forked from taovcu/FEMU_MultiStream
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathiscsi.c
2510 lines (2181 loc) · 79 KB
/
iscsi.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 Block driver for iSCSI images
*
* Copyright (c) 2010-2011 Ronnie Sahlberg <[email protected]>
* Copyright (c) 2012-2017 Peter Lieven <[email protected]>
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include <poll.h>
#include <math.h>
#include <arpa/inet.h>
#include "sysemu/sysemu.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
#include "block/block-io.h"
#include "block/block_int.h"
#include "block/qdict.h"
#include "scsi/constants.h"
#include "qemu/iov.h"
#include "qemu/module.h"
#include "qemu/option.h"
#include "qemu/uuid.h"
#include "sysemu/replay.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-machine.h"
#include "qapi/qmp/qdict.h"
#include "qapi/qmp/qstring.h"
#include "crypto/secret.h"
#include "scsi/utils.h"
#include "trace.h"
/* Conflict between scsi/utils.h and libiscsi! :( */
#define SCSI_XFER_NONE ISCSI_XFER_NONE
#include <iscsi/iscsi.h>
#define inline __attribute__((gnu_inline)) /* required for libiscsi v1.9.0 */
#include <iscsi/scsi-lowlevel.h>
#undef inline
#undef SCSI_XFER_NONE
QEMU_BUILD_BUG_ON((int)SCSI_XFER_NONE != (int)ISCSI_XFER_NONE);
#ifdef __linux__
#include <scsi/sg.h>
#endif
typedef struct IscsiLun {
struct iscsi_context *iscsi;
AioContext *aio_context;
int lun;
enum scsi_inquiry_peripheral_device_type type;
int block_size;
uint64_t num_blocks;
int events;
QEMUTimer *nop_timer;
QEMUTimer *event_timer;
QemuMutex mutex;
struct scsi_inquiry_logical_block_provisioning lbp;
struct scsi_inquiry_block_limits bl;
struct scsi_inquiry_device_designator *dd;
unsigned char *zeroblock;
/* The allocmap tracks which clusters (pages) on the iSCSI target are
* allocated and which are not. In case a target returns zeros for
* unallocated pages (iscsilun->lprz) we can directly return zeros instead
* of reading zeros over the wire if a read request falls within an
* unallocated block. As there are 3 possible states we need 2 bitmaps to
* track. allocmap_valid keeps track if QEMU's information about a page is
* valid. allocmap tracks if a page is allocated or not. In case QEMU has no
* valid information about a page the corresponding allocmap entry should be
* switched to unallocated as well to force a new lookup of the allocation
* status as lookups are generally skipped if a page is suspect to be
* allocated. If a iSCSI target is opened with cache.direct = on the
* allocmap_valid does not exist turning all cached information invalid so
* that a fresh lookup is made for any page even if allocmap entry returns
* it's unallocated. */
unsigned long *allocmap;
unsigned long *allocmap_valid;
long allocmap_size;
int cluster_size;
bool use_16_for_rw;
bool write_protected;
bool lbpme;
bool lbprz;
bool dpofua;
bool has_write_same;
bool request_timed_out;
} IscsiLun;
typedef struct IscsiTask {
int status;
int complete;
int retries;
int do_retry;
struct scsi_task *task;
Coroutine *co;
IscsiLun *iscsilun;
QEMUTimer retry_timer;
int err_code;
char *err_str;
} IscsiTask;
typedef struct IscsiAIOCB {
BlockAIOCB common;
QEMUBH *bh;
IscsiLun *iscsilun;
struct scsi_task *task;
int status;
int64_t sector_num;
int nb_sectors;
int ret;
#ifdef __linux__
sg_io_hdr_t *ioh;
#endif
bool cancelled;
} IscsiAIOCB;
/* libiscsi uses time_t so its enough to process events every second */
#define EVENT_INTERVAL 1000
#define NOP_INTERVAL 5000
#define MAX_NOP_FAILURES 3
#define ISCSI_CMD_RETRIES ARRAY_SIZE(iscsi_retry_times)
static const unsigned iscsi_retry_times[] = {8, 32, 128, 512, 2048, 8192, 32768};
/* this threshold is a trade-off knob to choose between
* the potential additional overhead of an extra GET_LBA_STATUS request
* vs. unnecessarily reading a lot of zero sectors over the wire.
* If a read request is greater or equal than ISCSI_CHECKALLOC_THRES
* sectors we check the allocation status of the area covered by the
* request first if the allocationmap indicates that the area might be
* unallocated. */
#define ISCSI_CHECKALLOC_THRES 64
#ifdef __linux__
static void
iscsi_bh_cb(void *p)
{
IscsiAIOCB *acb = p;
qemu_bh_delete(acb->bh);
acb->common.cb(acb->common.opaque, acb->status);
if (acb->task != NULL) {
scsi_free_scsi_task(acb->task);
acb->task = NULL;
}
qemu_aio_unref(acb);
}
static void
iscsi_schedule_bh(IscsiAIOCB *acb)
{
if (acb->bh) {
return;
}
acb->bh = aio_bh_new(acb->iscsilun->aio_context, iscsi_bh_cb, acb);
qemu_bh_schedule(acb->bh);
}
#endif
static void iscsi_co_generic_bh_cb(void *opaque)
{
struct IscsiTask *iTask = opaque;
iTask->complete = 1;
aio_co_wake(iTask->co);
}
static void iscsi_retry_timer_expired(void *opaque)
{
struct IscsiTask *iTask = opaque;
iTask->complete = 1;
if (iTask->co) {
aio_co_wake(iTask->co);
}
}
static inline unsigned exp_random(double mean)
{
return -mean * log((double)rand() / RAND_MAX);
}
/* SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST was introduced in
* libiscsi 1.10.0, together with other constants we need. Use it as
* a hint that we have to define them ourselves if needed, to keep the
* minimum required libiscsi version at 1.9.0. We use an ASCQ macro for
* the test because SCSI_STATUS_* is an enum.
*
* To guard against future changes where SCSI_SENSE_ASCQ_* also becomes
* an enum, check against the LIBISCSI_API_VERSION macro, which was
* introduced in 1.11.0. If it is present, there is no need to define
* anything.
*/
#if !defined(SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST) && \
!defined(LIBISCSI_API_VERSION)
#define SCSI_STATUS_TASK_SET_FULL 0x28
#define SCSI_STATUS_TIMEOUT 0x0f000002
#define SCSI_SENSE_ASCQ_INVALID_FIELD_IN_PARAMETER_LIST 0x2600
#define SCSI_SENSE_ASCQ_PARAMETER_LIST_LENGTH_ERROR 0x1a00
#endif
#ifndef LIBISCSI_API_VERSION
#define LIBISCSI_API_VERSION 20130701
#endif
static int iscsi_translate_sense(struct scsi_sense *sense)
{
return scsi_sense_to_errno(sense->key,
(sense->ascq & 0xFF00) >> 8,
sense->ascq & 0xFF);
}
/* Called (via iscsi_service) with QemuMutex held. */
static void
iscsi_co_generic_cb(struct iscsi_context *iscsi, int status,
void *command_data, void *opaque)
{
struct IscsiTask *iTask = opaque;
struct scsi_task *task = command_data;
iTask->status = status;
iTask->do_retry = 0;
iTask->err_code = 0;
iTask->task = task;
if (status != SCSI_STATUS_GOOD) {
iTask->err_code = -EIO;
if (iTask->retries++ < ISCSI_CMD_RETRIES) {
if (status == SCSI_STATUS_BUSY ||
status == SCSI_STATUS_TIMEOUT ||
status == SCSI_STATUS_TASK_SET_FULL) {
unsigned retry_time =
exp_random(iscsi_retry_times[iTask->retries - 1]);
if (status == SCSI_STATUS_TIMEOUT) {
/* make sure the request is rescheduled AFTER the
* reconnect is initiated */
retry_time = EVENT_INTERVAL * 2;
iTask->iscsilun->request_timed_out = true;
}
error_report("iSCSI Busy/TaskSetFull/TimeOut"
" (retry #%u in %u ms): %s",
iTask->retries, retry_time,
iscsi_get_error(iscsi));
aio_timer_init(iTask->iscsilun->aio_context,
&iTask->retry_timer, QEMU_CLOCK_REALTIME,
SCALE_MS, iscsi_retry_timer_expired, iTask);
timer_mod(&iTask->retry_timer,
qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + retry_time);
iTask->do_retry = 1;
return;
} else if (status == SCSI_STATUS_CHECK_CONDITION) {
int error = iscsi_translate_sense(&task->sense);
if (error == EAGAIN) {
error_report("iSCSI CheckCondition: %s",
iscsi_get_error(iscsi));
iTask->do_retry = 1;
} else {
iTask->err_code = -error;
iTask->err_str = g_strdup(iscsi_get_error(iscsi));
}
}
}
}
if (iTask->co) {
replay_bh_schedule_oneshot_event(iTask->iscsilun->aio_context,
iscsi_co_generic_bh_cb, iTask);
} else {
iTask->complete = 1;
}
}
static void coroutine_fn
iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask)
{
*iTask = (struct IscsiTask) {
.co = qemu_coroutine_self(),
.iscsilun = iscsilun,
};
}
#ifdef __linux__
/* Called (via iscsi_service) with QemuMutex held. */
static void
iscsi_abort_task_cb(struct iscsi_context *iscsi, int status, void *command_data,
void *private_data)
{
IscsiAIOCB *acb = private_data;
/* If the command callback hasn't been called yet, drop the task */
if (!acb->bh) {
/* Call iscsi_aio_ioctl_cb() with SCSI_STATUS_CANCELLED */
iscsi_scsi_cancel_task(iscsi, acb->task);
}
qemu_aio_unref(acb); /* acquired in iscsi_aio_cancel() */
}
static void
iscsi_aio_cancel(BlockAIOCB *blockacb)
{
IscsiAIOCB *acb = (IscsiAIOCB *)blockacb;
IscsiLun *iscsilun = acb->iscsilun;
WITH_QEMU_LOCK_GUARD(&iscsilun->mutex) {
/* If it was cancelled or completed already, our work is done here */
if (acb->cancelled || acb->status != -EINPROGRESS) {
return;
}
acb->cancelled = true;
qemu_aio_ref(acb); /* released in iscsi_abort_task_cb() */
/* send a task mgmt call to the target to cancel the task on the target */
if (iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
iscsi_abort_task_cb, acb) < 0) {
qemu_aio_unref(acb); /* since iscsi_abort_task_cb() won't be called */
}
}
}
static const AIOCBInfo iscsi_aiocb_info = {
.aiocb_size = sizeof(IscsiAIOCB),
.cancel_async = iscsi_aio_cancel,
};
#endif
static void iscsi_process_read(void *arg);
static void iscsi_process_write(void *arg);
/* Called with QemuMutex held. */
static void
iscsi_set_events(IscsiLun *iscsilun)
{
struct iscsi_context *iscsi = iscsilun->iscsi;
int ev = iscsi_which_events(iscsi);
if (ev != iscsilun->events) {
aio_set_fd_handler(iscsilun->aio_context, iscsi_get_fd(iscsi),
false,
(ev & POLLIN) ? iscsi_process_read : NULL,
(ev & POLLOUT) ? iscsi_process_write : NULL,
NULL, NULL,
iscsilun);
iscsilun->events = ev;
}
}
static void iscsi_timed_check_events(void *opaque)
{
IscsiLun *iscsilun = opaque;
WITH_QEMU_LOCK_GUARD(&iscsilun->mutex) {
/* check for timed out requests */
iscsi_service(iscsilun->iscsi, 0);
if (iscsilun->request_timed_out) {
iscsilun->request_timed_out = false;
iscsi_reconnect(iscsilun->iscsi);
}
/*
* newer versions of libiscsi may return zero events. Ensure we are
* able to return to service once this situation changes.
*/
iscsi_set_events(iscsilun);
}
timer_mod(iscsilun->event_timer,
qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + EVENT_INTERVAL);
}
static void
iscsi_process_read(void *arg)
{
IscsiLun *iscsilun = arg;
struct iscsi_context *iscsi = iscsilun->iscsi;
qemu_mutex_lock(&iscsilun->mutex);
iscsi_service(iscsi, POLLIN);
iscsi_set_events(iscsilun);
qemu_mutex_unlock(&iscsilun->mutex);
}
static void
iscsi_process_write(void *arg)
{
IscsiLun *iscsilun = arg;
struct iscsi_context *iscsi = iscsilun->iscsi;
qemu_mutex_lock(&iscsilun->mutex);
iscsi_service(iscsi, POLLOUT);
iscsi_set_events(iscsilun);
qemu_mutex_unlock(&iscsilun->mutex);
}
static int64_t sector_lun2qemu(int64_t sector, IscsiLun *iscsilun)
{
return sector * iscsilun->block_size / BDRV_SECTOR_SIZE;
}
static int64_t sector_qemu2lun(int64_t sector, IscsiLun *iscsilun)
{
return sector * BDRV_SECTOR_SIZE / iscsilun->block_size;
}
static bool is_byte_request_lun_aligned(int64_t offset, int64_t bytes,
IscsiLun *iscsilun)
{
if (offset % iscsilun->block_size || bytes % iscsilun->block_size) {
error_report("iSCSI misaligned request: "
"iscsilun->block_size %u, offset %" PRIi64
", bytes %" PRIi64,
iscsilun->block_size, offset, bytes);
return false;
}
return true;
}
static bool is_sector_request_lun_aligned(int64_t sector_num, int nb_sectors,
IscsiLun *iscsilun)
{
assert(nb_sectors <= BDRV_REQUEST_MAX_SECTORS);
return is_byte_request_lun_aligned(sector_num << BDRV_SECTOR_BITS,
nb_sectors << BDRV_SECTOR_BITS,
iscsilun);
}
static void iscsi_allocmap_free(IscsiLun *iscsilun)
{
g_free(iscsilun->allocmap);
g_free(iscsilun->allocmap_valid);
iscsilun->allocmap = NULL;
iscsilun->allocmap_valid = NULL;
}
static int iscsi_allocmap_init(IscsiLun *iscsilun, int open_flags)
{
iscsi_allocmap_free(iscsilun);
assert(iscsilun->cluster_size);
iscsilun->allocmap_size =
DIV_ROUND_UP(iscsilun->num_blocks * iscsilun->block_size,
iscsilun->cluster_size);
iscsilun->allocmap = bitmap_try_new(iscsilun->allocmap_size);
if (!iscsilun->allocmap) {
return -ENOMEM;
}
if (open_flags & BDRV_O_NOCACHE) {
/* when cache.direct = on all allocmap entries are
* treated as invalid to force a relookup of the block
* status on every read request */
return 0;
}
iscsilun->allocmap_valid = bitmap_try_new(iscsilun->allocmap_size);
if (!iscsilun->allocmap_valid) {
/* if we are under memory pressure free the allocmap as well */
iscsi_allocmap_free(iscsilun);
return -ENOMEM;
}
return 0;
}
static void
iscsi_allocmap_update(IscsiLun *iscsilun, int64_t offset,
int64_t bytes, bool allocated, bool valid)
{
int64_t cl_num_expanded, nb_cls_expanded, cl_num_shrunk, nb_cls_shrunk;
if (iscsilun->allocmap == NULL) {
return;
}
/* expand to entirely contain all affected clusters */
assert(iscsilun->cluster_size);
cl_num_expanded = offset / iscsilun->cluster_size;
nb_cls_expanded = DIV_ROUND_UP(offset + bytes,
iscsilun->cluster_size) - cl_num_expanded;
/* shrink to touch only completely contained clusters */
cl_num_shrunk = DIV_ROUND_UP(offset, iscsilun->cluster_size);
nb_cls_shrunk = (offset + bytes) / iscsilun->cluster_size - cl_num_shrunk;
if (allocated) {
bitmap_set(iscsilun->allocmap, cl_num_expanded, nb_cls_expanded);
} else {
if (nb_cls_shrunk > 0) {
bitmap_clear(iscsilun->allocmap, cl_num_shrunk, nb_cls_shrunk);
}
}
if (iscsilun->allocmap_valid == NULL) {
return;
}
if (valid) {
if (nb_cls_shrunk > 0) {
bitmap_set(iscsilun->allocmap_valid, cl_num_shrunk, nb_cls_shrunk);
}
} else {
bitmap_clear(iscsilun->allocmap_valid, cl_num_expanded,
nb_cls_expanded);
}
}
static void
iscsi_allocmap_set_allocated(IscsiLun *iscsilun, int64_t offset,
int64_t bytes)
{
iscsi_allocmap_update(iscsilun, offset, bytes, true, true);
}
static void
iscsi_allocmap_set_unallocated(IscsiLun *iscsilun, int64_t offset,
int64_t bytes)
{
/* Note: if cache.direct=on the fifth argument to iscsi_allocmap_update
* is ignored, so this will in effect be an iscsi_allocmap_set_invalid.
*/
iscsi_allocmap_update(iscsilun, offset, bytes, false, true);
}
static void iscsi_allocmap_set_invalid(IscsiLun *iscsilun, int64_t offset,
int64_t bytes)
{
iscsi_allocmap_update(iscsilun, offset, bytes, false, false);
}
static void iscsi_allocmap_invalidate(IscsiLun *iscsilun)
{
if (iscsilun->allocmap) {
bitmap_zero(iscsilun->allocmap, iscsilun->allocmap_size);
}
if (iscsilun->allocmap_valid) {
bitmap_zero(iscsilun->allocmap_valid, iscsilun->allocmap_size);
}
}
static inline bool
iscsi_allocmap_is_allocated(IscsiLun *iscsilun, int64_t offset,
int64_t bytes)
{
unsigned long size;
if (iscsilun->allocmap == NULL) {
return true;
}
assert(iscsilun->cluster_size);
size = DIV_ROUND_UP(offset + bytes, iscsilun->cluster_size);
return !(find_next_bit(iscsilun->allocmap, size,
offset / iscsilun->cluster_size) == size);
}
static inline bool iscsi_allocmap_is_valid(IscsiLun *iscsilun,
int64_t offset, int64_t bytes)
{
unsigned long size;
if (iscsilun->allocmap_valid == NULL) {
return false;
}
assert(iscsilun->cluster_size);
size = DIV_ROUND_UP(offset + bytes, iscsilun->cluster_size);
return (find_next_zero_bit(iscsilun->allocmap_valid, size,
offset / iscsilun->cluster_size) == size);
}
static void coroutine_fn iscsi_co_wait_for_task(IscsiTask *iTask,
IscsiLun *iscsilun)
{
while (!iTask->complete) {
iscsi_set_events(iscsilun);
qemu_mutex_unlock(&iscsilun->mutex);
qemu_coroutine_yield();
qemu_mutex_lock(&iscsilun->mutex);
}
}
static int coroutine_fn
iscsi_co_writev(BlockDriverState *bs, int64_t sector_num, int nb_sectors,
QEMUIOVector *iov, int flags)
{
IscsiLun *iscsilun = bs->opaque;
struct IscsiTask iTask;
uint64_t lba;
uint32_t num_sectors;
bool fua = flags & BDRV_REQ_FUA;
int r = 0;
if (fua) {
assert(iscsilun->dpofua);
}
if (!is_sector_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
return -EINVAL;
}
if (bs->bl.max_transfer) {
assert(nb_sectors << BDRV_SECTOR_BITS <= bs->bl.max_transfer);
}
lba = sector_qemu2lun(sector_num, iscsilun);
num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
iscsi_co_init_iscsitask(iscsilun, &iTask);
qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsilun->use_16_for_rw) {
#if LIBISCSI_API_VERSION >= (20160603)
iTask.task = iscsi_write16_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
NULL, num_sectors * iscsilun->block_size,
iscsilun->block_size, 0, 0, fua, 0, 0,
iscsi_co_generic_cb, &iTask,
(struct scsi_iovec *)iov->iov, iov->niov);
} else {
iTask.task = iscsi_write10_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
NULL, num_sectors * iscsilun->block_size,
iscsilun->block_size, 0, 0, fua, 0, 0,
iscsi_co_generic_cb, &iTask,
(struct scsi_iovec *)iov->iov, iov->niov);
}
#else
iTask.task = iscsi_write16_task(iscsilun->iscsi, iscsilun->lun, lba,
NULL, num_sectors * iscsilun->block_size,
iscsilun->block_size, 0, 0, fua, 0, 0,
iscsi_co_generic_cb, &iTask);
} else {
iTask.task = iscsi_write10_task(iscsilun->iscsi, iscsilun->lun, lba,
NULL, num_sectors * iscsilun->block_size,
iscsilun->block_size, 0, 0, fua, 0, 0,
iscsi_co_generic_cb, &iTask);
}
#endif
if (iTask.task == NULL) {
qemu_mutex_unlock(&iscsilun->mutex);
return -ENOMEM;
}
#if LIBISCSI_API_VERSION < (20160603)
scsi_task_set_iov_out(iTask.task, (struct scsi_iovec *) iov->iov,
iov->niov);
#endif
iscsi_co_wait_for_task(&iTask, iscsilun);
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
iTask.task = NULL;
}
if (iTask.do_retry) {
iTask.complete = 0;
goto retry;
}
if (iTask.status != SCSI_STATUS_GOOD) {
iscsi_allocmap_set_invalid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE);
error_report("iSCSI WRITE10/16 failed at lba %" PRIu64 ": %s", lba,
iTask.err_str);
r = iTask.err_code;
goto out_unlock;
}
iscsi_allocmap_set_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE);
out_unlock:
qemu_mutex_unlock(&iscsilun->mutex);
g_free(iTask.err_str);
return r;
}
static int coroutine_fn iscsi_co_block_status(BlockDriverState *bs,
bool want_zero, int64_t offset,
int64_t bytes, int64_t *pnum,
int64_t *map,
BlockDriverState **file)
{
IscsiLun *iscsilun = bs->opaque;
struct scsi_get_lba_status *lbas = NULL;
struct scsi_lba_status_descriptor *lbasd = NULL;
struct IscsiTask iTask;
uint64_t lba, max_bytes;
int ret;
iscsi_co_init_iscsitask(iscsilun, &iTask);
assert(QEMU_IS_ALIGNED(offset | bytes, iscsilun->block_size));
/* default to all sectors allocated */
ret = BDRV_BLOCK_DATA | BDRV_BLOCK_OFFSET_VALID;
if (map) {
*map = offset;
}
*pnum = bytes;
/* LUN does not support logical block provisioning */
if (!iscsilun->lbpme) {
goto out;
}
lba = offset / iscsilun->block_size;
max_bytes = (iscsilun->num_blocks - lba) * iscsilun->block_size;
qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsi_get_lba_status_task(iscsilun->iscsi, iscsilun->lun,
lba, 8 + 16, iscsi_co_generic_cb,
&iTask) == NULL) {
ret = -ENOMEM;
goto out_unlock;
}
iscsi_co_wait_for_task(&iTask, iscsilun);
if (iTask.do_retry) {
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
iTask.task = NULL;
}
iTask.complete = 0;
goto retry;
}
if (iTask.status != SCSI_STATUS_GOOD) {
/* in case the get_lba_status_callout fails (i.e.
* because the device is busy or the cmd is not
* supported) we pretend all blocks are allocated
* for backwards compatibility */
error_report("iSCSI GET_LBA_STATUS failed at lba %" PRIu64 ": %s",
lba, iTask.err_str);
goto out_unlock;
}
lbas = scsi_datain_unmarshall(iTask.task);
if (lbas == NULL || lbas->num_descriptors == 0) {
ret = -EIO;
goto out_unlock;
}
lbasd = &lbas->descriptors[0];
if (lba != lbasd->lba) {
ret = -EIO;
goto out_unlock;
}
*pnum = MIN((int64_t) lbasd->num_blocks * iscsilun->block_size, max_bytes);
if (lbasd->provisioning == SCSI_PROVISIONING_TYPE_DEALLOCATED ||
lbasd->provisioning == SCSI_PROVISIONING_TYPE_ANCHORED) {
ret &= ~BDRV_BLOCK_DATA;
if (iscsilun->lbprz) {
ret |= BDRV_BLOCK_ZERO;
}
}
if (ret & BDRV_BLOCK_ZERO) {
iscsi_allocmap_set_unallocated(iscsilun, offset, *pnum);
} else {
iscsi_allocmap_set_allocated(iscsilun, offset, *pnum);
}
out_unlock:
qemu_mutex_unlock(&iscsilun->mutex);
g_free(iTask.err_str);
out:
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
}
if (ret > 0 && ret & BDRV_BLOCK_OFFSET_VALID && file) {
*file = bs;
}
return ret;
}
static int coroutine_fn iscsi_co_readv(BlockDriverState *bs,
int64_t sector_num, int nb_sectors,
QEMUIOVector *iov)
{
IscsiLun *iscsilun = bs->opaque;
struct IscsiTask iTask;
uint64_t lba;
uint32_t num_sectors;
int r = 0;
if (!is_sector_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
return -EINVAL;
}
if (bs->bl.max_transfer) {
assert(nb_sectors << BDRV_SECTOR_BITS <= bs->bl.max_transfer);
}
/* if cache.direct is off and we have a valid entry in our allocation map
* we can skip checking the block status and directly return zeroes if
* the request falls within an unallocated area */
if (iscsi_allocmap_is_valid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE) &&
!iscsi_allocmap_is_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE)) {
qemu_iovec_memset(iov, 0, 0x00, iov->size);
return 0;
}
if (nb_sectors >= ISCSI_CHECKALLOC_THRES &&
!iscsi_allocmap_is_valid(iscsilun, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE) &&
!iscsi_allocmap_is_allocated(iscsilun, sector_num * BDRV_SECTOR_SIZE,
nb_sectors * BDRV_SECTOR_SIZE)) {
int64_t pnum;
/* check the block status from the beginning of the cluster
* containing the start sector */
int64_t head;
int ret;
assert(iscsilun->cluster_size);
head = (sector_num * BDRV_SECTOR_SIZE) % iscsilun->cluster_size;
ret = iscsi_co_block_status(bs, true,
sector_num * BDRV_SECTOR_SIZE - head,
BDRV_REQUEST_MAX_BYTES, &pnum, NULL, NULL);
if (ret < 0) {
return ret;
}
/* if the whole request falls into an unallocated area we can avoid
* reading and directly return zeroes instead */
if (ret & BDRV_BLOCK_ZERO &&
pnum >= nb_sectors * BDRV_SECTOR_SIZE + head) {
qemu_iovec_memset(iov, 0, 0x00, iov->size);
return 0;
}
}
lba = sector_qemu2lun(sector_num, iscsilun);
num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
iscsi_co_init_iscsitask(iscsilun, &iTask);
qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsilun->use_16_for_rw) {
#if LIBISCSI_API_VERSION >= (20160603)
iTask.task = iscsi_read16_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
num_sectors * iscsilun->block_size,
iscsilun->block_size, 0, 0, 0, 0, 0,
iscsi_co_generic_cb, &iTask,
(struct scsi_iovec *)iov->iov, iov->niov);
} else {
iTask.task = iscsi_read10_iov_task(iscsilun->iscsi, iscsilun->lun, lba,
num_sectors * iscsilun->block_size,
iscsilun->block_size,
0, 0, 0, 0, 0,
iscsi_co_generic_cb, &iTask,
(struct scsi_iovec *)iov->iov, iov->niov);
}
#else
iTask.task = iscsi_read16_task(iscsilun->iscsi, iscsilun->lun, lba,
num_sectors * iscsilun->block_size,
iscsilun->block_size, 0, 0, 0, 0, 0,
iscsi_co_generic_cb, &iTask);
} else {
iTask.task = iscsi_read10_task(iscsilun->iscsi, iscsilun->lun, lba,
num_sectors * iscsilun->block_size,
iscsilun->block_size,
0, 0, 0, 0, 0,
iscsi_co_generic_cb, &iTask);
}
#endif
if (iTask.task == NULL) {
qemu_mutex_unlock(&iscsilun->mutex);
return -ENOMEM;
}
#if LIBISCSI_API_VERSION < (20160603)
scsi_task_set_iov_in(iTask.task, (struct scsi_iovec *) iov->iov, iov->niov);
#endif
iscsi_co_wait_for_task(&iTask, iscsilun);
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
iTask.task = NULL;
}
if (iTask.do_retry) {
iTask.complete = 0;
goto retry;
}
if (iTask.status != SCSI_STATUS_GOOD) {
error_report("iSCSI READ10/16 failed at lba %" PRIu64 ": %s",
lba, iTask.err_str);
r = iTask.err_code;
}
qemu_mutex_unlock(&iscsilun->mutex);
g_free(iTask.err_str);
return r;
}
static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
{
IscsiLun *iscsilun = bs->opaque;
struct IscsiTask iTask;
int r = 0;
iscsi_co_init_iscsitask(iscsilun, &iTask);
qemu_mutex_lock(&iscsilun->mutex);
retry:
if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
0, iscsi_co_generic_cb, &iTask) == NULL) {
qemu_mutex_unlock(&iscsilun->mutex);
return -ENOMEM;
}
iscsi_co_wait_for_task(&iTask, iscsilun);
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
iTask.task = NULL;
}
if (iTask.do_retry) {
iTask.complete = 0;
goto retry;
}
if (iTask.status != SCSI_STATUS_GOOD) {
error_report("iSCSI SYNCHRONIZECACHE10 failed: %s", iTask.err_str);
r = iTask.err_code;
}
qemu_mutex_unlock(&iscsilun->mutex);
g_free(iTask.err_str);
return r;
}
#ifdef __linux__
/* Called (via iscsi_service) with QemuMutex held. */
static void
iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
void *command_data, void *opaque)
{
IscsiAIOCB *acb = opaque;
if (status == SCSI_STATUS_CANCELLED) {
if (!acb->bh) {
acb->status = -ECANCELED;
iscsi_schedule_bh(acb);
}
return;
}
acb->status = 0;
if (status < 0) {
error_report("Failed to ioctl(SG_IO) to iSCSI lun. %s",
iscsi_get_error(iscsi));
acb->status = -iscsi_translate_sense(&acb->task->sense);
}
acb->ioh->driver_status = 0;
acb->ioh->host_status = 0;
acb->ioh->resid = 0;
acb->ioh->status = status;
#define SG_ERR_DRIVER_SENSE 0x08
if (status == SCSI_STATUS_CHECK_CONDITION && acb->task->datain.size >= 2) {
int ss;
acb->ioh->driver_status |= SG_ERR_DRIVER_SENSE;
acb->ioh->sb_len_wr = acb->task->datain.size - 2;
ss = MIN(acb->ioh->mx_sb_len, acb->ioh->sb_len_wr);
memcpy(acb->ioh->sbp, &acb->task->datain.data[2], ss);
}
iscsi_schedule_bh(acb);
}