aboutsummaryrefslogtreecommitdiff
path: root/arch/arm/kvm/arm.c
blob: 3e0fb66d8e053b5bbd7317d8bbcedf69950833dc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
/*
 * Copyright (C) 2012 - Virtual Open Systems and Columbia University
 * Author: Christoffer Dall <c.dall@virtualopensystems.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License, version 2, as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301, USA.
 */

#include <linux/cpu.h>
#include <linux/cpu_pm.h>
#include <linux/errno.h>
#include <linux/err.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/fs.h>
#include <linux/mman.h>
#include <linux/sched.h>
#include <linux/kvm.h>
#include <trace/events/kvm.h>
#include <kvm/arm_pmu.h>

#define CREATE_TRACE_POINTS
#include "trace.h"

#include <asm/uaccess.h>
#include <asm/ptrace.h>
#include <asm/mman.h>
#include <asm/tlbflush.h>
#include <asm/cacheflush.h>
#include <asm/virt.h>
#include <asm/kvm_arm.h>
#include <asm/kvm_asm.h>
#include <asm/kvm_mmu.h>
#include <asm/kvm_emulate.h>
#include <asm/kvm_coproc.h>
#include <asm/kvm_psci.h>
#include <asm/sections.h>

#ifdef REQUIRES_VIRT
__asm__(".arch_extension	virt");
#endif

static DEFINE_PER_CPU(unsigned long, kvm_arm_hyp_stack_page);
static kvm_cpu_context_t __percpu *kvm_host_cpu_state;
static unsigned long hyp_default_vectors;

/* Per-CPU variable containing the currently running vcpu. */
static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_arm_running_vcpu);

/* The VMID used in the VTTBR */
static atomic64_t kvm_vmid_gen = ATOMIC64_INIT(1);
static u32 kvm_next_vmid;
static unsigned int kvm_vmid_bits __read_mostly;
static DEFINE_SPINLOCK(kvm_vmid_lock);

static bool vgic_present;

static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
{
	BUG_ON(preemptible());
	__this_cpu_write(kvm_arm_running_vcpu, vcpu);
}

/**
 * kvm_arm_get_running_vcpu - get the vcpu running on the current CPU.
 * Must be called from non-preemptible context
 */
struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
{
	BUG_ON(preemptible());
	return __this_cpu_read(kvm_arm_running_vcpu);
}

/**
 * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus.
 */
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
{
	return &kvm_arm_running_vcpu;
}

int kvm_arch_hardware_enable(void)
{
	return 0;
}

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

int kvm_arch_hardware_setup(void)
{
	return 0;
}

void kvm_arch_check_processor_compat(void *rtn)
{
	*(int *)rtn = 0;
}


/**
 * kvm_arch_init_vm - initializes a VM data structure
 * @kvm:	pointer to the KVM struct
 */
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
	int ret = 0;

	if (type)
		return -EINVAL;

	ret = kvm_alloc_stage2_pgd(kvm);
	if (ret)
		goto out_fail_alloc;

	ret = create_hyp_mappings(kvm, kvm + 1);
	if (ret)
		goto out_free_stage2_pgd;

	kvm_vgic_early_init(kvm);
	kvm_timer_init(kvm);

	/* Mark the initial VMID generation invalid */
	kvm->arch.vmid_gen = 0;

	/* The maximum number of VCPUs is limited by the host's GIC model */
	kvm->arch.max_vcpus = vgic_present ?
				kvm_vgic_get_max_vcpus() : KVM_MAX_VCPUS;

	return ret;
out_free_stage2_pgd:
	kvm_free_stage2_pgd(kvm);
out_fail_alloc:
	return ret;
}

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


/**
 * kvm_arch_destroy_vm - destroy the VM data structure
 * @kvm:	pointer to the KVM struct
 */
void kvm_arch_destroy_vm(struct kvm *kvm)
{
	int i;

	kvm_free_stage2_pgd(kvm);

	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
		if (kvm->vcpus[i]) {
			kvm_arch_vcpu_free(kvm->vcpus[i]);
			kvm->vcpus[i] = NULL;
		}
	}

	kvm_vgic_destroy(kvm);
}

int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
	int r;
	switch (ext) {
	case KVM_CAP_IRQCHIP:
		r = vgic_present;
		break;
	case KVM_CAP_IOEVENTFD:
	case KVM_CAP_DEVICE_CTRL:
	case KVM_CAP_USER_MEMORY:
	case KVM_CAP_SYNC_MMU:
	case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
	case KVM_CAP_ONE_REG:
	case KVM_CAP_ARM_PSCI:
	case KVM_CAP_ARM_PSCI_0_2:
	case KVM_CAP_READONLY_MEM:
	case KVM_CAP_MP_STATE:
		r = 1;
		break;
	case KVM_CAP_COALESCED_MMIO:
		r = KVM_COALESCED_MMIO_PAGE_OFFSET;
		break;
	case KVM_CAP_ARM_SET_DEVICE_ADDR:
		r = 1;
		break;
	case KVM_CAP_NR_VCPUS:
		r = num_online_cpus();
		break;
	case KVM_CAP_MAX_VCPUS:
		r = KVM_MAX_VCPUS;
		break;
	default:
		r = kvm_arch_dev_ioctl_check_extension(ext);
		break;
	}
	return r;
}

long kvm_arch_dev_ioctl(struct file *filp,
			unsigned int ioctl, unsigned long arg)
{
	return -EINVAL;
}


struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm, unsigned int id)
{
	int err;
	struct kvm_vcpu *vcpu;

	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm)) {
		err = -EBUSY;
		goto out;
	}

	if (id >= kvm->arch.max_vcpus) {
		err = -EINVAL;
		goto out;
	}

	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
	if (!vcpu) {
		err = -ENOMEM;
		goto out;
	}

	err = kvm_vcpu_init(vcpu, kvm, id);
	if (err)
		goto free_vcpu;

	err = create_hyp_mappings(vcpu, vcpu + 1);
	if (err)
		goto vcpu_uninit;

	return vcpu;
vcpu_uninit:
	kvm_vcpu_uninit(vcpu);
free_vcpu:
	kmem_cache_free(kvm_vcpu_cache, vcpu);
out:
	return ERR_PTR(err);
}

void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
{
	kvm_vgic_vcpu_early_init(vcpu);
}

void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
	kvm_mmu_free_memory_caches(vcpu);
	kvm_timer_vcpu_terminate(vcpu);
	kvm_vgic_vcpu_destroy(vcpu);
	kvm_pmu_vcpu_destroy(vcpu);
	kmem_cache_free(kvm_vcpu_cache, vcpu);
}

void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
	kvm_arch_vcpu_free(vcpu);
}

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

void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu)
{
	kvm_timer_schedule(vcpu);
}

void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu)
{
	kvm_timer_unschedule(vcpu);
}

int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
	/* Force users to call KVM_ARM_VCPU_INIT */
	vcpu->arch.target = -1;
	bitmap_zero(vcpu->arch.features, KVM_VCPU_MAX_FEATURES);

	/* Set up the timer */
	kvm_timer_vcpu_init(vcpu);

	kvm_arm_reset_debug_ptr(vcpu);

	return 0;
}

void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
	vcpu->cpu = cpu;
	vcpu->arch.host_cpu_context = this_cpu_ptr(kvm_host_cpu_state);

	kvm_arm_set_running_vcpu(vcpu);
}

void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
{
	/*
	 * The arch-generic KVM code expects the cpu field of a vcpu to be -1
	 * if the vcpu is no longer assigned to a cpu.  This is used for the
	 * optimized make_all_cpus_request path.
	 */
	vcpu->cpu = -1;

	kvm_arm_set_running_vcpu(NULL);
	kvm_timer_vcpu_put(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)
{
	switch (mp_state->mp_state) {
	case KVM_MP_STATE_RUNNABLE:
		vcpu->arch.power_off = false;
		break;
	case KVM_MP_STATE_STOPPED:
		vcpu->arch.power_off = true;
		break;
	default:
		return -EINVAL;
	}

	return 0;
}

/**
 * kvm_arch_vcpu_runnable - determine if the vcpu can be scheduled
 * @v:		The VCPU pointer
 *
 * If the guest CPU is not waiting for interrupts or an interrupt line is
 * asserted, the CPU is by definition runnable.
 */
int kvm_arch_vcpu_runnable(struct kvm_vcpu *v)
{
	return ((!!v->arch.irq_lines || kvm_vgic_vcpu_pending_irq(v))
		&& !v->arch.power_off && !v->arch.pause);
}

/* Just ensure a guest exit from a particular CPU */
static void exit_vm_noop(void *info)
{
}

void force_vm_exit(const cpumask_t *mask)
{
	smp_call_function_many(mask, exit_vm_noop, NULL, true);
}

/**
 * need_new_vmid_gen - check that the VMID is still valid
 * @kvm: The VM's VMID to checkt
 *
 * return true if there is a new generation of VMIDs being used
 *
 * The hardware supports only 256 values with the value zero reserved for the
 * host, so we check if an assigned value belongs to a previous generation,
 * which which requires us to assign a new value. If we're the first to use a
 * VMID for the new generation, we must flush necessary caches and TLBs on all
 * CPUs.
 */
static bool need_new_vmid_gen(struct kvm *kvm)
{
	return unlikely(kvm->arch.vmid_gen != atomic64_read(&kvm_vmid_gen));
}

/**
 * update_vttbr - Update the VTTBR with a valid VMID before the guest runs
 * @kvm	The guest that we are about to run
 *
 * Called from kvm_arch_vcpu_ioctl_run before entering the guest to ensure the
 * VM has a valid VMID, otherwise assigns a new one and flushes corresponding
 * caches and TLBs.
 */
static void update_vttbr(struct kvm *kvm)
{
	phys_addr_t pgd_phys;
	u64 vmid;

	if (!need_new_vmid_gen(kvm))
		return;

	spin_lock(&kvm_vmid_lock);

	/*
	 * We need to re-check the vmid_gen here to ensure that if another vcpu
	 * already allocated a valid vmid for this vm, then this vcpu should
	 * use the same vmid.
	 */
	if (!need_new_vmid_gen(kvm)) {
		spin_unlock(&kvm_vmid_lock);
		return;
	}

	/* First user of a new VMID generation? */
	if (unlikely(kvm_next_vmid == 0)) {
		atomic64_inc(&kvm_vmid_gen);
		kvm_next_vmid = 1;

		/*
		 * On SMP we know no other CPUs can use this CPU's or each
		 * other's VMID after force_vm_exit returns since the
		 * kvm_vmid_lock blocks them from reentry to the guest.
		 */
		force_vm_exit(cpu_all_mask);
		/*
		 * Now broadcast TLB + ICACHE invalidation over the inner
		 * shareable domain to make sure all data structures are
		 * clean.
		 */
		kvm_call_hyp(__kvm_flush_vm_context);
	}

	kvm->arch.vmid_gen = atomic64_read(&kvm_vmid_gen);
	kvm->arch.vmid = kvm_next_vmid;
	kvm_next_vmid++;
	kvm_next_vmid &= (1 << kvm_vmid_bits) - 1;

	/* update vttbr to be used with the new vmid */
	pgd_phys = virt_to_phys(kvm_get_hwpgd(kvm));
	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK(kvm_vmid_bits);
	kvm->arch.vttbr = pgd_phys | vmid;

	spin_unlock(&kvm_vmid_lock);
}

static int kvm_vcpu_first_run_init(struct kvm_vcpu *vcpu)
{
	struct kvm *kvm = vcpu->kvm;
	int ret;

	if (likely(vcpu->arch.has_run_once))
		return 0;

	vcpu->arch.has_run_once = true;

	/*
	 * Map the VGIC hardware resources before running a vcpu the first
	 * time on this VM.
	 */
	if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) {
		ret = kvm_vgic_map_resources(kvm);
		if (ret)
			return ret;
	}

	/*
	 * Enable the arch timers only if we have an in-kernel VGIC
	 * and it has been properly initialized, since we cannot handle
	 * interrupts from the virtual timer with a userspace gic.
	 */
	if (irqchip_in_kernel(kvm) && vgic_initialized(kvm))
		kvm_timer_enable(kvm);

	return 0;
}

bool kvm_arch_intc_initialized(struct kvm *kvm)
{
	return vgic_initialized(kvm);
}

static void kvm_arm_halt_guest(struct kvm *kvm) __maybe_unused;
static void kvm_arm_resume_guest(struct kvm *kvm) __maybe_unused;

static void kvm_arm_halt_guest(struct kvm *kvm)
{
	int i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm)
		vcpu->arch.pause = true;
	force_vm_exit(cpu_all_mask);
}

static void kvm_arm_resume_guest(struct kvm *kvm)
{
	int i;
	struct kvm_vcpu *vcpu;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);

		vcpu->arch.pause = false;
		swake_up(wq);
	}
}

static void vcpu_sleep(struct kvm_vcpu *vcpu)
{
	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);

	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
				       (!vcpu->arch.pause)));
}

static int kvm_vcpu_initialized(struct kvm_vcpu *vcpu)
{
	return vcpu->arch.target >= 0;
}

/**
 * kvm_arch_vcpu_ioctl_run - the main VCPU run function to execute guest code
 * @vcpu:	The VCPU pointer
 * @run:	The kvm_run structure pointer used for userspace state exchange
 *
 * This function is called through the VCPU_RUN ioctl called from user space. It
 * will execute VM code in a loop until the time slice for the process is used
 * or some emulation is needed from user space in which case the function will
 * return with return value 0 and with the kvm_run structure filled in with the
 * required data for the requested emulation.
 */
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *run)
{
	int ret;
	sigset_t sigsaved;

	if (unlikely(!kvm_vcpu_initialized(vcpu)))
		return -ENOEXEC;

	ret = kvm_vcpu_first_run_init(vcpu);
	if (ret)
		return ret;

	if (run->exit_reason == KVM_EXIT_MMIO) {
		ret = kvm_handle_mmio_return(vcpu, vcpu->run);
		if (ret)
			return ret;
	}

	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);

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

		update_vttbr(vcpu->kvm);

		if (vcpu->arch.power_off || vcpu->arch.pause)
			vcpu_sleep(vcpu);

		/*
		 * Preparing the interrupts to be injected also
		 * involves poking the GIC, which must be done in a
		 * non-preemptible context.
		 */
		preempt_disable();
		kvm_pmu_flush_hwstate(vcpu);
		kvm_timer_flush_hwstate(vcpu);
		kvm_vgic_flush_hwstate(vcpu);

		local_irq_disable();

		/*
		 * Re-check atomic conditions
		 */
		if (signal_pending(current)) {
			ret = -EINTR;
			run->exit_reason = KVM_EXIT_INTR;
		}

		if (ret <= 0 || need_new_vmid_gen(vcpu->kvm) ||
			vcpu->arch.power_off || vcpu->arch.pause) {
			local_irq_enable();
			kvm_pmu_sync_hwstate(vcpu);
			kvm_timer_sync_hwstate(vcpu);
			kvm_vgic_sync_hwstate(vcpu);
			preempt_enable();
			continue;
		}

		kvm_arm_setup_debug(vcpu);

		/**************************************************************
		 * Enter the guest
		 */
		trace_kvm_entry(*vcpu_pc(vcpu));
		__kvm_guest_enter();
		vcpu->mode = IN_GUEST_MODE;

		ret = kvm_call_hyp(__kvm_vcpu_run, vcpu);

		vcpu->mode = OUTSIDE_GUEST_MODE;
		vcpu->stat.exits++;
		/*
		 * Back from guest
		 *************************************************************/

		kvm_arm_clear_debug(vcpu);

		/*
		 * We may have taken a host interrupt in HYP mode (ie
		 * while executing the guest). This interrupt is still
		 * pending, as we haven't serviced it yet!
		 *
		 * We're now back in SVC mode, with interrupts
		 * disabled.  Enabling the interrupts now will have
		 * the effect of taking the interrupt again, in SVC
		 * mode this time.
		 */
		local_irq_enable();

		/*
		 * We do local_irq_enable() before calling kvm_guest_exit() so
		 * that if a timer interrupt hits while running the guest we
		 * account that tick as being spent in the guest.  We enable
		 * preemption after calling kvm_guest_exit() so that if we get
		 * preempted we make sure ticks after that is not counted as
		 * guest time.
		 */
		kvm_guest_exit();
		trace_kvm_exit(ret, kvm_vcpu_trap_get_class(vcpu), *vcpu_pc(vcpu));

		/*
		 * We must sync the PMU and timer state before the vgic state so
		 * that the vgic can properly sample the updated state of the
		 * interrupt line.
		 */
		kvm_pmu_sync_hwstate(vcpu);
		kvm_timer_sync_hwstate(vcpu);

		kvm_vgic_sync_hwstate(vcpu);

		preempt_enable();

		ret = handle_exit(vcpu, run, ret);
	}

	if (vcpu->sigset_active)
		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
	return ret;
}

static int vcpu_interrupt_line(struct kvm_vcpu *vcpu, int number, bool level)
{
	int bit_index;
	bool set;
	unsigned long *ptr;

	if (number == KVM_ARM_IRQ_CPU_IRQ)
		bit_index = __ffs(HCR_VI);
	else /* KVM_ARM_IRQ_CPU_FIQ */
		bit_index = __ffs(HCR_VF);

	ptr = (unsigned long *)&vcpu->arch.irq_lines;
	if (level)
		set = test_and_set_bit(bit_index, ptr);
	else
		set = test_and_clear_bit(bit_index, ptr);

	/*
	 * If we didn't change anything, no need to wake up or kick other CPUs
	 */
	if (set == level)
		return 0;

	/*
	 * The vcpu irq_lines field was updated, wake up sleeping VCPUs and
	 * trigger a world-switch round on the running physical CPU to set the
	 * virtual IRQ/FIQ fields in the HCR appropriately.
	 */
	kvm_vcpu_kick(vcpu);

	return 0;
}

int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_level,
			  bool line_status)
{
	u32 irq = irq_level->irq;
	unsigned int irq_type, vcpu_idx, irq_num;
	int nrcpus = atomic_read(&kvm->online_vcpus);
	struct kvm_vcpu *vcpu = NULL;
	bool level = irq_level->level;

	irq_type = (irq >> KVM_ARM_IRQ_TYPE_SHIFT) & KVM_ARM_IRQ_TYPE_MASK;
	vcpu_idx = (irq >> KVM_ARM_IRQ_VCPU_SHIFT) & KVM_ARM_IRQ_VCPU_MASK;
	irq_num = (irq >> KVM_ARM_IRQ_NUM_SHIFT) & KVM_ARM_IRQ_NUM_MASK;

	trace_kvm_irq_line(irq_type, vcpu_idx, irq_num, irq_level->level);

	switch (irq_type) {
	case KVM_ARM_IRQ_TYPE_CPU:
		if (irqchip_in_kernel(kvm))
			return -ENXIO;

		if (vcpu_idx >= nrcpus)
			return -EINVAL;

		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
		if (!vcpu)
			return -EINVAL;

		if (irq_num > KVM_ARM_IRQ_CPU_FIQ)
			return -EINVAL;

		return vcpu_interrupt_line(vcpu, irq_num, level);
	case KVM_ARM_IRQ_TYPE_PPI:
		if (!irqchip_in_kernel(kvm))
			return -ENXIO;

		if (vcpu_idx >= nrcpus)
			return -EINVAL;

		vcpu = kvm_get_vcpu(kvm, vcpu_idx);
		if (!vcpu)
			return -EINVAL;

		if (irq_num < VGIC_NR_SGIS || irq_num >= VGIC_NR_PRIVATE_IRQS)
			return -EINVAL;

		return kvm_vgic_inject_irq(kvm, vcpu->vcpu_id, irq_num, level);
	case KVM_ARM_IRQ_TYPE_SPI:
		if (!irqchip_in_kernel(kvm))
			return -ENXIO;

		if (irq_num < VGIC_NR_PRIVATE_IRQS)
			return -EINVAL;

		return kvm_vgic_inject_irq(kvm, 0, irq_num, level);
	}

	return -EINVAL;
}

static int kvm_vcpu_set_target(struct kvm_vcpu *vcpu,
			       const struct kvm_vcpu_init *init)
{
	unsigned int i;
	int phys_target = kvm_target_cpu();

	if (init->target != phys_target)
		return -EINVAL;

	/*
	 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
	 * use the same target.
	 */
	if (vcpu->arch.target != -1 && vcpu->arch.target != init->target)
		return -EINVAL;

	/* -ENOENT for unknown features, -EINVAL for invalid combinations. */
	for (i = 0; i < sizeof(init->features) * 8; i++) {
		bool set = (init->features[i / 32] & (1 << (i % 32)));

		if (set && i >= KVM_VCPU_MAX_FEATURES)
			return -ENOENT;

		/*
		 * Secondary and subsequent calls to KVM_ARM_VCPU_INIT must
		 * use the same feature set.
		 */
		if (vcpu->arch.target != -1 && i < KVM_VCPU_MAX_FEATURES &&
		    test_bit(i, vcpu->arch.features) != set)
			return -EINVAL;

		if (set)
			set_bit(i, vcpu->arch.features);
	}

	vcpu->arch.target = phys_target;

	/* Now we know what it is, we can reset it. */
	return kvm_reset_vcpu(vcpu);
}


static int kvm_arch_vcpu_ioctl_vcpu_init(struct kvm_vcpu *vcpu,
					 struct kvm_vcpu_init *init)
{
	int ret;

	ret = kvm_vcpu_set_target(vcpu, init);
	if (ret)
		return ret;

	/*
	 * Ensure a rebooted VM will fault in RAM pages and detect if the
	 * guest MMU is turned off and flush the caches as needed.
	 */
	if (vcpu->arch.has_run_once)
		stage2_unmap_vm(vcpu->kvm);

	vcpu_reset_hcr(vcpu);

	/*
	 * Handle the "start in power-off" case.
	 */
	if (test_bit(KVM_ARM_VCPU_POWER_OFF, vcpu->arch.features))
		vcpu->arch.power_off = true;
	else
		vcpu->arch.power_off = false;

	return 0;
}

static int kvm_arm_vcpu_set_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->group) {
	default:
		ret = kvm_arm_vcpu_arch_set_attr(vcpu, attr);
		break;
	}

	return ret;
}

static int kvm_arm_vcpu_get_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->group) {
	default:
		ret = kvm_arm_vcpu_arch_get_attr(vcpu, attr);
		break;
	}

	return ret;
}

static int kvm_arm_vcpu_has_attr(struct kvm_vcpu *vcpu,
				 struct kvm_device_attr *attr)
{
	int ret = -ENXIO;

	switch (attr->group) {
	default:
		ret = kvm_arm_vcpu_arch_has_attr(vcpu, attr);
		break;
	}

	return ret;
}

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;
	struct kvm_device_attr attr;

	switch (ioctl) {
	case KVM_ARM_VCPU_INIT: {
		struct kvm_vcpu_init init;

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

		return kvm_arch_vcpu_ioctl_vcpu_init(vcpu, &init);
	}
	case KVM_SET_ONE_REG:
	case KVM_GET_ONE_REG: {
		struct kvm_one_reg reg;

		if (unlikely(!kvm_vcpu_initialized(vcpu)))
			return -ENOEXEC;

		if (copy_from_user(&reg, argp, sizeof(reg)))
			return -EFAULT;
		if (ioctl == KVM_SET_ONE_REG)
			return kvm_arm_set_reg(vcpu, &reg);
		else
			return kvm_arm_get_reg(vcpu, &reg);
	}
	case KVM_GET_REG_LIST: {
		struct kvm_reg_list __user *user_list = argp;
		struct kvm_reg_list reg_list;
		unsigned n;

		if (unlikely(!kvm_vcpu_initialized(vcpu)))
			return -ENOEXEC;

		if (copy_from_user(&reg_list, user_list, sizeof(reg_list)))
			return -EFAULT;
		n = reg_list.n;
		reg_list.n = kvm_arm_num_regs(vcpu);
		if (copy_to_user(user_list, &reg_list, sizeof(reg_list)))
			return -EFAULT;
		if (n < reg_list.n)
			return -E2BIG;
		return kvm_arm_copy_reg_indices(vcpu, user_list->reg);
	}
	case KVM_SET_DEVICE_ATTR: {
		if (copy_from_user(&attr, argp, sizeof(attr)))
			return -EFAULT;
		return kvm_arm_vcpu_set_attr(vcpu, &attr);
	}
	case KVM_GET_DEVICE_ATTR: {
		if (copy_from_user(&attr, argp, sizeof(attr)))
			return -EFAULT;
		return kvm_arm_vcpu_get_attr(vcpu, &attr);
	}
	case KVM_HAS_DEVICE_ATTR: {
		if (copy_from_user(&attr, argp, sizeof(attr)))
			return -EFAULT;
		return kvm_arm_vcpu_has_attr(vcpu, &attr);
	}
	default:
		return -EINVAL;
	}
}

/**
 * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot
 * @kvm: kvm instance
 * @log: slot id and address to which we copy the log
 *
 * Steps 1-4 below provide general overview of dirty page logging. See
 * kvm_get_dirty_log_protect() function description for additional details.
 *
 * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we
 * always flush the TLB (step 4) even if previous step failed  and the dirty
 * bitmap may be corrupt. Regardless of previous outcome the KVM logging API
 * does not preclude user space subsequent dirty log read. Flushing TLB ensures
 * writes will be marked dirty for next log read.
 *
 *   1. Take a snapshot of the bit and clear it if needed.
 *   2. Write protect the corresponding page.
 *   3. Copy the snapshot to the userspace.
 *   4. Flush TLB's if needed.
 */
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log)
{
	bool is_dirty = false;
	int r;

	mutex_lock(&kvm->slots_lock);

	r = kvm_get_dirty_log_protect(kvm, log, &is_dirty);

	if (is_dirty)
		kvm_flush_remote_tlbs(kvm);

	mutex_unlock(&kvm->slots_lock);
	return r;
}

static int kvm_vm_ioctl_set_device_addr(struct kvm *kvm,
					struct kvm_arm_device_addr *dev_addr)
{
	unsigned long dev_id, type;

	dev_id = (dev_addr->id & KVM_ARM_DEVICE_ID_MASK) >>
		KVM_ARM_DEVICE_ID_SHIFT;
	type = (dev_addr->id & KVM_ARM_DEVICE_TYPE_MASK) >>
		KVM_ARM_DEVICE_TYPE_SHIFT;

	switch (dev_id) {
	case KVM_ARM_DEVICE_VGIC_V2:
		if (!vgic_present)
			return -ENXIO;
		return kvm_vgic_addr(kvm, type, &dev_addr->addr, true);
	default:
		return -ENODEV;
	}
}

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

	switch (ioctl) {
	case KVM_CREATE_IRQCHIP: {
		if (!vgic_present)
			return -ENXIO;
		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
	}
	case KVM_ARM_SET_DEVICE_ADDR: {
		struct kvm_arm_device_addr dev_addr;

		if (copy_from_user(&dev_addr, argp, sizeof(dev_addr)))
			return -EFAULT;
		return kvm_vm_ioctl_set_device_addr(kvm, &dev_addr);
	}
	case KVM_ARM_PREFERRED_TARGET: {
		int err;
		struct kvm_vcpu_init init;

		err = kvm_vcpu_preferred_target(&init);
		if (err)
			return err;

		if (copy_to_user(argp, &init, sizeof(init)))
			return -EFAULT;

		return 0;
	}
	default:
		return -EINVAL;
	}
}

static void cpu_init_stage2(void *dummy)
{
	__cpu_init_stage2();
}

static void cpu_init_hyp_mode(void *dummy)
{
	phys_addr_t boot_pgd_ptr;
	phys_addr_t pgd_ptr;
	unsigned long hyp_stack_ptr;
	unsigned long stack_page;
	unsigned long vector_ptr;

	/* Switch from the HYP stub to our own HYP init vector */
	__hyp_set_vectors(kvm_get_idmap_vector());

	boot_pgd_ptr = kvm_mmu_get_boot_httbr();
	pgd_ptr = kvm_mmu_get_httbr();
	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
	hyp_stack_ptr = stack_page + PAGE_SIZE;
	vector_ptr = (unsigned long)kvm_ksym_ref(__kvm_hyp_vector);

	__cpu_init_hyp_mode(boot_pgd_ptr, pgd_ptr, hyp_stack_ptr, vector_ptr);
	__cpu_init_stage2();

	kvm_arm_init_debug();
}

static int hyp_init_cpu_notify(struct notifier_block *self,
			       unsigned long action, void *cpu)
{
	switch (action) {
	case CPU_STARTING:
	case CPU_STARTING_FROZEN:
		if (__hyp_get_vectors() == hyp_default_vectors)
			cpu_init_hyp_mode(NULL);
		break;
	}

	return NOTIFY_OK;
}

static struct notifier_block hyp_init_cpu_nb = {
	.notifier_call = hyp_init_cpu_notify,
};

#ifdef CONFIG_CPU_PM
static int hyp_init_cpu_pm_notifier(struct notifier_block *self,
				    unsigned long cmd,
				    void *v)
{
	if (cmd == CPU_PM_EXIT &&
	    __hyp_get_vectors() == hyp_default_vectors) {
		cpu_init_hyp_mode(NULL);
		return NOTIFY_OK;
	}

	return NOTIFY_DONE;
}

static struct notifier_block hyp_init_cpu_pm_nb = {
	.notifier_call = hyp_init_cpu_pm_notifier,
};

static void __init hyp_cpu_pm_init(void)
{
	cpu_pm_register_notifier(&hyp_init_cpu_pm_nb);
}
#else
static inline void hyp_cpu_pm_init(void)
{
}
#endif

static void teardown_common_resources(void)
{
	free_percpu(kvm_host_cpu_state);
}

static int init_common_resources(void)
{
	kvm_host_cpu_state = alloc_percpu(kvm_cpu_context_t);
	if (!kvm_host_cpu_state) {
		kvm_err("Cannot allocate host CPU state\n");
		return -ENOMEM;
	}

	return 0;
}

static int init_subsystems(void)
{
	int err;

	/*
	 * Init HYP view of VGIC
	 */
	err = kvm_vgic_hyp_init();
	switch (err) {
	case 0:
		vgic_present = true;
		break;
	case -ENODEV:
	case -ENXIO:
		vgic_present = false;
		break;
	default:
		return err;
	}

	/*
	 * Init HYP architected timer support
	 */
	err = kvm_timer_hyp_init();
	if (err)
		return err;

	kvm_perf_init();
	kvm_coproc_table_init();

	return 0;
}

static void teardown_hyp_mode(void)
{
	int cpu;

	if (is_kernel_in_hyp_mode())
		return;

	free_hyp_pgds();
	for_each_possible_cpu(cpu)
		free_page(per_cpu(kvm_arm_hyp_stack_page, cpu));
}

static int init_vhe_mode(void)
{
	/*
	 * Execute the init code on each CPU.
	 */
	on_each_cpu(cpu_init_stage2, NULL, 1);

	/* set size of VMID supported by CPU */
	kvm_vmid_bits = kvm_get_vmid_bits();
	kvm_info("%d-bit VMID\n", kvm_vmid_bits);

	kvm_info("VHE mode initialized successfully\n");
	return 0;
}

/**
 * Inits Hyp-mode on all online CPUs
 */
static int init_hyp_mode(void)
{
	int cpu;
	int err = 0;

	/*
	 * Allocate Hyp PGD and setup Hyp identity mapping
	 */
	err = kvm_mmu_init();
	if (err)
		goto out_err;

	/*
	 * It is probably enough to obtain the default on one
	 * CPU. It's unlikely to be different on the others.
	 */
	hyp_default_vectors = __hyp_get_vectors();

	/*
	 * Allocate stack pages for Hypervisor-mode
	 */
	for_each_possible_cpu(cpu) {
		unsigned long stack_page;

		stack_page = __get_free_page(GFP_KERNEL);
		if (!stack_page) {
			err = -ENOMEM;
			goto out_err;
		}

		per_cpu(kvm_arm_hyp_stack_page, cpu) = stack_page;
	}

	/*
	 * Map the Hyp-code called directly from the host
	 */
	err = create_hyp_mappings(kvm_ksym_ref(__hyp_text_start),
				  kvm_ksym_ref(__hyp_text_end));
	if (err) {
		kvm_err("Cannot map world-switch code\n");
		goto out_err;
	}

	err = create_hyp_mappings(kvm_ksym_ref(__start_rodata),
				  kvm_ksym_ref(__end_rodata));
	if (err) {
		kvm_err("Cannot map rodata section\n");
		goto out_err;
	}

	/*
	 * Map the Hyp stack pages
	 */
	for_each_possible_cpu(cpu) {
		char *stack_page = (char *)per_cpu(kvm_arm_hyp_stack_page, cpu);
		err = create_hyp_mappings(stack_page, stack_page + PAGE_SIZE);

		if (err) {
			kvm_err("Cannot map hyp stack\n");
			goto out_err;
		}
	}

	for_each_possible_cpu(cpu) {
		kvm_cpu_context_t *cpu_ctxt;

		cpu_ctxt = per_cpu_ptr(kvm_host_cpu_state, cpu);
		err = create_hyp_mappings(cpu_ctxt, cpu_ctxt + 1);

		if (err) {
			kvm_err("Cannot map host CPU state: %d\n", err);
			goto out_err;
		}
	}

	/*
	 * Execute the init code on each CPU.
	 */
	on_each_cpu(cpu_init_hyp_mode, NULL, 1);

#ifndef CONFIG_HOTPLUG_CPU
	free_boot_hyp_pgd();
#endif

	cpu_notifier_register_begin();

	err = __register_cpu_notifier(&hyp_init_cpu_nb);

	cpu_notifier_register_done();

	if (err) {
		kvm_err("Cannot register HYP init CPU notifier (%d)\n", err);
		goto out_err;
	}

	hyp_cpu_pm_init();

	/* set size of VMID supported by CPU */
	kvm_vmid_bits = kvm_get_vmid_bits();
	kvm_info("%d-bit VMID\n", kvm_vmid_bits);

	kvm_info("Hyp mode initialized successfully\n");

	return 0;

out_err:
	teardown_hyp_mode();
	kvm_err("error initializing Hyp mode: %d\n", err);
	return err;
}

static void check_kvm_target_cpu(void *ret)
{
	*(int *)ret = kvm_target_cpu();
}

struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr)
{
	struct kvm_vcpu *vcpu;
	int i;

	mpidr &= MPIDR_HWID_BITMASK;
	kvm_for_each_vcpu(i, vcpu, kvm) {
		if (mpidr == kvm_vcpu_get_mpidr_aff(vcpu))
			return vcpu;
	}
	return NULL;
}

/**
 * Initialize Hyp-mode and memory mappings on all CPUs.
 */
int kvm_arch_init(void *opaque)
{
	int err;
	int ret, cpu;

	if (!is_hyp_mode_available()) {
		kvm_err("HYP mode not available\n");
		return -ENODEV;
	}

	for_each_online_cpu(cpu) {
		smp_call_function_single(cpu, check_kvm_target_cpu, &ret, 1);
		if (ret < 0) {
			kvm_err("Error, CPU %d not supported!\n", cpu);
			return -ENODEV;
		}
	}

	err = init_common_resources();
	if (err)
		return err;

	if (is_kernel_in_hyp_mode())
		err = init_vhe_mode();
	else
		err = init_hyp_mode();
	if (err)
		goto out_err;

	err = init_subsystems();
	if (err)
		goto out_hyp;

	return 0;

out_hyp:
	teardown_hyp_mode();
out_err:
	teardown_common_resources();
	return err;
}

/* NOP: Compiling as a module not supported */
void kvm_arch_exit(void)
{
	kvm_perf_teardown();
}

static int arm_init(void)
{
	int rc = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
	return rc;
}

module_init(arm_init);