summaryrefslogtreecommitdiffstats
path: root/virt/kvm/arm/vgic/vgic.c
blob: 8201899126f6bf338247be84dc1b91cd390b608b (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) 2015, 2016 ARM Ltd.
 *
 * 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, see <http://www.gnu.org/licenses/>.
 */

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

#include "vgic.h"

#define CREATE_TRACE_POINTS
#include "trace.h"

#ifdef CONFIG_DEBUG_SPINLOCK
#define DEBUG_SPINLOCK_BUG_ON(p) BUG_ON(p)
#else
#define DEBUG_SPINLOCK_BUG_ON(p)
#endif

struct vgic_global kvm_vgic_global_state __ro_after_init = {
	.gicv3_cpuif = STATIC_KEY_FALSE_INIT,
};

/*
 * Locking order is always:
 * kvm->lock (mutex)
 *   its->cmd_lock (mutex)
 *     its->its_lock (mutex)
 *       vgic_cpu->ap_list_lock
 *         kvm->lpi_list_lock
 *           vgic_irq->irq_lock
 *
 * If you need to take multiple locks, always take the upper lock first,
 * then the lower ones, e.g. first take the its_lock, then the irq_lock.
 * If you are already holding a lock and need to take a higher one, you
 * have to drop the lower ranking lock first and re-aquire it after having
 * taken the upper one.
 *
 * When taking more than one ap_list_lock at the same time, always take the
 * lowest numbered VCPU's ap_list_lock first, so:
 *   vcpuX->vcpu_id < vcpuY->vcpu_id:
 *     spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock);
 *     spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock);
 *
 * Since the VGIC must support injecting virtual interrupts from ISRs, we have
 * to use the spin_lock_irqsave/spin_unlock_irqrestore versions of outer
 * spinlocks for any lock that may be taken while injecting an interrupt.
 */

/*
 * Iterate over the VM's list of mapped LPIs to find the one with a
 * matching interrupt ID and return a reference to the IRQ structure.
 */
static struct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
{
	struct vgic_dist *dist = &kvm->arch.vgic;
	struct vgic_irq *irq = NULL;

	spin_lock(&dist->lpi_list_lock);

	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
		if (irq->intid != intid)
			continue;

		/*
		 * This increases the refcount, the caller is expected to
		 * call vgic_put_irq() later once it's finished with the IRQ.
		 */
		vgic_get_irq_kref(irq);
		goto out_unlock;
	}
	irq = NULL;

out_unlock:
	spin_unlock(&dist->lpi_list_lock);

	return irq;
}

/*
 * This looks up the virtual interrupt ID to get the corresponding
 * struct vgic_irq. It also increases the refcount, so any caller is expected
 * to call vgic_put_irq() once it's finished with this IRQ.
 */
struct vgic_irq *vgic_get_irq(struct kvm *kvm, struct kvm_vcpu *vcpu,
			      u32 intid)
{
	/* SGIs and PPIs */
	if (intid <= VGIC_MAX_PRIVATE)
		return &vcpu->arch.vgic_cpu.private_irqs[intid];

	/* SPIs */
	if (intid <= VGIC_MAX_SPI)
		return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];

	/* LPIs */
	if (intid >= VGIC_MIN_LPI)
		return vgic_get_lpi(kvm, intid);

	WARN(1, "Looking up struct vgic_irq for reserved INTID");
	return NULL;
}

/*
 * We can't do anything in here, because we lack the kvm pointer to
 * lock and remove the item from the lpi_list. So we keep this function
 * empty and use the return value of kref_put() to trigger the freeing.
 */
static void vgic_irq_release(struct kref *ref)
{
}

void vgic_put_irq(struct kvm *kvm, struct vgic_irq *irq)
{
	struct vgic_dist *dist = &kvm->arch.vgic;

	if (irq->intid < VGIC_MIN_LPI)
		return;

	spin_lock(&dist->lpi_list_lock);
	if (!kref_put(&irq->refcount, vgic_irq_release)) {
		spin_unlock(&dist->lpi_list_lock);
		return;
	};

	list_del(&irq->lpi_list);
	dist->lpi_list_count--;
	spin_unlock(&dist->lpi_list_lock);

	kfree(irq);
}

void vgic_irq_set_phys_pending(struct vgic_irq *irq, bool pending)
{
	WARN_ON(irq_set_irqchip_state(irq->host_irq,
				      IRQCHIP_STATE_PENDING,
				      pending));
}

bool vgic_get_phys_line_level(struct vgic_irq *irq)
{
	bool line_level;

	BUG_ON(!irq->hw);

	if (irq->get_input_level)
		return irq->get_input_level(irq->intid);

	WARN_ON(irq_get_irqchip_state(irq->host_irq,
				      IRQCHIP_STATE_PENDING,
				      &line_level));
	return line_level;
}

/* Set/Clear the physical active state */
void vgic_irq_set_phys_active(struct vgic_irq *irq, bool active)
{

	BUG_ON(!irq->hw);
	WARN_ON(irq_set_irqchip_state(irq->host_irq,
				      IRQCHIP_STATE_ACTIVE,
				      active));
}

/**
 * kvm_vgic_target_oracle - compute the target vcpu for an irq
 *
 * @irq:	The irq to route. Must be already locked.
 *
 * Based on the current state of the interrupt (enabled, pending,
 * active, vcpu and target_vcpu), compute the next vcpu this should be
 * given to. Return NULL if this shouldn't be injected at all.
 *
 * Requires the IRQ lock to be held.
 */
static struct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq)
{
	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));

	/* If the interrupt is active, it must stay on the current vcpu */
	if (irq->active)
		return irq->vcpu ? : irq->target_vcpu;

	/*
	 * If the IRQ is not active but enabled and pending, we should direct
	 * it to its configured target VCPU.
	 * If the distributor is disabled, pending interrupts shouldn't be
	 * forwarded.
	 */
	if (irq->enabled && irq_is_pending(irq)) {
		if (unlikely(irq->target_vcpu &&
			     !irq->target_vcpu->kvm->arch.vgic.enabled))
			return NULL;

		return irq->target_vcpu;
	}

	/* If neither active nor pending and enabled, then this IRQ should not
	 * be queued to any VCPU.
	 */
	return NULL;
}

/*
 * The order of items in the ap_lists defines how we'll pack things in LRs as
 * well, the first items in the list being the first things populated in the
 * LRs.
 *
 * A hard rule is that active interrupts can never be pushed out of the LRs
 * (and therefore take priority) since we cannot reliably trap on deactivation
 * of IRQs and therefore they have to be present in the LRs.
 *
 * Otherwise things should be sorted by the priority field and the GIC
 * hardware support will take care of preemption of priority groups etc.
 *
 * Return negative if "a" sorts before "b", 0 to preserve order, and positive
 * to sort "b" before "a".
 */
static int vgic_irq_cmp(void *priv, struct list_head *a, struct list_head *b)
{
	struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list);
	struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list);
	bool penda, pendb;
	int ret;

	spin_lock(&irqa->irq_lock);
	spin_lock_nested(&irqb->irq_lock, SINGLE_DEPTH_NESTING);

	if (irqa->active || irqb->active) {
		ret = (int)irqb->active - (int)irqa->active;
		goto out;
	}

	penda = irqa->enabled && irq_is_pending(irqa);
	pendb = irqb->enabled && irq_is_pending(irqb);

	if (!penda || !pendb) {
		ret = (int)pendb - (int)penda;
		goto out;
	}

	/* Both pending and enabled, sort by priority */
	ret = irqa->priority - irqb->priority;
out:
	spin_unlock(&irqb->irq_lock);
	spin_unlock(&irqa->irq_lock);
	return ret;
}

/* Must be called with the ap_list_lock held */
static void vgic_sort_ap_list(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));

	list_sort(NULL, &vgic_cpu->ap_list_head, vgic_irq_cmp);
}

/*
 * Only valid injection if changing level for level-triggered IRQs or for a
 * rising edge, and in-kernel connected IRQ lines can only be controlled by
 * their owner.
 */
static bool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owner)
{
	if (irq->owner != owner)
		return false;

	switch (irq->config) {
	case VGIC_CONFIG_LEVEL:
		return irq->line_level != level;
	case VGIC_CONFIG_EDGE:
		return level;
	}

	return false;
}

/*
 * Check whether an IRQ needs to (and can) be queued to a VCPU's ap list.
 * Do the queuing if necessary, taking the right locks in the right order.
 * Returns true when the IRQ was queued, false otherwise.
 *
 * Needs to be entered with the IRQ lock already held, but will return
 * with all locks dropped.
 */
bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq,
			   unsigned long flags)
{
	struct kvm_vcpu *vcpu;

	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));

retry:
	vcpu = vgic_target_oracle(irq);
	if (irq->vcpu || !vcpu) {
		/*
		 * If this IRQ is already on a VCPU's ap_list, then it
		 * cannot be moved or modified and there is no more work for
		 * us to do.
		 *
		 * Otherwise, if the irq is not pending and enabled, it does
		 * not need to be inserted into an ap_list and there is also
		 * no more work for us to do.
		 */
		spin_unlock_irqrestore(&irq->irq_lock, flags);

		/*
		 * We have to kick the VCPU here, because we could be
		 * queueing an edge-triggered interrupt for which we
		 * get no EOI maintenance interrupt. In that case,
		 * while the IRQ is already on the VCPU's AP list, the
		 * VCPU could have EOI'ed the original interrupt and
		 * won't see this one until it exits for some other
		 * reason.
		 */
		if (vcpu) {
			kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
			kvm_vcpu_kick(vcpu);
		}
		return false;
	}

	/*
	 * We must unlock the irq lock to take the ap_list_lock where
	 * we are going to insert this new pending interrupt.
	 */
	spin_unlock_irqrestore(&irq->irq_lock, flags);

	/* someone can do stuff here, which we re-check below */

	spin_lock_irqsave(&vcpu->arch.vgic_cpu.ap_list_lock, flags);
	spin_lock(&irq->irq_lock);

	/*
	 * Did something change behind our backs?
	 *
	 * There are two cases:
	 * 1) The irq lost its pending state or was disabled behind our
	 *    backs and/or it was queued to another VCPU's ap_list.
	 * 2) Someone changed the affinity on this irq behind our
	 *    backs and we are now holding the wrong ap_list_lock.
	 *
	 * In both cases, drop the locks and retry.
	 */

	if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) {
		spin_unlock(&irq->irq_lock);
		spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags);

		spin_lock_irqsave(&irq->irq_lock, flags);
		goto retry;
	}

	/*
	 * Grab a reference to the irq to reflect the fact that it is
	 * now in the ap_list.
	 */
	vgic_get_irq_kref(irq);
	list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head);
	irq->vcpu = vcpu;

	spin_unlock(&irq->irq_lock);
	spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock, flags);

	kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
	kvm_vcpu_kick(vcpu);

	return true;
}

/**
 * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic
 * @kvm:     The VM structure pointer
 * @cpuid:   The CPU for PPIs
 * @intid:   The INTID to inject a new state to.
 * @level:   Edge-triggered:  true:  to trigger the interrupt
 *			      false: to ignore the call
 *	     Level-sensitive  true:  raise the input signal
 *			      false: lower the input signal
 * @owner:   The opaque pointer to the owner of the IRQ being raised to verify
 *           that the caller is allowed to inject this IRQ.  Userspace
 *           injections will have owner == NULL.
 *
 * The VGIC is not concerned with devices being active-LOW or active-HIGH for
 * level-sensitive interrupts.  You can think of the level parameter as 1
 * being HIGH and 0 being LOW and all devices being active-HIGH.
 */
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int intid,
			bool level, void *owner)
{
	struct kvm_vcpu *vcpu;
	struct vgic_irq *irq;
	unsigned long flags;
	int ret;

	trace_vgic_update_irq_pending(cpuid, intid, level);

	ret = vgic_lazy_init(kvm);
	if (ret)
		return ret;

	vcpu = kvm_get_vcpu(kvm, cpuid);
	if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS)
		return -EINVAL;

	irq = vgic_get_irq(kvm, vcpu, intid);
	if (!irq)
		return -EINVAL;

	spin_lock_irqsave(&irq->irq_lock, flags);

	if (!vgic_validate_injection(irq, level, owner)) {
		/* Nothing to see here, move along... */
		spin_unlock_irqrestore(&irq->irq_lock, flags);
		vgic_put_irq(kvm, irq);
		return 0;
	}

	if (irq->config == VGIC_CONFIG_LEVEL)
		irq->line_level = level;
	else
		irq->pending_latch = true;

	vgic_queue_irq_unlock(kvm, irq, flags);
	vgic_put_irq(kvm, irq);

	return 0;
}

/* @irq->irq_lock must be held */
static int kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq,
			    unsigned int host_irq,
			    bool (*get_input_level)(int vindid))
{
	struct irq_desc *desc;
	struct irq_data *data;

	/*
	 * Find the physical IRQ number corresponding to @host_irq
	 */
	desc = irq_to_desc(host_irq);
	if (!desc) {
		kvm_err("%s: no interrupt descriptor\n", __func__);
		return -EINVAL;
	}
	data = irq_desc_get_irq_data(desc);
	while (data->parent_data)
		data = data->parent_data;

	irq->hw = true;
	irq->host_irq = host_irq;
	irq->hwintid = data->hwirq;
	irq->get_input_level = get_input_level;
	return 0;
}

/* @irq->irq_lock must be held */
static inline void kvm_vgic_unmap_irq(struct vgic_irq *irq)
{
	irq->hw = false;
	irq->hwintid = 0;
	irq->get_input_level = NULL;
}

int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq,
			  u32 vintid, bool (*get_input_level)(int vindid))
{
	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
	unsigned long flags;
	int ret;

	BUG_ON(!irq);

	spin_lock_irqsave(&irq->irq_lock, flags);
	ret = kvm_vgic_map_irq(vcpu, irq, host_irq, get_input_level);
	spin_unlock_irqrestore(&irq->irq_lock, flags);
	vgic_put_irq(vcpu->kvm, irq);

	return ret;
}

/**
 * kvm_vgic_reset_mapped_irq - Reset a mapped IRQ
 * @vcpu: The VCPU pointer
 * @vintid: The INTID of the interrupt
 *
 * Reset the active and pending states of a mapped interrupt.  Kernel
 * subsystems injecting mapped interrupts should reset their interrupt lines
 * when we are doing a reset of the VM.
 */
void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid)
{
	struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
	unsigned long flags;

	if (!irq->hw)
		goto out;

	spin_lock_irqsave(&irq->irq_lock, flags);
	irq->active = false;
	irq->pending_latch = false;
	irq->line_level = false;
	spin_unlock_irqrestore(&irq->irq_lock, flags);
out:
	vgic_put_irq(vcpu->kvm, irq);
}

int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid)
{
	struct vgic_irq *irq;
	unsigned long flags;

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

	irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
	BUG_ON(!irq);

	spin_lock_irqsave(&irq->irq_lock, flags);
	kvm_vgic_unmap_irq(irq);
	spin_unlock_irqrestore(&irq->irq_lock, flags);
	vgic_put_irq(vcpu->kvm, irq);

	return 0;
}

/**
 * kvm_vgic_set_owner - Set the owner of an interrupt for a VM
 *
 * @vcpu:   Pointer to the VCPU (used for PPIs)
 * @intid:  The virtual INTID identifying the interrupt (PPI or SPI)
 * @owner:  Opaque pointer to the owner
 *
 * Returns 0 if intid is not already used by another in-kernel device and the
 * owner is set, otherwise returns an error code.
 */
int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner)
{
	struct vgic_irq *irq;
	unsigned long flags;
	int ret = 0;

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

	/* SGIs and LPIs cannot be wired up to any device */
	if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid))
		return -EINVAL;

	irq = vgic_get_irq(vcpu->kvm, vcpu, intid);
	spin_lock_irqsave(&irq->irq_lock, flags);
	if (irq->owner && irq->owner != owner)
		ret = -EEXIST;
	else
		irq->owner = owner;
	spin_unlock_irqrestore(&irq->irq_lock, flags);

	return ret;
}

/**
 * vgic_prune_ap_list - Remove non-relevant interrupts from the list
 *
 * @vcpu: The VCPU pointer
 *
 * Go over the list of "interesting" interrupts, and prune those that we
 * won't have to consider in the near future.
 */
static void vgic_prune_ap_list(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_irq *irq, *tmp;
	unsigned long flags;

retry:
	spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);

	list_for_each_entry_safe(irq, tmp, &vgic_cpu->ap_list_head, ap_list) {
		struct kvm_vcpu *target_vcpu, *vcpuA, *vcpuB;

		spin_lock(&irq->irq_lock);

		BUG_ON(vcpu != irq->vcpu);

		target_vcpu = vgic_target_oracle(irq);

		if (!target_vcpu) {
			/*
			 * We don't need to process this interrupt any
			 * further, move it off the list.
			 */
			list_del(&irq->ap_list);
			irq->vcpu = NULL;
			spin_unlock(&irq->irq_lock);

			/*
			 * This vgic_put_irq call matches the
			 * vgic_get_irq_kref in vgic_queue_irq_unlock,
			 * where we added the LPI to the ap_list. As
			 * we remove the irq from the list, we drop
			 * also drop the refcount.
			 */
			vgic_put_irq(vcpu->kvm, irq);
			continue;
		}

		if (target_vcpu == vcpu) {
			/* We're on the right CPU */
			spin_unlock(&irq->irq_lock);
			continue;
		}

		/* This interrupt looks like it has to be migrated. */

		spin_unlock(&irq->irq_lock);
		spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);

		/*
		 * Ensure locking order by always locking the smallest
		 * ID first.
		 */
		if (vcpu->vcpu_id < target_vcpu->vcpu_id) {
			vcpuA = vcpu;
			vcpuB = target_vcpu;
		} else {
			vcpuA = target_vcpu;
			vcpuB = vcpu;
		}

		spin_lock_irqsave(&vcpuA->arch.vgic_cpu.ap_list_lock, flags);
		spin_lock_nested(&vcpuB->arch.vgic_cpu.ap_list_lock,
				 SINGLE_DEPTH_NESTING);
		spin_lock(&irq->irq_lock);

		/*
		 * If the affinity has been preserved, move the
		 * interrupt around. Otherwise, it means things have
		 * changed while the interrupt was unlocked, and we
		 * need to replay this.
		 *
		 * In all cases, we cannot trust the list not to have
		 * changed, so we restart from the beginning.
		 */
		if (target_vcpu == vgic_target_oracle(irq)) {
			struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu;

			list_del(&irq->ap_list);
			irq->vcpu = target_vcpu;
			list_add_tail(&irq->ap_list, &new_cpu->ap_list_head);
		}

		spin_unlock(&irq->irq_lock);
		spin_unlock(&vcpuB->arch.vgic_cpu.ap_list_lock);
		spin_unlock_irqrestore(&vcpuA->arch.vgic_cpu.ap_list_lock, flags);
		goto retry;
	}

	spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);
}

static inline void vgic_fold_lr_state(struct kvm_vcpu *vcpu)
{
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_fold_lr_state(vcpu);
	else
		vgic_v3_fold_lr_state(vcpu);
}

/* Requires the irq_lock to be held. */
static inline void vgic_populate_lr(struct kvm_vcpu *vcpu,
				    struct vgic_irq *irq, int lr)
{
	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&irq->irq_lock));

	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_populate_lr(vcpu, irq, lr);
	else
		vgic_v3_populate_lr(vcpu, irq, lr);
}

static inline void vgic_clear_lr(struct kvm_vcpu *vcpu, int lr)
{
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_clear_lr(vcpu, lr);
	else
		vgic_v3_clear_lr(vcpu, lr);
}

static inline void vgic_set_underflow(struct kvm_vcpu *vcpu)
{
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_set_underflow(vcpu);
	else
		vgic_v3_set_underflow(vcpu);
}

static inline void vgic_set_npie(struct kvm_vcpu *vcpu)
{
	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_set_npie(vcpu);
	else
		vgic_v3_set_npie(vcpu);
}

/* Requires the ap_list_lock to be held. */
static int compute_ap_list_depth(struct kvm_vcpu *vcpu,
				 bool *multi_sgi)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_irq *irq;
	int count = 0;

	*multi_sgi = false;

	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));

	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
		spin_lock(&irq->irq_lock);
		/* GICv2 SGIs can count for more than one... */
		if (vgic_irq_is_sgi(irq->intid) && irq->source) {
			int w = hweight8(irq->source);

			count += w;
			*multi_sgi |= (w > 1);
		} else {
			count++;
		}
		spin_unlock(&irq->irq_lock);
	}
	return count;
}

/* Requires the VCPU's ap_list_lock to be held. */
static void vgic_flush_lr_state(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_irq *irq;
	int count;
	bool npie = false;
	bool multi_sgi;
	u8 prio = 0xff;

	DEBUG_SPINLOCK_BUG_ON(!spin_is_locked(&vgic_cpu->ap_list_lock));

	count = compute_ap_list_depth(vcpu, &multi_sgi);
	if (count > kvm_vgic_global_state.nr_lr || multi_sgi)
		vgic_sort_ap_list(vcpu);

	count = 0;

	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
		spin_lock(&irq->irq_lock);

		/*
		 * If we have multi-SGIs in the pipeline, we need to
		 * guarantee that they are all seen before any IRQ of
		 * lower priority. In that case, we need to filter out
		 * these interrupts by exiting early. This is easy as
		 * the AP list has been sorted already.
		 */
		if (multi_sgi && irq->priority > prio) {
			spin_unlock(&irq->irq_lock);
			break;
		}

		if (likely(vgic_target_oracle(irq) == vcpu)) {
			vgic_populate_lr(vcpu, irq, count++);

			if (irq->source) {
				npie = true;
				prio = irq->priority;
			}
		}

		spin_unlock(&irq->irq_lock);

		if (count == kvm_vgic_global_state.nr_lr) {
			if (!list_is_last(&irq->ap_list,
					  &vgic_cpu->ap_list_head))
				vgic_set_underflow(vcpu);
			break;
		}
	}

	if (npie)
		vgic_set_npie(vcpu);

	vcpu->arch.vgic_cpu.used_lrs = count;

	/* Nuke remaining LRs */
	for ( ; count < kvm_vgic_global_state.nr_lr; count++)
		vgic_clear_lr(vcpu, count);
}

/* Sync back the hardware VGIC state into our emulation after a guest's run. */
void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;

	WARN_ON(vgic_v4_sync_hwstate(vcpu));

	/* An empty ap_list_head implies used_lrs == 0 */
	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
		return;

	if (vgic_cpu->used_lrs)
		vgic_fold_lr_state(vcpu);
	vgic_prune_ap_list(vcpu);
}

/* Flush our emulation state into the GIC hardware before entering the guest. */
void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
{
	WARN_ON(vgic_v4_flush_hwstate(vcpu));

	/*
	 * If there are no virtual interrupts active or pending for this
	 * VCPU, then there is no work to do and we can bail out without
	 * taking any lock.  There is a potential race with someone injecting
	 * interrupts to the VCPU, but it is a benign race as the VCPU will
	 * either observe the new interrupt before or after doing this check,
	 * and introducing additional synchronization mechanism doesn't change
	 * this.
	 */
	if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head))
		return;

	DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());

	spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
	vgic_flush_lr_state(vcpu);
	spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
}

void kvm_vgic_load(struct kvm_vcpu *vcpu)
{
	if (unlikely(!vgic_initialized(vcpu->kvm)))
		return;

	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_load(vcpu);
	else
		vgic_v3_load(vcpu);
}

void kvm_vgic_put(struct kvm_vcpu *vcpu)
{
	if (unlikely(!vgic_initialized(vcpu->kvm)))
		return;

	if (kvm_vgic_global_state.type == VGIC_V2)
		vgic_v2_put(vcpu);
	else
		vgic_v3_put(vcpu);
}

int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu)
{
	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
	struct vgic_irq *irq;
	bool pending = false;
	unsigned long flags;

	if (!vcpu->kvm->arch.vgic.enabled)
		return false;

	if (vcpu->arch.vgic_cpu.vgic_v3.its_vpe.pending_last)
		return true;

	spin_lock_irqsave(&vgic_cpu->ap_list_lock, flags);

	list_for_each_entry(irq, &vgic_cpu->ap_list_head, ap_list) {
		spin_lock(&irq->irq_lock);
		pending = irq_is_pending(irq) && irq->enabled;
		spin_unlock(&irq->irq_lock);

		if (pending)
			break;
	}

	spin_unlock_irqrestore(&vgic_cpu->ap_list_lock, flags);

	return pending;
}

void vgic_kick_vcpus(struct kvm *kvm)
{
	struct kvm_vcpu *vcpu;
	int c;

	/*
	 * We've injected an interrupt, time to find out who deserves
	 * a good kick...
	 */
	kvm_for_each_vcpu(c, vcpu, kvm) {
		if (kvm_vgic_vcpu_pending_irq(vcpu)) {
			kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
			kvm_vcpu_kick(vcpu);
		}
	}
}

bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid)
{
	struct vgic_irq *irq;
	bool map_is_active;
	unsigned long flags;

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

	irq = vgic_get_irq(vcpu->kvm, vcpu, vintid);
	spin_lock_irqsave(&irq->irq_lock, flags);
	map_is_active = irq->hw && irq->active;
	spin_unlock_irqrestore(&irq->irq_lock, flags);
	vgic_put_irq(vcpu->kvm, irq);

	return map_is_active;
}