summaryrefslogtreecommitdiffstats
path: root/arch/arm64/kvm/vgic/vgic-mmio-v3.c
blob: 15a6c98ee92f05cdf35f19c5ed5cbd7a6738f699 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * VGICv3 MMIO handling functions
 */

#include <linux/bitfield.h>
#include <linux/irqchip/arm-gic-v3.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <kvm/iodev.h>
#include <kvm/arm_vgic.h>

#include <asm/kvm_emulate.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_mmu.h>

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

/* extract @num bytes at @offset bytes offset in data */
unsigned long extract_bytes(u64 data, unsigned int offset,
			    unsigned int num)
{
	return (data >> (offset * 8)) & GENMASK_ULL(num * 8 - 1, 0);
}

/* allows updates of any half of a 64-bit register (or the whole thing) */
u64 update_64bit_reg(u64 reg, unsigned int offset, unsigned int len,
		     unsigned long val)
{
	int lower = (offset & 4) * 8;
	int upper = lower + 8 * len - 1;

	reg &= ~GENMASK_ULL(upper, lower);
	val &= GENMASK_ULL(len * 8 - 1, 0);

	return reg | ((u64)val << lower);
}

bool vgic_has_its(struct kvm *kvm)
{
	struct vgic_dist *dist = &kvm->arch.vgic;

	if (dist->vgic_model != KVM_DEV_TYPE_ARM_VGIC_V3)
		return false;

	return dist->has_its;
}

bool vgic_supports_direct_msis(struct kvm *kvm)
{
	return (kvm_vgic_global_state.has_gicv4_1 ||
		(kvm_vgic_global_state.has_gicv4 && vgic_has_its(kvm)));
}

/*
 * The Revision field in the IIDR have the following meanings:
 *
 * Revision 2: Interrupt groups are guest-configurable and signaled using
 * 	       their configured groups.
 */

static unsigned long vgic_mmio_read_v3_misc(struct kvm_vcpu *vcpu,
					    gpa_t addr, unsigned int len)
{
	struct vgic_dist *vgic = &vcpu->kvm->arch.vgic;
	u32 value = 0;

	switch (addr & 0x0c) {
	case GICD_CTLR:
		if (vgic->enabled)
			value |= GICD_CTLR_ENABLE_SS_G1;
		value |= GICD_CTLR_ARE_NS | GICD_CTLR_DS;
		if (vgic->nassgireq)
			value |= GICD_CTLR_nASSGIreq;
		break;
	case GICD_TYPER:
		value = vgic->nr_spis + VGIC_NR_PRIVATE_IRQS;
		value = (value >> 5) - 1;
		if (vgic_has_its(vcpu->kvm)) {
			value |= (INTERRUPT_ID_BITS_ITS - 1) << 19;
			value |= GICD_TYPER_LPIS;
		} else {
			value |= (INTERRUPT_ID_BITS_SPIS - 1) << 19;
		}
		break;
	case GICD_TYPER2:
		if (kvm_vgic_global_state.has_gicv4_1)
			value = GICD_TYPER2_nASSGIcap;
		break;
	case GICD_IIDR:
		value = (PRODUCT_ID_KVM << GICD_IIDR_PRODUCT_ID_SHIFT) |
			(vgic->implementation_rev << GICD_IIDR_REVISION_SHIFT) |
			(IMPLEMENTER_ARM << GICD_IIDR_IMPLEMENTER_SHIFT);
		break;
	default:
		return 0;
	}

	return value;
}

static void vgic_mmio_write_v3_misc(struct kvm_vcpu *vcpu,
				    gpa_t addr, unsigned int len,
				    unsigned long val)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	switch (addr & 0x0c) {
	case GICD_CTLR: {
		bool was_enabled, is_hwsgi;

		mutex_lock(&vcpu->kvm->lock);

		was_enabled = dist->enabled;
		is_hwsgi = dist->nassgireq;

		dist->enabled = val & GICD_CTLR_ENABLE_SS_G1;

		/* Not a GICv4.1? No HW SGIs */
		if (!kvm_vgic_global_state.has_gicv4_1)
			val &= ~GICD_CTLR_nASSGIreq;

		/* Dist stays enabled? nASSGIreq is RO */
		if (was_enabled && dist->enabled) {
			val &= ~GICD_CTLR_nASSGIreq;
			val |= FIELD_PREP(GICD_CTLR_nASSGIreq, is_hwsgi);
		}

		/* Switching HW SGIs? */
		dist->nassgireq = val & GICD_CTLR_nASSGIreq;
		if (is_hwsgi != dist->nassgireq)
			vgic_v4_configure_vsgis(vcpu->kvm);

		if (kvm_vgic_global_state.has_gicv4_1 &&
		    was_enabled != dist->enabled)
			kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_RELOAD_GICv4);
		else if (!was_enabled && dist->enabled)
			vgic_kick_vcpus(vcpu->kvm);

		mutex_unlock(&vcpu->kvm->lock);
		break;
	}
	case GICD_TYPER:
	case GICD_TYPER2:
	case GICD_IIDR:
		/* This is at best for documentation purposes... */
		return;
	}
}

static int vgic_mmio_uaccess_write_v3_misc(struct kvm_vcpu *vcpu,
					   gpa_t addr, unsigned int len,
					   unsigned long val)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	switch (addr & 0x0c) {
	case GICD_TYPER2:
	case GICD_IIDR:
		if (val != vgic_mmio_read_v3_misc(vcpu, addr, len))
			return -EINVAL;
		return 0;
	case GICD_CTLR:
		/* Not a GICv4.1? No HW SGIs */
		if (!kvm_vgic_global_state.has_gicv4_1)
			val &= ~GICD_CTLR_nASSGIreq;

		dist->enabled = val & GICD_CTLR_ENABLE_SS_G1;
		dist->nassgireq = val & GICD_CTLR_nASSGIreq;
		return 0;
	}

	vgic_mmio_write_v3_misc(vcpu, addr, len, val);
	return 0;
}

static unsigned long vgic_mmio_read_irouter(struct kvm_vcpu *vcpu,
					    gpa_t addr, unsigned int len)
{
	int intid = VGIC_ADDR_TO_INTID(addr, 64);
	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, NULL, intid);
	unsigned long ret = 0;

	if (!irq)
		return 0;

	/* The upper word is RAZ for us. */
	if (!(addr & 4))
		ret = extract_bytes(READ_ONCE(irq->mpidr), addr & 7, len);

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

static void vgic_mmio_write_irouter(struct kvm_vcpu *vcpu,
				    gpa_t addr, unsigned int len,
				    unsigned long val)
{
	int intid = VGIC_ADDR_TO_INTID(addr, 64);
	struct vgic_irq *irq;
	unsigned long flags;

	/* The upper word is WI for us since we don't implement Aff3. */
	if (addr & 4)
		return;

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

	if (!irq)
		return;

	raw_spin_lock_irqsave(&irq->irq_lock, flags);

	/* We only care about and preserve Aff0, Aff1 and Aff2. */
	irq->mpidr = val & GENMASK(23, 0);
	irq->target_vcpu = kvm_mpidr_to_vcpu(vcpu->kvm, irq->mpidr);

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

static unsigned long vgic_mmio_read_v3r_ctlr(struct kvm_vcpu *vcpu,
					     gpa_t addr, unsigned int len)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

	return vgic_cpu->lpis_enabled ? GICR_CTLR_ENABLE_LPIS : 0;
}


static void vgic_mmio_write_v3r_ctlr(struct kvm_vcpu *vcpu,
				     gpa_t addr, unsigned int len,
				     unsigned long val)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	bool was_enabled = vgic_cpu->lpis_enabled;

	if (!vgic_has_its(vcpu->kvm))
		return;

	vgic_cpu->lpis_enabled = val & GICR_CTLR_ENABLE_LPIS;

	if (was_enabled && !vgic_cpu->lpis_enabled) {
		vgic_flush_pending_lpis(vcpu);
		vgic_its_invalidate_cache(vcpu->kvm);
	}

	if (!was_enabled && vgic_cpu->lpis_enabled)
		vgic_enable_lpis(vcpu);
}

static unsigned long vgic_mmio_read_v3r_typer(struct kvm_vcpu *vcpu,
					      gpa_t addr, unsigned int len)
{
	unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_redist_region *rdreg = vgic_cpu->rdreg;
	int target_vcpu_id = vcpu->vcpu_id;
	gpa_t last_rdist_typer = rdreg->base + GICR_TYPER +
			(rdreg->free_index - 1) * KVM_VGIC_V3_REDIST_SIZE;
	u64 value;

	value = (u64)(mpidr & GENMASK(23, 0)) << 32;
	value |= ((target_vcpu_id & 0xffff) << 8);

	if (addr == last_rdist_typer)
		value |= GICR_TYPER_LAST;
	if (vgic_has_its(vcpu->kvm))
		value |= GICR_TYPER_PLPIS;

	return extract_bytes(value, addr & 7, len);
}

static unsigned long vgic_uaccess_read_v3r_typer(struct kvm_vcpu *vcpu,
						 gpa_t addr, unsigned int len)
{
	unsigned long mpidr = kvm_vcpu_get_mpidr_aff(vcpu);
	int target_vcpu_id = vcpu->vcpu_id;
	u64 value;

	value = (u64)(mpidr & GENMASK(23, 0)) << 32;
	value |= ((target_vcpu_id & 0xffff) << 8);

	if (vgic_has_its(vcpu->kvm))
		value |= GICR_TYPER_PLPIS;

	/* reporting of the Last bit is not supported for userspace */
	return extract_bytes(value, addr & 7, len);
}

static unsigned long vgic_mmio_read_v3r_iidr(struct kvm_vcpu *vcpu,
					     gpa_t addr, unsigned int len)
{
	return (PRODUCT_ID_KVM << 24) | (IMPLEMENTER_ARM << 0);
}

static unsigned long vgic_mmio_read_v3_idregs(struct kvm_vcpu *vcpu,
					      gpa_t addr, unsigned int len)
{
	switch (addr & 0xffff) {
	case GICD_PIDR2:
		/* report a GICv3 compliant implementation */
		return 0x3b;
	}

	return 0;
}

static unsigned long vgic_v3_uaccess_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;

	/*
	 * pending state of interrupt is latched in pending_latch variable.
	 * Userspace will save and restore pending state and line_level
	 * separately.
	 * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst
	 * for handling of ISPENDR and ICPENDR.
	 */
	for (i = 0; i < len * 8; i++) {
		struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i);
		bool state = irq->pending_latch;

		if (irq->hw && vgic_irq_is_sgi(irq->intid)) {
			int err;

			err = irq_get_irqchip_state(irq->host_irq,
						    IRQCHIP_STATE_PENDING,
						    &state);
			WARN_ON(err);
		}

		if (state)
			value |= (1U << i);

		vgic_put_irq(vcpu->kvm, irq);
	}

	return value;
}

static int vgic_v3_uaccess_write_pending(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);
		if (test_bit(i, &val)) {
			/*
			 * pending_latch is set irrespective of irq type
			 * (level or edge) to avoid dependency that VM should
			 * restore irq config before pending info.
			 */
			irq->pending_latch = true;
			vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
		} else {
			irq->pending_latch = false;
			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
		}

		vgic_put_irq(vcpu->kvm, irq);
	}

	return 0;
}

/* We want to avoid outer shareable. */
u64 vgic_sanitise_shareability(u64 field)
{
	switch (field) {
	case GIC_BASER_OuterShareable:
		return GIC_BASER_InnerShareable;
	default:
		return field;
	}
}

/* Avoid any inner non-cacheable mapping. */
u64 vgic_sanitise_inner_cacheability(u64 field)
{
	switch (field) {
	case GIC_BASER_CACHE_nCnB:
	case GIC_BASER_CACHE_nC:
		return GIC_BASER_CACHE_RaWb;
	default:
		return field;
	}
}

/* Non-cacheable or same-as-inner are OK. */
u64 vgic_sanitise_outer_cacheability(u64 field)
{
	switch (field) {
	case GIC_BASER_CACHE_SameAsInner:
	case GIC_BASER_CACHE_nC:
		return field;
	default:
		return GIC_BASER_CACHE_SameAsInner;
	}
}

u64 vgic_sanitise_field(u64 reg, u64 field_mask, int field_shift,
			u64 (*sanitise_fn)(u64))
{
	u64 field = (reg & field_mask) >> field_shift;

	field = sanitise_fn(field) << field_shift;
	return (reg & ~field_mask) | field;
}

#define PROPBASER_RES0_MASK						\
	(GENMASK_ULL(63, 59) | GENMASK_ULL(55, 52) | GENMASK_ULL(6, 5))
#define PENDBASER_RES0_MASK						\
	(BIT_ULL(63) | GENMASK_ULL(61, 59) | GENMASK_ULL(55, 52) |	\
	 GENMASK_ULL(15, 12) | GENMASK_ULL(6, 0))

static u64 vgic_sanitise_pendbaser(u64 reg)
{
	reg = vgic_sanitise_field(reg, GICR_PENDBASER_SHAREABILITY_MASK,
				  GICR_PENDBASER_SHAREABILITY_SHIFT,
				  vgic_sanitise_shareability);
	reg = vgic_sanitise_field(reg, GICR_PENDBASER_INNER_CACHEABILITY_MASK,
				  GICR_PENDBASER_INNER_CACHEABILITY_SHIFT,
				  vgic_sanitise_inner_cacheability);
	reg = vgic_sanitise_field(reg, GICR_PENDBASER_OUTER_CACHEABILITY_MASK,
				  GICR_PENDBASER_OUTER_CACHEABILITY_SHIFT,
				  vgic_sanitise_outer_cacheability);

	reg &= ~PENDBASER_RES0_MASK;

	return reg;
}

static u64 vgic_sanitise_propbaser(u64 reg)
{
	reg = vgic_sanitise_field(reg, GICR_PROPBASER_SHAREABILITY_MASK,
				  GICR_PROPBASER_SHAREABILITY_SHIFT,
				  vgic_sanitise_shareability);
	reg = vgic_sanitise_field(reg, GICR_PROPBASER_INNER_CACHEABILITY_MASK,
				  GICR_PROPBASER_INNER_CACHEABILITY_SHIFT,
				  vgic_sanitise_inner_cacheability);
	reg = vgic_sanitise_field(reg, GICR_PROPBASER_OUTER_CACHEABILITY_MASK,
				  GICR_PROPBASER_OUTER_CACHEABILITY_SHIFT,
				  vgic_sanitise_outer_cacheability);

	reg &= ~PROPBASER_RES0_MASK;
	return reg;
}

static unsigned long vgic_mmio_read_propbase(struct kvm_vcpu *vcpu,
					     gpa_t addr, unsigned int len)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;

	return extract_bytes(dist->propbaser, addr & 7, len);
}

static void vgic_mmio_write_propbase(struct kvm_vcpu *vcpu,
				     gpa_t addr, unsigned int len,
				     unsigned long val)
{
	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	u64 old_propbaser, propbaser;

	/* Storing a value with LPIs already enabled is undefined */
	if (vgic_cpu->lpis_enabled)
		return;

	do {
		old_propbaser = READ_ONCE(dist->propbaser);
		propbaser = old_propbaser;
		propbaser = update_64bit_reg(propbaser, addr & 4, len, val);
		propbaser = vgic_sanitise_propbaser(propbaser);
	} while (cmpxchg64(&dist->propbaser, old_propbaser,
			   propbaser) != old_propbaser);
}

static unsigned long vgic_mmio_read_pendbase(struct kvm_vcpu *vcpu,
					     gpa_t addr, unsigned int len)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	u64 value = vgic_cpu->pendbaser;

	value &= ~GICR_PENDBASER_PTZ;

	return extract_bytes(value, addr & 7, len);
}

static void vgic_mmio_write_pendbase(struct kvm_vcpu *vcpu,
				     gpa_t addr, unsigned int len,
				     unsigned long val)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	u64 old_pendbaser, pendbaser;

	/* Storing a value with LPIs already enabled is undefined */
	if (vgic_cpu->lpis_enabled)
		return;

	do {
		old_pendbaser = READ_ONCE(vgic_cpu->pendbaser);
		pendbaser = old_pendbaser;
		pendbaser = update_64bit_reg(pendbaser, addr & 4, len, val);
		pendbaser = vgic_sanitise_pendbaser(pendbaser);
	} while (cmpxchg64(&vgic_cpu->pendbaser, old_pendbaser,
			   pendbaser) != old_pendbaser);
}

/*
 * The GICv3 per-IRQ registers are split to control PPIs and SGIs in the
 * redistributors, while SPIs are covered by registers in the distributor
 * block. Trying to set private IRQs in this block gets ignored.
 * We take some special care here to fix the calculation of the register
 * offset.
 */
#define REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(off, rd, wr, ur, uw, bpi, acc) \
	{								\
		.reg_offset = off,					\
		.bits_per_irq = bpi,					\
		.len = (bpi * VGIC_NR_PRIVATE_IRQS) / 8,		\
		.access_flags = acc,					\
		.read = vgic_mmio_read_raz,				\
		.write = vgic_mmio_write_wi,				\
	}, {								\
		.reg_offset = off + (bpi * VGIC_NR_PRIVATE_IRQS) / 8,	\
		.bits_per_irq = bpi,					\
		.len = (bpi * (1024 - VGIC_NR_PRIVATE_IRQS)) / 8,	\
		.access_flags = acc,					\
		.read = rd,						\
		.write = wr,						\
		.uaccess_read = ur,					\
		.uaccess_write = uw,					\
	}

static const struct vgic_register_region vgic_v3_dist_registers[] = {
	REGISTER_DESC_WITH_LENGTH_UACCESS(GICD_CTLR,
		vgic_mmio_read_v3_misc, vgic_mmio_write_v3_misc,
		NULL, vgic_mmio_uaccess_write_v3_misc,
		16, VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICD_STATUSR,
		vgic_mmio_read_rao, vgic_mmio_write_wi, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGROUPR,
		vgic_mmio_read_group, vgic_mmio_write_group, NULL, NULL, 1,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISENABLER,
		vgic_mmio_read_enable, vgic_mmio_write_senable,
		NULL, vgic_uaccess_write_senable, 1,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICENABLER,
		vgic_mmio_read_enable, vgic_mmio_write_cenable,
	       NULL, vgic_uaccess_write_cenable, 1,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISPENDR,
		vgic_mmio_read_pending, vgic_mmio_write_spending,
		vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 1,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICPENDR,
		vgic_mmio_read_pending, vgic_mmio_write_cpending,
		vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 1,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ISACTIVER,
		vgic_mmio_read_active, vgic_mmio_write_sactive,
		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 1,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICACTIVER,
		vgic_mmio_read_active, vgic_mmio_write_cactive,
		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive,
		1, VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IPRIORITYR,
		vgic_mmio_read_priority, vgic_mmio_write_priority, NULL, NULL,
		8, VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ITARGETSR,
		vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 8,
		VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_ICFGR,
		vgic_mmio_read_config, vgic_mmio_write_config, NULL, NULL, 2,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IGRPMODR,
		vgic_mmio_read_raz, vgic_mmio_write_wi, NULL, NULL, 1,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_BITS_PER_IRQ_SHARED(GICD_IROUTER,
		vgic_mmio_read_irouter, vgic_mmio_write_irouter, NULL, NULL, 64,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICD_IDREGS,
		vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48,
		VGIC_ACCESS_32bit),
};

static const struct vgic_register_region vgic_v3_rd_registers[] = {
	/* RD_base registers */
	REGISTER_DESC_WITH_LENGTH(GICR_CTLR,
		vgic_mmio_read_v3r_ctlr, vgic_mmio_write_v3r_ctlr, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICR_STATUSR,
		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICR_IIDR,
		vgic_mmio_read_v3r_iidr, vgic_mmio_write_wi, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH_UACCESS(GICR_TYPER,
		vgic_mmio_read_v3r_typer, vgic_mmio_write_wi,
		vgic_uaccess_read_v3r_typer, vgic_mmio_uaccess_write_wi, 8,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICR_WAKER,
		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICR_PROPBASER,
		vgic_mmio_read_propbase, vgic_mmio_write_propbase, 8,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICR_PENDBASER,
		vgic_mmio_read_pendbase, vgic_mmio_write_pendbase, 8,
		VGIC_ACCESS_64bit | VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(GICR_IDREGS,
		vgic_mmio_read_v3_idregs, vgic_mmio_write_wi, 48,
		VGIC_ACCESS_32bit),
	/* SGI_base registers */
	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGROUPR0,
		vgic_mmio_read_group, vgic_mmio_write_group, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISENABLER0,
		vgic_mmio_read_enable, vgic_mmio_write_senable,
		NULL, vgic_uaccess_write_senable, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICENABLER0,
		vgic_mmio_read_enable, vgic_mmio_write_cenable,
		NULL, vgic_uaccess_write_cenable, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISPENDR0,
		vgic_mmio_read_pending, vgic_mmio_write_spending,
		vgic_v3_uaccess_read_pending, vgic_v3_uaccess_write_pending, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICPENDR0,
		vgic_mmio_read_pending, vgic_mmio_write_cpending,
		vgic_mmio_read_raz, vgic_mmio_uaccess_write_wi, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ISACTIVER0,
		vgic_mmio_read_active, vgic_mmio_write_sactive,
		vgic_uaccess_read_active, vgic_mmio_uaccess_write_sactive, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH_UACCESS(SZ_64K + GICR_ICACTIVER0,
		vgic_mmio_read_active, vgic_mmio_write_cactive,
		vgic_uaccess_read_active, vgic_mmio_uaccess_write_cactive, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IPRIORITYR0,
		vgic_mmio_read_priority, vgic_mmio_write_priority, 32,
		VGIC_ACCESS_32bit | VGIC_ACCESS_8bit),
	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_ICFGR0,
		vgic_mmio_read_config, vgic_mmio_write_config, 8,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_IGRPMODR0,
		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
		VGIC_ACCESS_32bit),
	REGISTER_DESC_WITH_LENGTH(SZ_64K + GICR_NSACR,
		vgic_mmio_read_raz, vgic_mmio_write_wi, 4,
		VGIC_ACCESS_32bit),
};

unsigned int vgic_v3_init_dist_iodev(struct vgic_io_device *dev)
{
	dev->regions = vgic_v3_dist_registers;
	dev->nr_regions = ARRAY_SIZE(vgic_v3_dist_registers);

	kvm_iodevice_init(&dev->dev, &kvm_io_gic_ops);

	return SZ_64K;
}

/**
 * vgic_register_redist_iodev - register a single redist iodev
 * @vcpu:    The VCPU to which the redistributor belongs
 *
 * Register a KVM iodev for this VCPU's redistributor using the address
 * provided.
 *
 * Return 0 on success, -ERRNO otherwise.
 */
int vgic_register_redist_iodev(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;
	struct vgic_dist *vgic = &kvm->arch.vgic;
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;
	struct vgic_redist_region *rdreg;
	gpa_t rd_base;
	int ret;

	if (!IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr))
		return 0;

	/*
	 * We may be creating VCPUs before having set the base address for the
	 * redistributor region, in which case we will come back to this
	 * function for all VCPUs when the base address is set.  Just return
	 * without doing any work for now.
	 */
	rdreg = vgic_v3_rdist_free_slot(&vgic->rd_regions);
	if (!rdreg)
		return 0;

	if (!vgic_v3_check_base(kvm))
		return -EINVAL;

	vgic_cpu->rdreg = rdreg;

	rd_base = rdreg->base + rdreg->free_index * KVM_VGIC_V3_REDIST_SIZE;

	kvm_iodevice_init(&rd_dev->dev, &kvm_io_gic_ops);
	rd_dev->base_addr = rd_base;
	rd_dev->iodev_type = IODEV_REDIST;
	rd_dev->regions = vgic_v3_rd_registers;
	rd_dev->nr_regions = ARRAY_SIZE(vgic_v3_rd_registers);
	rd_dev->redist_vcpu = vcpu;

	mutex_lock(&kvm->slots_lock);
	ret = kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, rd_base,
				      2 * SZ_64K, &rd_dev->dev);
	mutex_unlock(&kvm->slots_lock);

	if (ret)
		return ret;

	rdreg->free_index++;
	return 0;
}

static void vgic_unregister_redist_iodev(struct kvm_vcpu *vcpu)
{
	struct vgic_io_device *rd_dev = &vcpu->arch.vgic_cpu.rd_iodev;

	kvm_io_bus_unregister_dev(vcpu->kvm, KVM_MMIO_BUS, &rd_dev->dev);
}

static int vgic_register_all_redist_iodevs(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu;
	int c, ret = 0;

	kvm_for_each_vcpu(c, vcpu, kvm) {
		ret = vgic_register_redist_iodev(vcpu);
		if (ret)
			break;
	}

	if (ret) {
		/* The current c failed, so we start with the previous one. */
		mutex_lock(&kvm->slots_lock);
		for (c--; c >= 0; c--) {
			vcpu = kvm_get_vcpu(kvm, c);
			vgic_unregister_redist_iodev(vcpu);
		}
		mutex_unlock(&kvm->slots_lock);
	}

	return ret;
}

/**
 * vgic_v3_insert_redist_region - Insert a new redistributor region
 *
 * Performs various checks before inserting the rdist region in the list.
 * Those tests depend on whether the size of the rdist region is known
 * (ie. count != 0). The list is sorted by rdist region index.
 *
 * @kvm: kvm handle
 * @index: redist region index
 * @base: base of the new rdist region
 * @count: number of redistributors the region is made of (0 in the old style
 * single region, whose size is induced from the number of vcpus)
 *
 * Return 0 on success, < 0 otherwise
 */
static int vgic_v3_insert_redist_region(struct kvm *kvm, uint32_t index,
					gpa_t base, uint32_t count)
{
	struct vgic_dist *d = &kvm->arch.vgic;
	struct vgic_redist_region *rdreg;
	struct list_head *rd_regions = &d->rd_regions;
	size_t size = count * KVM_VGIC_V3_REDIST_SIZE;
	int ret;

	/* single rdist region already set ?*/
	if (!count && !list_empty(rd_regions))
		return -EINVAL;

	/* cross the end of memory ? */
	if (base + size < base)
		return -EINVAL;

	if (list_empty(rd_regions)) {
		if (index != 0)
			return -EINVAL;
	} else {
		rdreg = list_last_entry(rd_regions,
					struct vgic_redist_region, list);
		if (index != rdreg->index + 1)
			return -EINVAL;

		/* Cannot add an explicitly sized regions after legacy region */
		if (!rdreg->count)
			return -EINVAL;
	}

	/*
	 * For legacy single-region redistributor regions (!count),
	 * check that the redistributor region does not overlap with the
	 * distributor's address space.
	 */
	if (!count && !IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) &&
		vgic_dist_overlap(kvm, base, size))
		return -EINVAL;

	/* collision with any other rdist region? */
	if (vgic_v3_rdist_overlap(kvm, base, size))
		return -EINVAL;

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

	rdreg->base = VGIC_ADDR_UNDEF;

	ret = vgic_check_ioaddr(kvm, &rdreg->base, base, SZ_64K);
	if (ret)
		goto free;

	rdreg->base = base;
	rdreg->count = count;
	rdreg->free_index = 0;
	rdreg->index = index;

	list_add_tail(&rdreg->list, rd_regions);
	return 0;
free:
	kfree(rdreg);
	return ret;
}

int vgic_v3_set_redist_base(struct kvm *kvm, u32 index, u64 addr, u32 count)
{
	int ret;

	ret = vgic_v3_insert_redist_region(kvm, index, addr, count);
	if (ret)
		return ret;

	/*
	 * Register iodevs for each existing VCPU.  Adding more VCPUs
	 * afterwards will register the iodevs when needed.
	 */
	ret = vgic_register_all_redist_iodevs(kvm);
	if (ret)
		return ret;

	return 0;
}

int vgic_v3_has_attr_regs(struct kvm_device *dev, struct kvm_device_attr *attr)
{
	const struct vgic_register_region *region;
	struct vgic_io_device iodev;
	struct vgic_reg_attr reg_attr;
	struct kvm_vcpu *vcpu;
	gpa_t addr;
	int ret;

	ret = vgic_v3_parse_attr(dev, attr, &reg_attr);
	if (ret)
		return ret;

	vcpu = reg_attr.vcpu;
	addr = reg_attr.addr;

	switch (attr->group) {
	case KVM_DEV_ARM_VGIC_GRP_DIST_REGS:
		iodev.regions = vgic_v3_dist_registers;
		iodev.nr_regions = ARRAY_SIZE(vgic_v3_dist_registers);
		iodev.base_addr = 0;
		break;
	case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS:{
		iodev.regions = vgic_v3_rd_registers;
		iodev.nr_regions = ARRAY_SIZE(vgic_v3_rd_registers);
		iodev.base_addr = 0;
		break;
	}
	case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: {
		u64 reg, id;

		id = (attr->attr & KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK);
		return vgic_v3_has_cpu_sysregs_attr(vcpu, 0, id, &reg);
	}
	default:
		return -ENXIO;
	}

	/* We only support aligned 32-bit accesses. */
	if (addr & 3)
		return -ENXIO;

	region = vgic_get_mmio_region(vcpu, &iodev, addr, sizeof(u32));
	if (!region)
		return -ENXIO;

	return 0;
}
/*
 * Compare a given affinity (level 1-3 and a level 0 mask, from the SGI
 * generation register ICC_SGI1R_EL1) with a given VCPU.
 * If the VCPU's MPIDR matches, return the level0 affinity, otherwise
 * return -1.
 */
static int match_mpidr(u64 sgi_aff, u16 sgi_cpu_mask, struct kvm_vcpu *vcpu)
{
	unsigned long affinity;
	int level0;

	/*
	 * Split the current VCPU's MPIDR into affinity level 0 and the
	 * rest as this is what we have to compare against.
	 */
	affinity = kvm_vcpu_get_mpidr_aff(vcpu);
	level0 = MPIDR_AFFINITY_LEVEL(affinity, 0);
	affinity &= ~MPIDR_LEVEL_MASK;

	/* bail out if the upper three levels don't match */
	if (sgi_aff != affinity)
		return -1;

	/* Is this VCPU's bit set in the mask ? */
	if (!(sgi_cpu_mask & BIT(level0)))
		return -1;

	return level0;
}

/*
 * The ICC_SGI* registers encode the affinity differently from the MPIDR,
 * so provide a wrapper to use the existing defines to isolate a certain
 * affinity level.
 */
#define SGI_AFFINITY_LEVEL(reg, level) \
	((((reg) & ICC_SGI1R_AFFINITY_## level ##_MASK) \
	>> ICC_SGI1R_AFFINITY_## level ##_SHIFT) << MPIDR_LEVEL_SHIFT(level))

/**
 * vgic_v3_dispatch_sgi - handle SGI requests from VCPUs
 * @vcpu: The VCPU requesting a SGI
 * @reg: The value written into ICC_{ASGI1,SGI0,SGI1}R by that VCPU
 * @allow_group1: Does the sysreg access allow generation of G1 SGIs
 *
 * With GICv3 (and ARE=1) CPUs trigger SGIs by writing to a system register.
 * This will trap in sys_regs.c and call this function.
 * This ICC_SGI1R_EL1 register contains the upper three affinity levels of the
 * target processors as well as a bitmask of 16 Aff0 CPUs.
 * If the interrupt routing mode bit is not set, we iterate over all VCPUs to
 * check for matching ones. If this bit is set, we signal all, but not the
 * calling VCPU.
 */
void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1)
{
	struct kvm *kvm = vcpu->kvm;
	struct kvm_vcpu *c_vcpu;
	u16 target_cpus;
	u64 mpidr;
	int sgi, c;
	int vcpu_id = vcpu->vcpu_id;
	bool broadcast;
	unsigned long flags;

	sgi = (reg & ICC_SGI1R_SGI_ID_MASK) >> ICC_SGI1R_SGI_ID_SHIFT;
	broadcast = reg & BIT_ULL(ICC_SGI1R_IRQ_ROUTING_MODE_BIT);
	target_cpus = (reg & ICC_SGI1R_TARGET_LIST_MASK) >> ICC_SGI1R_TARGET_LIST_SHIFT;
	mpidr = SGI_AFFINITY_LEVEL(reg, 3);
	mpidr |= SGI_AFFINITY_LEVEL(reg, 2);
	mpidr |= SGI_AFFINITY_LEVEL(reg, 1);

	/*
	 * We iterate over all VCPUs to find the MPIDRs matching the request.
	 * If we have handled one CPU, we clear its bit to detect early
	 * if we are already finished. This avoids iterating through all
	 * VCPUs when most of the times we just signal a single VCPU.
	 */
	kvm_for_each_vcpu(c, c_vcpu, kvm) {
		struct vgic_irq *irq;

		/* Exit early if we have dealt with all requested CPUs */
		if (!broadcast && target_cpus == 0)
			break;

		/* Don't signal the calling VCPU */
		if (broadcast && c == vcpu_id)
			continue;

		if (!broadcast) {
			int level0;

			level0 = match_mpidr(mpidr, target_cpus, c_vcpu);
			if (level0 == -1)
				continue;

			/* remove this matching VCPU from the mask */
			target_cpus &= ~BIT(level0);
		}

		irq = vgic_get_irq(vcpu->kvm, c_vcpu, sgi);

		raw_spin_lock_irqsave(&irq->irq_lock, flags);

		/*
		 * An access targeting Group0 SGIs can only generate
		 * those, while an access targeting Group1 SGIs can
		 * generate interrupts of either group.
		 */
		if (!irq->group || allow_group1) {
			if (!irq->hw) {
				irq->pending_latch = true;
				vgic_queue_irq_unlock(vcpu->kvm, irq, flags);
			} else {
				/* 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);
			}
		} else {
			raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
		}

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

int vgic_v3_dist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
			 int offset, u32 *val)
{
	struct vgic_io_device dev = {
		.regions = vgic_v3_dist_registers,
		.nr_regions = ARRAY_SIZE(vgic_v3_dist_registers),
	};

	return vgic_uaccess(vcpu, &dev, is_write, offset, val);
}

int vgic_v3_redist_uaccess(struct kvm_vcpu *vcpu, bool is_write,
			   int offset, u32 *val)
{
	struct vgic_io_device rd_dev = {
		.regions = vgic_v3_rd_registers,
		.nr_regions = ARRAY_SIZE(vgic_v3_rd_registers),
	};

	return vgic_uaccess(vcpu, &rd_dev, is_write, offset, val);
}

int vgic_v3_line_level_info_uaccess(struct kvm_vcpu *vcpu, bool is_write,
				    u32 intid, u64 *val)
{
	if (intid % 32)
		return -EINVAL;

	if (is_write)
		vgic_write_irq_line_level_info(vcpu, intid, *val);
	else
		*val = vgic_read_irq_line_level_info(vcpu, intid);

	return 0;
}