summaryrefslogtreecommitdiff
path: root/drivers/pci/msi.c
blob: a32e75a4417e8c4a3be948dea95d40e3a7d1eab8 (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
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
/*
 * 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/mm.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/ioport.h>
#include <linux/smp_lock.h>
#include <linux/pci.h>
#include <linux/proc_fs.h>

#include <asm/errno.h>
#include <asm/io.h>
#include <asm/smp.h>

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

static DEFINE_SPINLOCK(msi_lock);
static struct msi_desc* msi_desc[NR_IRQS] = { [0 ... NR_IRQS-1] = NULL };
static kmem_cache_t* msi_cachep;

static int pci_msi_enable = 1;
static int last_alloc_vector;
static int nr_released_vectors;

#ifndef CONFIG_X86_IO_APIC
int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
#endif

static struct msi_ops *msi_ops;

int
msi_register(struct msi_ops *ops)
{
	msi_ops = ops;
	return 0;
}

static int msi_cache_init(void)
{
	msi_cachep = kmem_cache_create("msi_cache", sizeof(struct msi_desc),
					0, SLAB_HWCACHE_ALIGN, NULL, NULL);
	if (!msi_cachep)
		return -ENOMEM;

	return 0;
}

static void msi_set_mask_bit(unsigned int vector, int flag)
{
	struct msi_desc *entry;

	entry = (struct msi_desc *)msi_desc[vector];
	if (!entry || !entry->dev || !entry->mask_base)
		return;
	switch (entry->msi_attrib.type) {
	case PCI_CAP_ID_MSI:
	{
		int		pos;
		u32		mask_bits;

		pos = (long)entry->mask_base;
		pci_read_config_dword(entry->dev, pos, &mask_bits);
		mask_bits &= ~(1);
		mask_bits |= flag;
		pci_write_config_dword(entry->dev, pos, mask_bits);
		break;
	}
	case PCI_CAP_ID_MSIX:
	{
		int offset = entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
			PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET;
		writel(flag, entry->mask_base + offset);
		break;
	}
	default:
		break;
	}
}

static void read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
	switch(entry->msi_attrib.type) {
	case PCI_CAP_ID_MSI:
	{
		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, 1), &data);
		}
		msg->data = data;
		break;
	}
	case PCI_CAP_ID_MSIX:
	{
		void __iomem *base;
		base = entry->mask_base +
			entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;

		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
		msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
		msg->data = readl(base + PCI_MSIX_ENTRY_DATA_OFFSET);
 		break;
 	}
 	default:
		BUG();
	}
}

static void write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
	switch (entry->msi_attrib.type) {
	case PCI_CAP_ID_MSI:
	{
		struct pci_dev *dev = entry->dev;
		int pos = entry->msi_attrib.pos;

		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);
		}
		break;
	}
	case PCI_CAP_ID_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_OFFSET);
		writel(msg->address_hi,
			base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
		writel(msg->data, base + PCI_MSIX_ENTRY_DATA_OFFSET);
		break;
	}
	default:
		BUG();
	}
}

#ifdef CONFIG_SMP
static void set_msi_affinity(unsigned int irq, cpumask_t cpu_mask)
{
	struct msi_desc *entry;
	struct msi_msg msg;

	entry = msi_desc[irq];
	if (!entry || !entry->dev)
		return;

	read_msi_msg(entry, &msg);
	msi_ops->target(irq, cpu_mask, &msg);
	write_msi_msg(entry, &msg);
	set_native_irq_info(irq, cpu_mask);
}
#else
#define set_msi_affinity NULL
#endif /* CONFIG_SMP */

static void mask_MSI_irq(unsigned int vector)
{
	msi_set_mask_bit(vector, 1);
}

static void unmask_MSI_irq(unsigned int vector)
{
	msi_set_mask_bit(vector, 0);
}

static unsigned int startup_msi_irq_wo_maskbit(unsigned int vector)
{
	struct msi_desc *entry;
	unsigned long flags;

	spin_lock_irqsave(&msi_lock, flags);
	entry = msi_desc[vector];
	if (!entry || !entry->dev) {
		spin_unlock_irqrestore(&msi_lock, flags);
		return 0;
	}
	entry->msi_attrib.state = 1;	/* Mark it active */
	spin_unlock_irqrestore(&msi_lock, flags);

	return 0;	/* never anything pending */
}

static unsigned int startup_msi_irq_w_maskbit(unsigned int vector)
{
	startup_msi_irq_wo_maskbit(vector);
	unmask_MSI_irq(vector);
	return 0;	/* never anything pending */
}

static void shutdown_msi_irq(unsigned int vector)
{
	struct msi_desc *entry;
	unsigned long flags;

	spin_lock_irqsave(&msi_lock, flags);
	entry = msi_desc[vector];
	if (entry && entry->dev)
		entry->msi_attrib.state = 0;	/* Mark it not active */
	spin_unlock_irqrestore(&msi_lock, flags);
}

static void end_msi_irq_wo_maskbit(unsigned int vector)
{
	move_native_irq(vector);
	ack_APIC_irq();
}

static void end_msi_irq_w_maskbit(unsigned int vector)
{
	move_native_irq(vector);
	unmask_MSI_irq(vector);
	ack_APIC_irq();
}

static void do_nothing(unsigned int vector)
{
}

/*
 * Interrupt Type for MSI-X PCI/PCI-X/PCI-Express Devices,
 * which implement the MSI-X Capability Structure.
 */
static struct hw_interrupt_type msix_irq_type = {
	.typename	= "PCI-MSI-X",
	.startup	= startup_msi_irq_w_maskbit,
	.shutdown	= shutdown_msi_irq,
	.enable		= unmask_MSI_irq,
	.disable	= mask_MSI_irq,
	.ack		= mask_MSI_irq,
	.end		= end_msi_irq_w_maskbit,
	.set_affinity	= set_msi_affinity
};

/*
 * Interrupt Type for MSI PCI/PCI-X/PCI-Express Devices,
 * which implement the MSI Capability Structure with
 * Mask-and-Pending Bits.
 */
static struct hw_interrupt_type msi_irq_w_maskbit_type = {
	.typename	= "PCI-MSI",
	.startup	= startup_msi_irq_w_maskbit,
	.shutdown	= shutdown_msi_irq,
	.enable		= unmask_MSI_irq,
	.disable	= mask_MSI_irq,
	.ack		= mask_MSI_irq,
	.end		= end_msi_irq_w_maskbit,
	.set_affinity	= set_msi_affinity
};

/*
 * Interrupt Type for MSI PCI/PCI-X/PCI-Express Devices,
 * which implement the MSI Capability Structure without
 * Mask-and-Pending Bits.
 */
static struct hw_interrupt_type msi_irq_wo_maskbit_type = {
	.typename	= "PCI-MSI",
	.startup	= startup_msi_irq_wo_maskbit,
	.shutdown	= shutdown_msi_irq,
	.enable		= do_nothing,
	.disable	= do_nothing,
	.ack		= do_nothing,
	.end		= end_msi_irq_wo_maskbit,
	.set_affinity	= set_msi_affinity
};

static int msi_free_vector(struct pci_dev* dev, int vector, int reassign);
static int assign_msi_vector(void)
{
	static int new_vector_avail = 1;
	int vector;
	unsigned long flags;

	/*
	 * msi_lock is provided to ensure that successful allocation of MSI
	 * vector is assigned unique among drivers.
	 */
	spin_lock_irqsave(&msi_lock, flags);

	if (!new_vector_avail) {
		int free_vector = 0;

		/*
	 	 * vector_irq[] = -1 indicates that this specific vector is:
	 	 * - assigned for MSI (since MSI have no associated IRQ) or
	 	 * - assigned for legacy if less than 16, or
	 	 * - having no corresponding 1:1 vector-to-IOxAPIC IRQ mapping
	 	 * vector_irq[] = 0 indicates that this vector, previously
		 * assigned for MSI, is freed by hotplug removed operations.
		 * This vector will be reused for any subsequent hotplug added
		 * operations.
	 	 * vector_irq[] > 0 indicates that this vector is assigned for
		 * IOxAPIC IRQs. This vector and its value provides a 1-to-1
		 * vector-to-IOxAPIC IRQ mapping.
	 	 */
		for (vector = FIRST_DEVICE_VECTOR; vector < NR_IRQS; vector++) {
			if (vector_irq[vector] != 0)
				continue;
			free_vector = vector;
			if (!msi_desc[vector])
			      	break;
			else
				continue;
		}
		if (!free_vector) {
			spin_unlock_irqrestore(&msi_lock, flags);
			return -EBUSY;
		}
		vector_irq[free_vector] = -1;
		nr_released_vectors--;
		spin_unlock_irqrestore(&msi_lock, flags);
		if (msi_desc[free_vector] != NULL) {
			struct pci_dev *dev;
			int tail;

			/* free all linked vectors before re-assign */
			do {
				spin_lock_irqsave(&msi_lock, flags);
				dev = msi_desc[free_vector]->dev;
				tail = msi_desc[free_vector]->link.tail;
				spin_unlock_irqrestore(&msi_lock, flags);
				msi_free_vector(dev, tail, 1);
			} while (free_vector != tail);
		}

		return free_vector;
	}
	vector = assign_irq_vector(AUTO_ASSIGN);
	last_alloc_vector = vector;
	if (vector  == LAST_DEVICE_VECTOR)
		new_vector_avail = 0;

	spin_unlock_irqrestore(&msi_lock, flags);
	return vector;
}

static int get_new_vector(void)
{
	int vector = assign_msi_vector();

	if (vector > 0)
		set_intr_gate(vector, interrupt[vector]);

	return vector;
}

static int msi_init(void)
{
	static int status = -ENOMEM;

	if (!status)
		return status;

	if (pci_msi_quirk) {
		pci_msi_enable = 0;
		printk(KERN_WARNING "PCI: MSI quirk detected. MSI disabled.\n");
		status = -EINVAL;
		return status;
	}

	status = msi_arch_init();
	if (status < 0) {
		pci_msi_enable = 0;
		printk(KERN_WARNING
		       "PCI: MSI arch init failed.  MSI disabled.\n");
		return status;
	}

	if (! msi_ops) {
		printk(KERN_WARNING
		       "PCI: MSI ops not registered. MSI disabled.\n");
		status = -EINVAL;
		return status;
	}

	last_alloc_vector = assign_irq_vector(AUTO_ASSIGN);
	status = msi_cache_init();
	if (status < 0) {
		pci_msi_enable = 0;
		printk(KERN_WARNING "PCI: MSI cache init failed\n");
		return status;
	}

	if (last_alloc_vector < 0) {
		pci_msi_enable = 0;
		printk(KERN_WARNING "PCI: No interrupt vectors available for MSI\n");
		status = -EBUSY;
		return status;
	}
	vector_irq[last_alloc_vector] = 0;
	nr_released_vectors++;

	return status;
}

static int get_msi_vector(struct pci_dev *dev)
{
	return get_new_vector();
}

static struct msi_desc* alloc_msi_entry(void)
{
	struct msi_desc *entry;

	entry = kmem_cache_zalloc(msi_cachep, GFP_KERNEL);
	if (!entry)
		return NULL;

	entry->link.tail = entry->link.head = 0;	/* single message */
	entry->dev = NULL;

	return entry;
}

static void attach_msi_entry(struct msi_desc *entry, int vector)
{
	unsigned long flags;

	spin_lock_irqsave(&msi_lock, flags);
	msi_desc[vector] = entry;
	spin_unlock_irqrestore(&msi_lock, flags);
}

static void irq_handler_init(int cap_id, int pos, int mask)
{
	unsigned long flags;

	spin_lock_irqsave(&irq_desc[pos].lock, flags);
	if (cap_id == PCI_CAP_ID_MSIX)
		irq_desc[pos].chip = &msix_irq_type;
	else {
		if (!mask)
			irq_desc[pos].chip = &msi_irq_wo_maskbit_type;
		else
			irq_desc[pos].chip = &msi_irq_w_maskbit_type;
	}
	spin_unlock_irqrestore(&irq_desc[pos].lock, flags);
}

static void enable_msi_mode(struct pci_dev *dev, int pos, int type)
{
	u16 control;

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	if (type == PCI_CAP_ID_MSI) {
		/* Set enabled bits to single MSI & enable MSI_enable bit */
		msi_enable(control, 1);
		pci_write_config_word(dev, msi_control_reg(pos), control);
		dev->msi_enabled = 1;
	} else {
		msix_enable(control);
		pci_write_config_word(dev, msi_control_reg(pos), control);
		dev->msix_enabled = 1;
	}
    	if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
		/* PCI Express Endpoint device detected */
		pci_intx(dev, 0);  /* disable intx */
	}
}

void disable_msi_mode(struct pci_dev *dev, int pos, int type)
{
	u16 control;

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	if (type == PCI_CAP_ID_MSI) {
		/* Set enabled bits to single MSI & enable MSI_enable bit */
		msi_disable(control);
		pci_write_config_word(dev, msi_control_reg(pos), control);
		dev->msi_enabled = 0;
	} else {
		msix_disable(control);
		pci_write_config_word(dev, msi_control_reg(pos), control);
		dev->msix_enabled = 0;
	}
    	if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
		/* PCI Express Endpoint device detected */
		pci_intx(dev, 1);  /* enable intx */
	}
}

static int msi_lookup_vector(struct pci_dev *dev, int type)
{
	int vector;
	unsigned long flags;

	spin_lock_irqsave(&msi_lock, flags);
	for (vector = FIRST_DEVICE_VECTOR; vector < NR_IRQS; vector++) {
		if (!msi_desc[vector] || msi_desc[vector]->dev != dev ||
			msi_desc[vector]->msi_attrib.type != type ||
			msi_desc[vector]->msi_attrib.default_vector != dev->irq)
			continue;
		spin_unlock_irqrestore(&msi_lock, flags);
		/* This pre-assigned MSI vector for this device
		   already exits. Override dev->irq with this vector */
		dev->irq = vector;
		return 0;
	}
	spin_unlock_irqrestore(&msi_lock, flags);

	return -EACCES;
}

void pci_scan_msi_device(struct pci_dev *dev)
{
	if (!dev)
		return;
}

#ifdef CONFIG_PM
int pci_save_msi_state(struct pci_dev *dev)
{
	int pos, i = 0;
	u16 control;
	struct pci_cap_saved_state *save_state;
	u32 *cap;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
	if (pos <= 0 || dev->no_msi)
		return 0;

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	if (!(control & PCI_MSI_FLAGS_ENABLE))
		return 0;

	save_state = kzalloc(sizeof(struct pci_cap_saved_state) + sizeof(u32) * 5,
		GFP_KERNEL);
	if (!save_state) {
		printk(KERN_ERR "Out of memory in pci_save_msi_state\n");
		return -ENOMEM;
	}
	cap = &save_state->data[0];

	pci_read_config_dword(dev, pos, &cap[i++]);
	control = cap[0] >> 16;
	pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, &cap[i++]);
	if (control & PCI_MSI_FLAGS_64BIT) {
		pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, &cap[i++]);
		pci_read_config_dword(dev, pos + PCI_MSI_DATA_64, &cap[i++]);
	} else
		pci_read_config_dword(dev, pos + PCI_MSI_DATA_32, &cap[i++]);
	if (control & PCI_MSI_FLAGS_MASKBIT)
		pci_read_config_dword(dev, pos + PCI_MSI_MASK_BIT, &cap[i++]);
	save_state->cap_nr = PCI_CAP_ID_MSI;
	pci_add_saved_cap(dev, save_state);
	return 0;
}

void pci_restore_msi_state(struct pci_dev *dev)
{
	int i = 0, pos;
	u16 control;
	struct pci_cap_saved_state *save_state;
	u32 *cap;

	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_MSI);
	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
	if (!save_state || pos <= 0)
		return;
	cap = &save_state->data[0];

	control = cap[i++] >> 16;
	pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, cap[i++]);
	if (control & PCI_MSI_FLAGS_64BIT) {
		pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, cap[i++]);
		pci_write_config_dword(dev, pos + PCI_MSI_DATA_64, cap[i++]);
	} else
		pci_write_config_dword(dev, pos + PCI_MSI_DATA_32, cap[i++]);
	if (control & PCI_MSI_FLAGS_MASKBIT)
		pci_write_config_dword(dev, pos + PCI_MSI_MASK_BIT, cap[i++]);
	pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
	enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
	pci_remove_saved_cap(save_state);
	kfree(save_state);
}

int pci_save_msix_state(struct pci_dev *dev)
{
	int pos;
	int temp;
	int vector, head, tail = 0;
	u16 control;
	struct pci_cap_saved_state *save_state;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
	if (pos <= 0 || dev->no_msi)
		return 0;

	/* save the capability */
	pci_read_config_word(dev, msi_control_reg(pos), &control);
	if (!(control & PCI_MSIX_FLAGS_ENABLE))
		return 0;
	save_state = kzalloc(sizeof(struct pci_cap_saved_state) + sizeof(u16),
		GFP_KERNEL);
	if (!save_state) {
		printk(KERN_ERR "Out of memory in pci_save_msix_state\n");
		return -ENOMEM;
	}
	*((u16 *)&save_state->data[0]) = control;

	/* save the table */
	temp = dev->irq;
	if (msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
		kfree(save_state);
		return -EINVAL;
	}

	vector = head = dev->irq;
	while (head != tail) {
		struct msi_desc *entry;

		entry = msi_desc[vector];
		read_msi_msg(entry, &entry->msg_save);

		tail = msi_desc[vector]->link.tail;
		vector = tail;
	}
	dev->irq = temp;

	save_state->cap_nr = PCI_CAP_ID_MSIX;
	pci_add_saved_cap(dev, save_state);
	return 0;
}

void pci_restore_msix_state(struct pci_dev *dev)
{
	u16 save;
	int pos;
	int vector, head, tail = 0;
	struct msi_desc *entry;
	int temp;
	struct pci_cap_saved_state *save_state;

	save_state = pci_find_saved_cap(dev, PCI_CAP_ID_MSIX);
	if (!save_state)
		return;
	save = *((u16 *)&save_state->data[0]);
	pci_remove_saved_cap(save_state);
	kfree(save_state);

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

	/* route the table */
	temp = dev->irq;
	if (msi_lookup_vector(dev, PCI_CAP_ID_MSIX))
		return;
	vector = head = dev->irq;
	while (head != tail) {
		entry = msi_desc[vector];
		write_msi_msg(entry, &entry->msg_save);

		tail = msi_desc[vector]->link.tail;
		vector = tail;
	}
	dev->irq = temp;

	pci_write_config_word(dev, msi_control_reg(pos), save);
	enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
}
#endif

static int msi_register_init(struct pci_dev *dev, struct msi_desc *entry)
{
	int status;
	struct msi_msg msg;
	int pos;
	u16 control;

	pos = entry->msi_attrib.pos;
	pci_read_config_word(dev, msi_control_reg(pos), &control);

	/* Configure MSI capability structure */
	status = msi_ops->setup(dev, dev->irq, &msg);
	if (status < 0)
		return status;

	write_msi_msg(entry, &msg);
	if (entry->msi_attrib.maskbit) {
		unsigned int maskbits, temp;
		/* All MSIs are unmasked by default, Mask them all */
		pci_read_config_dword(dev,
			msi_mask_bits_reg(pos, is_64bit_address(control)),
			&maskbits);
		temp = (1 << multi_msi_capable(control));
		temp = ((temp - 1) & ~temp);
		maskbits |= temp;
		pci_write_config_dword(dev,
			msi_mask_bits_reg(pos, is_64bit_address(control)),
			maskbits);
	}

	return 0;
}

/**
 * msi_capability_init - configure device's MSI capability structure
 * @dev: pointer to the pci_dev data structure of MSI device function
 *
 * Setup the MSI capability structure of device function with a single
 * MSI vector, regardless of device function is capable of handling
 * multiple messages. A return of zero indicates the successful setup
 * of an entry zero with the new MSI vector or non-zero for otherwise.
 **/
static int msi_capability_init(struct pci_dev *dev)
{
	int status;
	struct msi_desc *entry;
	int pos, vector;
	u16 control;

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

	vector = get_msi_vector(dev);
	if (vector < 0) {
		kmem_cache_free(msi_cachep, entry);
		return -EBUSY;
	}
	entry->link.head = vector;
	entry->link.tail = vector;
	entry->msi_attrib.type = PCI_CAP_ID_MSI;
	entry->msi_attrib.state = 0;			/* Mark it not active */
	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_vector = dev->irq;	/* Save IOAPIC IRQ */
	entry->msi_attrib.pos = pos;
	dev->irq = vector;
	entry->dev = dev;
	if (is_mask_bit_support(control)) {
		entry->mask_base = (void __iomem *)(long)msi_mask_bits_reg(pos,
				is_64bit_address(control));
	}
	/* Replace with MSI handler */
	irq_handler_init(PCI_CAP_ID_MSI, vector, entry->msi_attrib.maskbit);
	/* Configure MSI capability structure */
	status = msi_register_init(dev, entry);
	if (status != 0) {
		dev->irq = entry->msi_attrib.default_vector;
		kmem_cache_free(msi_cachep, entry);
		return status;
	}

	attach_msi_entry(entry, vector);
	/* Set MSI enabled bits	 */
	enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);

	return 0;
}

/**
 * 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 vector. A return of zero indicates the successful setup of
 * requested MSI-X entries with allocated vectors or non-zero for otherwise.
 **/
static int msix_capability_init(struct pci_dev *dev,
				struct msix_entry *entries, int nvec)
{
	struct msi_desc *head = NULL, *tail = NULL, *entry = NULL;
	struct msi_msg msg;
	int status;
	int vector, pos, i, j, nr_entries, temp = 0;
	unsigned long phys_addr;
	u32 table_offset;
 	u16 control;
	u8 bir;
	void __iomem *base;

   	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
	/* Request & Map MSI-X table region */
 	pci_read_config_word(dev, msi_control_reg(pos), &control);
	nr_entries = multi_msix_capable(control);

 	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;
	base = ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
	if (base == NULL)
		return -ENOMEM;

	/* MSI-X Table Initialization */
	for (i = 0; i < nvec; i++) {
		entry = alloc_msi_entry();
		if (!entry)
			break;
		vector = get_msi_vector(dev);
		if (vector < 0) {
			kmem_cache_free(msi_cachep, entry);
			break;
		}

 		j = entries[i].entry;
 		entries[i].vector = vector;
		entry->msi_attrib.type = PCI_CAP_ID_MSIX;
 		entry->msi_attrib.state = 0;		/* Mark it not active */
		entry->msi_attrib.is_64 = 1;
		entry->msi_attrib.entry_nr = j;
		entry->msi_attrib.maskbit = 1;
		entry->msi_attrib.default_vector = dev->irq;
		entry->msi_attrib.pos = pos;
		entry->dev = dev;
		entry->mask_base = base;
		if (!head) {
			entry->link.head = vector;
			entry->link.tail = vector;
			head = entry;
		} else {
			entry->link.head = temp;
			entry->link.tail = tail->link.tail;
			tail->link.tail = vector;
			head->link.head = vector;
		}
		temp = vector;
		tail = entry;
		/* Replace with MSI-X handler */
		irq_handler_init(PCI_CAP_ID_MSIX, vector, 1);
		/* Configure MSI-X capability structure */
		status = msi_ops->setup(dev, vector, &msg);
		if (status < 0)
			break;

		write_msi_msg(entry, &msg);
		attach_msi_entry(entry, vector);
	}
	if (i != nvec) {
		int avail = i - 1;
		i--;
		for (; i >= 0; i--) {
			vector = (entries + i)->vector;
			msi_free_vector(dev, vector, 0);
			(entries + i)->vector = 0;
		}
		/* If we had some success report the number of irqs
		 * we succeeded in setting up.
		 */
		if (avail <= 0)
			avail = -EBUSY;
		return avail;
	}
	/* Set MSI-X enabled bits */
	enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);

	return 0;
}

/**
 * pci_msi_supported - check whether MSI may be enabled on device
 * @dev: pointer to the pci_dev data structure of MSI device function
 *
 * MSI must be globally enabled and supported by the device and its root
 * bus. But, the root bus is not easy to find since some architectures
 * have virtual busses on top of the PCI hierarchy (for instance the
 * hypertransport bus), while the actual bus where MSI must be supported
 * is below. So we test the MSI flag on all parent busses and assume
 * that no quirk will ever set the NO_MSI flag on a non-root bus.
 **/
static
int pci_msi_supported(struct pci_dev * dev)
{
	struct pci_bus *bus;

	if (!pci_msi_enable || !dev || dev->no_msi)
		return -EINVAL;

	/* check MSI flags of all parent busses */
	for (bus = dev->bus; bus; bus = bus->parent)
		if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
			return -EINVAL;

	return 0;
}

/**
 * pci_enable_msi - configure device's MSI capability structure
 * @dev: pointer to the pci_dev data structure of MSI device function
 *
 * Setup the MSI capability structure of device function with
 * a single MSI vector upon its software driver call to request for
 * MSI mode enabled on its hardware device function. A return of zero
 * indicates the successful setup of an entry zero with the new MSI
 * vector or non-zero for otherwise.
 **/
int pci_enable_msi(struct pci_dev* dev)
{
	int pos, temp, status;
	u16 control;

	if (pci_msi_supported(dev) < 0)
		return -EINVAL;

	temp = dev->irq;

	status = msi_init();
	if (status < 0)
		return status;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
	if (!pos)
		return -EINVAL;

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	if (!is_64bit_address(control) && msi_ops->needs_64bit_address)
		return -EINVAL;

	WARN_ON(!msi_lookup_vector(dev, PCI_CAP_ID_MSI));

	/* Check whether driver already requested for MSI-X vectors */
	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
	if (pos > 0 && !msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
			printk(KERN_INFO "PCI: %s: Can't enable MSI.  "
			       "Device already has MSI-X vectors assigned\n",
			       pci_name(dev));
			dev->irq = temp;
			return -EINVAL;
	}
	status = msi_capability_init(dev);
	return status;
}

void pci_disable_msi(struct pci_dev* dev)
{
	struct msi_desc *entry;
	int pos, default_vector;
	u16 control;
	unsigned long flags;

	if (!pci_msi_enable)
		return;
	if (!dev)
		return;

	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
	if (!pos)
		return;

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	if (!(control & PCI_MSI_FLAGS_ENABLE))
		return;

	disable_msi_mode(dev, pos, PCI_CAP_ID_MSI);

	spin_lock_irqsave(&msi_lock, flags);
	entry = msi_desc[dev->irq];
	if (!entry || !entry->dev || entry->msi_attrib.type != PCI_CAP_ID_MSI) {
		spin_unlock_irqrestore(&msi_lock, flags);
		return;
	}
	if (entry->msi_attrib.state) {
		spin_unlock_irqrestore(&msi_lock, flags);
		printk(KERN_WARNING "PCI: %s: pci_disable_msi() called without "
		       "free_irq() on MSI vector %d\n",
		       pci_name(dev), dev->irq);
		BUG_ON(entry->msi_attrib.state > 0);
	} else {
		default_vector = entry->msi_attrib.default_vector;
		spin_unlock_irqrestore(&msi_lock, flags);
		msi_free_vector(dev, dev->irq, 0);

		/* Restore dev->irq to its default pin-assertion vector */
		dev->irq = default_vector;
	}
}

static int msi_free_vector(struct pci_dev* dev, int vector, int reassign)
{
	struct msi_desc *entry;
	int head, entry_nr, type;
	void __iomem *base;
	unsigned long flags;

	msi_ops->teardown(vector);

	spin_lock_irqsave(&msi_lock, flags);
	entry = msi_desc[vector];
	if (!entry || entry->dev != dev) {
		spin_unlock_irqrestore(&msi_lock, flags);
		return -EINVAL;
	}
	type = entry->msi_attrib.type;
	entry_nr = entry->msi_attrib.entry_nr;
	head = entry->link.head;
	base = entry->mask_base;
	msi_desc[entry->link.head]->link.tail = entry->link.tail;
	msi_desc[entry->link.tail]->link.head = entry->link.head;
	entry->dev = NULL;
	if (!reassign) {
		vector_irq[vector] = 0;
		nr_released_vectors++;
	}
	msi_desc[vector] = NULL;
	spin_unlock_irqrestore(&msi_lock, flags);

	kmem_cache_free(msi_cachep, entry);

	if (type == PCI_CAP_ID_MSIX) {
		if (!reassign)
			writel(1, base +
				entry_nr * PCI_MSIX_ENTRY_SIZE +
				PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);

		if (head == vector)
			iounmap(base);
	}

	return 0;
}

/**
 * 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 vectors requested for allocation by device driver
 *
 * Setup the MSI-X capability structure of device function with the number
 * of requested vectors 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 vectors. A return of < 0 indicates a failure.
 * Or a return of > 0 indicates that driver request is exceeding the number
 * of 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, pos, nr_entries;
	int i, j, temp;
	u16 control;

	if (!entries || pci_msi_supported(dev) < 0)
 		return -EINVAL;

	status = msi_init();
	if (status < 0)
		return status;

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

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	nr_entries = multi_msix_capable(control);
	if (nvec > nr_entries)
		return -EINVAL;

	/* 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 */
		}
	}
	temp = dev->irq;
	WARN_ON(!msi_lookup_vector(dev, PCI_CAP_ID_MSIX));

	/* Check whether driver already requested for MSI vector */
   	if (pci_find_capability(dev, PCI_CAP_ID_MSI) > 0 &&
		!msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
		printk(KERN_INFO "PCI: %s: Can't enable MSI-X.  "
		       "Device already has an MSI vector assigned\n",
		       pci_name(dev));
		dev->irq = temp;
		return -EINVAL;
	}
	status = msix_capability_init(dev, entries, nvec);
	return status;
}

void pci_disable_msix(struct pci_dev* dev)
{
	int pos, temp;
	u16 control;

	if (!pci_msi_enable)
		return;
	if (!dev)
		return;

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

	pci_read_config_word(dev, msi_control_reg(pos), &control);
	if (!(control & PCI_MSIX_FLAGS_ENABLE))
		return;

	disable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);

	temp = dev->irq;
	if (!msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
		int state, vector, head, tail = 0, warning = 0;
		unsigned long flags;

		vector = head = dev->irq;
		dev->irq = temp;			/* Restore pin IRQ */
		while (head != tail) {
			spin_lock_irqsave(&msi_lock, flags);
			state = msi_desc[vector]->msi_attrib.state;
			tail = msi_desc[vector]->link.tail;
			spin_unlock_irqrestore(&msi_lock, flags);
			if (state)
				warning = 1;
			else if (vector != head)	/* Release MSI-X vector */
				msi_free_vector(dev, vector, 0);
			vector = tail;
		}
		msi_free_vector(dev, vector, 0);
		if (warning) {
			printk(KERN_WARNING "PCI: %s: pci_disable_msix() called without "
			       "free_irq() on all MSI-X vectors\n",
			       pci_name(dev));
			BUG_ON(warning > 0);
		}
	}
}

/**
 * msi_remove_pci_irq_vectors - reclaim MSI(X) vectors 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 vectors, 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)
{
	int state, pos, temp;
	unsigned long flags;

	if (!pci_msi_enable || !dev)
 		return;

	temp = dev->irq;		/* Save IOAPIC IRQ */
	pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
	if (pos > 0 && !msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
		spin_lock_irqsave(&msi_lock, flags);
		state = msi_desc[dev->irq]->msi_attrib.state;
		spin_unlock_irqrestore(&msi_lock, flags);
		if (state) {
			printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
			       "called without free_irq() on MSI vector %d\n",
			       pci_name(dev), dev->irq);
			BUG_ON(state > 0);
		} else /* Release MSI vector assigned to this device */
			msi_free_vector(dev, dev->irq, 0);
		dev->irq = temp;		/* Restore IOAPIC IRQ */
	}
	pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
	if (pos > 0 && !msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
		int vector, head, tail = 0, warning = 0;
		void __iomem *base = NULL;

		vector = head = dev->irq;
		while (head != tail) {
			spin_lock_irqsave(&msi_lock, flags);
			state = msi_desc[vector]->msi_attrib.state;
			tail = msi_desc[vector]->link.tail;
			base = msi_desc[vector]->mask_base;
			spin_unlock_irqrestore(&msi_lock, flags);
			if (state)
				warning = 1;
			else if (vector != head) /* Release MSI-X vector */
				msi_free_vector(dev, vector, 0);
			vector = tail;
		}
		msi_free_vector(dev, vector, 0);
		if (warning) {
			iounmap(base);
			printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
			       "called without free_irq() on all MSI-X vectors\n",
			       pci_name(dev));
			BUG_ON(warning > 0);
		}
		dev->irq = temp;		/* Restore IOAPIC IRQ */
	}
}

void pci_no_msi(void)
{
	pci_msi_enable = 0;
}

EXPORT_SYMBOL(pci_enable_msi);
EXPORT_SYMBOL(pci_disable_msi);
EXPORT_SYMBOL(pci_enable_msix);
EXPORT_SYMBOL(pci_disable_msix);