larb is a independent HW.
	 * All the ports in each a device should be in the same larbs.
	 */
	larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
	for (i = 1; i < fwspec->num_ids; i++) {
		larbidx = MTK_M4U_TO_LARB(fwspec->ids[i]);
		if (larbid != larbidx) {
			dev_err(dev, "Can only use one larb. Fail@larb%d-%d.\n",
				larbid, larbidx);
			return ERR_PTR(-EINVAL);
		}
	}
	larbdev = data->larb_imu[larbid].dev;
	link = device_link_add(dev, larbdev,
			       DL_FLAG_PM_RUNTIME | DL_FLAG_STATELESS);
	if (!link)
		dev_err(dev, "Unable to link %s\n", dev_name(larbdev));
	return &data->iommu;
}

static void mtk_iommu_release_device(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	struct mtk_iommu_data *data;
	struct device *larbdev;
	unsigned int larbid;

	if (!fwspec || fwspec->ops != &mtk_iommu_ops)
		return;

	data = dev_iommu_priv_get(dev);
	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
		larbid = MTK_M4U_TO_LARB(fwspec->ids[0]);
		larbdev = data->larb_imu[larbid].dev;
		device_link_remove(dev, larbdev);
	}

	iommu_fwspec_free(dev);
}

static struct iommu_group *mtk_iommu_device_group(struct device *dev)
{
	struct mtk_iommu_data *c_data = dev_iommu_priv_get(dev), *data;
	struct list_head *hw_list = c_data->hw_list;
	struct iommu_group *group;
	int domid;

	data = mtk_iommu_get_frst_data(hw_list);
	if (!data)
		return ERR_PTR(-ENODEV);

	domid = mtk_iommu_get_domain_id(dev, data->plat_data);
	if (domid < 0)
		return ERR_PTR(domid);

	mutex_lock(&data->mutex);
	group = data->m4u_group[domid];
	if (!group) {
		group = iommu_group_alloc();
		if (!IS_ERR(group))
			data->m4u_group[domid] = group;
	} else {
		iommu_group_ref_get(group);
	}
	mutex_unlock(&data->mutex);
	return group;
}

static int mtk_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
{
	struct platform_device *m4updev;

	if (args->args_count != 1) {
		dev_err(dev, "invalid #iommu-cells(%d) property for IOMMU\n",
			args->args_count);
		return -EINVAL;
	}

	if (!dev_iommu_priv_get(dev)) {
		/* Get the m4u device */
		m4updev = of_find_device_by_node(args->np);
		if (WARN_ON(!m4updev))
			return -EINVAL;

		dev_iommu_priv_set(dev, platform_get_drvdata(m4updev));
	}

	return iommu_fwspec_add_ids(dev, args->args, 1);
}

static void mtk_iommu_get_resv_regions(struct device *dev,
				       struct list_head *head)
{
	struct mtk_iommu_data *data = dev_iommu_priv_get(dev);
	unsigned int domid = mtk_iommu_get_domain_id(dev, data->plat_data), i;
	const struct mtk_iommu_iova_region *resv, *curdom;
	struct iommu_resv_region *region;
	int prot = IOMMU_WRITE | IOMMU_READ;

	if ((int)domid < 0)
		return;
	curdom = data->plat_data->iova_region + domid;
	for (i = 0; i < data->plat_data->iova_region_nr; i++) {
		resv = data->plat_data->iova_region + i;

		/* Only reserve when the region is inside the current domain */
		if (resv->iova_base <= curdom->iova_base ||
		    resv->iova_base + resv->size >= curdom->iova_base + curdom->size)
			continue;

		region = iommu_alloc_resv_region(resv->iova_base, resv->size,
						 prot, IOMMU_RESV_RESERVED);
		if (!region)
			return;

		list_add_tail(&region->list, head);
	}
}

static const struct iommu_ops mtk_iommu_ops = {
	.domain_alloc	= mtk_iommu_domain_alloc,
	.probe_device	= mtk_iommu_probe_device,
	.release_device	= mtk_iommu_release_device,
	.device_group	= mtk_iommu_device_group,
	.of_xlate	= mtk_iommu_of_xlate,
	.get_resv_regions = mtk_iommu_get_resv_regions,
	.put_resv_regions = generic_iommu_put_resv_regions,
	.pgsize_bitmap	= SZ_4K | SZ_64K | SZ_1M | SZ_16M,
	.owner		= THIS_MODULE,
	.default_domain_ops = &(const struct iommu_domain_ops) {
		.attach_dev	= mtk_iommu_attach_device,
		.detach_dev	= mtk_iommu_detach_device,
		.map		= mtk_iommu_map,
		.unmap		= mtk_iommu_unmap,
		.flush_iotlb_all = mtk_iommu_flush_iotlb_all,
		.iotlb_sync	= mtk_iommu_iotlb_sync,
		.iotlb_sync_map	= mtk_iommu_sync_map,
		.iova_to_phys	= mtk_iommu_iova_to_phys,
		.free		= mtk_iommu_domain_free,
	}
};

static int mtk_iommu_hw_init(const struct mtk_iommu_data *data)
{
	u32 regval;

	if (data->plat_data->m4u_plat == M4U_MT8173) {
		regval = F_MMU_PREFETCH_RT_REPLACE_MOD |
			 F_MMU_TF_PROT_TO_PROGRAM_ADDR_MT8173;
	} else {
		regval = readl_relaxed(data->base + REG_MMU_CTRL_REG);
		regval |= F_MMU_TF_PROT_TO_PROGRAM_ADDR;
	}
	writel_relaxed(regval, data->base + REG_MMU_CTRL_REG);

	if (data->enable_4GB &&
	    MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_VLD_PA_RNG)) {
		/*
		 * If 4GB mode is enabled, the validate PA range is from
		 * 0x1_0000_0000 to 0x1_ffff_ffff. here record bit[32:30].
		 */
		regval = F_MMU_VLD_PA_RNG(7, 4);
		writel_relaxed(regval, data->base + REG_MMU_VLD_PA_RNG);
	}
	if (MTK_IOMMU_HAS_FLAG(data->plat_data, DCM_DISABLE))
		writel_relaxed(F_MMU_DCM, data->base + REG_MMU_DCM_DIS);
	else
		writel_relaxed(0, data->base + REG_MMU_DCM_DIS);

	if (MTK_IOMMU_HAS_FLAG(data->plat_data, WR_THROT_EN)) {
		/* write command throttling mode */
		regval = readl_relaxed(data->base + REG_MMU_WR_LEN_CTRL);
		regval &= ~F_MMU_WR_THROT_DIS_MASK;
		writel_relaxed(regval, data->base + REG_MMU_WR_LEN_CTRL);
	}

	if (MTK_IOMMU_HAS_FLAG(data->plat_data, RESET_AXI)) {
		/* The register is called STANDARD_AXI_MODE in this case */
		regval = 0;
	} else {
		regval = readl_relaxed(data->base + REG_MMU_MISC_CTRL);
		if (!MTK_IOMMU_HAS_FLAG(data->plat_data, STD_AXI_MODE))
			regval &= ~F_MMU_STANDARD_AXI_MODE_MASK;
		if (MTK_IOMMU_HAS_FLAG(data->plat_data, OUT_ORDER_WR_EN))
			regval &= ~F_MMU_IN_ORDER_WR_EN_MASK;
	}
	writel_relaxed(regval, data->base + REG_MMU_MISC_CTRL);

	regval = F_L2_MULIT_HIT_EN |
		F_TABLE_WALK_FAULT_INT_EN |
		F_PREETCH_FIFO_OVERFLOW_INT_EN |
		F_MISS_FIFO_OVERFLOW_INT_EN |
		F_PREFETCH_FIFO_ERR_INT_EN |
		F_MISS_FIFO_ERR_INT_EN;
	writel_relaxed(regval, data->base + REG_MMU_INT_CONTROL0);

	regval = F_INT_TRANSLATION_FAULT |
		F_INT_MAIN_MULTI_HIT_FAULT |
		F_INT_INVALID_PA_FAULT |
		F_INT_ENTRY_REPLACEMENT_FAULT |
		F_INT_TLB_MISS_FAULT |
		F_INT_MISS_TRANSACTION_FIFO_FAULT |
		F_INT_PRETETCH_TRANSATION_FIFO_FAULT;
	writel_relaxed(regval, data->base + REG_MMU_INT_MAIN_CONTROL);

	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_LEGACY_IVRP_PADDR))
		regval = (data->protect_base >> 1) | (data->enable_4GB << 31);
	else
		regval = lower_32_bits(data->protect_base) |
			 upper_32_bits(data->protect_base);
	writel_relaxed(regval, data->base + REG_MMU_IVRP_PADDR);

	if (devm_request_irq(data->dev, data->irq, mtk_iommu_isr, 0,
			     dev_name(data->dev), (void *)data)) {
		writel_relaxed(0, data->base + REG_MMU_PT_BASE_ADDR);
		dev_err(data->dev, "Failed @ IRQ-%d Request\n", data->irq);
		return -ENODEV;
	}

	return 0;
}

static const struct component_master_ops mtk_iommu_com_ops = {
	.bind		= mtk_iommu_bind,
	.unbind		= mtk_iommu_unbind,
};

static int mtk_iommu_mm_dts_parse(struct device *dev, struct component_match **match,
				  struct mtk_iommu_data *data)
{
	struct device_node *larbnode, *smicomm_node, *smi_subcomm_node;
	struct platform_device *plarbdev;
	struct device_link *link;
	int i, larb_nr, ret;

	larb_nr = of_count_phandle_with_args(dev->of_node, "mediatek,larbs", NULL);
	if (larb_nr < 0)
		return larb_nr;

	for (i = 0; i < larb_nr; i++) {
		u32 id;

		larbnode = of_parse_phandle(dev->of_node, "mediatek,larbs", i);
		if (!larbnode)
			return -EINVAL;

		if (!of_device_is_available(larbnode)) {
			of_node_put(larbnode);
			continue;
		}

		ret = of_property_read_u32(larbnode, "mediatek,larb-id", &id);
		if (ret)/* The id is consecutive if there is no this property */
			id = i;

		plarbdev = of_find_device_by_node(larbnode);
		if (!plarbdev) {
			of_node_put(larbnode);
			return -ENODEV;
		}
		if (!plarbdev->dev.driver) {
			of_node_put(larbnode);
			return -EPROBE_DEFER;
		}
		data->larb_imu[id].dev = &plarbdev->dev;

		component_match_add_release(dev, match, component_release_of,
					    component_compare_of, larbnode);
	}

	/* Get smi-(sub)-common dev from the last larb. */
	smi_subcomm_node = of_parse_phandle(larbnode, "mediatek,smi", 0);
	if (!smi_subcomm_node)
		return -EINVAL;

	/*
	 * It may have two level smi-common. the node is smi-sub-common if it
	 * has a new mediatek,smi property. otherwise it is smi-commmon.
	 */
	smicomm_node = of_parse_phandle(smi_subcomm_node, "mediatek,smi", 0);
	if (smicomm_node)
		of_node_put(smi_subcomm_node);
	else
		smicomm_node = smi_subcomm_node;

	plarbdev = of_find_device_by_node(smicomm_node);
	of_node_put(smicomm_node);
	data->smicomm_dev = &plarbdev->dev;

	link = device_link_add(data->smicomm_dev, dev,
			       DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME);
	if (!link) {
		dev_err(dev, "Unable to link %s.\n", dev_name(data->smicomm_dev));
		return -EINVAL;
	}
	return 0;
}

static int mtk_iommu_probe(struct platform_device *pdev)
{
	struct mtk_iommu_data   *data;
	struct device           *dev = &pdev->dev;
	struct resource         *res;
	resource_size_t		ioaddr;
	struct component_match  *match = NULL;
	struct regmap		*infracfg;
	void                    *protect;
	int                     ret;
	u32			val;
	char                    *p;

	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
	if (!data)
		return -ENOMEM;
	data->dev = dev;
	data->plat_data = of_device_get_match_data(dev);

	/* Protect memory. HW will access here while translation fault.*/
	protect = devm_kzalloc(dev, MTK_PROTECT_PA_ALIGN * 2, GFP_KERNEL);
	if (!protect)
		return -ENOMEM;
	data->protect_base = ALIGN(virt_to_phys(protect), MTK_PROTECT_PA_ALIGN);

	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_4GB_MODE)) {
		switch (data->plat_data->m4u_plat) {
		case M4U_MT2712:
			p = "mediatek,mt2712-infracfg";
			break;
		case M4U_MT8173:
			p = "mediatek,mt8173-infracfg";
			break;
		default:
			p = NULL;
		}

		infracfg = syscon_regmap_lookup_by_compatible(p);

		if (IS_ERR(infracfg))
			return PTR_ERR(infracfg);

		ret = regmap_read(infracfg, REG_INFRA_MISC, &val);
		if (ret)
			return ret;
		data->enable_4GB = !!(val & F_DDR_4GB_SUPPORT_EN);
	}

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	data->base = devm_ioremap_resource(dev, res);
	if (IS_ERR(data->base))
		return PTR_ERR(data->base);
	ioaddr = res->start;

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

	if (MTK_IOMMU_HAS_FLAG(data->plat_data, HAS_BCLK)) {
		data->bclk = devm_clk_get(dev, "bclk");
		if (IS_ERR(data->bclk))
			return PTR_ERR(data->bclk);
	}

	pm_runtime_enable(dev);

	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
		ret = mtk_iommu_mm_dts_parse(dev, &match, data);
		if (ret) {
			dev_err(dev, "mm dts parse fail(%d).", ret);
			goto out_runtime_disable;
		}
	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
		   data->plat_data->pericfg_comp_str) {
		infracfg = syscon_regmap_lookup_by_compatible(data->plat_data->pericfg_comp_str);
		if (IS_ERR(infracfg)) {
			ret = PTR_ERR(infracfg);
			goto out_runtime_disable;
		}

		data->pericfg = infracfg;
	}

	platform_set_drvdata(pdev, data);
	mutex_init(&data->mutex);

	ret = iommu_device_sysfs_add(&data->iommu, dev, NULL,
				     "mtk-iommu.%pa", &ioaddr);
	if (ret)
		goto out_link_remove;

	ret = iommu_device_register(&data->iommu, &mtk_iommu_ops, dev);
	if (ret)
		goto out_sysfs_remove;

	spin_lock_init(&data->tlb_lock);

	if (MTK_IOMMU_HAS_FLAG(data->plat_data, SHARE_PGTABLE)) {
		list_add_tail(&data->list, data->plat_data->hw_list);
		data->hw_list = data->plat_data->hw_list;
	} else {
		INIT_LIST_HEAD(&data->hw_list_head);
		list_add_tail(&data->list, &data->hw_list_head);
		data->hw_list = &data->hw_list_head;
	}

	if (!iommu_present(&platform_bus_type)) {
		ret = bus_set_iommu(&platform_bus_type, &mtk_iommu_ops);
		if (ret)
			goto out_list_del;
	}

	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
		ret = component_master_add_with_match(dev, &mtk_iommu_com_ops, match);
		if (ret)
			goto out_bus_set_null;
	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
		   MTK_IOMMU_HAS_FLAG(data->plat_data, IFA_IOMMU_PCIE_SUPPORT)) {
#ifdef CONFIG_PCI
		if (!iommu_present(&pci_bus_type)) {
			ret = bus_set_iommu(&pci_bus_type, &mtk_iommu_ops);
			if (ret) /* PCIe fail don't affect platform_bus. */
				goto out_list_del;
		}
#endif
	}
	return ret;

out_bus_set_null:
	bus_set_iommu(&platform_bus_type, NULL);
out_list_del:
	list_del(&data->list);
	iommu_device_unregister(&data->iommu);
out_sysfs_remove:
	iommu_device_sysfs_remove(&data->iommu);
out_link_remove:
	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM))
		device_link_remove(data->smicomm_dev, dev);
out_runtime_disable:
	pm_runtime_disable(dev);
	return ret;
}

static int mtk_iommu_remove(struct platform_device *pdev)
{
	struct mtk_iommu_data *data = platform_get_drvdata(pdev);

	iommu_device_sysfs_remove(&data->iommu);
	iommu_device_unregister(&data->iommu);

	list_del(&data->list);

	if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_MM)) {
		device_link_remove(data->smicomm_dev, &pdev->dev);
		component_master_del(&pdev->dev, &mtk_iommu_com_ops);
	} else if (MTK_IOMMU_IS_TYPE(data->plat_data, MTK_IOMMU_TYPE_INFRA) &&
		   MTK_IOMMU_HAS_FLAG(data->plat_data, IFA_IOMMU_PCIE_SUPPORT)) {
#ifdef CONFIG_PCI
		bus_set_iommu(&pci_bus_type, NULL);
#endif
	}
	pm_runtime_disable(&pdev->dev);
	devm_free_irq(&pdev->dev, data->irq, data);
	return 0;
}

static int __maybe_unused mtk_iommu_runtime_suspend(struct device *dev)
{
	struct mtk_iommu_data *data = dev_get_drvdata(dev);
	struct mtk_iommu_suspend_reg *reg = &data->reg;
	void __iomem *base = data->base;

	reg->wr_len_ctrl = readl_relaxed(base + REG_MMU_WR_LEN_CTRL);
	reg->misc_ctrl = readl_relaxed(base + REG_MMU_MISC_CTRL);
	reg->dcm_dis = readl_relaxed(base + REG_MMU_DCM_DIS);
	reg->ctrl_reg = readl_relaxed(base + REG_MMU_CTRL_REG);
	reg->int_control0 = readl_relaxed(base + REG_MMU_INT_CONTROL0);
	reg->int_main_control = readl_relaxed(base + REG_MMU_INT_MAIN_CONTROL);
	reg->ivrp_paddr = readl_relaxed(base + REG_MMU_IVRP_PADDR);
	reg->vld_pa_rng = readl_relaxed(base + REG_MMU_VLD_PA_RNG);
	clk_disable_unprepare(data->bclk);
	return 0;
}

static int __maybe_unused mtk_iommu_runtime_resume(struct device *dev)
{
	struct mtk_iommu_data *data = dev_get_drvdata(dev);
	struct mtk_iommu_suspend_reg *reg = &data->reg;
	struct mtk_iommu_domain *m4u_dom = data->m4u_dom;
	void __iomem *base = data->base;
	int ret;

	ret = clk_prepare_enable(data->bclk);
	if (ret) {
		dev_err(data->dev, "Failed to enable clk(%d) in resume\n", ret);
		return ret;
	}

	/*
	 * Uppon first resume, only enable the clk and return, since the values of the
	 * registers are not yet set.
	 */
	if (!m4u_dom)
		return 0;

	writel_relaxed(reg->wr_len_ctrl, base + REG_MMU_WR_LEN_CTRL);
	writel_relaxed(reg->misc_ctrl, base + REG_MMU_MISC_CTRL);
	writel_relaxed(reg->dcm_dis, base + REG_MMU_DCM_DIS);
	writel_relaxed(reg->ctrl_reg, base + REG_MMU_CTRL_REG);
	writel_relaxed(reg->int_control0, base + REG_MMU_INT_CONTROL0);
	writel_relaxed(reg->int_main_control, base + REG_MMU_INT_MAIN_CONTROL);
	writel_relaxed(reg->ivrp_paddr, base + REG_MMU_IVRP_PADDR);
	writel_relaxed(reg->vld_pa_rng, base + REG_MMU_VLD_PA_RNG);
	writel(m4u_dom->cfg.arm_v7s_cfg.ttbr & MMU_PT_ADDR_MASK, base + REG_MMU_PT_BASE_ADDR);

	/*
	 * Users may allocate dma buffer before they call pm_runtime_get,
	 * in which case it will lack the necessary tlb flush.
	 * Thus, make sure to update the tlb after each PM resume.
	 */
	mtk_iommu_tlb_flush_all(data);
	return 0;
}

static const struct dev_pm_ops mtk_iommu_pm_ops = {
	SET_RUNTIME_PM_OPS(mtk_iommu_runtime_suspend, mtk_iommu_runtime_resume, NULL)
	SET_LATE_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
				     pm_runtime_force_resume)
};

static const struct mtk_iommu_plat_data mt2712_data = {
	.m4u_plat     = M4U_MT2712,
	.flags        = HAS_4GB_MODE | HAS_BCLK | HAS_VLD_PA_RNG | SHARE_PGTABLE |
			MTK_IOMMU_TYPE_MM,
	.hw_list      = &m4ulist,
	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
	.iova_region  = single_domain,
	.iova_region_nr = ARRAY_SIZE(single_domain),
	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}, {6}, {7}},
};

static const struct mtk_iommu_plat_data mt6779_data = {
	.m4u_plat      = M4U_MT6779,
	.flags         = HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN | WR_THROT_EN |
			 MTK_IOMMU_TYPE_MM,
	.inv_sel_reg   = REG_MMU_INV_SEL_GEN2,
	.iova_region   = single_domain,
	.iova_region_nr = ARRAY_SIZE(single_domain),
	.larbid_remap  = {{0}, {1}, {2}, {3}, {5}, {7, 8}, {10}, {9}},
};

static const struct mtk_iommu_plat_data mt8167_data = {
	.m4u_plat     = M4U_MT8167,
	.flags        = RESET_AXI | HAS_LEGACY_IVRP_PADDR | MTK_IOMMU_TYPE_MM,
	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
	.iova_region  = single_domain,
	.iova_region_nr = ARRAY_SIZE(single_domain),
	.larbid_remap = {{0}, {1}, {2}}, /* Linear mapping. */
};

static const struct mtk_iommu_plat_data mt8173_data = {
	.m4u_plat     = M4U_MT8173,
	.flags	      = HAS_4GB_MODE | HAS_BCLK | RESET_AXI |
			HAS_LEGACY_IVRP_PADDR | MTK_IOMMU_TYPE_MM,
	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
	.iova_region  = single_domain,
	.iova_region_nr = ARRAY_SIZE(single_domain),
	.larbid_remap = {{0}, {1}, {2}, {3}, {4}, {5}}, /* Linear mapping. */
};

static const struct mtk_iommu_plat_data mt8183_data = {
	.m4u_plat     = M4U_MT8183,
	.flags        = RESET_AXI | MTK_IOMMU_TYPE_MM,
	.inv_sel_reg  = REG_MMU_INV_SEL_GEN1,
	.iova_region  = single_domain,
	.iova_region_nr = ARRAY_SIZE(single_domain),
	.larbid_remap = {{0}, {4}, {5}, {6}, {7}, {2}, {3}, {1}},
};

static const struct mtk_iommu_plat_data mt8192_data = {
	.m4u_plat       = M4U_MT8192,
	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
			  WR_THROT_EN | IOVA_34_EN | MTK_IOMMU_TYPE_MM,
	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
	.iova_region    = mt8192_multi_dom,
	.iova_region_nr = ARRAY_SIZE(mt8192_multi_dom),
	.larbid_remap   = {{0}, {1}, {4, 5}, {7}, {2}, {9, 11, 19, 20},
			   {0, 14, 16}, {0, 13, 18, 17}},
};

static const struct mtk_iommu_plat_data mt8195_data_infra = {
	.m4u_plat	  = M4U_MT8195,
	.flags            = WR_THROT_EN | DCM_DISABLE | STD_AXI_MODE | PM_CLK_AO |
			    MTK_IOMMU_TYPE_INFRA | IFA_IOMMU_PCIE_SUPPORT,
	.pericfg_comp_str = "mediatek,mt8195-pericfg_ao",
	.inv_sel_reg      = REG_MMU_INV_SEL_GEN2,
	.iova_region      = single_domain,
	.iova_region_nr   = ARRAY_SIZE(single_domain),
};

static const struct mtk_iommu_plat_data mt8195_data_vdo = {
	.m4u_plat	= M4U_MT8195,
	.flags          = HAS_BCLK | HAS_SUB_COMM_2BITS | OUT_ORDER_WR_EN |
			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE | MTK_IOMMU_TYPE_MM,
	.hw_list        = &m4ulist,
	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
	.iova_region	= mt8192_multi_dom,
	.iova_region_nr	= ARRAY_SIZE(mt8192_multi_dom),
	.larbid_remap   = {{2, 0}, {21}, {24}, {7}, {19}, {9, 10, 11},
			   {13, 17, 15/* 17b */, 25}, {5}},
};

static const struct mtk_iommu_plat_data mt8195_data_vpp = {
	.m4u_plat	= M4U_MT8195,
	.flags          = HAS_BCLK | HAS_SUB_COMM_3BITS | OUT_ORDER_WR_EN |
			  WR_THROT_EN | IOVA_34_EN | SHARE_PGTABLE | MTK_IOMMU_TYPE_MM,
	.hw_list        = &m4ulist,
	.inv_sel_reg    = REG_MMU_INV_SEL_GEN2,
	.iova_region	= mt8192_multi_dom,
	.iova_region_nr	= ARRAY_SIZE(mt8192_multi_dom),
	.larbid_remap   = {{1}, {3},
			   {22, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 23},
			   {8}, {20}, {12},
			   /* 16: 16a; 29: 16b; 30: CCUtop0; 31: CCUtop1 */
			   {14, 16, 29, 26, 30, 31, 18},
			   {4, MTK_INVALID_LARBID, MTK_INVALID_LARBID, MTK_INVALID_LARBID, 6}},
};

static const struct of_device_id mtk_iommu_of_ids[] = {
	{ .compatible = "mediatek,mt2712-m4u", .data = &mt2712_data},
	{ .compatible = "mediatek,mt6779-m4u", .data = &mt6779_data},
	{ .compatible = "mediatek,mt8167-m4u", .data = &mt8167_data},
	{ .compatible = "mediatek,mt8173-m4u", .data = &mt8173_data},
	{ .compatible = "mediatek,mt8183-m4u", .data = &mt8183_data},
	{ .compatible = "mediatek,mt8192-m4u", .data = &mt8192_data},
	{ .compatible = "mediatek,mt8195-iommu-infra", .data = &mt8195_data_infra},
	{ .compatible = "mediatek,mt8195-iommu-vdo",   .data = &mt8195_data_vdo},
	{ .compatible = "mediatek,mt8195-iommu-vpp",   .data = &mt8195_data_vpp},
	{}
};

static struct platform_driver mtk_iommu_driver = {
	.probe	= mtk_iommu_probe,
	.remove	= mtk_iommu_remove,
	.driver	= {
		.name = "mtk-iommu",
		.of_match_table = mtk_iommu_of_ids,
		.pm = &mtk_iommu_pm_ops,
	}
};
module_platform_driver(mtk_iommu_driver);

MODULE_DESCRIPTION("IOMMU API for MediaTek M4U implementations");
MODULE_LICENSE("GPL v2");