summaryrefslogtreecommitdiff
path: root/drivers/iommu/virtio-iommu.c
blob: d5cac4f46ca53e5976184e461af29d75790dedf6 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Virtio driver for the paravirtualized IOMMU
 *
 * Copyright (C) 2019 Arm Limited
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/amba/bus.h>
#include <linux/delay.h>
#include <linux/dma-iommu.h>
#include <linux/freezer.h>
#include <linux/interval_tree.h>
#include <linux/iommu.h>
#include <linux/module.h>
#include <linux/of_iommu.h>
#include <linux/of_platform.h>
#include <linux/pci.h>
#include <linux/platform_device.h>
#include <linux/virtio.h>
#include <linux/virtio_config.h>
#include <linux/virtio_ids.h>
#include <linux/wait.h>

#include <uapi/linux/virtio_iommu.h>

#define MSI_IOVA_BASE			0x8000000
#define MSI_IOVA_LENGTH			0x100000

#define VIOMMU_REQUEST_VQ		0
#define VIOMMU_EVENT_VQ			1
#define VIOMMU_NR_VQS			2

struct viommu_dev {
	struct iommu_device		iommu;
	struct device			*dev;
	struct virtio_device		*vdev;

	struct ida			domain_ids;

	struct virtqueue		*vqs[VIOMMU_NR_VQS];
	spinlock_t			request_lock;
	struct list_head		requests;
	void				*evts;

	/* Device configuration */
	struct iommu_domain_geometry	geometry;
	u64				pgsize_bitmap;
	u32				first_domain;
	u32				last_domain;
	/* Supported MAP flags */
	u32				map_flags;
	u32				probe_size;
};

struct viommu_mapping {
	phys_addr_t			paddr;
	struct interval_tree_node	iova;
	u32				flags;
};

struct viommu_domain {
	struct iommu_domain		domain;
	struct viommu_dev		*viommu;
	struct mutex			mutex; /* protects viommu pointer */
	unsigned int			id;
	u32				map_flags;

	spinlock_t			mappings_lock;
	struct rb_root_cached		mappings;

	unsigned long			nr_endpoints;
};

struct viommu_endpoint {
	struct device			*dev;
	struct viommu_dev		*viommu;
	struct viommu_domain		*vdomain;
	struct list_head		resv_regions;
};

struct viommu_request {
	struct list_head		list;
	void				*writeback;
	unsigned int			write_offset;
	unsigned int			len;
	char				buf[];
};

#define VIOMMU_FAULT_RESV_MASK		0xffffff00

struct viommu_event {
	union {
		u32			head;
		struct virtio_iommu_fault fault;
	};
};

#define to_viommu_domain(domain)	\
	container_of(domain, struct viommu_domain, domain)

static int viommu_get_req_errno(void *buf, size_t len)
{
	struct virtio_iommu_req_tail *tail = buf + len - sizeof(*tail);

	switch (tail->status) {
	case VIRTIO_IOMMU_S_OK:
		return 0;
	case VIRTIO_IOMMU_S_UNSUPP:
		return -ENOSYS;
	case VIRTIO_IOMMU_S_INVAL:
		return -EINVAL;
	case VIRTIO_IOMMU_S_RANGE:
		return -ERANGE;
	case VIRTIO_IOMMU_S_NOENT:
		return -ENOENT;
	case VIRTIO_IOMMU_S_FAULT:
		return -EFAULT;
	case VIRTIO_IOMMU_S_NOMEM:
		return -ENOMEM;
	case VIRTIO_IOMMU_S_IOERR:
	case VIRTIO_IOMMU_S_DEVERR:
	default:
		return -EIO;
	}
}

static void viommu_set_req_status(void *buf, size_t len, int status)
{
	struct virtio_iommu_req_tail *tail = buf + len - sizeof(*tail);

	tail->status = status;
}

static off_t viommu_get_write_desc_offset(struct viommu_dev *viommu,
					  struct virtio_iommu_req_head *req,
					  size_t len)
{
	size_t tail_size = sizeof(struct virtio_iommu_req_tail);

	if (req->type == VIRTIO_IOMMU_T_PROBE)
		return len - viommu->probe_size - tail_size;

	return len - tail_size;
}

/*
 * __viommu_sync_req - Complete all in-flight requests
 *
 * Wait for all added requests to complete. When this function returns, all
 * requests that were in-flight at the time of the call have completed.
 */
static int __viommu_sync_req(struct viommu_dev *viommu)
{
	unsigned int len;
	size_t write_len;
	struct viommu_request *req;
	struct virtqueue *vq = viommu->vqs[VIOMMU_REQUEST_VQ];

	assert_spin_locked(&viommu->request_lock);

	virtqueue_kick(vq);

	while (!list_empty(&viommu->requests)) {
		len = 0;
		req = virtqueue_get_buf(vq, &len);
		if (!req)
			continue;

		if (!len)
			viommu_set_req_status(req->buf, req->len,
					      VIRTIO_IOMMU_S_IOERR);

		write_len = req->len - req->write_offset;
		if (req->writeback && len == write_len)
			memcpy(req->writeback, req->buf + req->write_offset,
			       write_len);

		list_del(&req->list);
		kfree(req);
	}

	return 0;
}

static int viommu_sync_req(struct viommu_dev *viommu)
{
	int ret;
	unsigned long flags;

	spin_lock_irqsave(&viommu->request_lock, flags);
	ret = __viommu_sync_req(viommu);
	if (ret)
		dev_dbg(viommu->dev, "could not sync requests (%d)\n", ret);
	spin_unlock_irqrestore(&viommu->request_lock, flags);

	return ret;
}

/*
 * __viommu_add_request - Add one request to the queue
 * @buf: pointer to the request buffer
 * @len: length of the request buffer
 * @writeback: copy data back to the buffer when the request completes.
 *
 * Add a request to the queue. Only synchronize the queue if it's already full.
 * Otherwise don't kick the queue nor wait for requests to complete.
 *
 * When @writeback is true, data written by the device, including the request
 * status, is copied into @buf after the request completes. This is unsafe if
 * the caller allocates @buf on stack and drops the lock between add_req() and
 * sync_req().
 *
 * Return 0 if the request was successfully added to the queue.
 */
static int __viommu_add_req(struct viommu_dev *viommu, void *buf, size_t len,
			    bool writeback)
{
	int ret;
	off_t write_offset;
	struct viommu_request *req;
	struct scatterlist top_sg, bottom_sg;
	struct scatterlist *sg[2] = { &top_sg, &bottom_sg };
	struct virtqueue *vq = viommu->vqs[VIOMMU_REQUEST_VQ];

	assert_spin_locked(&viommu->request_lock);

	write_offset = viommu_get_write_desc_offset(viommu, buf, len);
	if (write_offset <= 0)
		return -EINVAL;

	req = kzalloc(sizeof(*req) + len, GFP_ATOMIC);
	if (!req)
		return -ENOMEM;

	req->len = len;
	if (writeback) {
		req->writeback = buf + write_offset;
		req->write_offset = write_offset;
	}
	memcpy(&req->buf, buf, write_offset);

	sg_init_one(&top_sg, req->buf, write_offset);
	sg_init_one(&bottom_sg, req->buf + write_offset, len - write_offset);

	ret = virtqueue_add_sgs(vq, sg, 1, 1, req, GFP_ATOMIC);
	if (ret == -ENOSPC) {
		/* If the queue is full, sync and retry */
		if (!__viommu_sync_req(viommu))
			ret = virtqueue_add_sgs(vq, sg, 1, 1, req, GFP_ATOMIC);
	}
	if (ret)
		goto err_free;

	list_add_tail(&req->list, &viommu->requests);
	return 0;

err_free:
	kfree(req);
	return ret;
}

static int viommu_add_req(struct viommu_dev *viommu, void *buf, size_t len)
{
	int ret;
	unsigned long flags;

	spin_lock_irqsave(&viommu->request_lock, flags);
	ret = __viommu_add_req(viommu, buf, len, false);
	if (ret)
		dev_dbg(viommu->dev, "could not add request: %d\n", ret);
	spin_unlock_irqrestore(&viommu->request_lock, flags);

	return ret;
}

/*
 * Send a request and wait for it to complete. Return the request status (as an
 * errno)
 */
static int viommu_send_req_sync(struct viommu_dev *viommu, void *buf,
				size_t len)
{
	int ret;
	unsigned long flags;

	spin_lock_irqsave(&viommu->request_lock, flags);

	ret = __viommu_add_req(viommu, buf, len, true);
	if (ret) {
		dev_dbg(viommu->dev, "could not add request (%d)\n", ret);
		goto out_unlock;
	}

	ret = __viommu_sync_req(viommu);
	if (ret) {
		dev_dbg(viommu->dev, "could not sync requests (%d)\n", ret);
		/* Fall-through (get the actual request status) */
	}

	ret = viommu_get_req_errno(buf, len);
out_unlock:
	spin_unlock_irqrestore(&viommu->request_lock, flags);
	return ret;
}

/*
 * viommu_add_mapping - add a mapping to the internal tree
 *
 * On success, return the new mapping. Otherwise return NULL.
 */
static int viommu_add_mapping(struct viommu_domain *vdomain, unsigned long iova,
			      phys_addr_t paddr, size_t size, u32 flags)
{
	unsigned long irqflags;
	struct viommu_mapping *mapping;

	mapping = kzalloc(sizeof(*mapping), GFP_ATOMIC);
	if (!mapping)
		return -ENOMEM;

	mapping->paddr		= paddr;
	mapping->iova.start	= iova;
	mapping->iova.last	= iova + size - 1;
	mapping->flags		= flags;

	spin_lock_irqsave(&vdomain->mappings_lock, irqflags);
	interval_tree_insert(&mapping->iova, &vdomain->mappings);
	spin_unlock_irqrestore(&vdomain->mappings_lock, irqflags);

	return 0;
}

/*
 * viommu_del_mappings - remove mappings from the internal tree
 *
 * @vdomain: the domain
 * @iova: start of the range
 * @size: size of the range. A size of 0 corresponds to the entire address
 *	space.
 *
 * On success, returns the number of unmapped bytes (>= size)
 */
static size_t viommu_del_mappings(struct viommu_domain *vdomain,
				  unsigned long iova, size_t size)
{
	size_t unmapped = 0;
	unsigned long flags;
	unsigned long last = iova + size - 1;
	struct viommu_mapping *mapping = NULL;
	struct interval_tree_node *node, *next;

	spin_lock_irqsave(&vdomain->mappings_lock, flags);
	next = interval_tree_iter_first(&vdomain->mappings, iova, last);
	while (next) {
		node = next;
		mapping = container_of(node, struct viommu_mapping, iova);
		next = interval_tree_iter_next(node, iova, last);

		/* Trying to split a mapping? */
		if (mapping->iova.start < iova)
			break;

		/*
		 * Virtio-iommu doesn't allow UNMAP to split a mapping created
		 * with a single MAP request, so remove the full mapping.
		 */
		unmapped += mapping->iova.last - mapping->iova.start + 1;

		interval_tree_remove(node, &vdomain->mappings);
		kfree(mapping);
	}
	spin_unlock_irqrestore(&vdomain->mappings_lock, flags);

	return unmapped;
}

/*
 * viommu_replay_mappings - re-send MAP requests
 *
 * When reattaching a domain that was previously detached from all endpoints,
 * mappings were deleted from the device. Re-create the mappings available in
 * the internal tree.
 */
static int viommu_replay_mappings(struct viommu_domain *vdomain)
{
	int ret = 0;
	unsigned long flags;
	struct viommu_mapping *mapping;
	struct interval_tree_node *node;
	struct virtio_iommu_req_map map;

	spin_lock_irqsave(&vdomain->mappings_lock, flags);
	node = interval_tree_iter_first(&vdomain->mappings, 0, -1UL);
	while (node) {
		mapping = container_of(node, struct viommu_mapping, iova);
		map = (struct virtio_iommu_req_map) {
			.head.type	= VIRTIO_IOMMU_T_MAP,
			.domain		= cpu_to_le32(vdomain->id),
			.virt_start	= cpu_to_le64(mapping->iova.start),
			.virt_end	= cpu_to_le64(mapping->iova.last),
			.phys_start	= cpu_to_le64(mapping->paddr),
			.flags		= cpu_to_le32(mapping->flags),
		};

		ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
		if (ret)
			break;

		node = interval_tree_iter_next(node, 0, -1UL);
	}
	spin_unlock_irqrestore(&vdomain->mappings_lock, flags);

	return ret;
}

static int viommu_add_resv_mem(struct viommu_endpoint *vdev,
			       struct virtio_iommu_probe_resv_mem *mem,
			       size_t len)
{
	size_t size;
	u64 start64, end64;
	phys_addr_t start, end;
	struct iommu_resv_region *region = NULL;
	unsigned long prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;

	start = start64 = le64_to_cpu(mem->start);
	end = end64 = le64_to_cpu(mem->end);
	size = end64 - start64 + 1;

	/* Catch any overflow, including the unlikely end64 - start64 + 1 = 0 */
	if (start != start64 || end != end64 || size < end64 - start64)
		return -EOVERFLOW;

	if (len < sizeof(*mem))
		return -EINVAL;

	switch (mem->subtype) {
	default:
		dev_warn(vdev->dev, "unknown resv mem subtype 0x%x\n",
			 mem->subtype);
		/* Fall-through */
	case VIRTIO_IOMMU_RESV_MEM_T_RESERVED:
		region = iommu_alloc_resv_region(start, size, 0,
						 IOMMU_RESV_RESERVED);
		break;
	case VIRTIO_IOMMU_RESV_MEM_T_MSI:
		region = iommu_alloc_resv_region(start, size, prot,
						 IOMMU_RESV_MSI);
		break;
	}
	if (!region)
		return -ENOMEM;

	list_add(&vdev->resv_regions, &region->list);
	return 0;
}

static int viommu_probe_endpoint(struct viommu_dev *viommu, struct device *dev)
{
	int ret;
	u16 type, len;
	size_t cur = 0;
	size_t probe_len;
	struct virtio_iommu_req_probe *probe;
	struct virtio_iommu_probe_property *prop;
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);

	if (!fwspec->num_ids)
		return -EINVAL;

	probe_len = sizeof(*probe) + viommu->probe_size +
		    sizeof(struct virtio_iommu_req_tail);
	probe = kzalloc(probe_len, GFP_KERNEL);
	if (!probe)
		return -ENOMEM;

	probe->head.type = VIRTIO_IOMMU_T_PROBE;
	/*
	 * For now, assume that properties of an endpoint that outputs multiple
	 * IDs are consistent. Only probe the first one.
	 */
	probe->endpoint = cpu_to_le32(fwspec->ids[0]);

	ret = viommu_send_req_sync(viommu, probe, probe_len);
	if (ret)
		goto out_free;

	prop = (void *)probe->properties;
	type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK;

	while (type != VIRTIO_IOMMU_PROBE_T_NONE &&
	       cur < viommu->probe_size) {
		len = le16_to_cpu(prop->length) + sizeof(*prop);

		switch (type) {
		case VIRTIO_IOMMU_PROBE_T_RESV_MEM:
			ret = viommu_add_resv_mem(vdev, (void *)prop, len);
			break;
		default:
			dev_err(dev, "unknown viommu prop 0x%x\n", type);
		}

		if (ret)
			dev_err(dev, "failed to parse viommu prop 0x%x\n", type);

		cur += len;
		if (cur >= viommu->probe_size)
			break;

		prop = (void *)probe->properties + cur;
		type = le16_to_cpu(prop->type) & VIRTIO_IOMMU_PROBE_T_MASK;
	}

out_free:
	kfree(probe);
	return ret;
}

static int viommu_fault_handler(struct viommu_dev *viommu,
				struct virtio_iommu_fault *fault)
{
	char *reason_str;

	u8 reason	= fault->reason;
	u32 flags	= le32_to_cpu(fault->flags);
	u32 endpoint	= le32_to_cpu(fault->endpoint);
	u64 address	= le64_to_cpu(fault->address);

	switch (reason) {
	case VIRTIO_IOMMU_FAULT_R_DOMAIN:
		reason_str = "domain";
		break;
	case VIRTIO_IOMMU_FAULT_R_MAPPING:
		reason_str = "page";
		break;
	case VIRTIO_IOMMU_FAULT_R_UNKNOWN:
	default:
		reason_str = "unknown";
		break;
	}

	/* TODO: find EP by ID and report_iommu_fault */
	if (flags & VIRTIO_IOMMU_FAULT_F_ADDRESS)
		dev_err_ratelimited(viommu->dev, "%s fault from EP %u at %#llx [%s%s%s]\n",
				    reason_str, endpoint, address,
				    flags & VIRTIO_IOMMU_FAULT_F_READ ? "R" : "",
				    flags & VIRTIO_IOMMU_FAULT_F_WRITE ? "W" : "",
				    flags & VIRTIO_IOMMU_FAULT_F_EXEC ? "X" : "");
	else
		dev_err_ratelimited(viommu->dev, "%s fault from EP %u\n",
				    reason_str, endpoint);
	return 0;
}

static void viommu_event_handler(struct virtqueue *vq)
{
	int ret;
	unsigned int len;
	struct scatterlist sg[1];
	struct viommu_event *evt;
	struct viommu_dev *viommu = vq->vdev->priv;

	while ((evt = virtqueue_get_buf(vq, &len)) != NULL) {
		if (len > sizeof(*evt)) {
			dev_err(viommu->dev,
				"invalid event buffer (len %u != %zu)\n",
				len, sizeof(*evt));
		} else if (!(evt->head & VIOMMU_FAULT_RESV_MASK)) {
			viommu_fault_handler(viommu, &evt->fault);
		}

		sg_init_one(sg, evt, sizeof(*evt));
		ret = virtqueue_add_inbuf(vq, sg, 1, evt, GFP_ATOMIC);
		if (ret)
			dev_err(viommu->dev, "could not add event buffer\n");
	}

	virtqueue_kick(vq);
}

/* IOMMU API */

static struct iommu_domain *viommu_domain_alloc(unsigned type)
{
	struct viommu_domain *vdomain;

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

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

	mutex_init(&vdomain->mutex);
	spin_lock_init(&vdomain->mappings_lock);
	vdomain->mappings = RB_ROOT_CACHED;

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

	return &vdomain->domain;
}

static int viommu_domain_finalise(struct viommu_endpoint *vdev,
				  struct iommu_domain *domain)
{
	int ret;
	unsigned long viommu_page_size;
	struct viommu_dev *viommu = vdev->viommu;
	struct viommu_domain *vdomain = to_viommu_domain(domain);

	viommu_page_size = 1UL << __ffs(viommu->pgsize_bitmap);
	if (viommu_page_size > PAGE_SIZE) {
		dev_err(vdev->dev,
			"granule 0x%lx larger than system page size 0x%lx\n",
			viommu_page_size, PAGE_SIZE);
		return -EINVAL;
	}

	ret = ida_alloc_range(&viommu->domain_ids, viommu->first_domain,
			      viommu->last_domain, GFP_KERNEL);
	if (ret < 0)
		return ret;

	vdomain->id		= (unsigned int)ret;

	domain->pgsize_bitmap	= viommu->pgsize_bitmap;
	domain->geometry	= viommu->geometry;

	vdomain->map_flags	= viommu->map_flags;
	vdomain->viommu		= viommu;

	return 0;
}

static void viommu_domain_free(struct iommu_domain *domain)
{
	struct viommu_domain *vdomain = to_viommu_domain(domain);

	iommu_put_dma_cookie(domain);

	/* Free all remaining mappings (size 2^64) */
	viommu_del_mappings(vdomain, 0, 0);

	if (vdomain->viommu)
		ida_free(&vdomain->viommu->domain_ids, vdomain->id);

	kfree(vdomain);
}

static int viommu_attach_dev(struct iommu_domain *domain, struct device *dev)
{
	int i;
	int ret = 0;
	struct virtio_iommu_req_attach req;
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);
	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
	struct viommu_domain *vdomain = to_viommu_domain(domain);

	mutex_lock(&vdomain->mutex);
	if (!vdomain->viommu) {
		/*
		 * Properly initialize the domain now that we know which viommu
		 * owns it.
		 */
		ret = viommu_domain_finalise(vdev, domain);
	} else if (vdomain->viommu != vdev->viommu) {
		dev_err(dev, "cannot attach to foreign vIOMMU\n");
		ret = -EXDEV;
	}
	mutex_unlock(&vdomain->mutex);

	if (ret)
		return ret;

	/*
	 * In the virtio-iommu device, when attaching the endpoint to a new
	 * domain, it is detached from the old one and, if as as a result the
	 * old domain isn't attached to any endpoint, all mappings are removed
	 * from the old domain and it is freed.
	 *
	 * In the driver the old domain still exists, and its mappings will be
	 * recreated if it gets reattached to an endpoint. Otherwise it will be
	 * freed explicitly.
	 *
	 * vdev->vdomain is protected by group->mutex
	 */
	if (vdev->vdomain)
		vdev->vdomain->nr_endpoints--;

	req = (struct virtio_iommu_req_attach) {
		.head.type	= VIRTIO_IOMMU_T_ATTACH,
		.domain		= cpu_to_le32(vdomain->id),
	};

	for (i = 0; i < fwspec->num_ids; i++) {
		req.endpoint = cpu_to_le32(fwspec->ids[i]);

		ret = viommu_send_req_sync(vdomain->viommu, &req, sizeof(req));
		if (ret)
			return ret;
	}

	if (!vdomain->nr_endpoints) {
		/*
		 * This endpoint is the first to be attached to the domain.
		 * Replay existing mappings (e.g. SW MSI).
		 */
		ret = viommu_replay_mappings(vdomain);
		if (ret)
			return ret;
	}

	vdomain->nr_endpoints++;
	vdev->vdomain = vdomain;

	return 0;
}

static int viommu_map(struct iommu_domain *domain, unsigned long iova,
		      phys_addr_t paddr, size_t size, int prot, gfp_t gfp)
{
	int ret;
	u32 flags;
	struct virtio_iommu_req_map map;
	struct viommu_domain *vdomain = to_viommu_domain(domain);

	flags = (prot & IOMMU_READ ? VIRTIO_IOMMU_MAP_F_READ : 0) |
		(prot & IOMMU_WRITE ? VIRTIO_IOMMU_MAP_F_WRITE : 0) |
		(prot & IOMMU_MMIO ? VIRTIO_IOMMU_MAP_F_MMIO : 0);

	if (flags & ~vdomain->map_flags)
		return -EINVAL;

	ret = viommu_add_mapping(vdomain, iova, paddr, size, flags);
	if (ret)
		return ret;

	map = (struct virtio_iommu_req_map) {
		.head.type	= VIRTIO_IOMMU_T_MAP,
		.domain		= cpu_to_le32(vdomain->id),
		.virt_start	= cpu_to_le64(iova),
		.phys_start	= cpu_to_le64(paddr),
		.virt_end	= cpu_to_le64(iova + size - 1),
		.flags		= cpu_to_le32(flags),
	};

	if (!vdomain->nr_endpoints)
		return 0;

	ret = viommu_send_req_sync(vdomain->viommu, &map, sizeof(map));
	if (ret)
		viommu_del_mappings(vdomain, iova, size);

	return ret;
}

static size_t viommu_unmap(struct iommu_domain *domain, unsigned long iova,
			   size_t size, struct iommu_iotlb_gather *gather)
{
	int ret = 0;
	size_t unmapped;
	struct virtio_iommu_req_unmap unmap;
	struct viommu_domain *vdomain = to_viommu_domain(domain);

	unmapped = viommu_del_mappings(vdomain, iova, size);
	if (unmapped < size)
		return 0;

	/* Device already removed all mappings after detach. */
	if (!vdomain->nr_endpoints)
		return unmapped;

	unmap = (struct virtio_iommu_req_unmap) {
		.head.type	= VIRTIO_IOMMU_T_UNMAP,
		.domain		= cpu_to_le32(vdomain->id),
		.virt_start	= cpu_to_le64(iova),
		.virt_end	= cpu_to_le64(iova + unmapped - 1),
	};

	ret = viommu_add_req(vdomain->viommu, &unmap, sizeof(unmap));
	return ret ? 0 : unmapped;
}

static phys_addr_t viommu_iova_to_phys(struct iommu_domain *domain,
				       dma_addr_t iova)
{
	u64 paddr = 0;
	unsigned long flags;
	struct viommu_mapping *mapping;
	struct interval_tree_node *node;
	struct viommu_domain *vdomain = to_viommu_domain(domain);

	spin_lock_irqsave(&vdomain->mappings_lock, flags);
	node = interval_tree_iter_first(&vdomain->mappings, iova, iova);
	if (node) {
		mapping = container_of(node, struct viommu_mapping, iova);
		paddr = mapping->paddr + (iova - mapping->iova.start);
	}
	spin_unlock_irqrestore(&vdomain->mappings_lock, flags);

	return paddr;
}

static void viommu_iotlb_sync(struct iommu_domain *domain,
			      struct iommu_iotlb_gather *gather)
{
	struct viommu_domain *vdomain = to_viommu_domain(domain);

	viommu_sync_req(vdomain->viommu);
}

static void viommu_get_resv_regions(struct device *dev, struct list_head *head)
{
	struct iommu_resv_region *entry, *new_entry, *msi = NULL;
	struct viommu_endpoint *vdev = dev_iommu_priv_get(dev);
	int prot = IOMMU_WRITE | IOMMU_NOEXEC | IOMMU_MMIO;

	list_for_each_entry(entry, &vdev->resv_regions, list) {
		if (entry->type == IOMMU_RESV_MSI)
			msi = entry;

		new_entry = kmemdup(entry, sizeof(*entry), GFP_KERNEL);
		if (!new_entry)
			return;
		list_add_tail(&new_entry->list, head);
	}

	/*
	 * If the device didn't register any bypass MSI window, add a
	 * software-mapped region.
	 */
	if (!msi) {
		msi = iommu_alloc_resv_region(MSI_IOVA_BASE, MSI_IOVA_LENGTH,
					      prot, IOMMU_RESV_SW_MSI);
		if (!msi)
			return;

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

	iommu_dma_get_resv_regions(dev, head);
}

static struct iommu_ops viommu_ops;
static struct virtio_driver virtio_iommu_drv;

static int viommu_match_node(struct device *dev, const void *data)
{
	return dev->parent->fwnode == data;
}

static struct viommu_dev *viommu_get_by_fwnode(struct fwnode_handle *fwnode)
{
	struct device *dev = driver_find_device(&virtio_iommu_drv.driver, NULL,
						fwnode, viommu_match_node);
	put_device(dev);

	return dev ? dev_to_virtio(dev)->priv : NULL;
}

static int viommu_add_device(struct device *dev)
{
	int ret;
	struct iommu_group *group;
	struct viommu_endpoint *vdev;
	struct viommu_dev *viommu = NULL;
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);

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

	viommu = viommu_get_by_fwnode(fwspec->iommu_fwnode);
	if (!viommu)
		return -ENODEV;

	vdev = kzalloc(sizeof(*vdev), GFP_KERNEL);
	if (!vdev)
		return -ENOMEM;

	vdev->dev = dev;
	vdev->viommu = viommu;
	INIT_LIST_HEAD(&vdev->resv_regions);
	dev_iommu_priv_set(dev, vdev);

	if (viommu->probe_size) {
		/* Get additional information for this endpoint */
		ret = viommu_probe_endpoint(viommu, dev);
		if (ret)
			goto err_free_dev;
	}

	ret = iommu_device_link(&viommu->iommu, dev);
	if (ret)
		goto err_free_dev;

	/*
	 * Last step creates a default domain and attaches to it. Everything
	 * must be ready.
	 */
	group = iommu_group_get_for_dev(dev);
	if (IS_ERR(group)) {
		ret = PTR_ERR(group);
		goto err_unlink_dev;
	}

	iommu_group_put(group);

	return PTR_ERR_OR_ZERO(group);

err_unlink_dev:
	iommu_device_unlink(&viommu->iommu, dev);
err_free_dev:
	generic_iommu_put_resv_regions(dev, &vdev->resv_regions);
	kfree(vdev);

	return ret;
}

static void viommu_remove_device(struct device *dev)
{
	struct viommu_endpoint *vdev;
	struct iommu_fwspec *fwspec = dev_iommu_fwspec_get(dev);

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

	vdev = dev_iommu_priv_get(dev);

	iommu_group_remove_device(dev);
	iommu_device_unlink(&vdev->viommu->iommu, dev);
	generic_iommu_put_resv_regions(dev, &vdev->resv_regions);
	kfree(vdev);
}

static struct iommu_group *viommu_device_group(struct device *dev)
{
	if (dev_is_pci(dev))
		return pci_device_group(dev);
	else
		return generic_device_group(dev);
}

static int viommu_of_xlate(struct device *dev, struct of_phandle_args *args)
{
	return iommu_fwspec_add_ids(dev, args->args, 1);
}

static struct iommu_ops viommu_ops = {
	.domain_alloc		= viommu_domain_alloc,
	.domain_free		= viommu_domain_free,
	.attach_dev		= viommu_attach_dev,
	.map			= viommu_map,
	.unmap			= viommu_unmap,
	.iova_to_phys		= viommu_iova_to_phys,
	.iotlb_sync		= viommu_iotlb_sync,
	.add_device		= viommu_add_device,
	.remove_device		= viommu_remove_device,
	.device_group		= viommu_device_group,
	.get_resv_regions	= viommu_get_resv_regions,
	.put_resv_regions	= generic_iommu_put_resv_regions,
	.of_xlate		= viommu_of_xlate,
};

static int viommu_init_vqs(struct viommu_dev *viommu)
{
	struct virtio_device *vdev = dev_to_virtio(viommu->dev);
	const char *names[] = { "request", "event" };
	vq_callback_t *callbacks[] = {
		NULL, /* No async requests */
		viommu_event_handler,
	};

	return virtio_find_vqs(vdev, VIOMMU_NR_VQS, viommu->vqs, callbacks,
			       names, NULL);
}

static int viommu_fill_evtq(struct viommu_dev *viommu)
{
	int i, ret;
	struct scatterlist sg[1];
	struct viommu_event *evts;
	struct virtqueue *vq = viommu->vqs[VIOMMU_EVENT_VQ];
	size_t nr_evts = vq->num_free;

	viommu->evts = evts = devm_kmalloc_array(viommu->dev, nr_evts,
						 sizeof(*evts), GFP_KERNEL);
	if (!evts)
		return -ENOMEM;

	for (i = 0; i < nr_evts; i++) {
		sg_init_one(sg, &evts[i], sizeof(*evts));
		ret = virtqueue_add_inbuf(vq, sg, 1, &evts[i], GFP_KERNEL);
		if (ret)
			return ret;
	}

	return 0;
}

static int viommu_probe(struct virtio_device *vdev)
{
	struct device *parent_dev = vdev->dev.parent;
	struct viommu_dev *viommu = NULL;
	struct device *dev = &vdev->dev;
	u64 input_start = 0;
	u64 input_end = -1UL;
	int ret;

	if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1) ||
	    !virtio_has_feature(vdev, VIRTIO_IOMMU_F_MAP_UNMAP))
		return -ENODEV;

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

	spin_lock_init(&viommu->request_lock);
	ida_init(&viommu->domain_ids);
	viommu->dev = dev;
	viommu->vdev = vdev;
	INIT_LIST_HEAD(&viommu->requests);

	ret = viommu_init_vqs(viommu);
	if (ret)
		return ret;

	virtio_cread(vdev, struct virtio_iommu_config, page_size_mask,
		     &viommu->pgsize_bitmap);

	if (!viommu->pgsize_bitmap) {
		ret = -EINVAL;
		goto err_free_vqs;
	}

	viommu->map_flags = VIRTIO_IOMMU_MAP_F_READ | VIRTIO_IOMMU_MAP_F_WRITE;
	viommu->last_domain = ~0U;

	/* Optional features */
	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
			     struct virtio_iommu_config, input_range.start,
			     &input_start);

	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_INPUT_RANGE,
			     struct virtio_iommu_config, input_range.end,
			     &input_end);

	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
			     struct virtio_iommu_config, domain_range.start,
			     &viommu->first_domain);

	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_DOMAIN_RANGE,
			     struct virtio_iommu_config, domain_range.end,
			     &viommu->last_domain);

	virtio_cread_feature(vdev, VIRTIO_IOMMU_F_PROBE,
			     struct virtio_iommu_config, probe_size,
			     &viommu->probe_size);

	viommu->geometry = (struct iommu_domain_geometry) {
		.aperture_start	= input_start,
		.aperture_end	= input_end,
		.force_aperture	= true,
	};

	if (virtio_has_feature(vdev, VIRTIO_IOMMU_F_MMIO))
		viommu->map_flags |= VIRTIO_IOMMU_MAP_F_MMIO;

	viommu_ops.pgsize_bitmap = viommu->pgsize_bitmap;

	virtio_device_ready(vdev);

	/* Populate the event queue with buffers */
	ret = viommu_fill_evtq(viommu);
	if (ret)
		goto err_free_vqs;

	ret = iommu_device_sysfs_add(&viommu->iommu, dev, NULL, "%s",
				     virtio_bus_name(vdev));
	if (ret)
		goto err_free_vqs;

	iommu_device_set_ops(&viommu->iommu, &viommu_ops);
	iommu_device_set_fwnode(&viommu->iommu, parent_dev->fwnode);

	iommu_device_register(&viommu->iommu);

#ifdef CONFIG_PCI
	if (pci_bus_type.iommu_ops != &viommu_ops) {
		ret = bus_set_iommu(&pci_bus_type, &viommu_ops);
		if (ret)
			goto err_unregister;
	}
#endif
#ifdef CONFIG_ARM_AMBA
	if (amba_bustype.iommu_ops != &viommu_ops) {
		ret = bus_set_iommu(&amba_bustype, &viommu_ops);
		if (ret)
			goto err_unregister;
	}
#endif
	if (platform_bus_type.iommu_ops != &viommu_ops) {
		ret = bus_set_iommu(&platform_bus_type, &viommu_ops);
		if (ret)
			goto err_unregister;
	}

	vdev->priv = viommu;

	dev_info(dev, "input address: %u bits\n",
		 order_base_2(viommu->geometry.aperture_end));
	dev_info(dev, "page mask: %#llx\n", viommu->pgsize_bitmap);

	return 0;

err_unregister:
	iommu_device_sysfs_remove(&viommu->iommu);
	iommu_device_unregister(&viommu->iommu);
err_free_vqs:
	vdev->config->del_vqs(vdev);

	return ret;
}

static void viommu_remove(struct virtio_device *vdev)
{
	struct viommu_dev *viommu = vdev->priv;

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

	/* Stop all virtqueues */
	vdev->config->reset(vdev);
	vdev->config->del_vqs(vdev);

	dev_info(&vdev->dev, "device removed\n");
}

static void viommu_config_changed(struct virtio_device *vdev)
{
	dev_warn(&vdev->dev, "config changed\n");
}

static unsigned int features[] = {
	VIRTIO_IOMMU_F_MAP_UNMAP,
	VIRTIO_IOMMU_F_INPUT_RANGE,
	VIRTIO_IOMMU_F_DOMAIN_RANGE,
	VIRTIO_IOMMU_F_PROBE,
	VIRTIO_IOMMU_F_MMIO,
};

static struct virtio_device_id id_table[] = {
	{ VIRTIO_ID_IOMMU, VIRTIO_DEV_ANY_ID },
	{ 0 },
};

static struct virtio_driver virtio_iommu_drv = {
	.driver.name		= KBUILD_MODNAME,
	.driver.owner		= THIS_MODULE,
	.id_table		= id_table,
	.feature_table		= features,
	.feature_table_size	= ARRAY_SIZE(features),
	.probe			= viommu_probe,
	.remove			= viommu_remove,
	.config_changed		= viommu_config_changed,
};

module_virtio_driver(virtio_iommu_drv);

MODULE_DESCRIPTION("Virtio IOMMU driver");
MODULE_AUTHOR("Jean-Philippe Brucker <jean-philippe.brucker@arm.com>");
MODULE_LICENSE("GPL v2");