summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kvm/vgic/vgic-mmio.c
blob: 49837d3a3ef5625ba0c5e4d2fed57e362b55ffc0 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * VGIC MMIO handling functions
 */

#include <linux/bitops.h>
#include <linux/bsearch.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <kvm/iodev.h>
#include <kvm/arm_arch_timer.h>
#include <kvm/arm_vgic.h>

#include "vgic.h"
#include "vgic-mmio.h"

unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu,
				 gpa_t addr, unsigned int len)
{
	return 0;
}

unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu,
				 gpa_t addr, unsigned int len)
{
	return -1UL;
}

void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr,
			unsigned int len, unsigned long val)
{
	/* Ignore */
}

int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr,
			       unsigned int len, unsigned long val)
{
	/* Ignore */
	return 0;
}

unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu,
				   gpa_t addr, unsigned int len)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	u32 value = 0;
	int i;

	/* Loop over all IRQs affected by this read */
	for (i = 0; i < len * 8; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		if (irq->group)
			value |= BIT(i);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return value;
}

static void vgic_update_vsgi(struct vgic_irq *irq)
{
	WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group));
}

void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr,
			   unsigned int len, unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for (i = 0; i < len * 8; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		irq->group = !!(val & BIT(i));
		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
			vgic_update_vsgi(irq);
			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
		} else {
			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
		}

		vgic_put_irq(vcpu->kvm, irq);
	}
}

/*
 * Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value
 * of the enabled bit, so there is only one function for both here.
 */
unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu,
				    gpa_t addr, unsigned int len)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	u32 value = 0;
	int i;

	/* Loop over all IRQs affected by this read */
	for (i = 0; i < len * 8; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		if (irq->enabled)
			value |= (1U << i);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return value;
}

void vgic_mmio_write_senable(struct kvm_vcpu *vcpu,
			     gpa_t addr, unsigned int len,
			     unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
			if (!irq->enabled) {
				struct irq_data *data;

				irq->enabled = true;
				data = &irq_to_desc(irq->host_irq)->irq_data;
				while (irqd_irq_disabled(data))
					enable_irq(irq->host_irq);
			}

			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
			vgic_put_irq(vcpu->kvm, irq);

			continue;
		} else if (vgic_irq_is_mapped_level(irq)) {
			bool was_high = irq->line_level;

			/*
			 * We need to update the state of the interrupt because
			 * the guest might have changed the state of the device
			 * while the interrupt was disabled at the VGIC level.
			 */
			irq->line_level = vgic_get_phys_line_level(irq);
			/*
			 * Deactivate the physical interrupt so the GIC will let
			 * us know when it is asserted again.
			 */
			if (!irq->active && was_high && !irq->line_level)
				vgic_irq_set_phys_active(irq, false);
		}
		irq->enabled = true;
		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}
}

void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu,
			     gpa_t addr, unsigned int len,
			     unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled)
			disable_irq_nosync(irq->host_irq);

		irq->enabled = false;

		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
		vgic_put_irq(vcpu->kvm, irq);
	}
}

int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu,
			       gpa_t addr, unsigned int len,
			       unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		irq->enabled = true;
		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return 0;
}

int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu,
			       gpa_t addr, unsigned int len,
			       unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		irq->enabled = false;
		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return 0;
}

unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu,
				     gpa_t addr, unsigned int len)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	u32 value = 0;
	int i;

	/* Loop over all IRQs affected by this read */
	for (i = 0; i < len * 8; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
		unsigned long flags;
		bool val;

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
			int err;

			val = false;
			err = irq_get_irqchip_state(irq->host_irq,
						    IRQCHIP_STATE_PENDING,
						    &val);
			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);
		} else if (vgic_irq_is_mapped_level(irq)) {
			val = vgic_get_phys_line_level(irq);
		} else {
			val = irq_is_pending(irq);
		}

		value |= ((u32)val << i);
		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return value;
}

static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
{
	return (vgic_irq_is_sgi(irq->intid) &&
		vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2);
}

void vgic_mmio_write_spending(struct kvm_vcpu *vcpu,
			      gpa_t addr, unsigned int len,
			      unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		/* GICD_ISPENDR0 SGI bits are WI */
		if (is_vgic_v2_sgi(vcpu, irq)) {
			vgic_put_irq(vcpu->kvm, irq);
			continue;
		}

		raw_spin_lock_irqsave(&irq->irq_lock, flags);

		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
			/* HW SGI? Ask the GIC to inject it */
			int err;
			err = irq_set_irqchip_state(irq->host_irq,
						    IRQCHIP_STATE_PENDING,
						    true);
			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);

			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
			vgic_put_irq(vcpu->kvm, irq);

			continue;
		}

		irq->pending_latch = true;
		if (irq->hw)
			vgic_irq_set_phys_active(irq, true);

		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
		vgic_put_irq(vcpu->kvm, irq);
	}
}

int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu,
				gpa_t addr, unsigned int len,
				unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		irq->pending_latch = true;

		/*
		 * GICv2 SGIs are terribly broken. We can't restore
		 * the source of the interrupt, so just pick the vcpu
		 * itself as the source...
		 */
		if (is_vgic_v2_sgi(vcpu, irq))
			irq->source |= BIT(vcpu->vcpu_id);

		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return 0;
}

/* Must be called with irq->irq_lock held */
static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq)
{
	irq->pending_latch = false;

	/*
	 * We don't want the guest to effectively mask the physical
	 * interrupt by doing a write to SPENDR followed by a write to
	 * CPENDR for HW interrupts, so we clear the active state on
	 * the physical side if the virtual interrupt is not active.
	 * This may lead to taking an additional interrupt on the
	 * host, but that should not be a problem as the worst that
	 * can happen is an additional vgic injection.  We also clear
	 * the pending state to maintain proper semantics for edge HW
	 * interrupts.
	 */
	vgic_irq_set_phys_pending(irq, false);
	if (!irq->active)
		vgic_irq_set_phys_active(irq, false);
}

void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu,
			      gpa_t addr, unsigned int len,
			      unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		/* GICD_ICPENDR0 SGI bits are WI */
		if (is_vgic_v2_sgi(vcpu, irq)) {
			vgic_put_irq(vcpu->kvm, irq);
			continue;
		}

		raw_spin_lock_irqsave(&irq->irq_lock, flags);

		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
			/* HW SGI? Ask the GIC to clear its pending bit */
			int err;
			err = irq_set_irqchip_state(irq->host_irq,
						    IRQCHIP_STATE_PENDING,
						    false);
			WARN_RATELIMIT(err, "IRQ %d", irq->host_irq);

			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
			vgic_put_irq(vcpu->kvm, irq);

			continue;
		}

		if (irq->hw)
			vgic_hw_irq_cpending(vcpu, irq);
		else
			irq->pending_latch = false;

		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
		vgic_put_irq(vcpu->kvm, irq);
	}
}

int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu,
				gpa_t addr, unsigned int len,
				unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;
	unsigned long flags;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		/*
		 * More fun with GICv2 SGIs! If we're clearing one of them
		 * from userspace, which source vcpu to clear? Let's not
		 * even think of it, and blow the whole set.
		 */
		if (is_vgic_v2_sgi(vcpu, irq))
			irq->source = 0;

		irq->pending_latch = false;

		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return 0;
}

/*
 * If we are fiddling with an IRQ's active state, we have to make sure the IRQ
 * is not queued on some running VCPU's LRs, because then the change to the
 * active state can be overwritten when the VCPU's state is synced coming back
 * from the guest.
 *
 * For shared interrupts as well as GICv3 private interrupts, we have to
 * stop all the VCPUs because interrupts can be migrated while we don't hold
 * the IRQ locks and we don't want to be chasing moving targets.
 *
 * For GICv2 private interrupts we don't have to do anything because
 * userspace accesses to the VGIC state already require all VCPUs to be
 * stopped, and only the VCPU itself can modify its private interrupts
 * active state, which guarantees that the VCPU is not running.
 */
static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid)
{
	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
	    intid >= VGIC_NR_PRIVATE_IRQS)
		kvm_arm_halt_guest(vcpu->kvm);
}

/* See vgic_access_active_prepare */
static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid)
{
	if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 ||
	    intid >= VGIC_NR_PRIVATE_IRQS)
		kvm_arm_resume_guest(vcpu->kvm);
}

static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu,
					     gpa_t addr, unsigned int len)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	u32 value = 0;
	int i;

	/* Loop over all IRQs affected by this read */
	for (i = 0; i < len * 8; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		/*
		 * Even for HW interrupts, don't evaluate the HW state as
		 * all the guest is interested in is the virtual state.
		 */
		if (irq->active)
			value |= (1U << i);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return value;
}

unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu,
				    gpa_t addr, unsigned int len)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	u32 val;

	mutex_lock(&vcpu->kvm->lock);
	vgic_access_active_prepare(vcpu, intid);

	val = __vgic_mmio_read_active(vcpu, addr, len);

	vgic_access_active_finish(vcpu, intid);
	mutex_unlock(&vcpu->kvm->lock);

	return val;
}

unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu,
				    gpa_t addr, unsigned int len)
{
	return __vgic_mmio_read_active(vcpu, addr, len);
}

/* Must be called with irq->irq_lock held */
static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
				      bool active, bool is_uaccess)
{
	if (is_uaccess)
		return;

	irq->active = active;
	vgic_irq_set_phys_active(irq, active);
}

static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
				    bool active)
{
	unsigned long flags;
	struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu();

	raw_spin_lock_irqsave(&irq->irq_lock, flags);

	if (irq->hw && !vgic_irq_is_sgi(irq->intid)) {
		vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu);
	} else if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
		/*
		 * GICv4.1 VSGI feature doesn't track an active state,
		 * so let's not kid ourselves, there is nothing we can
		 * do here.
		 */
		irq->active = false;
	} else {
		u32 model = vcpu->kvm->arch.vgic.vgic_model;
		u8 active_source;

		irq->active = active;

		/*
		 * The GICv2 architecture indicates that the source CPUID for
		 * an SGI should be provided during an EOI which implies that
		 * the active state is stored somewhere, but at the same time
		 * this state is not architecturally exposed anywhere and we
		 * have no way of knowing the right source.
		 *
		 * This may lead to a VCPU not being able to receive
		 * additional instances of a particular SGI after migration
		 * for a GICv2 VM on some GIC implementations.  Oh well.
		 */
		active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0;

		if (model == KVM_DEV_TYPE_ARM_VGIC_V2 &&
		    active && vgic_irq_is_sgi(irq->intid))
			irq->active_source = active_source;
	}

	if (irq->active)
		vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
	else
		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
}

static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
				      gpa_t addr, unsigned int len,
				      unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
		vgic_mmio_change_active(vcpu, irq, false);
		vgic_put_irq(vcpu->kvm, irq);
	}
}

void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu,
			     gpa_t addr, unsigned int len,
			     unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);

	mutex_lock(&vcpu->kvm->lock);
	vgic_access_active_prepare(vcpu, intid);

	__vgic_mmio_write_cactive(vcpu, addr, len, val);

	vgic_access_active_finish(vcpu, intid);
	mutex_unlock(&vcpu->kvm->lock);
}

int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu,
				     gpa_t addr, unsigned int len,
				     unsigned long val)
{
	__vgic_mmio_write_cactive(vcpu, addr, len, val);
	return 0;
}

static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
				      gpa_t addr, unsigned int len,
				      unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);
	int i;

	for_each_set_bit(i, &val, len * 8) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
		vgic_mmio_change_active(vcpu, irq, true);
		vgic_put_irq(vcpu->kvm, irq);
	}
}

void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu,
			     gpa_t addr, unsigned int len,
			     unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 1);

	mutex_lock(&vcpu->kvm->lock);
	vgic_access_active_prepare(vcpu, intid);

	__vgic_mmio_write_sactive(vcpu, addr, len, val);

	vgic_access_active_finish(vcpu, intid);
	mutex_unlock(&vcpu->kvm->lock);
}

int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu,
				     gpa_t addr, unsigned int len,
				     unsigned long val)
{
	__vgic_mmio_write_sactive(vcpu, addr, len, val);
	return 0;
}

unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu,
				      gpa_t addr, unsigned int len)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
	int i;
	u64 val = 0;

	for (i = 0; i < len; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		val |= (u64)irq->priority << (i * 8);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return val;
}

/*
 * We currently don't handle changing the priority of an interrupt that
 * is already pending on a VCPU. If there is a need for this, we would
 * need to make this VCPU exit and re-evaluate the priorities, potentially
 * leading to this interrupt getting presented now to the guest (if it has
 * been masked by the priority mask before).
 */
void vgic_mmio_write_priority(struct kvm_vcpu *vcpu,
			      gpa_t addr, unsigned int len,
			      unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 8);
	int i;
	unsigned long flags;

	for (i = 0; i < len; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		/* Narrow the priority range to what we actually support */
		irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS);
		if (irq->hw && vgic_irq_is_sgi(irq->intid))
			vgic_update_vsgi(irq);
		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}
}

unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu,
				    gpa_t addr, unsigned int len)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 2);
	u32 value = 0;
	int i;

	for (i = 0; i < len * 4; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		if (irq->config == VGIC_CONFIG_EDGE)
			value |= (2U << (i * 2));

		vgic_put_irq(vcpu->kvm, irq);
	}

	return value;
}

void vgic_mmio_write_config(struct kvm_vcpu *vcpu,
			    gpa_t addr, unsigned int len,
			    unsigned long val)
{
	u32 intid = VGIC_ADDR_TO_INTID(addr, 2);
	int i;
	unsigned long flags;

	for (i = 0; i < len * 4; i++) {
		struct vgic_irq *irq;

		/*
		 * The configuration cannot be changed for SGIs in general,
		 * for PPIs this is IMPLEMENTATION DEFINED. The arch timer
		 * code relies on PPIs being level triggered, so we also
		 * make them read-only here.
		 */
		if (intid + i < VGIC_NR_PRIVATE_IRQS)
			continue;

		irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
		raw_spin_lock_irqsave(&irq->irq_lock, flags);

		if (test_bit(i * 2 + 1, &val))
			irq->config = VGIC_CONFIG_EDGE;
		else
			irq->config = VGIC_CONFIG_LEVEL;

		raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
		vgic_put_irq(vcpu->kvm, irq);
	}
}

u64 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid)
{
	int i;
	u64 val = 0;
	int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;

	for (i = 0; i < 32; i++) {
		struct vgic_irq *irq;

		if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs)
			continue;

		irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
		if (irq->config == VGIC_CONFIG_LEVEL && irq->line_level)
			val |= (1U << i);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return val;
}

void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid,
				    const u64 val)
{
	int i;
	int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;
	unsigned long flags;

	for (i = 0; i < 32; i++) {
		struct vgic_irq *irq;
		bool new_level;

		if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs)
			continue;

		irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);

		/*
		 * Line level is set irrespective of irq type
		 * (level or edge) to avoid dependency that VM should
		 * restore irq config before line level.
		 */
		new_level = !!(val & (1U << i));
		raw_spin_lock_irqsave(&irq->irq_lock, flags);
		irq->line_level = new_level;
		if (new_level)
			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
		else
			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);

		vgic_put_irq(vcpu->kvm, irq);
	}
}

static int match_region(const void *key, const void *elt)
{
	const unsigned int offset = (unsigned long)key;
	const struct vgic_register_region *region = elt;

	if (offset < region->reg_offset)
		return -1;

	if (offset >= region->reg_offset + region->len)
		return 1;

	return 0;
}

const struct vgic_register_region *
vgic_find_mmio_region(const struct vgic_register_region *regions,
		      int nr_regions, unsigned int offset)
{
	return bsearch((void *)(uintptr_t)offset, regions, nr_regions,
		       sizeof(regions[0]), match_region);
}

void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
{
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_set_vmcr(vcpu, vmcr);
	else
		vgic_v3_set_vmcr(vcpu, vmcr);
}

void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr)
{
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_get_vmcr(vcpu, vmcr);
	else
		vgic_v3_get_vmcr(vcpu, vmcr);
}

/*
 * kvm_mmio_read_buf() returns a value in a format where it can be converted
 * to a byte array and be directly observed as the guest wanted it to appear
 * in memory if it had done the store itself, which is LE for the GIC, as the
 * guest knows the GIC is always LE.
 *
 * We convert this value to the CPUs native format to deal with it as a data
 * value.
 */
unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len)
{
	unsigned long data = kvm_mmio_read_buf(val, len);

	switch (len) {
	case 1:
		return data;
	case 2:
		return le16_to_cpu(data);
	case 4:
		return le32_to_cpu(data);
	default:
		return le64_to_cpu(data);
	}
}

/*
 * kvm_mmio_write_buf() expects a value in a format such that if converted to
 * a byte array it is observed as the guest would see it if it could perform
 * the load directly.  Since the GIC is LE, and the guest knows this, the
 * guest expects a value in little endian format.
 *
 * We convert the data value from the CPUs native format to LE so that the
 * value is returned in the proper format.
 */
void vgic_data_host_to_mmio_bus(void *buf, unsigned int len,
				unsigned long data)
{
	switch (len) {
	case 1:
		break;
	case 2:
		data = cpu_to_le16(data);
		break;
	case 4:
		data = cpu_to_le32(data);
		break;
	default:
		data = cpu_to_le64(data);
	}

	kvm_mmio_write_buf(buf, len, data);
}

static
struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev)
{
	return container_of(dev, struct vgic_io_device, dev);
}

static bool check_region(const struct kvm *kvm,
			 const struct vgic_register_region *region,
			 gpa_t addr, int len)
{
	int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS;

	switch (len) {
	case sizeof(u8):
		flags = VGIC_ACCESS_8bit;
		break;
	case sizeof(u32):
		flags = VGIC_ACCESS_32bit;
		break;
	case sizeof(u64):
		flags = VGIC_ACCESS_64bit;
		break;
	default:
		return false;
	}

	if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) {
		if (!region->bits_per_irq)
			return true;

		/* Do we access a non-allocated IRQ? */
		return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs;
	}

	return false;
}

const struct vgic_register_region *
vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
		     gpa_t addr, int len)
{
	const struct vgic_register_region *region;

	region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions,
				       addr - iodev->base_addr);
	if (!region || !check_region(vcpu->kvm, region, addr, len))
		return NULL;

	return region;
}

static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
			     gpa_t addr, u32 *val)
{
	const struct vgic_register_region *region;
	struct kvm_vcpu *r_vcpu;

	region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32));
	if (!region) {
		*val = 0;
		return 0;
	}

	r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
	if (region->uaccess_read)
		*val = region->uaccess_read(r_vcpu, addr, sizeof(u32));
	else
		*val = region->read(r_vcpu, addr, sizeof(u32));

	return 0;
}

static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev,
			      gpa_t addr, const u32 *val)
{
	const struct vgic_register_region *region;
	struct kvm_vcpu *r_vcpu;

	region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32));
	if (!region)
		return 0;

	r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu;
	if (region->uaccess_write)
		return region->uaccess_write(r_vcpu, addr, sizeof(u32), *val);

	region->write(r_vcpu, addr, sizeof(u32), *val);
	return 0;
}

/*
 * Userland access to VGIC registers.
 */
int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev,
		 bool is_write, int offset, u32 *val)
{
	if (is_write)
		return vgic_uaccess_write(vcpu, dev, offset, val);
	else
		return vgic_uaccess_read(vcpu, dev, offset, val);
}

static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
			      gpa_t addr, int len, void *val)
{
	struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
	const struct vgic_register_region *region;
	unsigned long data = 0;

	region = vgic_get_mmio_region(vcpu, iodev, addr, len);
	if (!region) {
		memset(val, 0, len);
		return 0;
	}

	switch (iodev->iodev_type) {
	case IODEV_CPUIF:
		data = region->read(vcpu, addr, len);
		break;
	case IODEV_DIST:
		data = region->read(vcpu, addr, len);
		break;
	case IODEV_REDIST:
		data = region->read(iodev->redist_vcpu, addr, len);
		break;
	case IODEV_ITS:
		data = region->its_read(vcpu->kvm, iodev->its, addr, len);
		break;
	}

	vgic_data_host_to_mmio_bus(val, len, data);
	return 0;
}

static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev,
			       gpa_t addr, int len, const void *val)
{
	struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev);
	const struct vgic_register_region *region;
	unsigned long data = vgic_data_mmio_bus_to_host(val, len);

	region = vgic_get_mmio_region(vcpu, iodev, addr, len);
	if (!region)
		return 0;

	switch (iodev->iodev_type) {
	case IODEV_CPUIF:
		region->write(vcpu, addr, len, data);
		break;
	case IODEV_DIST:
		region->write(vcpu, addr, len, data);
		break;
	case IODEV_REDIST:
		region->write(iodev->redist_vcpu, addr, len, data);
		break;
	case IODEV_ITS:
		region->its_write(vcpu->kvm, iodev->its, addr, len, data);
		break;
	}

	return 0;
}

const struct kvm_io_device_ops kvm_io_gic_ops = {
	.read = dispatch_mmio_read,
	.write = dispatch_mmio_write,
};

int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address,
			     enum vgic_type type)
{
	struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev;
	int ret = 0;
	unsigned int len;

	switch (type) {
	case VGIC_V2:
		len = vgic_v2_init_dist_iodev(io_device);
		break;
	case VGIC_V3:
		len = vgic_v3_init_dist_iodev(io_device);
		break;
	default:
		BUG_ON(1);
	}

	io_device->base_addr = dist_base_address;
	io_device->iodev_type = IODEV_DIST;
	io_device->redist_vcpu = NULL;

	mutex_lock(&kvm->slots_lock);
	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address,
				      len, &io_device->dev);
	mutex_unlock(&kvm->slots_lock);

	return ret;
}