summaryrefslogtreecommitdiffstats
path: root/arch/riscv/kvm/vcpu.c
blob: d0f08d5b4282952c82a462cb8f4ba9bc27a5f9eb (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2019 Western Digital Corporation or its affiliates.
 *
 * Authors:
 *     Anup Patel <anup.patel@wdc.com>
 */

#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kdebug.h>
#include <linux/module.h>
#include <linux/percpu.h>
#include <linux/uaccess.h>
#include <linux/vmalloc.h>
#include <linux/sched/signal.h>
#include <linux/fs.h>
#include <linux/kvm_host.h>
#include <asm/csr.h>
#include <asm/hwcap.h>

const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
	KVM_GENERIC_VCPU_STATS(),
	STATS_DESC_COUNTER(VCPU, ecall_exit_stat),
	STATS_DESC_COUNTER(VCPU, wfi_exit_stat),
	STATS_DESC_COUNTER(VCPU, mmio_exit_user),
	STATS_DESC_COUNTER(VCPU, mmio_exit_kernel),
	STATS_DESC_COUNTER(VCPU, csr_exit_user),
	STATS_DESC_COUNTER(VCPU, csr_exit_kernel),
	STATS_DESC_COUNTER(VCPU, exits)
};

const struct kvm_stats_header kvm_vcpu_stats_header = {
	.name_size = KVM_STATS_NAME_SIZE,
	.num_desc = ARRAY_SIZE(kvm_vcpu_stats_desc),
	.id_offset = sizeof(struct kvm_stats_header),
	.desc_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE,
	.data_offset = sizeof(struct kvm_stats_header) + KVM_STATS_NAME_SIZE +
		       sizeof(kvm_vcpu_stats_desc),
};

#define KVM_RISCV_BASE_ISA_MASK		GENMASK(25, 0)

/* Mapping between KVM ISA Extension ID & Host ISA extension ID */
static const unsigned long kvm_isa_ext_arr[] = {
	RISCV_ISA_EXT_a,
	RISCV_ISA_EXT_c,
	RISCV_ISA_EXT_d,
	RISCV_ISA_EXT_f,
	RISCV_ISA_EXT_h,
	RISCV_ISA_EXT_i,
	RISCV_ISA_EXT_m,
	RISCV_ISA_EXT_SVPBMT,
	RISCV_ISA_EXT_SSTC,
};

static unsigned long kvm_riscv_vcpu_base2isa_ext(unsigned long base_ext)
{
	unsigned long i;

	for (i = 0; i < KVM_RISCV_ISA_EXT_MAX; i++) {
		if (kvm_isa_ext_arr[i] == base_ext)
			return i;
	}

	return KVM_RISCV_ISA_EXT_MAX;
}

static bool kvm_riscv_vcpu_isa_enable_allowed(unsigned long ext)
{
	switch (ext) {
	case KVM_RISCV_ISA_EXT_H:
		return false;
	default:
		break;
	}

	return true;
}

static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
{
	switch (ext) {
	case KVM_RISCV_ISA_EXT_A:
	case KVM_RISCV_ISA_EXT_C:
	case KVM_RISCV_ISA_EXT_I:
	case KVM_RISCV_ISA_EXT_M:
	case KVM_RISCV_ISA_EXT_SSTC:
		return false;
	default:
		break;
	}

	return true;
}

static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
	struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context;
	bool loaded;

	/**
	 * The preemption should be disabled here because it races with
	 * kvm_sched_out/kvm_sched_in(called from preempt notifiers) which
	 * also calls vcpu_load/put.
	 */
	get_cpu();
	loaded = (vcpu->cpu != -1);
	if (loaded)
		kvm_arch_vcpu_put(vcpu);

	vcpu->arch.last_exit_cpu = -1;

	memcpy(csr, reset_csr, sizeof(*csr));

	memcpy(cntx, reset_cntx, sizeof(*cntx));

	kvm_riscv_vcpu_fp_reset(vcpu);

	kvm_riscv_vcpu_timer_reset(vcpu);

	WRITE_ONCE(vcpu->arch.irqs_pending, 0);
	WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);

	vcpu->arch.hfence_head = 0;
	vcpu->arch.hfence_tail = 0;
	memset(vcpu->arch.hfence_queue, 0, sizeof(vcpu->arch.hfence_queue));

	/* Reset the guest CSRs for hotplug usecase */
	if (loaded)
		kvm_arch_vcpu_load(vcpu, smp_processor_id());
	put_cpu();
}

int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
{
	return 0;
}

int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
{
	struct kvm_cpu_context *cntx;
	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
	unsigned long host_isa, i;

	/* Mark this VCPU never ran */
	vcpu->arch.ran_atleast_once = false;
	vcpu->arch.mmu_page_cache.gfp_zero = __GFP_ZERO;
	bitmap_zero(vcpu->arch.isa, RISCV_ISA_EXT_MAX);

	/* Setup ISA features available to VCPU */
	for (i = 0; i < ARRAY_SIZE(kvm_isa_ext_arr); i++) {
		host_isa = kvm_isa_ext_arr[i];
		if (__riscv_isa_extension_available(NULL, host_isa) &&
		    kvm_riscv_vcpu_isa_enable_allowed(i))
			set_bit(host_isa, vcpu->arch.isa);
	}

	/* Setup VCPU hfence queue */
	spin_lock_init(&vcpu->arch.hfence_lock);

	/* Setup reset state of shadow SSTATUS and HSTATUS CSRs */
	cntx = &vcpu->arch.guest_reset_context;
	cntx->sstatus = SR_SPP | SR_SPIE;
	cntx->hstatus = 0;
	cntx->hstatus |= HSTATUS_VTW;
	cntx->hstatus |= HSTATUS_SPVP;
	cntx->hstatus |= HSTATUS_SPV;

	/* By default, make CY, TM, and IR counters accessible in VU mode */
	reset_csr->scounteren = 0x7;

	/* Setup VCPU timer */
	kvm_riscv_vcpu_timer_init(vcpu);

	/* Reset VCPU */
	kvm_riscv_reset_vcpu(vcpu);

	return 0;
}

void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	/**
	 * vcpu with id 0 is the designated boot cpu.
	 * Keep all vcpus with non-zero id in power-off state so that
	 * they can be brought up using SBI HSM extension.
	 */
	if (vcpu->vcpu_idx != 0)
		kvm_riscv_vcpu_power_off(vcpu);
}

void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	/* Cleanup VCPU timer */
	kvm_riscv_vcpu_timer_deinit(vcpu);

	/* Free unused pages pre-allocated for G-stage page table mappings */
	kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_cache);
}

int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
{
	return kvm_riscv_vcpu_timer_pending(vcpu);
}

void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{
}

void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
{
}

int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
	return (kvm_riscv_vcpu_has_interrupts(vcpu, -1UL) &&
		!vcpu->arch.power_off && !vcpu->arch.pause);
}

int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu)
{
	return kvm_vcpu_exiting_guest_mode(vcpu) == IN_GUEST_MODE;
}

bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
	return (vcpu->arch.guest_context.sstatus & SR_SPP) ? true : false;
}

vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
{
	return VM_FAULT_SIGBUS;
}

static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
					 const struct kvm_one_reg *reg)
{
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_CONFIG);
	unsigned long reg_val;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;

	switch (reg_num) {
	case KVM_REG_RISCV_CONFIG_REG(isa):
		reg_val = vcpu->arch.isa[0] & KVM_RISCV_BASE_ISA_MASK;
		break;
	default:
		return -EINVAL;
	}

	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	return 0;
}

static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
					 const struct kvm_one_reg *reg)
{
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_CONFIG);
	unsigned long i, isa_ext, reg_val;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;

	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	/* This ONE REG interface is only defined for single letter extensions */
	if (fls(reg_val) >= RISCV_ISA_EXT_BASE)
		return -EINVAL;

	switch (reg_num) {
	case KVM_REG_RISCV_CONFIG_REG(isa):
		if (!vcpu->arch.ran_atleast_once) {
			/* Ignore the enable/disable request for certain extensions */
			for (i = 0; i < RISCV_ISA_EXT_BASE; i++) {
				isa_ext = kvm_riscv_vcpu_base2isa_ext(i);
				if (isa_ext >= KVM_RISCV_ISA_EXT_MAX) {
					reg_val &= ~BIT(i);
					continue;
				}
				if (!kvm_riscv_vcpu_isa_enable_allowed(isa_ext))
					if (reg_val & BIT(i))
						reg_val &= ~BIT(i);
				if (!kvm_riscv_vcpu_isa_disable_allowed(isa_ext))
					if (!(reg_val & BIT(i)))
						reg_val |= BIT(i);
			}
			reg_val &= riscv_isa_extension_base(NULL);
			/* Do not modify anything beyond single letter extensions */
			reg_val = (vcpu->arch.isa[0] & ~KVM_RISCV_BASE_ISA_MASK) |
				  (reg_val & KVM_RISCV_BASE_ISA_MASK);
			vcpu->arch.isa[0] = reg_val;
			kvm_riscv_vcpu_fp_reset(vcpu);
		} else {
			return -EOPNOTSUPP;
		}
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
				       const struct kvm_one_reg *reg)
{
	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_CORE);
	unsigned long reg_val;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;
	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
		return -EINVAL;

	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
		reg_val = cntx->sepc;
	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
		reg_val = ((unsigned long *)cntx)[reg_num];
	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode))
		reg_val = (cntx->sstatus & SR_SPP) ?
				KVM_RISCV_MODE_S : KVM_RISCV_MODE_U;
	else
		return -EINVAL;

	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	return 0;
}

static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
				       const struct kvm_one_reg *reg)
{
	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_CORE);
	unsigned long reg_val;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;
	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
		return -EINVAL;

	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
		cntx->sepc = reg_val;
	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
		((unsigned long *)cntx)[reg_num] = reg_val;
	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode)) {
		if (reg_val == KVM_RISCV_MODE_S)
			cntx->sstatus |= SR_SPP;
		else
			cntx->sstatus &= ~SR_SPP;
	} else
		return -EINVAL;

	return 0;
}

static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
				      const struct kvm_one_reg *reg)
{
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_CSR);
	unsigned long reg_val;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;
	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
		return -EINVAL;

	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
		kvm_riscv_vcpu_flush_interrupts(vcpu);
		reg_val = (csr->hvip >> VSIP_TO_HVIP_SHIFT) & VSIP_VALID_MASK;
	} else
		reg_val = ((unsigned long *)csr)[reg_num];

	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	return 0;
}

static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
				      const struct kvm_one_reg *reg)
{
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_CSR);
	unsigned long reg_val;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;
	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
		return -EINVAL;

	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
		reg_val &= VSIP_VALID_MASK;
		reg_val <<= VSIP_TO_HVIP_SHIFT;
	}

	((unsigned long *)csr)[reg_num] = reg_val;

	if (reg_num == KVM_REG_RISCV_CSR_REG(sip))
		WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);

	return 0;
}

static int kvm_riscv_vcpu_get_reg_isa_ext(struct kvm_vcpu *vcpu,
					  const struct kvm_one_reg *reg)
{
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_ISA_EXT);
	unsigned long reg_val = 0;
	unsigned long host_isa_ext;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;

	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
		return -EINVAL;

	host_isa_ext = kvm_isa_ext_arr[reg_num];
	if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext))
		reg_val = 1; /* Mark the given extension as available */

	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	return 0;
}

static int kvm_riscv_vcpu_set_reg_isa_ext(struct kvm_vcpu *vcpu,
					  const struct kvm_one_reg *reg)
{
	unsigned long __user *uaddr =
			(unsigned long __user *)(unsigned long)reg->addr;
	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
					    KVM_REG_SIZE_MASK |
					    KVM_REG_RISCV_ISA_EXT);
	unsigned long reg_val;
	unsigned long host_isa_ext;

	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
		return -EINVAL;

	if (reg_num >= KVM_RISCV_ISA_EXT_MAX ||
	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
		return -EINVAL;

	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
		return -EFAULT;

	host_isa_ext = kvm_isa_ext_arr[reg_num];
	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
		return	-EOPNOTSUPP;

	if (!vcpu->arch.ran_atleast_once) {
		/*
		 * All multi-letter extension and a few single letter
		 * extension can be disabled
		 */
		if (reg_val == 1 &&
		    kvm_riscv_vcpu_isa_enable_allowed(reg_num))
			set_bit(host_isa_ext, vcpu->arch.isa);
		else if (!reg_val &&
			 kvm_riscv_vcpu_isa_disable_allowed(reg_num))
			clear_bit(host_isa_ext, vcpu->arch.isa);
		else
			return -EINVAL;
		kvm_riscv_vcpu_fp_reset(vcpu);
	} else {
		return -EOPNOTSUPP;
	}

	return 0;
}

static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
				  const struct kvm_one_reg *reg)
{
	if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CONFIG)
		return kvm_riscv_vcpu_set_reg_config(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CORE)
		return kvm_riscv_vcpu_set_reg_core(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
		return kvm_riscv_vcpu_set_reg_csr(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_TIMER)
		return kvm_riscv_vcpu_set_reg_timer(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_F)
		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
						 KVM_REG_RISCV_FP_F);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D)
		return kvm_riscv_vcpu_set_reg_fp(vcpu, reg,
						 KVM_REG_RISCV_FP_D);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
		return kvm_riscv_vcpu_set_reg_isa_ext(vcpu, reg);

	return -EINVAL;
}

static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
				  const struct kvm_one_reg *reg)
{
	if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CONFIG)
		return kvm_riscv_vcpu_get_reg_config(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CORE)
		return kvm_riscv_vcpu_get_reg_core(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
		return kvm_riscv_vcpu_get_reg_csr(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_TIMER)
		return kvm_riscv_vcpu_get_reg_timer(vcpu, reg);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_F)
		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
						 KVM_REG_RISCV_FP_F);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_FP_D)
		return kvm_riscv_vcpu_get_reg_fp(vcpu, reg,
						 KVM_REG_RISCV_FP_D);
	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_ISA_EXT)
		return kvm_riscv_vcpu_get_reg_isa_ext(vcpu, reg);

	return -EINVAL;
}

long kvm_arch_vcpu_async_ioctl(struct file *filp,
			       unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;

	if (ioctl == KVM_INTERRUPT) {
		struct kvm_interrupt irq;

		if (copy_from_user(&irq, argp, sizeof(irq)))
			return -EFAULT;

		if (irq.irq == KVM_INTERRUPT_SET)
			return kvm_riscv_vcpu_set_interrupt(vcpu, IRQ_VS_EXT);
		else
			return kvm_riscv_vcpu_unset_interrupt(vcpu, IRQ_VS_EXT);
	}

	return -ENOIOCTLCMD;
}

long kvm_arch_vcpu_ioctl(struct file *filp,
			 unsigned int ioctl, unsigned long arg)
{
	struct kvm_vcpu *vcpu = filp->private_data;
	void __user *argp = (void __user *)arg;
	long r = -EINVAL;

	switch (ioctl) {
	case KVM_SET_ONE_REG:
	case KVM_GET_ONE_REG: {
		struct kvm_one_reg reg;

		r = -EFAULT;
		if (copy_from_user(&reg, argp, sizeof(reg)))
			break;

		if (ioctl == KVM_SET_ONE_REG)
			r = kvm_riscv_vcpu_set_reg(vcpu, &reg);
		else
			r = kvm_riscv_vcpu_get_reg(vcpu, &reg);
		break;
	}
	default:
		break;
	}

	return r;
}

int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
				  struct kvm_sregs *sregs)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
				  struct kvm_translation *tr)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	return -EINVAL;
}

int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
{
	return -EINVAL;
}

void kvm_riscv_vcpu_flush_interrupts(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
	unsigned long mask, val;

	if (READ_ONCE(vcpu->arch.irqs_pending_mask)) {
		mask = xchg_acquire(&vcpu->arch.irqs_pending_mask, 0);
		val = READ_ONCE(vcpu->arch.irqs_pending) & mask;

		csr->hvip &= ~mask;
		csr->hvip |= val;
	}
}

void kvm_riscv_vcpu_sync_interrupts(struct kvm_vcpu *vcpu)
{
	unsigned long hvip;
	struct kvm_vcpu_arch *v = &vcpu->arch;
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;

	/* Read current HVIP and VSIE CSRs */
	csr->vsie = csr_read(CSR_VSIE);

	/* Sync-up HVIP.VSSIP bit changes does by Guest */
	hvip = csr_read(CSR_HVIP);
	if ((csr->hvip ^ hvip) & (1UL << IRQ_VS_SOFT)) {
		if (hvip & (1UL << IRQ_VS_SOFT)) {
			if (!test_and_set_bit(IRQ_VS_SOFT,
					      &v->irqs_pending_mask))
				set_bit(IRQ_VS_SOFT, &v->irqs_pending);
		} else {
			if (!test_and_set_bit(IRQ_VS_SOFT,
					      &v->irqs_pending_mask))
				clear_bit(IRQ_VS_SOFT, &v->irqs_pending);
		}
	}
}

int kvm_riscv_vcpu_set_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
{
	if (irq != IRQ_VS_SOFT &&
	    irq != IRQ_VS_TIMER &&
	    irq != IRQ_VS_EXT)
		return -EINVAL;

	set_bit(irq, &vcpu->arch.irqs_pending);
	smp_mb__before_atomic();
	set_bit(irq, &vcpu->arch.irqs_pending_mask);

	kvm_vcpu_kick(vcpu);

	return 0;
}

int kvm_riscv_vcpu_unset_interrupt(struct kvm_vcpu *vcpu, unsigned int irq)
{
	if (irq != IRQ_VS_SOFT &&
	    irq != IRQ_VS_TIMER &&
	    irq != IRQ_VS_EXT)
		return -EINVAL;

	clear_bit(irq, &vcpu->arch.irqs_pending);
	smp_mb__before_atomic();
	set_bit(irq, &vcpu->arch.irqs_pending_mask);

	return 0;
}

bool kvm_riscv_vcpu_has_interrupts(struct kvm_vcpu *vcpu, unsigned long mask)
{
	unsigned long ie = ((vcpu->arch.guest_csr.vsie & VSIP_VALID_MASK)
			    << VSIP_TO_HVIP_SHIFT) & mask;

	return (READ_ONCE(vcpu->arch.irqs_pending) & ie) ? true : false;
}

void kvm_riscv_vcpu_power_off(struct kvm_vcpu *vcpu)
{
	vcpu->arch.power_off = true;
	kvm_make_request(KVM_REQ_SLEEP, vcpu);
	kvm_vcpu_kick(vcpu);
}

void kvm_riscv_vcpu_power_on(struct kvm_vcpu *vcpu)
{
	vcpu->arch.power_off = false;
	kvm_vcpu_wake_up(vcpu);
}

int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	if (vcpu->arch.power_off)
		mp_state->mp_state = KVM_MP_STATE_STOPPED;
	else
		mp_state->mp_state = KVM_MP_STATE_RUNNABLE;

	return 0;
}

int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
				    struct kvm_mp_state *mp_state)
{
	int ret = 0;

	switch (mp_state->mp_state) {
	case KVM_MP_STATE_RUNNABLE:
		vcpu->arch.power_off = false;
		break;
	case KVM_MP_STATE_STOPPED:
		kvm_riscv_vcpu_power_off(vcpu);
		break;
	default:
		ret = -EINVAL;
	}

	return ret;
}

int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
					struct kvm_guest_debug *dbg)
{
	/* TODO; To be implemented later. */
	return -EINVAL;
}

static void kvm_riscv_vcpu_update_config(const unsigned long *isa)
{
	u64 henvcfg = 0;

	if (__riscv_isa_extension_available(isa, RISCV_ISA_EXT_SVPBMT))
		henvcfg |= ENVCFG_PBMTE;

	if (__riscv_isa_extension_available(isa, RISCV_ISA_EXT_SSTC))
		henvcfg |= ENVCFG_STCE;
	csr_write(CSR_HENVCFG, henvcfg);
#ifdef CONFIG_32BIT
	csr_write(CSR_HENVCFGH, henvcfg >> 32);
#endif
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;

	csr_write(CSR_VSSTATUS, csr->vsstatus);
	csr_write(CSR_VSIE, csr->vsie);
	csr_write(CSR_VSTVEC, csr->vstvec);
	csr_write(CSR_VSSCRATCH, csr->vsscratch);
	csr_write(CSR_VSEPC, csr->vsepc);
	csr_write(CSR_VSCAUSE, csr->vscause);
	csr_write(CSR_VSTVAL, csr->vstval);
	csr_write(CSR_HVIP, csr->hvip);
	csr_write(CSR_VSATP, csr->vsatp);

	kvm_riscv_vcpu_update_config(vcpu->arch.isa);

	kvm_riscv_gstage_update_hgatp(vcpu);

	kvm_riscv_vcpu_timer_restore(vcpu);

	kvm_riscv_vcpu_host_fp_save(&vcpu->arch.host_context);
	kvm_riscv_vcpu_guest_fp_restore(&vcpu->arch.guest_context,
					vcpu->arch.isa);

	vcpu->cpu = cpu;
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;

	vcpu->cpu = -1;

	kvm_riscv_vcpu_guest_fp_save(&vcpu->arch.guest_context,
				     vcpu->arch.isa);
	kvm_riscv_vcpu_host_fp_restore(&vcpu->arch.host_context);

	kvm_riscv_vcpu_timer_save(vcpu);

	csr->vsstatus = csr_read(CSR_VSSTATUS);
	csr->vsie = csr_read(CSR_VSIE);
	csr->vstvec = csr_read(CSR_VSTVEC);
	csr->vsscratch = csr_read(CSR_VSSCRATCH);
	csr->vsepc = csr_read(CSR_VSEPC);
	csr->vscause = csr_read(CSR_VSCAUSE);
	csr->vstval = csr_read(CSR_VSTVAL);
	csr->hvip = csr_read(CSR_HVIP);
	csr->vsatp = csr_read(CSR_VSATP);
}

static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
{
	struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu);

	if (kvm_request_pending(vcpu)) {
		if (kvm_check_request(KVM_REQ_SLEEP, vcpu)) {
			kvm_vcpu_srcu_read_unlock(vcpu);
			rcuwait_wait_event(wait,
				(!vcpu->arch.power_off) && (!vcpu->arch.pause),
				TASK_INTERRUPTIBLE);
			kvm_vcpu_srcu_read_lock(vcpu);

			if (vcpu->arch.power_off || vcpu->arch.pause) {
				/*
				 * Awaken to handle a signal, request to
				 * sleep again later.
				 */
				kvm_make_request(KVM_REQ_SLEEP, vcpu);
			}
		}

		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
			kvm_riscv_reset_vcpu(vcpu);

		if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu))
			kvm_riscv_gstage_update_hgatp(vcpu);

		if (kvm_check_request(KVM_REQ_FENCE_I, vcpu))
			kvm_riscv_fence_i_process(vcpu);

		/*
		 * The generic KVM_REQ_TLB_FLUSH is same as
		 * KVM_REQ_HFENCE_GVMA_VMID_ALL
		 */
		if (kvm_check_request(KVM_REQ_HFENCE_GVMA_VMID_ALL, vcpu))
			kvm_riscv_hfence_gvma_vmid_all_process(vcpu);

		if (kvm_check_request(KVM_REQ_HFENCE_VVMA_ALL, vcpu))
			kvm_riscv_hfence_vvma_all_process(vcpu);

		if (kvm_check_request(KVM_REQ_HFENCE, vcpu))
			kvm_riscv_hfence_process(vcpu);
	}
}

static void kvm_riscv_update_hvip(struct kvm_vcpu *vcpu)
{
	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;

	csr_write(CSR_HVIP, csr->hvip);
}

/*
 * Actually run the vCPU, entering an RCU extended quiescent state (EQS) while
 * the vCPU is running.
 *
 * This must be noinstr as instrumentation may make use of RCU, and this is not
 * safe during the EQS.
 */
static void noinstr kvm_riscv_vcpu_enter_exit(struct kvm_vcpu *vcpu)
{
	guest_state_enter_irqoff();
	__kvm_riscv_switch_to(&vcpu->arch);
	vcpu->arch.last_exit_cpu = vcpu->cpu;
	guest_state_exit_irqoff();
}

int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
	int ret;
	struct kvm_cpu_trap trap;
	struct kvm_run *run = vcpu->run;

	/* Mark this VCPU ran at least once */
	vcpu->arch.ran_atleast_once = true;

	kvm_vcpu_srcu_read_lock(vcpu);

	switch (run->exit_reason) {
	case KVM_EXIT_MMIO:
		/* Process MMIO value returned from user-space */
		ret = kvm_riscv_vcpu_mmio_return(vcpu, vcpu->run);
		break;
	case KVM_EXIT_RISCV_SBI:
		/* Process SBI value returned from user-space */
		ret = kvm_riscv_vcpu_sbi_return(vcpu, vcpu->run);
		break;
	case KVM_EXIT_RISCV_CSR:
		/* Process CSR value returned from user-space */
		ret = kvm_riscv_vcpu_csr_return(vcpu, vcpu->run);
		break;
	default:
		ret = 0;
		break;
	}
	if (ret) {
		kvm_vcpu_srcu_read_unlock(vcpu);
		return ret;
	}

	if (run->immediate_exit) {
		kvm_vcpu_srcu_read_unlock(vcpu);
		return -EINTR;
	}

	vcpu_load(vcpu);

	kvm_sigset_activate(vcpu);

	ret = 1;
	run->exit_reason = KVM_EXIT_UNKNOWN;
	while (ret > 0) {
		/* Check conditions before entering the guest */
		cond_resched();

		kvm_riscv_gstage_vmid_update(vcpu);

		kvm_riscv_check_vcpu_requests(vcpu);

		local_irq_disable();

		/*
		 * Exit if we have a signal pending so that we can deliver
		 * the signal to user space.
		 */
		if (signal_pending(current)) {
			ret = -EINTR;
			run->exit_reason = KVM_EXIT_INTR;
		}

		/*
		 * Ensure we set mode to IN_GUEST_MODE after we disable
		 * interrupts and before the final VCPU requests check.
		 * See the comment in kvm_vcpu_exiting_guest_mode() and
		 * Documentation/virt/kvm/vcpu-requests.rst
		 */
		vcpu->mode = IN_GUEST_MODE;

		kvm_vcpu_srcu_read_unlock(vcpu);
		smp_mb__after_srcu_read_unlock();

		/*
		 * We might have got VCPU interrupts updated asynchronously
		 * so update it in HW.
		 */
		kvm_riscv_vcpu_flush_interrupts(vcpu);

		/* Update HVIP CSR for current CPU */
		kvm_riscv_update_hvip(vcpu);

		if (ret <= 0 ||
		    kvm_riscv_gstage_vmid_ver_changed(&vcpu->kvm->arch.vmid) ||
		    kvm_request_pending(vcpu)) {
			vcpu->mode = OUTSIDE_GUEST_MODE;
			local_irq_enable();
			kvm_vcpu_srcu_read_lock(vcpu);
			continue;
		}

		/*
		 * Cleanup stale TLB enteries
		 *
		 * Note: This should be done after G-stage VMID has been
		 * updated using kvm_riscv_gstage_vmid_ver_changed()
		 */
		kvm_riscv_local_tlb_sanitize(vcpu);

		guest_timing_enter_irqoff();

		kvm_riscv_vcpu_enter_exit(vcpu);

		vcpu->mode = OUTSIDE_GUEST_MODE;
		vcpu->stat.exits++;

		/*
		 * Save SCAUSE, STVAL, HTVAL, and HTINST because we might
		 * get an interrupt between __kvm_riscv_switch_to() and
		 * local_irq_enable() which can potentially change CSRs.
		 */
		trap.sepc = vcpu->arch.guest_context.sepc;
		trap.scause = csr_read(CSR_SCAUSE);
		trap.stval = csr_read(CSR_STVAL);
		trap.htval = csr_read(CSR_HTVAL);
		trap.htinst = csr_read(CSR_HTINST);

		/* Syncup interrupts state with HW */
		kvm_riscv_vcpu_sync_interrupts(vcpu);

		preempt_disable();

		/*
		 * We must ensure that any pending interrupts are taken before
		 * we exit guest timing so that timer ticks are accounted as
		 * guest time. Transiently unmask interrupts so that any
		 * pending interrupts are taken.
		 *
		 * There's no barrier which ensures that pending interrupts are
		 * recognised, so we just hope that the CPU takes any pending
		 * interrupts between the enable and disable.
		 */
		local_irq_enable();
		local_irq_disable();

		guest_timing_exit_irqoff();

		local_irq_enable();

		preempt_enable();

		kvm_vcpu_srcu_read_lock(vcpu);

		ret = kvm_riscv_vcpu_exit(vcpu, run, &trap);
	}

	kvm_sigset_deactivate(vcpu);

	vcpu_put(vcpu);

	kvm_vcpu_srcu_read_unlock(vcpu);

	return ret;
}