aboutsummaryrefslogtreecommitdiff
path: root/drivers/pci/msi.c
blob: 69b7be33b3a24768a460843a13c17a88c96a8024 (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
/*
 * File:	msi.c
 * Purpose:	PCI Message Signaled Interrupt (MSI)
 *
 * Copyright (C) 2003-2004 Intel
 * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
 */

#include <linux/err.h>
#include <linux/mm.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>
#include <linux/msi.h>
#include <linux/smp.h>
#include <linux/errno.h>
#include <linux/io.h>
#include <linux/slab.h>

#include "pci.h"
#include "msi.h"

static int pci_msi_enable = 1;

/* Arch hooks */

#ifndef arch_msi_check_device
int arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
{
	return 0;
}
#endif

#ifndef arch_setup_msi_irqs
int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
	struct msi_desc *entry;
	int ret;

	/*
	 * If an architecture wants to support multiple MSI, it needs to
	 * override arch_setup_msi_irqs()
	 */
	if (type == PCI_CAP_ID_MSI && nvec > 1)
		return 1;

	list_for_each_entry(entry, &dev->msi_list, list) {
		ret = arch_setup_msi_irq(dev, entry);
		if (ret < 0)
			return ret;
		if (ret > 0)
			return -ENOSPC;
	}

	return 0;
}
#endif

#ifndef arch_teardown_msi_irqs
void arch_teardown_msi_irqs(struct pci_dev *dev)
{
	struct msi_desc *entry;

	list_for_each_entry(entry, &dev->msi_list, list) {
		int i, nvec;
		if (entry->irq == 0)
			continue;
		nvec = 1 << entry->msi_attrib.multiple;
		for (i = 0; i < nvec; i++)
			arch_teardown_msi_irq(entry->irq + i);
	}
}
#endif

static void msi_set_enable(struct pci_dev *dev, int pos, int enable)
{
	u16 control;

	BUG_ON(!pos);

	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
	control &= ~PCI_MSI_FLAGS_ENABLE;
	if (enable)
		control |= PCI_MSI_FLAGS_ENABLE;
	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
}

static void msix_set_enable(struct pci_dev *dev, int enable)
{
	int pos;
	u16 control;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
	if (pos) {
		pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
		control &= ~PCI_MSIX_FLAGS_ENABLE;
		if (enable)
			control |= PCI_MSIX_FLAGS_ENABLE;
		pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
	}
}

static inline __attribute_const__ u32 msi_mask(unsigned x)
{
	/* Don't shift by >= width of type */
	if (x >= 5)
		return 0xffffffff;
	return (1 << (1 << x)) - 1;
}

static inline __attribute_const__ u32 msi_capable_mask(u16 control)
{
	return msi_mask((control >> 1) & 7);
}

static inline __attribute_const__ u32 msi_enabled_mask(u16 control)
{
	return msi_mask((control >> 4) & 7);
}

/*
 * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
 * mask all MSI interrupts by clearing the MSI enable bit does not work
 * reliably as devices without an INTx disable bit will then generate a
 * level IRQ which will never be cleared.
 */
static u32 __msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
{
	u32 mask_bits = desc->masked;

	if (!desc->msi_attrib.maskbit)
		return 0;

	mask_bits &= ~mask;
	mask_bits |= flag;
	pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits);

	return mask_bits;
}

static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
{
	desc->masked = __msi_mask_irq(desc, mask, flag);
}

/*
 * This internal function does not flush PCI writes to the device.
 * All users must ensure that they read from the device before either
 * assuming that the device state is up to date, or returning out of this
 * file.  This saves a few milliseconds when initialising devices with lots
 * of MSI-X interrupts.
 */
static u32 __msix_mask_irq(struct msi_desc *desc, u32 flag)
{
	u32 mask_bits = desc->masked;
	unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
						PCI_MSIX_ENTRY_VECTOR_CTRL;
	mask_bits &= ~1;
	mask_bits |= flag;
	writel(mask_bits, desc->mask_base + offset);

	return mask_bits;
}

static void msix_mask_irq(struct msi_desc *desc, u32 flag)
{
	desc->masked = __msix_mask_irq(desc, flag);
}

static void msi_set_mask_bit(unsigned irq, u32 flag)
{
	struct msi_desc *desc = get_irq_msi(irq);

	if (desc->msi_attrib.is_msix) {
		msix_mask_irq(desc, flag);
		readl(desc->mask_base);		/* Flush write to device */
	} else {
		unsigned offset = irq - desc->dev->irq;
		msi_mask_irq(desc, 1 << offset, flag << offset);
	}
}

void mask_msi_irq(unsigned int irq)
{
	msi_set_mask_bit(irq, 1);
}

void unmask_msi_irq(unsigned int irq)
{
	msi_set_mask_bit(irq, 0);
}

void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
{
	struct msi_desc *entry = get_irq_desc_msi(desc);

	BUG_ON(entry->dev->current_state != PCI_D0);

	if (entry->msi_attrib.is_msix) {
		void __iomem *base = entry->mask_base +
			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;

		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
		msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
	} else {
		struct pci_dev *dev = entry->dev;
		int pos = entry->msi_attrib.pos;
		u16 data;

		pci_read_config_dword(dev, msi_lower_address_reg(pos),
					&msg->address_lo);
		if (entry->msi_attrib.is_64) {
			pci_read_config_dword(dev, msi_upper_address_reg(pos),
						&msg->address_hi);
			pci_read_config_word(dev, msi_data_reg(pos, 1), &data);
		} else {
			msg->address_hi = 0;
			pci_read_config_word(dev, msi_data_reg(pos, 0), &data);
		}
		msg->data = data;
	}
}

void read_msi_msg(unsigned int irq, struct msi_msg *msg)
{
	struct irq_desc *desc = irq_to_desc(irq);

	read_msi_msg_desc(desc, msg);
}

void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
{
	struct msi_desc *entry = get_irq_desc_msi(desc);

	/* Assert that the cache is valid, assuming that
	 * valid messages are not all-zeroes. */
	BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo |
		 entry->msg.data));

	*msg = entry->msg;
}

void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
{
	struct irq_desc *desc = irq_to_desc(irq);

	get_cached_msi_msg_desc(desc, msg);
}

void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
{
	struct msi_desc *entry = get_irq_desc_msi(desc);

	if (entry->dev->current_state != PCI_D0) {
		/* Don't touch the hardware now */
	} else if (entry->msi_attrib.is_msix) {
		void __iomem *base;
		base = entry->mask_base +
			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;

		writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
		writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
		writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
	} else {
		struct pci_dev *dev = entry->dev;
		int pos = entry->msi_attrib.pos;
		u16 msgctl;

		pci_read_config_word(dev, msi_control_reg(pos), &msgctl);
		msgctl &= ~PCI_MSI_FLAGS_QSIZE;
		msgctl |= entry->msi_attrib.multiple << 4;
		pci_write_config_word(dev, msi_control_reg(pos), msgctl);

		pci_write_config_dword(dev, msi_lower_address_reg(pos),
					msg->address_lo);
		if (entry->msi_attrib.is_64) {
			pci_write_config_dword(dev, msi_upper_address_reg(pos),
						msg->address_hi);
			pci_write_config_word(dev, msi_data_reg(pos, 1),
						msg->data);
		} else {
			pci_write_config_word(dev, msi_data_reg(pos, 0),
						msg->data);
		}
	}
	entry->msg = *msg;
}

void write_msi_msg(unsigned int irq, struct msi_msg *msg)
{
	struct irq_desc *desc = irq_to_desc(irq);

	write_msi_msg_desc(desc, msg);
}

static void free_msi_irqs(struct pci_dev *dev)
{
	struct msi_desc *entry, *tmp;

	list_for_each_entry(entry, &dev->msi_list, list) {
		int i, nvec;
		if (!entry->irq)
			continue;
		nvec = 1 << entry->msi_attrib.multiple;
		for (i = 0; i < nvec; i++)
			BUG_ON(irq_has_action(entry->irq + i));
	}

	arch_teardown_msi_irqs(dev);

	list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) {
		if (entry->msi_attrib.is_msix) {
			if (list_is_last(&entry->list, &dev->msi_list))
				iounmap(entry->mask_base);
		}
		list_del(&entry->list);
		kfree(entry);
	}
}

static struct msi_desc *alloc_msi_entry(struct pci_dev *dev)
{
	struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
	if (!desc)
		return NULL;

	INIT_LIST_HEAD(&desc->list);
	desc->dev = dev;

	return desc;
}

static void pci_intx_for_msi(struct pci_dev *dev, int enable)
{
	if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
		pci_intx(dev, enable);
}

static void __pci_restore_msi_state(struct pci_dev *dev)
{
	int pos;
	u16 control;
	struct msi_desc *entry;

	if (!dev->msi_enabled)
		return;

	entry = get_irq_msi(dev->irq);
	pos = entry->msi_attrib.pos;

	pci_intx_for_msi(dev, 0);
	msi_set_enable(dev, pos, 0);
	write_msi_msg(dev->irq, &entry->msg);

	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
	msi_mask_irq(entry, msi_capable_mask(control), entry->masked);
	control &= ~PCI_MSI_FLAGS_QSIZE;
	control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
}

static void __pci_restore_msix_state(struct pci_dev *dev)
{
	int pos;
	struct msi_desc *entry;
	u16 control;

	if (!dev->msix_enabled)
		return;
	BUG_ON(list_empty(&dev->msi_list));
	entry = list_first_entry(&dev->msi_list, struct msi_desc, list);
	pos = entry->msi_attrib.pos;
	pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);

	/* route the table */
	pci_intx_for_msi(dev, 0);
	control |= PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL;
	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);

	list_for_each_entry(entry, &dev->msi_list, list) {
		write_msi_msg(entry->irq, &entry->msg);
		msix_mask_irq(entry, entry->masked);
	}

	control &= ~PCI_MSIX_FLAGS_MASKALL;
	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
}

void pci_restore_msi_state(struct pci_dev *dev)
{
	__pci_restore_msi_state(dev);
	__pci_restore_msix_state(dev);
}
EXPORT_SYMBOL_GPL(pci_restore_msi_state);

/**
 * msi_capability_init - configure device's MSI capability structure
 * @dev: pointer to the pci_dev data structure of MSI device function
 * @nvec: number of interrupts to allocate
 *
 * Setup the MSI capability structure of the device with the requested
 * number of interrupts.  A return value of zero indicates the successful
 * setup of an entry with the new MSI irq.  A negative return value indicates
 * an error, and a positive return value indicates the number of interrupts
 * which could have been allocated.
 */
static int msi_capability_init(struct pci_dev *dev, int nvec)
{
	struct msi_desc *entry;
	int pos, ret;
	u16 control;
	unsigned mask;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
	msi_set_enable(dev, pos, 0);	/* Disable MSI during set up */

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	/* MSI Entry Initialization */
	entry = alloc_msi_entry(dev);
	if (!entry)
		return -ENOMEM;

	entry->msi_attrib.is_msix	= 0;
	entry->msi_attrib.is_64		= is_64bit_address(control);
	entry->msi_attrib.entry_nr	= 0;
	entry->msi_attrib.maskbit	= is_mask_bit_support(control);
	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
	entry->msi_attrib.pos		= pos;

	entry->mask_pos = msi_mask_reg(pos, entry->msi_attrib.is_64);
	/* All MSIs are unmasked by default, Mask them all */
	if (entry->msi_attrib.maskbit)
		pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
	mask = msi_capable_mask(control);
	msi_mask_irq(entry, mask, mask);

	list_add_tail(&entry->list, &dev->msi_list);

	/* Configure MSI capability structure */
	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
	if (ret) {
		msi_mask_irq(entry, mask, ~mask);
		free_msi_irqs(dev);
		return ret;
	}

	/* Set MSI enabled bits	 */
	pci_intx_for_msi(dev, 0);
	msi_set_enable(dev, pos, 1);
	dev->msi_enabled = 1;

	dev->irq = entry->irq;
	return 0;
}

static void __iomem *msix_map_region(struct pci_dev *dev, unsigned pos,
							unsigned nr_entries)
{
	resource_size_t phys_addr;
	u32 table_offset;
	u8 bir;

	pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset);
	bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
	table_offset &= ~PCI_MSIX_FLAGS_BIRMASK;
	phys_addr = pci_resource_start(dev, bir) + table_offset;

	return ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
}

static int msix_setup_entries(struct pci_dev *dev, unsigned pos,
				void __iomem *base, struct msix_entry *entries,
				int nvec)
{
	struct msi_desc *entry;
	int i;

	for (i = 0; i < nvec; i++) {
		entry = alloc_msi_entry(dev);
		if (!entry) {
			if (!i)
				iounmap(base);
			else
				free_msi_irqs(dev);
			/* No enough memory. Don't try again */
			return -ENOMEM;
		}

		entry->msi_attrib.is_msix	= 1;
		entry->msi_attrib.is_64		= 1;
		entry->msi_attrib.entry_nr	= entries[i].entry;
		entry->msi_attrib.default_irq	= dev->irq;
		entry->msi_attrib.pos		= pos;
		entry->mask_base		= base;

		list_add_tail(&entry->list, &dev->msi_list);
	}

	return 0;
}

static void msix_program_entries(struct pci_dev *dev,
					struct msix_entry *entries)
{
	struct msi_desc *entry;
	int i = 0;

	list_for_each_entry(entry, &dev->msi_list, list) {
		int offset = entries[i].entry * PCI_MSIX_ENTRY_SIZE +
						PCI_MSIX_ENTRY_VECTOR_CTRL;

		entries[i].vector = entry->irq;
		set_irq_msi(entry->irq, entry);
		entry->masked = readl(entry->mask_base + offset);
		msix_mask_irq(entry, 1);
		i++;
	}
}

/**
 * msix_capability_init - configure device's MSI-X capability
 * @dev: pointer to the pci_dev data structure of MSI-X device function
 * @entries: pointer to an array of struct msix_entry entries
 * @nvec: number of @entries
 *
 * Setup the MSI-X capability structure of device function with a
 * single MSI-X irq. A return of zero indicates the successful setup of
 * requested MSI-X entries with allocated irqs or non-zero for otherwise.
 **/
static int msix_capability_init(struct pci_dev *dev,
				struct msix_entry *entries, int nvec)
{
	int pos, ret;
	u16 control;
	void __iomem *base;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
	pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);

	/* Ensure MSI-X is disabled while it is set up */
	control &= ~PCI_MSIX_FLAGS_ENABLE;
	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);

	/* Request & Map MSI-X table region */
	base = msix_map_region(dev, pos, multi_msix_capable(control));
	if (!base)
		return -ENOMEM;

	ret = msix_setup_entries(dev, pos, base, entries, nvec);
	if (ret)
		return ret;

	ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
	if (ret)
		goto error;

	/*
	 * Some devices require MSI-X to be enabled before we can touch the
	 * MSI-X registers.  We need to mask all the vectors to prevent
	 * interrupts coming in before they're fully set up.
	 */
	control |= PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE;
	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);

	msix_program_entries(dev, entries);

	/* Set MSI-X enabled bits and unmask the function */
	pci_intx_for_msi(dev, 0);
	dev->msix_enabled = 1;

	control &= ~PCI_MSIX_FLAGS_MASKALL;
	pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);

	return 0;

error:
	if (ret < 0) {
		/*
		 * If we had some success, report the number of irqs
		 * we succeeded in setting up.
		 */
		struct msi_desc *entry;
		int avail = 0;

		list_for_each_entry(entry, &dev->msi_list, list) {
			if (entry->irq != 0)
				avail++;
		}
		if (avail != 0)
			ret = avail;
	}

	free_msi_irqs(dev);

	return ret;
}

/**
 * pci_msi_check_device - check whether MSI may be enabled on a device
 * @dev: pointer to the pci_dev data structure of MSI device function
 * @nvec: how many MSIs have been requested ?
 * @type: are we checking for MSI or MSI-X ?
 *
 * Look at global flags, the device itself, and its parent busses
 * to determine if MSI/-X are supported for the device. If MSI/-X is
 * supported return 0, else return an error code.
 **/
static int pci_msi_check_device(struct pci_dev *dev, int nvec, int type)
{
	struct pci_bus *bus;
	int ret;

	/* MSI must be globally enabled and supported by the device */
	if (!pci_msi_enable || !dev || dev->no_msi)
		return -EINVAL;

	/*
	 * You can't ask to have 0 or less MSIs configured.
	 *  a) it's stupid ..
	 *  b) the list manipulation code assumes nvec >= 1.
	 */
	if (nvec < 1)
		return -ERANGE;

	/*
	 * Any bridge which does NOT route MSI transactions from its
	 * secondary bus to its primary bus must set NO_MSI flag on
	 * the secondary pci_bus.
	 * We expect only arch-specific PCI host bus controller driver
	 * or quirks for specific PCI bridges to be setting NO_MSI.
	 */
	for (bus = dev->bus; bus; bus = bus->parent)
		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
			return -EINVAL;

	ret = arch_msi_check_device(dev, nvec, type);
	if (ret)
		return ret;

	if (!pci_find_capability(dev, type))
		return -EINVAL;

	return 0;
}

/**
 * pci_enable_msi_block - configure device's MSI capability structure
 * @dev: device to configure
 * @nvec: number of interrupts to configure
 *
 * Allocate IRQs for a device with the MSI capability.
 * This function returns a negative errno if an error occurs.  If it
 * is unable to allocate the number of interrupts requested, it returns
 * the number of interrupts it might be able to allocate.  If it successfully
 * allocates at least the number of interrupts requested, it returns 0 and
 * updates the @dev's irq member to the lowest new interrupt number; the
 * other interrupt numbers allocated to this device are consecutive.
 */
int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
{
	int status, pos, maxvec;
	u16 msgctl;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
	if (!pos)
		return -EINVAL;
	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
	maxvec = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
	if (nvec > maxvec)
		return maxvec;

	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI);
	if (status)
		return status;

	WARN_ON(!!dev->msi_enabled);

	/* Check whether driver already requested MSI-X irqs */
	if (dev->msix_enabled) {
		dev_info(&dev->dev, "can't enable MSI "
			 "(MSI-X already enabled)\n");
		return -EINVAL;
	}

	status = msi_capability_init(dev, nvec);
	return status;
}
EXPORT_SYMBOL(pci_enable_msi_block);

void pci_msi_shutdown(struct pci_dev *dev)
{
	struct msi_desc *desc;
	u32 mask;
	u16 ctrl;
	unsigned pos;

	if (!pci_msi_enable || !dev || !dev->msi_enabled)
		return;

	BUG_ON(list_empty(&dev->msi_list));
	desc = list_first_entry(&dev->msi_list, struct msi_desc, list);
	pos = desc->msi_attrib.pos;

	msi_set_enable(dev, pos, 0);
	pci_intx_for_msi(dev, 1);
	dev->msi_enabled = 0;

	/* Return the device with MSI unmasked as initial states */
	pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &ctrl);
	mask = msi_capable_mask(ctrl);
	/* Keep cached state to be restored */
	__msi_mask_irq(desc, mask, ~mask);

	/* Restore dev->irq to its default pin-assertion irq */
	dev->irq = desc->msi_attrib.default_irq;
}

void pci_disable_msi(struct pci_dev *dev)
{
	if (!pci_msi_enable || !dev || !dev->msi_enabled)
		return;

	pci_msi_shutdown(dev);
	free_msi_irqs(dev);
}
EXPORT_SYMBOL(pci_disable_msi);

/**
 * pci_msix_table_size - return the number of device's MSI-X table entries
 * @dev: pointer to the pci_dev data structure of MSI-X device function
 */
int pci_msix_table_size(struct pci_dev *dev)
{
	int pos;
	u16 control;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
	if (!pos)
		return 0;

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	return multi_msix_capable(control);
}

/**
 * pci_enable_msix - configure device's MSI-X capability structure
 * @dev: pointer to the pci_dev data structure of MSI-X device function
 * @entries: pointer to an array of MSI-X entries
 * @nvec: number of MSI-X irqs requested for allocation by device driver
 *
 * Setup the MSI-X capability structure of device function with the number
 * of requested irqs upon its software driver call to request for
 * MSI-X mode enabled on its hardware device function. A return of zero
 * indicates the successful configuration of MSI-X capability structure
 * with new allocated MSI-X irqs. A return of < 0 indicates a failure.
 * Or a return of > 0 indicates that driver request is exceeding the number
 * of irqs or MSI-X vectors available. Driver should use the returned value to
 * re-send its request.
 **/
int pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries, int nvec)
{
	int status, nr_entries;
	int i, j;

	if (!entries)
		return -EINVAL;

	status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX);
	if (status)
		return status;

	nr_entries = pci_msix_table_size(dev);
	if (nvec > nr_entries)
		return nr_entries;

	/* Check for any invalid entries */
	for (i = 0; i < nvec; i++) {
		if (entries[i].entry >= nr_entries)
			return -EINVAL;		/* invalid entry */
		for (j = i + 1; j < nvec; j++) {
			if (entries[i].entry == entries[j].entry)
				return -EINVAL;	/* duplicate entry */
		}
	}
	WARN_ON(!!dev->msix_enabled);

	/* Check whether driver already requested for MSI irq */
	if (dev->msi_enabled) {
		dev_info(&dev->dev, "can't enable MSI-X "
		       "(MSI IRQ already assigned)\n");
		return -EINVAL;
	}
	status = msix_capability_init(dev, entries, nvec);
	return status;
}
EXPORT_SYMBOL(pci_enable_msix);

void pci_msix_shutdown(struct pci_dev *dev)
{
	struct msi_desc *entry;

	if (!pci_msi_enable || !dev || !dev->msix_enabled)
		return;

	/* Return the device with MSI-X masked as initial states */
	list_for_each_entry(entry, &dev->msi_list, list) {
		/* Keep cached states to be restored */
		__msix_mask_irq(entry, 1);
	}

	msix_set_enable(dev, 0);
	pci_intx_for_msi(dev, 1);
	dev->msix_enabled = 0;
}

void pci_disable_msix(struct pci_dev *dev)
{
	if (!pci_msi_enable || !dev || !dev->msix_enabled)
		return;

	pci_msix_shutdown(dev);
	free_msi_irqs(dev);
}
EXPORT_SYMBOL(pci_disable_msix);

/**
 * msi_remove_pci_irq_vectors - reclaim MSI(X) irqs to unused state
 * @dev: pointer to the pci_dev data structure of MSI(X) device function
 *
 * Being called during hotplug remove, from which the device function
 * is hot-removed. All previous assigned MSI/MSI-X irqs, if
 * allocated for this device function, are reclaimed to unused state,
 * which may be used later on.
 **/
void msi_remove_pci_irq_vectors(struct pci_dev *dev)
{
	if (!pci_msi_enable || !dev)
		return;

	if (dev->msi_enabled || dev->msix_enabled)
		free_msi_irqs(dev);
}

void pci_no_msi(void)
{
	pci_msi_enable = 0;
}

/**
 * pci_msi_enabled - is MSI enabled?
 *
 * Returns true if MSI has not been disabled by the command-line option
 * pci=nomsi.
 **/
int pci_msi_enabled(void)
{
	return pci_msi_enable;
}
EXPORT_SYMBOL(pci_msi_enabled);

void pci_msi_init_pci_dev(struct pci_dev *dev)
{
	INIT_LIST_HEAD(&dev->msi_list);
}