Home Home > GIT Browse
summaryrefslogtreecommitdiff
blob: b20b751286fc612214c59c95e787c9fb0fac50b7 (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
/*
 * kvm eventfd support - use eventfd objects to signal various KVM events
 *
 * Copyright 2009 Novell.  All Rights Reserved.
 * Copyright 2010 Red Hat, Inc. and/or its affiliates.
 *
 * Author:
 *	Gregory Haskins <ghaskins@novell.com>
 *
 * This file is free software; you can redistribute it and/or modify
 * it under the terms of version 2 of the GNU General Public License
 * 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
 */

#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/kvm_irqfd.h>
#include <linux/workqueue.h>
#include <linux/syscalls.h>
#include <linux/wait.h>
#include <linux/poll.h>
#include <linux/file.h>
#include <linux/list.h>
#include <linux/eventfd.h>
#include <linux/kernel.h>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/seqlock.h>
#include <linux/irqbypass.h>
#include <trace/events/kvm.h>

#include <kvm/iodev.h>

#ifdef CONFIG_HAVE_KVM_IRQFD

static struct workqueue_struct *irqfd_cleanup_wq;

static void
irqfd_inject(struct work_struct *work)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(work, struct kvm_kernel_irqfd, inject);
	struct kvm *kvm = irqfd->kvm;

	if (!irqfd->resampler) {
		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1,
				false);
		kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0,
				false);
	} else
		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
			    irqfd->gsi, 1, false);
}

/*
 * Since resampler irqfds share an IRQ source ID, we de-assert once
 * then notify all of the resampler irqfds using this GSI.  We can't
 * do multiple de-asserts or we risk racing with incoming re-asserts.
 */
static void
irqfd_resampler_ack(struct kvm_irq_ack_notifier *kian)
{
	struct kvm_kernel_irqfd_resampler *resampler;
	struct kvm *kvm;
	struct kvm_kernel_irqfd *irqfd;
	int idx;

	resampler = container_of(kian,
			struct kvm_kernel_irqfd_resampler, notifier);
	kvm = resampler->kvm;

	kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
		    resampler->notifier.gsi, 0, false);

	idx = srcu_read_lock(&kvm->irq_srcu);

	list_for_each_entry_rcu(irqfd, &resampler->list, resampler_link)
		eventfd_signal(irqfd->resamplefd, 1);

	srcu_read_unlock(&kvm->irq_srcu, idx);
}

static void
irqfd_resampler_shutdown(struct kvm_kernel_irqfd *irqfd)
{
	struct kvm_kernel_irqfd_resampler *resampler = irqfd->resampler;
	struct kvm *kvm = resampler->kvm;

	mutex_lock(&kvm->irqfds.resampler_lock);

	list_del_rcu(&irqfd->resampler_link);
	synchronize_srcu(&kvm->irq_srcu);

	if (list_empty(&resampler->list)) {
		list_del(&resampler->link);
		kvm_unregister_irq_ack_notifier(kvm, &resampler->notifier);
		kvm_set_irq(kvm, KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
			    resampler->notifier.gsi, 0, false);
		kfree(resampler);
	}

	mutex_unlock(&kvm->irqfds.resampler_lock);
}

/*
 * Race-free decouple logic (ordering is critical)
 */
static void
irqfd_shutdown(struct work_struct *work)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(work, struct kvm_kernel_irqfd, shutdown);
	struct kvm *kvm = irqfd->kvm;
	u64 cnt;

	/* Make sure irqfd has been initalized in assign path. */
	synchronize_srcu(&kvm->irq_srcu);

	/*
	 * Synchronize with the wait-queue and unhook ourselves to prevent
	 * further events.
	 */
	eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt);

	/*
	 * We know no new events will be scheduled at this point, so block
	 * until all previously outstanding events have completed
	 */
	flush_work(&irqfd->inject);

	if (irqfd->resampler) {
		irqfd_resampler_shutdown(irqfd);
		eventfd_ctx_put(irqfd->resamplefd);
	}

	/*
	 * It is now safe to release the object's resources
	 */
#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
	irq_bypass_unregister_consumer(&irqfd->consumer);
#endif
	eventfd_ctx_put(irqfd->eventfd);
	kfree(irqfd);
}


/* assumes kvm->irqfds.lock is held */
static bool
irqfd_is_active(struct kvm_kernel_irqfd *irqfd)
{
	return list_empty(&irqfd->list) ? false : true;
}

/*
 * Mark the irqfd as inactive and schedule it for removal
 *
 * assumes kvm->irqfds.lock is held
 */
static void
irqfd_deactivate(struct kvm_kernel_irqfd *irqfd)
{
	BUG_ON(!irqfd_is_active(irqfd));

	list_del_init(&irqfd->list);

	queue_work(irqfd_cleanup_wq, &irqfd->shutdown);
}

int __attribute__((weak)) kvm_arch_set_irq_inatomic(
				struct kvm_kernel_irq_routing_entry *irq,
				struct kvm *kvm, int irq_source_id,
				int level,
				bool line_status)
{
	return -EWOULDBLOCK;
}

/*
 * Called with wqh->lock held and interrupts disabled
 */
static int
irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(wait, struct kvm_kernel_irqfd, wait);
	__poll_t flags = key_to_poll(key);
	struct kvm_kernel_irq_routing_entry irq;
	struct kvm *kvm = irqfd->kvm;
	unsigned seq;
	int idx;

	if (flags & EPOLLIN) {
		idx = srcu_read_lock(&kvm->irq_srcu);
		do {
			seq = read_seqcount_begin(&irqfd->irq_entry_sc);
			irq = irqfd->irq_entry;
		} while (read_seqcount_retry(&irqfd->irq_entry_sc, seq));
		/* An event has been signaled, inject an interrupt */
		if (kvm_arch_set_irq_inatomic(&irq, kvm,
					      KVM_USERSPACE_IRQ_SOURCE_ID, 1,
					      false) == -EWOULDBLOCK)
			schedule_work(&irqfd->inject);
		srcu_read_unlock(&kvm->irq_srcu, idx);
	}

	if (flags & EPOLLHUP) {
		/* The eventfd is closing, detach from KVM */
		unsigned long flags;

		spin_lock_irqsave(&kvm->irqfds.lock, flags);

		/*
		 * We must check if someone deactivated the irqfd before
		 * we could acquire the irqfds.lock since the item is
		 * deactivated from the KVM side before it is unhooked from
		 * the wait-queue.  If it is already deactivated, we can
		 * simply return knowing the other side will cleanup for us.
		 * We cannot race against the irqfd going away since the
		 * other side is required to acquire wqh->lock, which we hold
		 */
		if (irqfd_is_active(irqfd))
			irqfd_deactivate(irqfd);

		spin_unlock_irqrestore(&kvm->irqfds.lock, flags);
	}

	return 0;
}

static void
irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
			poll_table *pt)
{
	struct kvm_kernel_irqfd *irqfd =
		container_of(pt, struct kvm_kernel_irqfd, pt);
	add_wait_queue(wqh, &irqfd->wait);
}

/* Must be called under irqfds.lock */
static void irqfd_update(struct kvm *kvm, struct kvm_kernel_irqfd *irqfd)
{
	struct kvm_kernel_irq_routing_entry *e;
	struct kvm_kernel_irq_routing_entry entries[KVM_NR_IRQCHIPS];
	int n_entries;

	n_entries = kvm_irq_map_gsi(kvm, entries, irqfd->gsi);

	write_seqcount_begin(&irqfd->irq_entry_sc);

	e = entries;
	if (n_entries == 1)
		irqfd->irq_entry = *e;
	else
		irqfd->irq_entry.type = 0;

	write_seqcount_end(&irqfd->irq_entry_sc);
}

#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
void __attribute__((weak)) kvm_arch_irq_bypass_stop(
				struct irq_bypass_consumer *cons)
{
}

void __attribute__((weak)) kvm_arch_irq_bypass_start(
				struct irq_bypass_consumer *cons)
{
}

int  __attribute__((weak)) kvm_arch_update_irqfd_routing(
				struct kvm *kvm, unsigned int host_irq,
				uint32_t guest_irq, bool set)
{
	return 0;
}
#endif

static int
kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
{
	struct kvm_kernel_irqfd *irqfd, *tmp;
	struct fd f;
	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
	int ret;
	__poll_t events;
	int idx;

	if (!kvm_arch_intc_initialized(kvm))
		return -EAGAIN;

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

	irqfd->kvm = kvm;
	irqfd->gsi = args->gsi;
	INIT_LIST_HEAD(&irqfd->list);
	INIT_WORK(&irqfd->inject, irqfd_inject);
	INIT_WORK(&irqfd->shutdown, irqfd_shutdown);
	seqcount_init(&irqfd->irq_entry_sc);

	f = fdget(args->fd);
	if (!f.file) {
		ret = -EBADF;
		goto out;
	}

	eventfd = eventfd_ctx_fileget(f.file);
	if (IS_ERR(eventfd)) {
		ret = PTR_ERR(eventfd);
		goto fail;
	}

	irqfd->eventfd = eventfd;

	if (args->flags & KVM_IRQFD_FLAG_RESAMPLE) {
		struct kvm_kernel_irqfd_resampler *resampler;

		resamplefd = eventfd_ctx_fdget(args->resamplefd);
		if (IS_ERR(resamplefd)) {
			ret = PTR_ERR(resamplefd);
			goto fail;
		}

		irqfd->resamplefd = resamplefd;
		INIT_LIST_HEAD(&irqfd->resampler_link);

		mutex_lock(&kvm->irqfds.resampler_lock);

		list_for_each_entry(resampler,
				    &kvm->irqfds.resampler_list, link) {
			if (resampler->notifier.gsi == irqfd->gsi) {
				irqfd->resampler = resampler;
				break;
			}
		}

		if (!irqfd->resampler) {
			resampler = kzalloc(sizeof(*resampler), GFP_KERNEL);
			if (!resampler) {
				ret = -ENOMEM;
				mutex_unlock(&kvm->irqfds.resampler_lock);
				goto fail;
			}

			resampler->kvm = kvm;
			INIT_LIST_HEAD(&resampler->list);
			resampler->notifier.gsi = irqfd->gsi;
			resampler->notifier.irq_acked = irqfd_resampler_ack;
			INIT_LIST_HEAD(&resampler->link);

			list_add(&resampler->link, &kvm->irqfds.resampler_list);
			kvm_register_irq_ack_notifier(kvm,
						      &resampler->notifier);
			irqfd->resampler = resampler;
		}

		list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list);
		synchronize_srcu(&kvm->irq_srcu);

		mutex_unlock(&kvm->irqfds.resampler_lock);
	}

	/*
	 * Install our own custom wake-up handling so we are notified via
	 * a callback whenever someone signals the underlying eventfd
	 */
	init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
	init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);

	spin_lock_irq(&kvm->irqfds.lock);

	ret = 0;
	list_for_each_entry(tmp, &kvm->irqfds.items, list) {
		if (irqfd->eventfd != tmp->eventfd)
			continue;
		/* This fd is used for another irq already. */
		ret = -EBUSY;
		spin_unlock_irq(&kvm->irqfds.lock);
		goto fail;
	}

	idx = srcu_read_lock(&kvm->irq_srcu);
	irqfd_update(kvm, irqfd);

	list_add_tail(&irqfd->list, &kvm->irqfds.items);

	spin_unlock_irq(&kvm->irqfds.lock);

	/*
	 * Check if there was an event already pending on the eventfd
	 * before we registered, and trigger it as if we didn't miss it.
	 */
	events = vfs_poll(f.file, &irqfd->pt);

	if (events & EPOLLIN)
		schedule_work(&irqfd->inject);

#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
	if (kvm_arch_has_irq_bypass()) {
		irqfd->consumer.token = (void *)irqfd->eventfd;
		irqfd->consumer.add_producer = kvm_arch_irq_bypass_add_producer;
		irqfd->consumer.del_producer = kvm_arch_irq_bypass_del_producer;
		irqfd->consumer.stop = kvm_arch_irq_bypass_stop;
		irqfd->consumer.start = kvm_arch_irq_bypass_start;
		ret = irq_bypass_register_consumer(&irqfd->consumer);
		if (ret)
			pr_info("irq bypass consumer (token %p) registration fails: %d\n",
				irqfd->consumer.token, ret);
	}
#endif

	srcu_read_unlock(&kvm->irq_srcu, idx);

	/*
	 * do not drop the file until the irqfd is fully initialized, otherwise
	 * we might race against the EPOLLHUP
	 */
	fdput(f);
	return 0;

fail:
	if (irqfd->resampler)
		irqfd_resampler_shutdown(irqfd);

	if (resamplefd && !IS_ERR(resamplefd))
		eventfd_ctx_put(resamplefd);

	if (eventfd && !IS_ERR(eventfd))
		eventfd_ctx_put(eventfd);

	fdput(f);

out:
	kfree(irqfd);
	return ret;
}

bool kvm_irq_has_notifier(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
	struct kvm_irq_ack_notifier *kian;
	int gsi, idx;

	idx = srcu_read_lock(&kvm->irq_srcu);
	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
	if (gsi != -1)
		hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
					 link)
			if (kian->gsi == gsi) {
				srcu_read_unlock(&kvm->irq_srcu, idx);
				return true;
			}

	srcu_read_unlock(&kvm->irq_srcu, idx);

	return false;
}
EXPORT_SYMBOL_GPL(kvm_irq_has_notifier);

void kvm_notify_acked_gsi(struct kvm *kvm, int gsi)
{
	struct kvm_irq_ack_notifier *kian;

	hlist_for_each_entry_rcu(kian, &kvm->irq_ack_notifier_list,
				 link)
		if (kian->gsi == gsi)
			kian->irq_acked(kian);
}

void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
{
	int gsi, idx;

	trace_kvm_ack_irq(irqchip, pin);

	idx = srcu_read_lock(&kvm->irq_srcu);
	gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
	if (gsi != -1)
		kvm_notify_acked_gsi(kvm, gsi);
	srcu_read_unlock(&kvm->irq_srcu, idx);
}

void kvm_register_irq_ack_notifier(struct kvm *kvm,
				   struct kvm_irq_ack_notifier *kian)
{
	mutex_lock(&kvm->irq_lock);
	hlist_add_head_rcu(&kian->link, &kvm->irq_ack_notifier_list);
	mutex_unlock(&kvm->irq_lock);
	kvm_arch_post_irq_ack_notifier_list_update(kvm);
}

void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
				    struct kvm_irq_ack_notifier *kian)
{
	mutex_lock(&kvm->irq_lock);
	hlist_del_init_rcu(&kian->link);
	mutex_unlock(&kvm->irq_lock);
	synchronize_srcu(&kvm->irq_srcu);
	kvm_arch_post_irq_ack_notifier_list_update(kvm);
}
#endif

void
kvm_eventfd_init(struct kvm *kvm)
{
#ifdef CONFIG_HAVE_KVM_IRQFD
	spin_lock_init(&kvm->irqfds.lock);
	INIT_LIST_HEAD(&kvm->irqfds.items);
	INIT_LIST_HEAD(&kvm->irqfds.resampler_list);
	mutex_init(&kvm->irqfds.resampler_lock);
#endif
	INIT_LIST_HEAD(&kvm->ioeventfds);
}

#ifdef CONFIG_HAVE_KVM_IRQFD
/*
 * shutdown any irqfd's that match fd+gsi
 */
static int
kvm_irqfd_deassign(struct kvm *kvm, struct kvm_irqfd *args)
{
	struct kvm_kernel_irqfd *irqfd, *tmp;
	struct eventfd_ctx *eventfd;

	eventfd = eventfd_ctx_fdget(args->fd);
	if (IS_ERR(eventfd))
		return PTR_ERR(eventfd);

	spin_lock_irq(&kvm->irqfds.lock);

	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list) {
		if (irqfd->eventfd == eventfd && irqfd->gsi == args->gsi) {
			/*
			 * This clearing of irq_entry.type is needed for when
			 * another thread calls kvm_irq_routing_update before
			 * we flush workqueue below (we synchronize with
			 * kvm_irq_routing_update using irqfds.lock).
			 */
			write_seqcount_begin(&irqfd->irq_entry_sc);
			irqfd->irq_entry.type = 0;
			write_seqcount_end(&irqfd->irq_entry_sc);
			irqfd_deactivate(irqfd);
		}
	}

	spin_unlock_irq(&kvm->irqfds.lock);
	eventfd_ctx_put(eventfd);

	/*
	 * Block until we know all outstanding shutdown jobs have completed
	 * so that we guarantee there will not be any more interrupts on this
	 * gsi once this deassign function returns.
	 */
	flush_workqueue(irqfd_cleanup_wq);

	return 0;
}

int
kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
{
	if (args->flags & ~(KVM_IRQFD_FLAG_DEASSIGN | KVM_IRQFD_FLAG_RESAMPLE))
		return -EINVAL;

	if (args->flags & KVM_IRQFD_FLAG_DEASSIGN)
		return kvm_irqfd_deassign(kvm, args);

	return kvm_irqfd_assign(kvm, args);
}

/*
 * This function is called as the kvm VM fd is being released. Shutdown all
 * irqfds that still remain open
 */
void
kvm_irqfd_release(struct kvm *kvm)
{
	struct kvm_kernel_irqfd *irqfd, *tmp;

	spin_lock_irq(&kvm->irqfds.lock);

	list_for_each_entry_safe(irqfd, tmp, &kvm->irqfds.items, list)
		irqfd_deactivate(irqfd);

	spin_unlock_irq(&kvm->irqfds.lock);

	/*
	 * Block until we know all outstanding shutdown jobs have completed
	 * since we do not take a kvm* reference.
	 */
	flush_workqueue(irqfd_cleanup_wq);

}

/*
 * Take note of a change in irq routing.
 * Caller must invoke synchronize_srcu(&kvm->irq_srcu) afterwards.
 */
void kvm_irq_routing_update(struct kvm *kvm)
{
	struct kvm_kernel_irqfd *irqfd;

	spin_lock_irq(&kvm->irqfds.lock);

	list_for_each_entry(irqfd, &kvm->irqfds.items, list) {
		irqfd_update(kvm, irqfd);

#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
		if (irqfd->producer) {
			int ret = kvm_arch_update_irqfd_routing(
					irqfd->kvm, irqfd->producer->irq,
					irqfd->gsi, 1);
			WARN_ON(ret);
		}
#endif
	}

	spin_unlock_irq(&kvm->irqfds.lock);
}

/*
 * create a host-wide workqueue for issuing deferred shutdown requests
 * aggregated from all vm* instances. We need our own isolated
 * queue to ease flushing work items when a VM exits.
 */
int kvm_irqfd_init(void)
{
	irqfd_cleanup_wq = alloc_workqueue("kvm-irqfd-cleanup", 0, 0);
	if (!irqfd_cleanup_wq)
		return -ENOMEM;

	return 0;
}

void kvm_irqfd_exit(void)
{
	destroy_workqueue(irqfd_cleanup_wq);
}
#endif

/*
 * --------------------------------------------------------------------
 * ioeventfd: translate a PIO/MMIO memory write to an eventfd signal.
 *
 * userspace can register a PIO/MMIO address with an eventfd for receiving
 * notification when the memory has been touched.
 * --------------------------------------------------------------------
 */

struct _ioeventfd {
	struct list_head     list;
	u64                  addr;
	int                  length;
	struct eventfd_ctx  *eventfd;
	u64                  datamatch;
	struct kvm_io_device dev;
	u8                   bus_idx;
	bool                 wildcard;
};

static inline struct _ioeventfd *
to_ioeventfd(struct kvm_io_device *dev)
{
	return container_of(dev, struct _ioeventfd, dev);
}

static void
ioeventfd_release(struct _ioeventfd *p)
{
	eventfd_ctx_put(p->eventfd);
	list_del(&p->list);
	kfree(p);
}

static bool
ioeventfd_in_range(struct _ioeventfd *p, gpa_t addr, int len, const void *val)
{
	u64 _val;

	if (addr != p->addr)
		/* address must be precise for a hit */
		return false;

	if (!p->length)
		/* length = 0 means only look at the address, so always a hit */
		return true;

	if (len != p->length)
		/* address-range must be precise for a hit */
		return false;

	if (p->wildcard)
		/* all else equal, wildcard is always a hit */
		return true;

	/* otherwise, we have to actually compare the data */

	BUG_ON(!IS_ALIGNED((unsigned long)val, len));

	switch (len) {
	case 1:
		_val = *(u8 *)val;
		break;
	case 2:
		_val = *(u16 *)val;
		break;
	case 4:
		_val = *(u32 *)val;
		break;
	case 8:
		_val = *(u64 *)val;
		break;
	default:
		return false;
	}

	return _val == p->datamatch ? true : false;
}

/* MMIO/PIO writes trigger an event if the addr/val match */
static int
ioeventfd_write(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr,
		int len, const void *val)
{
	struct _ioeventfd *p = to_ioeventfd(this);

	if (!ioeventfd_in_range(p, addr, len, val))
		return -EOPNOTSUPP;

	eventfd_signal(p->eventfd, 1);
	return 0;
}

/*
 * This function is called as KVM is completely shutting down.  We do not
 * need to worry about locking just nuke anything we have as quickly as possible
 */
static void
ioeventfd_destructor(struct kvm_io_device *this)
{
	struct _ioeventfd *p = to_ioeventfd(this);

	ioeventfd_release(p);
}

static const struct kvm_io_device_ops ioeventfd_ops = {
	.write      = ioeventfd_write,
	.destructor = ioeventfd_destructor,
};

/* assumes kvm->slots_lock held */
static bool
ioeventfd_check_collision(struct kvm *kvm, struct _ioeventfd *p)
{
	struct _ioeventfd *_p;

	list_for_each_entry(_p, &kvm->ioeventfds, list)
		if (_p->bus_idx == p->bus_idx &&
		    _p->addr == p->addr &&
		    (!_p->length || !p->length ||
		     (_p->length == p->length &&
		      (_p->wildcard || p->wildcard ||
		       _p->datamatch == p->datamatch))))
			return true;

	return false;
}

static enum kvm_bus ioeventfd_bus_from_flags(__u32 flags)
{
	if (flags & KVM_IOEVENTFD_FLAG_PIO)
		return KVM_PIO_BUS;
	if (flags & KVM_IOEVENTFD_FLAG_VIRTIO_CCW_NOTIFY)
		return KVM_VIRTIO_CCW_NOTIFY_BUS;
	return KVM_MMIO_BUS;
}

static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
				enum kvm_bus bus_idx,
				struct kvm_ioeventfd *args)
{

	struct eventfd_ctx *eventfd;
	struct _ioeventfd *p;
	int ret;

	eventfd = eventfd_ctx_fdget(args->fd);
	if (IS_ERR(eventfd))
		return PTR_ERR(eventfd);

	p = kzalloc(sizeof(*p), GFP_KERNEL);
	if (!p) {
		ret = -ENOMEM;
		goto fail;
	}

	INIT_LIST_HEAD(&p->list);
	p->addr    = args->addr;
	p->bus_idx = bus_idx;
	p->length  = args->len;
	p->eventfd = eventfd;

	/* The datamatch feature is optional, otherwise this is a wildcard */
	if (args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH)
		p->datamatch = args->datamatch;
	else
		p->wildcard = true;

	mutex_lock(&kvm->slots_lock);

	/* Verify that there isn't a match already */
	if (ioeventfd_check_collision(kvm, p)) {
		ret = -EEXIST;
		goto unlock_fail;
	}

	kvm_iodevice_init(&p->dev, &ioeventfd_ops);

	ret = kvm_io_bus_register_dev(kvm, bus_idx, p->addr, p->length,
				      &p->dev);
	if (ret < 0)
		goto unlock_fail;

	kvm_get_bus(kvm, bus_idx)->ioeventfd_count++;
	list_add_tail(&p->list, &kvm->ioeventfds);

	mutex_unlock(&kvm->slots_lock);

	return 0;

unlock_fail:
	mutex_unlock(&kvm->slots_lock);

fail:
	kfree(p);
	eventfd_ctx_put(eventfd);

	return ret;
}

static int
kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
			   struct kvm_ioeventfd *args)
{
	struct _ioeventfd        *p, *tmp;
	struct eventfd_ctx       *eventfd;
	struct kvm_io_bus	 *bus;
	int                       ret = -ENOENT;

	eventfd = eventfd_ctx_fdget(args->fd);
	if (IS_ERR(eventfd))
		return PTR_ERR(eventfd);

	mutex_lock(&kvm->slots_lock);

	list_for_each_entry_safe(p, tmp, &kvm->ioeventfds, list) {
		bool wildcard = !(args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH);

		if (p->bus_idx != bus_idx ||
		    p->eventfd != eventfd  ||
		    p->addr != args->addr  ||
		    p->length != args->len ||
		    p->wildcard != wildcard)
			continue;

		if (!p->wildcard && p->datamatch != args->datamatch)
			continue;

		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
		bus = kvm_get_bus(kvm, bus_idx);
		if (bus)
			bus->ioeventfd_count--;
		ioeventfd_release(p);
		ret = 0;
		break;
	}

	mutex_unlock(&kvm->slots_lock);

	eventfd_ctx_put(eventfd);

	return ret;
}

static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
{
	enum kvm_bus bus_idx = ioeventfd_bus_from_flags(args->flags);
	int ret = kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);

	if (!args->len && bus_idx == KVM_MMIO_BUS)
		kvm_deassign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);

	return ret;
}

static int
kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
{
	enum kvm_bus              bus_idx;
	int ret;

	bus_idx = ioeventfd_bus_from_flags(args->flags);
	/* must be natural-word sized, or 0 to ignore length */
	switch (args->len) {
	case 0:
	case 1:
	case 2:
	case 4:
	case 8:
		break;
	default:
		return -EINVAL;
	}

	/* check for range overflow */
	if (args->addr + args->len < args->addr)
		return -EINVAL;

	/* check for extra flags that we don't understand */
	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
		return -EINVAL;

	/* ioeventfd with no length can't be combined with DATAMATCH */
	if (!args->len && (args->flags & KVM_IOEVENTFD_FLAG_DATAMATCH))
		return -EINVAL;

	ret = kvm_assign_ioeventfd_idx(kvm, bus_idx, args);
	if (ret)
		goto fail;

	/* When length is ignored, MMIO is also put on a separate bus, for
	 * faster lookups.
	 */
	if (!args->len && bus_idx == KVM_MMIO_BUS) {
		ret = kvm_assign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
		if (ret < 0)
			goto fast_fail;
	}

	return 0;

fast_fail:
	kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
fail:
	return ret;
}

int
kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
{
	if (args->flags & KVM_IOEVENTFD_FLAG_DEASSIGN)
		return kvm_deassign_ioeventfd(kvm, args);

	return kvm_assign_ioeventfd(kvm, args);
}