-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathiscsi.c
1815 lines (1562 loc) · 53.5 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) 2012-2015 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 "config-host.h"
#include <poll.h>
#include <math.h>
#include <arpa/inet.h>
#include "qemu-common.h"
#include "qemu/config-file.h"
#include "qemu/error-report.h"
#include "qemu/bitops.h"
#include "qemu/bitmap.h"
#include "block/block_int.h"
#include "block/scsi.h"
#include "qemu/iov.h"
#include "sysemu/sysemu.h"
#include "qmp-commands.h"
#include "qapi/qmp/qstring.h"
#include <iscsi/iscsi.h>
#include <iscsi/scsi-lowlevel.h>
#ifdef __linux__
#include <scsi/sg.h>
#include <block/scsi.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;
struct scsi_inquiry_logical_block_provisioning lbp;
struct scsi_inquiry_block_limits bl;
unsigned char *zeroblock;
unsigned long *allocationmap;
int cluster_sectors;
bool use_16_for_rw;
bool write_protected;
bool lbpme;
bool lbprz;
bool dpofua;
bool has_write_same;
bool force_next_flush;
bool request_timed_out;
} IscsiLun;
typedef struct IscsiTask {
int status;
int complete;
int retries;
int do_retry;
struct scsi_task *task;
Coroutine *co;
QEMUBH *bh;
IscsiLun *iscsilun;
QEMUTimer retry_timer;
bool force_next_flush;
} IscsiTask;
typedef struct IscsiAIOCB {
BlockAIOCB common;
QEMUIOVector *qiov;
QEMUBH *bh;
IscsiLun *iscsilun;
struct scsi_task *task;
uint8_t *buf;
int status;
int64_t sector_num;
int nb_sectors;
#ifdef __linux__
sg_io_hdr_t *ioh;
#endif
} 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
static void
iscsi_bh_cb(void *p)
{
IscsiAIOCB *acb = p;
qemu_bh_delete(acb->bh);
g_free(acb->buf);
acb->buf = NULL;
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);
}
static void iscsi_co_generic_bh_cb(void *opaque)
{
struct IscsiTask *iTask = opaque;
iTask->complete = 1;
qemu_bh_delete(iTask->bh);
qemu_coroutine_enter(iTask->co, NULL);
}
static void iscsi_retry_timer_expired(void *opaque)
{
struct IscsiTask *iTask = opaque;
iTask->complete = 1;
if (iTask->co) {
qemu_coroutine_enter(iTask->co, NULL);
}
}
static inline unsigned exp_random(double mean)
{
return -mean * log((double)rand() / RAND_MAX);
}
/* SCSI_STATUS_TASK_SET_FULL and SCSI_STATUS_TIMEOUT were introduced
* in libiscsi 1.10.0 as part of an enum. The LIBISCSI_API_VERSION
* macro was introduced in 1.11.0. So use the API_VERSION macro as
* a hint that the macros are defined and define them ourselves
* otherwise to keep the required libiscsi version at 1.9.0 */
#if !defined(LIBISCSI_API_VERSION)
#define QEMU_SCSI_STATUS_TASK_SET_FULL 0x28
#define QEMU_SCSI_STATUS_TIMEOUT 0x0f000002
#else
#define QEMU_SCSI_STATUS_TASK_SET_FULL SCSI_STATUS_TASK_SET_FULL
#define QEMU_SCSI_STATUS_TIMEOUT SCSI_STATUS_TIMEOUT
#endif
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->task = task;
if (status != SCSI_STATUS_GOOD) {
if (iTask->retries++ < ISCSI_CMD_RETRIES) {
if (status == SCSI_STATUS_CHECK_CONDITION
&& task->sense.key == SCSI_SENSE_UNIT_ATTENTION) {
error_report("iSCSI CheckCondition: %s",
iscsi_get_error(iscsi));
iTask->do_retry = 1;
goto out;
}
if (status == SCSI_STATUS_BUSY ||
status == QEMU_SCSI_STATUS_TIMEOUT ||
status == QEMU_SCSI_STATUS_TASK_SET_FULL) {
unsigned retry_time =
exp_random(iscsi_retry_times[iTask->retries - 1]);
if (status == QEMU_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;
}
}
error_report("iSCSI Failure: %s", iscsi_get_error(iscsi));
} else {
iTask->iscsilun->force_next_flush |= iTask->force_next_flush;
}
out:
if (iTask->co) {
iTask->bh = aio_bh_new(iTask->iscsilun->aio_context,
iscsi_co_generic_bh_cb, iTask);
qemu_bh_schedule(iTask->bh);
} else {
iTask->complete = 1;
}
}
static void iscsi_co_init_iscsitask(IscsiLun *iscsilun, struct IscsiTask *iTask)
{
*iTask = (struct IscsiTask) {
.co = qemu_coroutine_self(),
.iscsilun = iscsilun,
};
}
static void
iscsi_abort_task_cb(struct iscsi_context *iscsi, int status, void *command_data,
void *private_data)
{
IscsiAIOCB *acb = private_data;
acb->status = -ECANCELED;
iscsi_schedule_bh(acb);
}
static void
iscsi_aio_cancel(BlockAIOCB *blockacb)
{
IscsiAIOCB *acb = (IscsiAIOCB *)blockacb;
IscsiLun *iscsilun = acb->iscsilun;
if (acb->status != -EINPROGRESS) {
return;
}
/* send a task mgmt call to the target to cancel the task on the target */
iscsi_task_mgmt_abort_task_async(iscsilun->iscsi, acb->task,
iscsi_abort_task_cb, acb);
}
static const AIOCBInfo iscsi_aiocb_info = {
.aiocb_size = sizeof(IscsiAIOCB),
.cancel_async = iscsi_aio_cancel,
};
static void iscsi_process_read(void *arg);
static void iscsi_process_write(void *arg);
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),
(ev & POLLIN) ? iscsi_process_read : NULL,
(ev & POLLOUT) ? iscsi_process_write : NULL,
iscsilun);
iscsilun->events = ev;
}
}
static void iscsi_timed_check_events(void *opaque)
{
IscsiLun *iscsilun = opaque;
/* 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;
iscsi_service(iscsi, POLLIN);
iscsi_set_events(iscsilun);
}
static void
iscsi_process_write(void *arg)
{
IscsiLun *iscsilun = arg;
struct iscsi_context *iscsi = iscsilun->iscsi;
iscsi_service(iscsi, POLLOUT);
iscsi_set_events(iscsilun);
}
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_request_lun_aligned(int64_t sector_num, int nb_sectors,
IscsiLun *iscsilun)
{
if ((sector_num * BDRV_SECTOR_SIZE) % iscsilun->block_size ||
(nb_sectors * BDRV_SECTOR_SIZE) % iscsilun->block_size) {
error_report("iSCSI misaligned request: "
"iscsilun->block_size %u, sector_num %" PRIi64
", nb_sectors %d",
iscsilun->block_size, sector_num, nb_sectors);
return 0;
}
return 1;
}
static unsigned long *iscsi_allocationmap_init(IscsiLun *iscsilun)
{
return bitmap_try_new(DIV_ROUND_UP(sector_lun2qemu(iscsilun->num_blocks,
iscsilun),
iscsilun->cluster_sectors));
}
static void iscsi_allocationmap_set(IscsiLun *iscsilun, int64_t sector_num,
int nb_sectors)
{
if (iscsilun->allocationmap == NULL) {
return;
}
bitmap_set(iscsilun->allocationmap,
sector_num / iscsilun->cluster_sectors,
DIV_ROUND_UP(nb_sectors, iscsilun->cluster_sectors));
}
static void iscsi_allocationmap_clear(IscsiLun *iscsilun, int64_t sector_num,
int nb_sectors)
{
int64_t cluster_num, nb_clusters;
if (iscsilun->allocationmap == NULL) {
return;
}
cluster_num = DIV_ROUND_UP(sector_num, iscsilun->cluster_sectors);
nb_clusters = (sector_num + nb_sectors) / iscsilun->cluster_sectors
- cluster_num;
if (nb_clusters > 0) {
bitmap_clear(iscsilun->allocationmap, cluster_num, nb_clusters);
}
}
static int coroutine_fn iscsi_co_writev(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 fua;
if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
return -EINVAL;
}
if (bs->bl.max_transfer_length && nb_sectors > bs->bl.max_transfer_length) {
error_report("iSCSI Error: Write of %d sectors exceeds max_xfer_len "
"of %d sectors", nb_sectors, bs->bl.max_transfer_length);
return -EINVAL;
}
lba = sector_qemu2lun(sector_num, iscsilun);
num_sectors = sector_qemu2lun(nb_sectors, iscsilun);
iscsi_co_init_iscsitask(iscsilun, &iTask);
retry:
fua = iscsilun->dpofua && !bs->enable_write_cache;
iTask.force_next_flush = !fua;
if (iscsilun->use_16_for_rw) {
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);
}
if (iTask.task == NULL) {
return -ENOMEM;
}
scsi_task_set_iov_out(iTask.task, (struct scsi_iovec *) iov->iov,
iov->niov);
while (!iTask.complete) {
iscsi_set_events(iscsilun);
qemu_coroutine_yield();
}
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) {
return -EIO;
}
iscsi_allocationmap_set(iscsilun, sector_num, nb_sectors);
return 0;
}
static bool iscsi_allocationmap_is_allocated(IscsiLun *iscsilun,
int64_t sector_num, int nb_sectors)
{
unsigned long size;
if (iscsilun->allocationmap == NULL) {
return true;
}
size = DIV_ROUND_UP(sector_num + nb_sectors, iscsilun->cluster_sectors);
return !(find_next_bit(iscsilun->allocationmap, size,
sector_num / iscsilun->cluster_sectors) == size);
}
static int64_t coroutine_fn iscsi_co_get_block_status(BlockDriverState *bs,
int64_t sector_num,
int nb_sectors, int *pnum)
{
IscsiLun *iscsilun = bs->opaque;
struct scsi_get_lba_status *lbas = NULL;
struct scsi_lba_status_descriptor *lbasd = NULL;
struct IscsiTask iTask;
int64_t ret;
iscsi_co_init_iscsitask(iscsilun, &iTask);
if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
ret = -EINVAL;
goto out;
}
/* default to all sectors allocated */
ret = BDRV_BLOCK_DATA;
ret |= (sector_num << BDRV_SECTOR_BITS) | BDRV_BLOCK_OFFSET_VALID;
*pnum = nb_sectors;
/* LUN does not support logical block provisioning */
if (!iscsilun->lbpme) {
goto out;
}
retry:
if (iscsi_get_lba_status_task(iscsilun->iscsi, iscsilun->lun,
sector_qemu2lun(sector_num, iscsilun),
8 + 16, iscsi_co_generic_cb,
&iTask) == NULL) {
ret = -ENOMEM;
goto out;
}
while (!iTask.complete) {
iscsi_set_events(iscsilun);
qemu_coroutine_yield();
}
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 */
goto out;
}
lbas = scsi_datain_unmarshall(iTask.task);
if (lbas == NULL) {
ret = -EIO;
goto out;
}
lbasd = &lbas->descriptors[0];
if (sector_qemu2lun(sector_num, iscsilun) != lbasd->lba) {
ret = -EIO;
goto out;
}
*pnum = sector_lun2qemu(lbasd->num_blocks, iscsilun);
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_allocationmap_clear(iscsilun, sector_num, *pnum);
} else {
iscsi_allocationmap_set(iscsilun, sector_num, *pnum);
}
if (*pnum > nb_sectors) {
*pnum = nb_sectors;
}
out:
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
}
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;
if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
return -EINVAL;
}
if (bs->bl.max_transfer_length && nb_sectors > bs->bl.max_transfer_length) {
error_report("iSCSI Error: Read of %d sectors exceeds max_xfer_len "
"of %d sectors", nb_sectors, bs->bl.max_transfer_length);
return -EINVAL;
}
if (iscsilun->lbprz && nb_sectors >= ISCSI_CHECKALLOC_THRES &&
!iscsi_allocationmap_is_allocated(iscsilun, sector_num, nb_sectors)) {
int64_t ret;
int pnum;
ret = iscsi_co_get_block_status(bs, sector_num, INT_MAX, &pnum);
if (ret < 0) {
return ret;
}
if (ret & BDRV_BLOCK_ZERO && pnum >= nb_sectors) {
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);
retry:
if (iscsilun->use_16_for_rw) {
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);
}
if (iTask.task == NULL) {
return -ENOMEM;
}
scsi_task_set_iov_in(iTask.task, (struct scsi_iovec *) iov->iov, iov->niov);
while (!iTask.complete) {
iscsi_set_events(iscsilun);
qemu_coroutine_yield();
}
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) {
return -EIO;
}
return 0;
}
static int coroutine_fn iscsi_co_flush(BlockDriverState *bs)
{
IscsiLun *iscsilun = bs->opaque;
struct IscsiTask iTask;
if (!iscsilun->force_next_flush) {
return 0;
}
iscsilun->force_next_flush = false;
iscsi_co_init_iscsitask(iscsilun, &iTask);
retry:
if (iscsi_synchronizecache10_task(iscsilun->iscsi, iscsilun->lun, 0, 0, 0,
0, iscsi_co_generic_cb, &iTask) == NULL) {
return -ENOMEM;
}
while (!iTask.complete) {
iscsi_set_events(iscsilun);
qemu_coroutine_yield();
}
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) {
return -EIO;
}
return 0;
}
#ifdef __linux__
static void
iscsi_aio_ioctl_cb(struct iscsi_context *iscsi, int status,
void *command_data, void *opaque)
{
IscsiAIOCB *acb = opaque;
g_free(acb->buf);
acb->buf = NULL;
acb->status = 0;
if (status < 0) {
error_report("Failed to ioctl(SG_IO) to iSCSI lun. %s",
iscsi_get_error(iscsi));
acb->status = -EIO;
}
acb->ioh->driver_status = 0;
acb->ioh->host_status = 0;
acb->ioh->resid = 0;
#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 = (acb->ioh->mx_sb_len >= acb->ioh->sb_len_wr) ?
acb->ioh->mx_sb_len : acb->ioh->sb_len_wr;
memcpy(acb->ioh->sbp, &acb->task->datain.data[2], ss);
}
iscsi_schedule_bh(acb);
}
static BlockAIOCB *iscsi_aio_ioctl(BlockDriverState *bs,
unsigned long int req, void *buf,
BlockCompletionFunc *cb, void *opaque)
{
IscsiLun *iscsilun = bs->opaque;
struct iscsi_context *iscsi = iscsilun->iscsi;
struct iscsi_data data;
IscsiAIOCB *acb;
assert(req == SG_IO);
acb = qemu_aio_get(&iscsi_aiocb_info, bs, cb, opaque);
acb->iscsilun = iscsilun;
acb->bh = NULL;
acb->status = -EINPROGRESS;
acb->buf = NULL;
acb->ioh = buf;
acb->task = malloc(sizeof(struct scsi_task));
if (acb->task == NULL) {
error_report("iSCSI: Failed to allocate task for scsi command. %s",
iscsi_get_error(iscsi));
qemu_aio_unref(acb);
return NULL;
}
memset(acb->task, 0, sizeof(struct scsi_task));
switch (acb->ioh->dxfer_direction) {
case SG_DXFER_TO_DEV:
acb->task->xfer_dir = SCSI_XFER_WRITE;
break;
case SG_DXFER_FROM_DEV:
acb->task->xfer_dir = SCSI_XFER_READ;
break;
default:
acb->task->xfer_dir = SCSI_XFER_NONE;
break;
}
acb->task->cdb_size = acb->ioh->cmd_len;
memcpy(&acb->task->cdb[0], acb->ioh->cmdp, acb->ioh->cmd_len);
acb->task->expxferlen = acb->ioh->dxfer_len;
data.size = 0;
if (acb->task->xfer_dir == SCSI_XFER_WRITE) {
if (acb->ioh->iovec_count == 0) {
data.data = acb->ioh->dxferp;
data.size = acb->ioh->dxfer_len;
} else {
scsi_task_set_iov_out(acb->task,
(struct scsi_iovec *) acb->ioh->dxferp,
acb->ioh->iovec_count);
}
}
if (iscsi_scsi_command_async(iscsi, iscsilun->lun, acb->task,
iscsi_aio_ioctl_cb,
(data.size > 0) ? &data : NULL,
acb) != 0) {
scsi_free_scsi_task(acb->task);
qemu_aio_unref(acb);
return NULL;
}
/* tell libiscsi to read straight into the buffer we got from ioctl */
if (acb->task->xfer_dir == SCSI_XFER_READ) {
if (acb->ioh->iovec_count == 0) {
scsi_task_add_data_in_buffer(acb->task,
acb->ioh->dxfer_len,
acb->ioh->dxferp);
} else {
scsi_task_set_iov_in(acb->task,
(struct scsi_iovec *) acb->ioh->dxferp,
acb->ioh->iovec_count);
}
}
iscsi_set_events(iscsilun);
return &acb->common;
}
static void ioctl_cb(void *opaque, int status)
{
int *p_status = opaque;
*p_status = status;
}
static int iscsi_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
{
IscsiLun *iscsilun = bs->opaque;
int status;
switch (req) {
case SG_GET_VERSION_NUM:
*(int *)buf = 30000;
break;
case SG_GET_SCSI_ID:
((struct sg_scsi_id *)buf)->scsi_type = iscsilun->type;
break;
case SG_IO:
status = -EINPROGRESS;
iscsi_aio_ioctl(bs, req, buf, ioctl_cb, &status);
while (status == -EINPROGRESS) {
aio_poll(iscsilun->aio_context, true);
}
return 0;
default:
return -1;
}
return 0;
}
#endif
static int64_t
iscsi_getlength(BlockDriverState *bs)
{
IscsiLun *iscsilun = bs->opaque;
int64_t len;
len = iscsilun->num_blocks;
len *= iscsilun->block_size;
return len;
}
static int
coroutine_fn iscsi_co_discard(BlockDriverState *bs, int64_t sector_num,
int nb_sectors)
{
IscsiLun *iscsilun = bs->opaque;
struct IscsiTask iTask;
struct unmap_list list;
if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
return -EINVAL;
}
if (!iscsilun->lbp.lbpu) {
/* UNMAP is not supported by the target */
return 0;
}
list.lba = sector_qemu2lun(sector_num, iscsilun);
list.num = sector_qemu2lun(nb_sectors, iscsilun);
iscsi_co_init_iscsitask(iscsilun, &iTask);
retry:
if (iscsi_unmap_task(iscsilun->iscsi, iscsilun->lun, 0, 0, &list, 1,
iscsi_co_generic_cb, &iTask) == NULL) {
return -ENOMEM;
}
while (!iTask.complete) {
iscsi_set_events(iscsilun);
qemu_coroutine_yield();
}
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_CHECK_CONDITION) {
/* the target might fail with a check condition if it
is not happy with the alignment of the UNMAP request
we silently fail in this case */
return 0;
}
if (iTask.status != SCSI_STATUS_GOOD) {
return -EIO;
}
iscsi_allocationmap_clear(iscsilun, sector_num, nb_sectors);
return 0;
}
static int
coroutine_fn iscsi_co_write_zeroes(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, BdrvRequestFlags flags)
{
IscsiLun *iscsilun = bs->opaque;
struct IscsiTask iTask;
uint64_t lba;
uint32_t nb_blocks;
bool use_16_for_ws = iscsilun->use_16_for_rw;
if (!is_request_lun_aligned(sector_num, nb_sectors, iscsilun)) {
return -EINVAL;
}
if (flags & BDRV_REQ_MAY_UNMAP) {
if (!use_16_for_ws && !iscsilun->lbp.lbpws10) {
/* WRITESAME10 with UNMAP is unsupported try WRITESAME16 */
use_16_for_ws = true;
}
if (use_16_for_ws && !iscsilun->lbp.lbpws) {
/* WRITESAME16 with UNMAP is not supported by the target,
* fall back and try WRITESAME10/16 without UNMAP */
flags &= ~BDRV_REQ_MAY_UNMAP;
use_16_for_ws = iscsilun->use_16_for_rw;
}
}
if (!(flags & BDRV_REQ_MAY_UNMAP) && !iscsilun->has_write_same) {
/* WRITESAME without UNMAP is not supported by the target */
return -ENOTSUP;
}
lba = sector_qemu2lun(sector_num, iscsilun);
nb_blocks = sector_qemu2lun(nb_sectors, iscsilun);
if (iscsilun->zeroblock == NULL) {
iscsilun->zeroblock = g_try_malloc0(iscsilun->block_size);
if (iscsilun->zeroblock == NULL) {
return -ENOMEM;
}
}
iscsi_co_init_iscsitask(iscsilun, &iTask);
iTask.force_next_flush = true;
retry:
if (use_16_for_ws) {
iTask.task = iscsi_writesame16_task(iscsilun->iscsi, iscsilun->lun, lba,
iscsilun->zeroblock, iscsilun->block_size,
nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
0, 0, iscsi_co_generic_cb, &iTask);
} else {
iTask.task = iscsi_writesame10_task(iscsilun->iscsi, iscsilun->lun, lba,
iscsilun->zeroblock, iscsilun->block_size,
nb_blocks, 0, !!(flags & BDRV_REQ_MAY_UNMAP),
0, 0, iscsi_co_generic_cb, &iTask);
}
if (iTask.task == NULL) {
return -ENOMEM;
}
while (!iTask.complete) {
iscsi_set_events(iscsilun);
qemu_coroutine_yield();
}
if (iTask.status == SCSI_STATUS_CHECK_CONDITION &&
iTask.task->sense.key == SCSI_SENSE_ILLEGAL_REQUEST &&
(iTask.task->sense.ascq == SCSI_SENSE_ASCQ_INVALID_OPERATION_CODE ||
iTask.task->sense.ascq == SCSI_SENSE_ASCQ_INVALID_FIELD_IN_CDB)) {
/* WRITE SAME is not supported by the target */
iscsilun->has_write_same = false;
scsi_free_scsi_task(iTask.task);
return -ENOTSUP;
}
if (iTask.task != NULL) {
scsi_free_scsi_task(iTask.task);
iTask.task = NULL;
}
if (iTask.do_retry) {
iTask.complete = 0;
goto retry;
}