summaryrefslogtreecommitdiffstats
path: root/drivers/iommu/tegra-smmu.c
blob: 124c8848ab7ecfebdf6cc27d3f89a74c04711eb3 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2011-2014 NVIDIA CORPORATION.  All rights reserved.
 */

#include <linux/bitops.h>
#include <linux/debugfs.h>
#include <linux/err.h>
#include <linux/iommu.h>
#include <linux/kernel.h>
#include <linux/of.h>
#include <linux/of_device.h>
#include <linux/platform_device.h>
#include <linux/slab.h>
#include <linux/dma-mapping.h>

#include <soc/tegra/ahb.h>
#include <soc/tegra/mc.h>

struct tegra_smmu_group {
	struct list_head list;
	const struct tegra_smmu_group_soc *soc;
	struct iommu_group *group;
};

struct tegra_smmu {
	void __iomem *regs;
	struct device *dev;

	struct tegra_mc *mc;
	const struct tegra_smmu_soc *soc;

	struct list_head groups;

	unsigned long pfn_mask;
	unsigned long tlb_mask;

	unsigned long *asids;
	struct mutex lock;

	struct list_head list;

	struct dentry *debugfs;

	struct iommu_device iommu;	/* IOMMU Core code handle */
};

struct tegra_smmu_as {
	struct iommu_domain domain;
	struct tegra_smmu *smmu;
	unsigned int use_count;
	u32 *count;
	struct page **pts;
	struct page *pd;
	dma_addr_t pd_dma;
	unsigned id;
	u32 attr;
};

static struct tegra_smmu_as *to_smmu_as(struct iommu_domain *dom)
{
	return container_of(dom, struct tegra_smmu_as, domain);
}

static inline void smmu_writel(struct tegra_smmu *smmu, u32 value,
			       unsigned long offset)
{
	writel(value, smmu->regs + offset);
}

static inline u32 smmu_readl(struct tegra_smmu *smmu, unsigned long offset)
{
	return readl(smmu->regs + offset);
}

#define SMMU_CONFIG 0x010
#define  SMMU_CONFIG_ENABLE (1 << 0)

#define SMMU_TLB_CONFIG 0x14
#define  SMMU_TLB_CONFIG_HIT_UNDER_MISS (1 << 29)
#define  SMMU_TLB_CONFIG_ROUND_ROBIN_ARBITRATION (1 << 28)
#define  SMMU_TLB_CONFIG_ACTIVE_LINES(smmu) \
	((smmu)->soc->num_tlb_lines & (smmu)->tlb_mask)

#define SMMU_PTC_CONFIG 0x18
#define  SMMU_PTC_CONFIG_ENABLE (1 << 29)
#define  SMMU_PTC_CONFIG_REQ_LIMIT(x) (((x) & 0x0f) << 24)
#define  SMMU_PTC_CONFIG_INDEX_MAP(x) ((x) & 0x3f)

#define SMMU_PTB_ASID 0x01c
#define  SMMU_PTB_ASID_VALUE(x) ((x) & 0x7f)

#define SMMU_PTB_DATA 0x020
#define  SMMU_PTB_DATA_VALUE(dma, attr) ((dma) >> 12 | (attr))

#define SMMU_MK_PDE(dma, attr) ((dma) >> SMMU_PTE_SHIFT | (attr))

#define SMMU_TLB_FLUSH 0x030
#define  SMMU_TLB_FLUSH_VA_MATCH_ALL     (0 << 0)
#define  SMMU_TLB_FLUSH_VA_MATCH_SECTION (2 << 0)
#define  SMMU_TLB_FLUSH_VA_MATCH_GROUP   (3 << 0)
#define  SMMU_TLB_FLUSH_VA_SECTION(addr) ((((addr) & 0xffc00000) >> 12) | \
					  SMMU_TLB_FLUSH_VA_MATCH_SECTION)
#define  SMMU_TLB_FLUSH_VA_GROUP(addr)   ((((addr) & 0xffffc000) >> 12) | \
					  SMMU_TLB_FLUSH_VA_MATCH_GROUP)
#define  SMMU_TLB_FLUSH_ASID_MATCH       (1 << 31)

#define SMMU_PTC_FLUSH 0x034
#define  SMMU_PTC_FLUSH_TYPE_ALL (0 << 0)
#define  SMMU_PTC_FLUSH_TYPE_ADR (1 << 0)

#define SMMU_PTC_FLUSH_HI 0x9b8
#define  SMMU_PTC_FLUSH_HI_MASK 0x3

/* per-SWGROUP SMMU_*_ASID register */
#define SMMU_ASID_ENABLE (1 << 31)
#define SMMU_ASID_MASK 0x7f
#define SMMU_ASID_VALUE(x) ((x) & SMMU_ASID_MASK)

/* page table definitions */
#define SMMU_NUM_PDE 1024
#define SMMU_NUM_PTE 1024

#define SMMU_SIZE_PD (SMMU_NUM_PDE * 4)
#define SMMU_SIZE_PT (SMMU_NUM_PTE * 4)

#define SMMU_PDE_SHIFT 22
#define SMMU_PTE_SHIFT 12

#define SMMU_PD_READABLE	(1 << 31)
#define SMMU_PD_WRITABLE	(1 << 30)
#define SMMU_PD_NONSECURE	(1 << 29)

#define SMMU_PDE_READABLE	(1 << 31)
#define SMMU_PDE_WRITABLE	(1 << 30)
#define SMMU_PDE_NONSECURE	(1 << 29)
#define SMMU_PDE_NEXT		(1 << 28)

#define SMMU_PTE_READABLE	(1 << 31)
#define SMMU_PTE_WRITABLE	(1 << 30)
#define SMMU_PTE_NONSECURE	(1 << 29)

#define SMMU_PDE_ATTR		(SMMU_PDE_READABLE | SMMU_PDE_WRITABLE | \
				 SMMU_PDE_NONSECURE)

static unsigned int iova_pd_index(unsigned long iova)
{
	return (iova >> SMMU_PDE_SHIFT) & (SMMU_NUM_PDE - 1);
}

static unsigned int iova_pt_index(unsigned long iova)
{
	return (iova >> SMMU_PTE_SHIFT) & (SMMU_NUM_PTE - 1);
}

static bool smmu_dma_addr_valid(struct tegra_smmu *smmu, dma_addr_t addr)
{
	addr >>= 12;
	return (addr & smmu->pfn_mask) == addr;
}

static dma_addr_t smmu_pde_to_dma(struct tegra_smmu *smmu, u32 pde)
{
	return (dma_addr_t)(pde & smmu->pfn_mask) << 12;
}

static void smmu_flush_ptc_all(struct tegra_smmu *smmu)
{
	smmu_writel(smmu, SMMU_PTC_FLUSH_TYPE_ALL, SMMU_PTC_FLUSH);
}

static inline void smmu_flush_ptc(struct tegra_smmu *smmu, dma_addr_t dma,
				  unsigned long offset)
{
	u32 value;

	offset &= ~(smmu->mc->soc->atom_size - 1);

	if (smmu->mc->soc->num_address_bits > 32) {
#ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT
		value = (dma >> 32) & SMMU_PTC_FLUSH_HI_MASK;
#else
		value = 0;
#endif
		smmu_writel(smmu, value, SMMU_PTC_FLUSH_HI);
	}

	value = (dma + offset) | SMMU_PTC_FLUSH_TYPE_ADR;
	smmu_writel(smmu, value, SMMU_PTC_FLUSH);
}

static inline void smmu_flush_tlb(struct tegra_smmu *smmu)
{
	smmu_writel(smmu, SMMU_TLB_FLUSH_VA_MATCH_ALL, SMMU_TLB_FLUSH);
}

static inline void smmu_flush_tlb_asid(struct tegra_smmu *smmu,
				       unsigned long asid)
{
	u32 value;

	if (smmu->soc->num_asids == 4)
		value = (asid & 0x3) << 29;
	else
		value = (asid & 0x7f) << 24;

	value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_MATCH_ALL;
	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
}

static inline void smmu_flush_tlb_section(struct tegra_smmu *smmu,
					  unsigned long asid,
					  unsigned long iova)
{
	u32 value;

	if (smmu->soc->num_asids == 4)
		value = (asid & 0x3) << 29;
	else
		value = (asid & 0x7f) << 24;

	value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_SECTION(iova);
	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
}

static inline void smmu_flush_tlb_group(struct tegra_smmu *smmu,
					unsigned long asid,
					unsigned long iova)
{
	u32 value;

	if (smmu->soc->num_asids == 4)
		value = (asid & 0x3) << 29;
	else
		value = (asid & 0x7f) << 24;

	value |= SMMU_TLB_FLUSH_ASID_MATCH | SMMU_TLB_FLUSH_VA_GROUP(iova);
	smmu_writel(smmu, value, SMMU_TLB_FLUSH);
}

static inline void smmu_flush(struct tegra_smmu *smmu)
{
	smmu_readl(smmu, SMMU_PTB_ASID);
}

static int tegra_smmu_alloc_asid(struct tegra_smmu *smmu, unsigned int *idp)
{
	unsigned long id;

	mutex_lock(&smmu->lock);

	id = find_first_zero_bit(smmu->asids, smmu->soc->num_asids);
	if (id >= smmu->soc->num_asids) {
		mutex_unlock(&smmu->lock);
		return -ENOSPC;
	}

	set_bit(id, smmu->asids);
	*idp = id;

	mutex_unlock(&smmu->lock);
	return 0;
}

static void tegra_smmu_free_asid(struct tegra_smmu *smmu, unsigned int id)
{
	mutex_lock(&smmu->lock);
	clear_bit(id, smmu->asids);
	mutex_unlock(&smmu->lock);
}

static bool tegra_smmu_capable(enum iommu_cap cap)
{
	return false;
}

static struct iommu_domain *tegra_smmu_domain_alloc(unsigned type)
{
	struct tegra_smmu_as *as;

	if (type != IOMMU_DOMAIN_UNMANAGED)
		return NULL;

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

	as->attr = SMMU_PD_READABLE | SMMU_PD_WRITABLE | SMMU_PD_NONSECURE;

	as->pd = alloc_page(GFP_KERNEL | __GFP_DMA | __GFP_ZERO);
	if (!as->pd) {
		kfree(as);
		return NULL;
	}

	as->count = kcalloc(SMMU_NUM_PDE, sizeof(u32), GFP_KERNEL);
	if (!as->count) {
		__free_page(as->pd);
		kfree(as);
		return NULL;
	}

	as->pts = kcalloc(SMMU_NUM_PDE, sizeof(*as->pts), GFP_KERNEL);
	if (!as->pts) {
		kfree(as->count);
		__free_page(as->pd);
		kfree(as);
		return NULL;
	}

	/* setup aperture */
	as->domain.geometry.aperture_start = 0;
	as->domain.geometry.aperture_end = 0xffffffff;
	as->domain.geometry.force_aperture = true;

	return &as->domain;
}

static void tegra_smmu_domain_free(struct iommu_domain *domain)
{
	struct tegra_smmu_as *as = to_smmu_as(domain);

	/* TODO: free page directory and page tables */

	WARN_ON_ONCE(as->use_count);
	kfree(as->count);
	kfree(as->pts);
	kfree(as);
}

static const struct tegra_smmu_swgroup *
tegra_smmu_find_swgroup(struct tegra_smmu *smmu, unsigned int swgroup)
{
	const struct tegra_smmu_swgroup *group = NULL;
	unsigned int i;

	for (i = 0; i < smmu->soc->num_swgroups; i++) {
		if (smmu->soc->swgroups[i].swgroup == swgroup) {
			group = &smmu->soc->swgroups[i];
			break;
		}
	}

	return group;
}

static void tegra_smmu_enable(struct tegra_smmu *smmu, unsigned int swgroup,
			      unsigned int asid)
{
	const struct tegra_smmu_swgroup *group;
	unsigned int i;
	u32 value;

	group = tegra_smmu_find_swgroup(smmu, swgroup);
	if (group) {
		value = smmu_readl(smmu, group->reg);
		value &= ~SMMU_ASID_MASK;
		value |= SMMU_ASID_VALUE(asid);
		value |= SMMU_ASID_ENABLE;
		smmu_writel(smmu, value, group->reg);
	} else {
		pr_warn("%s group from swgroup %u not found\n", __func__,
				swgroup);
		/* No point moving ahead if group was not found */
		return;
	}

	for (i = 0; i < smmu->soc->num_clients; i++) {
		const struct tegra_mc_client *client = &smmu->soc->clients[i];

		if (client->swgroup != swgroup)
			continue;

		value = smmu_readl(smmu, client->smmu.reg);
		value |= BIT(client->smmu.bit);
		smmu_writel(smmu, value, client->smmu.reg);
	}
}

static void tegra_smmu_disable(struct tegra_smmu *smmu, unsigned int swgroup,
			       unsigned int asid)
{
	const struct tegra_smmu_swgroup *group;
	unsigned int i;
	u32 value;

	group = tegra_smmu_find_swgroup(smmu, swgroup);
	if (group) {
		value = smmu_readl(smmu, group->reg);
		value &= ~SMMU_ASID_MASK;
		value |= SMMU_ASID_VALUE(asid);
		value &= ~SMMU_ASID_ENABLE;
		smmu_writel(smmu, value, group->reg);
	}

	for (i = 0; i < smmu->soc->num_clients; i++) {
		const struct tegra_mc_client *client = &smmu->soc->clients[i];

		if (client->swgroup != swgroup)
			continue;

		value = smmu_readl(smmu, client->smmu.reg);
		value &= ~BIT(client->smmu.bit);
		smmu_writel(smmu, value, client->smmu.reg);
	}
}

static int tegra_smmu_as_prepare(struct tegra_smmu *smmu,
				 struct tegra_smmu_as *as)
{
	u32 value;
	int err;

	if (as->use_count > 0) {
		as->use_count++;
		return 0;
	}

	as->pd_dma = dma_map_page(smmu->dev, as->pd, 0, SMMU_SIZE_PD,
				  DMA_TO_DEVICE);
	if (dma_mapping_error(smmu->dev, as->pd_dma))
		return -ENOMEM;

	/* We can't handle 64-bit DMA addresses */
	if (!smmu_dma_addr_valid(smmu, as->pd_dma)) {
		err = -ENOMEM;
		goto err_unmap;
	}

	err = tegra_smmu_alloc_asid(smmu, &as->id);
	if (err < 0)
		goto err_unmap;

	smmu_flush_ptc(smmu, as->pd_dma, 0);
	smmu_flush_tlb_asid(smmu, as->id);

	smmu_writel(smmu, as->id & 0x7f, SMMU_PTB_ASID);
	value = SMMU_PTB_DATA_VALUE(as->pd_dma, as->attr);
	smmu_writel(smmu, value, SMMU_PTB_DATA);
	smmu_flush(smmu);

	as->smmu = smmu;
	as->use_count++;

	return 0;

err_unmap:
	dma_unmap_page(smmu->dev, as->pd_dma, SMMU_SIZE_PD, DMA_TO_DEVICE);
	return err;
}

static void tegra_smmu_as_unprepare(struct tegra_smmu *smmu,
				    struct tegra_smmu_as *as)
{
	if (--as->use_count > 0)
		return;

	tegra_smmu_free_asid(smmu, as->id);

	dma_unmap_page(smmu->dev, as->pd_dma, SMMU_SIZE_PD, DMA_TO_DEVICE);

	as->smmu = NULL;
}

static int tegra_smmu_attach_dev(struct iommu_domain *domain,
				 struct device *dev)
{
	struct tegra_smmu *smmu = dev_iommu_priv_get(dev);
	struct tegra_smmu_as *as = to_smmu_as(domain);
	struct device_node *np = dev->of_node;
	struct of_phandle_args args;
	unsigned int index = 0;
	int err = 0;

	while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
					   &args)) {
		unsigned int swgroup = args.args[0];

		if (args.np != smmu->dev->of_node) {
			of_node_put(args.np);
			continue;
		}

		of_node_put(args.np);

		err = tegra_smmu_as_prepare(smmu, as);
		if (err < 0)
			return err;

		tegra_smmu_enable(smmu, swgroup, as->id);
		index++;
	}

	if (index == 0)
		return -ENODEV;

	return 0;
}

static void tegra_smmu_detach_dev(struct iommu_domain *domain, struct device *dev)
{
	struct tegra_smmu_as *as = to_smmu_as(domain);
	struct device_node *np = dev->of_node;
	struct tegra_smmu *smmu = as->smmu;
	struct of_phandle_args args;
	unsigned int index = 0;

	while (!of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
					   &args)) {
		unsigned int swgroup = args.args[0];

		if (args.np != smmu->dev->of_node) {
			of_node_put(args.np);
			continue;
		}

		of_node_put(args.np);

		tegra_smmu_disable(smmu, swgroup, as->id);
		tegra_smmu_as_unprepare(smmu, as);
		index++;
	}
}

static void tegra_smmu_set_pde(struct tegra_smmu_as *as, unsigned long iova,
			       u32 value)
{
	unsigned int pd_index = iova_pd_index(iova);
	struct tegra_smmu *smmu = as->smmu;
	u32 *pd = page_address(as->pd);
	unsigned long offset = pd_index * sizeof(*pd);

	/* Set the page directory entry first */
	pd[pd_index] = value;

	/* The flush the page directory entry from caches */
	dma_sync_single_range_for_device(smmu->dev, as->pd_dma, offset,
					 sizeof(*pd), DMA_TO_DEVICE);

	/* And flush the iommu */
	smmu_flush_ptc(smmu, as->pd_dma, offset);
	smmu_flush_tlb_section(smmu, as->id, iova);
	smmu_flush(smmu);
}

static u32 *tegra_smmu_pte_offset(struct page *pt_page, unsigned long iova)
{
	u32 *pt = page_address(pt_page);

	return pt + iova_pt_index(iova);
}

static u32 *tegra_smmu_pte_lookup(struct tegra_smmu_as *as, unsigned long iova,
				  dma_addr_t *dmap)
{
	unsigned int pd_index = iova_pd_index(iova);
	struct tegra_smmu *smmu = as->smmu;
	struct page *pt_page;
	u32 *pd;

	pt_page = as->pts[pd_index];
	if (!pt_page)
		return NULL;

	pd = page_address(as->pd);
	*dmap = smmu_pde_to_dma(smmu, pd[pd_index]);

	return tegra_smmu_pte_offset(pt_page, iova);
}

static u32 *as_get_pte(struct tegra_smmu_as *as, dma_addr_t iova,
		       dma_addr_t *dmap)
{
	unsigned int pde = iova_pd_index(iova);
	struct tegra_smmu *smmu = as->smmu;

	if (!as->pts[pde]) {
		struct page *page;
		dma_addr_t dma;

		page = alloc_page(GFP_KERNEL | __GFP_DMA | __GFP_ZERO);
		if (!page)
			return NULL;

		dma = dma_map_page(smmu->dev, page, 0, SMMU_SIZE_PT,
				   DMA_TO_DEVICE);
		if (dma_mapping_error(smmu->dev, dma)) {
			__free_page(page);
			return NULL;
		}

		if (!smmu_dma_addr_valid(smmu, dma)) {
			dma_unmap_page(smmu->dev, dma, SMMU_SIZE_PT,
				       DMA_TO_DEVICE);
			__free_page(page);
			return NULL;
		}

		as->pts[pde] = page;

		tegra_smmu_set_pde(as, iova, SMMU_MK_PDE(dma, SMMU_PDE_ATTR |
							      SMMU_PDE_NEXT));

		*dmap = dma;
	} else {
		u32 *pd = page_address(as->pd);

		*dmap = smmu_pde_to_dma(smmu, pd[pde]);
	}

	return tegra_smmu_pte_offset(as->pts[pde], iova);
}

static void tegra_smmu_pte_get_use(struct tegra_smmu_as *as, unsigned long iova)
{
	unsigned int pd_index = iova_pd_index(iova);

	as->count[pd_index]++;
}

static void tegra_smmu_pte_put_use(struct tegra_smmu_as *as, unsigned long iova)
{
	unsigned int pde = iova_pd_index(iova);
	struct page *page = as->pts[pde];

	/*
	 * When no entries in this page table are used anymore, return the
	 * memory page to the system.
	 */
	if (--as->count[pde] == 0) {
		struct tegra_smmu *smmu = as->smmu;
		u32 *pd = page_address(as->pd);
		dma_addr_t pte_dma = smmu_pde_to_dma(smmu, pd[pde]);

		tegra_smmu_set_pde(as, iova, 0);

		dma_unmap_page(smmu->dev, pte_dma, SMMU_SIZE_PT, DMA_TO_DEVICE);
		__free_page(page);
		as->pts[pde] = NULL;
	}
}

static void tegra_smmu_set_pte(struct tegra_smmu_as *as, unsigned long iova,
			       u32 *pte, dma_addr_t pte_dma, u32 val)
{
	struct tegra_smmu *smmu = as->smmu;
	unsigned long offset = offset_in_page(pte);

	*pte = val;

	dma_sync_single_range_for_device(smmu->dev, pte_dma, offset,
					 4, DMA_TO_DEVICE);
	smmu_flush_ptc(smmu, pte_dma, offset);
	smmu_flush_tlb_group(smmu, as->id, iova);
	smmu_flush(smmu);
}

static int tegra_smmu_map(struct iommu_domain *domain, unsigned long iova,
			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
	struct tegra_smmu_as *as = to_smmu_as(domain);
	dma_addr_t pte_dma;
	u32 pte_attrs;
	u32 *pte;

	pte = as_get_pte(as, iova, &pte_dma);
	if (!pte)
		return -ENOMEM;

	/* If we aren't overwriting a pre-existing entry, increment use */
	if (*pte == 0)
		tegra_smmu_pte_get_use(as, iova);

	pte_attrs = SMMU_PTE_NONSECURE;

	if (prot & IOMMU_READ)
		pte_attrs |= SMMU_PTE_READABLE;

	if (prot & IOMMU_WRITE)
		pte_attrs |= SMMU_PTE_WRITABLE;

	tegra_smmu_set_pte(as, iova, pte, pte_dma,
			   __phys_to_pfn(paddr) | pte_attrs);

	return 0;
}

static size_t tegra_smmu_unmap(struct iommu_domain *domain, unsigned long iova,
			       size_t size, struct iommu_iotlb_gather *gather)
{
	struct tegra_smmu_as *as = to_smmu_as(domain);
	dma_addr_t pte_dma;
	u32 *pte;

	pte = tegra_smmu_pte_lookup(as, iova, &pte_dma);
	if (!pte || !*pte)
		return 0;

	tegra_smmu_set_pte(as, iova, pte, pte_dma, 0);
	tegra_smmu_pte_put_use(as, iova);

	return size;
}

static phys_addr_t tegra_smmu_iova_to_phys(struct iommu_domain *domain,
					   dma_addr_t iova)
{
	struct tegra_smmu_as *as = to_smmu_as(domain);
	unsigned long pfn;
	dma_addr_t pte_dma;
	u32 *pte;

	pte = tegra_smmu_pte_lookup(as, iova, &pte_dma);
	if (!pte || !*pte)
		return 0;

	pfn = *pte & as->smmu->pfn_mask;

	return PFN_PHYS(pfn);
}

static struct tegra_smmu *tegra_smmu_find(struct device_node *np)
{
	struct platform_device *pdev;
	struct tegra_mc *mc;

	pdev = of_find_device_by_node(np);
	if (!pdev)
		return NULL;

	mc = platform_get_drvdata(pdev);
	if (!mc)
		return NULL;

	return mc->smmu;
}

static int tegra_smmu_configure(struct tegra_smmu *smmu, struct device *dev,
				struct of_phandle_args *args)
{
	const struct iommu_ops *ops = smmu->iommu.ops;
	int err;

	err = iommu_fwspec_init(dev, &dev->of_node->fwnode, ops);
	if (err < 0) {
		dev_err(dev, "failed to initialize fwspec: %d\n", err);
		return err;
	}

	err = ops->of_xlate(dev, args);
	if (err < 0) {
		dev_err(dev, "failed to parse SW group ID: %d\n", err);
		iommu_fwspec_free(dev);
		return err;
	}

	return 0;
}

static struct iommu_device *tegra_smmu_probe_device(struct device *dev)
{
	struct device_node *np = dev->of_node;
	struct tegra_smmu *smmu = NULL;
	struct of_phandle_args args;
	unsigned int index = 0;
	int err;

	while (of_parse_phandle_with_args(np, "iommus", "#iommu-cells", index,
					  &args) == 0) {
		smmu = tegra_smmu_find(args.np);
		if (smmu) {
			err = tegra_smmu_configure(smmu, dev, &args);
			of_node_put(args.np);

			if (err < 0)
				return ERR_PTR(err);

			/*
			 * Only a single IOMMU master interface is currently
			 * supported by the Linux kernel, so abort after the
			 * first match.
			 */
			dev_iommu_priv_set(dev, smmu);

			break;
		}

		of_node_put(args.np);
		index++;
	}

	if (!smmu)
		return ERR_PTR(-ENODEV);

	return &smmu->iommu;
}

static void tegra_smmu_release_device(struct device *dev)
{
	dev_iommu_priv_set(dev, NULL);
}

static const struct tegra_smmu_group_soc *
tegra_smmu_find_group(struct tegra_smmu *smmu, unsigned int swgroup)
{
	unsigned int i, j;

	for (i = 0; i < smmu->soc->num_groups; i++)
		for (j = 0; j < smmu->soc->groups[i].num_swgroups; j++)
			if (smmu->soc->groups[i].swgroups[j] == swgroup)
				return &smmu->soc->groups[i];

	return NULL;
}

static struct iommu_group *tegra_smmu_group_get(struct tegra_smmu *smmu,
						unsigned int swgroup)
{
	const struct tegra_smmu_group_soc *soc;
	struct tegra_smmu_group *group;

	soc = tegra_smmu_find_group(smmu, swgroup);
	if (!soc)
		return NULL;

	mutex_lock(&smmu->lock);

	list_for_each_entry(group, &smmu->groups, list)
		if (group->soc == soc) {
			mutex_unlock(&smmu->lock);
			return group->group;
		}

	group = devm_kzalloc(smmu->dev, sizeof(*group), GFP_KERNEL);
	if (!group) {
		mutex_unlock(&smmu->lock);
		return NULL;
	}

	INIT_LIST_HEAD(&group->list);
	group->soc = soc;

	group->group = iommu_group_alloc();
	if (IS_ERR(group->group)) {
		devm_kfree(smmu->dev, group);
		mutex_unlock(&smmu->lock);
		return NULL;
	}

	list_add_tail(&group->list, &smmu->groups);
	mutex_unlock(&smmu->lock);

	return group->group;
}

static struct iommu_group *tegra_smmu_device_group(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	struct tegra_smmu *smmu = dev_iommu_priv_get(dev);
	struct iommu_group *group;

	group = tegra_smmu_group_get(smmu, fwspec->ids[0]);
	if (!group)
		group = generic_device_group(dev);

	return group;
}

static int tegra_smmu_of_xlate(struct device *dev,
			       struct of_phandle_args *args)
{
	u32 id = args->args[0];

	return iommu_fwspec_add_ids(dev, &id, 1);
}

static const struct iommu_ops tegra_smmu_ops = {
	.capable = tegra_smmu_capable,
	.domain_alloc = tegra_smmu_domain_alloc,
	.domain_free = tegra_smmu_domain_free,
	.attach_dev = tegra_smmu_attach_dev,
	.detach_dev = tegra_smmu_detach_dev,
	.probe_device = tegra_smmu_probe_device,
	.release_device = tegra_smmu_release_device,
	.device_group = tegra_smmu_device_group,
	.map = tegra_smmu_map,
	.unmap = tegra_smmu_unmap,
	.iova_to_phys = tegra_smmu_iova_to_phys,
	.of_xlate = tegra_smmu_of_xlate,
	.pgsize_bitmap = SZ_4K,
};

static void tegra_smmu_ahb_enable(void)
{
	static const struct of_device_id ahb_match[] = {
		{ .compatible = "nvidia,tegra30-ahb", },
		{ }
	};
	struct device_node *ahb;

	ahb = of_find_matching_node(NULL, ahb_match);
	if (ahb) {
		tegra_ahb_enable_smmu(ahb);
		of_node_put(ahb);
	}
}

static int tegra_smmu_swgroups_show(struct seq_file *s, void *data)
{
	struct tegra_smmu *smmu = s->private;
	unsigned int i;
	u32 value;

	seq_printf(s, "swgroup    enabled  ASID\n");
	seq_printf(s, "------------------------\n");

	for (i = 0; i < smmu->soc->num_swgroups; i++) {
		const struct tegra_smmu_swgroup *group = &smmu->soc->swgroups[i];
		const char *status;
		unsigned int asid;

		value = smmu_readl(smmu, group->reg);

		if (value & SMMU_ASID_ENABLE)
			status = "yes";
		else
			status = "no";

		asid = value & SMMU_ASID_MASK;

		seq_printf(s, "%-9s  %-7s  %#04x\n", group->name, status,
			   asid);
	}

	return 0;
}

DEFINE_SHOW_ATTRIBUTE(tegra_smmu_swgroups);

static int tegra_smmu_clients_show(struct seq_file *s, void *data)
{
	struct tegra_smmu *smmu = s->private;
	unsigned int i;
	u32 value;

	seq_printf(s, "client       enabled\n");
	seq_printf(s, "--------------------\n");

	for (i = 0; i < smmu->soc->num_clients; i++) {
		const struct tegra_mc_client *client = &smmu->soc->clients[i];
		const char *status;

		value = smmu_readl(smmu, client->smmu.reg);

		if (value & BIT(client->smmu.bit))
			status = "yes";
		else
			status = "no";

		seq_printf(s, "%-12s %s\n", client->name, status);
	}

	return 0;
}

DEFINE_SHOW_ATTRIBUTE(tegra_smmu_clients);

static void tegra_smmu_debugfs_init(struct tegra_smmu *smmu)
{
	smmu->debugfs = debugfs_create_dir("smmu", NULL);
	if (!smmu->debugfs)
		return;

	debugfs_create_file("swgroups", S_IRUGO, smmu->debugfs, smmu,
			    &tegra_smmu_swgroups_fops);
	debugfs_create_file("clients", S_IRUGO, smmu->debugfs, smmu,
			    &tegra_smmu_clients_fops);
}

static void tegra_smmu_debugfs_exit(struct tegra_smmu *smmu)
{
	debugfs_remove_recursive(smmu->debugfs);
}

struct tegra_smmu *tegra_smmu_probe(struct device *dev,
				    const struct tegra_smmu_soc *soc,
				    struct tegra_mc *mc)
{
	struct tegra_smmu *smmu;
	size_t size;
	u32 value;
	int err;

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

	/*
	 * This is a bit of a hack. Ideally we'd want to simply return this
	 * value. However the IOMMU registration process will attempt to add
	 * all devices to the IOMMU when bus_set_iommu() is called. In order
	 * not to rely on global variables to track the IOMMU instance, we
	 * set it here so that it can be looked up from the .probe_device()
	 * callback via the IOMMU device's .drvdata field.
	 */
	mc->smmu = smmu;

	size = BITS_TO_LONGS(soc->num_asids) * sizeof(long);

	smmu->asids = devm_kzalloc(dev, size, GFP_KERNEL);
	if (!smmu->asids)
		return ERR_PTR(-ENOMEM);

	INIT_LIST_HEAD(&smmu->groups);
	mutex_init(&smmu->lock);

	smmu->regs = mc->regs;
	smmu->soc = soc;
	smmu->dev = dev;
	smmu->mc = mc;

	smmu->pfn_mask = BIT_MASK(mc->soc->num_address_bits - PAGE_SHIFT) - 1;
	dev_dbg(dev, "address bits: %u, PFN mask: %#lx\n",
		mc->soc->num_address_bits, smmu->pfn_mask);
	smmu->tlb_mask = (smmu->soc->num_tlb_lines << 1) - 1;
	dev_dbg(dev, "TLB lines: %u, mask: %#lx\n", smmu->soc->num_tlb_lines,
		smmu->tlb_mask);

	value = SMMU_PTC_CONFIG_ENABLE | SMMU_PTC_CONFIG_INDEX_MAP(0x3f);

	if (soc->supports_request_limit)
		value |= SMMU_PTC_CONFIG_REQ_LIMIT(8);

	smmu_writel(smmu, value, SMMU_PTC_CONFIG);

	value = SMMU_TLB_CONFIG_HIT_UNDER_MISS |
		SMMU_TLB_CONFIG_ACTIVE_LINES(smmu);

	if (soc->supports_round_robin_arbitration)
		value |= SMMU_TLB_CONFIG_ROUND_ROBIN_ARBITRATION;

	smmu_writel(smmu, value, SMMU_TLB_CONFIG);

	smmu_flush_ptc_all(smmu);
	smmu_flush_tlb(smmu);
	smmu_writel(smmu, SMMU_CONFIG_ENABLE, SMMU_CONFIG);
	smmu_flush(smmu);

	tegra_smmu_ahb_enable();

	err = iommu_device_sysfs_add(&smmu->iommu, dev, NULL, dev_name(dev));
	if (err)
		return ERR_PTR(err);

	iommu_device_set_ops(&smmu->iommu, &tegra_smmu_ops);
	iommu_device_set_fwnode(&smmu->iommu, dev->fwnode);

	err = iommu_device_register(&smmu->iommu);
	if (err) {
		iommu_device_sysfs_remove(&smmu->iommu);
		return ERR_PTR(err);
	}

	err = bus_set_iommu(&platform_bus_type, &tegra_smmu_ops);
	if (err < 0) {
		iommu_device_unregister(&smmu->iommu);
		iommu_device_sysfs_remove(&smmu->iommu);
		return ERR_PTR(err);
	}

	if (IS_ENABLED(CONFIG_DEBUG_FS))
		tegra_smmu_debugfs_init(smmu);

	return smmu;
}

void tegra_smmu_remove(struct tegra_smmu *smmu)
{
	iommu_device_unregister(&smmu->iommu);
	iommu_device_sysfs_remove(&smmu->iommu);

	if (IS_ENABLED(CONFIG_DEBUG_FS))
		tegra_smmu_debugfs_exit(smmu);
}