-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvirtio-iommu.c
1451 lines (1217 loc) · 45.9 KB
/
virtio-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
/*
* virtio-iommu device
*
* Copyright (c) 2020 Red Hat, Inc.
*
* 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 or later, 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, see <http://www.gnu.org/licenses/>.
*
*/
#include "qemu/osdep.h"
#include "qemu/log.h"
#include "qemu/iov.h"
#include "exec/target_page.h"
#include "hw/qdev-properties.h"
#include "hw/virtio/virtio.h"
#include "sysemu/kvm.h"
#include "sysemu/reset.h"
#include "sysemu/sysemu.h"
#include "qapi/error.h"
#include "qemu/error-report.h"
#include "trace.h"
#include "standard-headers/linux/virtio_ids.h"
#include "hw/virtio/virtio-bus.h"
#include "hw/virtio/virtio-iommu.h"
#include "hw/pci/pci_bus.h"
#include "hw/pci/pci.h"
/* Max size */
#define VIOMMU_DEFAULT_QUEUE_SIZE 256
#define VIOMMU_PROBE_SIZE 512
typedef struct VirtIOIOMMUDomain {
uint32_t id;
bool bypass;
GTree *mappings;
QLIST_HEAD(, VirtIOIOMMUEndpoint) endpoint_list;
} VirtIOIOMMUDomain;
typedef struct VirtIOIOMMUEndpoint {
uint32_t id;
VirtIOIOMMUDomain *domain;
IOMMUMemoryRegion *iommu_mr;
QLIST_ENTRY(VirtIOIOMMUEndpoint) next;
} VirtIOIOMMUEndpoint;
typedef struct VirtIOIOMMUInterval {
uint64_t low;
uint64_t high;
} VirtIOIOMMUInterval;
typedef struct VirtIOIOMMUMapping {
uint64_t phys_addr;
uint32_t flags;
} VirtIOIOMMUMapping;
static inline uint16_t virtio_iommu_get_bdf(IOMMUDevice *dev)
{
return PCI_BUILD_BDF(pci_bus_num(dev->bus), dev->devfn);
}
static bool virtio_iommu_device_bypassed(IOMMUDevice *sdev)
{
uint32_t sid;
bool bypassed;
VirtIOIOMMU *s = sdev->viommu;
VirtIOIOMMUEndpoint *ep;
sid = virtio_iommu_get_bdf(sdev);
qemu_rec_mutex_lock(&s->mutex);
/* need to check bypass before system reset */
if (!s->endpoints) {
bypassed = s->config.bypass;
goto unlock;
}
ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(sid));
if (!ep || !ep->domain) {
bypassed = s->config.bypass;
} else {
bypassed = ep->domain->bypass;
}
unlock:
qemu_rec_mutex_unlock(&s->mutex);
return bypassed;
}
/* Return whether the device is using IOMMU translation. */
static bool virtio_iommu_switch_address_space(IOMMUDevice *sdev)
{
bool use_remapping;
assert(sdev);
use_remapping = !virtio_iommu_device_bypassed(sdev);
trace_virtio_iommu_switch_address_space(pci_bus_num(sdev->bus),
PCI_SLOT(sdev->devfn),
PCI_FUNC(sdev->devfn),
use_remapping);
/* Turn off first then on the other */
if (use_remapping) {
memory_region_set_enabled(&sdev->bypass_mr, false);
memory_region_set_enabled(MEMORY_REGION(&sdev->iommu_mr), true);
} else {
memory_region_set_enabled(MEMORY_REGION(&sdev->iommu_mr), false);
memory_region_set_enabled(&sdev->bypass_mr, true);
}
return use_remapping;
}
static void virtio_iommu_switch_address_space_all(VirtIOIOMMU *s)
{
GHashTableIter iter;
IOMMUPciBus *iommu_pci_bus;
int i;
g_hash_table_iter_init(&iter, s->as_by_busptr);
while (g_hash_table_iter_next(&iter, NULL, (void **)&iommu_pci_bus)) {
for (i = 0; i < PCI_DEVFN_MAX; i++) {
if (!iommu_pci_bus->pbdev[i]) {
continue;
}
virtio_iommu_switch_address_space(iommu_pci_bus->pbdev[i]);
}
}
}
/**
* The bus number is used for lookup when SID based operations occur.
* In that case we lazily populate the IOMMUPciBus array from the bus hash
* table. At the time the IOMMUPciBus is created (iommu_find_add_as), the bus
* numbers may not be always initialized yet.
*/
static IOMMUPciBus *iommu_find_iommu_pcibus(VirtIOIOMMU *s, uint8_t bus_num)
{
IOMMUPciBus *iommu_pci_bus = s->iommu_pcibus_by_bus_num[bus_num];
if (!iommu_pci_bus) {
GHashTableIter iter;
g_hash_table_iter_init(&iter, s->as_by_busptr);
while (g_hash_table_iter_next(&iter, NULL, (void **)&iommu_pci_bus)) {
if (pci_bus_num(iommu_pci_bus->bus) == bus_num) {
s->iommu_pcibus_by_bus_num[bus_num] = iommu_pci_bus;
return iommu_pci_bus;
}
}
return NULL;
}
return iommu_pci_bus;
}
static IOMMUMemoryRegion *virtio_iommu_mr(VirtIOIOMMU *s, uint32_t sid)
{
uint8_t bus_n, devfn;
IOMMUPciBus *iommu_pci_bus;
IOMMUDevice *dev;
bus_n = PCI_BUS_NUM(sid);
iommu_pci_bus = iommu_find_iommu_pcibus(s, bus_n);
if (iommu_pci_bus) {
devfn = sid & (PCI_DEVFN_MAX - 1);
dev = iommu_pci_bus->pbdev[devfn];
if (dev) {
return &dev->iommu_mr;
}
}
return NULL;
}
static gint interval_cmp(gconstpointer a, gconstpointer b, gpointer user_data)
{
VirtIOIOMMUInterval *inta = (VirtIOIOMMUInterval *)a;
VirtIOIOMMUInterval *intb = (VirtIOIOMMUInterval *)b;
if (inta->high < intb->low) {
return -1;
} else if (intb->high < inta->low) {
return 1;
} else {
return 0;
}
}
static void virtio_iommu_notify_map_unmap(IOMMUMemoryRegion *mr,
IOMMUTLBEvent *event,
hwaddr virt_start, hwaddr virt_end)
{
uint64_t delta = virt_end - virt_start;
event->entry.iova = virt_start;
event->entry.addr_mask = delta;
if (delta == UINT64_MAX) {
memory_region_notify_iommu(mr, 0, *event);
}
while (virt_start != virt_end + 1) {
uint64_t mask = dma_aligned_pow2_mask(virt_start, virt_end, 64);
event->entry.addr_mask = mask;
event->entry.iova = virt_start;
memory_region_notify_iommu(mr, 0, *event);
virt_start += mask + 1;
if (event->entry.perm != IOMMU_NONE) {
event->entry.translated_addr += mask + 1;
}
}
}
static void virtio_iommu_notify_map(IOMMUMemoryRegion *mr, hwaddr virt_start,
hwaddr virt_end, hwaddr paddr,
uint32_t flags)
{
IOMMUTLBEvent event;
IOMMUAccessFlags perm = IOMMU_ACCESS_FLAG(flags & VIRTIO_IOMMU_MAP_F_READ,
flags & VIRTIO_IOMMU_MAP_F_WRITE);
if (!(mr->iommu_notify_flags & IOMMU_NOTIFIER_MAP) ||
(flags & VIRTIO_IOMMU_MAP_F_MMIO) || !perm) {
return;
}
trace_virtio_iommu_notify_map(mr->parent_obj.name, virt_start, virt_end,
paddr, perm);
event.type = IOMMU_NOTIFIER_MAP;
event.entry.target_as = &address_space_memory;
event.entry.perm = perm;
event.entry.translated_addr = paddr;
virtio_iommu_notify_map_unmap(mr, &event, virt_start, virt_end);
}
static void virtio_iommu_notify_unmap(IOMMUMemoryRegion *mr, hwaddr virt_start,
hwaddr virt_end)
{
IOMMUTLBEvent event;
if (!(mr->iommu_notify_flags & IOMMU_NOTIFIER_UNMAP)) {
return;
}
trace_virtio_iommu_notify_unmap(mr->parent_obj.name, virt_start, virt_end);
event.type = IOMMU_NOTIFIER_UNMAP;
event.entry.target_as = &address_space_memory;
event.entry.perm = IOMMU_NONE;
event.entry.translated_addr = 0;
virtio_iommu_notify_map_unmap(mr, &event, virt_start, virt_end);
}
static gboolean virtio_iommu_notify_unmap_cb(gpointer key, gpointer value,
gpointer data)
{
VirtIOIOMMUInterval *interval = (VirtIOIOMMUInterval *) key;
IOMMUMemoryRegion *mr = (IOMMUMemoryRegion *) data;
virtio_iommu_notify_unmap(mr, interval->low, interval->high);
return false;
}
static gboolean virtio_iommu_notify_map_cb(gpointer key, gpointer value,
gpointer data)
{
VirtIOIOMMUMapping *mapping = (VirtIOIOMMUMapping *) value;
VirtIOIOMMUInterval *interval = (VirtIOIOMMUInterval *) key;
IOMMUMemoryRegion *mr = (IOMMUMemoryRegion *) data;
virtio_iommu_notify_map(mr, interval->low, interval->high,
mapping->phys_addr, mapping->flags);
return false;
}
static void virtio_iommu_detach_endpoint_from_domain(VirtIOIOMMUEndpoint *ep)
{
VirtIOIOMMUDomain *domain = ep->domain;
IOMMUDevice *sdev = container_of(ep->iommu_mr, IOMMUDevice, iommu_mr);
if (!ep->domain) {
return;
}
g_tree_foreach(domain->mappings, virtio_iommu_notify_unmap_cb,
ep->iommu_mr);
QLIST_REMOVE(ep, next);
ep->domain = NULL;
virtio_iommu_switch_address_space(sdev);
}
static VirtIOIOMMUEndpoint *virtio_iommu_get_endpoint(VirtIOIOMMU *s,
uint32_t ep_id)
{
VirtIOIOMMUEndpoint *ep;
IOMMUMemoryRegion *mr;
ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(ep_id));
if (ep) {
return ep;
}
mr = virtio_iommu_mr(s, ep_id);
if (!mr) {
return NULL;
}
ep = g_malloc0(sizeof(*ep));
ep->id = ep_id;
ep->iommu_mr = mr;
trace_virtio_iommu_get_endpoint(ep_id);
g_tree_insert(s->endpoints, GUINT_TO_POINTER(ep_id), ep);
return ep;
}
static void virtio_iommu_put_endpoint(gpointer data)
{
VirtIOIOMMUEndpoint *ep = (VirtIOIOMMUEndpoint *)data;
if (ep->domain) {
virtio_iommu_detach_endpoint_from_domain(ep);
}
trace_virtio_iommu_put_endpoint(ep->id);
g_free(ep);
}
static VirtIOIOMMUDomain *virtio_iommu_get_domain(VirtIOIOMMU *s,
uint32_t domain_id,
bool bypass)
{
VirtIOIOMMUDomain *domain;
domain = g_tree_lookup(s->domains, GUINT_TO_POINTER(domain_id));
if (domain) {
if (domain->bypass != bypass) {
return NULL;
}
return domain;
}
domain = g_malloc0(sizeof(*domain));
domain->id = domain_id;
domain->mappings = g_tree_new_full((GCompareDataFunc)interval_cmp,
NULL, (GDestroyNotify)g_free,
(GDestroyNotify)g_free);
domain->bypass = bypass;
g_tree_insert(s->domains, GUINT_TO_POINTER(domain_id), domain);
QLIST_INIT(&domain->endpoint_list);
trace_virtio_iommu_get_domain(domain_id);
return domain;
}
static void virtio_iommu_put_domain(gpointer data)
{
VirtIOIOMMUDomain *domain = (VirtIOIOMMUDomain *)data;
VirtIOIOMMUEndpoint *iter, *tmp;
QLIST_FOREACH_SAFE(iter, &domain->endpoint_list, next, tmp) {
virtio_iommu_detach_endpoint_from_domain(iter);
}
g_tree_destroy(domain->mappings);
trace_virtio_iommu_put_domain(domain->id);
g_free(domain);
}
static AddressSpace *virtio_iommu_find_add_as(PCIBus *bus, void *opaque,
int devfn)
{
VirtIOIOMMU *s = opaque;
IOMMUPciBus *sbus = g_hash_table_lookup(s->as_by_busptr, bus);
static uint32_t mr_index;
IOMMUDevice *sdev;
if (!sbus) {
sbus = g_malloc0(sizeof(IOMMUPciBus) +
sizeof(IOMMUDevice *) * PCI_DEVFN_MAX);
sbus->bus = bus;
g_hash_table_insert(s->as_by_busptr, bus, sbus);
}
sdev = sbus->pbdev[devfn];
if (!sdev) {
char *name = g_strdup_printf("%s-%d-%d",
TYPE_VIRTIO_IOMMU_MEMORY_REGION,
mr_index++, devfn);
sdev = sbus->pbdev[devfn] = g_new0(IOMMUDevice, 1);
sdev->viommu = s;
sdev->bus = bus;
sdev->devfn = devfn;
trace_virtio_iommu_init_iommu_mr(name);
memory_region_init(&sdev->root, OBJECT(s), name, UINT64_MAX);
address_space_init(&sdev->as, &sdev->root, TYPE_VIRTIO_IOMMU);
/*
* Build the IOMMU disabled container with aliases to the
* shared MRs. Note that aliasing to a shared memory region
* could help the memory API to detect same FlatViews so we
* can have devices to share the same FlatView when in bypass
* mode. (either by not configuring virtio-iommu driver or with
* "iommu=pt"). It will greatly reduce the total number of
* FlatViews of the system hence VM runs faster.
*/
memory_region_init_alias(&sdev->bypass_mr, OBJECT(s),
"system", get_system_memory(), 0,
memory_region_size(get_system_memory()));
memory_region_init_iommu(&sdev->iommu_mr, sizeof(sdev->iommu_mr),
TYPE_VIRTIO_IOMMU_MEMORY_REGION,
OBJECT(s), name,
UINT64_MAX);
/*
* Hook both the containers under the root container, we
* switch between iommu & bypass MRs by enable/disable
* corresponding sub-containers
*/
memory_region_add_subregion_overlap(&sdev->root, 0,
MEMORY_REGION(&sdev->iommu_mr),
0);
memory_region_add_subregion_overlap(&sdev->root, 0,
&sdev->bypass_mr, 0);
virtio_iommu_switch_address_space(sdev);
g_free(name);
}
return &sdev->as;
}
static int virtio_iommu_attach(VirtIOIOMMU *s,
struct virtio_iommu_req_attach *req)
{
uint32_t domain_id = le32_to_cpu(req->domain);
uint32_t ep_id = le32_to_cpu(req->endpoint);
uint32_t flags = le32_to_cpu(req->flags);
VirtIOIOMMUDomain *domain;
VirtIOIOMMUEndpoint *ep;
IOMMUDevice *sdev;
trace_virtio_iommu_attach(domain_id, ep_id);
if (flags & ~VIRTIO_IOMMU_ATTACH_F_BYPASS) {
return VIRTIO_IOMMU_S_INVAL;
}
ep = virtio_iommu_get_endpoint(s, ep_id);
if (!ep) {
return VIRTIO_IOMMU_S_NOENT;
}
if (ep->domain) {
VirtIOIOMMUDomain *previous_domain = ep->domain;
/*
* the device is already attached to a domain,
* detach it first
*/
virtio_iommu_detach_endpoint_from_domain(ep);
if (QLIST_EMPTY(&previous_domain->endpoint_list)) {
g_tree_remove(s->domains, GUINT_TO_POINTER(previous_domain->id));
}
}
domain = virtio_iommu_get_domain(s, domain_id,
flags & VIRTIO_IOMMU_ATTACH_F_BYPASS);
if (!domain) {
/* Incompatible bypass flag */
return VIRTIO_IOMMU_S_INVAL;
}
QLIST_INSERT_HEAD(&domain->endpoint_list, ep, next);
ep->domain = domain;
sdev = container_of(ep->iommu_mr, IOMMUDevice, iommu_mr);
virtio_iommu_switch_address_space(sdev);
/* Replay domain mappings on the associated memory region */
g_tree_foreach(domain->mappings, virtio_iommu_notify_map_cb,
ep->iommu_mr);
return VIRTIO_IOMMU_S_OK;
}
static int virtio_iommu_detach(VirtIOIOMMU *s,
struct virtio_iommu_req_detach *req)
{
uint32_t domain_id = le32_to_cpu(req->domain);
uint32_t ep_id = le32_to_cpu(req->endpoint);
VirtIOIOMMUDomain *domain;
VirtIOIOMMUEndpoint *ep;
trace_virtio_iommu_detach(domain_id, ep_id);
ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(ep_id));
if (!ep) {
return VIRTIO_IOMMU_S_NOENT;
}
domain = ep->domain;
if (!domain || domain->id != domain_id) {
return VIRTIO_IOMMU_S_INVAL;
}
virtio_iommu_detach_endpoint_from_domain(ep);
if (QLIST_EMPTY(&domain->endpoint_list)) {
g_tree_remove(s->domains, GUINT_TO_POINTER(domain->id));
}
return VIRTIO_IOMMU_S_OK;
}
static int virtio_iommu_map(VirtIOIOMMU *s,
struct virtio_iommu_req_map *req)
{
uint32_t domain_id = le32_to_cpu(req->domain);
uint64_t phys_start = le64_to_cpu(req->phys_start);
uint64_t virt_start = le64_to_cpu(req->virt_start);
uint64_t virt_end = le64_to_cpu(req->virt_end);
uint32_t flags = le32_to_cpu(req->flags);
VirtIOIOMMUDomain *domain;
VirtIOIOMMUInterval *interval;
VirtIOIOMMUMapping *mapping;
VirtIOIOMMUEndpoint *ep;
if (flags & ~VIRTIO_IOMMU_MAP_F_MASK) {
return VIRTIO_IOMMU_S_INVAL;
}
domain = g_tree_lookup(s->domains, GUINT_TO_POINTER(domain_id));
if (!domain) {
return VIRTIO_IOMMU_S_NOENT;
}
if (domain->bypass) {
return VIRTIO_IOMMU_S_INVAL;
}
interval = g_malloc0(sizeof(*interval));
interval->low = virt_start;
interval->high = virt_end;
mapping = g_tree_lookup(domain->mappings, (gpointer)interval);
if (mapping) {
g_free(interval);
return VIRTIO_IOMMU_S_INVAL;
}
trace_virtio_iommu_map(domain_id, virt_start, virt_end, phys_start, flags);
mapping = g_malloc0(sizeof(*mapping));
mapping->phys_addr = phys_start;
mapping->flags = flags;
g_tree_insert(domain->mappings, interval, mapping);
QLIST_FOREACH(ep, &domain->endpoint_list, next) {
virtio_iommu_notify_map(ep->iommu_mr, virt_start, virt_end, phys_start,
flags);
}
return VIRTIO_IOMMU_S_OK;
}
static int virtio_iommu_unmap(VirtIOIOMMU *s,
struct virtio_iommu_req_unmap *req)
{
uint32_t domain_id = le32_to_cpu(req->domain);
uint64_t virt_start = le64_to_cpu(req->virt_start);
uint64_t virt_end = le64_to_cpu(req->virt_end);
VirtIOIOMMUMapping *iter_val;
VirtIOIOMMUInterval interval, *iter_key;
VirtIOIOMMUDomain *domain;
VirtIOIOMMUEndpoint *ep;
int ret = VIRTIO_IOMMU_S_OK;
trace_virtio_iommu_unmap(domain_id, virt_start, virt_end);
domain = g_tree_lookup(s->domains, GUINT_TO_POINTER(domain_id));
if (!domain) {
return VIRTIO_IOMMU_S_NOENT;
}
if (domain->bypass) {
return VIRTIO_IOMMU_S_INVAL;
}
interval.low = virt_start;
interval.high = virt_end;
while (g_tree_lookup_extended(domain->mappings, &interval,
(void **)&iter_key, (void**)&iter_val)) {
uint64_t current_low = iter_key->low;
uint64_t current_high = iter_key->high;
if (interval.low <= current_low && interval.high >= current_high) {
QLIST_FOREACH(ep, &domain->endpoint_list, next) {
virtio_iommu_notify_unmap(ep->iommu_mr, current_low,
current_high);
}
g_tree_remove(domain->mappings, iter_key);
trace_virtio_iommu_unmap_done(domain_id, current_low, current_high);
} else {
ret = VIRTIO_IOMMU_S_RANGE;
break;
}
}
return ret;
}
static ssize_t virtio_iommu_fill_resv_mem_prop(VirtIOIOMMU *s, uint32_t ep,
uint8_t *buf, size_t free)
{
struct virtio_iommu_probe_resv_mem prop = {};
size_t size = sizeof(prop), length = size - sizeof(prop.head), total;
int i;
total = size * s->nb_reserved_regions;
if (total > free) {
return -ENOSPC;
}
for (i = 0; i < s->nb_reserved_regions; i++) {
unsigned subtype = s->reserved_regions[i].type;
assert(subtype == VIRTIO_IOMMU_RESV_MEM_T_RESERVED ||
subtype == VIRTIO_IOMMU_RESV_MEM_T_MSI);
prop.head.type = cpu_to_le16(VIRTIO_IOMMU_PROBE_T_RESV_MEM);
prop.head.length = cpu_to_le16(length);
prop.subtype = subtype;
prop.start = cpu_to_le64(s->reserved_regions[i].low);
prop.end = cpu_to_le64(s->reserved_regions[i].high);
memcpy(buf, &prop, size);
trace_virtio_iommu_fill_resv_property(ep, prop.subtype,
prop.start, prop.end);
buf += size;
}
return total;
}
/**
* virtio_iommu_probe - Fill the probe request buffer with
* the properties the device is able to return
*/
static int virtio_iommu_probe(VirtIOIOMMU *s,
struct virtio_iommu_req_probe *req,
uint8_t *buf)
{
uint32_t ep_id = le32_to_cpu(req->endpoint);
size_t free = VIOMMU_PROBE_SIZE;
ssize_t count;
if (!virtio_iommu_mr(s, ep_id)) {
return VIRTIO_IOMMU_S_NOENT;
}
count = virtio_iommu_fill_resv_mem_prop(s, ep_id, buf, free);
if (count < 0) {
return VIRTIO_IOMMU_S_INVAL;
}
buf += count;
free -= count;
return VIRTIO_IOMMU_S_OK;
}
static int virtio_iommu_iov_to_req(struct iovec *iov,
unsigned int iov_cnt,
void *req, size_t payload_sz)
{
size_t sz = iov_to_buf(iov, iov_cnt, 0, req, payload_sz);
if (unlikely(sz != payload_sz)) {
return VIRTIO_IOMMU_S_INVAL;
}
return 0;
}
#define virtio_iommu_handle_req(__req) \
static int virtio_iommu_handle_ ## __req(VirtIOIOMMU *s, \
struct iovec *iov, \
unsigned int iov_cnt) \
{ \
struct virtio_iommu_req_ ## __req req; \
int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, \
sizeof(req) - sizeof(struct virtio_iommu_req_tail));\
\
return ret ? ret : virtio_iommu_ ## __req(s, &req); \
}
virtio_iommu_handle_req(attach)
virtio_iommu_handle_req(detach)
virtio_iommu_handle_req(map)
virtio_iommu_handle_req(unmap)
static int virtio_iommu_handle_probe(VirtIOIOMMU *s,
struct iovec *iov,
unsigned int iov_cnt,
uint8_t *buf)
{
struct virtio_iommu_req_probe req;
int ret = virtio_iommu_iov_to_req(iov, iov_cnt, &req, sizeof(req));
return ret ? ret : virtio_iommu_probe(s, &req, buf);
}
static void virtio_iommu_handle_command(VirtIODevice *vdev, VirtQueue *vq)
{
VirtIOIOMMU *s = VIRTIO_IOMMU(vdev);
struct virtio_iommu_req_head head;
struct virtio_iommu_req_tail tail = {};
VirtQueueElement *elem;
unsigned int iov_cnt;
struct iovec *iov;
void *buf = NULL;
size_t sz;
for (;;) {
size_t output_size = sizeof(tail);
elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
if (!elem) {
return;
}
if (iov_size(elem->in_sg, elem->in_num) < sizeof(tail) ||
iov_size(elem->out_sg, elem->out_num) < sizeof(head)) {
virtio_error(vdev, "virtio-iommu bad head/tail size");
virtqueue_detach_element(vq, elem, 0);
g_free(elem);
break;
}
iov_cnt = elem->out_num;
iov = elem->out_sg;
sz = iov_to_buf(iov, iov_cnt, 0, &head, sizeof(head));
if (unlikely(sz != sizeof(head))) {
tail.status = VIRTIO_IOMMU_S_DEVERR;
goto out;
}
qemu_rec_mutex_lock(&s->mutex);
switch (head.type) {
case VIRTIO_IOMMU_T_ATTACH:
tail.status = virtio_iommu_handle_attach(s, iov, iov_cnt);
break;
case VIRTIO_IOMMU_T_DETACH:
tail.status = virtio_iommu_handle_detach(s, iov, iov_cnt);
break;
case VIRTIO_IOMMU_T_MAP:
tail.status = virtio_iommu_handle_map(s, iov, iov_cnt);
break;
case VIRTIO_IOMMU_T_UNMAP:
tail.status = virtio_iommu_handle_unmap(s, iov, iov_cnt);
break;
case VIRTIO_IOMMU_T_PROBE:
{
struct virtio_iommu_req_tail *ptail;
output_size = s->config.probe_size + sizeof(tail);
buf = g_malloc0(output_size);
ptail = buf + s->config.probe_size;
ptail->status = virtio_iommu_handle_probe(s, iov, iov_cnt, buf);
break;
}
default:
tail.status = VIRTIO_IOMMU_S_UNSUPP;
}
qemu_rec_mutex_unlock(&s->mutex);
out:
sz = iov_from_buf(elem->in_sg, elem->in_num, 0,
buf ? buf : &tail, output_size);
assert(sz == output_size);
virtqueue_push(vq, elem, sz);
virtio_notify(vdev, vq);
g_free(elem);
g_free(buf);
buf = NULL;
}
}
static void virtio_iommu_report_fault(VirtIOIOMMU *viommu, uint8_t reason,
int flags, uint32_t endpoint,
uint64_t address)
{
VirtIODevice *vdev = &viommu->parent_obj;
VirtQueue *vq = viommu->event_vq;
struct virtio_iommu_fault fault;
VirtQueueElement *elem;
size_t sz;
memset(&fault, 0, sizeof(fault));
fault.reason = reason;
fault.flags = cpu_to_le32(flags);
fault.endpoint = cpu_to_le32(endpoint);
fault.address = cpu_to_le64(address);
elem = virtqueue_pop(vq, sizeof(VirtQueueElement));
if (!elem) {
error_report_once(
"no buffer available in event queue to report event");
return;
}
if (iov_size(elem->in_sg, elem->in_num) < sizeof(fault)) {
virtio_error(vdev, "error buffer of wrong size");
virtqueue_detach_element(vq, elem, 0);
g_free(elem);
return;
}
sz = iov_from_buf(elem->in_sg, elem->in_num, 0,
&fault, sizeof(fault));
assert(sz == sizeof(fault));
trace_virtio_iommu_report_fault(reason, flags, endpoint, address);
virtqueue_push(vq, elem, sz);
virtio_notify(vdev, vq);
g_free(elem);
}
static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr,
IOMMUAccessFlags flag,
int iommu_idx)
{
IOMMUDevice *sdev = container_of(mr, IOMMUDevice, iommu_mr);
VirtIOIOMMUInterval interval, *mapping_key;
VirtIOIOMMUMapping *mapping_value;
VirtIOIOMMU *s = sdev->viommu;
bool read_fault, write_fault;
VirtIOIOMMUEndpoint *ep;
uint32_t sid, flags;
bool bypass_allowed;
int granule;
bool found;
int i;
interval.low = addr;
interval.high = addr + 1;
granule = ctz64(s->config.page_size_mask);
IOMMUTLBEntry entry = {
.target_as = &address_space_memory,
.iova = addr,
.translated_addr = addr,
.addr_mask = BIT_ULL(granule) - 1,
.perm = IOMMU_NONE,
};
bypass_allowed = s->config.bypass;
sid = virtio_iommu_get_bdf(sdev);
trace_virtio_iommu_translate(mr->parent_obj.name, sid, addr, flag);
qemu_rec_mutex_lock(&s->mutex);
ep = g_tree_lookup(s->endpoints, GUINT_TO_POINTER(sid));
if (bypass_allowed)
assert(ep && ep->domain && !ep->domain->bypass);
if (!ep) {
if (!bypass_allowed) {
error_report_once("%s sid=%d is not known!!", __func__, sid);
virtio_iommu_report_fault(s, VIRTIO_IOMMU_FAULT_R_UNKNOWN,
VIRTIO_IOMMU_FAULT_F_ADDRESS,
sid, addr);
} else {
entry.perm = flag;
}
goto unlock;
}
for (i = 0; i < s->nb_reserved_regions; i++) {
ReservedRegion *reg = &s->reserved_regions[i];
if (addr >= reg->low && addr <= reg->high) {
switch (reg->type) {
case VIRTIO_IOMMU_RESV_MEM_T_MSI:
entry.perm = flag;
break;
case VIRTIO_IOMMU_RESV_MEM_T_RESERVED:
default:
virtio_iommu_report_fault(s, VIRTIO_IOMMU_FAULT_R_MAPPING,
VIRTIO_IOMMU_FAULT_F_ADDRESS,
sid, addr);
break;
}
goto unlock;
}
}
if (!ep->domain) {
if (!bypass_allowed) {
error_report_once("%s %02x:%02x.%01x not attached to any domain",
__func__, PCI_BUS_NUM(sid),
PCI_SLOT(sid), PCI_FUNC(sid));
virtio_iommu_report_fault(s, VIRTIO_IOMMU_FAULT_R_DOMAIN,
VIRTIO_IOMMU_FAULT_F_ADDRESS,
sid, addr);
} else {
entry.perm = flag;
}
goto unlock;
} else if (ep->domain->bypass) {
entry.perm = flag;
goto unlock;
}
found = g_tree_lookup_extended(ep->domain->mappings, (gpointer)(&interval),
(void **)&mapping_key,
(void **)&mapping_value);
if (!found) {
error_report_once("%s no mapping for 0x%"PRIx64" for sid=%d",
__func__, addr, sid);
virtio_iommu_report_fault(s, VIRTIO_IOMMU_FAULT_R_MAPPING,
VIRTIO_IOMMU_FAULT_F_ADDRESS,
sid, addr);
goto unlock;
}
read_fault = (flag & IOMMU_RO) &&
!(mapping_value->flags & VIRTIO_IOMMU_MAP_F_READ);
write_fault = (flag & IOMMU_WO) &&
!(mapping_value->flags & VIRTIO_IOMMU_MAP_F_WRITE);
flags = read_fault ? VIRTIO_IOMMU_FAULT_F_READ : 0;
flags |= write_fault ? VIRTIO_IOMMU_FAULT_F_WRITE : 0;
if (flags) {
error_report_once("%s permission error on 0x%"PRIx64"(%d): allowed=%d",
__func__, addr, flag, mapping_value->flags);
flags |= VIRTIO_IOMMU_FAULT_F_ADDRESS;
virtio_iommu_report_fault(s, VIRTIO_IOMMU_FAULT_R_MAPPING,
flags | VIRTIO_IOMMU_FAULT_F_ADDRESS,
sid, addr);
goto unlock;
}
entry.translated_addr = addr - mapping_key->low + mapping_value->phys_addr;
entry.perm = flag;
trace_virtio_iommu_translate_out(addr, entry.translated_addr, sid);
unlock:
qemu_rec_mutex_unlock(&s->mutex);
return entry;
}
static void virtio_iommu_get_config(VirtIODevice *vdev, uint8_t *config_data)
{
VirtIOIOMMU *dev = VIRTIO_IOMMU(vdev);
struct virtio_iommu_config *dev_config = &dev->config;
struct virtio_iommu_config *out_config = (void *)config_data;
out_config->page_size_mask = cpu_to_le64(dev_config->page_size_mask);
out_config->input_range.start = cpu_to_le64(dev_config->input_range.start);
out_config->input_range.end = cpu_to_le64(dev_config->input_range.end);
out_config->domain_range.start = cpu_to_le32(dev_config->domain_range.start);
out_config->domain_range.end = cpu_to_le32(dev_config->domain_range.end);
out_config->probe_size = cpu_to_le32(dev_config->probe_size);
out_config->bypass = dev_config->bypass;
trace_virtio_iommu_get_config(dev_config->page_size_mask,
dev_config->input_range.start,
dev_config->input_range.end,
dev_config->domain_range.start,
dev_config->domain_range.end,
dev_config->probe_size,
dev_config->bypass);
}
static void virtio_iommu_set_config(VirtIODevice *vdev,
const uint8_t *config_data)
{
VirtIOIOMMU *dev = VIRTIO_IOMMU(vdev);
struct virtio_iommu_config *dev_config = &dev->config;
const struct virtio_iommu_config *in_config = (void *)config_data;
if (in_config->bypass != dev_config->bypass) {