summaryrefslogtreecommitdiffstats
path: root/kernel/irq/msi.c
blob: 4e462b5f7bbe891a796834aecc6dc4bdefa2a115 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2014 Intel Corp.
 * Author: Jiang Liu <jiang.liu@linux.intel.com>
 *
 * This file is licensed under GPLv2.
 *
 * This file contains common code to support Message Signaled Interrupts for
 * PCI compatible and non PCI compatible devices.
 */
#include <linux/types.h>
#include <linux/device.h>
#include <linux/irq.h>
#include <linux/irqdomain.h>
#include <linux/msi.h>
#include <linux/slab.h>
#include <linux/sysfs.h>
#include <linux/pci.h>

#include "internals.h"

static inline int msi_sysfs_create_group(struct device *dev);

/**
 * msi_alloc_desc - Allocate an initialized msi_desc
 * @dev:	Pointer to the device for which this is allocated
 * @nvec:	The number of vectors used in this entry
 * @affinity:	Optional pointer to an affinity mask array size of @nvec
 *
 * If @affinity is not %NULL then an affinity array[@nvec] is allocated
 * and the affinity masks and flags from @affinity are copied.
 *
 * Return: pointer to allocated &msi_desc on success or %NULL on failure
 */
static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec,
					const struct irq_affinity_desc *affinity)
{
	struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);

	if (!desc)
		return NULL;

	desc->dev = dev;
	desc->nvec_used = nvec;
	if (affinity) {
		desc->affinity = kmemdup(affinity, nvec * sizeof(*desc->affinity), GFP_KERNEL);
		if (!desc->affinity) {
			kfree(desc);
			return NULL;
		}
	}
	return desc;
}

static void msi_free_desc(struct msi_desc *desc)
{
	kfree(desc->affinity);
	kfree(desc);
}

static int msi_insert_desc(struct msi_device_data *md, struct msi_desc *desc, unsigned int index)
{
	int ret;

	desc->msi_index = index;
	ret = xa_insert(&md->__store, index, desc, GFP_KERNEL);
	if (ret)
		msi_free_desc(desc);
	return ret;
}

/**
 * msi_add_msi_desc - Allocate and initialize a MSI descriptor
 * @dev:	Pointer to the device for which the descriptor is allocated
 * @init_desc:	Pointer to an MSI descriptor to initialize the new descriptor
 *
 * Return: 0 on success or an appropriate failure code.
 */
int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc)
{
	struct msi_desc *desc;

	lockdep_assert_held(&dev->msi.data->mutex);

	desc = msi_alloc_desc(dev, init_desc->nvec_used, init_desc->affinity);
	if (!desc)
		return -ENOMEM;

	/* Copy type specific data to the new descriptor. */
	desc->pci = init_desc->pci;
	return msi_insert_desc(dev->msi.data, desc, init_desc->msi_index);
}

/**
 * msi_add_simple_msi_descs - Allocate and initialize MSI descriptors
 * @dev:	Pointer to the device for which the descriptors are allocated
 * @index:	Index for the first MSI descriptor
 * @ndesc:	Number of descriptors to allocate
 *
 * Return: 0 on success or an appropriate failure code.
 */
static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsigned int ndesc)
{
	unsigned int idx, last = index + ndesc - 1;
	struct msi_desc *desc;
	int ret;

	lockdep_assert_held(&dev->msi.data->mutex);

	for (idx = index; idx <= last; idx++) {
		desc = msi_alloc_desc(dev, 1, NULL);
		if (!desc)
			goto fail_mem;
		ret = msi_insert_desc(dev->msi.data, desc, idx);
		if (ret)
			goto fail;
	}
	return 0;

fail_mem:
	ret = -ENOMEM;
fail:
	msi_free_msi_descs_range(dev, MSI_DESC_NOTASSOCIATED, index, last);
	return ret;
}

static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter)
{
	switch (filter) {
	case MSI_DESC_ALL:
		return true;
	case MSI_DESC_NOTASSOCIATED:
		return !desc->irq;
	case MSI_DESC_ASSOCIATED:
		return !!desc->irq;
	}
	WARN_ON_ONCE(1);
	return false;
}

/**
 * msi_free_msi_descs_range - Free MSI descriptors of a device
 * @dev:		Device to free the descriptors
 * @filter:		Descriptor state filter
 * @first_index:	Index to start freeing from
 * @last_index:		Last index to be freed
 */
void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter,
			      unsigned int first_index, unsigned int last_index)
{
	struct xarray *xa = &dev->msi.data->__store;
	struct msi_desc *desc;
	unsigned long idx;

	lockdep_assert_held(&dev->msi.data->mutex);

	xa_for_each_range(xa, idx, desc, first_index, last_index) {
		if (msi_desc_match(desc, filter)) {
			xa_erase(xa, idx);
			msi_free_desc(desc);
		}
	}
}

void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
	*msg = entry->msg;
}

void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
{
	struct msi_desc *entry = irq_get_msi_desc(irq);

	__get_cached_msi_msg(entry, msg);
}
EXPORT_SYMBOL_GPL(get_cached_msi_msg);

static void msi_device_data_release(struct device *dev, void *res)
{
	struct msi_device_data *md = res;

	WARN_ON_ONCE(!xa_empty(&md->__store));
	xa_destroy(&md->__store);
	dev->msi.data = NULL;
}

/**
 * msi_setup_device_data - Setup MSI device data
 * @dev:	Device for which MSI device data should be set up
 *
 * Return: 0 on success, appropriate error code otherwise
 *
 * This can be called more than once for @dev. If the MSI device data is
 * already allocated the call succeeds. The allocated memory is
 * automatically released when the device is destroyed.
 */
int msi_setup_device_data(struct device *dev)
{
	struct msi_device_data *md;
	int ret;

	if (dev->msi.data)
		return 0;

	md = devres_alloc(msi_device_data_release, sizeof(*md), GFP_KERNEL);
	if (!md)
		return -ENOMEM;

	ret = msi_sysfs_create_group(dev);
	if (ret) {
		devres_free(md);
		return ret;
	}

	xa_init(&md->__store);
	mutex_init(&md->mutex);
	dev->msi.data = md;
	devres_add(dev, md);
	return 0;
}

/**
 * msi_lock_descs - Lock the MSI descriptor storage of a device
 * @dev:	Device to operate on
 */
void msi_lock_descs(struct device *dev)
{
	mutex_lock(&dev->msi.data->mutex);
}
EXPORT_SYMBOL_GPL(msi_lock_descs);

/**
 * msi_unlock_descs - Unlock the MSI descriptor storage of a device
 * @dev:	Device to operate on
 */
void msi_unlock_descs(struct device *dev)
{
	/* Invalidate the index wich was cached by the iterator */
	dev->msi.data->__iter_idx = MSI_MAX_INDEX;
	mutex_unlock(&dev->msi.data->mutex);
}
EXPORT_SYMBOL_GPL(msi_unlock_descs);

static struct msi_desc *msi_find_desc(struct msi_device_data *md, enum msi_desc_filter filter)
{
	struct msi_desc *desc;

	xa_for_each_start(&md->__store, md->__iter_idx, desc, md->__iter_idx) {
		if (msi_desc_match(desc, filter))
			return desc;
	}
	md->__iter_idx = MSI_MAX_INDEX;
	return NULL;
}

/**
 * msi_first_desc - Get the first MSI descriptor of a device
 * @dev:	Device to operate on
 * @filter:	Descriptor state filter
 *
 * Must be called with the MSI descriptor mutex held, i.e. msi_lock_descs()
 * must be invoked before the call.
 *
 * Return: Pointer to the first MSI descriptor matching the search
 *	   criteria, NULL if none found.
 */
struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter)
{
	struct msi_device_data *md = dev->msi.data;

	if (WARN_ON_ONCE(!md))
		return NULL;

	lockdep_assert_held(&md->mutex);

	md->__iter_idx = 0;
	return msi_find_desc(md, filter);
}
EXPORT_SYMBOL_GPL(msi_first_desc);

/**
 * msi_next_desc - Get the next MSI descriptor of a device
 * @dev:	Device to operate on
 *
 * The first invocation of msi_next_desc() has to be preceeded by a
 * successful invocation of __msi_first_desc(). Consecutive invocations are
 * only valid if the previous one was successful. All these operations have
 * to be done within the same MSI mutex held region.
 *
 * Return: Pointer to the next MSI descriptor matching the search
 *	   criteria, NULL if none found.
 */
struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter)
{
	struct msi_device_data *md = dev->msi.data;

	if (WARN_ON_ONCE(!md))
		return NULL;

	lockdep_assert_held(&md->mutex);

	if (md->__iter_idx >= (unsigned long)MSI_MAX_INDEX)
		return NULL;

	md->__iter_idx++;
	return msi_find_desc(md, filter);
}
EXPORT_SYMBOL_GPL(msi_next_desc);

/**
 * msi_get_virq - Return Linux interrupt number of a MSI interrupt
 * @dev:	Device to operate on
 * @index:	MSI interrupt index to look for (0-based)
 *
 * Return: The Linux interrupt number on success (> 0), 0 if not found
 */
unsigned int msi_get_virq(struct device *dev, unsigned int index)
{
	struct msi_desc *desc;
	unsigned int ret = 0;
	bool pcimsi;

	if (!dev->msi.data)
		return 0;

	pcimsi = dev_is_pci(dev) ? to_pci_dev(dev)->msi_enabled : false;

	msi_lock_descs(dev);
	desc = xa_load(&dev->msi.data->__store, pcimsi ? 0 : index);
	if (desc && desc->irq) {
		/*
		 * PCI-MSI has only one descriptor for multiple interrupts.
		 * PCI-MSIX and platform MSI use a descriptor per
		 * interrupt.
		 */
		if (pcimsi) {
			if (index < desc->nvec_used)
				ret = desc->irq + index;
		} else {
			ret = desc->irq;
		}
	}
	msi_unlock_descs(dev);
	return ret;
}
EXPORT_SYMBOL_GPL(msi_get_virq);

#ifdef CONFIG_SYSFS
static struct attribute *msi_dev_attrs[] = {
	NULL
};

static const struct attribute_group msi_irqs_group = {
	.name	= "msi_irqs",
	.attrs	= msi_dev_attrs,
};

static inline int msi_sysfs_create_group(struct device *dev)
{
	return devm_device_add_group(dev, &msi_irqs_group);
}

static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr,
			     char *buf)
{
	/* MSI vs. MSIX is per device not per interrupt */
	bool is_msix = dev_is_pci(dev) ? to_pci_dev(dev)->msix_enabled : false;

	return sysfs_emit(buf, "%s\n", is_msix ? "msix" : "msi");
}

static void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc)
{
	struct device_attribute *attrs = desc->sysfs_attrs;
	int i;

	if (!attrs)
		return;

	desc->sysfs_attrs = NULL;
	for (i = 0; i < desc->nvec_used; i++) {
		if (attrs[i].show)
			sysfs_remove_file_from_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name);
		kfree(attrs[i].attr.name);
	}
	kfree(attrs);
}

static int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc)
{
	struct device_attribute *attrs;
	int ret, i;

	attrs = kcalloc(desc->nvec_used, sizeof(*attrs), GFP_KERNEL);
	if (!attrs)
		return -ENOMEM;

	desc->sysfs_attrs = attrs;
	for (i = 0; i < desc->nvec_used; i++) {
		sysfs_attr_init(&attrs[i].attr);
		attrs[i].attr.name = kasprintf(GFP_KERNEL, "%d", desc->irq + i);
		if (!attrs[i].attr.name) {
			ret = -ENOMEM;
			goto fail;
		}

		attrs[i].attr.mode = 0444;
		attrs[i].show = msi_mode_show;

		ret = sysfs_add_file_to_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name);
		if (ret) {
			attrs[i].show = NULL;
			goto fail;
		}
	}
	return 0;

fail:
	msi_sysfs_remove_desc(dev, desc);
	return ret;
}

#if defined(CONFIG_PCI_MSI_ARCH_FALLBACKS) || defined(CONFIG_PCI_XEN)
/**
 * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device
 * @dev:	The device (PCI, platform etc) which will get sysfs entries
 */
int msi_device_populate_sysfs(struct device *dev)
{
	struct msi_desc *desc;
	int ret;

	msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) {
		if (desc->sysfs_attrs)
			continue;
		ret = msi_sysfs_populate_desc(dev, desc);
		if (ret)
			return ret;
	}
	return 0;
}

/**
 * msi_device_destroy_sysfs - Destroy msi_irqs sysfs entries for a device
 * @dev:		The device (PCI, platform etc) for which to remove
 *			sysfs entries
 */
void msi_device_destroy_sysfs(struct device *dev)
{
	struct msi_desc *desc;

	msi_for_each_desc(desc, dev, MSI_DESC_ALL)
		msi_sysfs_remove_desc(dev, desc);
}
#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK || CONFIG_PCI_XEN */
#else /* CONFIG_SYSFS */
static inline int msi_sysfs_create_group(struct device *dev) { return 0; }
static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; }
static inline void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { }
#endif /* !CONFIG_SYSFS */

#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
static inline void irq_chip_write_msi_msg(struct irq_data *data,
					  struct msi_msg *msg)
{
	data->chip->irq_write_msi_msg(data, msg);
}

static void msi_check_level(struct irq_domain *domain, struct msi_msg *msg)
{
	struct msi_domain_info *info = domain->host_data;

	/*
	 * If the MSI provider has messed with the second message and
	 * not advertized that it is level-capable, signal the breakage.
	 */
	WARN_ON(!((info->flags & MSI_FLAG_LEVEL_CAPABLE) &&
		  (info->chip->flags & IRQCHIP_SUPPORTS_LEVEL_MSI)) &&
		(msg[1].address_lo || msg[1].address_hi || msg[1].data));
}

/**
 * msi_domain_set_affinity - Generic affinity setter function for MSI domains
 * @irq_data:	The irq data associated to the interrupt
 * @mask:	The affinity mask to set
 * @force:	Flag to enforce setting (disable online checks)
 *
 * Intended to be used by MSI interrupt controllers which are
 * implemented with hierarchical domains.
 *
 * Return: IRQ_SET_MASK_* result code
 */
int msi_domain_set_affinity(struct irq_data *irq_data,
			    const struct cpumask *mask, bool force)
{
	struct irq_data *parent = irq_data->parent_data;
	struct msi_msg msg[2] = { [1] = { }, };
	int ret;

	ret = parent->chip->irq_set_affinity(parent, mask, force);
	if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
		BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
		msi_check_level(irq_data->domain, msg);
		irq_chip_write_msi_msg(irq_data, msg);
	}

	return ret;
}

static int msi_domain_activate(struct irq_domain *domain,
			       struct irq_data *irq_data, bool early)
{
	struct msi_msg msg[2] = { [1] = { }, };

	BUG_ON(irq_chip_compose_msi_msg(irq_data, msg));
	msi_check_level(irq_data->domain, msg);
	irq_chip_write_msi_msg(irq_data, msg);
	return 0;
}

static void msi_domain_deactivate(struct irq_domain *domain,
				  struct irq_data *irq_data)
{
	struct msi_msg msg[2];

	memset(msg, 0, sizeof(msg));
	irq_chip_write_msi_msg(irq_data, msg);
}

static int msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
			    unsigned int nr_irqs, void *arg)
{
	struct msi_domain_info *info = domain->host_data;
	struct msi_domain_ops *ops = info->ops;
	irq_hw_number_t hwirq = ops->get_hwirq(info, arg);
	int i, ret;

	if (irq_find_mapping(domain, hwirq) > 0)
		return -EEXIST;

	if (domain->parent) {
		ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
		if (ret < 0)
			return ret;
	}

	for (i = 0; i < nr_irqs; i++) {
		ret = ops->msi_init(domain, info, virq + i, hwirq + i, arg);
		if (ret < 0) {
			if (ops->msi_free) {
				for (i--; i > 0; i--)
					ops->msi_free(domain, info, virq + i);
			}
			irq_domain_free_irqs_top(domain, virq, nr_irqs);
			return ret;
		}
	}

	return 0;
}

static void msi_domain_free(struct irq_domain *domain, unsigned int virq,
			    unsigned int nr_irqs)
{
	struct msi_domain_info *info = domain->host_data;
	int i;

	if (info->ops->msi_free) {
		for (i = 0; i < nr_irqs; i++)
			info->ops->msi_free(domain, info, virq + i);
	}
	irq_domain_free_irqs_top(domain, virq, nr_irqs);
}

static const struct irq_domain_ops msi_domain_ops = {
	.alloc		= msi_domain_alloc,
	.free		= msi_domain_free,
	.activate	= msi_domain_activate,
	.deactivate	= msi_domain_deactivate,
};

static irq_hw_number_t msi_domain_ops_get_hwirq(struct msi_domain_info *info,
						msi_alloc_info_t *arg)
{
	return arg->hwirq;
}

static int msi_domain_ops_prepare(struct irq_domain *domain, struct device *dev,
				  int nvec, msi_alloc_info_t *arg)
{
	memset(arg, 0, sizeof(*arg));
	return 0;
}

static void msi_domain_ops_set_desc(msi_alloc_info_t *arg,
				    struct msi_desc *desc)
{
	arg->desc = desc;
}

static int msi_domain_ops_init(struct irq_domain *domain,
			       struct msi_domain_info *info,
			       unsigned int virq, irq_hw_number_t hwirq,
			       msi_alloc_info_t *arg)
{
	irq_domain_set_hwirq_and_chip(domain, virq, hwirq, info->chip,
				      info->chip_data);
	if (info->handler && info->handler_name) {
		__irq_set_handler(virq, info->handler, 0, info->handler_name);
		if (info->handler_data)
			irq_set_handler_data(virq, info->handler_data);
	}
	return 0;
}

static int msi_domain_ops_check(struct irq_domain *domain,
				struct msi_domain_info *info,
				struct device *dev)
{
	return 0;
}

static struct msi_domain_ops msi_domain_ops_default = {
	.get_hwirq		= msi_domain_ops_get_hwirq,
	.msi_init		= msi_domain_ops_init,
	.msi_check		= msi_domain_ops_check,
	.msi_prepare		= msi_domain_ops_prepare,
	.set_desc		= msi_domain_ops_set_desc,
	.domain_alloc_irqs	= __msi_domain_alloc_irqs,
	.domain_free_irqs	= __msi_domain_free_irqs,
};

static void msi_domain_update_dom_ops(struct msi_domain_info *info)
{
	struct msi_domain_ops *ops = info->ops;

	if (ops == NULL) {
		info->ops = &msi_domain_ops_default;
		return;
	}

	if (ops->domain_alloc_irqs == NULL)
		ops->domain_alloc_irqs = msi_domain_ops_default.domain_alloc_irqs;
	if (ops->domain_free_irqs == NULL)
		ops->domain_free_irqs = msi_domain_ops_default.domain_free_irqs;

	if (!(info->flags & MSI_FLAG_USE_DEF_DOM_OPS))
		return;

	if (ops->get_hwirq == NULL)
		ops->get_hwirq = msi_domain_ops_default.get_hwirq;
	if (ops->msi_init == NULL)
		ops->msi_init = msi_domain_ops_default.msi_init;
	if (ops->msi_check == NULL)
		ops->msi_check = msi_domain_ops_default.msi_check;
	if (ops->msi_prepare == NULL)
		ops->msi_prepare = msi_domain_ops_default.msi_prepare;
	if (ops->set_desc == NULL)
		ops->set_desc = msi_domain_ops_default.set_desc;
}

static void msi_domain_update_chip_ops(struct msi_domain_info *info)
{
	struct irq_chip *chip = info->chip;

	BUG_ON(!chip || !chip->irq_mask || !chip->irq_unmask);
	if (!chip->irq_set_affinity)
		chip->irq_set_affinity = msi_domain_set_affinity;
}

/**
 * msi_create_irq_domain - Create an MSI interrupt domain
 * @fwnode:	Optional fwnode of the interrupt controller
 * @info:	MSI domain info
 * @parent:	Parent irq domain
 *
 * Return: pointer to the created &struct irq_domain or %NULL on failure
 */
struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
					 struct msi_domain_info *info,
					 struct irq_domain *parent)
{
	struct irq_domain *domain;

	msi_domain_update_dom_ops(info);
	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
		msi_domain_update_chip_ops(info);

	domain = irq_domain_create_hierarchy(parent, IRQ_DOMAIN_FLAG_MSI, 0,
					     fwnode, &msi_domain_ops, info);

	if (domain && !domain->name && info->chip)
		domain->name = info->chip->name;

	return domain;
}

int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
			    int nvec, msi_alloc_info_t *arg)
{
	struct msi_domain_info *info = domain->host_data;
	struct msi_domain_ops *ops = info->ops;
	int ret;

	ret = ops->msi_check(domain, info, dev);
	if (ret == 0)
		ret = ops->msi_prepare(domain, dev, nvec, arg);

	return ret;
}

int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
			     int virq_base, int nvec, msi_alloc_info_t *arg)
{
	struct msi_domain_info *info = domain->host_data;
	struct msi_domain_ops *ops = info->ops;
	struct msi_desc *desc;
	int ret, virq;

	msi_lock_descs(dev);
	ret = msi_add_simple_msi_descs(dev, virq_base, nvec);
	if (ret)
		goto unlock;

	for (virq = virq_base; virq < virq_base + nvec; virq++) {
		desc = xa_load(&dev->msi.data->__store, virq);
		desc->irq = virq;

		ops->set_desc(arg, desc);
		ret = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg);
		if (ret)
			goto fail;

		irq_set_msi_desc(virq, desc);
	}
	msi_unlock_descs(dev);
	return 0;

fail:
	for (--virq; virq >= virq_base; virq--)
		irq_domain_free_irqs_common(domain, virq, 1);
	msi_free_msi_descs_range(dev, MSI_DESC_ALL, virq_base, virq_base + nvec - 1);
unlock:
	msi_unlock_descs(dev);
	return ret;
}

/*
 * Carefully check whether the device can use reservation mode. If
 * reservation mode is enabled then the early activation will assign a
 * dummy vector to the device. If the PCI/MSI device does not support
 * masking of the entry then this can result in spurious interrupts when
 * the device driver is not absolutely careful. But even then a malfunction
 * of the hardware could result in a spurious interrupt on the dummy vector
 * and render the device unusable. If the entry can be masked then the core
 * logic will prevent the spurious interrupt and reservation mode can be
 * used. For now reservation mode is restricted to PCI/MSI.
 */
static bool msi_check_reservation_mode(struct irq_domain *domain,
				       struct msi_domain_info *info,
				       struct device *dev)
{
	struct msi_desc *desc;

	switch(domain->bus_token) {
	case DOMAIN_BUS_PCI_MSI:
	case DOMAIN_BUS_VMD_MSI:
		break;
	default:
		return false;
	}

	if (!(info->flags & MSI_FLAG_MUST_REACTIVATE))
		return false;

	if (IS_ENABLED(CONFIG_PCI_MSI) && pci_msi_ignore_mask)
		return false;

	/*
	 * Checking the first MSI descriptor is sufficient. MSIX supports
	 * masking and MSI does so when the can_mask attribute is set.
	 */
	desc = msi_first_desc(dev, MSI_DESC_ALL);
	return desc->pci.msi_attrib.is_msix || desc->pci.msi_attrib.can_mask;
}

static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc,
			       int allocated)
{
	switch(domain->bus_token) {
	case DOMAIN_BUS_PCI_MSI:
	case DOMAIN_BUS_VMD_MSI:
		if (IS_ENABLED(CONFIG_PCI_MSI))
			break;
		fallthrough;
	default:
		return -ENOSPC;
	}

	/* Let a failed PCI multi MSI allocation retry */
	if (desc->nvec_used > 1)
		return 1;

	/* If there was a successful allocation let the caller know */
	return allocated ? allocated : -ENOSPC;
}

#define VIRQ_CAN_RESERVE	0x01
#define VIRQ_ACTIVATE		0x02

static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags)
{
	struct irq_data *irqd = irq_domain_get_irq_data(domain, virq);
	int ret;

	if (!(vflags & VIRQ_CAN_RESERVE)) {
		irqd_clr_can_reserve(irqd);

		/*
		 * If the interrupt is managed but no CPU is available to
		 * service it, shut it down until better times. Note that
		 * we only do this on the !RESERVE path as x86 (the only
		 * architecture using this flag) deals with this in a
		 * different way by using a catch-all vector.
		 */
		if ((vflags & VIRQ_ACTIVATE) &&
		    irqd_affinity_is_managed(irqd) &&
		    !cpumask_intersects(irq_data_get_affinity_mask(irqd),
					cpu_online_mask)) {
			    irqd_set_managed_shutdown(irqd);
			    return 0;
		    }
	}

	if (!(vflags & VIRQ_ACTIVATE))
		return 0;

	ret = irq_domain_activate_irq(irqd, vflags & VIRQ_CAN_RESERVE);
	if (ret)
		return ret;
	/*
	 * If the interrupt uses reservation mode, clear the activated bit
	 * so request_irq() will assign the final vector.
	 */
	if (vflags & VIRQ_CAN_RESERVE)
		irqd_clr_activated(irqd);
	return 0;
}

int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
			    int nvec)
{
	struct msi_domain_info *info = domain->host_data;
	struct msi_domain_ops *ops = info->ops;
	msi_alloc_info_t arg = { };
	unsigned int vflags = 0;
	struct msi_desc *desc;
	int allocated = 0;
	int i, ret, virq;

	ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
	if (ret)
		return ret;

	/*
	 * This flag is set by the PCI layer as we need to activate
	 * the MSI entries before the PCI layer enables MSI in the
	 * card. Otherwise the card latches a random msi message.
	 */
	if (info->flags & MSI_FLAG_ACTIVATE_EARLY)
		vflags |= VIRQ_ACTIVATE;

	/*
	 * Interrupt can use a reserved vector and will not occupy
	 * a real device vector until the interrupt is requested.
	 */
	if (msi_check_reservation_mode(domain, info, dev))
		vflags |= VIRQ_CAN_RESERVE;

	msi_for_each_desc(desc, dev, MSI_DESC_NOTASSOCIATED) {
		ops->set_desc(&arg, desc);

		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
					       dev_to_node(dev), &arg, false,
					       desc->affinity);
		if (virq < 0)
			return msi_handle_pci_fail(domain, desc, allocated);

		for (i = 0; i < desc->nvec_used; i++) {
			irq_set_msi_desc_off(virq, i, desc);
			irq_debugfs_copy_devname(virq + i, dev);
			ret = msi_init_virq(domain, virq + i, vflags);
			if (ret)
				return ret;
		}
		if (info->flags & MSI_FLAG_DEV_SYSFS) {
			ret = msi_sysfs_populate_desc(dev, desc);
			if (ret)
				return ret;
		}
		allocated++;
	}
	return 0;
}

static int msi_domain_add_simple_msi_descs(struct msi_domain_info *info,
					   struct device *dev,
					   unsigned int num_descs)
{
	if (!(info->flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS))
		return 0;

	return msi_add_simple_msi_descs(dev, 0, num_descs);
}

/**
 * msi_domain_alloc_irqs_descs_locked - Allocate interrupts from a MSI interrupt domain
 * @domain:	The domain to allocate from
 * @dev:	Pointer to device struct of the device for which the interrupts
 *		are allocated
 * @nvec:	The number of interrupts to allocate
 *
 * Must be invoked from within a msi_lock_descs() / msi_unlock_descs()
 * pair. Use this for MSI irqdomains which implement their own vector
 * allocation/free.
 *
 * Return: %0 on success or an error code.
 */
int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev,
				       int nvec)
{
	struct msi_domain_info *info = domain->host_data;
	struct msi_domain_ops *ops = info->ops;
	int ret;

	lockdep_assert_held(&dev->msi.data->mutex);

	ret = msi_domain_add_simple_msi_descs(info, dev, nvec);
	if (ret)
		return ret;

	ret = ops->domain_alloc_irqs(domain, dev, nvec);
	if (ret)
		msi_domain_free_irqs_descs_locked(domain, dev);
	return ret;
}

/**
 * msi_domain_alloc_irqs - Allocate interrupts from a MSI interrupt domain
 * @domain:	The domain to allocate from
 * @dev:	Pointer to device struct of the device for which the interrupts
 *		are allocated
 * @nvec:	The number of interrupts to allocate
 *
 * Return: %0 on success or an error code.
 */
int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec)
{
	int ret;

	msi_lock_descs(dev);
	ret = msi_domain_alloc_irqs_descs_locked(domain, dev, nvec);
	msi_unlock_descs(dev);
	return ret;
}

void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
{
	struct msi_domain_info *info = domain->host_data;
	struct irq_data *irqd;
	struct msi_desc *desc;
	int i;

	/* Only handle MSI entries which have an interrupt associated */
	msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) {
		/* Make sure all interrupts are deactivated */
		for (i = 0; i < desc->nvec_used; i++) {
			irqd = irq_domain_get_irq_data(domain, desc->irq + i);
			if (irqd && irqd_is_activated(irqd))
				irq_domain_deactivate_irq(irqd);
		}

		irq_domain_free_irqs(desc->irq, desc->nvec_used);
		if (info->flags & MSI_FLAG_DEV_SYSFS)
			msi_sysfs_remove_desc(dev, desc);
		desc->irq = 0;
	}
}

static void msi_domain_free_msi_descs(struct msi_domain_info *info,
				      struct device *dev)
{
	if (info->flags & MSI_FLAG_FREE_MSI_DESCS)
		msi_free_msi_descs(dev);
}

/**
 * msi_domain_free_irqs_descs_locked - Free interrupts from a MSI interrupt @domain associated to @dev
 * @domain:	The domain to managing the interrupts
 * @dev:	Pointer to device struct of the device for which the interrupts
 *		are free
 *
 * Must be invoked from within a msi_lock_descs() / msi_unlock_descs()
 * pair. Use this for MSI irqdomains which implement their own vector
 * allocation.
 */
void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev)
{
	struct msi_domain_info *info = domain->host_data;
	struct msi_domain_ops *ops = info->ops;

	lockdep_assert_held(&dev->msi.data->mutex);

	ops->domain_free_irqs(domain, dev);
	msi_domain_free_msi_descs(info, dev);
}

/**
 * msi_domain_free_irqs - Free interrupts from a MSI interrupt @domain associated to @dev
 * @domain:	The domain to managing the interrupts
 * @dev:	Pointer to device struct of the device for which the interrupts
 *		are free
 */
void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
{
	msi_lock_descs(dev);
	msi_domain_free_irqs_descs_locked(domain, dev);
	msi_unlock_descs(dev);
}

/**
 * msi_get_domain_info - Get the MSI interrupt domain info for @domain
 * @domain:	The interrupt domain to retrieve data from
 *
 * Return: the pointer to the msi_domain_info stored in @domain->host_data.
 */
struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain)
{
	return (struct msi_domain_info *)domain->host_data;
}

#endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */