summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/amd_iommu_init.c
blob: 3cc63e2b8dd4c4acc4ee7f77c3ad432d97beb169 (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
/*
 * Copyright (C) 2007-2009 Advanced Micro Devices, Inc.
 * Author: Joerg Roedel <joerg.roedel@amd.com>
 *         Leo Duran <leo.duran@amd.com>
 *
 * This program is free software; you can redistribute it and/or modify it
 * under the terms of the GNU General Public License version 2 as published
 * by the Free Software Foundation.
 *
 * This program is distributed in the hope that 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
 */

#include <linux/pci.h>
#include <linux/acpi.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/sysdev.h>
#include <linux/interrupt.h>
#include <linux/msi.h>
#include <asm/pci-direct.h>
#include <asm/amd_iommu_proto.h>
#include <asm/amd_iommu_types.h>
#include <asm/amd_iommu.h>
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/x86_init.h>

/*
 * definitions for the ACPI scanning code
 */
#define IVRS_HEADER_LENGTH 48

#define ACPI_IVHD_TYPE                  0x10
#define ACPI_IVMD_TYPE_ALL              0x20
#define ACPI_IVMD_TYPE                  0x21
#define ACPI_IVMD_TYPE_RANGE            0x22

#define IVHD_DEV_ALL                    0x01
#define IVHD_DEV_SELECT                 0x02
#define IVHD_DEV_SELECT_RANGE_START     0x03
#define IVHD_DEV_RANGE_END              0x04
#define IVHD_DEV_ALIAS                  0x42
#define IVHD_DEV_ALIAS_RANGE            0x43
#define IVHD_DEV_EXT_SELECT             0x46
#define IVHD_DEV_EXT_SELECT_RANGE       0x47

#define IVHD_FLAG_HT_TUN_EN_MASK        0x01
#define IVHD_FLAG_PASSPW_EN_MASK        0x02
#define IVHD_FLAG_RESPASSPW_EN_MASK     0x04
#define IVHD_FLAG_ISOC_EN_MASK          0x08

#define IVMD_FLAG_EXCL_RANGE            0x08
#define IVMD_FLAG_UNITY_MAP             0x01

#define ACPI_DEVFLAG_INITPASS           0x01
#define ACPI_DEVFLAG_EXTINT             0x02
#define ACPI_DEVFLAG_NMI                0x04
#define ACPI_DEVFLAG_SYSMGT1            0x10
#define ACPI_DEVFLAG_SYSMGT2            0x20
#define ACPI_DEVFLAG_LINT0              0x40
#define ACPI_DEVFLAG_LINT1              0x80
#define ACPI_DEVFLAG_ATSDIS             0x10000000

/*
 * ACPI table definitions
 *
 * These data structures are laid over the table to parse the important values
 * out of it.
 */

/*
 * structure describing one IOMMU in the ACPI table. Typically followed by one
 * or more ivhd_entrys.
 */
struct ivhd_header {
	u8 type;
	u8 flags;
	u16 length;
	u16 devid;
	u16 cap_ptr;
	u64 mmio_phys;
	u16 pci_seg;
	u16 info;
	u32 reserved;
} __attribute__((packed));

/*
 * A device entry describing which devices a specific IOMMU translates and
 * which requestor ids they use.
 */
struct ivhd_entry {
	u8 type;
	u16 devid;
	u8 flags;
	u32 ext;
} __attribute__((packed));

/*
 * An AMD IOMMU memory definition structure. It defines things like exclusion
 * ranges for devices and regions that should be unity mapped.
 */
struct ivmd_header {
	u8 type;
	u8 flags;
	u16 length;
	u16 devid;
	u16 aux;
	u64 resv;
	u64 range_start;
	u64 range_length;
} __attribute__((packed));

bool amd_iommu_dump;

static int __initdata amd_iommu_detected;
static bool __initdata amd_iommu_disabled;

u16 amd_iommu_last_bdf;			/* largest PCI device id we have
					   to handle */
LIST_HEAD(amd_iommu_unity_map);		/* a list of required unity mappings
					   we find in ACPI */
bool amd_iommu_unmap_flush;		/* if true, flush on every unmap */

LIST_HEAD(amd_iommu_list);		/* list of all AMD IOMMUs in the
					   system */

/* Array to assign indices to IOMMUs*/
struct amd_iommu *amd_iommus[MAX_IOMMUS];
int amd_iommus_present;

/* IOMMUs have a non-present cache? */
bool amd_iommu_np_cache __read_mostly;

/*
 * The ACPI table parsing functions set this variable on an error
 */
static int __initdata amd_iommu_init_err;

/*
 * List of protection domains - used during resume
 */
LIST_HEAD(amd_iommu_pd_list);
spinlock_t amd_iommu_pd_lock;

/*
 * Pointer to the device table which is shared by all AMD IOMMUs
 * it is indexed by the PCI device id or the HT unit id and contains
 * information about the domain the device belongs to as well as the
 * page table root pointer.
 */
struct dev_table_entry *amd_iommu_dev_table;

/*
 * The alias table is a driver specific data structure which contains the
 * mappings of the PCI device ids to the actual requestor ids on the IOMMU.
 * More than one device can share the same requestor id.
 */
u16 *amd_iommu_alias_table;

/*
 * The rlookup table is used to find the IOMMU which is responsible
 * for a specific device. It is also indexed by the PCI device id.
 */
struct amd_iommu **amd_iommu_rlookup_table;

/*
 * AMD IOMMU allows up to 2^16 differend protection domains. This is a bitmap
 * to know which ones are already in use.
 */
unsigned long *amd_iommu_pd_alloc_bitmap;

static u32 dev_table_size;	/* size of the device table */
static u32 alias_table_size;	/* size of the alias table */
static u32 rlookup_table_size;	/* size if the rlookup table */

static inline void update_last_devid(u16 devid)
{
	if (devid > amd_iommu_last_bdf)
		amd_iommu_last_bdf = devid;
}

static inline unsigned long tbl_size(int entry_size)
{
	unsigned shift = PAGE_SHIFT +
			 get_order(((int)amd_iommu_last_bdf + 1) * entry_size);

	return 1UL << shift;
}

/****************************************************************************
 *
 * AMD IOMMU MMIO register space handling functions
 *
 * These functions are used to program the IOMMU device registers in
 * MMIO space required for that driver.
 *
 ****************************************************************************/

/*
 * This function set the exclusion range in the IOMMU. DMA accesses to the
 * exclusion range are passed through untranslated
 */
static void iommu_set_exclusion_range(struct amd_iommu *iommu)
{
	u64 start = iommu->exclusion_start & PAGE_MASK;
	u64 limit = (start + iommu->exclusion_length) & PAGE_MASK;
	u64 entry;

	if (!iommu->exclusion_start)
		return;

	entry = start | MMIO_EXCL_ENABLE_MASK;
	memcpy_toio(iommu->mmio_base + MMIO_EXCL_BASE_OFFSET,
			&entry, sizeof(entry));

	entry = limit;
	memcpy_toio(iommu->mmio_base + MMIO_EXCL_LIMIT_OFFSET,
			&entry, sizeof(entry));
}

/* Programs the physical address of the device table into the IOMMU hardware */
static void __init iommu_set_device_table(struct amd_iommu *iommu)
{
	u64 entry;

	BUG_ON(iommu->mmio_base == NULL);

	entry = virt_to_phys(amd_iommu_dev_table);
	entry |= (dev_table_size >> 12) - 1;
	memcpy_toio(iommu->mmio_base + MMIO_DEV_TABLE_OFFSET,
			&entry, sizeof(entry));
}

/* Generic functions to enable/disable certain features of the IOMMU. */
static void iommu_feature_enable(struct amd_iommu *iommu, u8 bit)
{
	u32 ctrl;

	ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET);
	ctrl |= (1 << bit);
	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
}

static void iommu_feature_disable(struct amd_iommu *iommu, u8 bit)
{
	u32 ctrl;

	ctrl = readl(iommu->mmio_base + MMIO_CONTROL_OFFSET);
	ctrl &= ~(1 << bit);
	writel(ctrl, iommu->mmio_base + MMIO_CONTROL_OFFSET);
}

/* Function to enable the hardware */
static void iommu_enable(struct amd_iommu *iommu)
{
	printk(KERN_INFO "AMD-Vi: Enabling IOMMU at %s cap 0x%hx\n",
	       dev_name(&iommu->dev->dev), iommu->cap_ptr);

	iommu_feature_enable(iommu, CONTROL_IOMMU_EN);
}

static void iommu_disable(struct amd_iommu *iommu)
{
	/* Disable command buffer */
	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);

	/* Disable event logging and event interrupts */
	iommu_feature_disable(iommu, CONTROL_EVT_INT_EN);
	iommu_feature_disable(iommu, CONTROL_EVT_LOG_EN);

	/* Disable IOMMU hardware itself */
	iommu_feature_disable(iommu, CONTROL_IOMMU_EN);
}

/*
 * mapping and unmapping functions for the IOMMU MMIO space. Each AMD IOMMU in
 * the system has one.
 */
static u8 * __init iommu_map_mmio_space(u64 address)
{
	u8 *ret;

	if (!request_mem_region(address, MMIO_REGION_LENGTH, "amd_iommu")) {
		pr_err("AMD-Vi: Can not reserve memory region %llx for mmio\n",
			address);
		pr_err("AMD-Vi: This is a BIOS bug. Please contact your hardware vendor\n");
		return NULL;
	}

	ret = ioremap_nocache(address, MMIO_REGION_LENGTH);
	if (ret != NULL)
		return ret;

	release_mem_region(address, MMIO_REGION_LENGTH);

	return NULL;
}

static void __init iommu_unmap_mmio_space(struct amd_iommu *iommu)
{
	if (iommu->mmio_base)
		iounmap(iommu->mmio_base);
	release_mem_region(iommu->mmio_phys, MMIO_REGION_LENGTH);
}

/****************************************************************************
 *
 * The functions below belong to the first pass of AMD IOMMU ACPI table
 * parsing. In this pass we try to find out the highest device id this
 * code has to handle. Upon this information the size of the shared data
 * structures is determined later.
 *
 ****************************************************************************/

/*
 * This function calculates the length of a given IVHD entry
 */
static inline int ivhd_entry_length(u8 *ivhd)
{
	return 0x04 << (*ivhd >> 6);
}

/*
 * This function reads the last device id the IOMMU has to handle from the PCI
 * capability header for this IOMMU
 */
static int __init find_last_devid_on_pci(int bus, int dev, int fn, int cap_ptr)
{
	u32 cap;

	cap = read_pci_config(bus, dev, fn, cap_ptr+MMIO_RANGE_OFFSET);
	update_last_devid(calc_devid(MMIO_GET_BUS(cap), MMIO_GET_LD(cap)));

	return 0;
}

/*
 * After reading the highest device id from the IOMMU PCI capability header
 * this function looks if there is a higher device id defined in the ACPI table
 */
static int __init find_last_devid_from_ivhd(struct ivhd_header *h)
{
	u8 *p = (void *)h, *end = (void *)h;
	struct ivhd_entry *dev;

	p += sizeof(*h);
	end += h->length;

	find_last_devid_on_pci(PCI_BUS(h->devid),
			PCI_SLOT(h->devid),
			PCI_FUNC(h->devid),
			h->cap_ptr);

	while (p < end) {
		dev = (struct ivhd_entry *)p;
		switch (dev->type) {
		case IVHD_DEV_SELECT:
		case IVHD_DEV_RANGE_END:
		case IVHD_DEV_ALIAS:
		case IVHD_DEV_EXT_SELECT:
			/* all the above subfield types refer to device ids */
			update_last_devid(dev->devid);
			break;
		default:
			break;
		}
		p += ivhd_entry_length(p);
	}

	WARN_ON(p != end);

	return 0;
}

/*
 * Iterate over all IVHD entries in the ACPI table and find the highest device
 * id which we need to handle. This is the first of three functions which parse
 * the ACPI table. So we check the checksum here.
 */
static int __init find_last_devid_acpi(struct acpi_table_header *table)
{
	int i;
	u8 checksum = 0, *p = (u8 *)table, *end = (u8 *)table;
	struct ivhd_header *h;

	/*
	 * Validate checksum here so we don't need to do it when
	 * we actually parse the table
	 */
	for (i = 0; i < table->length; ++i)
		checksum += p[i];
	if (checksum != 0) {
		/* ACPI table corrupt */
		amd_iommu_init_err = -ENODEV;
		return 0;
	}

	p += IVRS_HEADER_LENGTH;

	end += table->length;
	while (p < end) {
		h = (struct ivhd_header *)p;
		switch (h->type) {
		case ACPI_IVHD_TYPE:
			find_last_devid_from_ivhd(h);
			break;
		default:
			break;
		}
		p += h->length;
	}
	WARN_ON(p != end);

	return 0;
}

/****************************************************************************
 *
 * The following functions belong the the code path which parses the ACPI table
 * the second time. In this ACPI parsing iteration we allocate IOMMU specific
 * data structures, initialize the device/alias/rlookup table and also
 * basically initialize the hardware.
 *
 ****************************************************************************/

/*
 * Allocates the command buffer. This buffer is per AMD IOMMU. We can
 * write commands to that buffer later and the IOMMU will execute them
 * asynchronously
 */
static u8 * __init alloc_command_buffer(struct amd_iommu *iommu)
{
	u8 *cmd_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
			get_order(CMD_BUFFER_SIZE));

	if (cmd_buf == NULL)
		return NULL;

	iommu->cmd_buf_size = CMD_BUFFER_SIZE | CMD_BUFFER_UNINITIALIZED;

	return cmd_buf;
}

/*
 * This function resets the command buffer if the IOMMU stopped fetching
 * commands from it.
 */
void amd_iommu_reset_cmd_buffer(struct amd_iommu *iommu)
{
	iommu_feature_disable(iommu, CONTROL_CMDBUF_EN);

	writel(0x00, iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
	writel(0x00, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);

	iommu_feature_enable(iommu, CONTROL_CMDBUF_EN);
}

/*
 * This function writes the command buffer address to the hardware and
 * enables it.
 */
static void iommu_enable_command_buffer(struct amd_iommu *iommu)
{
	u64 entry;

	BUG_ON(iommu->cmd_buf == NULL);

	entry = (u64)virt_to_phys(iommu->cmd_buf);
	entry |= MMIO_CMD_SIZE_512;

	memcpy_toio(iommu->mmio_base + MMIO_CMD_BUF_OFFSET,
		    &entry, sizeof(entry));

	amd_iommu_reset_cmd_buffer(iommu);
	iommu->cmd_buf_size &= ~(CMD_BUFFER_UNINITIALIZED);
}

static void __init free_command_buffer(struct amd_iommu *iommu)
{
	free_pages((unsigned long)iommu->cmd_buf,
		   get_order(iommu->cmd_buf_size & ~(CMD_BUFFER_UNINITIALIZED)));
}

/* allocates the memory where the IOMMU will log its events to */
static u8 * __init alloc_event_buffer(struct amd_iommu *iommu)
{
	iommu->evt_buf = (u8 *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
						get_order(EVT_BUFFER_SIZE));

	if (iommu->evt_buf == NULL)
		return NULL;

	iommu->evt_buf_size = EVT_BUFFER_SIZE;

	return iommu->evt_buf;
}

static void iommu_enable_event_buffer(struct amd_iommu *iommu)
{
	u64 entry;

	BUG_ON(iommu->evt_buf == NULL);

	entry = (u64)virt_to_phys(iommu->evt_buf) | EVT_LEN_MASK;

	memcpy_toio(iommu->mmio_base + MMIO_EVT_BUF_OFFSET,
		    &entry, sizeof(entry));

	/* set head and tail to zero manually */
	writel(0x00, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
	writel(0x00, iommu->mmio_base + MMIO_EVT_TAIL_OFFSET);

	iommu_feature_enable(iommu, CONTROL_EVT_LOG_EN);
}

static void __init free_event_buffer(struct amd_iommu *iommu)
{
	free_pages((unsigned long)iommu->evt_buf, get_order(EVT_BUFFER_SIZE));
}

/* sets a specific bit in the device table entry. */
static void set_dev_entry_bit(u16 devid, u8 bit)
{
	int i = (bit >> 5) & 0x07;
	int _bit = bit & 0x1f;

	amd_iommu_dev_table[devid].data[i] |= (1 << _bit);
}

static int get_dev_entry_bit(u16 devid, u8 bit)
{
	int i = (bit >> 5) & 0x07;
	int _bit = bit & 0x1f;

	return (amd_iommu_dev_table[devid].data[i] & (1 << _bit)) >> _bit;
}


void amd_iommu_apply_erratum_63(u16 devid)
{
	int sysmgt;

	sysmgt = get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1) |
		 (get_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2) << 1);

	if (sysmgt == 0x01)
		set_dev_entry_bit(devid, DEV_ENTRY_IW);
}

/* Writes the specific IOMMU for a device into the rlookup table */
static void __init set_iommu_for_device(struct amd_iommu *iommu, u16 devid)
{
	amd_iommu_rlookup_table[devid] = iommu;
}

/*
 * This function takes the device specific flags read from the ACPI
 * table and sets up the device table entry with that information
 */
static void __init set_dev_entry_from_acpi(struct amd_iommu *iommu,
					   u16 devid, u32 flags, u32 ext_flags)
{
	if (flags & ACPI_DEVFLAG_INITPASS)
		set_dev_entry_bit(devid, DEV_ENTRY_INIT_PASS);
	if (flags & ACPI_DEVFLAG_EXTINT)
		set_dev_entry_bit(devid, DEV_ENTRY_EINT_PASS);
	if (flags & ACPI_DEVFLAG_NMI)
		set_dev_entry_bit(devid, DEV_ENTRY_NMI_PASS);
	if (flags & ACPI_DEVFLAG_SYSMGT1)
		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT1);
	if (flags & ACPI_DEVFLAG_SYSMGT2)
		set_dev_entry_bit(devid, DEV_ENTRY_SYSMGT2);
	if (flags & ACPI_DEVFLAG_LINT0)
		set_dev_entry_bit(devid, DEV_ENTRY_LINT0_PASS);
	if (flags & ACPI_DEVFLAG_LINT1)
		set_dev_entry_bit(devid, DEV_ENTRY_LINT1_PASS);

	amd_iommu_apply_erratum_63(devid);

	set_iommu_for_device(iommu, devid);
}

/*
 * Reads the device exclusion range from ACPI and initialize IOMMU with
 * it
 */
static void __init set_device_exclusion_range(u16 devid, struct ivmd_header *m)
{
	struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];

	if (!(m->flags & IVMD_FLAG_EXCL_RANGE))
		return;

	if (iommu) {
		/*
		 * We only can configure exclusion ranges per IOMMU, not
		 * per device. But we can enable the exclusion range per
		 * device. This is done here
		 */
		set_dev_entry_bit(m->devid, DEV_ENTRY_EX);
		iommu->exclusion_start = m->range_start;
		iommu->exclusion_length = m->range_length;
	}
}

/*
 * This function reads some important data from the IOMMU PCI space and
 * initializes the driver data structure with it. It reads the hardware
 * capabilities and the first/last device entries
 */
static void __init init_iommu_from_pci(struct amd_iommu *iommu)
{
	int cap_ptr = iommu->cap_ptr;
	u32 range, misc;

	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_CAP_HDR_OFFSET,
			      &iommu->cap);
	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_RANGE_OFFSET,
			      &range);
	pci_read_config_dword(iommu->dev, cap_ptr + MMIO_MISC_OFFSET,
			      &misc);

	iommu->first_device = calc_devid(MMIO_GET_BUS(range),
					 MMIO_GET_FD(range));
	iommu->last_device = calc_devid(MMIO_GET_BUS(range),
					MMIO_GET_LD(range));
	iommu->evt_msi_num = MMIO_MSI_NUM(misc);
}

/*
 * Takes a pointer to an AMD IOMMU entry in the ACPI table and
 * initializes the hardware and our data structures with it.
 */
static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
					struct ivhd_header *h)
{
	u8 *p = (u8 *)h;
	u8 *end = p, flags = 0;
	u16 dev_i, devid = 0, devid_start = 0, devid_to = 0;
	u32 ext_flags = 0;
	bool alias = false;
	struct ivhd_entry *e;

	/*
	 * First set the recommended feature enable bits from ACPI
	 * into the IOMMU control registers
	 */
	h->flags & IVHD_FLAG_HT_TUN_EN_MASK ?
		iommu_feature_enable(iommu, CONTROL_HT_TUN_EN) :
		iommu_feature_disable(iommu, CONTROL_HT_TUN_EN);

	h->flags & IVHD_FLAG_PASSPW_EN_MASK ?
		iommu_feature_enable(iommu, CONTROL_PASSPW_EN) :
		iommu_feature_disable(iommu, CONTROL_PASSPW_EN);

	h->flags & IVHD_FLAG_RESPASSPW_EN_MASK ?
		iommu_feature_enable(iommu, CONTROL_RESPASSPW_EN) :
		iommu_feature_disable(iommu, CONTROL_RESPASSPW_EN);

	h->flags & IVHD_FLAG_ISOC_EN_MASK ?
		iommu_feature_enable(iommu, CONTROL_ISOC_EN) :
		iommu_feature_disable(iommu, CONTROL_ISOC_EN);

	/*
	 * make IOMMU memory accesses cache coherent
	 */
	iommu_feature_enable(iommu, CONTROL_COHERENT_EN);

	/*
	 * Done. Now parse the device entries
	 */
	p += sizeof(struct ivhd_header);
	end += h->length;


	while (p < end) {
		e = (struct ivhd_entry *)p;
		switch (e->type) {
		case IVHD_DEV_ALL:

			DUMP_printk("  DEV_ALL\t\t\t first devid: %02x:%02x.%x"
				    " last device %02x:%02x.%x flags: %02x\n",
				    PCI_BUS(iommu->first_device),
				    PCI_SLOT(iommu->first_device),
				    PCI_FUNC(iommu->first_device),
				    PCI_BUS(iommu->last_device),
				    PCI_SLOT(iommu->last_device),
				    PCI_FUNC(iommu->last_device),
				    e->flags);

			for (dev_i = iommu->first_device;
					dev_i <= iommu->last_device; ++dev_i)
				set_dev_entry_from_acpi(iommu, dev_i,
							e->flags, 0);
			break;
		case IVHD_DEV_SELECT:

			DUMP_printk("  DEV_SELECT\t\t\t devid: %02x:%02x.%x "
				    "flags: %02x\n",
				    PCI_BUS(e->devid),
				    PCI_SLOT(e->devid),
				    PCI_FUNC(e->devid),
				    e->flags);

			devid = e->devid;
			set_dev_entry_from_acpi(iommu, devid, e->flags, 0);
			break;
		case IVHD_DEV_SELECT_RANGE_START:

			DUMP_printk("  DEV_SELECT_RANGE_START\t "
				    "devid: %02x:%02x.%x flags: %02x\n",
				    PCI_BUS(e->devid),
				    PCI_SLOT(e->devid),
				    PCI_FUNC(e->devid),
				    e->flags);

			devid_start = e->devid;
			flags = e->flags;
			ext_flags = 0;
			alias = false;
			break;
		case IVHD_DEV_ALIAS:

			DUMP_printk("  DEV_ALIAS\t\t\t devid: %02x:%02x.%x "
				    "flags: %02x devid_to: %02x:%02x.%x\n",
				    PCI_BUS(e->devid),
				    PCI_SLOT(e->devid),
				    PCI_FUNC(e->devid),
				    e->flags,
				    PCI_BUS(e->ext >> 8),
				    PCI_SLOT(e->ext >> 8),
				    PCI_FUNC(e->ext >> 8));

			devid = e->devid;
			devid_to = e->ext >> 8;
			set_dev_entry_from_acpi(iommu, devid   , e->flags, 0);
			set_dev_entry_from_acpi(iommu, devid_to, e->flags, 0);
			amd_iommu_alias_table[devid] = devid_to;
			break;
		case IVHD_DEV_ALIAS_RANGE:

			DUMP_printk("  DEV_ALIAS_RANGE\t\t "
				    "devid: %02x:%02x.%x flags: %02x "
				    "devid_to: %02x:%02x.%x\n",
				    PCI_BUS(e->devid),
				    PCI_SLOT(e->devid),
				    PCI_FUNC(e->devid),
				    e->flags,
				    PCI_BUS(e->ext >> 8),
				    PCI_SLOT(e->ext >> 8),
				    PCI_FUNC(e->ext >> 8));

			devid_start = e->devid;
			flags = e->flags;
			devid_to = e->ext >> 8;
			ext_flags = 0;
			alias = true;
			break;
		case IVHD_DEV_EXT_SELECT:

			DUMP_printk("  DEV_EXT_SELECT\t\t devid: %02x:%02x.%x "
				    "flags: %02x ext: %08x\n",
				    PCI_BUS(e->devid),
				    PCI_SLOT(e->devid),
				    PCI_FUNC(e->devid),
				    e->flags, e->ext);

			devid = e->devid;
			set_dev_entry_from_acpi(iommu, devid, e->flags,
						e->ext);
			break;
		case IVHD_DEV_EXT_SELECT_RANGE:

			DUMP_printk("  DEV_EXT_SELECT_RANGE\t devid: "
				    "%02x:%02x.%x flags: %02x ext: %08x\n",
				    PCI_BUS(e->devid),
				    PCI_SLOT(e->devid),
				    PCI_FUNC(e->devid),
				    e->flags, e->ext);

			devid_start = e->devid;
			flags = e->flags;
			ext_flags = e->ext;
			alias = false;
			break;
		case IVHD_DEV_RANGE_END:

			DUMP_printk("  DEV_RANGE_END\t\t devid: %02x:%02x.%x\n",
				    PCI_BUS(e->devid),
				    PCI_SLOT(e->devid),
				    PCI_FUNC(e->devid));

			devid = e->devid;
			for (dev_i = devid_start; dev_i <= devid; ++dev_i) {
				if (alias) {
					amd_iommu_alias_table[dev_i] = devid_to;
					set_dev_entry_from_acpi(iommu,
						devid_to, flags, ext_flags);
				}
				set_dev_entry_from_acpi(iommu, dev_i,
							flags, ext_flags);
			}
			break;
		default:
			break;
		}

		p += ivhd_entry_length(p);
	}
}

/* Initializes the device->iommu mapping for the driver */
static int __init init_iommu_devices(struct amd_iommu *iommu)
{
	u16 i;

	for (i = iommu->first_device; i <= iommu->last_device; ++i)
		set_iommu_for_device(iommu, i);

	return 0;
}

static void __init free_iommu_one(struct amd_iommu *iommu)
{
	free_command_buffer(iommu);
	free_event_buffer(iommu);
	iommu_unmap_mmio_space(iommu);
}

static void __init free_iommu_all(void)
{
	struct amd_iommu *iommu, *next;

	for_each_iommu_safe(iommu, next) {
		list_del(&iommu->list);
		free_iommu_one(iommu);
		kfree(iommu);
	}
}

/*
 * This function clues the initialization function for one IOMMU
 * together and also allocates the command buffer and programs the
 * hardware. It does NOT enable the IOMMU. This is done afterwards.
 */
static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
{
	spin_lock_init(&iommu->lock);

	/* Add IOMMU to internal data structures */
	list_add_tail(&iommu->list, &amd_iommu_list);
	iommu->index             = amd_iommus_present++;

	if (unlikely(iommu->index >= MAX_IOMMUS)) {
		WARN(1, "AMD-Vi: System has more IOMMUs than supported by this driver\n");
		return -ENOSYS;
	}

	/* Index is fine - add IOMMU to the array */
	amd_iommus[iommu->index] = iommu;

	/*
	 * Copy data from ACPI table entry to the iommu struct
	 */
	iommu->dev = pci_get_bus_and_slot(PCI_BUS(h->devid), h->devid & 0xff);
	if (!iommu->dev)
		return 1;

	iommu->cap_ptr = h->cap_ptr;
	iommu->pci_seg = h->pci_seg;
	iommu->mmio_phys = h->mmio_phys;
	iommu->mmio_base = iommu_map_mmio_space(h->mmio_phys);
	if (!iommu->mmio_base)
		return -ENOMEM;

	iommu->cmd_buf = alloc_command_buffer(iommu);
	if (!iommu->cmd_buf)
		return -ENOMEM;

	iommu->evt_buf = alloc_event_buffer(iommu);
	if (!iommu->evt_buf)
		return -ENOMEM;

	iommu->int_enabled = false;

	init_iommu_from_pci(iommu);
	init_iommu_from_acpi(iommu, h);
	init_iommu_devices(iommu);

	if (iommu->cap & (1UL << IOMMU_CAP_NPCACHE))
		amd_iommu_np_cache = true;

	return pci_enable_device(iommu->dev);
}

/*
 * Iterates over all IOMMU entries in the ACPI table, allocates the
 * IOMMU structure and initializes it with init_iommu_one()
 */
static int __init init_iommu_all(struct acpi_table_header *table)
{
	u8 *p = (u8 *)table, *end = (u8 *)table;
	struct ivhd_header *h;
	struct amd_iommu *iommu;
	int ret;

	end += table->length;
	p += IVRS_HEADER_LENGTH;

	while (p < end) {
		h = (struct ivhd_header *)p;
		switch (*p) {
		case ACPI_IVHD_TYPE:

			DUMP_printk("device: %02x:%02x.%01x cap: %04x "
				    "seg: %d flags: %01x info %04x\n",
				    PCI_BUS(h->devid), PCI_SLOT(h->devid),
				    PCI_FUNC(h->devid), h->cap_ptr,
				    h->pci_seg, h->flags, h->info);
			DUMP_printk("       mmio-addr: %016llx\n",
				    h->mmio_phys);

			iommu = kzalloc(sizeof(struct amd_iommu), GFP_KERNEL);
			if (iommu == NULL) {
				amd_iommu_init_err = -ENOMEM;
				return 0;
			}

			ret = init_iommu_one(iommu, h);
			if (ret) {
				amd_iommu_init_err = ret;
				return 0;
			}
			break;
		default:
			break;
		}
		p += h->length;

	}
	WARN_ON(p != end);

	return 0;
}

/****************************************************************************
 *
 * The following functions initialize the MSI interrupts for all IOMMUs
 * in the system. Its a bit challenging because there could be multiple
 * IOMMUs per PCI BDF but we can call pci_enable_msi(x) only once per
 * pci_dev.
 *
 ****************************************************************************/

static int iommu_setup_msi(struct amd_iommu *iommu)
{
	int r;

	if (pci_enable_msi(iommu->dev))
		return 1;

	r = request_irq(iommu->dev->irq, amd_iommu_int_handler,
			IRQF_SAMPLE_RANDOM,
			"AMD-Vi",
			NULL);

	if (r) {
		pci_disable_msi(iommu->dev);
		return 1;
	}

	iommu->int_enabled = true;
	iommu_feature_enable(iommu, CONTROL_EVT_INT_EN);

	return 0;
}

static int iommu_init_msi(struct amd_iommu *iommu)
{
	if (iommu->int_enabled)
		return 0;

	if (pci_find_capability(iommu->dev, PCI_CAP_ID_MSI))
		return iommu_setup_msi(iommu);

	return 1;
}

/****************************************************************************
 *
 * The next functions belong to the third pass of parsing the ACPI
 * table. In this last pass the memory mapping requirements are
 * gathered (like exclusion and unity mapping reanges).
 *
 ****************************************************************************/

static void __init free_unity_maps(void)
{
	struct unity_map_entry *entry, *next;

	list_for_each_entry_safe(entry, next, &amd_iommu_unity_map, list) {
		list_del(&entry->list);
		kfree(entry);
	}
}

/* called when we find an exclusion range definition in ACPI */
static int __init init_exclusion_range(struct ivmd_header *m)
{
	int i;

	switch (m->type) {
	case ACPI_IVMD_TYPE:
		set_device_exclusion_range(m->devid, m);
		break;
	case ACPI_IVMD_TYPE_ALL:
		for (i = 0; i <= amd_iommu_last_bdf; ++i)
			set_device_exclusion_range(i, m);
		break;
	case ACPI_IVMD_TYPE_RANGE:
		for (i = m->devid; i <= m->aux; ++i)
			set_device_exclusion_range(i, m);
		break;
	default:
		break;
	}

	return 0;
}

/* called for unity map ACPI definition */
static int __init init_unity_map_range(struct ivmd_header *m)
{
	struct unity_map_entry *e = 0;
	char *s;

	e = kzalloc(sizeof(*e), GFP_KERNEL);
	if (e == NULL)
		return -ENOMEM;

	switch (m->type) {
	default:
		kfree(e);
		return 0;
	case ACPI_IVMD_TYPE:
		s = "IVMD_TYPEi\t\t\t";
		e->devid_start = e->devid_end = m->devid;
		break;
	case ACPI_IVMD_TYPE_ALL:
		s = "IVMD_TYPE_ALL\t\t";
		e->devid_start = 0;
		e->devid_end = amd_iommu_last_bdf;
		break;
	case ACPI_IVMD_TYPE_RANGE:
		s = "IVMD_TYPE_RANGE\t\t";
		e->devid_start = m->devid;
		e->devid_end = m->aux;
		break;
	}
	e->address_start = PAGE_ALIGN(m->range_start);
	e->address_end = e->address_start + PAGE_ALIGN(m->range_length);
	e->prot = m->flags >> 1;

	DUMP_printk("%s devid_start: %02x:%02x.%x devid_end: %02x:%02x.%x"
		    " range_start: %016llx range_end: %016llx flags: %x\n", s,
		    PCI_BUS(e->devid_start), PCI_SLOT(e->devid_start),
		    PCI_FUNC(e->devid_start), PCI_BUS(e->devid_end),
		    PCI_SLOT(e->devid_end), PCI_FUNC(e->devid_end),
		    e->address_start, e->address_end, m->flags);

	list_add_tail(&e->list, &amd_iommu_unity_map);

	return 0;
}

/* iterates over all memory definitions we find in the ACPI table */
static int __init init_memory_definitions(struct acpi_table_header *table)
{
	u8 *p = (u8 *)table, *end = (u8 *)table;
	struct ivmd_header *m;

	end += table->length;
	p += IVRS_HEADER_LENGTH;

	while (p < end) {
		m = (struct ivmd_header *)p;
		if (m->flags & IVMD_FLAG_EXCL_RANGE)
			init_exclusion_range(m);
		else if (m->flags & IVMD_FLAG_UNITY_MAP)
			init_unity_map_range(m);

		p += m->length;
	}

	return 0;
}

/*
 * Init the device table to not allow DMA access for devices and
 * suppress all page faults
 */
static void init_device_table(void)
{
	u16 devid;

	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
		set_dev_entry_bit(devid, DEV_ENTRY_TRANSLATION);
	}
}

/*
 * This function finally enables all IOMMUs found in the system after
 * they have been initialized
 */
static void enable_iommus(void)
{
	struct amd_iommu *iommu;

	for_each_iommu(iommu) {
		iommu_disable(iommu);
		iommu_set_device_table(iommu);
		iommu_enable_command_buffer(iommu);
		iommu_enable_event_buffer(iommu);
		iommu_set_exclusion_range(iommu);
		iommu_init_msi(iommu);
		iommu_enable(iommu);
	}
}

static void disable_iommus(void)
{
	struct amd_iommu *iommu;

	for_each_iommu(iommu)
		iommu_disable(iommu);
}

/*
 * Suspend/Resume support
 * disable suspend until real resume implemented
 */

static int amd_iommu_resume(struct sys_device *dev)
{
	/* re-load the hardware */
	enable_iommus();

	/*
	 * we have to flush after the IOMMUs are enabled because a
	 * disabled IOMMU will never execute the commands we send
	 */
	amd_iommu_flush_all_devices();
	amd_iommu_flush_all_domains();

	return 0;
}

static int amd_iommu_suspend(struct sys_device *dev, pm_message_t state)
{
	/* disable IOMMUs to go out of the way for BIOS */
	disable_iommus();

	return 0;
}

static struct sysdev_class amd_iommu_sysdev_class = {
	.name = "amd_iommu",
	.suspend = amd_iommu_suspend,
	.resume = amd_iommu_resume,
};

static struct sys_device device_amd_iommu = {
	.id = 0,
	.cls = &amd_iommu_sysdev_class,
};

/*
 * This is the core init function for AMD IOMMU hardware in the system.
 * This function is called from the generic x86 DMA layer initialization
 * code.
 *
 * This function basically parses the ACPI table for AMD IOMMU (IVRS)
 * three times:
 *
 *	1 pass) Find the highest PCI device id the driver has to handle.
 *		Upon this information the size of the data structures is
 *		determined that needs to be allocated.
 *
 *	2 pass) Initialize the data structures just allocated with the
 *		information in the ACPI table about available AMD IOMMUs
 *		in the system. It also maps the PCI devices in the
 *		system to specific IOMMUs
 *
 *	3 pass) After the basic data structures are allocated and
 *		initialized we update them with information about memory
 *		remapping requirements parsed out of the ACPI table in
 *		this last pass.
 *
 * After that the hardware is initialized and ready to go. In the last
 * step we do some Linux specific things like registering the driver in
 * the dma_ops interface and initializing the suspend/resume support
 * functions. Finally it prints some information about AMD IOMMUs and
 * the driver state and enables the hardware.
 */
static int __init amd_iommu_init(void)
{
	int i, ret = 0;

	/*
	 * First parse ACPI tables to find the largest Bus/Dev/Func
	 * we need to handle. Upon this information the shared data
	 * structures for the IOMMUs in the system will be allocated
	 */
	if (acpi_table_parse("IVRS", find_last_devid_acpi) != 0)
		return -ENODEV;

	ret = amd_iommu_init_err;
	if (ret)
		goto out;

	dev_table_size     = tbl_size(DEV_TABLE_ENTRY_SIZE);
	alias_table_size   = tbl_size(ALIAS_TABLE_ENTRY_SIZE);
	rlookup_table_size = tbl_size(RLOOKUP_TABLE_ENTRY_SIZE);

	ret = -ENOMEM;

	/* Device table - directly used by all IOMMUs */
	amd_iommu_dev_table = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
				      get_order(dev_table_size));
	if (amd_iommu_dev_table == NULL)
		goto out;

	/*
	 * Alias table - map PCI Bus/Dev/Func to Bus/Dev/Func the
	 * IOMMU see for that device
	 */
	amd_iommu_alias_table = (void *)__get_free_pages(GFP_KERNEL,
			get_order(alias_table_size));
	if (amd_iommu_alias_table == NULL)
		goto free;

	/* IOMMU rlookup table - find the IOMMU for a specific device */
	amd_iommu_rlookup_table = (void *)__get_free_pages(
			GFP_KERNEL | __GFP_ZERO,
			get_order(rlookup_table_size));
	if (amd_iommu_rlookup_table == NULL)
		goto free;

	amd_iommu_pd_alloc_bitmap = (void *)__get_free_pages(
					    GFP_KERNEL | __GFP_ZERO,
					    get_order(MAX_DOMAIN_ID/8));
	if (amd_iommu_pd_alloc_bitmap == NULL)
		goto free;

	/* init the device table */
	init_device_table();

	/*
	 * let all alias entries point to itself
	 */
	for (i = 0; i <= amd_iommu_last_bdf; ++i)
		amd_iommu_alias_table[i] = i;

	/*
	 * never allocate domain 0 because its used as the non-allocated and
	 * error value placeholder
	 */
	amd_iommu_pd_alloc_bitmap[0] = 1;

	spin_lock_init(&amd_iommu_pd_lock);

	/*
	 * now the data structures are allocated and basically initialized
	 * start the real acpi table scan
	 */
	ret = -ENODEV;
	if (acpi_table_parse("IVRS", init_iommu_all) != 0)
		goto free;

	if (amd_iommu_init_err) {
		ret = amd_iommu_init_err;
		goto free;
	}

	if (acpi_table_parse("IVRS", init_memory_definitions) != 0)
		goto free;

	if (amd_iommu_init_err) {
		ret = amd_iommu_init_err;
		goto free;
	}

	ret = sysdev_class_register(&amd_iommu_sysdev_class);
	if (ret)
		goto free;

	ret = sysdev_register(&device_amd_iommu);
	if (ret)
		goto free;

	ret = amd_iommu_init_devices();
	if (ret)
		goto free;

	enable_iommus();

	if (iommu_pass_through)
		ret = amd_iommu_init_passthrough();
	else
		ret = amd_iommu_init_dma_ops();

	if (ret)
		goto free_disable;

	amd_iommu_init_api();

	amd_iommu_init_notifier();

	if (iommu_pass_through)
		goto out;

	if (amd_iommu_unmap_flush)
		printk(KERN_INFO "AMD-Vi: IO/TLB flush on unmap enabled\n");
	else
		printk(KERN_INFO "AMD-Vi: Lazy IO/TLB flushing enabled\n");

	x86_platform.iommu_shutdown = disable_iommus;
out:
	return ret;

free_disable:
	disable_iommus();

free:
	amd_iommu_uninit_devices();

	free_pages((unsigned long)amd_iommu_pd_alloc_bitmap,
		   get_order(MAX_DOMAIN_ID/8));

	free_pages((unsigned long)amd_iommu_rlookup_table,
		   get_order(rlookup_table_size));

	free_pages((unsigned long)amd_iommu_alias_table,
		   get_order(alias_table_size));

	free_pages((unsigned long)amd_iommu_dev_table,
		   get_order(dev_table_size));

	free_iommu_all();

	free_unity_maps();

#ifdef CONFIG_GART_IOMMU
	/*
	 * We failed to initialize the AMD IOMMU - try fallback to GART
	 * if possible.
	 */
	gart_iommu_init();

#endif

	goto out;
}

/****************************************************************************
 *
 * Early detect code. This code runs at IOMMU detection time in the DMA
 * layer. It just looks if there is an IVRS ACPI table to detect AMD
 * IOMMUs
 *
 ****************************************************************************/
static int __init early_amd_iommu_detect(struct acpi_table_header *table)
{
	return 0;
}

void __init amd_iommu_detect(void)
{
	if (no_iommu || (iommu_detected && !gart_iommu_aperture))
		return;

	if (amd_iommu_disabled)
		return;

	if (acpi_table_parse("IVRS", early_amd_iommu_detect) == 0) {
		iommu_detected = 1;
		amd_iommu_detected = 1;
		x86_init.iommu.iommu_init = amd_iommu_init;

		/* Make sure ACS will be enabled */
		pci_request_acs();
	}
}

/****************************************************************************
 *
 * Parsing functions for the AMD IOMMU specific kernel command line
 * options.
 *
 ****************************************************************************/

static int __init parse_amd_iommu_dump(char *str)
{
	amd_iommu_dump = true;

	return 1;
}

static int __init parse_amd_iommu_options(char *str)
{
	for (; *str; ++str) {
		if (strncmp(str, "fullflush", 9) == 0)
			amd_iommu_unmap_flush = true;
		if (strncmp(str, "off", 3) == 0)
			amd_iommu_disabled = true;
	}

	return 1;
}

__setup("amd_iommu_dump", parse_amd_iommu_dump);
__setup("amd_iommu=", parse_amd_iommu_options);