-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvhost.c
2089 lines (1831 loc) · 63.8 KB
/
vhost.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
/*
* vhost support
*
* Copyright Red Hat, Inc. 2010
*
* Authors:
* Michael S. Tsirkin <[email protected]>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "hw/virtio/vhost.h"
#include "qemu/atomic.h"
#include "qemu/range.h"
#include "qemu/error-report.h"
#include "qemu/memfd.h"
#include "qemu/log.h"
#include "standard-headers/linux/vhost_types.h"
#include "hw/virtio/virtio-bus.h"
#include "migration/blocker.h"
#include "migration/qemu-file-types.h"
#include "sysemu/dma.h"
#include "trace.h"
/* enabled until disconnected backend stabilizes */
#define _VHOST_DEBUG 1
#ifdef _VHOST_DEBUG
#define VHOST_OPS_DEBUG(retval, fmt, ...) \
do { \
error_report(fmt ": %s (%d)", ## __VA_ARGS__, \
strerror(-retval), -retval); \
} while (0)
#else
#define VHOST_OPS_DEBUG(retval, fmt, ...) \
do { } while (0)
#endif
static struct vhost_log *vhost_log;
static struct vhost_log *vhost_log_shm;
static unsigned int used_memslots;
static QLIST_HEAD(, vhost_dev) vhost_devices =
QLIST_HEAD_INITIALIZER(vhost_devices);
bool vhost_has_free_slot(void)
{
unsigned int slots_limit = ~0U;
struct vhost_dev *hdev;
QLIST_FOREACH(hdev, &vhost_devices, entry) {
unsigned int r = hdev->vhost_ops->vhost_backend_memslots_limit(hdev);
slots_limit = MIN(slots_limit, r);
}
return slots_limit > used_memslots;
}
static void vhost_dev_sync_region(struct vhost_dev *dev,
MemoryRegionSection *section,
uint64_t mfirst, uint64_t mlast,
uint64_t rfirst, uint64_t rlast)
{
vhost_log_chunk_t *log = dev->log->log;
uint64_t start = MAX(mfirst, rfirst);
uint64_t end = MIN(mlast, rlast);
vhost_log_chunk_t *from = log + start / VHOST_LOG_CHUNK;
vhost_log_chunk_t *to = log + end / VHOST_LOG_CHUNK + 1;
uint64_t addr = QEMU_ALIGN_DOWN(start, VHOST_LOG_CHUNK);
if (end < start) {
return;
}
assert(end / VHOST_LOG_CHUNK < dev->log_size);
assert(start / VHOST_LOG_CHUNK < dev->log_size);
for (;from < to; ++from) {
vhost_log_chunk_t log;
/* We first check with non-atomic: much cheaper,
* and we expect non-dirty to be the common case. */
if (!*from) {
addr += VHOST_LOG_CHUNK;
continue;
}
/* Data must be read atomically. We don't really need barrier semantics
* but it's easier to use atomic_* than roll our own. */
log = qatomic_xchg(from, 0);
while (log) {
int bit = ctzl(log);
hwaddr page_addr;
hwaddr section_offset;
hwaddr mr_offset;
page_addr = addr + bit * VHOST_LOG_PAGE;
section_offset = page_addr - section->offset_within_address_space;
mr_offset = section_offset + section->offset_within_region;
memory_region_set_dirty(section->mr, mr_offset, VHOST_LOG_PAGE);
log &= ~(0x1ull << bit);
}
addr += VHOST_LOG_CHUNK;
}
}
bool vhost_dev_has_iommu(struct vhost_dev *dev)
{
VirtIODevice *vdev = dev->vdev;
/*
* For vhost, VIRTIO_F_IOMMU_PLATFORM means the backend support
* incremental memory mapping API via IOTLB API. For platform that
* does not have IOMMU, there's no need to enable this feature
* which may cause unnecessary IOTLB miss/update transactions.
*/
if (vdev) {
return virtio_bus_device_iommu_enabled(vdev) &&
virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM);
} else {
return false;
}
}
static int vhost_sync_dirty_bitmap(struct vhost_dev *dev,
MemoryRegionSection *section,
hwaddr first,
hwaddr last)
{
int i;
hwaddr start_addr;
hwaddr end_addr;
if (!dev->log_enabled || !dev->started) {
return 0;
}
start_addr = section->offset_within_address_space;
end_addr = range_get_last(start_addr, int128_get64(section->size));
start_addr = MAX(first, start_addr);
end_addr = MIN(last, end_addr);
for (i = 0; i < dev->mem->nregions; ++i) {
struct vhost_memory_region *reg = dev->mem->regions + i;
vhost_dev_sync_region(dev, section, start_addr, end_addr,
reg->guest_phys_addr,
range_get_last(reg->guest_phys_addr,
reg->memory_size));
}
for (i = 0; i < dev->nvqs; ++i) {
struct vhost_virtqueue *vq = dev->vqs + i;
if (!vq->used_phys && !vq->used_size) {
continue;
}
if (vhost_dev_has_iommu(dev)) {
IOMMUTLBEntry iotlb;
hwaddr used_phys = vq->used_phys, used_size = vq->used_size;
hwaddr phys, s, offset;
while (used_size) {
rcu_read_lock();
iotlb = address_space_get_iotlb_entry(dev->vdev->dma_as,
used_phys,
true,
MEMTXATTRS_UNSPECIFIED);
rcu_read_unlock();
if (!iotlb.target_as) {
qemu_log_mask(LOG_GUEST_ERROR, "translation "
"failure for used_iova %"PRIx64"\n",
used_phys);
return -EINVAL;
}
offset = used_phys & iotlb.addr_mask;
phys = iotlb.translated_addr + offset;
/*
* Distance from start of used ring until last byte of
* IOMMU page.
*/
s = iotlb.addr_mask - offset;
/*
* Size of used ring, or of the part of it until end
* of IOMMU page. To avoid zero result, do the adding
* outside of MIN().
*/
s = MIN(s, used_size - 1) + 1;
vhost_dev_sync_region(dev, section, start_addr, end_addr, phys,
range_get_last(phys, s));
used_size -= s;
used_phys += s;
}
} else {
vhost_dev_sync_region(dev, section, start_addr,
end_addr, vq->used_phys,
range_get_last(vq->used_phys, vq->used_size));
}
}
return 0;
}
static void vhost_log_sync(MemoryListener *listener,
MemoryRegionSection *section)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
memory_listener);
vhost_sync_dirty_bitmap(dev, section, 0x0, ~0x0ULL);
}
static void vhost_log_sync_range(struct vhost_dev *dev,
hwaddr first, hwaddr last)
{
int i;
/* FIXME: this is N^2 in number of sections */
for (i = 0; i < dev->n_mem_sections; ++i) {
MemoryRegionSection *section = &dev->mem_sections[i];
vhost_sync_dirty_bitmap(dev, section, first, last);
}
}
static uint64_t vhost_get_log_size(struct vhost_dev *dev)
{
uint64_t log_size = 0;
int i;
for (i = 0; i < dev->mem->nregions; ++i) {
struct vhost_memory_region *reg = dev->mem->regions + i;
uint64_t last = range_get_last(reg->guest_phys_addr,
reg->memory_size);
log_size = MAX(log_size, last / VHOST_LOG_CHUNK + 1);
}
return log_size;
}
static int vhost_set_backend_type(struct vhost_dev *dev,
VhostBackendType backend_type)
{
int r = 0;
switch (backend_type) {
#ifdef CONFIG_VHOST_KERNEL
case VHOST_BACKEND_TYPE_KERNEL:
dev->vhost_ops = &kernel_ops;
break;
#endif
#ifdef CONFIG_VHOST_USER
case VHOST_BACKEND_TYPE_USER:
dev->vhost_ops = &user_ops;
break;
#endif
#ifdef CONFIG_VHOST_VDPA
case VHOST_BACKEND_TYPE_VDPA:
dev->vhost_ops = &vdpa_ops;
break;
#endif
default:
error_report("Unknown vhost backend type");
r = -1;
}
return r;
}
static struct vhost_log *vhost_log_alloc(uint64_t size, bool share)
{
Error *err = NULL;
struct vhost_log *log;
uint64_t logsize = size * sizeof(*(log->log));
int fd = -1;
log = g_new0(struct vhost_log, 1);
if (share) {
log->log = qemu_memfd_alloc("vhost-log", logsize,
F_SEAL_GROW | F_SEAL_SHRINK | F_SEAL_SEAL,
&fd, &err);
if (err) {
error_report_err(err);
g_free(log);
return NULL;
}
memset(log->log, 0, logsize);
} else {
log->log = g_malloc0(logsize);
}
log->size = size;
log->refcnt = 1;
log->fd = fd;
return log;
}
static struct vhost_log *vhost_log_get(uint64_t size, bool share)
{
struct vhost_log *log = share ? vhost_log_shm : vhost_log;
if (!log || log->size != size) {
log = vhost_log_alloc(size, share);
if (share) {
vhost_log_shm = log;
} else {
vhost_log = log;
}
} else {
++log->refcnt;
}
return log;
}
static void vhost_log_put(struct vhost_dev *dev, bool sync)
{
struct vhost_log *log = dev->log;
if (!log) {
return;
}
--log->refcnt;
if (log->refcnt == 0) {
/* Sync only the range covered by the old log */
if (dev->log_size && sync) {
vhost_log_sync_range(dev, 0, dev->log_size * VHOST_LOG_CHUNK - 1);
}
if (vhost_log == log) {
g_free(log->log);
vhost_log = NULL;
} else if (vhost_log_shm == log) {
qemu_memfd_free(log->log, log->size * sizeof(*(log->log)),
log->fd);
vhost_log_shm = NULL;
}
g_free(log);
}
dev->log = NULL;
dev->log_size = 0;
}
static bool vhost_dev_log_is_shared(struct vhost_dev *dev)
{
return dev->vhost_ops->vhost_requires_shm_log &&
dev->vhost_ops->vhost_requires_shm_log(dev);
}
static inline void vhost_dev_log_resize(struct vhost_dev *dev, uint64_t size)
{
struct vhost_log *log = vhost_log_get(size, vhost_dev_log_is_shared(dev));
uint64_t log_base = (uintptr_t)log->log;
int r;
/* inform backend of log switching, this must be done before
releasing the current log, to ensure no logging is lost */
r = dev->vhost_ops->vhost_set_log_base(dev, log_base, log);
if (r < 0) {
VHOST_OPS_DEBUG(r, "vhost_set_log_base failed");
}
vhost_log_put(dev, true);
dev->log = log;
dev->log_size = size;
}
static void *vhost_memory_map(struct vhost_dev *dev, hwaddr addr,
hwaddr *plen, bool is_write)
{
if (!vhost_dev_has_iommu(dev)) {
return cpu_physical_memory_map(addr, plen, is_write);
} else {
return (void *)(uintptr_t)addr;
}
}
static void vhost_memory_unmap(struct vhost_dev *dev, void *buffer,
hwaddr len, int is_write,
hwaddr access_len)
{
if (!vhost_dev_has_iommu(dev)) {
cpu_physical_memory_unmap(buffer, len, is_write, access_len);
}
}
static int vhost_verify_ring_part_mapping(void *ring_hva,
uint64_t ring_gpa,
uint64_t ring_size,
void *reg_hva,
uint64_t reg_gpa,
uint64_t reg_size)
{
uint64_t hva_ring_offset;
uint64_t ring_last = range_get_last(ring_gpa, ring_size);
uint64_t reg_last = range_get_last(reg_gpa, reg_size);
if (ring_last < reg_gpa || ring_gpa > reg_last) {
return 0;
}
/* check that whole ring's is mapped */
if (ring_last > reg_last) {
return -ENOMEM;
}
/* check that ring's MemoryRegion wasn't replaced */
hva_ring_offset = ring_gpa - reg_gpa;
if (ring_hva != reg_hva + hva_ring_offset) {
return -EBUSY;
}
return 0;
}
static int vhost_verify_ring_mappings(struct vhost_dev *dev,
void *reg_hva,
uint64_t reg_gpa,
uint64_t reg_size)
{
int i, j;
int r = 0;
const char *part_name[] = {
"descriptor table",
"available ring",
"used ring"
};
if (vhost_dev_has_iommu(dev)) {
return 0;
}
for (i = 0; i < dev->nvqs; ++i) {
struct vhost_virtqueue *vq = dev->vqs + i;
if (vq->desc_phys == 0) {
continue;
}
j = 0;
r = vhost_verify_ring_part_mapping(
vq->desc, vq->desc_phys, vq->desc_size,
reg_hva, reg_gpa, reg_size);
if (r) {
break;
}
j++;
r = vhost_verify_ring_part_mapping(
vq->avail, vq->avail_phys, vq->avail_size,
reg_hva, reg_gpa, reg_size);
if (r) {
break;
}
j++;
r = vhost_verify_ring_part_mapping(
vq->used, vq->used_phys, vq->used_size,
reg_hva, reg_gpa, reg_size);
if (r) {
break;
}
}
if (r == -ENOMEM) {
error_report("Unable to map %s for ring %d", part_name[j], i);
} else if (r == -EBUSY) {
error_report("%s relocated for ring %d", part_name[j], i);
}
return r;
}
/*
* vhost_section: identify sections needed for vhost access
*
* We only care about RAM sections here (where virtqueue and guest
* internals accessed by virtio might live). If we find one we still
* allow the backend to potentially filter it out of our list.
*/
static bool vhost_section(struct vhost_dev *dev, MemoryRegionSection *section)
{
MemoryRegion *mr = section->mr;
if (memory_region_is_ram(mr) && !memory_region_is_rom(mr)) {
uint8_t dirty_mask = memory_region_get_dirty_log_mask(mr);
uint8_t handled_dirty;
/*
* Kernel based vhost doesn't handle any block which is doing
* dirty-tracking other than migration for which it has
* specific logging support. However for TCG the kernel never
* gets involved anyway so we can also ignore it's
* self-modiying code detection flags. However a vhost-user
* client could still confuse a TCG guest if it re-writes
* executable memory that has already been translated.
*/
handled_dirty = (1 << DIRTY_MEMORY_MIGRATION) |
(1 << DIRTY_MEMORY_CODE);
if (dirty_mask & ~handled_dirty) {
trace_vhost_reject_section(mr->name, 1);
return false;
}
if (dev->vhost_ops->vhost_backend_mem_section_filter &&
!dev->vhost_ops->vhost_backend_mem_section_filter(dev, section)) {
trace_vhost_reject_section(mr->name, 2);
return false;
}
trace_vhost_section(mr->name);
return true;
} else {
trace_vhost_reject_section(mr->name, 3);
return false;
}
}
static void vhost_begin(MemoryListener *listener)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
memory_listener);
dev->tmp_sections = NULL;
dev->n_tmp_sections = 0;
}
static void vhost_commit(MemoryListener *listener)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
memory_listener);
MemoryRegionSection *old_sections;
int n_old_sections;
uint64_t log_size;
size_t regions_size;
int r;
int i;
bool changed = false;
/* Note we can be called before the device is started, but then
* starting the device calls set_mem_table, so we need to have
* built the data structures.
*/
old_sections = dev->mem_sections;
n_old_sections = dev->n_mem_sections;
dev->mem_sections = dev->tmp_sections;
dev->n_mem_sections = dev->n_tmp_sections;
if (dev->n_mem_sections != n_old_sections) {
changed = true;
} else {
/* Same size, lets check the contents */
for (int i = 0; i < n_old_sections; i++) {
if (!MemoryRegionSection_eq(&old_sections[i],
&dev->mem_sections[i])) {
changed = true;
break;
}
}
}
trace_vhost_commit(dev->started, changed);
if (!changed) {
goto out;
}
/* Rebuild the regions list from the new sections list */
regions_size = offsetof(struct vhost_memory, regions) +
dev->n_mem_sections * sizeof dev->mem->regions[0];
dev->mem = g_realloc(dev->mem, regions_size);
dev->mem->nregions = dev->n_mem_sections;
used_memslots = dev->mem->nregions;
for (i = 0; i < dev->n_mem_sections; i++) {
struct vhost_memory_region *cur_vmr = dev->mem->regions + i;
struct MemoryRegionSection *mrs = dev->mem_sections + i;
cur_vmr->guest_phys_addr = mrs->offset_within_address_space;
cur_vmr->memory_size = int128_get64(mrs->size);
cur_vmr->userspace_addr =
(uintptr_t)memory_region_get_ram_ptr(mrs->mr) +
mrs->offset_within_region;
cur_vmr->flags_padding = 0;
}
if (!dev->started) {
goto out;
}
for (i = 0; i < dev->mem->nregions; i++) {
if (vhost_verify_ring_mappings(dev,
(void *)(uintptr_t)dev->mem->regions[i].userspace_addr,
dev->mem->regions[i].guest_phys_addr,
dev->mem->regions[i].memory_size)) {
error_report("Verify ring failure on region %d", i);
abort();
}
}
if (!dev->log_enabled) {
r = dev->vhost_ops->vhost_set_mem_table(dev, dev->mem);
if (r < 0) {
VHOST_OPS_DEBUG(r, "vhost_set_mem_table failed");
}
goto out;
}
log_size = vhost_get_log_size(dev);
/* We allocate an extra 4K bytes to log,
* to reduce the * number of reallocations. */
#define VHOST_LOG_BUFFER (0x1000 / sizeof *dev->log)
/* To log more, must increase log size before table update. */
if (dev->log_size < log_size) {
vhost_dev_log_resize(dev, log_size + VHOST_LOG_BUFFER);
}
r = dev->vhost_ops->vhost_set_mem_table(dev, dev->mem);
if (r < 0) {
VHOST_OPS_DEBUG(r, "vhost_set_mem_table failed");
}
/* To log less, can only decrease log size after table update. */
if (dev->log_size > log_size + VHOST_LOG_BUFFER) {
vhost_dev_log_resize(dev, log_size);
}
out:
/* Deref the old list of sections, this must happen _after_ the
* vhost_set_mem_table to ensure the client isn't still using the
* section we're about to unref.
*/
while (n_old_sections--) {
memory_region_unref(old_sections[n_old_sections].mr);
}
g_free(old_sections);
return;
}
/* Adds the section data to the tmp_section structure.
* It relies on the listener calling us in memory address order
* and for each region (via the _add and _nop methods) to
* join neighbours.
*/
static void vhost_region_add_section(struct vhost_dev *dev,
MemoryRegionSection *section)
{
bool need_add = true;
uint64_t mrs_size = int128_get64(section->size);
uint64_t mrs_gpa = section->offset_within_address_space;
uintptr_t mrs_host = (uintptr_t)memory_region_get_ram_ptr(section->mr) +
section->offset_within_region;
RAMBlock *mrs_rb = section->mr->ram_block;
trace_vhost_region_add_section(section->mr->name, mrs_gpa, mrs_size,
mrs_host);
if (dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_USER) {
/* Round the section to it's page size */
/* First align the start down to a page boundary */
size_t mrs_page = qemu_ram_pagesize(mrs_rb);
uint64_t alignage = mrs_host & (mrs_page - 1);
if (alignage) {
mrs_host -= alignage;
mrs_size += alignage;
mrs_gpa -= alignage;
}
/* Now align the size up to a page boundary */
alignage = mrs_size & (mrs_page - 1);
if (alignage) {
mrs_size += mrs_page - alignage;
}
trace_vhost_region_add_section_aligned(section->mr->name, mrs_gpa,
mrs_size, mrs_host);
}
if (dev->n_tmp_sections) {
/* Since we already have at least one section, lets see if
* this extends it; since we're scanning in order, we only
* have to look at the last one, and the FlatView that calls
* us shouldn't have overlaps.
*/
MemoryRegionSection *prev_sec = dev->tmp_sections +
(dev->n_tmp_sections - 1);
uint64_t prev_gpa_start = prev_sec->offset_within_address_space;
uint64_t prev_size = int128_get64(prev_sec->size);
uint64_t prev_gpa_end = range_get_last(prev_gpa_start, prev_size);
uint64_t prev_host_start =
(uintptr_t)memory_region_get_ram_ptr(prev_sec->mr) +
prev_sec->offset_within_region;
uint64_t prev_host_end = range_get_last(prev_host_start, prev_size);
if (mrs_gpa <= (prev_gpa_end + 1)) {
/* OK, looks like overlapping/intersecting - it's possible that
* the rounding to page sizes has made them overlap, but they should
* match up in the same RAMBlock if they do.
*/
if (mrs_gpa < prev_gpa_start) {
error_report("%s:Section '%s' rounded to %"PRIx64
" prior to previous '%s' %"PRIx64,
__func__, section->mr->name, mrs_gpa,
prev_sec->mr->name, prev_gpa_start);
/* A way to cleanly fail here would be better */
return;
}
/* Offset from the start of the previous GPA to this GPA */
size_t offset = mrs_gpa - prev_gpa_start;
if (prev_host_start + offset == mrs_host &&
section->mr == prev_sec->mr &&
(!dev->vhost_ops->vhost_backend_can_merge ||
dev->vhost_ops->vhost_backend_can_merge(dev,
mrs_host, mrs_size,
prev_host_start, prev_size))) {
uint64_t max_end = MAX(prev_host_end, mrs_host + mrs_size);
need_add = false;
prev_sec->offset_within_address_space =
MIN(prev_gpa_start, mrs_gpa);
prev_sec->offset_within_region =
MIN(prev_host_start, mrs_host) -
(uintptr_t)memory_region_get_ram_ptr(prev_sec->mr);
prev_sec->size = int128_make64(max_end - MIN(prev_host_start,
mrs_host));
trace_vhost_region_add_section_merge(section->mr->name,
int128_get64(prev_sec->size),
prev_sec->offset_within_address_space,
prev_sec->offset_within_region);
} else {
/* adjoining regions are fine, but overlapping ones with
* different blocks/offsets shouldn't happen
*/
if (mrs_gpa != prev_gpa_end + 1) {
error_report("%s: Overlapping but not coherent sections "
"at %"PRIx64,
__func__, mrs_gpa);
return;
}
}
}
}
if (need_add) {
++dev->n_tmp_sections;
dev->tmp_sections = g_renew(MemoryRegionSection, dev->tmp_sections,
dev->n_tmp_sections);
dev->tmp_sections[dev->n_tmp_sections - 1] = *section;
/* The flatview isn't stable and we don't use it, making it NULL
* means we can memcmp the list.
*/
dev->tmp_sections[dev->n_tmp_sections - 1].fv = NULL;
memory_region_ref(section->mr);
}
}
/* Used for both add and nop callbacks */
static void vhost_region_addnop(MemoryListener *listener,
MemoryRegionSection *section)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
memory_listener);
if (!vhost_section(dev, section)) {
return;
}
vhost_region_add_section(dev, section);
}
static void vhost_iommu_unmap_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
{
struct vhost_iommu *iommu = container_of(n, struct vhost_iommu, n);
struct vhost_dev *hdev = iommu->hdev;
hwaddr iova = iotlb->iova + iommu->iommu_offset;
if (vhost_backend_invalidate_device_iotlb(hdev, iova,
iotlb->addr_mask + 1)) {
error_report("Fail to invalidate device iotlb");
}
}
static void vhost_iommu_region_add(MemoryListener *listener,
MemoryRegionSection *section)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
iommu_listener);
struct vhost_iommu *iommu;
Int128 end;
int iommu_idx;
IOMMUMemoryRegion *iommu_mr;
if (!memory_region_is_iommu(section->mr)) {
return;
}
iommu_mr = IOMMU_MEMORY_REGION(section->mr);
iommu = g_malloc0(sizeof(*iommu));
end = int128_add(int128_make64(section->offset_within_region),
section->size);
end = int128_sub(end, int128_one());
iommu_idx = memory_region_iommu_attrs_to_index(iommu_mr,
MEMTXATTRS_UNSPECIFIED);
iommu_notifier_init(&iommu->n, vhost_iommu_unmap_notify,
dev->vdev->device_iotlb_enabled ?
IOMMU_NOTIFIER_DEVIOTLB_UNMAP :
IOMMU_NOTIFIER_UNMAP,
section->offset_within_region,
int128_get64(end),
iommu_idx);
iommu->mr = section->mr;
iommu->iommu_offset = section->offset_within_address_space -
section->offset_within_region;
iommu->hdev = dev;
memory_region_register_iommu_notifier(section->mr, &iommu->n,
&error_fatal);
QLIST_INSERT_HEAD(&dev->iommu_list, iommu, iommu_next);
/* TODO: can replay help performance here? */
}
static void vhost_iommu_region_del(MemoryListener *listener,
MemoryRegionSection *section)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
iommu_listener);
struct vhost_iommu *iommu;
if (!memory_region_is_iommu(section->mr)) {
return;
}
QLIST_FOREACH(iommu, &dev->iommu_list, iommu_next) {
if (iommu->mr == section->mr &&
iommu->n.start == section->offset_within_region) {
memory_region_unregister_iommu_notifier(iommu->mr,
&iommu->n);
QLIST_REMOVE(iommu, iommu_next);
g_free(iommu);
break;
}
}
}
void vhost_toggle_device_iotlb(VirtIODevice *vdev)
{
VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev);
struct vhost_dev *dev;
struct vhost_iommu *iommu;
if (vdev->vhost_started) {
dev = vdc->get_vhost(vdev);
} else {
return;
}
QLIST_FOREACH(iommu, &dev->iommu_list, iommu_next) {
memory_region_unregister_iommu_notifier(iommu->mr, &iommu->n);
iommu->n.notifier_flags = vdev->device_iotlb_enabled ?
IOMMU_NOTIFIER_DEVIOTLB_UNMAP : IOMMU_NOTIFIER_UNMAP;
memory_region_register_iommu_notifier(iommu->mr, &iommu->n,
&error_fatal);
}
}
static int vhost_virtqueue_set_addr(struct vhost_dev *dev,
struct vhost_virtqueue *vq,
unsigned idx, bool enable_log)
{
struct vhost_vring_addr addr;
int r;
memset(&addr, 0, sizeof(struct vhost_vring_addr));
if (dev->vhost_ops->vhost_vq_get_addr) {
r = dev->vhost_ops->vhost_vq_get_addr(dev, &addr, vq);
if (r < 0) {
VHOST_OPS_DEBUG(r, "vhost_vq_get_addr failed");
return r;
}
} else {
addr.desc_user_addr = (uint64_t)(unsigned long)vq->desc;
addr.avail_user_addr = (uint64_t)(unsigned long)vq->avail;
addr.used_user_addr = (uint64_t)(unsigned long)vq->used;
}
addr.index = idx;
addr.log_guest_addr = vq->used_phys;
addr.flags = enable_log ? (1 << VHOST_VRING_F_LOG) : 0;
r = dev->vhost_ops->vhost_set_vring_addr(dev, &addr);
if (r < 0) {
VHOST_OPS_DEBUG(r, "vhost_set_vring_addr failed");
}
return r;
}
static int vhost_dev_set_features(struct vhost_dev *dev,
bool enable_log)
{
uint64_t features = dev->acked_features;
int r;
if (enable_log) {
features |= 0x1ULL << VHOST_F_LOG_ALL;
}
if (!vhost_dev_has_iommu(dev)) {
features &= ~(0x1ULL << VIRTIO_F_IOMMU_PLATFORM);
}
if (dev->vhost_ops->vhost_force_iommu) {
if (dev->vhost_ops->vhost_force_iommu(dev) == true) {
features |= 0x1ULL << VIRTIO_F_IOMMU_PLATFORM;
}
}
r = dev->vhost_ops->vhost_set_features(dev, features);
if (r < 0) {
VHOST_OPS_DEBUG(r, "vhost_set_features failed");
goto out;
}
if (dev->vhost_ops->vhost_set_backend_cap) {
r = dev->vhost_ops->vhost_set_backend_cap(dev);
if (r < 0) {
VHOST_OPS_DEBUG(r, "vhost_set_backend_cap failed");
goto out;
}
}
out:
return r;
}
static int vhost_dev_set_log(struct vhost_dev *dev, bool enable_log)
{
int r, i, idx;
hwaddr addr;
r = vhost_dev_set_features(dev, enable_log);
if (r < 0) {
goto err_features;
}
for (i = 0; i < dev->nvqs; ++i) {
idx = dev->vhost_ops->vhost_get_vq_index(dev, dev->vq_index + i);
addr = virtio_queue_get_desc_addr(dev->vdev, idx);
if (!addr) {
/*
* The queue might not be ready for start. If this
* is the case there is no reason to continue the process.
* The similar logic is used by the vhost_virtqueue_start()
* routine.
*/
continue;
}
r = vhost_virtqueue_set_addr(dev, dev->vqs + i, idx,
enable_log);
if (r < 0) {
goto err_vq;
}
}
return 0;
err_vq:
for (; i >= 0; --i) {
idx = dev->vhost_ops->vhost_get_vq_index(dev, dev->vq_index + i);
addr = virtio_queue_get_desc_addr(dev->vdev, idx);
if (!addr) {
continue;
}
vhost_virtqueue_set_addr(dev, dev->vqs + i, idx,
dev->log_enabled);
}
vhost_dev_set_features(dev, dev->log_enabled);
err_features:
return r;
}
static int vhost_migration_log(MemoryListener *listener, bool enable)
{
struct vhost_dev *dev = container_of(listener, struct vhost_dev,
memory_listener);
int r;
if (enable == dev->log_enabled) {
return 0;
}
if (!dev->started) {
dev->log_enabled = enable;
return 0;
}
r = 0;
if (!enable) {
r = vhost_dev_set_log(dev, false);
if (r < 0) {
goto check_dev_state;
}
vhost_log_put(dev, false);
} else {
vhost_dev_log_resize(dev, vhost_get_log_size(dev));
r = vhost_dev_set_log(dev, true);
if (r < 0) {
goto check_dev_state;
}
}
check_dev_state:
dev->log_enabled = enable;
/*
* vhost-user-* devices could change their state during log
* initialization due to disconnect. So check dev state after
* vhost communication.
*/
if (!dev->started) {
/*
* Since device is in the stopped state, it is okay for
* migration. Return success.