summaryrefslogtreecommitdiff
path: root/drivers/iommu/ipmmu-vmsa.c
blob: 2a38aa15be17d1810382f5d1dd6c0ee982fd084b (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
/*
 * IPMMU VMSA
 *
 * Copyright (C) 2014 Renesas Electronics Corporation
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; version 2 of the License.
 */

#include <linux/bitmap.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#include <linux/dma-mapping.h>
#include <linux/err.h>
#include <linux/export.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
#include <linux/sizes.h>
#include <linux/slab.h>

#if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)
#include <asm/dma-iommu.h>
#include <asm/pgalloc.h>
#endif

#include "io-pgtable.h"

#define IPMMU_CTX_MAX 1

struct ipmmu_vmsa_device {
	struct device *dev;
	void __iomem *base;
	struct list_head list;

	unsigned int num_utlbs;
	spinlock_t lock;			/* Protects ctx and domains[] */
	DECLARE_BITMAP(ctx, IPMMU_CTX_MAX);
	struct ipmmu_vmsa_domain *domains[IPMMU_CTX_MAX];

	struct dma_iommu_mapping *mapping;
};

struct ipmmu_vmsa_domain {
	struct ipmmu_vmsa_device *mmu;
	struct iommu_domain io_domain;

	struct io_pgtable_cfg cfg;
	struct io_pgtable_ops *iop;

	unsigned int context_id;
	spinlock_t lock;			/* Protects mappings */
};

struct ipmmu_vmsa_iommu_priv {
	struct ipmmu_vmsa_device *mmu;
	unsigned int *utlbs;
	unsigned int num_utlbs;
	struct device *dev;
	struct list_head list;
};

static DEFINE_SPINLOCK(ipmmu_devices_lock);
static LIST_HEAD(ipmmu_devices);

static struct ipmmu_vmsa_domain *to_vmsa_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct ipmmu_vmsa_domain, io_domain);
}


static struct ipmmu_vmsa_iommu_priv *to_priv(struct device *dev)
{
#if defined(CONFIG_ARM)
	return dev->archdata.iommu;
#else
	return dev->iommu_fwspec->iommu_priv;
#endif
}
static void set_priv(struct device *dev, struct ipmmu_vmsa_iommu_priv *p)
{
#if defined(CONFIG_ARM)
	dev->archdata.iommu = p;
#else
	dev->iommu_fwspec->iommu_priv = p;
#endif
}

#define TLB_LOOP_TIMEOUT		100	/* 100us */

/* -----------------------------------------------------------------------------
 * Registers Definition
 */

#define IM_NS_ALIAS_OFFSET		0x800

#define IM_CTX_SIZE			0x40

#define IMCTR				0x0000
#define IMCTR_TRE			(1 << 17)
#define IMCTR_AFE			(1 << 16)
#define IMCTR_RTSEL_MASK		(3 << 4)
#define IMCTR_RTSEL_SHIFT		4
#define IMCTR_TREN			(1 << 3)
#define IMCTR_INTEN			(1 << 2)
#define IMCTR_FLUSH			(1 << 1)
#define IMCTR_MMUEN			(1 << 0)

#define IMCAAR				0x0004

#define IMTTBCR				0x0008
#define IMTTBCR_EAE			(1 << 31)
#define IMTTBCR_PMB			(1 << 30)
#define IMTTBCR_SH1_NON_SHAREABLE	(0 << 28)
#define IMTTBCR_SH1_OUTER_SHAREABLE	(2 << 28)
#define IMTTBCR_SH1_INNER_SHAREABLE	(3 << 28)
#define IMTTBCR_SH1_MASK		(3 << 28)
#define IMTTBCR_ORGN1_NC		(0 << 26)
#define IMTTBCR_ORGN1_WB_WA		(1 << 26)
#define IMTTBCR_ORGN1_WT		(2 << 26)
#define IMTTBCR_ORGN1_WB		(3 << 26)
#define IMTTBCR_ORGN1_MASK		(3 << 26)
#define IMTTBCR_IRGN1_NC		(0 << 24)
#define IMTTBCR_IRGN1_WB_WA		(1 << 24)
#define IMTTBCR_IRGN1_WT		(2 << 24)
#define IMTTBCR_IRGN1_WB		(3 << 24)
#define IMTTBCR_IRGN1_MASK		(3 << 24)
#define IMTTBCR_TSZ1_MASK		(7 << 16)
#define IMTTBCR_TSZ1_SHIFT		16
#define IMTTBCR_SH0_NON_SHAREABLE	(0 << 12)
#define IMTTBCR_SH0_OUTER_SHAREABLE	(2 << 12)
#define IMTTBCR_SH0_INNER_SHAREABLE	(3 << 12)
#define IMTTBCR_SH0_MASK		(3 << 12)
#define IMTTBCR_ORGN0_NC		(0 << 10)
#define IMTTBCR_ORGN0_WB_WA		(1 << 10)
#define IMTTBCR_ORGN0_WT		(2 << 10)
#define IMTTBCR_ORGN0_WB		(3 << 10)
#define IMTTBCR_ORGN0_MASK		(3 << 10)
#define IMTTBCR_IRGN0_NC		(0 << 8)
#define IMTTBCR_IRGN0_WB_WA		(1 << 8)
#define IMTTBCR_IRGN0_WT		(2 << 8)
#define IMTTBCR_IRGN0_WB		(3 << 8)
#define IMTTBCR_IRGN0_MASK		(3 << 8)
#define IMTTBCR_SL0_LVL_2		(0 << 4)
#define IMTTBCR_SL0_LVL_1		(1 << 4)
#define IMTTBCR_TSZ0_MASK		(7 << 0)
#define IMTTBCR_TSZ0_SHIFT		O

#define IMBUSCR				0x000c
#define IMBUSCR_DVM			(1 << 2)
#define IMBUSCR_BUSSEL_SYS		(0 << 0)
#define IMBUSCR_BUSSEL_CCI		(1 << 0)
#define IMBUSCR_BUSSEL_IMCAAR		(2 << 0)
#define IMBUSCR_BUSSEL_CCI_IMCAAR	(3 << 0)
#define IMBUSCR_BUSSEL_MASK		(3 << 0)

#define IMTTLBR0			0x0010
#define IMTTUBR0			0x0014
#define IMTTLBR1			0x0018
#define IMTTUBR1			0x001c

#define IMSTR				0x0020
#define IMSTR_ERRLVL_MASK		(3 << 12)
#define IMSTR_ERRLVL_SHIFT		12
#define IMSTR_ERRCODE_TLB_FORMAT	(1 << 8)
#define IMSTR_ERRCODE_ACCESS_PERM	(4 << 8)
#define IMSTR_ERRCODE_SECURE_ACCESS	(5 << 8)
#define IMSTR_ERRCODE_MASK		(7 << 8)
#define IMSTR_MHIT			(1 << 4)
#define IMSTR_ABORT			(1 << 2)
#define IMSTR_PF			(1 << 1)
#define IMSTR_TF			(1 << 0)

#define IMMAIR0				0x0028
#define IMMAIR1				0x002c
#define IMMAIR_ATTR_MASK		0xff
#define IMMAIR_ATTR_DEVICE		0x04
#define IMMAIR_ATTR_NC			0x44
#define IMMAIR_ATTR_WBRWA		0xff
#define IMMAIR_ATTR_SHIFT(n)		((n) << 3)
#define IMMAIR_ATTR_IDX_NC		0
#define IMMAIR_ATTR_IDX_WBRWA		1
#define IMMAIR_ATTR_IDX_DEV		2

#define IMEAR				0x0030

#define IMPCTR				0x0200
#define IMPSTR				0x0208
#define IMPEAR				0x020c
#define IMPMBA(n)			(0x0280 + ((n) * 4))
#define IMPMBD(n)			(0x02c0 + ((n) * 4))

#define IMUCTR(n)			(0x0300 + ((n) * 16))
#define IMUCTR_FIXADDEN			(1 << 31)
#define IMUCTR_FIXADD_MASK		(0xff << 16)
#define IMUCTR_FIXADD_SHIFT		16
#define IMUCTR_TTSEL_MMU(n)		((n) << 4)
#define IMUCTR_TTSEL_PMB		(8 << 4)
#define IMUCTR_TTSEL_MASK		(15 << 4)
#define IMUCTR_FLUSH			(1 << 1)
#define IMUCTR_MMUEN			(1 << 0)

#define IMUASID(n)			(0x0308 + ((n) * 16))
#define IMUASID_ASID8_MASK		(0xff << 8)
#define IMUASID_ASID8_SHIFT		8
#define IMUASID_ASID0_MASK		(0xff << 0)
#define IMUASID_ASID0_SHIFT		0

/* -----------------------------------------------------------------------------
 * Read/Write Access
 */

static u32 ipmmu_read(struct ipmmu_vmsa_device *mmu, unsigned int offset)
{
	return ioread32(mmu->base + offset);
}

static void ipmmu_write(struct ipmmu_vmsa_device *mmu, unsigned int offset,
			u32 data)
{
	iowrite32(data, mmu->base + offset);
}

static u32 ipmmu_ctx_read(struct ipmmu_vmsa_domain *domain, unsigned int reg)
{
	return ipmmu_read(domain->mmu, domain->context_id * IM_CTX_SIZE + reg);
}

static void ipmmu_ctx_write(struct ipmmu_vmsa_domain *domain, unsigned int reg,
			    u32 data)
{
	ipmmu_write(domain->mmu, domain->context_id * IM_CTX_SIZE + reg, data);
}

/* -----------------------------------------------------------------------------
 * TLB and microTLB Management
 */

/* Wait for any pending TLB invalidations to complete */
static void ipmmu_tlb_sync(struct ipmmu_vmsa_domain *domain)
{
	unsigned int count = 0;

	while (ipmmu_ctx_read(domain, IMCTR) & IMCTR_FLUSH) {
		cpu_relax();
		if (++count == TLB_LOOP_TIMEOUT) {
			dev_err_ratelimited(domain->mmu->dev,
			"TLB sync timed out -- MMU may be deadlocked\n");
			return;
		}
		udelay(1);
	}
}

static void ipmmu_tlb_invalidate(struct ipmmu_vmsa_domain *domain)
{
	u32 reg;

	reg = ipmmu_ctx_read(domain, IMCTR);
	reg |= IMCTR_FLUSH;
	ipmmu_ctx_write(domain, IMCTR, reg);

	ipmmu_tlb_sync(domain);
}

/*
 * Enable MMU translation for the microTLB.
 */
static void ipmmu_utlb_enable(struct ipmmu_vmsa_domain *domain,
			      unsigned int utlb)
{
	struct ipmmu_vmsa_device *mmu = domain->mmu;

	/*
	 * TODO: Reference-count the microTLB as several bus masters can be
	 * connected to the same microTLB.
	 */

	/* TODO: What should we set the ASID to ? */
	ipmmu_write(mmu, IMUASID(utlb), 0);
	/* TODO: Do we need to flush the microTLB ? */
	ipmmu_write(mmu, IMUCTR(utlb),
		    IMUCTR_TTSEL_MMU(domain->context_id) | IMUCTR_FLUSH |
		    IMUCTR_MMUEN);
}

/*
 * Disable MMU translation for the microTLB.
 */
static void ipmmu_utlb_disable(struct ipmmu_vmsa_domain *domain,
			       unsigned int utlb)
{
	struct ipmmu_vmsa_device *mmu = domain->mmu;

	ipmmu_write(mmu, IMUCTR(utlb), 0);
}

static void ipmmu_tlb_flush_all(void *cookie)
{
	struct ipmmu_vmsa_domain *domain = cookie;

	ipmmu_tlb_invalidate(domain);
}

static void ipmmu_tlb_add_flush(unsigned long iova, size_t size,
				size_t granule, bool leaf, void *cookie)
{
	/* The hardware doesn't support selective TLB flush. */
}

static struct iommu_gather_ops ipmmu_gather_ops = {
	.tlb_flush_all = ipmmu_tlb_flush_all,
	.tlb_add_flush = ipmmu_tlb_add_flush,
	.tlb_sync = ipmmu_tlb_flush_all,
};

/* -----------------------------------------------------------------------------
 * Domain/Context Management
 */

static int ipmmu_domain_allocate_context(struct ipmmu_vmsa_device *mmu,
					 struct ipmmu_vmsa_domain *domain)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&mmu->lock, flags);

	ret = find_first_zero_bit(mmu->ctx, IPMMU_CTX_MAX);
	if (ret != IPMMU_CTX_MAX) {
		mmu->domains[ret] = domain;
		set_bit(ret, mmu->ctx);
	}

	spin_unlock_irqrestore(&mmu->lock, flags);

	return ret;
}

static int ipmmu_domain_init_context(struct ipmmu_vmsa_domain *domain)
{
	u64 ttbr;
	int ret;

	/*
	 * Allocate the page table operations.
	 *
	 * VMSA states in section B3.6.3 "Control of Secure or Non-secure memory
	 * access, Long-descriptor format" that the NStable bit being set in a
	 * table descriptor will result in the NStable and NS bits of all child
	 * entries being ignored and considered as being set. The IPMMU seems
	 * not to comply with this, as it generates a secure access page fault
	 * if any of the NStable and NS bits isn't set when running in
	 * non-secure mode.
	 */
	domain->cfg.quirks = IO_PGTABLE_QUIRK_ARM_NS;
	domain->cfg.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K;
	domain->cfg.ias = 32;
	domain->cfg.oas = 40;
	domain->cfg.tlb = &ipmmu_gather_ops;
	domain->io_domain.geometry.aperture_end = DMA_BIT_MASK(32);
	domain->io_domain.geometry.force_aperture = true;
	/*
	 * TODO: Add support for coherent walk through CCI with DVM and remove
	 * cache handling. For now, delegate it to the io-pgtable code.
	 */
	domain->cfg.iommu_dev = domain->mmu->dev;

	domain->iop = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &domain->cfg,
					   domain);
	if (!domain->iop)
		return -EINVAL;

	/*
	 * Find an unused context.
	 */
	ret = ipmmu_domain_allocate_context(domain->mmu, domain);
	if (ret == IPMMU_CTX_MAX) {
		free_io_pgtable_ops(domain->iop);
		return -EBUSY;
	}

	domain->context_id = ret;

	/* TTBR0 */
	ttbr = domain->cfg.arm_lpae_s1_cfg.ttbr[0];
	ipmmu_ctx_write(domain, IMTTLBR0, ttbr);
	ipmmu_ctx_write(domain, IMTTUBR0, ttbr >> 32);

	/*
	 * TTBCR
	 * We use long descriptors with inner-shareable WBWA tables and allocate
	 * the whole 32-bit VA space to TTBR0.
	 */
	ipmmu_ctx_write(domain, IMTTBCR, IMTTBCR_EAE |
			IMTTBCR_SH0_INNER_SHAREABLE | IMTTBCR_ORGN0_WB_WA |
			IMTTBCR_IRGN0_WB_WA | IMTTBCR_SL0_LVL_1);

	/* MAIR0 */
	ipmmu_ctx_write(domain, IMMAIR0, domain->cfg.arm_lpae_s1_cfg.mair[0]);

	/* IMBUSCR */
	ipmmu_ctx_write(domain, IMBUSCR,
			ipmmu_ctx_read(domain, IMBUSCR) &
			~(IMBUSCR_DVM | IMBUSCR_BUSSEL_MASK));

	/*
	 * IMSTR
	 * Clear all interrupt flags.
	 */
	ipmmu_ctx_write(domain, IMSTR, ipmmu_ctx_read(domain, IMSTR));

	/*
	 * IMCTR
	 * Enable the MMU and interrupt generation. The long-descriptor
	 * translation table format doesn't use TEX remapping. Don't enable AF
	 * software management as we have no use for it. Flush the TLB as
	 * required when modifying the context registers.
	 */
	ipmmu_ctx_write(domain, IMCTR, IMCTR_INTEN | IMCTR_FLUSH | IMCTR_MMUEN);

	return 0;
}

static void ipmmu_domain_free_context(struct ipmmu_vmsa_device *mmu,
				      unsigned int context_id)
{
	unsigned long flags;

	spin_lock_irqsave(&mmu->lock, flags);

	clear_bit(context_id, mmu->ctx);
	mmu->domains[context_id] = NULL;

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

static void ipmmu_domain_destroy_context(struct ipmmu_vmsa_domain *domain)
{
	/*
	 * Disable the context. Flush the TLB as required when modifying the
	 * context registers.
	 *
	 * TODO: Is TLB flush really needed ?
	 */
	ipmmu_ctx_write(domain, IMCTR, IMCTR_FLUSH);
	ipmmu_tlb_sync(domain);
	ipmmu_domain_free_context(domain->mmu, domain->context_id);
}

/* -----------------------------------------------------------------------------
 * Fault Handling
 */

static irqreturn_t ipmmu_domain_irq(struct ipmmu_vmsa_domain *domain)
{
	const u32 err_mask = IMSTR_MHIT | IMSTR_ABORT | IMSTR_PF | IMSTR_TF;
	struct ipmmu_vmsa_device *mmu = domain->mmu;
	u32 status;
	u32 iova;

	status = ipmmu_ctx_read(domain, IMSTR);
	if (!(status & err_mask))
		return IRQ_NONE;

	iova = ipmmu_ctx_read(domain, IMEAR);

	/*
	 * Clear the error status flags. Unlike traditional interrupt flag
	 * registers that must be cleared by writing 1, this status register
	 * seems to require 0. The error address register must be read before,
	 * otherwise its value will be 0.
	 */
	ipmmu_ctx_write(domain, IMSTR, 0);

	/* Log fatal errors. */
	if (status & IMSTR_MHIT)
		dev_err_ratelimited(mmu->dev, "Multiple TLB hits @0x%08x\n",
				    iova);
	if (status & IMSTR_ABORT)
		dev_err_ratelimited(mmu->dev, "Page Table Walk Abort @0x%08x\n",
				    iova);

	if (!(status & (IMSTR_PF | IMSTR_TF)))
		return IRQ_NONE;

	/*
	 * Try to handle page faults and translation faults.
	 *
	 * TODO: We need to look up the faulty device based on the I/O VA. Use
	 * the IOMMU device for now.
	 */
	if (!report_iommu_fault(&domain->io_domain, mmu->dev, iova, 0))
		return IRQ_HANDLED;

	dev_err_ratelimited(mmu->dev,
			    "Unhandled fault: status 0x%08x iova 0x%08x\n",
			    status, iova);

	return IRQ_HANDLED;
}

static irqreturn_t ipmmu_irq(int irq, void *dev)
{
	struct ipmmu_vmsa_device *mmu = dev;
	irqreturn_t status = IRQ_NONE;
	unsigned int i;
	unsigned long flags;

	spin_lock_irqsave(&mmu->lock, flags);

	/*
	 * Check interrupts for all active contexts.
	 */
	for (i = 0; i < IPMMU_CTX_MAX; i++) {
		if (!mmu->domains[i])
			continue;
		if (ipmmu_domain_irq(mmu->domains[i]) == IRQ_HANDLED)
			status = IRQ_HANDLED;
	}

	spin_unlock_irqrestore(&mmu->lock, flags);

	return status;
}

/* -----------------------------------------------------------------------------
 * IOMMU Operations
 */

static struct iommu_domain *__ipmmu_domain_alloc(unsigned type)
{
	struct ipmmu_vmsa_domain *domain;

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

	spin_lock_init(&domain->lock);

	return &domain->io_domain;
}

static void ipmmu_domain_free(struct iommu_domain *io_domain)
{
	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);

	/*
	 * Free the domain resources. We assume that all devices have already
	 * been detached.
	 */
	ipmmu_domain_destroy_context(domain);
	free_io_pgtable_ops(domain->iop);
	kfree(domain);
}

static int ipmmu_attach_device(struct iommu_domain *io_domain,
			       struct device *dev)
{
	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);
	struct ipmmu_vmsa_device *mmu = priv->mmu;
	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
	unsigned long flags;
	unsigned int i;
	int ret = 0;

	if (!mmu) {
		dev_err(dev, "Cannot attach to IPMMU\n");
		return -ENXIO;
	}

	spin_lock_irqsave(&domain->lock, flags);

	if (!domain->mmu) {
		/* The domain hasn't been used yet, initialize it. */
		domain->mmu = mmu;
		ret = ipmmu_domain_init_context(domain);
	} else if (domain->mmu != mmu) {
		/*
		 * Something is wrong, we can't attach two devices using
		 * different IOMMUs to the same domain.
		 */
		dev_err(dev, "Can't attach IPMMU %s to domain on IPMMU %s\n",
			dev_name(mmu->dev), dev_name(domain->mmu->dev));
		ret = -EINVAL;
	} else
		dev_info(dev, "Reusing IPMMU context %u\n", domain->context_id);

	spin_unlock_irqrestore(&domain->lock, flags);

	if (ret < 0)
		return ret;

	for (i = 0; i < priv->num_utlbs; ++i)
		ipmmu_utlb_enable(domain, priv->utlbs[i]);

	return 0;
}

static void ipmmu_detach_device(struct iommu_domain *io_domain,
				struct device *dev)
{
	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);
	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);
	unsigned int i;

	for (i = 0; i < priv->num_utlbs; ++i)
		ipmmu_utlb_disable(domain, priv->utlbs[i]);

	/*
	 * TODO: Optimize by disabling the context when no device is attached.
	 */
}

static int ipmmu_map(struct iommu_domain *io_domain, unsigned long iova,
		     phys_addr_t paddr, size_t size, int prot)
{
	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);

	if (!domain)
		return -ENODEV;

	return domain->iop->map(domain->iop, iova, paddr, size, prot);
}

static size_t ipmmu_unmap(struct iommu_domain *io_domain, unsigned long iova,
			  size_t size)
{
	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);

	return domain->iop->unmap(domain->iop, iova, size);
}

static phys_addr_t ipmmu_iova_to_phys(struct iommu_domain *io_domain,
				      dma_addr_t iova)
{
	struct ipmmu_vmsa_domain *domain = to_vmsa_domain(io_domain);

	/* TODO: Is locking needed ? */

	return domain->iop->iova_to_phys(domain->iop, iova);
}

static int ipmmu_find_utlbs(struct ipmmu_vmsa_device *mmu, struct device *dev,
			    unsigned int *utlbs, unsigned int num_utlbs)
{
	unsigned int i;

	for (i = 0; i < num_utlbs; ++i) {
		struct of_phandle_args args;
		int ret;

		ret = of_parse_phandle_with_args(dev->of_node, "iommus",
						 "#iommu-cells", i, &args);
		if (ret < 0)
			return ret;

		of_node_put(args.np);

		if (args.np != mmu->dev->of_node || args.args_count != 1)
			return -EINVAL;

		utlbs[i] = args.args[0];
	}

	return 0;
}

static int ipmmu_init_platform_device(struct device *dev)
{
	struct ipmmu_vmsa_iommu_priv *priv;
	struct ipmmu_vmsa_device *mmu;
	unsigned int *utlbs;
	unsigned int i;
	int num_utlbs;
	int ret = -ENODEV;

	/* Find the master corresponding to the device. */

	num_utlbs = of_count_phandle_with_args(dev->of_node, "iommus",
					       "#iommu-cells");
	if (num_utlbs < 0)
		return -ENODEV;

	utlbs = kcalloc(num_utlbs, sizeof(*utlbs), GFP_KERNEL);
	if (!utlbs)
		return -ENOMEM;

	spin_lock(&ipmmu_devices_lock);

	list_for_each_entry(mmu, &ipmmu_devices, list) {
		ret = ipmmu_find_utlbs(mmu, dev, utlbs, num_utlbs);
		if (!ret) {
			/*
			 * TODO Take a reference to the MMU to protect
			 * against device removal.
			 */
			break;
		}
	}

	spin_unlock(&ipmmu_devices_lock);

	if (ret < 0)
		goto error;

	for (i = 0; i < num_utlbs; ++i) {
		if (utlbs[i] >= mmu->num_utlbs) {
			ret = -EINVAL;
			goto error;
		}
	}

	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
	if (!priv) {
		ret = -ENOMEM;
		goto error;
	}

	priv->mmu = mmu;
	priv->utlbs = utlbs;
	priv->num_utlbs = num_utlbs;
	priv->dev = dev;
	set_priv(dev, priv);
	return 0;

error:
	kfree(utlbs);
	return ret;
}

#if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)

static struct iommu_domain *ipmmu_domain_alloc(unsigned type)
{
	if (type != IOMMU_DOMAIN_UNMANAGED)
		return NULL;

	return __ipmmu_domain_alloc(type);
}

static int ipmmu_add_device(struct device *dev)
{
	struct ipmmu_vmsa_device *mmu = NULL;
	struct iommu_group *group;
	int ret;

	if (to_priv(dev)) {
		dev_warn(dev, "IOMMU driver already assigned to device %s\n",
			 dev_name(dev));
		return -EINVAL;
	}

	/* Create a device group and add the device to it. */
	group = iommu_group_alloc();
	if (IS_ERR(group)) {
		dev_err(dev, "Failed to allocate IOMMU group\n");
		ret = PTR_ERR(group);
		goto error;
	}

	ret = iommu_group_add_device(group, dev);
	iommu_group_put(group);

	if (ret < 0) {
		dev_err(dev, "Failed to add device to IPMMU group\n");
		group = NULL;
		goto error;
	}

	ret = ipmmu_init_platform_device(dev);
	if (ret < 0)
		goto error;

	/*
	 * Create the ARM mapping, used by the ARM DMA mapping core to allocate
	 * VAs. This will allocate a corresponding IOMMU domain.
	 *
	 * TODO:
	 * - Create one mapping per context (TLB).
	 * - Make the mapping size configurable ? We currently use a 2GB mapping
	 *   at a 1GB offset to ensure that NULL VAs will fault.
	 */
	mmu = to_priv(dev)->mmu;
	if (!mmu->mapping) {
		struct dma_iommu_mapping *mapping;

		mapping = arm_iommu_create_mapping(&platform_bus_type,
						   SZ_1G, SZ_2G);
		if (IS_ERR(mapping)) {
			dev_err(mmu->dev, "failed to create ARM IOMMU mapping\n");
			ret = PTR_ERR(mapping);
			goto error;
		}

		mmu->mapping = mapping;
	}

	/* Attach the ARM VA mapping to the device. */
	ret = arm_iommu_attach_device(dev, mmu->mapping);
	if (ret < 0) {
		dev_err(dev, "Failed to attach device to VA mapping\n");
		goto error;
	}

	return 0;

error:
	if (mmu)
		arm_iommu_release_mapping(mmu->mapping);

	if (!IS_ERR_OR_NULL(group))
		iommu_group_remove_device(dev);

	kfree(to_priv(dev)->utlbs);
	kfree(to_priv(dev));
	set_priv(dev, NULL);

	return ret;
}

static void ipmmu_remove_device(struct device *dev)
{
	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);

	arm_iommu_detach_device(dev);
	iommu_group_remove_device(dev);

	kfree(priv->utlbs);
	kfree(priv);

	set_priv(dev, NULL);
}

static const struct iommu_ops ipmmu_ops = {
	.domain_alloc = ipmmu_domain_alloc,
	.domain_free = ipmmu_domain_free,
	.attach_dev = ipmmu_attach_device,
	.detach_dev = ipmmu_detach_device,
	.map = ipmmu_map,
	.unmap = ipmmu_unmap,
	.map_sg = default_iommu_map_sg,
	.iova_to_phys = ipmmu_iova_to_phys,
	.add_device = ipmmu_add_device,
	.remove_device = ipmmu_remove_device,
	.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
};

#endif /* !CONFIG_ARM && CONFIG_IOMMU_DMA */

#ifdef CONFIG_IOMMU_DMA

static DEFINE_SPINLOCK(ipmmu_slave_devices_lock);
static LIST_HEAD(ipmmu_slave_devices);

static struct iommu_domain *ipmmu_domain_alloc_dma(unsigned type)
{
	struct iommu_domain *io_domain = NULL;

	switch (type) {
	case IOMMU_DOMAIN_UNMANAGED:
		io_domain = __ipmmu_domain_alloc(type);
		break;

	case IOMMU_DOMAIN_DMA:
		io_domain = __ipmmu_domain_alloc(type);
		if (io_domain)
			iommu_get_dma_cookie(io_domain);
		break;
	}

	return io_domain;
}

static void ipmmu_domain_free_dma(struct iommu_domain *io_domain)
{
	switch (io_domain->type) {
	case IOMMU_DOMAIN_DMA:
		iommu_put_dma_cookie(io_domain);
		/* fall-through */
	default:
		ipmmu_domain_free(io_domain);
		break;
	}
}

static int ipmmu_add_device_dma(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev->iommu_fwspec;
	struct iommu_group *group;

	/*
	 * Only let through devices that have been verified in xlate()
	 * We may get called with dev->iommu_fwspec set to NULL.
	 */
	if (!fwspec || !fwspec->iommu_priv)
		return -ENODEV;

	group = iommu_group_get_for_dev(dev);
	if (IS_ERR(group))
		return PTR_ERR(group);

	spin_lock(&ipmmu_slave_devices_lock);
	list_add(&to_priv(dev)->list, &ipmmu_slave_devices);
	spin_unlock(&ipmmu_slave_devices_lock);
	return 0;
}

static void ipmmu_remove_device_dma(struct device *dev)
{
	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);

	spin_lock(&ipmmu_slave_devices_lock);
	list_del(&priv->list);
	spin_unlock(&ipmmu_slave_devices_lock);

	iommu_group_remove_device(dev);
}

static struct device *ipmmu_find_sibling_device(struct device *dev)
{
	struct ipmmu_vmsa_iommu_priv *priv = to_priv(dev);
	struct ipmmu_vmsa_iommu_priv *sibling_priv = NULL;
	bool found = false;

	spin_lock(&ipmmu_slave_devices_lock);

	list_for_each_entry(sibling_priv, &ipmmu_slave_devices, list) {
		if (priv == sibling_priv)
			continue;
		if (sibling_priv->mmu == priv->mmu) {
			found = true;
			break;
		}
	}

	spin_unlock(&ipmmu_slave_devices_lock);

	return found ? sibling_priv->dev : NULL;
}

static struct iommu_group *ipmmu_find_group_dma(struct device *dev)
{
	struct iommu_group *group;
	struct device *sibling;

	sibling = ipmmu_find_sibling_device(dev);
	if (sibling)
		group = iommu_group_get(sibling);
	if (!sibling || IS_ERR(group))
		group = generic_device_group(dev);

	return group;
}

static int ipmmu_of_xlate_dma(struct device *dev,
			      struct of_phandle_args *spec)
{
	/* If the IPMMU device is disabled in DT then return error
	 * to make sure the of_iommu code does not install ops
	 * even though the iommu device is disabled
	 */
	if (!of_device_is_available(spec->np))
		return -ENODEV;

	return ipmmu_init_platform_device(dev);
}

static const struct iommu_ops ipmmu_ops = {
	.domain_alloc = ipmmu_domain_alloc_dma,
	.domain_free = ipmmu_domain_free_dma,
	.attach_dev = ipmmu_attach_device,
	.detach_dev = ipmmu_detach_device,
	.map = ipmmu_map,
	.unmap = ipmmu_unmap,
	.map_sg = default_iommu_map_sg,
	.iova_to_phys = ipmmu_iova_to_phys,
	.add_device = ipmmu_add_device_dma,
	.remove_device = ipmmu_remove_device_dma,
	.device_group = ipmmu_find_group_dma,
	.pgsize_bitmap = SZ_1G | SZ_2M | SZ_4K,
	.of_xlate = ipmmu_of_xlate_dma,
};

#endif /* CONFIG_IOMMU_DMA */

/* -----------------------------------------------------------------------------
 * Probe/remove and init
 */

static void ipmmu_device_reset(struct ipmmu_vmsa_device *mmu)
{
	unsigned int i;

	/* Disable all contexts. */
	for (i = 0; i < 4; ++i)
		ipmmu_write(mmu, i * IM_CTX_SIZE + IMCTR, 0);
}

static int ipmmu_probe(struct platform_device *pdev)
{
	struct ipmmu_vmsa_device *mmu;
	struct resource *res;
	int irq;
	int ret;

	mmu = devm_kzalloc(&pdev->dev, sizeof(*mmu), GFP_KERNEL);
	if (!mmu) {
		dev_err(&pdev->dev, "cannot allocate device data\n");
		return -ENOMEM;
	}

	mmu->dev = &pdev->dev;
	mmu->num_utlbs = 32;
	spin_lock_init(&mmu->lock);
	bitmap_zero(mmu->ctx, IPMMU_CTX_MAX);

	/* Map I/O memory and request IRQ. */
	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	mmu->base = devm_ioremap_resource(&pdev->dev, res);
	if (IS_ERR(mmu->base))
		return PTR_ERR(mmu->base);

	/*
	 * The IPMMU has two register banks, for secure and non-secure modes.
	 * The bank mapped at the beginning of the IPMMU address space
	 * corresponds to the running mode of the CPU. When running in secure
	 * mode the non-secure register bank is also available at an offset.
	 *
	 * Secure mode operation isn't clearly documented and is thus currently
	 * not implemented in the driver. Furthermore, preliminary tests of
	 * non-secure operation with the main register bank were not successful.
	 * Offset the registers base unconditionally to point to the non-secure
	 * alias space for now.
	 */
	mmu->base += IM_NS_ALIAS_OFFSET;

	irq = platform_get_irq(pdev, 0);
	if (irq < 0) {
		dev_err(&pdev->dev, "no IRQ found\n");
		return irq;
	}

	ret = devm_request_irq(&pdev->dev, irq, ipmmu_irq, 0,
			       dev_name(&pdev->dev), mmu);
	if (ret < 0) {
		dev_err(&pdev->dev, "failed to request IRQ %d\n", irq);
		return ret;
	}

	ipmmu_device_reset(mmu);

	/*
	 * We can't create the ARM mapping here as it requires the bus to have
	 * an IOMMU, which only happens when bus_set_iommu() is called in
	 * ipmmu_init() after the probe function returns.
	 */

	spin_lock(&ipmmu_devices_lock);
	list_add(&mmu->list, &ipmmu_devices);
	spin_unlock(&ipmmu_devices_lock);

	platform_set_drvdata(pdev, mmu);

	return 0;
}

static int ipmmu_remove(struct platform_device *pdev)
{
	struct ipmmu_vmsa_device *mmu = platform_get_drvdata(pdev);

	spin_lock(&ipmmu_devices_lock);
	list_del(&mmu->list);
	spin_unlock(&ipmmu_devices_lock);

#if defined(CONFIG_ARM) && !defined(CONFIG_IOMMU_DMA)
	arm_iommu_release_mapping(mmu->mapping);
#endif

	ipmmu_device_reset(mmu);

	return 0;
}

static const struct of_device_id ipmmu_of_ids[] = {
	{ .compatible = "renesas,ipmmu-vmsa", },
	{ }
};

static struct platform_driver ipmmu_driver = {
	.driver = {
		.name = "ipmmu-vmsa",
		.of_match_table = of_match_ptr(ipmmu_of_ids),
	},
	.probe = ipmmu_probe,
	.remove	= ipmmu_remove,
};

static int __init ipmmu_init(void)
{
	int ret;

	ret = platform_driver_register(&ipmmu_driver);
	if (ret < 0)
		return ret;

	if (!iommu_present(&platform_bus_type))
		bus_set_iommu(&platform_bus_type, &ipmmu_ops);

	return 0;
}

static void __exit ipmmu_exit(void)
{
	return platform_driver_unregister(&ipmmu_driver);
}

subsys_initcall(ipmmu_init);
module_exit(ipmmu_exit);

MODULE_DESCRIPTION("IOMMU API for Renesas VMSA-compatible IPMMU");
MODULE_AUTHOR("Laurent Pinchart <laurent.pinchart@ideasonboard.com>");
MODULE_LICENSE("GPL v2");