summaryrefslogtreecommitdiffstats
path: root/drivers/vfio/pci/vfio_pci_intrs.c
blob: cbb4bcbfbf83d98ec3e9c3a44a120c9fb74623f2 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * VFIO PCI interrupt handling
 *
 * Copyright (C) 2012 Red Hat, Inc.  All rights reserved.
 *     Author: Alex Williamson <alex.williamson@redhat.com>
 *
 * Derived from original vfio:
 * Copyright 2010 Cisco Systems, Inc.  All rights reserved.
 * Author: Tom Lyon, pugs@cisco.com
 */

#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/eventfd.h>
#include <linux/msi.h>
#include <linux/pci.h>
#include <linux/file.h>
#include <linux/vfio.h>
#include <linux/wait.h>
#include <linux/slab.h>

#include "vfio_pci_priv.h"

struct vfio_pci_irq_ctx {
	struct eventfd_ctx	*trigger;
	struct virqfd		*unmask;
	struct virqfd		*mask;
	char			*name;
	bool			masked;
	struct irq_bypass_producer	producer;
};

static bool irq_is(struct vfio_pci_core_device *vdev, int type)
{
	return vdev->irq_type == type;
}

static bool is_intx(struct vfio_pci_core_device *vdev)
{
	return vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX;
}

static bool is_irq_none(struct vfio_pci_core_device *vdev)
{
	return !(vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX ||
		 vdev->irq_type == VFIO_PCI_MSI_IRQ_INDEX ||
		 vdev->irq_type == VFIO_PCI_MSIX_IRQ_INDEX);
}

static
struct vfio_pci_irq_ctx *vfio_irq_ctx_get(struct vfio_pci_core_device *vdev,
					  unsigned long index)
{
	return xa_load(&vdev->ctx, index);
}

static void vfio_irq_ctx_free(struct vfio_pci_core_device *vdev,
			      struct vfio_pci_irq_ctx *ctx, unsigned long index)
{
	xa_erase(&vdev->ctx, index);
	kfree(ctx);
}

static struct vfio_pci_irq_ctx *
vfio_irq_ctx_alloc(struct vfio_pci_core_device *vdev, unsigned long index)
{
	struct vfio_pci_irq_ctx *ctx;
	int ret;

	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT);
	if (!ctx)
		return NULL;

	ret = xa_insert(&vdev->ctx, index, ctx, GFP_KERNEL_ACCOUNT);
	if (ret) {
		kfree(ctx);
		return NULL;
	}

	return ctx;
}

/*
 * INTx
 */
static void vfio_send_intx_eventfd(void *opaque, void *unused)
{
	struct vfio_pci_core_device *vdev = opaque;

	if (likely(is_intx(vdev) && !vdev->virq_disabled)) {
		struct vfio_pci_irq_ctx *ctx;

		ctx = vfio_irq_ctx_get(vdev, 0);
		if (WARN_ON_ONCE(!ctx))
			return;
		eventfd_signal(ctx->trigger, 1);
	}
}

/* Returns true if the INTx vfio_pci_irq_ctx.masked value is changed. */
bool vfio_pci_intx_mask(struct vfio_pci_core_device *vdev)
{
	struct pci_dev *pdev = vdev->pdev;
	struct vfio_pci_irq_ctx *ctx;
	unsigned long flags;
	bool masked_changed = false;

	spin_lock_irqsave(&vdev->irqlock, flags);

	/*
	 * Masking can come from interrupt, ioctl, or config space
	 * via INTx disable.  The latter means this can get called
	 * even when not using intx delivery.  In this case, just
	 * try to have the physical bit follow the virtual bit.
	 */
	if (unlikely(!is_intx(vdev))) {
		if (vdev->pci_2_3)
			pci_intx(pdev, 0);
		goto out_unlock;
	}

	ctx = vfio_irq_ctx_get(vdev, 0);
	if (WARN_ON_ONCE(!ctx))
		goto out_unlock;

	if (!ctx->masked) {
		/*
		 * Can't use check_and_mask here because we always want to
		 * mask, not just when something is pending.
		 */
		if (vdev->pci_2_3)
			pci_intx(pdev, 0);
		else
			disable_irq_nosync(pdev->irq);

		ctx->masked = true;
		masked_changed = true;
	}

out_unlock:
	spin_unlock_irqrestore(&vdev->irqlock, flags);
	return masked_changed;
}

/*
 * If this is triggered by an eventfd, we can't call eventfd_signal
 * or else we'll deadlock on the eventfd wait queue.  Return >0 when
 * a signal is necessary, which can then be handled via a work queue
 * or directly depending on the caller.
 */
static int vfio_pci_intx_unmask_handler(void *opaque, void *unused)
{
	struct vfio_pci_core_device *vdev = opaque;
	struct pci_dev *pdev = vdev->pdev;
	struct vfio_pci_irq_ctx *ctx;
	unsigned long flags;
	int ret = 0;

	spin_lock_irqsave(&vdev->irqlock, flags);

	/*
	 * Unmasking comes from ioctl or config, so again, have the
	 * physical bit follow the virtual even when not using INTx.
	 */
	if (unlikely(!is_intx(vdev))) {
		if (vdev->pci_2_3)
			pci_intx(pdev, 1);
		goto out_unlock;
	}

	ctx = vfio_irq_ctx_get(vdev, 0);
	if (WARN_ON_ONCE(!ctx))
		goto out_unlock;

	if (ctx->masked && !vdev->virq_disabled) {
		/*
		 * A pending interrupt here would immediately trigger,
		 * but we can avoid that overhead by just re-sending
		 * the interrupt to the user.
		 */
		if (vdev->pci_2_3) {
			if (!pci_check_and_unmask_intx(pdev))
				ret = 1;
		} else
			enable_irq(pdev->irq);

		ctx->masked = (ret > 0);
	}

out_unlock:
	spin_unlock_irqrestore(&vdev->irqlock, flags);

	return ret;
}

void vfio_pci_intx_unmask(struct vfio_pci_core_device *vdev)
{
	if (vfio_pci_intx_unmask_handler(vdev, NULL) > 0)
		vfio_send_intx_eventfd(vdev, NULL);
}

static irqreturn_t vfio_intx_handler(int irq, void *dev_id)
{
	struct vfio_pci_core_device *vdev = dev_id;
	struct vfio_pci_irq_ctx *ctx;
	unsigned long flags;
	int ret = IRQ_NONE;

	ctx = vfio_irq_ctx_get(vdev, 0);
	if (WARN_ON_ONCE(!ctx))
		return ret;

	spin_lock_irqsave(&vdev->irqlock, flags);

	if (!vdev->pci_2_3) {
		disable_irq_nosync(vdev->pdev->irq);
		ctx->masked = true;
		ret = IRQ_HANDLED;
	} else if (!ctx->masked &&  /* may be shared */
		   pci_check_and_mask_intx(vdev->pdev)) {
		ctx->masked = true;
		ret = IRQ_HANDLED;
	}

	spin_unlock_irqrestore(&vdev->irqlock, flags);

	if (ret == IRQ_HANDLED)
		vfio_send_intx_eventfd(vdev, NULL);

	return ret;
}

static int vfio_intx_enable(struct vfio_pci_core_device *vdev)
{
	struct vfio_pci_irq_ctx *ctx;

	if (!is_irq_none(vdev))
		return -EINVAL;

	if (!vdev->pdev->irq)
		return -ENODEV;

	ctx = vfio_irq_ctx_alloc(vdev, 0);
	if (!ctx)
		return -ENOMEM;

	/*
	 * If the virtual interrupt is masked, restore it.  Devices
	 * supporting DisINTx can be masked at the hardware level
	 * here, non-PCI-2.3 devices will have to wait until the
	 * interrupt is enabled.
	 */
	ctx->masked = vdev->virq_disabled;
	if (vdev->pci_2_3)
		pci_intx(vdev->pdev, !ctx->masked);

	vdev->irq_type = VFIO_PCI_INTX_IRQ_INDEX;

	return 0;
}

static int vfio_intx_set_signal(struct vfio_pci_core_device *vdev, int fd)
{
	struct pci_dev *pdev = vdev->pdev;
	unsigned long irqflags = IRQF_SHARED;
	struct vfio_pci_irq_ctx *ctx;
	struct eventfd_ctx *trigger;
	unsigned long flags;
	int ret;

	ctx = vfio_irq_ctx_get(vdev, 0);
	if (WARN_ON_ONCE(!ctx))
		return -EINVAL;

	if (ctx->trigger) {
		free_irq(pdev->irq, vdev);
		kfree(ctx->name);
		eventfd_ctx_put(ctx->trigger);
		ctx->trigger = NULL;
	}

	if (fd < 0) /* Disable only */
		return 0;

	ctx->name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-intx(%s)",
			      pci_name(pdev));
	if (!ctx->name)
		return -ENOMEM;

	trigger = eventfd_ctx_fdget(fd);
	if (IS_ERR(trigger)) {
		kfree(ctx->name);
		return PTR_ERR(trigger);
	}

	ctx->trigger = trigger;

	if (!vdev->pci_2_3)
		irqflags = 0;

	ret = request_irq(pdev->irq, vfio_intx_handler,
			  irqflags, ctx->name, vdev);
	if (ret) {
		ctx->trigger = NULL;
		kfree(ctx->name);
		eventfd_ctx_put(trigger);
		return ret;
	}

	/*
	 * INTx disable will stick across the new irq setup,
	 * disable_irq won't.
	 */
	spin_lock_irqsave(&vdev->irqlock, flags);
	if (!vdev->pci_2_3 && ctx->masked)
		disable_irq_nosync(pdev->irq);
	spin_unlock_irqrestore(&vdev->irqlock, flags);

	return 0;
}

static void vfio_intx_disable(struct vfio_pci_core_device *vdev)
{
	struct vfio_pci_irq_ctx *ctx;

	ctx = vfio_irq_ctx_get(vdev, 0);
	WARN_ON_ONCE(!ctx);
	if (ctx) {
		vfio_virqfd_disable(&ctx->unmask);
		vfio_virqfd_disable(&ctx->mask);
	}
	vfio_intx_set_signal(vdev, -1);
	vdev->irq_type = VFIO_PCI_NUM_IRQS;
	vfio_irq_ctx_free(vdev, ctx, 0);
}

/*
 * MSI/MSI-X
 */
static irqreturn_t vfio_msihandler(int irq, void *arg)
{
	struct eventfd_ctx *trigger = arg;

	eventfd_signal(trigger, 1);
	return IRQ_HANDLED;
}

static int vfio_msi_enable(struct vfio_pci_core_device *vdev, int nvec, bool msix)
{
	struct pci_dev *pdev = vdev->pdev;
	unsigned int flag = msix ? PCI_IRQ_MSIX : PCI_IRQ_MSI;
	int ret;
	u16 cmd;

	if (!is_irq_none(vdev))
		return -EINVAL;

	/* return the number of supported vectors if we can't get all: */
	cmd = vfio_pci_memory_lock_and_enable(vdev);
	ret = pci_alloc_irq_vectors(pdev, 1, nvec, flag);
	if (ret < nvec) {
		if (ret > 0)
			pci_free_irq_vectors(pdev);
		vfio_pci_memory_unlock_and_restore(vdev, cmd);
		return ret;
	}
	vfio_pci_memory_unlock_and_restore(vdev, cmd);

	vdev->irq_type = msix ? VFIO_PCI_MSIX_IRQ_INDEX :
				VFIO_PCI_MSI_IRQ_INDEX;

	if (!msix) {
		/*
		 * Compute the virtual hardware field for max msi vectors -
		 * it is the log base 2 of the number of vectors.
		 */
		vdev->msi_qmax = fls(nvec * 2 - 1) - 1;
	}

	return 0;
}

/*
 * vfio_msi_alloc_irq() returns the Linux IRQ number of an MSI or MSI-X device
 * interrupt vector. If a Linux IRQ number is not available then a new
 * interrupt is allocated if dynamic MSI-X is supported.
 *
 * Where is vfio_msi_free_irq()? Allocated interrupts are maintained,
 * essentially forming a cache that subsequent allocations can draw from.
 * Interrupts are freed using pci_free_irq_vectors() when MSI/MSI-X is
 * disabled.
 */
static int vfio_msi_alloc_irq(struct vfio_pci_core_device *vdev,
			      unsigned int vector, bool msix)
{
	struct pci_dev *pdev = vdev->pdev;
	struct msi_map map;
	int irq;
	u16 cmd;

	irq = pci_irq_vector(pdev, vector);
	if (WARN_ON_ONCE(irq == 0))
		return -EINVAL;
	if (irq > 0 || !msix || !vdev->has_dyn_msix)
		return irq;

	cmd = vfio_pci_memory_lock_and_enable(vdev);
	map = pci_msix_alloc_irq_at(pdev, vector, NULL);
	vfio_pci_memory_unlock_and_restore(vdev, cmd);

	return map.index < 0 ? map.index : map.virq;
}

static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev,
				      unsigned int vector, int fd, bool msix)
{
	struct pci_dev *pdev = vdev->pdev;
	struct vfio_pci_irq_ctx *ctx;
	struct eventfd_ctx *trigger;
	int irq = -EINVAL, ret;
	u16 cmd;

	ctx = vfio_irq_ctx_get(vdev, vector);

	if (ctx) {
		irq_bypass_unregister_producer(&ctx->producer);
		irq = pci_irq_vector(pdev, vector);
		cmd = vfio_pci_memory_lock_and_enable(vdev);
		free_irq(irq, ctx->trigger);
		vfio_pci_memory_unlock_and_restore(vdev, cmd);
		/* Interrupt stays allocated, will be freed at MSI-X disable. */
		kfree(ctx->name);
		eventfd_ctx_put(ctx->trigger);
		vfio_irq_ctx_free(vdev, ctx, vector);
	}

	if (fd < 0)
		return 0;

	if (irq == -EINVAL) {
		/* Interrupt stays allocated, will be freed at MSI-X disable. */
		irq = vfio_msi_alloc_irq(vdev, vector, msix);
		if (irq < 0)
			return irq;
	}

	ctx = vfio_irq_ctx_alloc(vdev, vector);
	if (!ctx)
		return -ENOMEM;

	ctx->name = kasprintf(GFP_KERNEL_ACCOUNT, "vfio-msi%s[%d](%s)",
			      msix ? "x" : "", vector, pci_name(pdev));
	if (!ctx->name) {
		ret = -ENOMEM;
		goto out_free_ctx;
	}

	trigger = eventfd_ctx_fdget(fd);
	if (IS_ERR(trigger)) {
		ret = PTR_ERR(trigger);
		goto out_free_name;
	}

	/*
	 * If the vector was previously allocated, refresh the on-device
	 * message data before enabling in case it had been cleared or
	 * corrupted (e.g. due to backdoor resets) since writing.
	 */
	cmd = vfio_pci_memory_lock_and_enable(vdev);
	if (msix) {
		struct msi_msg msg;

		get_cached_msi_msg(irq, &msg);
		pci_write_msi_msg(irq, &msg);
	}

	ret = request_irq(irq, vfio_msihandler, 0, ctx->name, trigger);
	vfio_pci_memory_unlock_and_restore(vdev, cmd);
	if (ret)
		goto out_put_eventfd_ctx;

	ctx->producer.token = trigger;
	ctx->producer.irq = irq;
	ret = irq_bypass_register_producer(&ctx->producer);
	if (unlikely(ret)) {
		dev_info(&pdev->dev,
		"irq bypass producer (token %p) registration fails: %d\n",
		ctx->producer.token, ret);

		ctx->producer.token = NULL;
	}
	ctx->trigger = trigger;

	return 0;

out_put_eventfd_ctx:
	eventfd_ctx_put(trigger);
out_free_name:
	kfree(ctx->name);
out_free_ctx:
	vfio_irq_ctx_free(vdev, ctx, vector);
	return ret;
}

static int vfio_msi_set_block(struct vfio_pci_core_device *vdev, unsigned start,
			      unsigned count, int32_t *fds, bool msix)
{
	unsigned int i, j;
	int ret = 0;

	for (i = 0, j = start; i < count && !ret; i++, j++) {
		int fd = fds ? fds[i] : -1;
		ret = vfio_msi_set_vector_signal(vdev, j, fd, msix);
	}

	if (ret) {
		for (i = start; i < j; i++)
			vfio_msi_set_vector_signal(vdev, i, -1, msix);
	}

	return ret;
}

static void vfio_msi_disable(struct vfio_pci_core_device *vdev, bool msix)
{
	struct pci_dev *pdev = vdev->pdev;
	struct vfio_pci_irq_ctx *ctx;
	unsigned long i;
	u16 cmd;

	xa_for_each(&vdev->ctx, i, ctx) {
		vfio_virqfd_disable(&ctx->unmask);
		vfio_virqfd_disable(&ctx->mask);
		vfio_msi_set_vector_signal(vdev, i, -1, msix);
	}

	cmd = vfio_pci_memory_lock_and_enable(vdev);
	pci_free_irq_vectors(pdev);
	vfio_pci_memory_unlock_and_restore(vdev, cmd);

	/*
	 * Both disable paths above use pci_intx_for_msi() to clear DisINTx
	 * via their shutdown paths.  Restore for NoINTx devices.
	 */
	if (vdev->nointx)
		pci_intx(pdev, 0);

	vdev->irq_type = VFIO_PCI_NUM_IRQS;
}

/*
 * IOCTL support
 */
static int vfio_pci_set_intx_unmask(struct vfio_pci_core_device *vdev,
				    unsigned index, unsigned start,
				    unsigned count, uint32_t flags, void *data)
{
	if (!is_intx(vdev) || start != 0 || count != 1)
		return -EINVAL;

	if (flags & VFIO_IRQ_SET_DATA_NONE) {
		vfio_pci_intx_unmask(vdev);
	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
		uint8_t unmask = *(uint8_t *)data;
		if (unmask)
			vfio_pci_intx_unmask(vdev);
	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
		struct vfio_pci_irq_ctx *ctx = vfio_irq_ctx_get(vdev, 0);
		int32_t fd = *(int32_t *)data;

		if (WARN_ON_ONCE(!ctx))
			return -EINVAL;
		if (fd >= 0)
			return vfio_virqfd_enable((void *) vdev,
						  vfio_pci_intx_unmask_handler,
						  vfio_send_intx_eventfd, NULL,
						  &ctx->unmask, fd);

		vfio_virqfd_disable(&ctx->unmask);
	}

	return 0;
}

static int vfio_pci_set_intx_mask(struct vfio_pci_core_device *vdev,
				  unsigned index, unsigned start,
				  unsigned count, uint32_t flags, void *data)
{
	if (!is_intx(vdev) || start != 0 || count != 1)
		return -EINVAL;

	if (flags & VFIO_IRQ_SET_DATA_NONE) {
		vfio_pci_intx_mask(vdev);
	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
		uint8_t mask = *(uint8_t *)data;
		if (mask)
			vfio_pci_intx_mask(vdev);
	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
		return -ENOTTY; /* XXX implement me */
	}

	return 0;
}

static int vfio_pci_set_intx_trigger(struct vfio_pci_core_device *vdev,
				     unsigned index, unsigned start,
				     unsigned count, uint32_t flags, void *data)
{
	if (is_intx(vdev) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
		vfio_intx_disable(vdev);
		return 0;
	}

	if (!(is_intx(vdev) || is_irq_none(vdev)) || start != 0 || count != 1)
		return -EINVAL;

	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
		int32_t fd = *(int32_t *)data;
		int ret;

		if (is_intx(vdev))
			return vfio_intx_set_signal(vdev, fd);

		ret = vfio_intx_enable(vdev);
		if (ret)
			return ret;

		ret = vfio_intx_set_signal(vdev, fd);
		if (ret)
			vfio_intx_disable(vdev);

		return ret;
	}

	if (!is_intx(vdev))
		return -EINVAL;

	if (flags & VFIO_IRQ_SET_DATA_NONE) {
		vfio_send_intx_eventfd(vdev, NULL);
	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
		uint8_t trigger = *(uint8_t *)data;
		if (trigger)
			vfio_send_intx_eventfd(vdev, NULL);
	}
	return 0;
}

static int vfio_pci_set_msi_trigger(struct vfio_pci_core_device *vdev,
				    unsigned index, unsigned start,
				    unsigned count, uint32_t flags, void *data)
{
	struct vfio_pci_irq_ctx *ctx;
	unsigned int i;
	bool msix = (index == VFIO_PCI_MSIX_IRQ_INDEX) ? true : false;

	if (irq_is(vdev, index) && !count && (flags & VFIO_IRQ_SET_DATA_NONE)) {
		vfio_msi_disable(vdev, msix);
		return 0;
	}

	if (!(irq_is(vdev, index) || is_irq_none(vdev)))
		return -EINVAL;

	if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
		int32_t *fds = data;
		int ret;

		if (vdev->irq_type == index)
			return vfio_msi_set_block(vdev, start, count,
						  fds, msix);

		ret = vfio_msi_enable(vdev, start + count, msix);
		if (ret)
			return ret;

		ret = vfio_msi_set_block(vdev, start, count, fds, msix);
		if (ret)
			vfio_msi_disable(vdev, msix);

		return ret;
	}

	if (!irq_is(vdev, index))
		return -EINVAL;

	for (i = start; i < start + count; i++) {
		ctx = vfio_irq_ctx_get(vdev, i);
		if (!ctx)
			continue;
		if (flags & VFIO_IRQ_SET_DATA_NONE) {
			eventfd_signal(ctx->trigger, 1);
		} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
			uint8_t *bools = data;
			if (bools[i - start])
				eventfd_signal(ctx->trigger, 1);
		}
	}
	return 0;
}

static int vfio_pci_set_ctx_trigger_single(struct eventfd_ctx **ctx,
					   unsigned int count, uint32_t flags,
					   void *data)
{
	/* DATA_NONE/DATA_BOOL enables loopback testing */
	if (flags & VFIO_IRQ_SET_DATA_NONE) {
		if (*ctx) {
			if (count) {
				eventfd_signal(*ctx, 1);
			} else {
				eventfd_ctx_put(*ctx);
				*ctx = NULL;
			}
			return 0;
		}
	} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
		uint8_t trigger;

		if (!count)
			return -EINVAL;

		trigger = *(uint8_t *)data;
		if (trigger && *ctx)
			eventfd_signal(*ctx, 1);

		return 0;
	} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
		int32_t fd;

		if (!count)
			return -EINVAL;

		fd = *(int32_t *)data;
		if (fd == -1) {
			if (*ctx)
				eventfd_ctx_put(*ctx);
			*ctx = NULL;
		} else if (fd >= 0) {
			struct eventfd_ctx *efdctx;

			efdctx = eventfd_ctx_fdget(fd);
			if (IS_ERR(efdctx))
				return PTR_ERR(efdctx);

			if (*ctx)
				eventfd_ctx_put(*ctx);

			*ctx = efdctx;
		}
		return 0;
	}

	return -EINVAL;
}

static int vfio_pci_set_err_trigger(struct vfio_pci_core_device *vdev,
				    unsigned index, unsigned start,
				    unsigned count, uint32_t flags, void *data)
{
	if (index != VFIO_PCI_ERR_IRQ_INDEX || start != 0 || count > 1)
		return -EINVAL;

	return vfio_pci_set_ctx_trigger_single(&vdev->err_trigger,
					       count, flags, data);
}

static int vfio_pci_set_req_trigger(struct vfio_pci_core_device *vdev,
				    unsigned index, unsigned start,
				    unsigned count, uint32_t flags, void *data)
{
	if (index != VFIO_PCI_REQ_IRQ_INDEX || start != 0 || count > 1)
		return -EINVAL;

	return vfio_pci_set_ctx_trigger_single(&vdev->req_trigger,
					       count, flags, data);
}

int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, uint32_t flags,
			    unsigned index, unsigned start, unsigned count,
			    void *data)
{
	int (*func)(struct vfio_pci_core_device *vdev, unsigned index,
		    unsigned start, unsigned count, uint32_t flags,
		    void *data) = NULL;

	switch (index) {
	case VFIO_PCI_INTX_IRQ_INDEX:
		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
		case VFIO_IRQ_SET_ACTION_MASK:
			func = vfio_pci_set_intx_mask;
			break;
		case VFIO_IRQ_SET_ACTION_UNMASK:
			func = vfio_pci_set_intx_unmask;
			break;
		case VFIO_IRQ_SET_ACTION_TRIGGER:
			func = vfio_pci_set_intx_trigger;
			break;
		}
		break;
	case VFIO_PCI_MSI_IRQ_INDEX:
	case VFIO_PCI_MSIX_IRQ_INDEX:
		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
		case VFIO_IRQ_SET_ACTION_MASK:
		case VFIO_IRQ_SET_ACTION_UNMASK:
			/* XXX Need masking support exported */
			break;
		case VFIO_IRQ_SET_ACTION_TRIGGER:
			func = vfio_pci_set_msi_trigger;
			break;
		}
		break;
	case VFIO_PCI_ERR_IRQ_INDEX:
		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
		case VFIO_IRQ_SET_ACTION_TRIGGER:
			if (pci_is_pcie(vdev->pdev))
				func = vfio_pci_set_err_trigger;
			break;
		}
		break;
	case VFIO_PCI_REQ_IRQ_INDEX:
		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
		case VFIO_IRQ_SET_ACTION_TRIGGER:
			func = vfio_pci_set_req_trigger;
			break;
		}
		break;
	}

	if (!func)
		return -ENOTTY;

	return func(vdev, index, start, count, flags, data);
}