aboutsummaryrefslogtreecommitdiff
path: root/virt/kvm/arm/arch_timer.c
blob: 4986028d98292501e069cef18dc93ede7c8a3401 (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
/*
 * Copyright (C) 2012 ARM Ltd.
 * Author: Marc Zyngier <marc.zyngier@arm.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, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 */

#include <linux/cpu.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/uaccess.h>

#include <clocksource/arm_arch_timer.h>
#include <asm/arch_timer.h>
#include <asm/kvm_hyp.h>

#include <kvm/arm_vgic.h>
#include <kvm/arm_arch_timer.h>

#include "trace.h"

static struct timecounter *timecounter;
static unsigned int host_vtimer_irq;
static u32 host_vtimer_irq_flags;

static DEFINE_STATIC_KEY_FALSE(has_gic_active_state);

static const struct kvm_irq_level default_ptimer_irq = {
	.irq	= 30,
	.level	= 1,
};

static const struct kvm_irq_level default_vtimer_irq = {
	.irq	= 27,
	.level	= 1,
};

static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx);
static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
				 struct arch_timer_context *timer_ctx);
static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx);

u64 kvm_phys_timer_read(void)
{
	return timecounter->cc->read(timecounter->cc);
}

static inline bool userspace_irqchip(struct kvm *kvm)
{
	return static_branch_unlikely(&userspace_irqchip_in_use) &&
		unlikely(!irqchip_in_kernel(kvm));
}

static void soft_timer_start(struct hrtimer *hrt, u64 ns)
{
	hrtimer_start(hrt, ktime_add_ns(ktime_get(), ns),
		      HRTIMER_MODE_ABS);
}

static void soft_timer_cancel(struct hrtimer *hrt)
{
	hrtimer_cancel(hrt);
}

static irqreturn_t kvm_arch_timer_handler(int irq, void *dev_id)
{
	struct kvm_vcpu *vcpu = *(struct kvm_vcpu **)dev_id;
	struct arch_timer_context *vtimer;

	/*
	 * We may see a timer interrupt after vcpu_put() has been called which
	 * sets the CPU's vcpu pointer to NULL, because even though the timer
	 * has been disabled in vtimer_save_state(), the hardware interrupt
	 * signal may not have been retired from the interrupt controller yet.
	 */
	if (!vcpu)
		return IRQ_HANDLED;

	vtimer = vcpu_vtimer(vcpu);
	if (kvm_timer_should_fire(vtimer))
		kvm_timer_update_irq(vcpu, true, vtimer);

	if (userspace_irqchip(vcpu->kvm) &&
	    !static_branch_unlikely(&has_gic_active_state))
		disable_percpu_irq(host_vtimer_irq);

	return IRQ_HANDLED;
}

static u64 kvm_timer_compute_delta(struct arch_timer_context *timer_ctx)
{
	u64 cval, now;

	cval = timer_ctx->cnt_cval;
	now = kvm_phys_timer_read() - timer_ctx->cntvoff;

	if (now < cval) {
		u64 ns;

		ns = cyclecounter_cyc2ns(timecounter->cc,
					 cval - now,
					 timecounter->mask,
					 &timecounter->frac);
		return ns;
	}

	return 0;
}

static bool kvm_timer_irq_can_fire(struct arch_timer_context *timer_ctx)
{
	return !(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_IT_MASK) &&
		(timer_ctx->cnt_ctl & ARCH_TIMER_CTRL_ENABLE);
}

/*
 * Returns the earliest expiration time in ns among guest timers.
 * Note that it will return 0 if none of timers can fire.
 */
static u64 kvm_timer_earliest_exp(struct kvm_vcpu *vcpu)
{
	u64 min_virt = ULLONG_MAX, min_phys = ULLONG_MAX;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	if (kvm_timer_irq_can_fire(vtimer))
		min_virt = kvm_timer_compute_delta(vtimer);

	if (kvm_timer_irq_can_fire(ptimer))
		min_phys = kvm_timer_compute_delta(ptimer);

	/* If none of timers can fire, then return 0 */
	if ((min_virt == ULLONG_MAX) && (min_phys == ULLONG_MAX))
		return 0;

	return min(min_virt, min_phys);
}

static enum hrtimer_restart kvm_bg_timer_expire(struct hrtimer *hrt)
{
	struct arch_timer_cpu *timer;
	struct kvm_vcpu *vcpu;
	u64 ns;

	timer = container_of(hrt, struct arch_timer_cpu, bg_timer);
	vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);

	/*
	 * Check that the timer has really expired from the guest's
	 * PoV (NTP on the host may have forced it to expire
	 * early). If we should have slept longer, restart it.
	 */
	ns = kvm_timer_earliest_exp(vcpu);
	if (unlikely(ns)) {
		hrtimer_forward_now(hrt, ns_to_ktime(ns));
		return HRTIMER_RESTART;
	}

	kvm_vcpu_wake_up(vcpu);
	return HRTIMER_NORESTART;
}

static enum hrtimer_restart kvm_phys_timer_expire(struct hrtimer *hrt)
{
	struct arch_timer_context *ptimer;
	struct arch_timer_cpu *timer;
	struct kvm_vcpu *vcpu;
	u64 ns;

	timer = container_of(hrt, struct arch_timer_cpu, phys_timer);
	vcpu = container_of(timer, struct kvm_vcpu, arch.timer_cpu);
	ptimer = vcpu_ptimer(vcpu);

	/*
	 * Check that the timer has really expired from the guest's
	 * PoV (NTP on the host may have forced it to expire
	 * early). If not ready, schedule for a later time.
	 */
	ns = kvm_timer_compute_delta(ptimer);
	if (unlikely(ns)) {
		hrtimer_forward_now(hrt, ns_to_ktime(ns));
		return HRTIMER_RESTART;
	}

	kvm_timer_update_irq(vcpu, true, ptimer);
	return HRTIMER_NORESTART;
}

static bool kvm_timer_should_fire(struct arch_timer_context *timer_ctx)
{
	u64 cval, now;

	if (timer_ctx->loaded) {
		u32 cnt_ctl;

		/* Only the virtual timer can be loaded so far */
		cnt_ctl = read_sysreg_el0(cntv_ctl);
		return  (cnt_ctl & ARCH_TIMER_CTRL_ENABLE) &&
		        (cnt_ctl & ARCH_TIMER_CTRL_IT_STAT) &&
		       !(cnt_ctl & ARCH_TIMER_CTRL_IT_MASK);
	}

	if (!kvm_timer_irq_can_fire(timer_ctx))
		return false;

	cval = timer_ctx->cnt_cval;
	now = kvm_phys_timer_read() - timer_ctx->cntvoff;

	return cval <= now;
}

bool kvm_timer_is_pending(struct kvm_vcpu *vcpu)
{
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	if (kvm_timer_should_fire(vtimer))
		return true;

	return kvm_timer_should_fire(ptimer);
}

/*
 * Reflect the timer output level into the kvm_run structure
 */
void kvm_timer_update_run(struct kvm_vcpu *vcpu)
{
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
	struct kvm_sync_regs *regs = &vcpu->run->s.regs;

	/* Populate the device bitmap with the timer states */
	regs->device_irq_level &= ~(KVM_ARM_DEV_EL1_VTIMER |
				    KVM_ARM_DEV_EL1_PTIMER);
	if (kvm_timer_should_fire(vtimer))
		regs->device_irq_level |= KVM_ARM_DEV_EL1_VTIMER;
	if (kvm_timer_should_fire(ptimer))
		regs->device_irq_level |= KVM_ARM_DEV_EL1_PTIMER;
}

static void kvm_timer_update_irq(struct kvm_vcpu *vcpu, bool new_level,
				 struct arch_timer_context *timer_ctx)
{
	int ret;

	timer_ctx->irq.level = new_level;
	trace_kvm_timer_update_irq(vcpu->vcpu_id, timer_ctx->irq.irq,
				   timer_ctx->irq.level);

	if (!userspace_irqchip(vcpu->kvm)) {
		ret = kvm_vgic_inject_irq(vcpu->kvm, vcpu->vcpu_id,
					  timer_ctx->irq.irq,
					  timer_ctx->irq.level,
					  timer_ctx);
		WARN_ON(ret);
	}
}

/* Schedule the background timer for the emulated timer. */
static void phys_timer_emulate(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	/*
	 * If the timer can fire now, we don't need to have a soft timer
	 * scheduled for the future.  If the timer cannot fire at all,
	 * then we also don't need a soft timer.
	 */
	if (kvm_timer_should_fire(ptimer) || !kvm_timer_irq_can_fire(ptimer)) {
		soft_timer_cancel(&timer->phys_timer);
		return;
	}

	soft_timer_start(&timer->phys_timer, kvm_timer_compute_delta(ptimer));
}

/*
 * Check if there was a change in the timer state, so that we should either
 * raise or lower the line level to the GIC or schedule a background timer to
 * emulate the physical timer.
 */
static void kvm_timer_update_state(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
	bool level;

	if (unlikely(!timer->enabled))
		return;

	/*
	 * The vtimer virtual interrupt is a 'mapped' interrupt, meaning part
	 * of its lifecycle is offloaded to the hardware, and we therefore may
	 * not have lowered the irq.level value before having to signal a new
	 * interrupt, but have to signal an interrupt every time the level is
	 * asserted.
	 */
	level = kvm_timer_should_fire(vtimer);
	kvm_timer_update_irq(vcpu, level, vtimer);

	phys_timer_emulate(vcpu);

	if (kvm_timer_should_fire(ptimer) != ptimer->irq.level)
		kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer);
}

static void vtimer_save_state(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	unsigned long flags;

	local_irq_save(flags);

	if (!vtimer->loaded)
		goto out;

	if (timer->enabled) {
		vtimer->cnt_ctl = read_sysreg_el0(cntv_ctl);
		vtimer->cnt_cval = read_sysreg_el0(cntv_cval);
	}

	/* Disable the virtual timer */
	write_sysreg_el0(0, cntv_ctl);
	isb();

	vtimer->loaded = false;
out:
	local_irq_restore(flags);
}

/*
 * Schedule the background timer before calling kvm_vcpu_block, so that this
 * thread is removed from its waitqueue and made runnable when there's a timer
 * interrupt to handle.
 */
static void kvm_timer_blocking(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	/*
	 * If both timers are not capable of raising interrupts (disabled or
	 * masked), then there's no more work for us to do.
	 */
	if (!kvm_timer_irq_can_fire(vtimer) && !kvm_timer_irq_can_fire(ptimer))
		return;

	/*
	 * At least one guest time will expire. Schedule a background timer.
	 * Set the earliest expiration time among the guest timers.
	 */
	soft_timer_start(&timer->bg_timer, kvm_timer_earliest_exp(vcpu));
}

static void kvm_timer_unblocking(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;

	soft_timer_cancel(&timer->bg_timer);
}

static void vtimer_restore_state(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	unsigned long flags;

	local_irq_save(flags);

	if (vtimer->loaded)
		goto out;

	if (timer->enabled) {
		write_sysreg_el0(vtimer->cnt_cval, cntv_cval);
		isb();
		write_sysreg_el0(vtimer->cnt_ctl, cntv_ctl);
	}

	vtimer->loaded = true;
out:
	local_irq_restore(flags);
}

static void set_cntvoff(u64 cntvoff)
{
	u32 low = lower_32_bits(cntvoff);
	u32 high = upper_32_bits(cntvoff);

	/*
	 * Since kvm_call_hyp doesn't fully support the ARM PCS especially on
	 * 32-bit systems, but rather passes register by register shifted one
	 * place (we put the function address in r0/x0), we cannot simply pass
	 * a 64-bit value as an argument, but have to split the value in two
	 * 32-bit halves.
	 */
	kvm_call_hyp(__kvm_timer_set_cntvoff, low, high);
}

static inline void set_vtimer_irq_phys_active(struct kvm_vcpu *vcpu, bool active)
{
	int r;
	r = irq_set_irqchip_state(host_vtimer_irq, IRQCHIP_STATE_ACTIVE, active);
	WARN_ON(r);
}

static void kvm_timer_vcpu_load_gic(struct kvm_vcpu *vcpu)
{
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	bool phys_active;

	if (irqchip_in_kernel(vcpu->kvm))
		phys_active = kvm_vgic_map_is_active(vcpu, vtimer->irq.irq);
	else
		phys_active = vtimer->irq.level;
	set_vtimer_irq_phys_active(vcpu, phys_active);
}

static void kvm_timer_vcpu_load_nogic(struct kvm_vcpu *vcpu)
{
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);

	/*
	 * When using a userspace irqchip with the architected timers and a
	 * host interrupt controller that doesn't support an active state, we
	 * must still prevent continuously exiting from the guest, and
	 * therefore mask the physical interrupt by disabling it on the host
	 * interrupt controller when the virtual level is high, such that the
	 * guest can make forward progress.  Once we detect the output level
	 * being de-asserted, we unmask the interrupt again so that we exit
	 * from the guest when the timer fires.
	 */
	if (vtimer->irq.level)
		disable_percpu_irq(host_vtimer_irq);
	else
		enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
}

void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	if (unlikely(!timer->enabled))
		return;

	if (static_branch_likely(&has_gic_active_state))
		kvm_timer_vcpu_load_gic(vcpu);
	else
		kvm_timer_vcpu_load_nogic(vcpu);

	set_cntvoff(vtimer->cntvoff);

	vtimer_restore_state(vcpu);

	/* Set the background timer for the physical timer emulation. */
	phys_timer_emulate(vcpu);

	kvm_timer_unblocking(vcpu);

	/* If the timer fired while we weren't running, inject it now */
	if (kvm_timer_should_fire(ptimer) != ptimer->irq.level)
		kvm_timer_update_irq(vcpu, !ptimer->irq.level, ptimer);
}

bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu)
{
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
	struct kvm_sync_regs *sregs = &vcpu->run->s.regs;
	bool vlevel, plevel;

	if (likely(irqchip_in_kernel(vcpu->kvm)))
		return false;

	vlevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_VTIMER;
	plevel = sregs->device_irq_level & KVM_ARM_DEV_EL1_PTIMER;

	return kvm_timer_should_fire(vtimer) != vlevel ||
	       kvm_timer_should_fire(ptimer) != plevel;
}

void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;

	if (unlikely(!timer->enabled))
		return;

	vtimer_save_state(vcpu);

	/*
	 * Cancel the physical timer emulation, because the only case where we
	 * need it after a vcpu_put is in the context of a sleeping VCPU, and
	 * in that case we already factor in the deadline for the physical
	 * timer when scheduling the bg_timer.
	 *
	 * In any case, we re-schedule the hrtimer for the physical timer when
	 * coming back to the VCPU thread in kvm_timer_vcpu_load().
	 */
	soft_timer_cancel(&timer->phys_timer);

	if (swait_active(kvm_arch_vcpu_wq(vcpu)))
		kvm_timer_blocking(vcpu);

	/*
	 * The kernel may decide to run userspace after calling vcpu_put, so
	 * we reset cntvoff to 0 to ensure a consistent read between user
	 * accesses to the virtual counter and kernel access to the physical
	 * counter of non-VHE case. For VHE, the virtual counter uses a fixed
	 * virtual offset of zero, so no need to zero CNTVOFF_EL2 register.
	 */
	if (!has_vhe())
		set_cntvoff(0);
}

/*
 * With a userspace irqchip we have to check if the guest de-asserted the
 * timer and if so, unmask the timer irq signal on the host interrupt
 * controller to ensure that we see future timer signals.
 */
static void unmask_vtimer_irq_user(struct kvm_vcpu *vcpu)
{
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);

	if (!kvm_timer_should_fire(vtimer)) {
		kvm_timer_update_irq(vcpu, false, vtimer);
		if (static_branch_likely(&has_gic_active_state))
			set_vtimer_irq_phys_active(vcpu, false);
		else
			enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
	}
}

void kvm_timer_sync_hwstate(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;

	if (unlikely(!timer->enabled))
		return;

	if (unlikely(!irqchip_in_kernel(vcpu->kvm)))
		unmask_vtimer_irq_user(vcpu);
}

int kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	/*
	 * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8
	 * and to 0 for ARMv7.  We provide an implementation that always
	 * resets the timer to be disabled and unmasked and is compliant with
	 * the ARMv7 architecture.
	 */
	vtimer->cnt_ctl = 0;
	ptimer->cnt_ctl = 0;
	kvm_timer_update_state(vcpu);

	if (timer->enabled && irqchip_in_kernel(vcpu->kvm))
		kvm_vgic_reset_mapped_irq(vcpu, vtimer->irq.irq);

	return 0;
}

/* Make the updates of cntvoff for all vtimer contexts atomic */
static void update_vtimer_cntvoff(struct kvm_vcpu *vcpu, u64 cntvoff)
{
	int i;
	struct kvm *kvm = vcpu->kvm;
	struct kvm_vcpu *tmp;

	mutex_lock(&kvm->lock);
	kvm_for_each_vcpu(i, tmp, kvm)
		vcpu_vtimer(tmp)->cntvoff = cntvoff;

	/*
	 * When called from the vcpu create path, the CPU being created is not
	 * included in the loop above, so we just set it here as well.
	 */
	vcpu_vtimer(vcpu)->cntvoff = cntvoff;
	mutex_unlock(&kvm->lock);
}

void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	/* Synchronize cntvoff across all vtimers of a VM. */
	update_vtimer_cntvoff(vcpu, kvm_phys_timer_read());
	vcpu_ptimer(vcpu)->cntvoff = 0;

	hrtimer_init(&timer->bg_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
	timer->bg_timer.function = kvm_bg_timer_expire;

	hrtimer_init(&timer->phys_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
	timer->phys_timer.function = kvm_phys_timer_expire;

	vtimer->irq.irq = default_vtimer_irq.irq;
	ptimer->irq.irq = default_ptimer_irq.irq;
}

static void kvm_timer_init_interrupt(void *info)
{
	enable_percpu_irq(host_vtimer_irq, host_vtimer_irq_flags);
}

int kvm_arm_timer_set_reg(struct kvm_vcpu *vcpu, u64 regid, u64 value)
{
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);

	switch (regid) {
	case KVM_REG_ARM_TIMER_CTL:
		vtimer->cnt_ctl = value & ~ARCH_TIMER_CTRL_IT_STAT;
		break;
	case KVM_REG_ARM_TIMER_CNT:
		update_vtimer_cntvoff(vcpu, kvm_phys_timer_read() - value);
		break;
	case KVM_REG_ARM_TIMER_CVAL:
		vtimer->cnt_cval = value;
		break;
	case KVM_REG_ARM_PTIMER_CTL:
		ptimer->cnt_ctl = value & ~ARCH_TIMER_CTRL_IT_STAT;
		break;
	case KVM_REG_ARM_PTIMER_CVAL:
		ptimer->cnt_cval = value;
		break;

	default:
		return -1;
	}

	kvm_timer_update_state(vcpu);
	return 0;
}

static u64 read_timer_ctl(struct arch_timer_context *timer)
{
	/*
	 * Set ISTATUS bit if it's expired.
	 * Note that according to ARMv8 ARM Issue A.k, ISTATUS bit is
	 * UNKNOWN when ENABLE bit is 0, so we chose to set ISTATUS bit
	 * regardless of ENABLE bit for our implementation convenience.
	 */
	if (!kvm_timer_compute_delta(timer))
		return timer->cnt_ctl | ARCH_TIMER_CTRL_IT_STAT;
	else
		return timer->cnt_ctl;
}

u64 kvm_arm_timer_get_reg(struct kvm_vcpu *vcpu, u64 regid)
{
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);

	switch (regid) {
	case KVM_REG_ARM_TIMER_CTL:
		return read_timer_ctl(vtimer);
	case KVM_REG_ARM_TIMER_CNT:
		return kvm_phys_timer_read() - vtimer->cntvoff;
	case KVM_REG_ARM_TIMER_CVAL:
		return vtimer->cnt_cval;
	case KVM_REG_ARM_PTIMER_CTL:
		return read_timer_ctl(ptimer);
	case KVM_REG_ARM_PTIMER_CVAL:
		return ptimer->cnt_cval;
	case KVM_REG_ARM_PTIMER_CNT:
		return kvm_phys_timer_read();
	}
	return (u64)-1;
}

static int kvm_timer_starting_cpu(unsigned int cpu)
{
	kvm_timer_init_interrupt(NULL);
	return 0;
}

static int kvm_timer_dying_cpu(unsigned int cpu)
{
	disable_percpu_irq(host_vtimer_irq);
	return 0;
}

int kvm_timer_hyp_init(bool has_gic)
{
	struct arch_timer_kvm_info *info;
	int err;

	info = arch_timer_get_kvm_info();
	timecounter = &info->timecounter;

	if (!timecounter->cc) {
		kvm_err("kvm_arch_timer: uninitialized timecounter\n");
		return -ENODEV;
	}

	if (info->virtual_irq <= 0) {
		kvm_err("kvm_arch_timer: invalid virtual timer IRQ: %d\n",
			info->virtual_irq);
		return -ENODEV;
	}
	host_vtimer_irq = info->virtual_irq;

	host_vtimer_irq_flags = irq_get_trigger_type(host_vtimer_irq);
	if (host_vtimer_irq_flags != IRQF_TRIGGER_HIGH &&
	    host_vtimer_irq_flags != IRQF_TRIGGER_LOW) {
		kvm_err("Invalid trigger for IRQ%d, assuming level low\n",
			host_vtimer_irq);
		host_vtimer_irq_flags = IRQF_TRIGGER_LOW;
	}

	err = request_percpu_irq(host_vtimer_irq, kvm_arch_timer_handler,
				 "kvm guest timer", kvm_get_running_vcpus());
	if (err) {
		kvm_err("kvm_arch_timer: can't request interrupt %d (%d)\n",
			host_vtimer_irq, err);
		return err;
	}

	if (has_gic) {
		err = irq_set_vcpu_affinity(host_vtimer_irq,
					    kvm_get_running_vcpus());
		if (err) {
			kvm_err("kvm_arch_timer: error setting vcpu affinity\n");
			goto out_free_irq;
		}

		static_branch_enable(&has_gic_active_state);
	}

	kvm_debug("virtual timer IRQ%d\n", host_vtimer_irq);

	cpuhp_setup_state(CPUHP_AP_KVM_ARM_TIMER_STARTING,
			  "kvm/arm/timer:starting", kvm_timer_starting_cpu,
			  kvm_timer_dying_cpu);
	return 0;
out_free_irq:
	free_percpu_irq(host_vtimer_irq, kvm_get_running_vcpus());
	return err;
}

void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;

	soft_timer_cancel(&timer->bg_timer);
}

static bool timer_irqs_are_valid(struct kvm_vcpu *vcpu)
{
	int vtimer_irq, ptimer_irq;
	int i, ret;

	vtimer_irq = vcpu_vtimer(vcpu)->irq.irq;
	ret = kvm_vgic_set_owner(vcpu, vtimer_irq, vcpu_vtimer(vcpu));
	if (ret)
		return false;

	ptimer_irq = vcpu_ptimer(vcpu)->irq.irq;
	ret = kvm_vgic_set_owner(vcpu, ptimer_irq, vcpu_ptimer(vcpu));
	if (ret)
		return false;

	kvm_for_each_vcpu(i, vcpu, vcpu->kvm) {
		if (vcpu_vtimer(vcpu)->irq.irq != vtimer_irq ||
		    vcpu_ptimer(vcpu)->irq.irq != ptimer_irq)
			return false;
	}

	return true;
}

bool kvm_arch_timer_get_input_level(int vintid)
{
	struct kvm_vcpu *vcpu = kvm_arm_get_running_vcpu();
	struct arch_timer_context *timer;

	if (vintid == vcpu_vtimer(vcpu)->irq.irq)
		timer = vcpu_vtimer(vcpu);
	else
		BUG(); /* We only map the vtimer so far */

	return kvm_timer_should_fire(timer);
}

int kvm_timer_enable(struct kvm_vcpu *vcpu)
{
	struct arch_timer_cpu *timer = &vcpu->arch.timer_cpu;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	int ret;

	if (timer->enabled)
		return 0;

	/* Without a VGIC we do not map virtual IRQs to physical IRQs */
	if (!irqchip_in_kernel(vcpu->kvm))
		goto no_vgic;

	if (!vgic_initialized(vcpu->kvm))
		return -ENODEV;

	if (!timer_irqs_are_valid(vcpu)) {
		kvm_debug("incorrectly configured timer irqs\n");
		return -EINVAL;
	}

	ret = kvm_vgic_map_phys_irq(vcpu, host_vtimer_irq, vtimer->irq.irq,
				    kvm_arch_timer_get_input_level);
	if (ret)
		return ret;

no_vgic:
	timer->enabled = 1;
	return 0;
}

/*
 * On VHE system, we only need to configure trap on physical timer and counter
 * accesses in EL0 and EL1 once, not for every world switch.
 * The host kernel runs at EL2 with HCR_EL2.TGE == 1,
 * and this makes those bits have no effect for the host kernel execution.
 */
void kvm_timer_init_vhe(void)
{
	/* When HCR_EL2.E2H ==1, EL1PCEN and EL1PCTEN are shifted by 10 */
	u32 cnthctl_shift = 10;
	u64 val;

	/*
	 * Disallow physical timer access for the guest.
	 * Physical counter access is allowed.
	 */
	val = read_sysreg(cnthctl_el2);
	val &= ~(CNTHCTL_EL1PCEN << cnthctl_shift);
	val |= (CNTHCTL_EL1PCTEN << cnthctl_shift);
	write_sysreg(val, cnthctl_el2);
}

static void set_timer_irqs(struct kvm *kvm, int vtimer_irq, int ptimer_irq)
{
	struct kvm_vcpu *vcpu;
	int i;

	kvm_for_each_vcpu(i, vcpu, kvm) {
		vcpu_vtimer(vcpu)->irq.irq = vtimer_irq;
		vcpu_ptimer(vcpu)->irq.irq = ptimer_irq;
	}
}

int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
	int __user *uaddr = (int __user *)(long)attr->addr;
	struct arch_timer_context *vtimer = vcpu_vtimer(vcpu);
	struct arch_timer_context *ptimer = vcpu_ptimer(vcpu);
	int irq;

	if (!irqchip_in_kernel(vcpu->kvm))
		return -EINVAL;

	if (get_user(irq, uaddr))
		return -EFAULT;

	if (!(irq_is_ppi(irq)))
		return -EINVAL;

	if (vcpu->arch.timer_cpu.enabled)
		return -EBUSY;

	switch (attr->attr) {
	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
		set_timer_irqs(vcpu->kvm, irq, ptimer->irq.irq);
		break;
	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
		set_timer_irqs(vcpu->kvm, vtimer->irq.irq, irq);
		break;
	default:
		return -ENXIO;
	}

	return 0;
}

int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
	int __user *uaddr = (int __user *)(long)attr->addr;
	struct arch_timer_context *timer;
	int irq;

	switch (attr->attr) {
	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
		timer = vcpu_vtimer(vcpu);
		break;
	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
		timer = vcpu_ptimer(vcpu);
		break;
	default:
		return -ENXIO;
	}

	irq = timer->irq.irq;
	return put_user(irq, uaddr);
}

int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
{
	switch (attr->attr) {
	case KVM_ARM_VCPU_TIMER_IRQ_VTIMER:
	case KVM_ARM_VCPU_TIMER_IRQ_PTIMER:
		return 0;
	}

	return -ENXIO;
}