summaryrefslogtreecommitdiff
path: root/drivers/iommu/qcom_iommu.c
blob: 5b3b270972f809c62eb11714613e53e75fc63320 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * IOMMU API for QCOM secure IOMMUs.  Somewhat based on arm-smmu.c
 *
 * Copyright (C) 2013 ARM Limited
 * Copyright (C) 2017 Red Hat
 */

#include <linux/atomic.h>
#include <linux/bitfield.h>
#include <linux/clk.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#include <linux/dma-mapping.h>
#include <linux/err.h>
#include <linux/interrupt.h>
#include <linux/io.h>
#include <linux/io-64-nonatomic-hi-lo.h>
#include <linux/io-pgtable.h>
#include <linux/iommu.h>
#include <linux/iopoll.h>
#include <linux/kconfig.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/of.h>
#include <linux/of_address.h>
#include <linux/of_device.h>
#include <linux/of_iommu.h>
#include <linux/platform_device.h>
#include <linux/pm.h>
#include <linux/pm_runtime.h>
#include <linux/qcom_scm.h>
#include <linux/slab.h>
#include <linux/spinlock.h>

#include "arm-smmu.h"

#define SMMU_INTR_SEL_NS     0x2000

struct qcom_iommu_ctx;

struct qcom_iommu_dev {
	/* IOMMU core code handle */
	struct iommu_device	 iommu;
	struct device		*dev;
	struct clk		*iface_clk;
	struct clk		*bus_clk;
	void __iomem		*local_base;
	u32			 sec_id;
	u8			 num_ctxs;
	struct qcom_iommu_ctx	*ctxs[];   /* indexed by asid-1 */
};

struct qcom_iommu_ctx {
	struct device		*dev;
	void __iomem		*base;
	bool			 secure_init;
	u8			 asid;      /* asid and ctx bank # are 1:1 */
	struct iommu_domain	*domain;
};

struct qcom_iommu_domain {
	struct io_pgtable_ops	*pgtbl_ops;
	spinlock_t		 pgtbl_lock;
	struct mutex		 init_mutex; /* Protects iommu pointer */
	struct iommu_domain	 domain;
	struct qcom_iommu_dev	*iommu;
};

static struct qcom_iommu_domain *to_qcom_iommu_domain(struct iommu_domain *dom)
{
	return container_of(dom, struct qcom_iommu_domain, domain);
}

static const struct iommu_ops qcom_iommu_ops;

static struct qcom_iommu_dev * to_iommu(struct device *dev)
{
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);

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

	return dev_iommu_priv_get(dev);
}

static struct qcom_iommu_ctx * to_ctx(struct device *dev, unsigned asid)
{
	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
	if (!qcom_iommu)
		return NULL;
	return qcom_iommu->ctxs[asid - 1];
}

static inline void
iommu_writel(struct qcom_iommu_ctx *ctx, unsigned reg, u32 val)
{
	writel_relaxed(val, ctx->base + reg);
}

static inline void
iommu_writeq(struct qcom_iommu_ctx *ctx, unsigned reg, u64 val)
{
	writeq_relaxed(val, ctx->base + reg);
}

static inline u32
iommu_readl(struct qcom_iommu_ctx *ctx, unsigned reg)
{
	return readl_relaxed(ctx->base + reg);
}

static inline u64
iommu_readq(struct qcom_iommu_ctx *ctx, unsigned reg)
{
	return readq_relaxed(ctx->base + reg);
}

static void qcom_iommu_tlb_sync(void *cookie)
{
	struct iommu_fwspec *fwspec;
	struct device *dev = cookie;
	unsigned i;

	fwspec = dev_iommu_fwspec_get(dev);

	for (i = 0; i < fwspec->num_ids; i++) {
		struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]);
		unsigned int val, ret;

		iommu_writel(ctx, ARM_SMMU_CB_TLBSYNC, 0);

		ret = readl_poll_timeout(ctx->base + ARM_SMMU_CB_TLBSTATUS, val,
					 (val & 0x1) == 0, 0, 5000000);
		if (ret)
			dev_err(ctx->dev, "timeout waiting for TLB SYNC\n");
	}
}

static void qcom_iommu_tlb_inv_context(void *cookie)
{
	struct device *dev = cookie;
	struct iommu_fwspec *fwspec;
	unsigned i;

	fwspec = dev_iommu_fwspec_get(dev);

	for (i = 0; i < fwspec->num_ids; i++) {
		struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]);
		iommu_writel(ctx, ARM_SMMU_CB_S1_TLBIASID, ctx->asid);
	}

	qcom_iommu_tlb_sync(cookie);
}

static void qcom_iommu_tlb_inv_range_nosync(unsigned long iova, size_t size,
					    size_t granule, bool leaf, void *cookie)
{
	struct device *dev = cookie;
	struct iommu_fwspec *fwspec;
	unsigned i, reg;

	reg = leaf ? ARM_SMMU_CB_S1_TLBIVAL : ARM_SMMU_CB_S1_TLBIVA;

	fwspec = dev_iommu_fwspec_get(dev);

	for (i = 0; i < fwspec->num_ids; i++) {
		struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]);
		size_t s = size;

		iova = (iova >> 12) << 12;
		iova |= ctx->asid;
		do {
			iommu_writel(ctx, reg, iova);
			iova += granule;
		} while (s -= granule);
	}
}

static void qcom_iommu_tlb_flush_walk(unsigned long iova, size_t size,
				      size_t granule, void *cookie)
{
	qcom_iommu_tlb_inv_range_nosync(iova, size, granule, false, cookie);
	qcom_iommu_tlb_sync(cookie);
}

static void qcom_iommu_tlb_flush_leaf(unsigned long iova, size_t size,
				      size_t granule, void *cookie)
{
	qcom_iommu_tlb_inv_range_nosync(iova, size, granule, true, cookie);
	qcom_iommu_tlb_sync(cookie);
}

static void qcom_iommu_tlb_add_page(struct iommu_iotlb_gather *gather,
				    unsigned long iova, size_t granule,
				    void *cookie)
{
	qcom_iommu_tlb_inv_range_nosync(iova, granule, granule, true, cookie);
}

static const struct iommu_flush_ops qcom_flush_ops = {
	.tlb_flush_all	= qcom_iommu_tlb_inv_context,
	.tlb_flush_walk = qcom_iommu_tlb_flush_walk,
	.tlb_flush_leaf = qcom_iommu_tlb_flush_leaf,
	.tlb_add_page	= qcom_iommu_tlb_add_page,
};

static irqreturn_t qcom_iommu_fault(int irq, void *dev)
{
	struct qcom_iommu_ctx *ctx = dev;
	u32 fsr, fsynr;
	u64 iova;

	fsr = iommu_readl(ctx, ARM_SMMU_CB_FSR);

	if (!(fsr & ARM_SMMU_FSR_FAULT))
		return IRQ_NONE;

	fsynr = iommu_readl(ctx, ARM_SMMU_CB_FSYNR0);
	iova = iommu_readq(ctx, ARM_SMMU_CB_FAR);

	if (!report_iommu_fault(ctx->domain, ctx->dev, iova, 0)) {
		dev_err_ratelimited(ctx->dev,
				    "Unhandled context fault: fsr=0x%x, "
				    "iova=0x%016llx, fsynr=0x%x, cb=%d\n",
				    fsr, iova, fsynr, ctx->asid);
	}

	iommu_writel(ctx, ARM_SMMU_CB_FSR, fsr);
	iommu_writel(ctx, ARM_SMMU_CB_RESUME, ARM_SMMU_RESUME_TERMINATE);

	return IRQ_HANDLED;
}

static int qcom_iommu_init_domain(struct iommu_domain *domain,
				  struct qcom_iommu_dev *qcom_iommu,
				  struct device *dev)
{
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	struct io_pgtable_ops *pgtbl_ops;
	struct io_pgtable_cfg pgtbl_cfg;
	int i, ret = 0;
	u32 reg;

	mutex_lock(&qcom_domain->init_mutex);
	if (qcom_domain->iommu)
		goto out_unlock;

	pgtbl_cfg = (struct io_pgtable_cfg) {
		.pgsize_bitmap	= qcom_iommu_ops.pgsize_bitmap,
		.ias		= 32,
		.oas		= 40,
		.tlb		= &qcom_flush_ops,
		.iommu_dev	= qcom_iommu->dev,
	};

	qcom_domain->iommu = qcom_iommu;
	pgtbl_ops = alloc_io_pgtable_ops(ARM_32_LPAE_S1, &pgtbl_cfg, dev);
	if (!pgtbl_ops) {
		dev_err(qcom_iommu->dev, "failed to allocate pagetable ops\n");
		ret = -ENOMEM;
		goto out_clear_iommu;
	}

	/* Update the domain's page sizes to reflect the page table format */
	domain->pgsize_bitmap = pgtbl_cfg.pgsize_bitmap;
	domain->geometry.aperture_end = (1ULL << pgtbl_cfg.ias) - 1;
	domain->geometry.force_aperture = true;

	for (i = 0; i < fwspec->num_ids; i++) {
		struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]);

		if (!ctx->secure_init) {
			ret = qcom_scm_restore_sec_cfg(qcom_iommu->sec_id, ctx->asid);
			if (ret) {
				dev_err(qcom_iommu->dev, "secure init failed: %d\n", ret);
				goto out_clear_iommu;
			}
			ctx->secure_init = true;
		}

		/* TTBRs */
		iommu_writeq(ctx, ARM_SMMU_CB_TTBR0,
				pgtbl_cfg.arm_lpae_s1_cfg.ttbr |
				FIELD_PREP(ARM_SMMU_TTBRn_ASID, ctx->asid));
		iommu_writeq(ctx, ARM_SMMU_CB_TTBR1, 0);

		/* TCR */
		iommu_writel(ctx, ARM_SMMU_CB_TCR2,
				arm_smmu_lpae_tcr2(&pgtbl_cfg));
		iommu_writel(ctx, ARM_SMMU_CB_TCR,
			     arm_smmu_lpae_tcr(&pgtbl_cfg) | ARM_SMMU_TCR_EAE);

		/* MAIRs (stage-1 only) */
		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR0,
				pgtbl_cfg.arm_lpae_s1_cfg.mair);
		iommu_writel(ctx, ARM_SMMU_CB_S1_MAIR1,
				pgtbl_cfg.arm_lpae_s1_cfg.mair >> 32);

		/* SCTLR */
		reg = ARM_SMMU_SCTLR_CFIE | ARM_SMMU_SCTLR_CFRE |
		      ARM_SMMU_SCTLR_AFE | ARM_SMMU_SCTLR_TRE |
		      ARM_SMMU_SCTLR_M | ARM_SMMU_SCTLR_S1_ASIDPNE |
		      ARM_SMMU_SCTLR_CFCFG;

		if (IS_ENABLED(CONFIG_BIG_ENDIAN))
			reg |= ARM_SMMU_SCTLR_E;

		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, reg);

		ctx->domain = domain;
	}

	mutex_unlock(&qcom_domain->init_mutex);

	/* Publish page table ops for map/unmap */
	qcom_domain->pgtbl_ops = pgtbl_ops;

	return 0;

out_clear_iommu:
	qcom_domain->iommu = NULL;
out_unlock:
	mutex_unlock(&qcom_domain->init_mutex);
	return ret;
}

static struct iommu_domain *qcom_iommu_domain_alloc(unsigned type)
{
	struct qcom_iommu_domain *qcom_domain;

	if (type != IOMMU_DOMAIN_UNMANAGED && type != IOMMU_DOMAIN_DMA)
		return NULL;
	/*
	 * Allocate the domain and initialise some of its data structures.
	 * We can't really do anything meaningful until we've added a
	 * master.
	 */
	qcom_domain = kzalloc(sizeof(*qcom_domain), GFP_KERNEL);
	if (!qcom_domain)
		return NULL;

	if (type == IOMMU_DOMAIN_DMA &&
	    iommu_get_dma_cookie(&qcom_domain->domain)) {
		kfree(qcom_domain);
		return NULL;
	}

	mutex_init(&qcom_domain->init_mutex);
	spin_lock_init(&qcom_domain->pgtbl_lock);

	return &qcom_domain->domain;
}

static void qcom_iommu_domain_free(struct iommu_domain *domain)
{
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);

	iommu_put_dma_cookie(domain);

	if (qcom_domain->iommu) {
		/*
		 * NOTE: unmap can be called after client device is powered
		 * off, for example, with GPUs or anything involving dma-buf.
		 * So we cannot rely on the device_link.  Make sure the IOMMU
		 * is on to avoid unclocked accesses in the TLB inv path:
		 */
		pm_runtime_get_sync(qcom_domain->iommu->dev);
		free_io_pgtable_ops(qcom_domain->pgtbl_ops);
		pm_runtime_put_sync(qcom_domain->iommu->dev);
	}

	kfree(qcom_domain);
}

static int qcom_iommu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
	int ret;

	if (!qcom_iommu) {
		dev_err(dev, "cannot attach to IOMMU, is it on the same bus?\n");
		return -ENXIO;
	}

	/* Ensure that the domain is finalized */
	pm_runtime_get_sync(qcom_iommu->dev);
	ret = qcom_iommu_init_domain(domain, qcom_iommu, dev);
	pm_runtime_put_sync(qcom_iommu->dev);
	if (ret < 0)
		return ret;

	/*
	 * Sanity check the domain. We don't support domains across
	 * different IOMMUs.
	 */
	if (qcom_domain->iommu != qcom_iommu) {
		dev_err(dev, "cannot attach to IOMMU %s while already "
			"attached to domain on IOMMU %s\n",
			dev_name(qcom_domain->iommu->dev),
			dev_name(qcom_iommu->dev));
		return -EINVAL;
	}

	return 0;
}

static void qcom_iommu_detach_dev(struct iommu_domain *domain, struct device *dev)
{
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
	unsigned i;

	if (WARN_ON(!qcom_domain->iommu))
		return;

	pm_runtime_get_sync(qcom_iommu->dev);
	for (i = 0; i < fwspec->num_ids; i++) {
		struct qcom_iommu_ctx *ctx = to_ctx(dev, fwspec->ids[i]);

		/* Disable the context bank: */
		iommu_writel(ctx, ARM_SMMU_CB_SCTLR, 0);

		ctx->domain = NULL;
	}
	pm_runtime_put_sync(qcom_iommu->dev);
}

static int qcom_iommu_map(struct iommu_domain *domain, unsigned long iova,
			  phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
	int ret;
	unsigned long flags;
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
	struct io_pgtable_ops *ops = qcom_domain->pgtbl_ops;

	if (!ops)
		return -ENODEV;

	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
	ret = ops->map(ops, iova, paddr, size, prot);
	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
	return ret;
}

static size_t qcom_iommu_unmap(struct iommu_domain *domain, unsigned long iova,
			       size_t size, struct iommu_iotlb_gather *gather)
{
	size_t ret;
	unsigned long flags;
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
	struct io_pgtable_ops *ops = qcom_domain->pgtbl_ops;

	if (!ops)
		return 0;

	/* NOTE: unmap can be called after client device is powered off,
	 * for example, with GPUs or anything involving dma-buf.  So we
	 * cannot rely on the device_link.  Make sure the IOMMU is on to
	 * avoid unclocked accesses in the TLB inv path:
	 */
	pm_runtime_get_sync(qcom_domain->iommu->dev);
	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
	ret = ops->unmap(ops, iova, size, gather);
	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);
	pm_runtime_put_sync(qcom_domain->iommu->dev);

	return ret;
}

static void qcom_iommu_flush_iotlb_all(struct iommu_domain *domain)
{
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
	struct io_pgtable *pgtable = container_of(qcom_domain->pgtbl_ops,
						  struct io_pgtable, ops);
	if (!qcom_domain->pgtbl_ops)
		return;

	pm_runtime_get_sync(qcom_domain->iommu->dev);
	qcom_iommu_tlb_sync(pgtable->cookie);
	pm_runtime_put_sync(qcom_domain->iommu->dev);
}

static void qcom_iommu_iotlb_sync(struct iommu_domain *domain,
				  struct iommu_iotlb_gather *gather)
{
	qcom_iommu_flush_iotlb_all(domain);
}

static phys_addr_t qcom_iommu_iova_to_phys(struct iommu_domain *domain,
					   dma_addr_t iova)
{
	phys_addr_t ret;
	unsigned long flags;
	struct qcom_iommu_domain *qcom_domain = to_qcom_iommu_domain(domain);
	struct io_pgtable_ops *ops = qcom_domain->pgtbl_ops;

	if (!ops)
		return 0;

	spin_lock_irqsave(&qcom_domain->pgtbl_lock, flags);
	ret = ops->iova_to_phys(ops, iova);
	spin_unlock_irqrestore(&qcom_domain->pgtbl_lock, flags);

	return ret;
}

static bool qcom_iommu_capable(enum iommu_cap cap)
{
	switch (cap) {
	case IOMMU_CAP_CACHE_COHERENCY:
		/*
		 * Return true here as the SMMU can always send out coherent
		 * requests.
		 */
		return true;
	case IOMMU_CAP_NOEXEC:
		return true;
	default:
		return false;
	}
}

static int qcom_iommu_add_device(struct device *dev)
{
	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);
	struct iommu_group *group;
	struct device_link *link;

	if (!qcom_iommu)
		return -ENODEV;

	/*
	 * Establish the link between iommu and master, so that the
	 * iommu gets runtime enabled/disabled as per the master's
	 * needs.
	 */
	link = device_link_add(dev, qcom_iommu->dev, DL_FLAG_PM_RUNTIME);
	if (!link) {
		dev_err(qcom_iommu->dev, "Unable to create device link between %s and %s\n",
			dev_name(qcom_iommu->dev), dev_name(dev));
		return -ENODEV;
	}

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

	iommu_group_put(group);
	iommu_device_link(&qcom_iommu->iommu, dev);

	return 0;
}

static void qcom_iommu_remove_device(struct device *dev)
{
	struct qcom_iommu_dev *qcom_iommu = to_iommu(dev);

	if (!qcom_iommu)
		return;

	iommu_device_unlink(&qcom_iommu->iommu, dev);
	iommu_group_remove_device(dev);
	iommu_fwspec_free(dev);
}

static int qcom_iommu_of_xlate(struct device *dev, struct of_phandle_args *args)
{
	struct qcom_iommu_dev *qcom_iommu;
	struct platform_device *iommu_pdev;
	unsigned asid = args->args[0];

	if (args->args_count != 1) {
		dev_err(dev, "incorrect number of iommu params found for %s "
			"(found %d, expected 1)\n",
			args->np->full_name, args->args_count);
		return -EINVAL;
	}

	iommu_pdev = of_find_device_by_node(args->np);
	if (WARN_ON(!iommu_pdev))
		return -EINVAL;

	qcom_iommu = platform_get_drvdata(iommu_pdev);

	/* make sure the asid specified in dt is valid, so we don't have
	 * to sanity check this elsewhere, since 'asid - 1' is used to
	 * index into qcom_iommu->ctxs:
	 */
	if (WARN_ON(asid < 1) ||
	    WARN_ON(asid > qcom_iommu->num_ctxs))
		return -EINVAL;

	if (!dev_iommu_priv_get(dev)) {
		dev_iommu_priv_set(dev, qcom_iommu);
	} else {
		/* make sure devices iommus dt node isn't referring to
		 * multiple different iommu devices.  Multiple context
		 * banks are ok, but multiple devices are not:
		 */
		if (WARN_ON(qcom_iommu != dev_iommu_priv_get(dev)))
			return -EINVAL;
	}

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

static const struct iommu_ops qcom_iommu_ops = {
	.capable	= qcom_iommu_capable,
	.domain_alloc	= qcom_iommu_domain_alloc,
	.domain_free	= qcom_iommu_domain_free,
	.attach_dev	= qcom_iommu_attach_dev,
	.detach_dev	= qcom_iommu_detach_dev,
	.map		= qcom_iommu_map,
	.unmap		= qcom_iommu_unmap,
	.flush_iotlb_all = qcom_iommu_flush_iotlb_all,
	.iotlb_sync	= qcom_iommu_iotlb_sync,
	.iova_to_phys	= qcom_iommu_iova_to_phys,
	.add_device	= qcom_iommu_add_device,
	.remove_device	= qcom_iommu_remove_device,
	.device_group	= generic_device_group,
	.of_xlate	= qcom_iommu_of_xlate,
	.pgsize_bitmap	= SZ_4K | SZ_64K | SZ_1M | SZ_16M,
};

static int qcom_iommu_enable_clocks(struct qcom_iommu_dev *qcom_iommu)
{
	int ret;

	ret = clk_prepare_enable(qcom_iommu->iface_clk);
	if (ret) {
		dev_err(qcom_iommu->dev, "Couldn't enable iface_clk\n");
		return ret;
	}

	ret = clk_prepare_enable(qcom_iommu->bus_clk);
	if (ret) {
		dev_err(qcom_iommu->dev, "Couldn't enable bus_clk\n");
		clk_disable_unprepare(qcom_iommu->iface_clk);
		return ret;
	}

	return 0;
}

static void qcom_iommu_disable_clocks(struct qcom_iommu_dev *qcom_iommu)
{
	clk_disable_unprepare(qcom_iommu->bus_clk);
	clk_disable_unprepare(qcom_iommu->iface_clk);
}

static int qcom_iommu_sec_ptbl_init(struct device *dev)
{
	size_t psize = 0;
	unsigned int spare = 0;
	void *cpu_addr;
	dma_addr_t paddr;
	unsigned long attrs;
	static bool allocated = false;
	int ret;

	if (allocated)
		return 0;

	ret = qcom_scm_iommu_secure_ptbl_size(spare, &psize);
	if (ret) {
		dev_err(dev, "failed to get iommu secure pgtable size (%d)\n",
			ret);
		return ret;
	}

	dev_info(dev, "iommu sec: pgtable size: %zu\n", psize);

	attrs = DMA_ATTR_NO_KERNEL_MAPPING;

	cpu_addr = dma_alloc_attrs(dev, psize, &paddr, GFP_KERNEL, attrs);
	if (!cpu_addr) {
		dev_err(dev, "failed to allocate %zu bytes for pgtable\n",
			psize);
		return -ENOMEM;
	}

	ret = qcom_scm_iommu_secure_ptbl_init(paddr, psize, spare);
	if (ret) {
		dev_err(dev, "failed to init iommu pgtable (%d)\n", ret);
		goto free_mem;
	}

	allocated = true;
	return 0;

free_mem:
	dma_free_attrs(dev, psize, cpu_addr, paddr, attrs);
	return ret;
}

static int get_asid(const struct device_node *np)
{
	u32 reg;

	/* read the "reg" property directly to get the relative address
	 * of the context bank, and calculate the asid from that:
	 */
	if (of_property_read_u32_index(np, "reg", 0, &reg))
		return -ENODEV;

	return reg / 0x1000;      /* context banks are 0x1000 apart */
}

static int qcom_iommu_ctx_probe(struct platform_device *pdev)
{
	struct qcom_iommu_ctx *ctx;
	struct device *dev = &pdev->dev;
	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev->parent);
	struct resource *res;
	int ret, irq;

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

	ctx->dev = dev;
	platform_set_drvdata(pdev, ctx);

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

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

	/* clear IRQs before registering fault handler, just in case the
	 * boot-loader left us a surprise:
	 */
	iommu_writel(ctx, ARM_SMMU_CB_FSR, iommu_readl(ctx, ARM_SMMU_CB_FSR));

	ret = devm_request_irq(dev, irq,
			       qcom_iommu_fault,
			       IRQF_SHARED,
			       "qcom-iommu-fault",
			       ctx);
	if (ret) {
		dev_err(dev, "failed to request IRQ %u\n", irq);
		return ret;
	}

	ret = get_asid(dev->of_node);
	if (ret < 0) {
		dev_err(dev, "missing reg property\n");
		return ret;
	}

	ctx->asid = ret;

	dev_dbg(dev, "found asid %u\n", ctx->asid);

	qcom_iommu->ctxs[ctx->asid - 1] = ctx;

	return 0;
}

static int qcom_iommu_ctx_remove(struct platform_device *pdev)
{
	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(pdev->dev.parent);
	struct qcom_iommu_ctx *ctx = platform_get_drvdata(pdev);

	platform_set_drvdata(pdev, NULL);

	qcom_iommu->ctxs[ctx->asid - 1] = NULL;

	return 0;
}

static const struct of_device_id ctx_of_match[] = {
	{ .compatible = "qcom,msm-iommu-v1-ns" },
	{ .compatible = "qcom,msm-iommu-v1-sec" },
	{ /* sentinel */ }
};

static struct platform_driver qcom_iommu_ctx_driver = {
	.driver	= {
		.name		= "qcom-iommu-ctx",
		.of_match_table	= of_match_ptr(ctx_of_match),
	},
	.probe	= qcom_iommu_ctx_probe,
	.remove = qcom_iommu_ctx_remove,
};

static bool qcom_iommu_has_secure_context(struct qcom_iommu_dev *qcom_iommu)
{
	struct device_node *child;

	for_each_child_of_node(qcom_iommu->dev->of_node, child)
		if (of_device_is_compatible(child, "qcom,msm-iommu-v1-sec"))
			return true;

	return false;
}

static int qcom_iommu_device_probe(struct platform_device *pdev)
{
	struct device_node *child;
	struct qcom_iommu_dev *qcom_iommu;
	struct device *dev = &pdev->dev;
	struct resource *res;
	int ret, max_asid = 0;

	/* find the max asid (which is 1:1 to ctx bank idx), so we know how
	 * many child ctx devices we have:
	 */
	for_each_child_of_node(dev->of_node, child)
		max_asid = max(max_asid, get_asid(child));

	qcom_iommu = devm_kzalloc(dev, struct_size(qcom_iommu, ctxs, max_asid),
				  GFP_KERNEL);
	if (!qcom_iommu)
		return -ENOMEM;
	qcom_iommu->num_ctxs = max_asid;
	qcom_iommu->dev = dev;

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (res) {
		qcom_iommu->local_base = devm_ioremap_resource(dev, res);
		if (IS_ERR(qcom_iommu->local_base))
			return PTR_ERR(qcom_iommu->local_base);
	}

	qcom_iommu->iface_clk = devm_clk_get(dev, "iface");
	if (IS_ERR(qcom_iommu->iface_clk)) {
		dev_err(dev, "failed to get iface clock\n");
		return PTR_ERR(qcom_iommu->iface_clk);
	}

	qcom_iommu->bus_clk = devm_clk_get(dev, "bus");
	if (IS_ERR(qcom_iommu->bus_clk)) {
		dev_err(dev, "failed to get bus clock\n");
		return PTR_ERR(qcom_iommu->bus_clk);
	}

	if (of_property_read_u32(dev->of_node, "qcom,iommu-secure-id",
				 &qcom_iommu->sec_id)) {
		dev_err(dev, "missing qcom,iommu-secure-id property\n");
		return -ENODEV;
	}

	if (qcom_iommu_has_secure_context(qcom_iommu)) {
		ret = qcom_iommu_sec_ptbl_init(dev);
		if (ret) {
			dev_err(dev, "cannot init secure pg table(%d)\n", ret);
			return ret;
		}
	}

	platform_set_drvdata(pdev, qcom_iommu);

	pm_runtime_enable(dev);

	/* register context bank devices, which are child nodes: */
	ret = devm_of_platform_populate(dev);
	if (ret) {
		dev_err(dev, "Failed to populate iommu contexts\n");
		return ret;
	}

	ret = iommu_device_sysfs_add(&qcom_iommu->iommu, dev, NULL,
				     dev_name(dev));
	if (ret) {
		dev_err(dev, "Failed to register iommu in sysfs\n");
		return ret;
	}

	iommu_device_set_ops(&qcom_iommu->iommu, &qcom_iommu_ops);
	iommu_device_set_fwnode(&qcom_iommu->iommu, dev->fwnode);

	ret = iommu_device_register(&qcom_iommu->iommu);
	if (ret) {
		dev_err(dev, "Failed to register iommu\n");
		return ret;
	}

	bus_set_iommu(&platform_bus_type, &qcom_iommu_ops);

	if (qcom_iommu->local_base) {
		pm_runtime_get_sync(dev);
		writel_relaxed(0xffffffff, qcom_iommu->local_base + SMMU_INTR_SEL_NS);
		pm_runtime_put_sync(dev);
	}

	return 0;
}

static int qcom_iommu_device_remove(struct platform_device *pdev)
{
	struct qcom_iommu_dev *qcom_iommu = platform_get_drvdata(pdev);

	bus_set_iommu(&platform_bus_type, NULL);

	pm_runtime_force_suspend(&pdev->dev);
	platform_set_drvdata(pdev, NULL);
	iommu_device_sysfs_remove(&qcom_iommu->iommu);
	iommu_device_unregister(&qcom_iommu->iommu);

	return 0;
}

static int __maybe_unused qcom_iommu_resume(struct device *dev)
{
	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);

	return qcom_iommu_enable_clocks(qcom_iommu);
}

static int __maybe_unused qcom_iommu_suspend(struct device *dev)
{
	struct qcom_iommu_dev *qcom_iommu = dev_get_drvdata(dev);

	qcom_iommu_disable_clocks(qcom_iommu);

	return 0;
}

static const struct dev_pm_ops qcom_iommu_pm_ops = {
	SET_RUNTIME_PM_OPS(qcom_iommu_suspend, qcom_iommu_resume, NULL)
	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
				pm_runtime_force_resume)
};

static const struct of_device_id qcom_iommu_of_match[] = {
	{ .compatible = "qcom,msm-iommu-v1" },
	{ /* sentinel */ }
};

static struct platform_driver qcom_iommu_driver = {
	.driver	= {
		.name		= "qcom-iommu",
		.of_match_table	= of_match_ptr(qcom_iommu_of_match),
		.pm		= &qcom_iommu_pm_ops,
	},
	.probe	= qcom_iommu_device_probe,
	.remove	= qcom_iommu_device_remove,
};

static int __init qcom_iommu_init(void)
{
	int ret;

	ret = platform_driver_register(&qcom_iommu_ctx_driver);
	if (ret)
		return ret;

	ret = platform_driver_register(&qcom_iommu_driver);
	if (ret)
		platform_driver_unregister(&qcom_iommu_ctx_driver);

	return ret;
}
device_initcall(qcom_iommu_init);