aboutsummaryrefslogtreecommitdiff
path: root/drivers/iommu/dmar.c
blob: c9db04d4ef39ae36553279859b6ca0f1c7972db1 (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
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
/*
 * 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
 */

#define pr_fmt(fmt)     "DMAR: " fmt

#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 <linux/iommu.h>
#include <asm/irq_remapping.h>
#include <asm/iommu_table.h>

#include "irq_remapping.h"

typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
struct dmar_res_callback {
	dmar_res_handler_t	cb[ACPI_DMAR_TYPE_RESERVED];
	void			*arg[ACPI_DMAR_TYPE_RESERVED];
	bool			ignore_unhandled;
	bool			print_entry;
};

/*
 * Assumptions:
 * 1) The hotplug framework guarentees that DMAR unit will be hot-added
 *    before IO devices managed by that unit.
 * 2) The hotplug framework guarantees that DMAR unit will be hot-removed
 *    after IO devices managed by that unit.
 * 3) Hotplug events are rare.
 *
 * Locking rules for DMA and interrupt remapping related global data structures:
 * 1) Use dmar_global_lock in process context
 * 2) Use RCU in interrupt context
 */
DECLARE_RWSEM(dmar_global_lock);
LIST_HEAD(dmar_drhd_units);

struct acpi_table_header * __initdata dmar_tbl;
static acpi_size dmar_tbl_size;
static int dmar_dev_scope_status = 1;
static unsigned long dmar_seq_ids[BITS_TO_LONGS(DMAR_UNITS_SUPPORTED)];

static int alloc_iommu(struct dmar_drhd_unit *drhd);
static void free_iommu(struct intel_iommu *iommu);

static void 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_rcu(&drhd->list, &dmar_drhd_units);
	else
		list_add_rcu(&drhd->list, &dmar_drhd_units);
}

void *dmar_alloc_dev_scope(void *start, void *end, int *cnt)
{
	struct acpi_dmar_device_scope *scope;

	*cnt = 0;
	while (start < end) {
		scope = start;
		if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_NAMESPACE ||
		    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 &&
			scope->entry_type != ACPI_DMAR_SCOPE_TYPE_HPET) {
			pr_warn("Unsupported device scope\n");
		}
		start += scope->length;
	}
	if (*cnt == 0)
		return NULL;

	return kcalloc(*cnt, sizeof(struct dmar_dev_scope), GFP_KERNEL);
}

void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt)
{
	int i;
	struct device *tmp_dev;

	if (*devices && *cnt) {
		for_each_active_dev_scope(*devices, *cnt, i, tmp_dev)
			put_device(tmp_dev);
		kfree(*devices);
	}

	*devices = NULL;
	*cnt = 0;
}

/* Optimize out kzalloc()/kfree() for normal cases */
static char dmar_pci_notify_info_buf[64];

static struct dmar_pci_notify_info *
dmar_alloc_pci_notify_info(struct pci_dev *dev, unsigned long event)
{
	int level = 0;
	size_t size;
	struct pci_dev *tmp;
	struct dmar_pci_notify_info *info;

	BUG_ON(dev->is_virtfn);

	/* Only generate path[] for device addition event */
	if (event == BUS_NOTIFY_ADD_DEVICE)
		for (tmp = dev; tmp; tmp = tmp->bus->self)
			level++;

	size = sizeof(*info) + level * sizeof(struct acpi_dmar_pci_path);
	if (size <= sizeof(dmar_pci_notify_info_buf)) {
		info = (struct dmar_pci_notify_info *)dmar_pci_notify_info_buf;
	} else {
		info = kzalloc(size, GFP_KERNEL);
		if (!info) {
			pr_warn("Out of memory when allocating notify_info "
				"for %s.\n", pci_name(dev));
			if (dmar_dev_scope_status == 0)
				dmar_dev_scope_status = -ENOMEM;
			return NULL;
		}
	}

	info->event = event;
	info->dev = dev;
	info->seg = pci_domain_nr(dev->bus);
	info->level = level;
	if (event == BUS_NOTIFY_ADD_DEVICE) {
		for (tmp = dev; tmp; tmp = tmp->bus->self) {
			level--;
			info->path[level].bus = tmp->bus->number;
			info->path[level].device = PCI_SLOT(tmp->devfn);
			info->path[level].function = PCI_FUNC(tmp->devfn);
			if (pci_is_root_bus(tmp->bus))
				info->bus = tmp->bus->number;
		}
	}

	return info;
}

static inline void dmar_free_pci_notify_info(struct dmar_pci_notify_info *info)
{
	if ((void *)info != dmar_pci_notify_info_buf)
		kfree(info);
}

static bool dmar_match_pci_path(struct dmar_pci_notify_info *info, int bus,
				struct acpi_dmar_pci_path *path, int count)
{
	int i;

	if (info->bus != bus)
		goto fallback;
	if (info->level != count)
		goto fallback;

	for (i = 0; i < count; i++) {
		if (path[i].device != info->path[i].device ||
		    path[i].function != info->path[i].function)
			goto fallback;
	}

	return true;

fallback:

	if (count != 1)
		return false;

	i = info->level - 1;
	if (bus              == info->path[i].bus &&
	    path[0].device   == info->path[i].device &&
	    path[0].function == info->path[i].function) {
		pr_info(FW_BUG "RMRR entry for device %02x:%02x.%x is broken - applying workaround\n",
			bus, path[0].device, path[0].function);
		return true;
	}

	return false;
}

/* Return: > 0 if match found, 0 if no match found, < 0 if error happens */
int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
			  void *start, void*end, u16 segment,
			  struct dmar_dev_scope *devices,
			  int devices_cnt)
{
	int i, level;
	struct device *tmp, *dev = &info->dev->dev;
	struct acpi_dmar_device_scope *scope;
	struct acpi_dmar_pci_path *path;

	if (segment != info->seg)
		return 0;

	for (; start < end; start += scope->length) {
		scope = start;
		if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_ENDPOINT &&
		    scope->entry_type != ACPI_DMAR_SCOPE_TYPE_BRIDGE)
			continue;

		path = (struct acpi_dmar_pci_path *)(scope + 1);
		level = (scope->length - sizeof(*scope)) / sizeof(*path);
		if (!dmar_match_pci_path(info, scope->bus, path, level))
			continue;

		if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT) ^
		    (info->dev->hdr_type == PCI_HEADER_TYPE_NORMAL)) {
			pr_warn("Device scope type does not match for %s\n",
				pci_name(info->dev));
			return -EINVAL;
		}

		for_each_dev_scope(devices, devices_cnt, i, tmp)
			if (tmp == NULL) {
				devices[i].bus = info->dev->bus->number;
				devices[i].devfn = info->dev->devfn;
				rcu_assign_pointer(devices[i].dev,
						   get_device(dev));
				return 1;
			}
		BUG_ON(i >= devices_cnt);
	}

	return 0;
}

int dmar_remove_dev_scope(struct dmar_pci_notify_info *info, u16 segment,
			  struct dmar_dev_scope *devices, int count)
{
	int index;
	struct device *tmp;

	if (info->seg != segment)
		return 0;

	for_each_active_dev_scope(devices, count, index, tmp)
		if (tmp == &info->dev->dev) {
			RCU_INIT_POINTER(devices[index].dev, NULL);
			synchronize_rcu();
			put_device(tmp);
			return 1;
		}

	return 0;
}

static int dmar_pci_bus_add_dev(struct dmar_pci_notify_info *info)
{
	int ret = 0;
	struct dmar_drhd_unit *dmaru;
	struct acpi_dmar_hardware_unit *drhd;

	for_each_drhd_unit(dmaru) {
		if (dmaru->include_all)
			continue;

		drhd = container_of(dmaru->hdr,
				    struct acpi_dmar_hardware_unit, header);
		ret = dmar_insert_dev_scope(info, (void *)(drhd + 1),
				((void *)drhd) + drhd->header.length,
				dmaru->segment,
				dmaru->devices, dmaru->devices_cnt);
		if (ret != 0)
			break;
	}
	if (ret >= 0)
		ret = dmar_iommu_notify_scope_dev(info);
	if (ret < 0 && dmar_dev_scope_status == 0)
		dmar_dev_scope_status = ret;

	return ret;
}

static void  dmar_pci_bus_del_dev(struct dmar_pci_notify_info *info)
{
	struct dmar_drhd_unit *dmaru;

	for_each_drhd_unit(dmaru)
		if (dmar_remove_dev_scope(info, dmaru->segment,
			dmaru->devices, dmaru->devices_cnt))
			break;
	dmar_iommu_notify_scope_dev(info);
}

static int dmar_pci_bus_notifier(struct notifier_block *nb,
				 unsigned long action, void *data)
{
	struct pci_dev *pdev = to_pci_dev(data);
	struct dmar_pci_notify_info *info;

	/* Only care about add/remove events for physical functions */
	if (pdev->is_virtfn)
		return NOTIFY_DONE;
	if (action != BUS_NOTIFY_ADD_DEVICE && action != BUS_NOTIFY_DEL_DEVICE)
		return NOTIFY_DONE;

	info = dmar_alloc_pci_notify_info(pdev, action);
	if (!info)
		return NOTIFY_DONE;

	down_write(&dmar_global_lock);
	if (action == BUS_NOTIFY_ADD_DEVICE)
		dmar_pci_bus_add_dev(info);
	else if (action == BUS_NOTIFY_DEL_DEVICE)
		dmar_pci_bus_del_dev(info);
	up_write(&dmar_global_lock);

	dmar_free_pci_notify_info(info);

	return NOTIFY_OK;
}

static struct notifier_block dmar_pci_bus_nb = {
	.notifier_call = dmar_pci_bus_notifier,
	.priority = INT_MIN,
};

static struct dmar_drhd_unit *
dmar_find_dmaru(struct acpi_dmar_hardware_unit *drhd)
{
	struct dmar_drhd_unit *dmaru;

	list_for_each_entry_rcu(dmaru, &dmar_drhd_units, list)
		if (dmaru->segment == drhd->segment &&
		    dmaru->reg_base_addr == drhd->address)
			return dmaru;

	return NULL;
}

/**
 * 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 dmar_parse_one_drhd(struct acpi_dmar_header *header, void *arg)
{
	struct acpi_dmar_hardware_unit *drhd;
	struct dmar_drhd_unit *dmaru;
	int ret = 0;

	drhd = (struct acpi_dmar_hardware_unit *)header;
	dmaru = dmar_find_dmaru(drhd);
	if (dmaru)
		goto out;

	dmaru = kzalloc(sizeof(*dmaru) + header->length, GFP_KERNEL);
	if (!dmaru)
		return -ENOMEM;

	/*
	 * If header is allocated from slab by ACPI _DSM method, we need to
	 * copy the content because the memory buffer will be freed on return.
	 */
	dmaru->hdr = (void *)(dmaru + 1);
	memcpy(dmaru->hdr, header, header->length);
	dmaru->reg_base_addr = drhd->address;
	dmaru->segment = drhd->segment;
	dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
	dmaru->devices = dmar_alloc_dev_scope((void *)(drhd + 1),
					      ((void *)drhd) + drhd->header.length,
					      &dmaru->devices_cnt);
	if (dmaru->devices_cnt && dmaru->devices == NULL) {
		kfree(dmaru);
		return -ENOMEM;
	}

	ret = alloc_iommu(dmaru);
	if (ret) {
		dmar_free_dev_scope(&dmaru->devices,
				    &dmaru->devices_cnt);
		kfree(dmaru);
		return ret;
	}
	dmar_register_drhd_unit(dmaru);

out:
	if (arg)
		(*(int *)arg)++;

	return 0;
}

static void dmar_free_drhd(struct dmar_drhd_unit *dmaru)
{
	if (dmaru->devices && dmaru->devices_cnt)
		dmar_free_dev_scope(&dmaru->devices, &dmaru->devices_cnt);
	if (dmaru->iommu)
		free_iommu(dmaru->iommu);
	kfree(dmaru);
}

static int __init dmar_parse_one_andd(struct acpi_dmar_header *header,
				      void *arg)
{
	struct acpi_dmar_andd *andd = (void *)header;

	/* Check for NUL termination within the designated length */
	if (strnlen(andd->device_name, header->length - 8) == header->length - 8) {
		WARN_TAINT(1, TAINT_FIRMWARE_WORKAROUND,
			   "Your BIOS is broken; ANDD object name is not NUL-terminated\n"
			   "BIOS vendor: %s; Ver: %s; Product Version: %s\n",
			   dmi_get_system_info(DMI_BIOS_VENDOR),
			   dmi_get_system_info(DMI_BIOS_VERSION),
			   dmi_get_system_info(DMI_PRODUCT_VERSION));
		return -EINVAL;
	}
	pr_info("ANDD device: %x name: %s\n", andd->device_number,
		andd->device_name);

	return 0;
}

#ifdef CONFIG_ACPI_NUMA
static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg)
{
	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;
}
#else
#define	dmar_parse_one_rhsa		dmar_res_noop
#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);
		pr_info("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);
		pr_info("RMRR base: %#016Lx end: %#016Lx\n",
			(unsigned long long)rmrr->base_address,
			(unsigned long long)rmrr->end_address);
		break;
	case ACPI_DMAR_TYPE_ROOT_ATS:
		atsr = container_of(header, struct acpi_dmar_atsr, header);
		pr_info("ATSR flags: %#x\n", atsr->flags);
		break;
	case ACPI_DMAR_TYPE_HARDWARE_AFFINITY:
		rhsa = container_of(header, struct acpi_dmar_rhsa, header);
		pr_info("RHSA base: %#016Lx proximity domain: %#x\n",
		       (unsigned long long)rhsa->base_address,
		       rhsa->proximity_domain);
		break;
	case ACPI_DMAR_TYPE_NAMESPACE:
		/* We don't print this here because we need to sanity-check
		   it first. So print it in dmar_parse_one_andd() instead. */
		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) {
		pr_warn("Unable to map DMAR\n");
		status = AE_NOT_FOUND;
	}

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

static int dmar_walk_remapping_entries(struct acpi_dmar_header *start,
				       size_t len, struct dmar_res_callback *cb)
{
	int ret = 0;
	struct acpi_dmar_header *iter, *next;
	struct acpi_dmar_header *end = ((void *)start) + len;

	for (iter = start; iter < end && ret == 0; iter = next) {
		next = (void *)iter + iter->length;
		if (iter->length == 0) {
			/* Avoid looping forever on bad ACPI tables */
			pr_debug(FW_BUG "Invalid 0-length structure\n");
			break;
		} else if (next > end) {
			/* Avoid passing table end */
			pr_warn(FW_BUG "Record passes table end\n");
			ret = -EINVAL;
			break;
		}

		if (cb->print_entry)
			dmar_table_print_dmar_entry(iter);

		if (iter->type >= ACPI_DMAR_TYPE_RESERVED) {
			/* continue for forward compatibility */
			pr_debug("Unknown DMAR structure type %d\n",
				 iter->type);
		} else if (cb->cb[iter->type]) {
			ret = cb->cb[iter->type](iter, cb->arg[iter->type]);
		} else if (!cb->ignore_unhandled) {
			pr_warn("No handler for DMAR structure type %d\n",
				iter->type);
			ret = -EINVAL;
		}
	}

	return ret;
}

static inline int dmar_walk_dmar_table(struct acpi_table_dmar *dmar,
				       struct dmar_res_callback *cb)
{
	return dmar_walk_remapping_entries((void *)(dmar + 1),
			dmar->header.length - sizeof(*dmar), cb);
}

/**
 * parse_dmar_table - parses the DMA reporting table
 */
static int __init
parse_dmar_table(void)
{
	struct acpi_table_dmar *dmar;
	int ret = 0;
	int drhd_count = 0;
	struct dmar_res_callback cb = {
		.print_entry = true,
		.ignore_unhandled = true,
		.arg[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &drhd_count,
		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_parse_one_drhd,
		.cb[ACPI_DMAR_TYPE_RESERVED_MEMORY] = &dmar_parse_one_rmrr,
		.cb[ACPI_DMAR_TYPE_ROOT_ATS] = &dmar_parse_one_atsr,
		.cb[ACPI_DMAR_TYPE_HARDWARE_AFFINITY] = &dmar_parse_one_rhsa,
		.cb[ACPI_DMAR_TYPE_NAMESPACE] = &dmar_parse_one_andd,
	};

	/*
	 * 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) {
		pr_warn("Invalid DMAR haw\n");
		return -EINVAL;
	}

	pr_info("Host address width %d\n", dmar->width + 1);
	ret = dmar_walk_dmar_table(dmar, &cb);
	if (ret == 0 && drhd_count == 0)
		pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");

	return ret;
}

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

	while (dev) {
		for_each_active_dev_scope(devices, cnt, index, tmp)
			if (dev_is_pci(tmp) && dev == to_pci_dev(tmp))
				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;
	struct acpi_dmar_hardware_unit *drhd;

	dev = pci_physfn(dev);

	rcu_read_lock();
	for_each_drhd_unit(dmaru) {
		drhd = container_of(dmaru->hdr,
				    struct acpi_dmar_hardware_unit,
				    header);

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

		if (dmar_pci_device_match(dmaru->devices,
					  dmaru->devices_cnt, dev))
			goto out;
	}
	dmaru = NULL;
out:
	rcu_read_unlock();

	return dmaru;
}

static void __init dmar_acpi_insert_dev_scope(u8 device_number,
					      struct acpi_device *adev)
{
	struct dmar_drhd_unit *dmaru;
	struct acpi_dmar_hardware_unit *drhd;
	struct acpi_dmar_device_scope *scope;
	struct device *tmp;
	int i;
	struct acpi_dmar_pci_path *path;

	for_each_drhd_unit(dmaru) {
		drhd = container_of(dmaru->hdr,
				    struct acpi_dmar_hardware_unit,
				    header);

		for (scope = (void *)(drhd + 1);
		     (unsigned long)scope < ((unsigned long)drhd) + drhd->header.length;
		     scope = ((void *)scope) + scope->length) {
			if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_NAMESPACE)
				continue;
			if (scope->enumeration_id != device_number)
				continue;

			path = (void *)(scope + 1);
			pr_info("ACPI device \"%s\" under DMAR at %llx as %02x:%02x.%d\n",
				dev_name(&adev->dev), dmaru->reg_base_addr,
				scope->bus, path->device, path->function);
			for_each_dev_scope(dmaru->devices, dmaru->devices_cnt, i, tmp)
				if (tmp == NULL) {
					dmaru->devices[i].bus = scope->bus;
					dmaru->devices[i].devfn = PCI_DEVFN(path->device,
									    path->function);
					rcu_assign_pointer(dmaru->devices[i].dev,
							   get_device(&adev->dev));
					return;
				}
			BUG_ON(i >= dmaru->devices_cnt);
		}
	}
	pr_warn("No IOMMU scope found for ANDD enumeration ID %d (%s)\n",
		device_number, dev_name(&adev->dev));
}

static int __init dmar_acpi_dev_scope_init(void)
{
	struct acpi_dmar_andd *andd;

	if (dmar_tbl == NULL)
		return -ENODEV;

	for (andd = (void *)dmar_tbl + sizeof(struct acpi_table_dmar);
	     ((unsigned long)andd) < ((unsigned long)dmar_tbl) + dmar_tbl->length;
	     andd = ((void *)andd) + andd->header.length) {
		if (andd->header.type == ACPI_DMAR_TYPE_NAMESPACE) {
			acpi_handle h;
			struct acpi_device *adev;

			if (!ACPI_SUCCESS(acpi_get_handle(ACPI_ROOT_OBJECT,
							  andd->device_name,
							  &h))) {
				pr_err("Failed to find handle for ACPI object %s\n",
				       andd->device_name);
				continue;
			}
			if (acpi_bus_get_device(h, &adev)) {
				pr_err("Failed to get device for ACPI object %s\n",
				       andd->device_name);
				continue;
			}
			dmar_acpi_insert_dev_scope(andd->device_number, adev);
		}
	}
	return 0;
}

int __init dmar_dev_scope_init(void)
{
	struct pci_dev *dev = NULL;
	struct dmar_pci_notify_info *info;

	if (dmar_dev_scope_status != 1)
		return dmar_dev_scope_status;

	if (list_empty(&dmar_drhd_units)) {
		dmar_dev_scope_status = -ENODEV;
	} else {
		dmar_dev_scope_status = 0;

		dmar_acpi_dev_scope_init();

		for_each_pci_dev(dev) {
			if (dev->is_virtfn)
				continue;

			info = dmar_alloc_pci_notify_info(dev,
					BUS_NOTIFY_ADD_DEVICE);
			if (!info) {
				return dmar_dev_scope_status;
			} else {
				dmar_pci_bus_add_dev(info);
				dmar_free_pci_notify_info(info);
			}
		}

		bus_register_notifier(&pci_bus_type, &dmar_pci_bus_nb);
	}

	return dmar_dev_scope_status;
}


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

	if (dmar_table_initialized == 0) {
		ret = parse_dmar_table();
		if (ret < 0) {
			if (ret != -ENODEV)
				pr_info("Parse DMAR table failure.\n");
		} else  if (list_empty(&dmar_drhd_units)) {
			pr_info("No DMAR devices found\n");
			ret = -ENODEV;
		}

		if (ret < 0)
			dmar_table_initialized = ret;
		else
			dmar_table_initialized = 1;
	}

	return dmar_table_initialized < 0 ? dmar_table_initialized : 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));
}

static int __ref
dmar_validate_one_drhd(struct acpi_dmar_header *entry, void *arg)
{
	struct acpi_dmar_hardware_unit *drhd;
	void __iomem *addr;
	u64 cap, ecap;

	drhd = (void *)entry;
	if (!drhd->address) {
		warn_invalid_dmar(0, "");
		return -EINVAL;
	}

	if (arg)
		addr = ioremap(drhd->address, VTD_PAGE_SIZE);
	else
		addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
	if (!addr) {
		pr_warn("Can't validate DRHD address: %llx\n", drhd->address);
		return -EINVAL;
	}

	cap = dmar_readq(addr + DMAR_CAP_REG);
	ecap = dmar_readq(addr + DMAR_ECAP_REG);

	if (arg)
		iounmap(addr);
	else
		early_iounmap(addr, VTD_PAGE_SIZE);

	if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
		warn_invalid_dmar(drhd->address, " returns all ones");
		return -EINVAL;
	}

	return 0;
}

int __init detect_intel_iommu(void)
{
	int ret;
	struct dmar_res_callback validate_drhd_cb = {
		.cb[ACPI_DMAR_TYPE_HARDWARE_UNIT] = &dmar_validate_one_drhd,
		.ignore_unhandled = true,
	};

	down_write(&dmar_global_lock);
	ret = dmar_table_detect();
	if (ret)
		ret = !dmar_walk_dmar_table((struct acpi_table_dmar *)dmar_tbl,
					    &validate_drhd_cb);
	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((void __iomem *)dmar_tbl, dmar_tbl_size);
	dmar_tbl = NULL;
	up_write(&dmar_global_lock);

	return ret ? 1 : -ENODEV;
}


static void unmap_iommu(struct intel_iommu *iommu)
{
	iounmap(iommu->reg);
	release_mem_region(iommu->reg_phys, iommu->reg_size);
}

/**
 * map_iommu: map the iommu's registers
 * @iommu: the iommu to map
 * @phys_addr: the physical address of the base resgister
 *
 * Memory map the iommu's registers.  Start w/ a single page, and
 * possibly expand if that turns out to be insufficent.
 */
static int map_iommu(struct intel_iommu *iommu, u64 phys_addr)
{
	int map_size, err=0;

	iommu->reg_phys = phys_addr;
	iommu->reg_size = VTD_PAGE_SIZE;

	if (!request_mem_region(iommu->reg_phys, iommu->reg_size, iommu->name)) {
		pr_err("Can't reserve memory\n");
		err = -EBUSY;
		goto out;
	}

	iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
	if (!iommu->reg) {
		pr_err("Can't map the region\n");
		err = -ENOMEM;
		goto release;
	}

	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) {
		err = -EINVAL;
		warn_invalid_dmar(phys_addr, " returns all ones");
		goto unmap;
	}

	/* 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 > iommu->reg_size) {
		iounmap(iommu->reg);
		release_mem_region(iommu->reg_phys, iommu->reg_size);
		iommu->reg_size = map_size;
		if (!request_mem_region(iommu->reg_phys, iommu->reg_size,
					iommu->name)) {
			pr_err("Can't reserve memory\n");
			err = -EBUSY;
			goto out;
		}
		iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
		if (!iommu->reg) {
			pr_err("Can't map the region\n");
			err = -ENOMEM;
			goto release;
		}
	}
	err = 0;
	goto out;

unmap:
	iounmap(iommu->reg);
release:
	release_mem_region(iommu->reg_phys, iommu->reg_size);
out:
	return err;
}

static int dmar_alloc_seq_id(struct intel_iommu *iommu)
{
	iommu->seq_id = find_first_zero_bit(dmar_seq_ids,
					    DMAR_UNITS_SUPPORTED);
	if (iommu->seq_id >= DMAR_UNITS_SUPPORTED) {
		iommu->seq_id = -1;
	} else {
		set_bit(iommu->seq_id, dmar_seq_ids);
		sprintf(iommu->name, "dmar%d", iommu->seq_id);
	}

	return iommu->seq_id;
}

static void dmar_free_seq_id(struct intel_iommu *iommu)
{
	if (iommu->seq_id >= 0) {
		clear_bit(iommu->seq_id, dmar_seq_ids);
		iommu->seq_id = -1;
	}
}

static int alloc_iommu(struct dmar_drhd_unit *drhd)
{
	struct intel_iommu *iommu;
	u32 ver, sts;
	int agaw = 0;
	int msagaw = 0;
	int err;

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

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

	if (dmar_alloc_seq_id(iommu) < 0) {
		pr_err("Failed to allocate seq_id\n");
		err = -ENOSPC;
		goto error;
	}

	err = map_iommu(iommu, drhd->reg_base_addr);
	if (err) {
		pr_err("Failed to map %s\n", iommu->name);
		goto error_free_seq_id;
	}

	err = -EINVAL;
	agaw = iommu_calculate_agaw(iommu);
	if (agaw < 0) {
		pr_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) {
		pr_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->segment = drhd->segment;

	iommu->node = -1;

	ver = readl(iommu->reg + DMAR_VER_REG);
	pr_info("%s: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
		iommu->name,
		(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);

	/* Reflect status in gcmd */
	sts = readl(iommu->reg + DMAR_GSTS_REG);
	if (sts & DMA_GSTS_IRES)
		iommu->gcmd |= DMA_GCMD_IRE;
	if (sts & DMA_GSTS_TES)
		iommu->gcmd |= DMA_GCMD_TE;
	if (sts & DMA_GSTS_QIES)
		iommu->gcmd |= DMA_GCMD_QIE;

	raw_spin_lock_init(&iommu->register_lock);

	drhd->iommu = iommu;

	if (intel_iommu_enabled)
		iommu->iommu_dev = iommu_device_create(NULL, iommu,
						       intel_iommu_groups,
						       iommu->name);

	return 0;

err_unmap:
	unmap_iommu(iommu);
error_free_seq_id:
	dmar_free_seq_id(iommu);
error:
	kfree(iommu);
	return err;
}

static void free_iommu(struct intel_iommu *iommu)
{
	iommu_device_destroy(iommu->iommu_dev);

	if (iommu->irq) {
		free_irq(iommu->irq, iommu);
		dmar_free_hwirq(iommu->irq);
		iommu->irq = 0;
	}

	if (iommu->qi) {
		free_page((unsigned long)iommu->qi->desc);
		kfree(iommu->qi->desc_status);
		kfree(iommu->qi);
	}

	if (iommu->reg)
		unmap_iommu(iommu);

	dmar_free_seq_id(iommu);
	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) {
			pr_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 = NULL;
		return -ENOMEM;
	}

	qi->desc = page_address(desc_page);

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

	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",
	"PCE for translation request specifies blocking",
};

static const char *irq_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",
};

static const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
{
	if (fault_reason >= 0x20 && (fault_reason - 0x20 <
					ARRAY_SIZE(irq_remap_fault_reasons))) {
		*fault_type = INTR_REMAP;
		return irq_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)
		pr_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
		pr_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)
		pr_err("DRHD: handling fault status reg %x\n", fault_status);

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

	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);
	}

	writel(DMA_FSTS_PFO | DMA_FSTS_PPF, iommu->reg + DMAR_FSTS_REG);

unlock_exit:
	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 = dmar_alloc_hwirq(iommu->seq_id, iommu->node, iommu);
	if (irq > 0) {
		iommu->irq = irq;
	} else {
		pr_err("No free IRQ vectors\n");
		return -EINVAL;
	}

	ret = request_irq(irq, dmar_fault, IRQF_NO_THREAD, iommu->name, iommu);
	if (ret)
		pr_err("Can't request irq\n");
	return ret;
}

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

	/*
	 * Enable fault control interrupt.
	 */
	for_each_iommu(iommu, drhd) {
		u32 fault_status;
		int ret = dmar_set_interrupt(iommu);

		if (ret) {
			pr_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);
		fault_status = readl(iommu->reg + DMAR_FSTS_REG);
		writel(fault_status, iommu->reg + DMAR_FSTS_REG);
	}

	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;
}

/* Check whether DMAR units are in use */
static inline bool dmar_in_use(void)
{
	return irq_remapping_enabled || intel_iommu_enabled;
}

static int __init dmar_free_unused_resources(void)
{
	struct dmar_drhd_unit *dmaru, *dmaru_n;

	if (dmar_in_use())
		return 0;

	if (dmar_dev_scope_status != 1 && !list_empty(&dmar_drhd_units))
		bus_unregister_notifier(&pci_bus_type, &dmar_pci_bus_nb);

	down_write(&dmar_global_lock);
	list_for_each_entry_safe(dmaru, dmaru_n, &dmar_drhd_units, list) {
		list_del(&dmaru->list);
		dmar_free_drhd(dmaru);
	}
	up_write(&dmar_global_lock);

	return 0;
}

late_initcall(dmar_free_unused_resources);
IOMMU_INIT_POST(detect_intel_iommu);

/*
 * DMAR Hotplug Support
 * For more details, please refer to Intel(R) Virtualization Technology
 * for Directed-IO Architecture Specifiction, Rev 2.2, Section 8.8
 * "Remapping Hardware Unit Hot Plug".
 */
static u8 dmar_hp_uuid[] = {
	/* 0000 */    0xA6, 0xA3, 0xC1, 0xD8, 0x9B, 0xBE, 0x9B, 0x4C,
	/* 0008 */    0x91, 0xBF, 0xC3, 0xCB, 0x81, 0xFC, 0x5D, 0xAF
};

/*
 * Currently there's only one revision and BIOS will not check the revision id,
 * so use 0 for safety.
 */
#define	DMAR_DSM_REV_ID			0
#define	DMAR_DSM_FUNC_DRHD		1
#define	DMAR_DSM_FUNC_ATSR		2
#define	DMAR_DSM_FUNC_RHSA		3

static inline bool dmar_detect_dsm(acpi_handle handle, int func)
{
	return acpi_check_dsm(handle, dmar_hp_uuid, DMAR_DSM_REV_ID, 1 << func);
}

static int dmar_walk_dsm_resource(acpi_handle handle, int func,
				  dmar_res_handler_t handler, void *arg)
{
	int ret = -ENODEV;
	union acpi_object *obj;
	struct acpi_dmar_header *start;
	struct dmar_res_callback callback;
	static int res_type[] = {
		[DMAR_DSM_FUNC_DRHD] = ACPI_DMAR_TYPE_HARDWARE_UNIT,
		[DMAR_DSM_FUNC_ATSR] = ACPI_DMAR_TYPE_ROOT_ATS,
		[DMAR_DSM_FUNC_RHSA] = ACPI_DMAR_TYPE_HARDWARE_AFFINITY,
	};

	if (!dmar_detect_dsm(handle, func))
		return 0;

	obj = acpi_evaluate_dsm_typed(handle, dmar_hp_uuid, DMAR_DSM_REV_ID,
				      func, NULL, ACPI_TYPE_BUFFER);
	if (!obj)
		return -ENODEV;

	memset(&callback, 0, sizeof(callback));
	callback.cb[res_type[func]] = handler;
	callback.arg[res_type[func]] = arg;
	start = (struct acpi_dmar_header *)obj->buffer.pointer;
	ret = dmar_walk_remapping_entries(start, obj->buffer.length, &callback);

	ACPI_FREE(obj);

	return ret;
}

static int dmar_hp_add_drhd(struct acpi_dmar_header *header, void *arg)
{
	int ret;
	struct dmar_drhd_unit *dmaru;

	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
	if (!dmaru)
		return -ENODEV;

	ret = dmar_ir_hotplug(dmaru, true);
	if (ret == 0)
		ret = dmar_iommu_hotplug(dmaru, true);

	return ret;
}

static int dmar_hp_remove_drhd(struct acpi_dmar_header *header, void *arg)
{
	int i, ret;
	struct device *dev;
	struct dmar_drhd_unit *dmaru;

	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
	if (!dmaru)
		return 0;

	/*
	 * All PCI devices managed by this unit should have been destroyed.
	 */
	if (!dmaru->include_all && dmaru->devices && dmaru->devices_cnt)
		for_each_active_dev_scope(dmaru->devices,
					  dmaru->devices_cnt, i, dev)
			return -EBUSY;

	ret = dmar_ir_hotplug(dmaru, false);
	if (ret == 0)
		ret = dmar_iommu_hotplug(dmaru, false);

	return ret;
}

static int dmar_hp_release_drhd(struct acpi_dmar_header *header, void *arg)
{
	struct dmar_drhd_unit *dmaru;

	dmaru = dmar_find_dmaru((struct acpi_dmar_hardware_unit *)header);
	if (dmaru) {
		list_del_rcu(&dmaru->list);
		synchronize_rcu();
		dmar_free_drhd(dmaru);
	}

	return 0;
}

static int dmar_hotplug_insert(acpi_handle handle)
{
	int ret;
	int drhd_count = 0;

	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
				     &dmar_validate_one_drhd, (void *)1);
	if (ret)
		goto out;

	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
				     &dmar_parse_one_drhd, (void *)&drhd_count);
	if (ret == 0 && drhd_count == 0) {
		pr_warn(FW_BUG "No DRHD structures in buffer returned by _DSM method\n");
		goto out;
	} else if (ret) {
		goto release_drhd;
	}

	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_RHSA,
				     &dmar_parse_one_rhsa, NULL);
	if (ret)
		goto release_drhd;

	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
				     &dmar_parse_one_atsr, NULL);
	if (ret)
		goto release_atsr;

	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
				     &dmar_hp_add_drhd, NULL);
	if (!ret)
		return 0;

	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
			       &dmar_hp_remove_drhd, NULL);
release_atsr:
	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
			       &dmar_release_one_atsr, NULL);
release_drhd:
	dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
			       &dmar_hp_release_drhd, NULL);
out:
	return ret;
}

static int dmar_hotplug_remove(acpi_handle handle)
{
	int ret;

	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
				     &dmar_check_one_atsr, NULL);
	if (ret)
		return ret;

	ret = dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
				     &dmar_hp_remove_drhd, NULL);
	if (ret == 0) {
		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_ATSR,
					       &dmar_release_one_atsr, NULL));
		WARN_ON(dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
					       &dmar_hp_release_drhd, NULL));
	} else {
		dmar_walk_dsm_resource(handle, DMAR_DSM_FUNC_DRHD,
				       &dmar_hp_add_drhd, NULL);
	}

	return ret;
}

static acpi_status dmar_get_dsm_handle(acpi_handle handle, u32 lvl,
				       void *context, void **retval)
{
	acpi_handle *phdl = retval;

	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
		*phdl = handle;
		return AE_CTRL_TERMINATE;
	}

	return AE_OK;
}

static int dmar_device_hotplug(acpi_handle handle, bool insert)
{
	int ret;
	acpi_handle tmp = NULL;
	acpi_status status;

	if (!dmar_in_use())
		return 0;

	if (dmar_detect_dsm(handle, DMAR_DSM_FUNC_DRHD)) {
		tmp = handle;
	} else {
		status = acpi_walk_namespace(ACPI_TYPE_DEVICE, handle,
					     ACPI_UINT32_MAX,
					     dmar_get_dsm_handle,
					     NULL, NULL, &tmp);
		if (ACPI_FAILURE(status)) {
			pr_warn("Failed to locate _DSM method.\n");
			return -ENXIO;
		}
	}
	if (tmp == NULL)
		return 0;

	down_write(&dmar_global_lock);
	if (insert)
		ret = dmar_hotplug_insert(tmp);
	else
		ret = dmar_hotplug_remove(tmp);
	up_write(&dmar_global_lock);

	return ret;
}

int dmar_device_add(acpi_handle handle)
{
	return dmar_device_hotplug(handle, true);
}

int dmar_device_remove(acpi_handle handle)
{
	return dmar_device_hotplug(handle, false);
}