forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dmar.c
1398 lines (1167 loc) · 33.3 KB
/
dmar.c
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
/*
* 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 <[email protected]>
* Author: Shaohua Li <[email protected]>
* Author: Anil S Keshavamurthy <[email protected]>
*
* 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) KBUILD_MODNAME ": " fmt /* has to precede printk.h */
#include <linux/pci.h>
#include <linux/dmar.h>
#include <linux/iova.h>
#include <linux/intel-iommu.h>
#include <linux/timer.h>
#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/tboot.h>
#include <linux/dmi.h>
#include <linux/slab.h>
#include <asm/irq_remapping.h>
#include <asm/iommu_table.h>
#include "irq_remapping.h"
/* No locks are needed as DMA remapping hardware unit
* list is constructed at boot time and hotplug of
* these units are not supported by the architecture.
*/
LIST_HEAD(dmar_drhd_units);
struct acpi_table_header * __initdata dmar_tbl;
static acpi_size dmar_tbl_size;
static int alloc_iommu(struct dmar_drhd_unit *drhd);
static void free_iommu(struct intel_iommu *iommu);
static void __init dmar_register_drhd_unit(struct dmar_drhd_unit *drhd)
{
/*
* add INCLUDE_ALL at the tail, so scan the list will find it at
* the very end.
*/
if (drhd->include_all)
list_add_tail(&drhd->list, &dmar_drhd_units);
else
list_add(&drhd->list, &dmar_drhd_units);
}
static int __init dmar_parse_one_dev_scope(struct acpi_dmar_device_scope *scope,
struct pci_dev **dev, u16 segment)
{
struct pci_bus *bus;
struct pci_dev *pdev = NULL;
struct acpi_dmar_pci_path *path;
int count;
bus = pci_find_bus(segment, scope->bus);
path = (struct acpi_dmar_pci_path *)(scope + 1);
count = (scope->length - sizeof(struct acpi_dmar_device_scope))
/ sizeof(struct acpi_dmar_pci_path);
while (count) {
if (pdev)
pci_dev_put(pdev);
/*
* Some BIOSes list non-exist devices in DMAR table, just
* ignore it
*/
if (!bus) {
pr_warn("Device scope bus [%d] not found\n", scope->bus);
break;
}
pdev = pci_get_slot(bus, PCI_DEVFN(path->device, path->function));
if (!pdev) {
/* warning will be printed below */
break;
}
path ++;
count --;
bus = pdev->subordinate;
}
if (!pdev) {
pr_warn("Device scope device [%04x:%02x:%02x.%02x] not found\n",
segment, scope->bus, path->device, path->function);
return 0;
}
if ((scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT && \
pdev->subordinate) || (scope->entry_type == \
ACPI_DMAR_SCOPE_TYPE_BRIDGE && !pdev->subordinate)) {
pci_dev_put(pdev);
pr_warn("Device scope type does not match for %s\n",
pci_name(pdev));
return -EINVAL;
}
*dev = pdev;
return 0;
}
int __init dmar_parse_dev_scope(void *start, void *end, int *cnt,
struct pci_dev ***devices, u16 segment)
{
struct acpi_dmar_device_scope *scope;
void * tmp = start;
int index;
int ret;
*cnt = 0;
while (start < end) {
scope = start;
if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE)
(*cnt)++;
else if (scope->entry_type != ACPI_DMAR_SCOPE_TYPE_IOAPIC &&
scope->entry_type != ACPI_DMAR_SCOPE_TYPE_HPET) {
pr_warn("Unsupported device scope\n");
}
start += scope->length;
}
if (*cnt == 0)
return 0;
*devices = kcalloc(*cnt, sizeof(struct pci_dev *), GFP_KERNEL);
if (!*devices)
return -ENOMEM;
start = tmp;
index = 0;
while (start < end) {
scope = start;
if (scope->entry_type == ACPI_DMAR_SCOPE_TYPE_ENDPOINT ||
scope->entry_type == ACPI_DMAR_SCOPE_TYPE_BRIDGE) {
ret = dmar_parse_one_dev_scope(scope,
&(*devices)[index], segment);
if (ret) {
dmar_free_dev_scope(devices, cnt);
return ret;
}
index ++;
}
start += scope->length;
}
return 0;
}
void dmar_free_dev_scope(struct pci_dev ***devices, int *cnt)
{
if (*devices && *cnt) {
while (--*cnt >= 0)
pci_dev_put((*devices)[*cnt]);
kfree(*devices);
*devices = NULL;
*cnt = 0;
}
}
/**
* dmar_parse_one_drhd - parses exactly one DMA remapping hardware definition
* structure which uniquely represent one DMA remapping hardware unit
* present in the platform
*/
static int __init
dmar_parse_one_drhd(struct acpi_dmar_header *header)
{
struct acpi_dmar_hardware_unit *drhd;
struct dmar_drhd_unit *dmaru;
int ret = 0;
drhd = (struct acpi_dmar_hardware_unit *)header;
dmaru = kzalloc(sizeof(*dmaru), GFP_KERNEL);
if (!dmaru)
return -ENOMEM;
dmaru->hdr = header;
dmaru->reg_base_addr = drhd->address;
dmaru->segment = drhd->segment;
dmaru->include_all = drhd->flags & 0x1; /* BIT0: INCLUDE_ALL */
ret = alloc_iommu(dmaru);
if (ret) {
kfree(dmaru);
return ret;
}
dmar_register_drhd_unit(dmaru);
return 0;
}
static 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_dev(struct dmar_drhd_unit *dmaru)
{
struct acpi_dmar_hardware_unit *drhd;
drhd = (struct acpi_dmar_hardware_unit *) dmaru->hdr;
if (dmaru->include_all)
return 0;
return dmar_parse_dev_scope((void *)(drhd + 1),
((void *)drhd) + drhd->header.length,
&dmaru->devices_cnt, &dmaru->devices,
drhd->segment);
}
#ifdef CONFIG_ACPI_NUMA
static int __init
dmar_parse_one_rhsa(struct acpi_dmar_header *header)
{
struct acpi_dmar_rhsa *rhsa;
struct dmar_drhd_unit *drhd;
rhsa = (struct acpi_dmar_rhsa *)header;
for_each_drhd_unit(drhd) {
if (drhd->reg_base_addr == rhsa->base_address) {
int node = acpi_map_pxm_to_node(rhsa->proximity_domain);
if (!node_online(node))
node = -1;
drhd->iommu->node = node;
return 0;
}
}
WARN_TAINT(
1, TAINT_FIRMWARE_WORKAROUND,
"Your BIOS is broken; RHSA refers to non-existent DMAR unit at %llx\n"
"BIOS vendor: %s; Ver: %s; Product Version: %s\n",
drhd->reg_base_addr,
dmi_get_system_info(DMI_BIOS_VENDOR),
dmi_get_system_info(DMI_BIOS_VERSION),
dmi_get_system_info(DMI_PRODUCT_VERSION));
return 0;
}
#endif
static void __init
dmar_table_print_dmar_entry(struct acpi_dmar_header *header)
{
struct acpi_dmar_hardware_unit *drhd;
struct acpi_dmar_reserved_memory *rmrr;
struct acpi_dmar_atsr *atsr;
struct acpi_dmar_rhsa *rhsa;
switch (header->type) {
case ACPI_DMAR_TYPE_HARDWARE_UNIT:
drhd = container_of(header, struct acpi_dmar_hardware_unit,
header);
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_ATSR:
atsr = container_of(header, struct acpi_dmar_atsr, header);
pr_info("ATSR flags: %#x\n", atsr->flags);
break;
case ACPI_DMAR_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;
}
}
/**
* 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);
}
/**
* parse_dmar_table - parses the DMA reporting table
*/
static int __init
parse_dmar_table(void)
{
struct acpi_table_dmar *dmar;
struct acpi_dmar_header *entry_header;
int ret = 0;
int drhd_count = 0;
/*
* Do it again, earlier dmar_tbl mapping could be mapped with
* fixed map.
*/
dmar_table_detect();
/*
* ACPI tables may not be DMA protected by tboot, so use DMAR copy
* SINIT saved in SinitMleData in TXT heap (which is DMA protected)
*/
dmar_tbl = tboot_get_dmar_table(dmar_tbl);
dmar = (struct acpi_table_dmar *)dmar_tbl;
if (!dmar)
return -ENODEV;
if (dmar->width < PAGE_SHIFT - 1) {
pr_warn("Invalid DMAR haw\n");
return -EINVAL;
}
pr_info("Host address width %d\n", dmar->width + 1);
entry_header = (struct acpi_dmar_header *)(dmar + 1);
while (((unsigned long)entry_header) <
(((unsigned long)dmar) + dmar_tbl->length)) {
/* Avoid looping forever on bad ACPI tables */
if (entry_header->length == 0) {
pr_warn("Invalid 0-length structure\n");
ret = -EINVAL;
break;
}
dmar_table_print_dmar_entry(entry_header);
switch (entry_header->type) {
case ACPI_DMAR_TYPE_HARDWARE_UNIT:
drhd_count++;
ret = dmar_parse_one_drhd(entry_header);
break;
case ACPI_DMAR_TYPE_RESERVED_MEMORY:
ret = dmar_parse_one_rmrr(entry_header);
break;
case ACPI_DMAR_TYPE_ATSR:
ret = dmar_parse_one_atsr(entry_header);
break;
case ACPI_DMAR_HARDWARE_AFFINITY:
#ifdef CONFIG_ACPI_NUMA
ret = dmar_parse_one_rhsa(entry_header);
#endif
break;
default:
pr_warn("Unknown DMAR structure type %d\n",
entry_header->type);
ret = 0; /* for forward compatibility */
break;
}
if (ret)
break;
entry_header = ((void *)entry_header + entry_header->length);
}
if (drhd_count == 0)
pr_warn(FW_BUG "No DRHD structure found in DMAR table\n");
return ret;
}
static int dmar_pci_device_match(struct pci_dev *devices[], int cnt,
struct pci_dev *dev)
{
int index;
while (dev) {
for (index = 0; index < cnt; index++)
if (dev == devices[index])
return 1;
/* Check our parent */
dev = dev->bus->self;
}
return 0;
}
struct dmar_drhd_unit *
dmar_find_matched_drhd_unit(struct pci_dev *dev)
{
struct dmar_drhd_unit *dmaru = NULL;
struct acpi_dmar_hardware_unit *drhd;
dev = pci_physfn(dev);
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))
return dmaru;
if (dmar_pci_device_match(dmaru->devices,
dmaru->devices_cnt, dev))
return dmaru;
}
return NULL;
}
int __init dmar_dev_scope_init(void)
{
static int dmar_dev_scope_initialized;
struct dmar_drhd_unit *drhd;
int ret = -ENODEV;
if (dmar_dev_scope_initialized)
return dmar_dev_scope_initialized;
if (list_empty(&dmar_drhd_units))
goto fail;
list_for_each_entry(drhd, &dmar_drhd_units, list) {
ret = dmar_parse_dev(drhd);
if (ret)
goto fail;
}
ret = dmar_parse_rmrr_atsr_dev();
if (ret)
goto fail;
dmar_dev_scope_initialized = 1;
return 0;
fail:
dmar_dev_scope_initialized = ret;
return ret;
}
int __init dmar_table_init(void)
{
static int dmar_table_initialized;
int ret;
if (dmar_table_initialized == 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 __init check_zero_address(void)
{
struct acpi_table_dmar *dmar;
struct acpi_dmar_header *entry_header;
struct acpi_dmar_hardware_unit *drhd;
dmar = (struct acpi_table_dmar *)dmar_tbl;
entry_header = (struct acpi_dmar_header *)(dmar + 1);
while (((unsigned long)entry_header) <
(((unsigned long)dmar) + dmar_tbl->length)) {
/* Avoid looping forever on bad ACPI tables */
if (entry_header->length == 0) {
pr_warn("Invalid 0-length structure\n");
return 0;
}
if (entry_header->type == ACPI_DMAR_TYPE_HARDWARE_UNIT) {
void __iomem *addr;
u64 cap, ecap;
drhd = (void *)entry_header;
if (!drhd->address) {
warn_invalid_dmar(0, "");
goto failed;
}
addr = early_ioremap(drhd->address, VTD_PAGE_SIZE);
if (!addr ) {
printk("IOMMU: can't validate: %llx\n", drhd->address);
goto failed;
}
cap = dmar_readq(addr + DMAR_CAP_REG);
ecap = dmar_readq(addr + DMAR_ECAP_REG);
early_iounmap(addr, VTD_PAGE_SIZE);
if (cap == (uint64_t)-1 && ecap == (uint64_t)-1) {
warn_invalid_dmar(drhd->address,
" returns all ones");
goto failed;
}
}
entry_header = ((void *)entry_header + entry_header->length);
}
return 1;
failed:
return 0;
}
int __init detect_intel_iommu(void)
{
int ret;
ret = dmar_table_detect();
if (ret)
ret = check_zero_address();
{
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;
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("IOMMU: can't reserve memory\n");
err = -EBUSY;
goto out;
}
iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
if (!iommu->reg) {
pr_err("IOMMU: 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("IOMMU: can't reserve memory\n");
err = -EBUSY;
goto out;
}
iommu->reg = ioremap(iommu->reg_phys, iommu->reg_size);
if (!iommu->reg) {
pr_err("IOMMU: 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 alloc_iommu(struct dmar_drhd_unit *drhd)
{
struct intel_iommu *iommu;
u32 ver, sts;
static int iommu_allocated = 0;
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;
iommu->seq_id = iommu_allocated++;
sprintf (iommu->name, "dmar%d", iommu->seq_id);
err = map_iommu(iommu, drhd->reg_base_addr);
if (err) {
pr_err("IOMMU: failed to map %s\n", iommu->name);
goto error;
}
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->node = -1;
ver = readl(iommu->reg + DMAR_VER_REG);
pr_info("IOMMU %d: reg_base_addr %llx ver %d:%d cap %llx ecap %llx\n",
iommu->seq_id,
(unsigned long long)drhd->reg_base_addr,
DMAR_VER_MAJOR(ver), DMAR_VER_MINOR(ver),
(unsigned long long)iommu->cap,
(unsigned long long)iommu->ecap);
/* 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;
return 0;
err_unmap:
unmap_iommu(iommu);
error:
kfree(iommu);
return err;
}
static void free_iommu(struct intel_iommu *iommu)
{
if (iommu->irq) {
free_irq(iommu->irq, iommu);
irq_set_handler_data(iommu->irq, NULL);
destroy_irq(iommu->irq);
}
if (iommu->qi) {
free_page((unsigned long)iommu->qi->desc);
kfree(iommu->qi->desc_status);
kfree(iommu->qi);
}
if (iommu->reg)
unmap_iommu(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();