forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathamd_iommu.c
4537 lines (3603 loc) · 105 KB
/
amd_iommu.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) 2007-2010 Advanced Micro Devices, Inc.
* Author: Joerg Roedel <[email protected]>
* Leo Duran <[email protected]>
*
* 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
*/
#define pr_fmt(fmt) "AMD-Vi: " fmt
#include <linux/ratelimit.h>
#include <linux/pci.h>
#include <linux/acpi.h>
#include <linux/amba/bus.h>
#include <linux/platform_device.h>
#include <linux/pci-ats.h>
#include <linux/bitmap.h>
#include <linux/slab.h>
#include <linux/debugfs.h>
#include <linux/scatterlist.h>
#include <linux/dma-mapping.h>
#include <linux/dma-direct.h>
#include <linux/iommu-helper.h>
#include <linux/iommu.h>
#include <linux/delay.h>
#include <linux/amd-iommu.h>
#include <linux/notifier.h>
#include <linux/export.h>
#include <linux/irq.h>
#include <linux/msi.h>
#include <linux/dma-contiguous.h>
#include <linux/irqdomain.h>
#include <linux/percpu.h>
#include <linux/iova.h>
#include <asm/irq_remapping.h>
#include <asm/io_apic.h>
#include <asm/apic.h>
#include <asm/hw_irq.h>
#include <asm/msidef.h>
#include <asm/proto.h>
#include <asm/iommu.h>
#include <asm/gart.h>
#include <asm/dma.h>
#include "amd_iommu_proto.h"
#include "amd_iommu_types.h"
#include "irq_remapping.h"
#define CMD_SET_TYPE(cmd, t) ((cmd)->data[1] |= ((t) << 28))
#define LOOP_TIMEOUT 100000
/* IO virtual address start page frame number */
#define IOVA_START_PFN (1)
#define IOVA_PFN(addr) ((addr) >> PAGE_SHIFT)
/* Reserved IOVA ranges */
#define MSI_RANGE_START (0xfee00000)
#define MSI_RANGE_END (0xfeefffff)
#define HT_RANGE_START (0xfd00000000ULL)
#define HT_RANGE_END (0xffffffffffULL)
/*
* This bitmap is used to advertise the page sizes our hardware support
* to the IOMMU core, which will then use this information to split
* physically contiguous memory regions it is mapping into page sizes
* that we support.
*
* 512GB Pages are not supported due to a hardware bug
*/
#define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38))
static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
static DEFINE_SPINLOCK(pd_bitmap_lock);
/* List of all available dev_data structures */
static LLIST_HEAD(dev_data_list);
LIST_HEAD(ioapic_map);
LIST_HEAD(hpet_map);
LIST_HEAD(acpihid_map);
/*
* Domain for untranslated devices - only allocated
* if iommu=pt passed on kernel cmd line.
*/
const struct iommu_ops amd_iommu_ops;
static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
int amd_iommu_max_glx_val = -1;
static const struct dma_map_ops amd_iommu_dma_ops;
/*
* general struct to manage commands send to an IOMMU
*/
struct iommu_cmd {
u32 data[4];
};
struct kmem_cache *amd_iommu_irq_cache;
static void update_domain(struct protection_domain *domain);
static int protection_domain_init(struct protection_domain *domain);
static void detach_device(struct device *dev);
static void iova_domain_flush_tlb(struct iova_domain *iovad);
/*
* Data container for a dma_ops specific protection domain
*/
struct dma_ops_domain {
/* generic protection domain information */
struct protection_domain domain;
/* IOVA RB-Tree */
struct iova_domain iovad;
};
static struct iova_domain reserved_iova_ranges;
static struct lock_class_key reserved_rbtree_key;
/****************************************************************************
*
* Helper functions
*
****************************************************************************/
static inline int match_hid_uid(struct device *dev,
struct acpihid_map_entry *entry)
{
const char *hid, *uid;
hid = acpi_device_hid(ACPI_COMPANION(dev));
uid = acpi_device_uid(ACPI_COMPANION(dev));
if (!hid || !(*hid))
return -ENODEV;
if (!uid || !(*uid))
return strcmp(hid, entry->hid);
if (!(*entry->uid))
return strcmp(hid, entry->hid);
return (strcmp(hid, entry->hid) || strcmp(uid, entry->uid));
}
static inline u16 get_pci_device_id(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
return PCI_DEVID(pdev->bus->number, pdev->devfn);
}
static inline int get_acpihid_device_id(struct device *dev,
struct acpihid_map_entry **entry)
{
struct acpihid_map_entry *p;
list_for_each_entry(p, &acpihid_map, list) {
if (!match_hid_uid(dev, p)) {
if (entry)
*entry = p;
return p->devid;
}
}
return -EINVAL;
}
static inline int get_device_id(struct device *dev)
{
int devid;
if (dev_is_pci(dev))
devid = get_pci_device_id(dev);
else
devid = get_acpihid_device_id(dev, NULL);
return devid;
}
static struct protection_domain *to_pdomain(struct iommu_domain *dom)
{
return container_of(dom, struct protection_domain, domain);
}
static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain)
{
BUG_ON(domain->flags != PD_DMA_OPS_MASK);
return container_of(domain, struct dma_ops_domain, domain);
}
static struct iommu_dev_data *alloc_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
if (!dev_data)
return NULL;
dev_data->devid = devid;
ratelimit_default_init(&dev_data->rs);
llist_add(&dev_data->dev_data_list, &dev_data_list);
return dev_data;
}
static struct iommu_dev_data *search_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
struct llist_node *node;
if (llist_empty(&dev_data_list))
return NULL;
node = dev_data_list.first;
llist_for_each_entry(dev_data, node, dev_data_list) {
if (dev_data->devid == devid)
return dev_data;
}
return NULL;
}
static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
{
*(u16 *)data = alias;
return 0;
}
static u16 get_alias(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
u16 devid, ivrs_alias, pci_alias;
/* The callers make sure that get_device_id() does not fail here */
devid = get_device_id(dev);
/* For ACPI HID devices, we simply return the devid as such */
if (!dev_is_pci(dev))
return devid;
ivrs_alias = amd_iommu_alias_table[devid];
pci_for_each_dma_alias(pdev, __last_alias, &pci_alias);
if (ivrs_alias == pci_alias)
return ivrs_alias;
/*
* DMA alias showdown
*
* The IVRS is fairly reliable in telling us about aliases, but it
* can't know about every screwy device. If we don't have an IVRS
* reported alias, use the PCI reported alias. In that case we may
* still need to initialize the rlookup and dev_table entries if the
* alias is to a non-existent device.
*/
if (ivrs_alias == devid) {
if (!amd_iommu_rlookup_table[pci_alias]) {
amd_iommu_rlookup_table[pci_alias] =
amd_iommu_rlookup_table[devid];
memcpy(amd_iommu_dev_table[pci_alias].data,
amd_iommu_dev_table[devid].data,
sizeof(amd_iommu_dev_table[pci_alias].data));
}
return pci_alias;
}
pr_info("Using IVRS reported alias %02x:%02x.%d "
"for device %s[%04x:%04x], kernel reported alias "
"%02x:%02x.%d\n", PCI_BUS_NUM(ivrs_alias), PCI_SLOT(ivrs_alias),
PCI_FUNC(ivrs_alias), dev_name(dev), pdev->vendor, pdev->device,
PCI_BUS_NUM(pci_alias), PCI_SLOT(pci_alias),
PCI_FUNC(pci_alias));
/*
* If we don't have a PCI DMA alias and the IVRS alias is on the same
* bus, then the IVRS table may know about a quirk that we don't.
*/
if (pci_alias == devid &&
PCI_BUS_NUM(ivrs_alias) == pdev->bus->number) {
pci_add_dma_alias(pdev, ivrs_alias & 0xff);
pr_info("Added PCI DMA alias %02x.%d for %s\n",
PCI_SLOT(ivrs_alias), PCI_FUNC(ivrs_alias),
dev_name(dev));
}
return ivrs_alias;
}
static struct iommu_dev_data *find_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
dev_data = search_dev_data(devid);
if (dev_data == NULL) {
dev_data = alloc_dev_data(devid);
if (!dev_data)
return NULL;
if (translation_pre_enabled(iommu))
dev_data->defer_attach = true;
}
return dev_data;
}
struct iommu_dev_data *get_dev_data(struct device *dev)
{
return dev->archdata.iommu;
}
EXPORT_SYMBOL(get_dev_data);
/*
* Find or create an IOMMU group for a acpihid device.
*/
static struct iommu_group *acpihid_device_group(struct device *dev)
{
struct acpihid_map_entry *p, *entry = NULL;
int devid;
devid = get_acpihid_device_id(dev, &entry);
if (devid < 0)
return ERR_PTR(devid);
list_for_each_entry(p, &acpihid_map, list) {
if ((devid == p->devid) && p->group)
entry->group = p->group;
}
if (!entry->group)
entry->group = generic_device_group(dev);
else
iommu_group_ref_get(entry->group);
return entry->group;
}
static bool pci_iommuv2_capable(struct pci_dev *pdev)
{
static const int caps[] = {
PCI_EXT_CAP_ID_ATS,
PCI_EXT_CAP_ID_PRI,
PCI_EXT_CAP_ID_PASID,
};
int i, pos;
if (pci_ats_disabled())
return false;
for (i = 0; i < 3; ++i) {
pos = pci_find_ext_capability(pdev, caps[i]);
if (pos == 0)
return false;
}
return true;
}
static bool pdev_pri_erratum(struct pci_dev *pdev, u32 erratum)
{
struct iommu_dev_data *dev_data;
dev_data = get_dev_data(&pdev->dev);
return dev_data->errata & (1 << erratum) ? true : false;
}
/*
* This function checks if the driver got a valid device from the caller to
* avoid dereferencing invalid pointers.
*/
static bool check_device(struct device *dev)
{
int devid;
if (!dev || !dev->dma_mask)
return false;
devid = get_device_id(dev);
if (devid < 0)
return false;
/* Out of our scope? */
if (devid > amd_iommu_last_bdf)
return false;
if (amd_iommu_rlookup_table[devid] == NULL)
return false;
return true;
}
static void init_iommu_group(struct device *dev)
{
struct iommu_group *group;
group = iommu_group_get_for_dev(dev);
if (IS_ERR(group))
return;
iommu_group_put(group);
}
static int iommu_init_device(struct device *dev)
{
struct iommu_dev_data *dev_data;
struct amd_iommu *iommu;
int devid;
if (dev->archdata.iommu)
return 0;
devid = get_device_id(dev);
if (devid < 0)
return devid;
iommu = amd_iommu_rlookup_table[devid];
dev_data = find_dev_data(devid);
if (!dev_data)
return -ENOMEM;
dev_data->alias = get_alias(dev);
/*
* By default we use passthrough mode for IOMMUv2 capable device.
* But if amd_iommu=force_isolation is set (e.g. to debug DMA to
* invalid address), we ignore the capability for the device so
* it'll be forced to go into translation mode.
*/
if ((iommu_pass_through || !amd_iommu_force_isolation) &&
dev_is_pci(dev) && pci_iommuv2_capable(to_pci_dev(dev))) {
struct amd_iommu *iommu;
iommu = amd_iommu_rlookup_table[dev_data->devid];
dev_data->iommu_v2 = iommu->is_iommu_v2;
}
dev->archdata.iommu = dev_data;
iommu_device_link(&iommu->iommu, dev);
return 0;
}
static void iommu_ignore_device(struct device *dev)
{
u16 alias;
int devid;
devid = get_device_id(dev);
if (devid < 0)
return;
alias = get_alias(dev);
memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
amd_iommu_rlookup_table[devid] = NULL;
amd_iommu_rlookup_table[alias] = NULL;
}
static void iommu_uninit_device(struct device *dev)
{
struct iommu_dev_data *dev_data;
struct amd_iommu *iommu;
int devid;
devid = get_device_id(dev);
if (devid < 0)
return;
iommu = amd_iommu_rlookup_table[devid];
dev_data = search_dev_data(devid);
if (!dev_data)
return;
if (dev_data->domain)
detach_device(dev);
iommu_device_unlink(&iommu->iommu, dev);
iommu_group_remove_device(dev);
/* Remove dma-ops */
dev->dma_ops = NULL;
/*
* We keep dev_data around for unplugged devices and reuse it when the
* device is re-plugged - not doing so would introduce a ton of races.
*/
}
/****************************************************************************
*
* Interrupt handling functions
*
****************************************************************************/
static void dump_dte_entry(u16 devid)
{
int i;
for (i = 0; i < 4; ++i)
pr_err("DTE[%d]: %016llx\n", i,
amd_iommu_dev_table[devid].data[i]);
}
static void dump_command(unsigned long phys_addr)
{
struct iommu_cmd *cmd = iommu_phys_to_virt(phys_addr);
int i;
for (i = 0; i < 4; ++i)
pr_err("CMD[%d]: %08x\n", i, cmd->data[i]);
}
static void amd_iommu_report_page_fault(u16 devid, u16 domain_id,
u64 address, int flags)
{
struct iommu_dev_data *dev_data = NULL;
struct pci_dev *pdev;
pdev = pci_get_domain_bus_and_slot(0, PCI_BUS_NUM(devid),
devid & 0xff);
if (pdev)
dev_data = get_dev_data(&pdev->dev);
if (dev_data && __ratelimit(&dev_data->rs)) {
dev_err(&pdev->dev, "Event logged [IO_PAGE_FAULT domain=0x%04x address=0x%llx flags=0x%04x]\n",
domain_id, address, flags);
} else if (printk_ratelimit()) {
pr_err("Event logged [IO_PAGE_FAULT device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
domain_id, address, flags);
}
if (pdev)
pci_dev_put(pdev);
}
static void iommu_print_event(struct amd_iommu *iommu, void *__evt)
{
struct device *dev = iommu->iommu.dev;
int type, devid, pasid, flags, tag;
volatile u32 *event = __evt;
int count = 0;
u64 address;
retry:
type = (event[1] >> EVENT_TYPE_SHIFT) & EVENT_TYPE_MASK;
devid = (event[0] >> EVENT_DEVID_SHIFT) & EVENT_DEVID_MASK;
pasid = PPR_PASID(*(u64 *)&event[0]);
flags = (event[1] >> EVENT_FLAGS_SHIFT) & EVENT_FLAGS_MASK;
address = (u64)(((u64)event[3]) << 32) | event[2];
if (type == 0) {
/* Did we hit the erratum? */
if (++count == LOOP_TIMEOUT) {
pr_err("No event written to event log\n");
return;
}
udelay(1);
goto retry;
}
if (type == EVENT_TYPE_IO_FAULT) {
amd_iommu_report_page_fault(devid, pasid, address, flags);
return;
}
switch (type) {
case EVENT_TYPE_ILL_DEV:
dev_err(dev, "Event logged [ILLEGAL_DEV_TABLE_ENTRY device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
pasid, address, flags);
dump_dte_entry(devid);
break;
case EVENT_TYPE_DEV_TAB_ERR:
dev_err(dev, "Event logged [DEV_TAB_HARDWARE_ERROR device=%02x:%02x.%x "
"address=0x%llx flags=0x%04x]\n",
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
address, flags);
break;
case EVENT_TYPE_PAGE_TAB_ERR:
dev_err(dev, "Event logged [PAGE_TAB_HARDWARE_ERROR device=%02x:%02x.%x domain=0x%04x address=0x%llx flags=0x%04x]\n",
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
pasid, address, flags);
break;
case EVENT_TYPE_ILL_CMD:
dev_err(dev, "Event logged [ILLEGAL_COMMAND_ERROR address=0x%llx]\n", address);
dump_command(address);
break;
case EVENT_TYPE_CMD_HARD_ERR:
dev_err(dev, "Event logged [COMMAND_HARDWARE_ERROR address=0x%llx flags=0x%04x]\n",
address, flags);
break;
case EVENT_TYPE_IOTLB_INV_TO:
dev_err(dev, "Event logged [IOTLB_INV_TIMEOUT device=%02x:%02x.%x address=0x%llx]\n",
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
address);
break;
case EVENT_TYPE_INV_DEV_REQ:
dev_err(dev, "Event logged [INVALID_DEVICE_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
pasid, address, flags);
break;
case EVENT_TYPE_INV_PPR_REQ:
pasid = ((event[0] >> 16) & 0xFFFF)
| ((event[1] << 6) & 0xF0000);
tag = event[1] & 0x03FF;
dev_err(dev, "Event logged [INVALID_PPR_REQUEST device=%02x:%02x.%x pasid=0x%05x address=0x%llx flags=0x%04x]\n",
PCI_BUS_NUM(devid), PCI_SLOT(devid), PCI_FUNC(devid),
pasid, address, flags);
break;
default:
dev_err(dev, "Event logged [UNKNOWN event[0]=0x%08x event[1]=0x%08x event[2]=0x%08x event[3]=0x%08x\n",
event[0], event[1], event[2], event[3]);
}
memset(__evt, 0, 4 * sizeof(u32));
}
static void iommu_poll_events(struct amd_iommu *iommu)
{
u32 head, tail;
head = readl(iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_EVT_TAIL_OFFSET);
while (head != tail) {
iommu_print_event(iommu, iommu->evt_buf + head);
head = (head + EVENT_ENTRY_SIZE) % EVT_BUFFER_SIZE;
}
writel(head, iommu->mmio_base + MMIO_EVT_HEAD_OFFSET);
}
static void iommu_handle_ppr_entry(struct amd_iommu *iommu, u64 *raw)
{
struct amd_iommu_fault fault;
if (PPR_REQ_TYPE(raw[0]) != PPR_REQ_FAULT) {
pr_err_ratelimited("Unknown PPR request received\n");
return;
}
fault.address = raw[1];
fault.pasid = PPR_PASID(raw[0]);
fault.device_id = PPR_DEVID(raw[0]);
fault.tag = PPR_TAG(raw[0]);
fault.flags = PPR_FLAGS(raw[0]);
atomic_notifier_call_chain(&ppr_notifier, 0, &fault);
}
static void iommu_poll_ppr_log(struct amd_iommu *iommu)
{
u32 head, tail;
if (iommu->ppr_log == NULL)
return;
head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
while (head != tail) {
volatile u64 *raw;
u64 entry[2];
int i;
raw = (u64 *)(iommu->ppr_log + head);
/*
* Hardware bug: Interrupt may arrive before the entry is
* written to memory. If this happens we need to wait for the
* entry to arrive.
*/
for (i = 0; i < LOOP_TIMEOUT; ++i) {
if (PPR_REQ_TYPE(raw[0]) != 0)
break;
udelay(1);
}
/* Avoid memcpy function-call overhead */
entry[0] = raw[0];
entry[1] = raw[1];
/*
* To detect the hardware bug we need to clear the entry
* back to zero.
*/
raw[0] = raw[1] = 0UL;
/* Update head pointer of hardware ring-buffer */
head = (head + PPR_ENTRY_SIZE) % PPR_LOG_SIZE;
writel(head, iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
/* Handle PPR entry */
iommu_handle_ppr_entry(iommu, entry);
/* Refresh ring-buffer information */
head = readl(iommu->mmio_base + MMIO_PPR_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_PPR_TAIL_OFFSET);
}
}
#ifdef CONFIG_IRQ_REMAP
static int (*iommu_ga_log_notifier)(u32);
int amd_iommu_register_ga_log_notifier(int (*notifier)(u32))
{
iommu_ga_log_notifier = notifier;
return 0;
}
EXPORT_SYMBOL(amd_iommu_register_ga_log_notifier);
static void iommu_poll_ga_log(struct amd_iommu *iommu)
{
u32 head, tail, cnt = 0;
if (iommu->ga_log == NULL)
return;
head = readl(iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
tail = readl(iommu->mmio_base + MMIO_GA_TAIL_OFFSET);
while (head != tail) {
volatile u64 *raw;
u64 log_entry;
raw = (u64 *)(iommu->ga_log + head);
cnt++;
/* Avoid memcpy function-call overhead */
log_entry = *raw;
/* Update head pointer of hardware ring-buffer */
head = (head + GA_ENTRY_SIZE) % GA_LOG_SIZE;
writel(head, iommu->mmio_base + MMIO_GA_HEAD_OFFSET);
/* Handle GA entry */
switch (GA_REQ_TYPE(log_entry)) {
case GA_GUEST_NR:
if (!iommu_ga_log_notifier)
break;
pr_debug("%s: devid=%#x, ga_tag=%#x\n",
__func__, GA_DEVID(log_entry),
GA_TAG(log_entry));
if (iommu_ga_log_notifier(GA_TAG(log_entry)) != 0)
pr_err("GA log notifier failed.\n");
break;
default:
break;
}
}
}
#endif /* CONFIG_IRQ_REMAP */
#define AMD_IOMMU_INT_MASK \
(MMIO_STATUS_EVT_INT_MASK | \
MMIO_STATUS_PPR_INT_MASK | \
MMIO_STATUS_GALOG_INT_MASK)
irqreturn_t amd_iommu_int_thread(int irq, void *data)
{
struct amd_iommu *iommu = (struct amd_iommu *) data;
u32 status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
while (status & AMD_IOMMU_INT_MASK) {
/* Enable EVT and PPR and GA interrupts again */
writel(AMD_IOMMU_INT_MASK,
iommu->mmio_base + MMIO_STATUS_OFFSET);
if (status & MMIO_STATUS_EVT_INT_MASK) {
pr_devel("Processing IOMMU Event Log\n");
iommu_poll_events(iommu);
}
if (status & MMIO_STATUS_PPR_INT_MASK) {
pr_devel("Processing IOMMU PPR Log\n");
iommu_poll_ppr_log(iommu);
}
#ifdef CONFIG_IRQ_REMAP
if (status & MMIO_STATUS_GALOG_INT_MASK) {
pr_devel("Processing IOMMU GA Log\n");
iommu_poll_ga_log(iommu);
}
#endif
/*
* Hardware bug: ERBT1312
* When re-enabling interrupt (by writing 1
* to clear the bit), the hardware might also try to set
* the interrupt bit in the event status register.
* In this scenario, the bit will be set, and disable
* subsequent interrupts.
*
* Workaround: The IOMMU driver should read back the
* status register and check if the interrupt bits are cleared.
* If not, driver will need to go through the interrupt handler
* again and re-clear the bits
*/
status = readl(iommu->mmio_base + MMIO_STATUS_OFFSET);
}
return IRQ_HANDLED;
}
irqreturn_t amd_iommu_int_handler(int irq, void *data)
{
return IRQ_WAKE_THREAD;
}
/****************************************************************************
*
* IOMMU command queuing functions
*
****************************************************************************/
static int wait_on_sem(volatile u64 *sem)
{
int i = 0;
while (*sem == 0 && i < LOOP_TIMEOUT) {
udelay(1);
i += 1;
}
if (i == LOOP_TIMEOUT) {
pr_alert("Completion-Wait loop timed out\n");
return -EIO;
}
return 0;
}
static void copy_cmd_to_buffer(struct amd_iommu *iommu,
struct iommu_cmd *cmd)
{
u8 *target;
target = iommu->cmd_buf + iommu->cmd_buf_tail;
iommu->cmd_buf_tail += sizeof(*cmd);
iommu->cmd_buf_tail %= CMD_BUFFER_SIZE;
/* Copy command to buffer */
memcpy(target, cmd, sizeof(*cmd));
/* Tell the IOMMU about it */
writel(iommu->cmd_buf_tail, iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
}
static void build_completion_wait(struct iommu_cmd *cmd, u64 address)
{
u64 paddr = iommu_virt_to_phys((void *)address);
WARN_ON(address & 0x7ULL);
memset(cmd, 0, sizeof(*cmd));
cmd->data[0] = lower_32_bits(paddr) | CMD_COMPL_WAIT_STORE_MASK;
cmd->data[1] = upper_32_bits(paddr);
cmd->data[2] = 1;
CMD_SET_TYPE(cmd, CMD_COMPL_WAIT);
}
static void build_inv_dte(struct iommu_cmd *cmd, u16 devid)
{
memset(cmd, 0, sizeof(*cmd));
cmd->data[0] = devid;
CMD_SET_TYPE(cmd, CMD_INV_DEV_ENTRY);
}
static void build_inv_iommu_pages(struct iommu_cmd *cmd, u64 address,
size_t size, u16 domid, int pde)
{
u64 pages;
bool s;
pages = iommu_num_pages(address, size, PAGE_SIZE);
s = false;
if (pages > 1) {
/*
* If we have to flush more than one page, flush all
* TLB entries for this domain
*/
address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
s = true;
}
address &= PAGE_MASK;
memset(cmd, 0, sizeof(*cmd));
cmd->data[1] |= domid;
cmd->data[2] = lower_32_bits(address);
cmd->data[3] = upper_32_bits(address);
CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
if (s) /* size bit - we flush more than one 4kb page */
cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
if (pde) /* PDE bit - we want to flush everything, not only the PTEs */
cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
}
static void build_inv_iotlb_pages(struct iommu_cmd *cmd, u16 devid, int qdep,
u64 address, size_t size)
{
u64 pages;
bool s;
pages = iommu_num_pages(address, size, PAGE_SIZE);
s = false;
if (pages > 1) {
/*
* If we have to flush more than one page, flush all
* TLB entries for this domain
*/
address = CMD_INV_IOMMU_ALL_PAGES_ADDRESS;
s = true;
}
address &= PAGE_MASK;
memset(cmd, 0, sizeof(*cmd));
cmd->data[0] = devid;
cmd->data[0] |= (qdep & 0xff) << 24;
cmd->data[1] = devid;
cmd->data[2] = lower_32_bits(address);
cmd->data[3] = upper_32_bits(address);
CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
if (s)
cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
}
static void build_inv_iommu_pasid(struct iommu_cmd *cmd, u16 domid, int pasid,
u64 address, bool size)
{
memset(cmd, 0, sizeof(*cmd));
address &= ~(0xfffULL);
cmd->data[0] = pasid;
cmd->data[1] = domid;
cmd->data[2] = lower_32_bits(address);
cmd->data[3] = upper_32_bits(address);
cmd->data[2] |= CMD_INV_IOMMU_PAGES_PDE_MASK;
cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
if (size)
cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
CMD_SET_TYPE(cmd, CMD_INV_IOMMU_PAGES);
}
static void build_inv_iotlb_pasid(struct iommu_cmd *cmd, u16 devid, int pasid,
int qdep, u64 address, bool size)
{
memset(cmd, 0, sizeof(*cmd));
address &= ~(0xfffULL);
cmd->data[0] = devid;
cmd->data[0] |= ((pasid >> 8) & 0xff) << 16;
cmd->data[0] |= (qdep & 0xff) << 24;
cmd->data[1] = devid;
cmd->data[1] |= (pasid & 0xff) << 16;
cmd->data[2] = lower_32_bits(address);
cmd->data[2] |= CMD_INV_IOMMU_PAGES_GN_MASK;
cmd->data[3] = upper_32_bits(address);
if (size)
cmd->data[2] |= CMD_INV_IOMMU_PAGES_SIZE_MASK;
CMD_SET_TYPE(cmd, CMD_INV_IOTLB_PAGES);
}
static void build_complete_ppr(struct iommu_cmd *cmd, u16 devid, int pasid,
int status, int tag, bool gn)
{
memset(cmd, 0, sizeof(*cmd));