aboutsummaryrefslogtreecommitdiff
path: root/drivers/iommu/intel_irq_remapping.c
blob: ac596928f6b40af32e9c44ecf388ebf7ed4b10ed (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
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477

#define pr_fmt(fmt)     "DMAR-IR: " fmt

#include <linux/interrupt.h>
#include <linux/dmar.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/jiffies.h>
#include <linux/hpet.h>
#include <linux/pci.h>
#include <linux/irq.h>
#include <linux/intel-iommu.h>
#include <linux/acpi.h>
#include <linux/irqdomain.h>
#include <linux/crash_dump.h>
#include <asm/io_apic.h>
#include <asm/smp.h>
#include <asm/cpu.h>
#include <asm/irq_remapping.h>
#include <asm/pci-direct.h>
#include <asm/msidef.h>

#include "irq_remapping.h"

enum irq_mode {
	IRQ_REMAPPING,
	IRQ_POSTING,
};

struct ioapic_scope {
	struct intel_iommu *iommu;
	unsigned int id;
	unsigned int bus;	/* PCI bus number */
	unsigned int devfn;	/* PCI devfn number */
};

struct hpet_scope {
	struct intel_iommu *iommu;
	u8 id;
	unsigned int bus;
	unsigned int devfn;
};

struct irq_2_iommu {
	struct intel_iommu *iommu;
	u16 irte_index;
	u16 sub_handle;
	u8  irte_mask;
	enum irq_mode mode;
};

struct intel_ir_data {
	struct irq_2_iommu			irq_2_iommu;
	struct irte				irte_entry;
	union {
		struct msi_msg			msi_entry;
	};
};

#define IR_X2APIC_MODE(mode) (mode ? (1 << 11) : 0)
#define IRTE_DEST(dest) ((eim_mode) ? dest : dest << 8)

static int __read_mostly eim_mode;
static struct ioapic_scope ir_ioapic[MAX_IO_APICS];
static struct hpet_scope ir_hpet[MAX_HPET_TBS];

/*
 * Lock ordering:
 * ->dmar_global_lock
 *	->irq_2_ir_lock
 *		->qi->q_lock
 *	->iommu->register_lock
 * Note:
 * intel_irq_remap_ops.{supported,prepare,enable,disable,reenable} are called
 * in single-threaded environment with interrupt disabled, so no need to tabke
 * the dmar_global_lock.
 */
static DEFINE_RAW_SPINLOCK(irq_2_ir_lock);
static struct irq_domain_ops intel_ir_domain_ops;

static void iommu_disable_irq_remapping(struct intel_iommu *iommu);
static int __init parse_ioapics_under_ir(void);

static bool ir_pre_enabled(struct intel_iommu *iommu)
{
	return (iommu->flags & VTD_FLAG_IRQ_REMAP_PRE_ENABLED);
}

static void clear_ir_pre_enabled(struct intel_iommu *iommu)
{
	iommu->flags &= ~VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
}

static void init_ir_status(struct intel_iommu *iommu)
{
	u32 gsts;

	gsts = readl(iommu->reg + DMAR_GSTS_REG);
	if (gsts & DMA_GSTS_IRES)
		iommu->flags |= VTD_FLAG_IRQ_REMAP_PRE_ENABLED;
}

static int alloc_irte(struct intel_iommu *iommu, int irq,
		      struct irq_2_iommu *irq_iommu, u16 count)
{
	struct ir_table *table = iommu->ir_table;
	unsigned int mask = 0;
	unsigned long flags;
	int index;

	if (!count || !irq_iommu)
		return -1;

	if (count > 1) {
		count = __roundup_pow_of_two(count);
		mask = ilog2(count);
	}

	if (mask > ecap_max_handle_mask(iommu->ecap)) {
		pr_err("Requested mask %x exceeds the max invalidation handle"
		       " mask value %Lx\n", mask,
		       ecap_max_handle_mask(iommu->ecap));
		return -1;
	}

	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
	index = bitmap_find_free_region(table->bitmap,
					INTR_REMAP_TABLE_ENTRIES, mask);
	if (index < 0) {
		pr_warn("IR%d: can't allocate an IRTE\n", iommu->seq_id);
	} else {
		irq_iommu->iommu = iommu;
		irq_iommu->irte_index =  index;
		irq_iommu->sub_handle = 0;
		irq_iommu->irte_mask = mask;
		irq_iommu->mode = IRQ_REMAPPING;
	}
	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);

	return index;
}

static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
{
	struct qi_desc desc;

	desc.low = QI_IEC_IIDEX(index) | QI_IEC_TYPE | QI_IEC_IM(mask)
		   | QI_IEC_SELECTIVE;
	desc.high = 0;

	return qi_submit_sync(&desc, iommu);
}

static int modify_irte(struct irq_2_iommu *irq_iommu,
		       struct irte *irte_modified)
{
	struct intel_iommu *iommu;
	unsigned long flags;
	struct irte *irte;
	int rc, index;

	if (!irq_iommu)
		return -1;

	raw_spin_lock_irqsave(&irq_2_ir_lock, flags);

	iommu = irq_iommu->iommu;

	index = irq_iommu->irte_index + irq_iommu->sub_handle;
	irte = &iommu->ir_table->base[index];

#if defined(CONFIG_HAVE_CMPXCHG_DOUBLE)
	if ((irte->pst == 1) || (irte_modified->pst == 1)) {
		bool ret;

		ret = cmpxchg_double(&irte->low, &irte->high,
				     irte->low, irte->high,
				     irte_modified->low, irte_modified->high);
		/*
		 * We use cmpxchg16 to atomically update the 128-bit IRTE,
		 * and it cannot be updated by the hardware or other processors
		 * behind us, so the return value of cmpxchg16 should be the
		 * same as the old value.
		 */
		WARN_ON(!ret);
	} else
#endif
	{
		set_64bit(&irte->low, irte_modified->low);
		set_64bit(&irte->high, irte_modified->high);
	}
	__iommu_flush_cache(iommu, irte, sizeof(*irte));

	rc = qi_flush_iec(iommu, index, 0);

	/* Update iommu mode according to the IRTE mode */
	irq_iommu->mode = irte->pst ? IRQ_POSTING : IRQ_REMAPPING;
	raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);

	return rc;
}

static struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
{
	int i;

	for (i = 0; i < MAX_HPET_TBS; i++)
		if (ir_hpet[i].id == hpet_id && ir_hpet[i].iommu)
			return ir_hpet[i].iommu;
	return NULL;
}

static struct intel_iommu *map_ioapic_to_ir(int apic)
{
	int i;

	for (i = 0; i < MAX_IO_APICS; i++)
		if (ir_ioapic[i].id == apic && ir_ioapic[i].iommu)
			return ir_ioapic[i].iommu;
	return NULL;
}

static struct intel_iommu *map_dev_to_ir(struct pci_dev *dev)
{
	struct dmar_drhd_unit *drhd;

	drhd = dmar_find_matched_drhd_unit(dev);
	if (!drhd)
		return NULL;

	return drhd->iommu;
}

static int clear_entries(struct irq_2_iommu *irq_iommu)
{
	struct irte *start, *entry, *end;
	struct intel_iommu *iommu;
	int index;

	if (irq_iommu->sub_handle)
		return 0;

	iommu = irq_iommu->iommu;
	index = irq_iommu->irte_index;

	start = iommu->ir_table->base + index;
	end = start + (1 << irq_iommu->irte_mask);

	for (entry = start; entry < end; entry++) {
		set_64bit(&entry->low, 0);
		set_64bit(&entry->high, 0);
	}
	bitmap_release_region(iommu->ir_table->bitmap, index,
			      irq_iommu->irte_mask);

	return qi_flush_iec(iommu, index, irq_iommu->irte_mask);
}

/*
 * source validation type
 */
#define SVT_NO_VERIFY		0x0  /* no verification is required */
#define SVT_VERIFY_SID_SQ	0x1  /* verify using SID and SQ fields */
#define SVT_VERIFY_BUS		0x2  /* verify bus of request-id */

/*
 * source-id qualifier
 */
#define SQ_ALL_16	0x0  /* verify all 16 bits of request-id */
#define SQ_13_IGNORE_1	0x1  /* verify most significant 13 bits, ignore
			      * the third least significant bit
			      */
#define SQ_13_IGNORE_2	0x2  /* verify most significant 13 bits, ignore
			      * the second and third least significant bits
			      */
#define SQ_13_IGNORE_3	0x3  /* verify most significant 13 bits, ignore
			      * the least three significant bits
			      */

/*
 * set SVT, SQ and SID fields of irte to verify
 * source ids of interrupt requests
 */
static void set_irte_sid(struct irte *irte, unsigned int svt,
			 unsigned int sq, unsigned int sid)
{
	if (disable_sourceid_checking)
		svt = SVT_NO_VERIFY;
	irte->svt = svt;
	irte->sq = sq;
	irte->sid = sid;
}

static int set_ioapic_sid(struct irte *irte, int apic)
{
	int i;
	u16 sid = 0;

	if (!irte)
		return -1;

	down_read(&dmar_global_lock);
	for (i = 0; i < MAX_IO_APICS; i++) {
		if (ir_ioapic[i].iommu && ir_ioapic[i].id == apic) {
			sid = (ir_ioapic[i].bus << 8) | ir_ioapic[i].devfn;
			break;
		}
	}
	up_read(&dmar_global_lock);

	if (sid == 0) {
		pr_warn("Failed to set source-id of IOAPIC (%d)\n", apic);
		return -1;
	}

	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, sid);

	return 0;
}

static int set_hpet_sid(struct irte *irte, u8 id)
{
	int i;
	u16 sid = 0;

	if (!irte)
		return -1;

	down_read(&dmar_global_lock);
	for (i = 0; i < MAX_HPET_TBS; i++) {
		if (ir_hpet[i].iommu && ir_hpet[i].id == id) {
			sid = (ir_hpet[i].bus << 8) | ir_hpet[i].devfn;
			break;
		}
	}
	up_read(&dmar_global_lock);

	if (sid == 0) {
		pr_warn("Failed to set source-id of HPET block (%d)\n", id);
		return -1;
	}

	/*
	 * Should really use SQ_ALL_16. Some platforms are broken.
	 * While we figure out the right quirks for these broken platforms, use
	 * SQ_13_IGNORE_3 for now.
	 */
	set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_13_IGNORE_3, sid);

	return 0;
}

struct set_msi_sid_data {
	struct pci_dev *pdev;
	u16 alias;
};

static int set_msi_sid_cb(struct pci_dev *pdev, u16 alias, void *opaque)
{
	struct set_msi_sid_data *data = opaque;

	data->pdev = pdev;
	data->alias = alias;

	return 0;
}

static int set_msi_sid(struct irte *irte, struct pci_dev *dev)
{
	struct set_msi_sid_data data;

	if (!irte || !dev)
		return -1;

	pci_for_each_dma_alias(dev, set_msi_sid_cb, &data);

	/*
	 * DMA alias provides us with a PCI device and alias.  The only case
	 * where the it will return an alias on a different bus than the
	 * device is the case of a PCIe-to-PCI bridge, where the alias is for
	 * the subordinate bus.  In this case we can only verify the bus.
	 *
	 * If the alias device is on a different bus than our source device
	 * then we have a topology based alias, use it.
	 *
	 * Otherwise, the alias is for a device DMA quirk and we cannot
	 * assume that MSI uses the same requester ID.  Therefore use the
	 * original device.
	 */
	if (PCI_BUS_NUM(data.alias) != data.pdev->bus->number)
		set_irte_sid(irte, SVT_VERIFY_BUS, SQ_ALL_16,
			     PCI_DEVID(PCI_BUS_NUM(data.alias),
				       dev->bus->number));
	else if (data.pdev->bus->number != dev->bus->number)
		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16, data.alias);
	else
		set_irte_sid(irte, SVT_VERIFY_SID_SQ, SQ_ALL_16,
			     PCI_DEVID(dev->bus->number, dev->devfn));

	return 0;
}

static int iommu_load_old_irte(struct intel_iommu *iommu)
{
	struct irte *old_ir_table;
	phys_addr_t irt_phys;
	unsigned int i;
	size_t size;
	u64 irta;

	if (!is_kdump_kernel()) {
		pr_warn("IRQ remapping was enabled on %s but we are not in kdump mode\n",
			iommu->name);
		clear_ir_pre_enabled(iommu);
		iommu_disable_irq_remapping(iommu);
		return -EINVAL;
	}

	/* Check whether the old ir-table has the same size as ours */
	irta = dmar_readq(iommu->reg + DMAR_IRTA_REG);
	if ((irta & INTR_REMAP_TABLE_REG_SIZE_MASK)
	     != INTR_REMAP_TABLE_REG_SIZE)
		return -EINVAL;

	irt_phys = irta & VTD_PAGE_MASK;
	size     = INTR_REMAP_TABLE_ENTRIES*sizeof(struct irte);

	/* Map the old IR table */
	old_ir_table = memremap(irt_phys, size, MEMREMAP_WB);
	if (!old_ir_table)
		return -ENOMEM;

	/* Copy data over */
	memcpy(iommu->ir_table->base, old_ir_table, size);

	__iommu_flush_cache(iommu, iommu->ir_table->base, size);

	/*
	 * Now check the table for used entries and mark those as
	 * allocated in the bitmap
	 */
	for (i = 0; i < INTR_REMAP_TABLE_ENTRIES; i++) {
		if (iommu->ir_table->base[i].present)
			bitmap_set(iommu->ir_table->bitmap, i, 1);
	}

	memunmap(old_ir_table);

	return 0;
}


static void iommu_set_irq_remapping(struct intel_iommu *iommu, int mode)
{
	unsigned long flags;
	u64 addr;
	u32 sts;

	addr = virt_to_phys((void *)iommu->ir_table->base);

	raw_spin_lock_irqsave(&iommu->register_lock, flags);

	dmar_writeq(iommu->reg + DMAR_IRTA_REG,
		    (addr) | IR_X2APIC_MODE(mode) | INTR_REMAP_TABLE_REG_SIZE);

	/* Set interrupt-remapping table pointer */
	writel(iommu->gcmd | DMA_GCMD_SIRTP, iommu->reg + DMAR_GCMD_REG);

	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (sts & DMA_GSTS_IRTPS), sts);
	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);

	/*
	 * Global invalidation of interrupt entry cache to make sure the
	 * hardware uses the new irq remapping table.
	 */
	qi_global_iec(iommu);
}

static void iommu_enable_irq_remapping(struct intel_iommu *iommu)
{
	unsigned long flags;
	u32 sts;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);

	/* Enable interrupt-remapping */
	iommu->gcmd |= DMA_GCMD_IRE;
	iommu->gcmd &= ~DMA_GCMD_CFI;  /* Block compatibility-format MSIs */
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, (sts & DMA_GSTS_IRES), sts);

	/*
	 * With CFI clear in the Global Command register, we should be
	 * protected from dangerous (i.e. compatibility) interrupts
	 * regardless of x2apic status.  Check just to be sure.
	 */
	if (sts & DMA_GSTS_CFIS)
		WARN(1, KERN_WARNING
			"Compatibility-format IRQs enabled despite intr remapping;\n"
			"you are vulnerable to IRQ injection.\n");

	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}

static int intel_setup_irq_remapping(struct intel_iommu *iommu)
{
	struct ir_table *ir_table;
	struct page *pages;
	unsigned long *bitmap;

	if (iommu->ir_table)
		return 0;

	ir_table = kzalloc(sizeof(struct ir_table), GFP_KERNEL);
	if (!ir_table)
		return -ENOMEM;

	pages = alloc_pages_node(iommu->node, GFP_KERNEL | __GFP_ZERO,
				 INTR_REMAP_PAGE_ORDER);
	if (!pages) {
		pr_err("IR%d: failed to allocate pages of order %d\n",
		       iommu->seq_id, INTR_REMAP_PAGE_ORDER);
		goto out_free_table;
	}

	bitmap = kcalloc(BITS_TO_LONGS(INTR_REMAP_TABLE_ENTRIES),
			 sizeof(long), GFP_ATOMIC);
	if (bitmap == NULL) {
		pr_err("IR%d: failed to allocate bitmap\n", iommu->seq_id);
		goto out_free_pages;
	}

	iommu->ir_domain = irq_domain_add_hierarchy(arch_get_ir_parent_domain(),
						    0, INTR_REMAP_TABLE_ENTRIES,
						    NULL, &intel_ir_domain_ops,
						    iommu);
	if (!iommu->ir_domain) {
		pr_err("IR%d: failed to allocate irqdomain\n", iommu->seq_id);
		goto out_free_bitmap;
	}
	iommu->ir_msi_domain = arch_create_msi_irq_domain(iommu->ir_domain);

	ir_table->base = page_address(pages);
	ir_table->bitmap = bitmap;
	iommu->ir_table = ir_table;

	/*
	 * If the queued invalidation is already initialized,
	 * shouldn't disable it.
	 */
	if (!iommu->qi) {
		/*
		 * Clear previous faults.
		 */
		dmar_fault(-1, iommu);
		dmar_disable_qi(iommu);

		if (dmar_enable_qi(iommu)) {
			pr_err("Failed to enable queued invalidation\n");
			goto out_free_bitmap;
		}
	}

	init_ir_status(iommu);

	if (ir_pre_enabled(iommu)) {
		if (iommu_load_old_irte(iommu))
			pr_err("Failed to copy IR table for %s from previous kernel\n",
			       iommu->name);
		else
			pr_info("Copied IR table for %s from previous kernel\n",
				iommu->name);
	}

	iommu_set_irq_remapping(iommu, eim_mode);

	return 0;

out_free_bitmap:
	kfree(bitmap);
out_free_pages:
	__free_pages(pages, INTR_REMAP_PAGE_ORDER);
out_free_table:
	kfree(ir_table);

	iommu->ir_table  = NULL;

	return -ENOMEM;
}

static void intel_teardown_irq_remapping(struct intel_iommu *iommu)
{
	if (iommu && iommu->ir_table) {
		if (iommu->ir_msi_domain) {
			irq_domain_remove(iommu->ir_msi_domain);
			iommu->ir_msi_domain = NULL;
		}
		if (iommu->ir_domain) {
			irq_domain_remove(iommu->ir_domain);
			iommu->ir_domain = NULL;
		}
		free_pages((unsigned long)iommu->ir_table->base,
			   INTR_REMAP_PAGE_ORDER);
		kfree(iommu->ir_table->bitmap);
		kfree(iommu->ir_table);
		iommu->ir_table = NULL;
	}
}

/*
 * Disable Interrupt Remapping.
 */
static void iommu_disable_irq_remapping(struct intel_iommu *iommu)
{
	unsigned long flags;
	u32 sts;

	if (!ecap_ir_support(iommu->ecap))
		return;

	/*
	 * global invalidation of interrupt entry cache before disabling
	 * interrupt-remapping.
	 */
	qi_global_iec(iommu);

	raw_spin_lock_irqsave(&iommu->register_lock, flags);

	sts = readl(iommu->reg + DMAR_GSTS_REG);
	if (!(sts & DMA_GSTS_IRES))
		goto end;

	iommu->gcmd &= ~DMA_GCMD_IRE;
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG,
		      readl, !(sts & DMA_GSTS_IRES), sts);

end:
	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}

static int __init dmar_x2apic_optout(void)
{
	struct acpi_table_dmar *dmar;
	dmar = (struct acpi_table_dmar *)dmar_tbl;
	if (!dmar || no_x2apic_optout)
		return 0;
	return dmar->flags & DMAR_X2APIC_OPT_OUT;
}

static void __init intel_cleanup_irq_remapping(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;

	for_each_iommu(iommu, drhd) {
		if (ecap_ir_support(iommu->ecap)) {
			iommu_disable_irq_remapping(iommu);
			intel_teardown_irq_remapping(iommu);
		}
	}

	if (x2apic_supported())
		pr_warn("Failed to enable irq remapping. You are vulnerable to irq-injection attacks.\n");
}

static int __init intel_prepare_irq_remapping(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	int eim = 0;

	if (irq_remap_broken) {
		pr_warn("This system BIOS has enabled interrupt remapping\n"
			"on a chipset that contains an erratum making that\n"
			"feature unstable.  To maintain system stability\n"
			"interrupt remapping is being disabled.  Please\n"
			"contact your BIOS vendor for an update\n");
		add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
		return -ENODEV;
	}

	if (dmar_table_init() < 0)
		return -ENODEV;

	if (!dmar_ir_support())
		return -ENODEV;

	if (parse_ioapics_under_ir()) {
		pr_info("Not enabling interrupt remapping\n");
		goto error;
	}

	/* First make sure all IOMMUs support IRQ remapping */
	for_each_iommu(iommu, drhd)
		if (!ecap_ir_support(iommu->ecap))
			goto error;

	/* Detect remapping mode: lapic or x2apic */
	if (x2apic_supported()) {
		eim = !dmar_x2apic_optout();
		if (!eim) {
			pr_info("x2apic is disabled because BIOS sets x2apic opt out bit.");
			pr_info("Use 'intremap=no_x2apic_optout' to override the BIOS setting.\n");
		}
	}

	for_each_iommu(iommu, drhd) {
		if (eim && !ecap_eim_support(iommu->ecap)) {
			pr_info("%s does not support EIM\n", iommu->name);
			eim = 0;
		}
	}

	eim_mode = eim;
	if (eim)
		pr_info("Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");

	/* Do the initializations early */
	for_each_iommu(iommu, drhd) {
		if (intel_setup_irq_remapping(iommu)) {
			pr_err("Failed to setup irq remapping for %s\n",
			       iommu->name);
			goto error;
		}
	}

	return 0;

error:
	intel_cleanup_irq_remapping();
	return -ENODEV;
}

/*
 * Set Posted-Interrupts capability.
 */
static inline void set_irq_posting_cap(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;

	if (!disable_irq_post) {
		/*
		 * If IRTE is in posted format, the 'pda' field goes across the
		 * 64-bit boundary, we need use cmpxchg16b to atomically update
		 * it. We only expose posted-interrupt when X86_FEATURE_CX16
		 * is supported. Actually, hardware platforms supporting PI
		 * should have X86_FEATURE_CX16 support, this has been confirmed
		 * with Intel hardware guys.
		 */
		if (boot_cpu_has(X86_FEATURE_CX16))
			intel_irq_remap_ops.capability |= 1 << IRQ_POSTING_CAP;

		for_each_iommu(iommu, drhd)
			if (!cap_pi_support(iommu->cap)) {
				intel_irq_remap_ops.capability &=
						~(1 << IRQ_POSTING_CAP);
				break;
			}
	}
}

static int __init intel_enable_irq_remapping(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	bool setup = false;

	/*
	 * Setup Interrupt-remapping for all the DRHD's now.
	 */
	for_each_iommu(iommu, drhd) {
		if (!ir_pre_enabled(iommu))
			iommu_enable_irq_remapping(iommu);
		setup = true;
	}

	if (!setup)
		goto error;

	irq_remapping_enabled = 1;

	set_irq_posting_cap();

	pr_info("Enabled IRQ remapping in %s mode\n", eim_mode ? "x2apic" : "xapic");

	return eim_mode ? IRQ_REMAP_X2APIC_MODE : IRQ_REMAP_XAPIC_MODE;

error:
	intel_cleanup_irq_remapping();
	return -1;
}

static int ir_parse_one_hpet_scope(struct acpi_dmar_device_scope *scope,
				   struct intel_iommu *iommu,
				   struct acpi_dmar_hardware_unit *drhd)
{
	struct acpi_dmar_pci_path *path;
	u8 bus;
	int count, free = -1;

	bus = scope->bus;
	path = (struct acpi_dmar_pci_path *)(scope + 1);
	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
		/ sizeof(struct acpi_dmar_pci_path);

	while (--count > 0) {
		/*
		 * Access PCI directly due to the PCI
		 * subsystem isn't initialized yet.
		 */
		bus = read_pci_config_byte(bus, path->device, path->function,
					   PCI_SECONDARY_BUS);
		path++;
	}

	for (count = 0; count < MAX_HPET_TBS; count++) {
		if (ir_hpet[count].iommu == iommu &&
		    ir_hpet[count].id == scope->enumeration_id)
			return 0;
		else if (ir_hpet[count].iommu == NULL && free == -1)
			free = count;
	}
	if (free == -1) {
		pr_warn("Exceeded Max HPET blocks\n");
		return -ENOSPC;
	}

	ir_hpet[free].iommu = iommu;
	ir_hpet[free].id    = scope->enumeration_id;
	ir_hpet[free].bus   = bus;
	ir_hpet[free].devfn = PCI_DEVFN(path->device, path->function);
	pr_info("HPET id %d under DRHD base 0x%Lx\n",
		scope->enumeration_id, drhd->address);

	return 0;
}

static int ir_parse_one_ioapic_scope(struct acpi_dmar_device_scope *scope,
				     struct intel_iommu *iommu,
				     struct acpi_dmar_hardware_unit *drhd)
{
	struct acpi_dmar_pci_path *path;
	u8 bus;
	int count, free = -1;

	bus = scope->bus;
	path = (struct acpi_dmar_pci_path *)(scope + 1);
	count = (scope->length - sizeof(struct acpi_dmar_device_scope))
		/ sizeof(struct acpi_dmar_pci_path);

	while (--count > 0) {
		/*
		 * Access PCI directly due to the PCI
		 * subsystem isn't initialized yet.
		 */
		bus = read_pci_config_byte(bus, path->device, path->function,
					   PCI_SECONDARY_BUS);
		path++;
	}

	for (count = 0; count < MAX_IO_APICS; count++) {
		if (ir_ioapic[count].iommu == iommu &&
		    ir_ioapic[count].id == scope->enumeration_id)
			return 0;
		else if (ir_ioapic[count].iommu == NULL && free == -1)
			free = count;
	}
	if (free == -1) {
		pr_warn("Exceeded Max IO APICS\n");
		return -ENOSPC;
	}

	ir_ioapic[free].bus   = bus;
	ir_ioapic[free].devfn = PCI_DEVFN(path->device, path->function);
	ir_ioapic[free].iommu = iommu;
	ir_ioapic[free].id    = scope->enumeration_id;
	pr_info("IOAPIC id %d under DRHD base  0x%Lx IOMMU %d\n",
		scope->enumeration_id, drhd->address, iommu->seq_id);

	return 0;
}

static int ir_parse_ioapic_hpet_scope(struct acpi_dmar_header *header,
				      struct intel_iommu *iommu)
{
	int ret = 0;
	struct acpi_dmar_hardware_unit *drhd;
	struct acpi_dmar_device_scope *scope;
	void *start, *end;

	drhd = (struct acpi_dmar_hardware_unit *)header;
	start = (void *)(drhd + 1);
	end = ((void *)drhd) + header->length;

	while (start < end && ret == 0) {
		scope = start;
		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_IOAPIC)
			ret = ir_parse_one_ioapic_scope(scope, iommu, drhd);
		else if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_HPET)
			ret = ir_parse_one_hpet_scope(scope, iommu, drhd);
		start += scope->length;
	}

	return ret;
}

static void ir_remove_ioapic_hpet_scope(struct intel_iommu *iommu)
{
	int i;

	for (i = 0; i < MAX_HPET_TBS; i++)
		if (ir_hpet[i].iommu == iommu)
			ir_hpet[i].iommu = NULL;

	for (i = 0; i < MAX_IO_APICS; i++)
		if (ir_ioapic[i].iommu == iommu)
			ir_ioapic[i].iommu = NULL;
}

/*
 * Finds the assocaition between IOAPIC's and its Interrupt-remapping
 * hardware unit.
 */
static int __init parse_ioapics_under_ir(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu;
	bool ir_supported = false;
	int ioapic_idx;

	for_each_iommu(iommu, drhd) {
		int ret;

		if (!ecap_ir_support(iommu->ecap))
			continue;

		ret = ir_parse_ioapic_hpet_scope(drhd->hdr, iommu);
		if (ret)
			return ret;

		ir_supported = true;
	}

	if (!ir_supported)
		return -ENODEV;

	for (ioapic_idx = 0; ioapic_idx < nr_ioapics; ioapic_idx++) {
		int ioapic_id = mpc_ioapic_id(ioapic_idx);
		if (!map_ioapic_to_ir(ioapic_id)) {
			pr_err(FW_BUG "ioapic %d has no mapping iommu, "
			       "interrupt remapping will be disabled\n",
			       ioapic_id);
			return -1;
		}
	}

	return 0;
}

static int __init ir_dev_scope_init(void)
{
	int ret;

	if (!irq_remapping_enabled)
		return 0;

	down_write(&dmar_global_lock);
	ret = dmar_dev_scope_init();
	up_write(&dmar_global_lock);

	return ret;
}
rootfs_initcall(ir_dev_scope_init);

static void disable_irq_remapping(void)
{
	struct dmar_drhd_unit *drhd;
	struct intel_iommu *iommu = NULL;

	/*
	 * Disable Interrupt-remapping for all the DRHD's now.
	 */
	for_each_iommu(iommu, drhd) {
		if (!ecap_ir_support(iommu->ecap))
			continue;

		iommu_disable_irq_remapping(iommu);
	}

	/*
	 * Clear Posted-Interrupts capability.
	 */
	if (!disable_irq_post)
		intel_irq_remap_ops.capability &= ~(1 << IRQ_POSTING_CAP);
}

static int reenable_irq_remapping(int eim)
{
	struct dmar_drhd_unit *drhd;
	bool setup = false;
	struct intel_iommu *iommu = NULL;

	for_each_iommu(iommu, drhd)
		if (iommu->qi)
			dmar_reenable_qi(iommu);

	/*
	 * Setup Interrupt-remapping for all the DRHD's now.
	 */
	for_each_iommu(iommu, drhd) {
		if (!ecap_ir_support(iommu->ecap))
			continue;

		/* Set up interrupt remapping for iommu.*/
		iommu_set_irq_remapping(iommu, eim);
		iommu_enable_irq_remapping(iommu);
		setup = true;
	}

	if (!setup)
		goto error;

	set_irq_posting_cap();

	return 0;

error:
	/*
	 * handle error condition gracefully here!
	 */
	return -1;
}

static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
{
	memset(irte, 0, sizeof(*irte));

	irte->present = 1;
	irte->dst_mode = apic->irq_dest_mode;
	/*
	 * Trigger mode in the IRTE will always be edge, and for IO-APIC, the
	 * actual level or edge trigger will be setup in the IO-APIC
	 * RTE. This will help simplify level triggered irq migration.
	 * For more details, see the comments (in io_apic.c) explainig IO-APIC
	 * irq migration in the presence of interrupt-remapping.
	*/
	irte->trigger_mode = 0;
	irte->dlvry_mode = apic->irq_delivery_mode;
	irte->vector = vector;
	irte->dest_id = IRTE_DEST(dest);
	irte->redir_hint = 1;
}

static struct irq_domain *intel_get_ir_irq_domain(struct irq_alloc_info *info)
{
	struct intel_iommu *iommu = NULL;

	if (!info)
		return NULL;

	switch (info->type) {
	case X86_IRQ_ALLOC_TYPE_IOAPIC:
		iommu = map_ioapic_to_ir(info->ioapic_id);
		break;
	case X86_IRQ_ALLOC_TYPE_HPET:
		iommu = map_hpet_to_ir(info->hpet_id);
		break;
	case X86_IRQ_ALLOC_TYPE_MSI:
	case X86_IRQ_ALLOC_TYPE_MSIX:
		iommu = map_dev_to_ir(info->msi_dev);
		break;
	default:
		BUG_ON(1);
		break;
	}

	return iommu ? iommu->ir_domain : NULL;
}

static struct irq_domain *intel_get_irq_domain(struct irq_alloc_info *info)
{
	struct intel_iommu *iommu;

	if (!info)
		return NULL;

	switch (info->type) {
	case X86_IRQ_ALLOC_TYPE_MSI:
	case X86_IRQ_ALLOC_TYPE_MSIX:
		iommu = map_dev_to_ir(info->msi_dev);
		if (iommu)
			return iommu->ir_msi_domain;
		break;
	default:
		break;
	}

	return NULL;
}

struct irq_remap_ops intel_irq_remap_ops = {
	.prepare		= intel_prepare_irq_remapping,
	.enable			= intel_enable_irq_remapping,
	.disable		= disable_irq_remapping,
	.reenable		= reenable_irq_remapping,
	.enable_faulting	= enable_drhd_fault_handling,
	.get_ir_irq_domain	= intel_get_ir_irq_domain,
	.get_irq_domain		= intel_get_irq_domain,
};

/*
 * Migrate the IO-APIC irq in the presence of intr-remapping.
 *
 * For both level and edge triggered, irq migration is a simple atomic
 * update(of vector and cpu destination) of IRTE and flush the hardware cache.
 *
 * For level triggered, we eliminate the io-apic RTE modification (with the
 * updated vector information), by using a virtual vector (io-apic pin number).
 * Real vector that is used for interrupting cpu will be coming from
 * the interrupt-remapping table entry.
 *
 * As the migration is a simple atomic update of IRTE, the same mechanism
 * is used to migrate MSI irq's in the presence of interrupt-remapping.
 */
static int
intel_ir_set_affinity(struct irq_data *data, const struct cpumask *mask,
		      bool force)
{
	struct intel_ir_data *ir_data = data->chip_data;
	struct irte *irte = &ir_data->irte_entry;
	struct irq_cfg *cfg = irqd_cfg(data);
	struct irq_data *parent = data->parent_data;
	int ret;

	ret = parent->chip->irq_set_affinity(parent, mask, force);
	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
		return ret;

	/*
	 * Atomically updates the IRTE with the new destination, vector
	 * and flushes the interrupt entry cache.
	 */
	irte->vector = cfg->vector;
	irte->dest_id = IRTE_DEST(cfg->dest_apicid);

	/* Update the hardware only if the interrupt is in remapped mode. */
	if (ir_data->irq_2_iommu.mode == IRQ_REMAPPING)
		modify_irte(&ir_data->irq_2_iommu, irte);

	/*
	 * After this point, all the interrupts will start arriving
	 * at the new destination. So, time to cleanup the previous
	 * vector allocation.
	 */
	send_cleanup_vector(cfg);

	return IRQ_SET_MASK_OK_DONE;
}

static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
				     struct msi_msg *msg)
{
	struct intel_ir_data *ir_data = irq_data->chip_data;

	*msg = ir_data->msi_entry;
}

static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
{
	struct intel_ir_data *ir_data = data->chip_data;
	struct vcpu_data *vcpu_pi_info = info;

	/* stop posting interrupts, back to remapping mode */
	if (!vcpu_pi_info) {
		modify_irte(&ir_data->irq_2_iommu, &ir_data->irte_entry);
	} else {
		struct irte irte_pi;

		/*
		 * We are not caching the posted interrupt entry. We
		 * copy the data from the remapped entry and modify
		 * the fields which are relevant for posted mode. The
		 * cached remapped entry is used for switching back to
		 * remapped mode.
		 */
		memset(&irte_pi, 0, sizeof(irte_pi));
		dmar_copy_shared_irte(&irte_pi, &ir_data->irte_entry);

		/* Update the posted mode fields */
		irte_pi.p_pst = 1;
		irte_pi.p_urgent = 0;
		irte_pi.p_vector = vcpu_pi_info->vector;
		irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
				(32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
				~(-1UL << PDA_HIGH_BIT);

		modify_irte(&ir_data->irq_2_iommu, &irte_pi);
	}

	return 0;
}

static struct irq_chip intel_ir_chip = {
	.irq_ack = ir_ack_apic_edge,
	.irq_set_affinity = intel_ir_set_affinity,
	.irq_compose_msi_msg = intel_ir_compose_msi_msg,
	.irq_set_vcpu_affinity = intel_ir_set_vcpu_affinity,
};

static void intel_irq_remapping_prepare_irte(struct intel_ir_data *data,
					     struct irq_cfg *irq_cfg,
					     struct irq_alloc_info *info,
					     int index, int sub_handle)
{
	struct IR_IO_APIC_route_entry *entry;
	struct irte *irte = &data->irte_entry;
	struct msi_msg *msg = &data->msi_entry;

	prepare_irte(irte, irq_cfg->vector, irq_cfg->dest_apicid);
	switch (info->type) {
	case X86_IRQ_ALLOC_TYPE_IOAPIC:
		/* Set source-id of interrupt request */
		set_ioapic_sid(irte, info->ioapic_id);
		apic_printk(APIC_VERBOSE, KERN_DEBUG "IOAPIC[%d]: Set IRTE entry (P:%d FPD:%d Dst_Mode:%d Redir_hint:%d Trig_Mode:%d Dlvry_Mode:%X Avail:%X Vector:%02X Dest:%08X SID:%04X SQ:%X SVT:%X)\n",
			info->ioapic_id, irte->present, irte->fpd,
			irte->dst_mode, irte->redir_hint,
			irte->trigger_mode, irte->dlvry_mode,
			irte->avail, irte->vector, irte->dest_id,
			irte->sid, irte->sq, irte->svt);

		entry = (struct IR_IO_APIC_route_entry *)info->ioapic_entry;
		info->ioapic_entry = NULL;
		memset(entry, 0, sizeof(*entry));
		entry->index2	= (index >> 15) & 0x1;
		entry->zero	= 0;
		entry->format	= 1;
		entry->index	= (index & 0x7fff);
		/*
		 * IO-APIC RTE will be configured with virtual vector.
		 * irq handler will do the explicit EOI to the io-apic.
		 */
		entry->vector	= info->ioapic_pin;
		entry->mask	= 0;			/* enable IRQ */
		entry->trigger	= info->ioapic_trigger;
		entry->polarity	= info->ioapic_polarity;
		if (info->ioapic_trigger)
			entry->mask = 1; /* Mask level triggered irqs. */
		break;

	case X86_IRQ_ALLOC_TYPE_HPET:
	case X86_IRQ_ALLOC_TYPE_MSI:
	case X86_IRQ_ALLOC_TYPE_MSIX:
		if (info->type == X86_IRQ_ALLOC_TYPE_HPET)
			set_hpet_sid(irte, info->hpet_id);
		else
			set_msi_sid(irte, info->msi_dev);

		msg->address_hi = MSI_ADDR_BASE_HI;
		msg->data = sub_handle;
		msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_IR_EXT_INT |
				  MSI_ADDR_IR_SHV |
				  MSI_ADDR_IR_INDEX1(index) |
				  MSI_ADDR_IR_INDEX2(index);
		break;

	default:
		BUG_ON(1);
		break;
	}
}

static void intel_free_irq_resources(struct irq_domain *domain,
				     unsigned int virq, unsigned int nr_irqs)
{
	struct irq_data *irq_data;
	struct intel_ir_data *data;
	struct irq_2_iommu *irq_iommu;
	unsigned long flags;
	int i;
	for (i = 0; i < nr_irqs; i++) {
		irq_data = irq_domain_get_irq_data(domain, virq  + i);
		if (irq_data && irq_data->chip_data) {
			data = irq_data->chip_data;
			irq_iommu = &data->irq_2_iommu;
			raw_spin_lock_irqsave(&irq_2_ir_lock, flags);
			clear_entries(irq_iommu);
			raw_spin_unlock_irqrestore(&irq_2_ir_lock, flags);
			irq_domain_reset_irq_data(irq_data);
			kfree(data);
		}
	}
}

static int intel_irq_remapping_alloc(struct irq_domain *domain,
				     unsigned int virq, unsigned int nr_irqs,
				     void *arg)
{
	struct intel_iommu *iommu = domain->host_data;
	struct irq_alloc_info *info = arg;
	struct intel_ir_data *data, *ird;
	struct irq_data *irq_data;
	struct irq_cfg *irq_cfg;
	int i, ret, index;

	if (!info || !iommu)
		return -EINVAL;
	if (nr_irqs > 1 && info->type != X86_IRQ_ALLOC_TYPE_MSI &&
	    info->type != X86_IRQ_ALLOC_TYPE_MSIX)
		return -EINVAL;

	/*
	 * With IRQ remapping enabled, don't need contiguous CPU vectors
	 * to support multiple MSI interrupts.
	 */
	if (info->type == X86_IRQ_ALLOC_TYPE_MSI)
		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;

	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
	if (ret < 0)
		return ret;

	ret = -ENOMEM;
	data = kzalloc(sizeof(*data), GFP_KERNEL);
	if (!data)
		goto out_free_parent;

	down_read(&dmar_global_lock);
	index = alloc_irte(iommu, virq, &data->irq_2_iommu, nr_irqs);
	up_read(&dmar_global_lock);
	if (index < 0) {
		pr_warn("Failed to allocate IRTE\n");
		kfree(data);
		goto out_free_parent;
	}

	for (i = 0; i < nr_irqs; i++) {
		irq_data = irq_domain_get_irq_data(domain, virq + i);
		irq_cfg = irqd_cfg(irq_data);
		if (!irq_data || !irq_cfg) {
			ret = -EINVAL;
			goto out_free_data;
		}

		if (i > 0) {
			ird = kzalloc(sizeof(*ird), GFP_KERNEL);
			if (!ird)
				goto out_free_data;
			/* Initialize the common data */
			ird->irq_2_iommu = data->irq_2_iommu;
			ird->irq_2_iommu.sub_handle = i;
		} else {
			ird = data;
		}

		irq_data->hwirq = (index << 16) + i;
		irq_data->chip_data = ird;
		irq_data->chip = &intel_ir_chip;
		intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
	}
	return 0;

out_free_data:
	intel_free_irq_resources(domain, virq, i);
out_free_parent:
	irq_domain_free_irqs_common(domain, virq, nr_irqs);
	return ret;
}

static void intel_irq_remapping_free(struct irq_domain *domain,
				     unsigned int virq, unsigned int nr_irqs)
{
	intel_free_irq_resources(domain, virq, nr_irqs);
	irq_domain_free_irqs_common(domain, virq, nr_irqs);
}

static void intel_irq_remapping_activate(struct irq_domain *domain,
					 struct irq_data *irq_data)
{
	struct intel_ir_data *data = irq_data->chip_data;

	modify_irte(&data->irq_2_iommu, &data->irte_entry);
}

static void intel_irq_remapping_deactivate(struct irq_domain *domain,
					   struct irq_data *irq_data)
{
	struct intel_ir_data *data = irq_data->chip_data;
	struct irte entry;

	memset(&entry, 0, sizeof(entry));
	modify_irte(&data->irq_2_iommu, &entry);
}

static struct irq_domain_ops intel_ir_domain_ops = {
	.alloc = intel_irq_remapping_alloc,
	.free = intel_irq_remapping_free,
	.activate = intel_irq_remapping_activate,
	.deactivate = intel_irq_remapping_deactivate,
};

/*
 * Support of Interrupt Remapping Unit Hotplug
 */
static int dmar_ir_add(struct dmar_drhd_unit *dmaru, struct intel_iommu *iommu)
{
	int ret;
	int eim = x2apic_enabled();

	if (eim && !ecap_eim_support(iommu->ecap)) {
		pr_info("DRHD %Lx: EIM not supported by DRHD, ecap %Lx\n",
			iommu->reg_phys, iommu->ecap);
		return -ENODEV;
	}

	if (ir_parse_ioapic_hpet_scope(dmaru->hdr, iommu)) {
		pr_warn("DRHD %Lx: failed to parse managed IOAPIC/HPET\n",
			iommu->reg_phys);
		return -ENODEV;
	}

	/* TODO: check all IOAPICs are covered by IOMMU */

	/* Setup Interrupt-remapping now. */
	ret = intel_setup_irq_remapping(iommu);
	if (ret) {
		pr_err("Failed to setup irq remapping for %s\n",
		       iommu->name);
		intel_teardown_irq_remapping(iommu);
		ir_remove_ioapic_hpet_scope(iommu);
	} else {
		iommu_enable_irq_remapping(iommu);
	}

	return ret;
}

int dmar_ir_hotplug(struct dmar_drhd_unit *dmaru, bool insert)
{
	int ret = 0;
	struct intel_iommu *iommu = dmaru->iommu;

	if (!irq_remapping_enabled)
		return 0;
	if (iommu == NULL)
		return -EINVAL;
	if (!ecap_ir_support(iommu->ecap))
		return 0;
	if (irq_remapping_cap(IRQ_POSTING_CAP) &&
	    !cap_pi_support(iommu->cap))
		return -EBUSY;

	if (insert) {
		if (!iommu->ir_table)
			ret = dmar_ir_add(dmaru, iommu);
	} else {
		if (iommu->ir_table) {
			if (!bitmap_empty(iommu->ir_table->bitmap,
					  INTR_REMAP_TABLE_ENTRIES)) {
				ret = -EBUSY;
			} else {
				iommu_disable_irq_remapping(iommu);
				intel_teardown_irq_remapping(iommu);
				ir_remove_ioapic_hpet_scope(iommu);
			}
		}
	}

	return ret;
}