-
Notifications
You must be signed in to change notification settings - Fork 0
/
qed.c
1652 lines (1419 loc) · 48.3 KB
/
qed.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
/*
* QEMU Enhanced Disk Format
*
* Copyright IBM, Corp. 2010
*
* Authors:
* Stefan Hajnoczi <[email protected]>
* Anthony Liguori <[email protected]>
*
* This work is licensed under the terms of the GNU LGPL, version 2 or later.
* See the COPYING.LIB file in the top-level directory.
*
*/
#include "qemu/osdep.h"
#include "block/qdict.h"
#include "qapi/error.h"
#include "qemu/timer.h"
#include "qemu/bswap.h"
#include "qemu/main-loop.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/memalign.h"
#include "trace.h"
#include "qed.h"
#include "sysemu/block-backend.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qobject-input-visitor.h"
#include "qapi/qapi-visit-block-core.h"
static QemuOptsList qed_create_opts;
static int bdrv_qed_probe(const uint8_t *buf, int buf_size,
const char *filename)
{
const QEDHeader *header = (const QEDHeader *)buf;
if (buf_size < sizeof(*header)) {
return 0;
}
if (le32_to_cpu(header->magic) != QED_MAGIC) {
return 0;
}
return 100;
}
/**
* Check whether an image format is raw
*
* @fmt: Backing file format, may be NULL
*/
static bool qed_fmt_is_raw(const char *fmt)
{
return fmt && strcmp(fmt, "raw") == 0;
}
static void qed_header_le_to_cpu(const QEDHeader *le, QEDHeader *cpu)
{
cpu->magic = le32_to_cpu(le->magic);
cpu->cluster_size = le32_to_cpu(le->cluster_size);
cpu->table_size = le32_to_cpu(le->table_size);
cpu->header_size = le32_to_cpu(le->header_size);
cpu->features = le64_to_cpu(le->features);
cpu->compat_features = le64_to_cpu(le->compat_features);
cpu->autoclear_features = le64_to_cpu(le->autoclear_features);
cpu->l1_table_offset = le64_to_cpu(le->l1_table_offset);
cpu->image_size = le64_to_cpu(le->image_size);
cpu->backing_filename_offset = le32_to_cpu(le->backing_filename_offset);
cpu->backing_filename_size = le32_to_cpu(le->backing_filename_size);
}
static void qed_header_cpu_to_le(const QEDHeader *cpu, QEDHeader *le)
{
le->magic = cpu_to_le32(cpu->magic);
le->cluster_size = cpu_to_le32(cpu->cluster_size);
le->table_size = cpu_to_le32(cpu->table_size);
le->header_size = cpu_to_le32(cpu->header_size);
le->features = cpu_to_le64(cpu->features);
le->compat_features = cpu_to_le64(cpu->compat_features);
le->autoclear_features = cpu_to_le64(cpu->autoclear_features);
le->l1_table_offset = cpu_to_le64(cpu->l1_table_offset);
le->image_size = cpu_to_le64(cpu->image_size);
le->backing_filename_offset = cpu_to_le32(cpu->backing_filename_offset);
le->backing_filename_size = cpu_to_le32(cpu->backing_filename_size);
}
int qed_write_header_sync(BDRVQEDState *s)
{
QEDHeader le;
qed_header_cpu_to_le(&s->header, &le);
return bdrv_pwrite(s->bs->file, 0, sizeof(le), &le, 0);
}
/**
* Update header in-place (does not rewrite backing filename or other strings)
*
* This function only updates known header fields in-place and does not affect
* extra data after the QED header.
*
* No new allocating reqs can start while this function runs.
*/
static int coroutine_fn qed_write_header(BDRVQEDState *s)
{
/* We must write full sectors for O_DIRECT but cannot necessarily generate
* the data following the header if an unrecognized compat feature is
* active. Therefore, first read the sectors containing the header, update
* them, and write back.
*/
int nsectors = DIV_ROUND_UP(sizeof(QEDHeader), BDRV_SECTOR_SIZE);
size_t len = nsectors * BDRV_SECTOR_SIZE;
uint8_t *buf;
int ret;
assert(s->allocating_acb || s->allocating_write_reqs_plugged);
buf = qemu_blockalign(s->bs, len);
ret = bdrv_co_pread(s->bs->file, 0, len, buf, 0);
if (ret < 0) {
goto out;
}
/* Update header */
qed_header_cpu_to_le(&s->header, (QEDHeader *) buf);
ret = bdrv_co_pwrite(s->bs->file, 0, len, buf, 0);
if (ret < 0) {
goto out;
}
ret = 0;
out:
qemu_vfree(buf);
return ret;
}
static uint64_t qed_max_image_size(uint32_t cluster_size, uint32_t table_size)
{
uint64_t table_entries;
uint64_t l2_size;
table_entries = (table_size * cluster_size) / sizeof(uint64_t);
l2_size = table_entries * cluster_size;
return l2_size * table_entries;
}
static bool qed_is_cluster_size_valid(uint32_t cluster_size)
{
if (cluster_size < QED_MIN_CLUSTER_SIZE ||
cluster_size > QED_MAX_CLUSTER_SIZE) {
return false;
}
if (cluster_size & (cluster_size - 1)) {
return false; /* not power of 2 */
}
return true;
}
static bool qed_is_table_size_valid(uint32_t table_size)
{
if (table_size < QED_MIN_TABLE_SIZE ||
table_size > QED_MAX_TABLE_SIZE) {
return false;
}
if (table_size & (table_size - 1)) {
return false; /* not power of 2 */
}
return true;
}
static bool qed_is_image_size_valid(uint64_t image_size, uint32_t cluster_size,
uint32_t table_size)
{
if (image_size % BDRV_SECTOR_SIZE != 0) {
return false; /* not multiple of sector size */
}
if (image_size > qed_max_image_size(cluster_size, table_size)) {
return false; /* image is too large */
}
return true;
}
/**
* Read a string of known length from the image file
*
* @file: Image file
* @offset: File offset to start of string, in bytes
* @n: String length in bytes
* @buf: Destination buffer
* @buflen: Destination buffer length in bytes
* @ret: 0 on success, -errno on failure
*
* The string is NUL-terminated.
*/
static int qed_read_string(BdrvChild *file, uint64_t offset, size_t n,
char *buf, size_t buflen)
{
int ret;
if (n >= buflen) {
return -EINVAL;
}
ret = bdrv_pread(file, offset, n, buf, 0);
if (ret < 0) {
return ret;
}
buf[n] = '\0';
return 0;
}
/**
* Allocate new clusters
*
* @s: QED state
* @n: Number of contiguous clusters to allocate
* @ret: Offset of first allocated cluster
*
* This function only produces the offset where the new clusters should be
* written. It updates BDRVQEDState but does not make any changes to the image
* file.
*
* Called with table_lock held.
*/
static uint64_t qed_alloc_clusters(BDRVQEDState *s, unsigned int n)
{
uint64_t offset = s->file_size;
s->file_size += n * s->header.cluster_size;
return offset;
}
QEDTable *qed_alloc_table(BDRVQEDState *s)
{
/* Honor O_DIRECT memory alignment requirements */
return qemu_blockalign(s->bs,
s->header.cluster_size * s->header.table_size);
}
/**
* Allocate a new zeroed L2 table
*
* Called with table_lock held.
*/
static CachedL2Table *qed_new_l2_table(BDRVQEDState *s)
{
CachedL2Table *l2_table = qed_alloc_l2_cache_entry(&s->l2_cache);
l2_table->table = qed_alloc_table(s);
l2_table->offset = qed_alloc_clusters(s, s->header.table_size);
memset(l2_table->table->offsets, 0,
s->header.cluster_size * s->header.table_size);
return l2_table;
}
static bool qed_plug_allocating_write_reqs(BDRVQEDState *s)
{
qemu_co_mutex_lock(&s->table_lock);
/* No reentrancy is allowed. */
assert(!s->allocating_write_reqs_plugged);
if (s->allocating_acb != NULL) {
/* Another allocating write came concurrently. This cannot happen
* from bdrv_qed_co_drain_begin, but it can happen when the timer runs.
*/
qemu_co_mutex_unlock(&s->table_lock);
return false;
}
s->allocating_write_reqs_plugged = true;
qemu_co_mutex_unlock(&s->table_lock);
return true;
}
static void qed_unplug_allocating_write_reqs(BDRVQEDState *s)
{
qemu_co_mutex_lock(&s->table_lock);
assert(s->allocating_write_reqs_plugged);
s->allocating_write_reqs_plugged = false;
qemu_co_queue_next(&s->allocating_write_reqs);
qemu_co_mutex_unlock(&s->table_lock);
}
static void coroutine_fn qed_need_check_timer_entry(void *opaque)
{
BDRVQEDState *s = opaque;
int ret;
trace_qed_need_check_timer_cb(s);
if (!qed_plug_allocating_write_reqs(s)) {
return;
}
/* Ensure writes are on disk before clearing flag */
ret = bdrv_co_flush(s->bs->file->bs);
if (ret < 0) {
qed_unplug_allocating_write_reqs(s);
return;
}
s->header.features &= ~QED_F_NEED_CHECK;
ret = qed_write_header(s);
(void) ret;
qed_unplug_allocating_write_reqs(s);
ret = bdrv_co_flush(s->bs);
(void) ret;
}
static void qed_need_check_timer_cb(void *opaque)
{
Coroutine *co = qemu_coroutine_create(qed_need_check_timer_entry, opaque);
qemu_coroutine_enter(co);
}
static void qed_start_need_check_timer(BDRVQEDState *s)
{
trace_qed_start_need_check_timer(s);
/* Use QEMU_CLOCK_VIRTUAL so we don't alter the image file while suspended for
* migration.
*/
timer_mod(s->need_check_timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) +
NANOSECONDS_PER_SECOND * QED_NEED_CHECK_TIMEOUT);
}
/* It's okay to call this multiple times or when no timer is started */
static void qed_cancel_need_check_timer(BDRVQEDState *s)
{
trace_qed_cancel_need_check_timer(s);
timer_del(s->need_check_timer);
}
static void bdrv_qed_detach_aio_context(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
qed_cancel_need_check_timer(s);
timer_free(s->need_check_timer);
}
static void bdrv_qed_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
BDRVQEDState *s = bs->opaque;
s->need_check_timer = aio_timer_new(new_context,
QEMU_CLOCK_VIRTUAL, SCALE_NS,
qed_need_check_timer_cb, s);
if (s->header.features & QED_F_NEED_CHECK) {
qed_start_need_check_timer(s);
}
}
static void coroutine_fn bdrv_qed_co_drain_begin(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
/* Fire the timer immediately in order to start doing I/O as soon as the
* header is flushed.
*/
if (s->need_check_timer && timer_pending(s->need_check_timer)) {
qed_cancel_need_check_timer(s);
qed_need_check_timer_entry(s);
}
}
static void bdrv_qed_init_state(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
memset(s, 0, sizeof(BDRVQEDState));
s->bs = bs;
qemu_co_mutex_init(&s->table_lock);
qemu_co_queue_init(&s->allocating_write_reqs);
}
/* Called with table_lock held. */
static int coroutine_fn bdrv_qed_do_open(BlockDriverState *bs, QDict *options,
int flags, Error **errp)
{
BDRVQEDState *s = bs->opaque;
QEDHeader le_header;
int64_t file_size;
int ret;
ret = bdrv_pread(bs->file, 0, sizeof(le_header), &le_header, 0);
if (ret < 0) {
error_setg(errp, "Failed to read QED header");
return ret;
}
qed_header_le_to_cpu(&le_header, &s->header);
if (s->header.magic != QED_MAGIC) {
error_setg(errp, "Image not in QED format");
return -EINVAL;
}
if (s->header.features & ~QED_FEATURE_MASK) {
/* image uses unsupported feature bits */
error_setg(errp, "Unsupported QED features: %" PRIx64,
s->header.features & ~QED_FEATURE_MASK);
return -ENOTSUP;
}
if (!qed_is_cluster_size_valid(s->header.cluster_size)) {
error_setg(errp, "QED cluster size is invalid");
return -EINVAL;
}
/* Round down file size to the last cluster */
file_size = bdrv_getlength(bs->file->bs);
if (file_size < 0) {
error_setg(errp, "Failed to get file length");
return file_size;
}
s->file_size = qed_start_of_cluster(s, file_size);
if (!qed_is_table_size_valid(s->header.table_size)) {
error_setg(errp, "QED table size is invalid");
return -EINVAL;
}
if (!qed_is_image_size_valid(s->header.image_size,
s->header.cluster_size,
s->header.table_size)) {
error_setg(errp, "QED image size is invalid");
return -EINVAL;
}
if (!qed_check_table_offset(s, s->header.l1_table_offset)) {
error_setg(errp, "QED table offset is invalid");
return -EINVAL;
}
s->table_nelems = (s->header.cluster_size * s->header.table_size) /
sizeof(uint64_t);
s->l2_shift = ctz32(s->header.cluster_size);
s->l2_mask = s->table_nelems - 1;
s->l1_shift = s->l2_shift + ctz32(s->table_nelems);
/* Header size calculation must not overflow uint32_t */
if (s->header.header_size > UINT32_MAX / s->header.cluster_size) {
error_setg(errp, "QED header size is too large");
return -EINVAL;
}
if ((s->header.features & QED_F_BACKING_FILE)) {
if ((uint64_t)s->header.backing_filename_offset +
s->header.backing_filename_size >
s->header.cluster_size * s->header.header_size) {
error_setg(errp, "QED backing filename offset is invalid");
return -EINVAL;
}
ret = qed_read_string(bs->file, s->header.backing_filename_offset,
s->header.backing_filename_size,
bs->auto_backing_file,
sizeof(bs->auto_backing_file));
if (ret < 0) {
error_setg(errp, "Failed to read backing filename");
return ret;
}
pstrcpy(bs->backing_file, sizeof(bs->backing_file),
bs->auto_backing_file);
if (s->header.features & QED_F_BACKING_FORMAT_NO_PROBE) {
pstrcpy(bs->backing_format, sizeof(bs->backing_format), "raw");
}
}
/* Reset unknown autoclear feature bits. This is a backwards
* compatibility mechanism that allows images to be opened by older
* programs, which "knock out" unknown feature bits. When an image is
* opened by a newer program again it can detect that the autoclear
* feature is no longer valid.
*/
if ((s->header.autoclear_features & ~QED_AUTOCLEAR_FEATURE_MASK) != 0 &&
!bdrv_is_read_only(bs->file->bs) && !(flags & BDRV_O_INACTIVE)) {
s->header.autoclear_features &= QED_AUTOCLEAR_FEATURE_MASK;
ret = qed_write_header_sync(s);
if (ret) {
error_setg(errp, "Failed to update header");
return ret;
}
/* From here on only known autoclear feature bits are valid */
bdrv_flush(bs->file->bs);
}
s->l1_table = qed_alloc_table(s);
qed_init_l2_cache(&s->l2_cache);
ret = qed_read_l1_table_sync(s);
if (ret) {
error_setg(errp, "Failed to read L1 table");
goto out;
}
/* If image was not closed cleanly, check consistency */
if (!(flags & BDRV_O_CHECK) && (s->header.features & QED_F_NEED_CHECK)) {
/* Read-only images cannot be fixed. There is no risk of corruption
* since write operations are not possible. Therefore, allow
* potentially inconsistent images to be opened read-only. This can
* aid data recovery from an otherwise inconsistent image.
*/
if (!bdrv_is_read_only(bs->file->bs) &&
!(flags & BDRV_O_INACTIVE)) {
BdrvCheckResult result = {0};
ret = qed_check(s, &result, true);
if (ret) {
error_setg(errp, "Image corrupted");
goto out;
}
}
}
bdrv_qed_attach_aio_context(bs, bdrv_get_aio_context(bs));
out:
if (ret) {
qed_free_l2_cache(&s->l2_cache);
qemu_vfree(s->l1_table);
}
return ret;
}
typedef struct QEDOpenCo {
BlockDriverState *bs;
QDict *options;
int flags;
Error **errp;
int ret;
} QEDOpenCo;
static void coroutine_fn bdrv_qed_open_entry(void *opaque)
{
QEDOpenCo *qoc = opaque;
BDRVQEDState *s = qoc->bs->opaque;
qemu_co_mutex_lock(&s->table_lock);
qoc->ret = bdrv_qed_do_open(qoc->bs, qoc->options, qoc->flags, qoc->errp);
qemu_co_mutex_unlock(&s->table_lock);
}
static int bdrv_qed_open(BlockDriverState *bs, QDict *options, int flags,
Error **errp)
{
QEDOpenCo qoc = {
.bs = bs,
.options = options,
.flags = flags,
.errp = errp,
.ret = -EINPROGRESS
};
bs->file = bdrv_open_child(NULL, options, "file", bs, &child_of_bds,
BDRV_CHILD_IMAGE, false, errp);
if (!bs->file) {
return -EINVAL;
}
bdrv_qed_init_state(bs);
if (qemu_in_coroutine()) {
bdrv_qed_open_entry(&qoc);
} else {
assert(qemu_get_current_aio_context() == qemu_get_aio_context());
qemu_coroutine_enter(qemu_coroutine_create(bdrv_qed_open_entry, &qoc));
BDRV_POLL_WHILE(bs, qoc.ret == -EINPROGRESS);
}
BDRV_POLL_WHILE(bs, qoc.ret == -EINPROGRESS);
return qoc.ret;
}
static void bdrv_qed_refresh_limits(BlockDriverState *bs, Error **errp)
{
BDRVQEDState *s = bs->opaque;
bs->bl.pwrite_zeroes_alignment = s->header.cluster_size;
bs->bl.max_pwrite_zeroes = QEMU_ALIGN_DOWN(INT_MAX, s->header.cluster_size);
}
/* We have nothing to do for QED reopen, stubs just return
* success */
static int bdrv_qed_reopen_prepare(BDRVReopenState *state,
BlockReopenQueue *queue, Error **errp)
{
return 0;
}
static void bdrv_qed_close(BlockDriverState *bs)
{
BDRVQEDState *s = bs->opaque;
bdrv_qed_detach_aio_context(bs);
/* Ensure writes reach stable storage */
bdrv_flush(bs->file->bs);
/* Clean shutdown, no check required on next open */
if (s->header.features & QED_F_NEED_CHECK) {
s->header.features &= ~QED_F_NEED_CHECK;
qed_write_header_sync(s);
}
qed_free_l2_cache(&s->l2_cache);
qemu_vfree(s->l1_table);
}
static int coroutine_fn bdrv_qed_co_create(BlockdevCreateOptions *opts,
Error **errp)
{
BlockdevCreateOptionsQed *qed_opts;
BlockBackend *blk = NULL;
BlockDriverState *bs = NULL;
QEDHeader header;
QEDHeader le_header;
uint8_t *l1_table = NULL;
size_t l1_size;
int ret = 0;
assert(opts->driver == BLOCKDEV_DRIVER_QED);
qed_opts = &opts->u.qed;
/* Validate options and set default values */
if (!qed_opts->has_cluster_size) {
qed_opts->cluster_size = QED_DEFAULT_CLUSTER_SIZE;
}
if (!qed_opts->has_table_size) {
qed_opts->table_size = QED_DEFAULT_TABLE_SIZE;
}
if (!qed_is_cluster_size_valid(qed_opts->cluster_size)) {
error_setg(errp, "QED cluster size must be within range [%u, %u] "
"and power of 2",
QED_MIN_CLUSTER_SIZE, QED_MAX_CLUSTER_SIZE);
return -EINVAL;
}
if (!qed_is_table_size_valid(qed_opts->table_size)) {
error_setg(errp, "QED table size must be within range [%u, %u] "
"and power of 2",
QED_MIN_TABLE_SIZE, QED_MAX_TABLE_SIZE);
return -EINVAL;
}
if (!qed_is_image_size_valid(qed_opts->size, qed_opts->cluster_size,
qed_opts->table_size))
{
error_setg(errp, "QED image size must be a non-zero multiple of "
"cluster size and less than %" PRIu64 " bytes",
qed_max_image_size(qed_opts->cluster_size,
qed_opts->table_size));
return -EINVAL;
}
/* Create BlockBackend to write to the image */
bs = bdrv_open_blockdev_ref(qed_opts->file, errp);
if (bs == NULL) {
return -EIO;
}
blk = blk_new_with_bs(bs, BLK_PERM_WRITE | BLK_PERM_RESIZE, BLK_PERM_ALL,
errp);
if (!blk) {
ret = -EPERM;
goto out;
}
blk_set_allow_write_beyond_eof(blk, true);
/* Prepare image format */
header = (QEDHeader) {
.magic = QED_MAGIC,
.cluster_size = qed_opts->cluster_size,
.table_size = qed_opts->table_size,
.header_size = 1,
.features = 0,
.compat_features = 0,
.l1_table_offset = qed_opts->cluster_size,
.image_size = qed_opts->size,
};
l1_size = header.cluster_size * header.table_size;
/*
* The QED format associates file length with allocation status,
* so a new file (which is empty) must have a length of 0.
*/
ret = blk_truncate(blk, 0, true, PREALLOC_MODE_OFF, 0, errp);
if (ret < 0) {
goto out;
}
if (qed_opts->has_backing_file) {
header.features |= QED_F_BACKING_FILE;
header.backing_filename_offset = sizeof(le_header);
header.backing_filename_size = strlen(qed_opts->backing_file);
if (qed_opts->has_backing_fmt) {
const char *backing_fmt = BlockdevDriver_str(qed_opts->backing_fmt);
if (qed_fmt_is_raw(backing_fmt)) {
header.features |= QED_F_BACKING_FORMAT_NO_PROBE;
}
}
}
qed_header_cpu_to_le(&header, &le_header);
ret = blk_pwrite(blk, 0, sizeof(le_header), &le_header, 0);
if (ret < 0) {
goto out;
}
ret = blk_pwrite(blk, sizeof(le_header), header.backing_filename_size,
qed_opts->backing_file, 0);
if (ret < 0) {
goto out;
}
l1_table = g_malloc0(l1_size);
ret = blk_pwrite(blk, header.l1_table_offset, l1_size, l1_table, 0);
if (ret < 0) {
goto out;
}
ret = 0; /* success */
out:
g_free(l1_table);
blk_unref(blk);
bdrv_unref(bs);
return ret;
}
static int coroutine_fn bdrv_qed_co_create_opts(BlockDriver *drv,
const char *filename,
QemuOpts *opts,
Error **errp)
{
BlockdevCreateOptions *create_options = NULL;
QDict *qdict;
Visitor *v;
BlockDriverState *bs = NULL;
int ret;
static const QDictRenames opt_renames[] = {
{ BLOCK_OPT_BACKING_FILE, "backing-file" },
{ BLOCK_OPT_BACKING_FMT, "backing-fmt" },
{ BLOCK_OPT_CLUSTER_SIZE, "cluster-size" },
{ BLOCK_OPT_TABLE_SIZE, "table-size" },
{ NULL, NULL },
};
/* Parse options and convert legacy syntax */
qdict = qemu_opts_to_qdict_filtered(opts, NULL, &qed_create_opts, true);
if (!qdict_rename_keys(qdict, opt_renames, errp)) {
ret = -EINVAL;
goto fail;
}
/* Create and open the file (protocol layer) */
ret = bdrv_create_file(filename, opts, errp);
if (ret < 0) {
goto fail;
}
bs = bdrv_open(filename, NULL, NULL,
BDRV_O_RDWR | BDRV_O_RESIZE | BDRV_O_PROTOCOL, errp);
if (bs == NULL) {
ret = -EIO;
goto fail;
}
/* Now get the QAPI type BlockdevCreateOptions */
qdict_put_str(qdict, "driver", "qed");
qdict_put_str(qdict, "file", bs->node_name);
v = qobject_input_visitor_new_flat_confused(qdict, errp);
if (!v) {
ret = -EINVAL;
goto fail;
}
visit_type_BlockdevCreateOptions(v, NULL, &create_options, errp);
visit_free(v);
if (!create_options) {
ret = -EINVAL;
goto fail;
}
/* Silently round up size */
assert(create_options->driver == BLOCKDEV_DRIVER_QED);
create_options->u.qed.size =
ROUND_UP(create_options->u.qed.size, BDRV_SECTOR_SIZE);
/* Create the qed image (format layer) */
ret = bdrv_qed_co_create(create_options, errp);
fail:
qobject_unref(qdict);
bdrv_unref(bs);
qapi_free_BlockdevCreateOptions(create_options);
return ret;
}
static int coroutine_fn bdrv_qed_co_block_status(BlockDriverState *bs,
bool want_zero,
int64_t pos, int64_t bytes,
int64_t *pnum, int64_t *map,
BlockDriverState **file)
{
BDRVQEDState *s = bs->opaque;
size_t len = MIN(bytes, SIZE_MAX);
int status;
QEDRequest request = { .l2_table = NULL };
uint64_t offset;
int ret;
qemu_co_mutex_lock(&s->table_lock);
ret = qed_find_cluster(s, &request, pos, &len, &offset);
*pnum = len;
switch (ret) {
case QED_CLUSTER_FOUND:
*map = offset | qed_offset_into_cluster(s, pos);
status = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
*file = bs->file->bs;
break;
case QED_CLUSTER_ZERO:
status = BDRV_BLOCK_ZERO;
break;
case QED_CLUSTER_L2:
case QED_CLUSTER_L1:
status = 0;
break;
default:
assert(ret < 0);
status = ret;
break;
}
qed_unref_l2_cache_entry(request.l2_table);
qemu_co_mutex_unlock(&s->table_lock);
return status;
}
static BDRVQEDState *acb_to_s(QEDAIOCB *acb)
{
return acb->bs->opaque;
}
/**
* Read from the backing file or zero-fill if no backing file
*
* @s: QED state
* @pos: Byte position in device
* @qiov: Destination I/O vector
*
* This function reads qiov->size bytes starting at pos from the backing file.
* If there is no backing file then zeroes are read.
*/
static int coroutine_fn qed_read_backing_file(BDRVQEDState *s, uint64_t pos,
QEMUIOVector *qiov)
{
if (s->bs->backing) {
BLKDBG_EVENT(s->bs->file, BLKDBG_READ_BACKING_AIO);
return bdrv_co_preadv(s->bs->backing, pos, qiov->size, qiov, 0);
}
qemu_iovec_memset(qiov, 0, 0, qiov->size);
return 0;
}
/**
* Copy data from backing file into the image
*
* @s: QED state
* @pos: Byte position in device
* @len: Number of bytes
* @offset: Byte offset in image file
*/
static int coroutine_fn qed_copy_from_backing_file(BDRVQEDState *s,
uint64_t pos, uint64_t len,
uint64_t offset)
{
QEMUIOVector qiov;
int ret;
/* Skip copy entirely if there is no work to do */
if (len == 0) {
return 0;
}
qemu_iovec_init_buf(&qiov, qemu_blockalign(s->bs, len), len);
ret = qed_read_backing_file(s, pos, &qiov);
if (ret) {
goto out;
}
BLKDBG_EVENT(s->bs->file, BLKDBG_COW_WRITE);
ret = bdrv_co_pwritev(s->bs->file, offset, qiov.size, &qiov, 0);
if (ret < 0) {
goto out;
}
ret = 0;
out:
qemu_vfree(qemu_iovec_buf(&qiov));
return ret;
}
/**
* Link one or more contiguous clusters into a table
*
* @s: QED state
* @table: L2 table
* @index: First cluster index
* @n: Number of contiguous clusters
* @cluster: First cluster offset
*
* The cluster offset may be an allocated byte offset in the image file, the
* zero cluster marker, or the unallocated cluster marker.
*
* Called with table_lock held.
*/
static void coroutine_fn qed_update_l2_table(BDRVQEDState *s, QEDTable *table,
int index, unsigned int n,
uint64_t cluster)
{
int i;
for (i = index; i < index + n; i++) {
table->offsets[i] = cluster;
if (!qed_offset_is_unalloc_cluster(cluster) &&
!qed_offset_is_zero_cluster(cluster)) {
cluster += s->header.cluster_size;
}
}
}
/* Called with table_lock held. */
static void coroutine_fn qed_aio_complete(QEDAIOCB *acb)
{
BDRVQEDState *s = acb_to_s(acb);
/* Free resources */
qemu_iovec_destroy(&acb->cur_qiov);
qed_unref_l2_cache_entry(acb->request.l2_table);
/* Free the buffer we may have allocated for zero writes */
if (acb->flags & QED_AIOCB_ZERO) {
qemu_vfree(acb->qiov->iov[0].iov_base);
acb->qiov->iov[0].iov_base = NULL;
}
/* Start next allocating write request waiting behind this one. Note that
* requests enqueue themselves when they first hit an unallocated cluster
* but they wait until the entire request is finished before waking up the
* next request in the queue. This ensures that we don't cycle through
* requests multiple times but rather finish one at a time completely.
*/
if (acb == s->allocating_acb) {
s->allocating_acb = NULL;
if (!qemu_co_queue_empty(&s->allocating_write_reqs)) {
qemu_co_queue_next(&s->allocating_write_reqs);
} else if (s->header.features & QED_F_NEED_CHECK) {
qed_start_need_check_timer(s);
}
}
}
/**
* Update L1 table with new L2 table offset and write it out
*
* Called with table_lock held.
*/
static int coroutine_fn qed_aio_write_l1_update(QEDAIOCB *acb)
{
BDRVQEDState *s = acb_to_s(acb);
CachedL2Table *l2_table = acb->request.l2_table;
uint64_t l2_offset = l2_table->offset;
int index, ret;
index = qed_l1_index(s, acb->cur_pos);
s->l1_table->offsets[index] = l2_table->offset;
ret = qed_write_l1_table(s, index, 1);
/* Commit the current L2 table to the cache */
qed_commit_l2_cache_entry(&s->l2_cache, l2_table);
/* This is guaranteed to succeed because we just committed the entry to the
* cache.
*/
acb->request.l2_table = qed_find_l2_cache_entry(&s->l2_cache, l2_offset);
assert(acb->request.l2_table != NULL);
return ret;
}
/**