summaryrefslogtreecommitdiffstats
path: root/drivers/iommu/dmar.c
blob: 35c1e17fce1d09a67547234a0448526370db49f7 (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
/*
 * Copyright (c) 2006, Intel Corporation.
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms and conditions of the GNU General Public License,
 * version 2, as published by the Free Software Foundation.
 *
 * This program is distributed in the hope it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
 * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
 * more details.
 *
 * You should have received a copy of the GNU General Public License along with
 * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
 * Place - Suite 330, Boston, MA 02111-1307 USA.
 *
 * Copyright (C) 2006-2008 Intel Corporation
 * Author: Ashok Raj <ashok.raj@intel.com>
 * Author: Shaohua Li <shaohua.li@intel.com>
 * Author: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
 *
 * This file implements early detection/parsing of Remapping Devices
 * reported to OS through BIOS via DMA remapping reporting (DMAR) ACPI
 * tables.
 *
 * These routines are used by both DMA-remapping and Interrupt-remapping
 */

#include <linux/pci.h>
#include <linux/dmar.h>
#include <linux/iova.h>
#include <linux/intel-iommu.h>
#include <linux/timer.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/tboot.h>
#include <linux/dmi.h>
#include <linux/slab.h>
#include <asm/iommu_table.h>

#define PREFIX "DMAR: "

/* No locks are needed as DMA remapping hardware unit
 * list is constructed at boot time and hotplug of
 * these units are not supported by the architecture.
 */
LIST_HEAD(dmar_drhd_units);

struct acpi_table_header * __initdata dmar_tbl;
static acpi_size dmar_tbl_size;

static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
{
	/*
	 * add INCLUDE_ALL at the tail, so scan the list will find it at
	 * the very end.
	 */
	if (drhd->include_all)
		list_add_tail(&drhd->list, &dmar_drhd_units);
	else
		list_add(&drhd->list, &dmar_drhd_units);
}

static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
					   struct pci_dev **dev, u16 segment)
{
	struct pci_bus *bus;
	struct pci_dev *pdev = NULL;
	struct acpi_dmar_pci_path *path;
	int count;

	bus = pci_find_bus(segment, 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) {
		if (pdev)
			pci_dev_put(pdev);
		/*
		 * Some BIOSes list non-exist devices in DMAR table, just
		 * ignore it
		 */
		if (!bus) {
			printk(KERN_WARNING
			PREFIX "Device scope bus [%d] not found\n",
			scope->bus);
			break;
		}
		pdev = pci_get_slot(bus, PCI_DEVFN(path->dev, path->fn));
		if (!pdev) {
			printk(KERN_WARNING PREFIX
			"Device scope device [%04x:%02x:%02x.%02x] not found\n",
				segment, bus->number, path->dev, path->fn);
			break;
		}
		path ++;
		count --;
		bus = pdev->subordinate;
	}
	if (!pdev) {
		printk(KERN_WARNING PREFIX
		"Device scope device [%04x:%02x:%02x.%02x] not found\n",
		segment, scope->bus, path->dev, path->fn);
		*dev = NULL;
		return 0;
	}
	if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT && \
			pdev->subordinate) || (scope->entry_type == \
			ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) {
		pci_dev_put(pdev);
		printk(KERN_WARNING PREFIX
			"Device scope type does not match for %s\n",
			 pci_name(pdev));
		return -EINVAL;
	}
	*dev = pdev;
	return 0;
}

int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
				struct pci_dev ***devices, u16 segment)
{
	struct acpi_dmar_device_scope *scope;
	void * tmp = start;
	int index;
	int ret;

	*cnt = 0;
	while (start < end) {
		scope = start;
		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
			(*cnt)++;
		else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC) {
			printk(KERN_WARNING PREFIX
			       "Unsupported device scope\n");
		}
		start += scope->length;
	}
	if (*cnt == 0)
		return 0;

	*devices = kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
	if (!*devices)
		return -ENOMEM;

	start = tmp;
	index = 0;
	while (start < end) {
		scope = start;
		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
		    scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) {
			ret = dmar_parse_one_dev_scope(scope,
				&(*devices)[index], segment);
			if (ret) {
				kfree(*devices);
				return ret;
			}
			index ++;
		}
		start += scope->length;
	}

	return 0;
}

/**
 * dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
 * structure which uniquely represent one DMA remapping hardware unit
 * present in the platform
 */
static int __init
dmar_parse_one_drhd(struct acpi_dmar_header *header)
{
	struct acpi_dmar_hardware_unit *drhd;
	struct dmar_drhd_unit *dmaru;
	int ret = 0;

	drhd = (struct acpi_dmar_hardware_unit *)header;
	dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
	if (!dmaru)
		return -ENOMEM;

	dmaru->hdr = header;
	dmaru->reg_base_addr = drhd->address;
	dmaru->segment = drhd->segment;
	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */

	ret = alloc_iommu(dmaru);
	if (ret) {
		kfree(dmaru);
		return ret;
	}
	dmar_register_drhd_unit(dmaru);
	return 0;
}

static int __init dmar_parse_dev(struct dmar_drhd_unit *dmaru)
{
	struct acpi_dmar_hardware_unit *drhd;
	int ret = 0;

	drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;

	if (dmaru->include_all)
		return 0;

	ret = dmar_parse_dev_scope((void *)(drhd + 1),
				((void *)drhd) + drhd->header.length,
				&dmaru->devices_cnt, &dmaru->devices,
				drhd->segment);
	if (ret) {
		list_del(&dmaru->list);
		kfree(dmaru);
	}
	return ret;
}

#ifdef CONFIG_ACPI_NUMA
static int __init
dmar_parse_one_rhsa(struct acpi_dmar_header *header)
{
	struct acpi_dmar_rhsa *rhsa;
	struct dmar_drhd_unit *drhd;

	rhsa = (struct acpi_dmar_rhsa *)header;
	for_each_drhd_unit(drhd) {
		if (drhd->reg_base_addr == rhsa->base_address) {
			int node = acpi_map_pxm_to_node(rhsa->proximity_domain);

			if (!node_online(node))
				node = -1;
			drhd->iommu->node = node;
			return 0;
		}
	}
	WARN_TAINT(
		1, TAINT_FIRMWARE_WORKAROUND,
		"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
		drhd->reg_base_addr,
		dmi_get_system_info(DMI_BIOS_VENDOR),
		dmi_get_system_info(DMI_BIOS_VERSION),
		dmi_get_system_info(DMI_PRODUCT_VERSION));

	return 0;
}
#endif

static void __init
dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
{
	struct acpi_dmar_hardware_unit *drhd;
	struct acpi_dmar_reserved_memory *rmrr;
	struct acpi_dmar_atsr *atsr;
	struct acpi_dmar_rhsa *rhsa;

	switch (header->type) {
	case ACPI_DMAR_TYPE_HARDWARE_UNIT:
		drhd = container_of(header, struct acpi_dmar_hardware_unit,
				    header);
		printk (KERN_INFO PREFIX
			"DRHD base: %#016Lx flags: %#x\n",
			(unsigned long long)drhd->address, drhd->flags);
		break;
	case ACPI_DMAR_TYPE_RESERVED_MEMORY:
		rmrr = container_of(header, struct acpi_dmar_reserved_memory,
				    header);
		printk (KERN_INFO PREFIX
			"RMRR base: %#016Lx end: %#016Lx\n",
			(unsigned long long)rmrr->base_address,
			(unsigned long long)rmrr->end_address);
		break;
	case ACPI_DMAR_TYPE_ATSR:
		atsr = container_of(header, struct acpi_dmar_atsr, header);
		printk(KERN_INFO PREFIX "ATSR flags: %#x\n", atsr->flags);
		break;
	case ACPI_DMAR_HARDWARE_AFFINITY:
		rhsa = container_of(header, struct acpi_dmar_rhsa, header);
		printk(KERN_INFO PREFIX "RHSA base: %#016Lx proximity domain: %#x\n",
		       (unsigned long long)rhsa->base_address,
		       rhsa->proximity_domain);
		break;
	}
}

/**
 * dmar_table_detect - checks to see if the platform supports DMAR devices
 */
static int __init dmar_table_detect(void)
{
	acpi_status status = AE_OK;

	/* if we could find DMAR table, then there are DMAR devices */
	status = acpi_get_table_with_size(ACPI_SIG_DMAR, 0,
				(struct acpi_table_header **)&dmar_tbl,
				&dmar_tbl_size);

	if (ACPI_SUCCESS(status) && !dmar_tbl) {
		printk (KERN_WARNING PREFIX "Unable to map DMAR\n");
		status = AE_NOT_FOUND;
	}

	return (ACPI_SUCCESS(status) ? 1 : 0);
}

/**
 * parse_dmar_table - parses the DMA reporting table
 */
static int __init
parse_dmar_table(void)
{
	struct acpi_table_dmar *dmar;
	struct acpi_dmar_header *entry_header;
	int ret = 0;

	/*
	 * Do it again, earlier dmar_tbl mapping could be mapped with
	 * fixed map.
	 */
	dmar_table_detect();

	/*
	 * ACPI tables may not be DMA protected by tboot, so use DMAR copy
	 * SINIT saved in SinitMleData in TXT heap (which is DMA protected)
	 */
	dmar_tbl = tboot_get_dmar_table(dmar_tbl);

	dmar = (struct acpi_table_dmar *)dmar_tbl;
	if (!dmar)
		return -ENODEV;

	if (dmar->width < PAGE_SHIFT - 1) {
		printk(KERN_WARNING PREFIX "Invalid DMAR haw\n");
		return -EINVAL;
	}

	printk (KERN_INFO PREFIX "Host address width %d\n",
		dmar->width + 1);

	entry_header = (struct acpi_dmar_header *)(dmar + 1);
	while (((unsigned long)entry_header) <
			(((unsigned long)dmar) + dmar_tbl->length)) {
		/* Avoid looping forever on bad ACPI tables */
		if (entry_header->length == 0) {
			printk(KERN_WARNING PREFIX
				"Invalid 0-length structure\n");
			ret = -EINVAL;
			break;
		}

		dmar_table_print_dmar_entry(entry_header);

		switch (entry_header->type) {
		case ACPI_DMAR_TYPE_HARDWARE_UNIT:
			ret = dmar_parse_one_drhd(entry_header);
			break;
		case ACPI_DMAR_TYPE_RESERVED_MEMORY:
			ret = dmar_parse_one_rmrr(entry_header);
			break;
		case ACPI_DMAR_TYPE_ATSR:
			ret = dmar_parse_one_atsr(entry_header);
			break;
		case ACPI_DMAR_HARDWARE_AFFINITY:
#ifdef CONFIG_ACPI_NUMA
			ret = dmar_parse_one_rhsa(entry_header);
#endif
			break;
		default:
			printk(KERN_WARNING PREFIX
				"Unknown DMAR structure type %d\n",
				entry_header->type);
			ret = 0; /* for forward compatibility */
			break;
		}
		if (ret)
			break;

		entry_header = ((void *)entry_header + entry_header->length);
	}
	return ret;
}

static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
			  struct pci_dev *dev)
{
	int index;

	while (dev) {
		for (index = 0; index < cnt; index++)
			if (dev == devices[index])
				return 1;

		/* Check our parent */
		dev = dev->bus->self;
	}

	return 0;
}

struct dmar_drhd_unit *
dmar_find_matched_drhd_unit(struct pci_dev *dev)
{
	struct dmar_drhd_unit *dmaru = NULL;
	struct acpi_dmar_hardware_unit *drhd;

	dev = pci_physfn(dev);

	list_for_each_entry(dmaru, &dmar_drhd_units, list) {
		drhd = container_of(dmaru->hdr,
				    struct acpi_dmar_hardware_unit,
				    header);

		if (dmaru->include_all &&
		    drhd->segment == pci_domain_nr(dev->bus))
			return dmaru;

		if (dmar_pci_device_match(dmaru->devices,
					  dmaru->devices_cnt, dev))
			return dmaru;
	}

	return NULL;
}

int __init dmar_dev_scope_init(void)
{
	static int dmar_dev_scope_initialized;
	struct dmar_drhd_unit *drhd, *drhd_n;
	int ret = -ENODEV;

	if (dmar_dev_scope_initialized)
		return dmar_dev_scope_initialized;

	if (list_empty(&dmar_drhd_units))
		goto fail;

	list_for_each_entry_safe(drhd, drhd_n, &dmar_drhd_units, list) {
		ret = dmar_parse_dev(drhd);
		if (ret)
			goto fail;
	}

	ret = dmar_parse_rmrr_atsr_dev();
	if (ret)
		goto fail;

	dmar_dev_scope_initialized = 1;
	return 0;

fail:
	dmar_dev_scope_initialized = ret;
	return ret;
}


int __init dmar_table_init(void)
{
	static int dmar_table_initialized;
	int ret;

	if (dmar_table_initialized)
		return 0;

	dmar_table_initialized = 1;

	ret = parse_dmar_table();
	if (ret) {
		if (ret != -ENODEV)
			printk(KERN_INFO PREFIX "parse DMAR table failure.\n");
		return ret;
	}

	if (list_empty(&dmar_drhd_units)) {
		printk(KERN_INFO PREFIX "No DMAR devices found\n");
		return -ENODEV;
	}

	return 0;
}

static void warn_invalid_dmar(u64 addr, const char *message)
{
	WARN_TAINT_ONCE(
		1, TAINT_FIRMWARE_WORKAROUND,
		"Your BIOS is broken; DMAR reported at address %llx%s!\n"
		"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
		addr, message,
		dmi_get_system_info(DMI_BIOS_VENDOR),
		dmi_get_system_info(DMI_BIOS_VERSION),
		dmi_get_system_info(DMI_PRODUCT_VERSION));
}

int __init check_zero_address(void)
{
	struct acpi_table_dmar *dmar;
	struct acpi_dmar_header *entry_header;
	struct acpi_dmar_hardware_unit *drhd;

	dmar = (struct acpi_table_dmar *)dmar_tbl;
	entry_header = (struct acpi_dmar_header *)(dmar + 1);

	while (((unsigned long)entry_header) <
			(((unsigned long)dmar) + dmar_tbl->length)) {
		/* Avoid looping forever on bad ACPI tables */
		if (entry_header->length == 0) {
			printk(KERN_WARNING PREFIX
				"Invalid 0-length structure\n");
			return 0;
		}

		if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
			void __iomem *addr;
			u64 cap, ecap;

			drhd = (void *)entry_header;
			if (!drhd->address) {
				warn_invalid_dmar(0, "");
				goto failed;
			}

			addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
			if (!addr ) {
				printk("IOMMU: can't validate: %llx\n", drhd->address);
				goto failed;
			}
			cap = dmar_readq(addr + DMAR_CAP_REG);
			ecap = dmar_readq(addr + DMAR_ECAP_REG);
			early_iounmap(addr, VTD_PAGE_SIZE);
			if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
				warn_invalid_dmar(drhd->address,
						  " returns all ones");
				goto failed;
			}
		}

		entry_header = ((void *)entry_header + entry_header->length);
	}
	return 1;

failed:
	return 0;
}

int __init detect_intel_iommu(void)
{
	int ret;

	ret = dmar_table_detect();
	if (ret)
		ret = check_zero_address();
	{
		struct acpi_table_dmar *dmar;

		dmar = (struct acpi_table_dmar *) dmar_tbl;

		if (ret && intr_remapping_enabled && cpu_has_x2apic &&
		    dmar->flags & 0x1)
			printk(KERN_INFO
			       "Queued invalidation will be enabled to support x2apic and Intr-remapping.\n");

		if (ret && !no_iommu && !iommu_detected && !dmar_disabled) {
			iommu_detected = 1;
			/* Make sure ACS will be enabled */
			pci_request_acs();
		}

#ifdef CONFIG_X86
		if (ret)
			x86_init.iommu.iommu_init = intel_iommu_init;
#endif
	}
	early_acpi_os_unmap_memory(dmar_tbl, dmar_tbl_size);
	dmar_tbl = NULL;

	return ret ? 1 : -ENODEV;
}


int alloc_iommu(struct dmar_drhd_unit *drhd)
{
	struct intel_iommu *iommu;
	int map_size;
	u32 ver;
	static int iommu_allocated = 0;
	int agaw = 0;
	int msagaw = 0;

	if (!drhd->reg_base_addr) {
		warn_invalid_dmar(0, "");
		return -EINVAL;
	}

	iommu = kzalloc(sizeof(*iommu), GFP_KERNEL);
	if (!iommu)
		return -ENOMEM;

	iommu->seq_id = iommu_allocated++;
	sprintf (iommu->name, "dmar%d", iommu->seq_id);

	iommu->reg = ioremap(drhd->reg_base_addr, VTD_PAGE_SIZE);
	if (!iommu->reg) {
		printk(KERN_ERR "IOMMU: can't map the region\n");
		goto error;
	}
	iommu->cap = dmar_readq(iommu->reg + DMAR_CAP_REG);
	iommu->ecap = dmar_readq(iommu->reg + DMAR_ECAP_REG);

	if (iommu->cap == (uint64_t)-1 && iommu->ecap == (uint64_t)-1) {
		warn_invalid_dmar(drhd->reg_base_addr, " returns all ones");
		goto err_unmap;
	}

	agaw = iommu_calculate_agaw(iommu);
	if (agaw < 0) {
		printk(KERN_ERR
		       "Cannot get a valid agaw for iommu (seq_id = %d)\n",
		       iommu->seq_id);
		goto err_unmap;
	}
	msagaw = iommu_calculate_max_sagaw(iommu);
	if (msagaw < 0) {
		printk(KERN_ERR
			"Cannot get a valid max agaw for iommu (seq_id = %d)\n",
			iommu->seq_id);
		goto err_unmap;
	}
	iommu->agaw = agaw;
	iommu->msagaw = msagaw;

	iommu->node = -1;

	/* the registers might be more than one page */
	map_size = max_t(int, ecap_max_iotlb_offset(iommu->ecap),
		cap_max_fault_reg_offset(iommu->cap));
	map_size = VTD_PAGE_ALIGN(map_size);
	if (map_size > VTD_PAGE_SIZE) {
		iounmap(iommu->reg);
		iommu->reg = ioremap(drhd->reg_base_addr, map_size);
		if (!iommu->reg) {
			printk(KERN_ERR "IOMMU: can't map the region\n");
			goto error;
		}
	}

	ver = readl(iommu->reg + DMAR_VER_REG);
	pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
		iommu->seq_id,
		(unsigned long long)drhd->reg_base_addr,
		DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
		(unsigned long long)iommu->cap,
		(unsigned long long)iommu->ecap);

	raw_spin_lock_init(&iommu->register_lock);

	drhd->iommu = iommu;
	return 0;

 err_unmap:
	iounmap(iommu->reg);
 error:
	kfree(iommu);
	return -1;
}

void free_iommu(struct intel_iommu *iommu)
{
	if (!iommu)
		return;

	free_dmar_iommu(iommu);

	if (iommu->reg)
		iounmap(iommu->reg);
	kfree(iommu);
}

/*
 * Reclaim all the submitted descriptors which have completed its work.
 */
static inline void reclaim_free_desc(struct q_inval *qi)
{
	while (qi->desc_status[qi->free_tail] == QI_DONE ||
	       qi->desc_status[qi->free_tail] == QI_ABORT) {
		qi->desc_status[qi->free_tail] = QI_FREE;
		qi->free_tail = (qi->free_tail + 1) % QI_LENGTH;
		qi->free_cnt++;
	}
}

static int qi_check_fault(struct intel_iommu *iommu, int index)
{
	u32 fault;
	int head, tail;
	struct q_inval *qi = iommu->qi;
	int wait_index = (index + 1) % QI_LENGTH;

	if (qi->desc_status[wait_index] == QI_ABORT)
		return -EAGAIN;

	fault = readl(iommu->reg + DMAR_FSTS_REG);

	/*
	 * If IQE happens, the head points to the descriptor associated
	 * with the error. No new descriptors are fetched until the IQE
	 * is cleared.
	 */
	if (fault & DMA_FSTS_IQE) {
		head = readl(iommu->reg + DMAR_IQH_REG);
		if ((head >> DMAR_IQ_SHIFT) == index) {
			printk(KERN_ERR "VT-d detected invalid descriptor: "
				"low=%llx, high=%llx\n",
				(unsigned long long)qi->desc[index].low,
				(unsigned long long)qi->desc[index].high);
			memcpy(&qi->desc[index], &qi->desc[wait_index],
					sizeof(struct qi_desc));
			__iommu_flush_cache(iommu, &qi->desc[index],
					sizeof(struct qi_desc));
			writel(DMA_FSTS_IQE, iommu->reg + DMAR_FSTS_REG);
			return -EINVAL;
		}
	}

	/*
	 * If ITE happens, all pending wait_desc commands are aborted.
	 * No new descriptors are fetched until the ITE is cleared.
	 */
	if (fault & DMA_FSTS_ITE) {
		head = readl(iommu->reg + DMAR_IQH_REG);
		head = ((head >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;
		head |= 1;
		tail = readl(iommu->reg + DMAR_IQT_REG);
		tail = ((tail >> DMAR_IQ_SHIFT) - 1 + QI_LENGTH) % QI_LENGTH;

		writel(DMA_FSTS_ITE, iommu->reg + DMAR_FSTS_REG);

		do {
			if (qi->desc_status[head] == QI_IN_USE)
				qi->desc_status[head] = QI_ABORT;
			head = (head - 2 + QI_LENGTH) % QI_LENGTH;
		} while (head != tail);

		if (qi->desc_status[wait_index] == QI_ABORT)
			return -EAGAIN;
	}

	if (fault & DMA_FSTS_ICE)
		writel(DMA_FSTS_ICE, iommu->reg + DMAR_FSTS_REG);

	return 0;
}

/*
 * Submit the queued invalidation descriptor to the remapping
 * hardware unit and wait for its completion.
 */
int qi_submit_sync(struct qi_desc *desc, struct intel_iommu *iommu)
{
	int rc;
	struct q_inval *qi = iommu->qi;
	struct qi_desc *hw, wait_desc;
	int wait_index, index;
	unsigned long flags;

	if (!qi)
		return 0;

	hw = qi->desc;

restart:
	rc = 0;

	raw_spin_lock_irqsave(&qi->q_lock, flags);
	while (qi->free_cnt < 3) {
		raw_spin_unlock_irqrestore(&qi->q_lock, flags);
		cpu_relax();
		raw_spin_lock_irqsave(&qi->q_lock, flags);
	}

	index = qi->free_head;
	wait_index = (index + 1) % QI_LENGTH;

	qi->desc_status[index] = qi->desc_status[wait_index] = QI_IN_USE;

	hw[index] = *desc;

	wait_desc.low = QI_IWD_STATUS_DATA(QI_DONE) |
			QI_IWD_STATUS_WRITE | QI_IWD_TYPE;
	wait_desc.high = virt_to_phys(&qi->desc_status[wait_index]);

	hw[wait_index] = wait_desc;

	__iommu_flush_cache(iommu, &hw[index], sizeof(struct qi_desc));
	__iommu_flush_cache(iommu, &hw[wait_index], sizeof(struct qi_desc));

	qi->free_head = (qi->free_head + 2) % QI_LENGTH;
	qi->free_cnt -= 2;

	/*
	 * update the HW tail register indicating the presence of
	 * new descriptors.
	 */
	writel(qi->free_head << DMAR_IQ_SHIFT, iommu->reg + DMAR_IQT_REG);

	while (qi->desc_status[wait_index] != QI_DONE) {
		/*
		 * We will leave the interrupts disabled, to prevent interrupt
		 * context to queue another cmd while a cmd is already submitted
		 * and waiting for completion on this cpu. This is to avoid
		 * a deadlock where the interrupt context can wait indefinitely
		 * for free slots in the queue.
		 */
		rc = qi_check_fault(iommu, index);
		if (rc)
			break;

		raw_spin_unlock(&qi->q_lock);
		cpu_relax();
		raw_spin_lock(&qi->q_lock);
	}

	qi->desc_status[index] = QI_DONE;

	reclaim_free_desc(qi);
	raw_spin_unlock_irqrestore(&qi->q_lock, flags);

	if (rc == -EAGAIN)
		goto restart;

	return rc;
}

/*
 * Flush the global interrupt entry cache.
 */
void qi_global_iec(struct intel_iommu *iommu)
{
	struct qi_desc desc;

	desc.low = QI_IEC_TYPE;
	desc.high = 0;

	/* should never fail */
	qi_submit_sync(&desc, iommu);
}

void qi_flush_context(struct intel_iommu *iommu, u16 did, u16 sid, u8 fm,
		      u64 type)
{
	struct qi_desc desc;

	desc.low = QI_CC_FM(fm) | QI_CC_SID(sid) | QI_CC_DID(did)
			| QI_CC_GRAN(type) | QI_CC_TYPE;
	desc.high = 0;

	qi_submit_sync(&desc, iommu);
}

void qi_flush_iotlb(struct intel_iommu *iommu, u16 did, u64 addr,
		    unsigned int size_order, u64 type)
{
	u8 dw = 0, dr = 0;

	struct qi_desc desc;
	int ih = 0;

	if (cap_write_drain(iommu->cap))
		dw = 1;

	if (cap_read_drain(iommu->cap))
		dr = 1;

	desc.low = QI_IOTLB_DID(did) | QI_IOTLB_DR(dr) | QI_IOTLB_DW(dw)
		| QI_IOTLB_GRAN(type) | QI_IOTLB_TYPE;
	desc.high = QI_IOTLB_ADDR(addr) | QI_IOTLB_IH(ih)
		| QI_IOTLB_AM(size_order);

	qi_submit_sync(&desc, iommu);
}

void qi_flush_dev_iotlb(struct intel_iommu *iommu, u16 sid, u16 qdep,
			u64 addr, unsigned mask)
{
	struct qi_desc desc;

	if (mask) {
		BUG_ON(addr & ((1 << (VTD_PAGE_SHIFT + mask)) - 1));
		addr |= (1 << (VTD_PAGE_SHIFT + mask - 1)) - 1;
		desc.high = QI_DEV_IOTLB_ADDR(addr) | QI_DEV_IOTLB_SIZE;
	} else
		desc.high = QI_DEV_IOTLB_ADDR(addr);

	if (qdep >= QI_DEV_IOTLB_MAX_INVS)
		qdep = 0;

	desc.low = QI_DEV_IOTLB_SID(sid) | QI_DEV_IOTLB_QDEP(qdep) |
		   QI_DIOTLB_TYPE;

	qi_submit_sync(&desc, iommu);
}

/*
 * Disable Queued Invalidation interface.
 */
void dmar_disable_qi(struct intel_iommu *iommu)
{
	unsigned long flags;
	u32 sts;
	cycles_t start_time = get_cycles();

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

	raw_spin_lock_irqsave(&iommu->register_lock, flags);

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

	/*
	 * Give a chance to HW to complete the pending invalidation requests.
	 */
	while ((readl(iommu->reg + DMAR_IQT_REG) !=
		readl(iommu->reg + DMAR_IQH_REG)) &&
		(DMAR_OPERATION_TIMEOUT > (get_cycles() - start_time)))
		cpu_relax();

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

	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl,
		      !(sts & DMA_GSTS_QIES), sts);
end:
	raw_spin_unlock_irqrestore(&iommu->register_lock, flags);
}

/*
 * Enable queued invalidation.
 */
static void __dmar_enable_qi(struct intel_iommu *iommu)
{
	u32 sts;
	unsigned long flags;
	struct q_inval *qi = iommu->qi;

	qi->free_head = qi->free_tail = 0;
	qi->free_cnt = QI_LENGTH;

	raw_spin_lock_irqsave(&iommu->register_lock, flags);

	/* write zero to the tail reg */
	writel(0, iommu->reg + DMAR_IQT_REG);

	dmar_writeq(iommu->reg + DMAR_IQA_REG, virt_to_phys(qi->desc));

	iommu->gcmd |= DMA_GCMD_QIE;
	writel(iommu->gcmd, iommu->reg + DMAR_GCMD_REG);

	/* Make sure hardware complete it */
	IOMMU_WAIT_OP(iommu, DMAR_GSTS_REG, readl, (sts & DMA_GSTS_QIES), sts);

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

/*
 * Enable Queued Invalidation interface. This is a must to support
 * interrupt-remapping. Also used by DMA-remapping, which replaces
 * register based IOTLB invalidation.
 */
int dmar_enable_qi(struct intel_iommu *iommu)
{
	struct q_inval *qi;
	struct page *desc_page;

	if (!ecap_qis(iommu->ecap))
		return -ENOENT;

	/*
	 * queued invalidation is already setup and enabled.
	 */
	if (iommu->qi)
		return 0;

	iommu->qi = kmalloc(sizeof(*qi), GFP_ATOMIC);
	if (!iommu->qi)
		return -ENOMEM;

	qi = iommu->qi;


	desc_page = alloc_pages_node(iommu->node, GFP_ATOMIC | __GFP_ZERO, 0);
	if (!desc_page) {
		kfree(qi);
		iommu->qi = 0;
		return -ENOMEM;
	}

	qi->desc = page_address(desc_page);

	qi->desc_status = kmalloc(QI_LENGTH * sizeof(int), GFP_ATOMIC);
	if (!qi->desc_status) {
		free_page((unsigned long) qi->desc);
		kfree(qi);
		iommu->qi = 0;
		return -ENOMEM;
	}

	qi->free_head = qi->free_tail = 0;
	qi->free_cnt = QI_LENGTH;

	raw_spin_lock_init(&qi->q_lock);

	__dmar_enable_qi(iommu);

	return 0;
}

/* iommu interrupt handling. Most stuff are MSI-like. */

enum faulttype {
	DMA_REMAP,
	INTR_REMAP,
	UNKNOWN,
};

static const char *dma_remap_fault_reasons[] =
{
	"Software",
	"Present bit in root entry is clear",
	"Present bit in context entry is clear",
	"Invalid context entry",
	"Access beyond MGAW",
	"PTE Write access is not set",
	"PTE Read access is not set",
	"Next page table ptr is invalid",
	"Root table address invalid",
	"Context table ptr is invalid",
	"non-zero reserved fields in RTP",
	"non-zero reserved fields in CTP",
	"non-zero reserved fields in PTE",
};

static const char *intr_remap_fault_reasons[] =
{
	"Detected reserved fields in the decoded interrupt-remapped request",
	"Interrupt index exceeded the interrupt-remapping table size",
	"Present field in the IRTE entry is clear",
	"Error accessing interrupt-remapping table pointed by IRTA_REG",
	"Detected reserved fields in the IRTE entry",
	"Blocked a compatibility format interrupt request",
	"Blocked an interrupt request due to source-id verification failure",
};

#define MAX_FAULT_REASON_IDX 	(ARRAY_SIZE(fault_reason_strings) - 1)

const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
{
	if (fault_reason >= 0x20 && (fault_reason <= 0x20 +
				     ARRAY_SIZE(intr_remap_fault_reasons))) {
		*fault_type = INTR_REMAP;
		return intr_remap_fault_reasons[fault_reason - 0x20];
	} else if (fault_reason < ARRAY_SIZE(dma_remap_fault_reasons)) {
		*fault_type = DMA_REMAP;
		return dma_remap_fault_reasons[fault_reason];
	} else {
		*fault_type = UNKNOWN;
		return "Unknown";
	}
}

void dmar_msi_unmask(struct irq_data *data)
{
	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);
	unsigned long flag;

	/* unmask it */
	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	writel(0, iommu->reg + DMAR_FECTL_REG);
	/* Read a reg to force flush the post write */
	readl(iommu->reg + DMAR_FECTL_REG);
	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

void dmar_msi_mask(struct irq_data *data)
{
	unsigned long flag;
	struct intel_iommu *iommu = irq_data_get_irq_handler_data(data);

	/* mask it */
	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	writel(DMA_FECTL_IM, iommu->reg + DMAR_FECTL_REG);
	/* Read a reg to force flush the post write */
	readl(iommu->reg + DMAR_FECTL_REG);
	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

void dmar_msi_write(int irq, struct msi_msg *msg)
{
	struct intel_iommu *iommu = irq_get_handler_data(irq);
	unsigned long flag;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	writel(msg->data, iommu->reg + DMAR_FEDATA_REG);
	writel(msg->address_lo, iommu->reg + DMAR_FEADDR_REG);
	writel(msg->address_hi, iommu->reg + DMAR_FEUADDR_REG);
	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

void dmar_msi_read(int irq, struct msi_msg *msg)
{
	struct intel_iommu *iommu = irq_get_handler_data(irq);
	unsigned long flag;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	msg->data = readl(iommu->reg + DMAR_FEDATA_REG);
	msg->address_lo = readl(iommu->reg + DMAR_FEADDR_REG);
	msg->address_hi = readl(iommu->reg + DMAR_FEUADDR_REG);
	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
}

static int dmar_fault_do_one(struct intel_iommu *iommu, int type,
		u8 fault_reason, u16 source_id, unsigned long long addr)
{
	const char *reason;
	int fault_type;

	reason = dmar_get_fault_reason(fault_reason, &fault_type);

	if (fault_type == INTR_REMAP)
		printk(KERN_ERR "INTR-REMAP: Request device [[%02x:%02x.%d] "
		       "fault index %llx\n"
			"INTR-REMAP:[fault reason %02d] %s\n",
			(source_id >> 8), PCI_SLOT(source_id & 0xFF),
			PCI_FUNC(source_id & 0xFF), addr >> 48,
			fault_reason, reason);
	else
		printk(KERN_ERR
		       "DMAR:[%s] Request device [%02x:%02x.%d] "
		       "fault addr %llx \n"
		       "DMAR:[fault reason %02d] %s\n",
		       (type ? "DMA Read" : "DMA Write"),
		       (source_id >> 8), PCI_SLOT(source_id & 0xFF),
		       PCI_FUNC(source_id & 0xFF), addr, fault_reason, reason);
	return 0;
}

#define PRIMARY_FAULT_REG_LEN (16)
irqreturn_t dmar_fault(int irq, void *dev_id)
{
	struct intel_iommu *iommu = dev_id;
	int reg, fault_index;
	u32 fault_status;
	unsigned long flag;

	raw_spin_lock_irqsave(&iommu->register_lock, flag);
	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
	if (fault_status)
		printk(KERN_ERR "DRHD: handling fault status reg %x\n",
		       fault_status);

	/* TBD: ignore advanced fault log currently */
	if (!(fault_status & DMA_FSTS_PPF))
		goto clear_rest;

	fault_index = dma_fsts_fault_record_index(fault_status);
	reg = cap_fault_reg_offset(iommu->cap);
	while (1) {
		u8 fault_reason;
		u16 source_id;
		u64 guest_addr;
		int type;
		u32 data;

		/* highest 32 bits */
		data = readl(iommu->reg + reg +
				fault_index * PRIMARY_FAULT_REG_LEN + 12);
		if (!(data & DMA_FRCD_F))
			break;

		fault_reason = dma_frcd_fault_reason(data);
		type = dma_frcd_type(data);

		data = readl(iommu->reg + reg +
				fault_index * PRIMARY_FAULT_REG_LEN + 8);
		source_id = dma_frcd_source_id(data);

		guest_addr = dmar_readq(iommu->reg + reg +
				fault_index * PRIMARY_FAULT_REG_LEN);
		guest_addr = dma_frcd_page_addr(guest_addr);
		/* clear the fault */
		writel(DMA_FRCD_F, iommu->reg + reg +
			fault_index * PRIMARY_FAULT_REG_LEN + 12);

		raw_spin_unlock_irqrestore(&iommu->register_lock, flag);

		dmar_fault_do_one(iommu, type, fault_reason,
				source_id, guest_addr);

		fault_index++;
		if (fault_index >= cap_num_fault_regs(iommu->cap))
			fault_index = 0;
		raw_spin_lock_irqsave(&iommu->register_lock, flag);
	}
clear_rest:
	/* clear all the other faults */
	fault_status = readl(iommu->reg + DMAR_FSTS_REG);
	writel(fault_status, iommu->reg + DMAR_FSTS_REG);

	raw_spin_unlock_irqrestore(&iommu->register_lock, flag);
	return IRQ_HANDLED;
}

int dmar_set_interrupt(struct intel_iommu *iommu)
{
	int irq, ret;

	/*
	 * Check if the fault interrupt is already initialized.
	 */
	if (iommu->irq)
		return 0;

	irq = create_irq();
	if (!irq) {
		printk(KERN_ERR "IOMMU: no free vectors\n");
		return -EINVAL;
	}

	irq_set_handler_data(irq, iommu);
	iommu->irq = irq;

	ret = arch_setup_dmar_msi(irq);
	if (ret) {
		irq_set_handler_data(irq, NULL);
		iommu->irq = 0;
		destroy_irq(irq);
		return ret;
	}

	ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
	if (ret)
		printk(KERN_ERR "IOMMU: can't request irq\n");
	return ret;
}

int __init enable_drhd_fault_handling(void)
{
	struct dmar_drhd_unit *drhd;

	/*
	 * Enable fault control interrupt.
	 */
	for_each_drhd_unit(drhd) {
		int ret;
		struct intel_iommu *iommu = drhd->iommu;
		ret = dmar_set_interrupt(iommu);

		if (ret) {
			printk(KERN_ERR "DRHD %Lx: failed to enable fault, "
			       " interrupt, ret %d\n",
			       (unsigned long long)drhd->reg_base_addr, ret);
			return -1;
		}

		/*
		 * Clear any previous faults.
		 */
		dmar_fault(iommu->irq, iommu);
	}

	return 0;
}

/*
 * Re-enable Queued Invalidation interface.
 */
int dmar_reenable_qi(struct intel_iommu *iommu)
{
	if (!ecap_qis(iommu->ecap))
		return -ENOENT;

	if (!iommu->qi)
		return -ENOENT;

	/*
	 * First disable queued invalidation.
	 */
	dmar_disable_qi(iommu);
	/*
	 * Then enable queued invalidation again. Since there is no pending
	 * invalidation requests now, it's safe to re-enable queued
	 * invalidation.
	 */
	__dmar_enable_qi(iommu);

	return 0;
}

/*
 * Check interrupt remapping support in DMAR table description.
 */
int __init dmar_ir_support(void)
{
	struct acpi_table_dmar *dmar;
	dmar = (struct acpi_table_dmar *)dmar_tbl;
	if (!dmar)
		return 0;
	return dmar->flags & 0x1;
}
IOMMU_INIT_POST(detect_intel_iommu);