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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
|
/*
* Block driver for RAW files (posix)
*
* Copyright (c) 2006 Fabrice Bellard
*
* 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-common.h"
#include "qemu-timer.h"
#include "qemu-char.h"
#include "block_int.h"
#include <assert.h>
#ifdef CONFIG_AIO
#include "posix-aio-compat.h"
#endif
#ifdef CONFIG_COCOA
#include <paths.h>
#include <sys/param.h>
#include <IOKit/IOKitLib.h>
#include <IOKit/IOBSD.h>
#include <IOKit/storage/IOMediaBSDClient.h>
#include <IOKit/storage/IOMedia.h>
#include <IOKit/storage/IOCDMedia.h>
//#include <IOKit/storage/IOCDTypes.h>
#include <CoreFoundation/CoreFoundation.h>
#endif
#ifdef __sun__
#define _POSIX_PTHREAD_SEMANTICS 1
#include <signal.h>
#include <sys/dkio.h>
#endif
#ifdef __linux__
#include <sys/ioctl.h>
#include <linux/cdrom.h>
#include <linux/fd.h>
#endif
#ifdef __FreeBSD__
#include <signal.h>
#include <sys/disk.h>
#endif
#ifdef __OpenBSD__
#include <sys/ioctl.h>
#include <sys/disklabel.h>
#include <sys/dkio.h>
#endif
#ifdef __DragonFly__
#include <sys/ioctl.h>
#include <sys/diskslice.h>
#endif
//#define DEBUG_FLOPPY
//#define DEBUG_BLOCK
#if defined(DEBUG_BLOCK)
#define DEBUG_BLOCK_PRINT(formatCstr, args...) do { if (qemu_log_enabled()) \
{ qemu_log(formatCstr, ##args); qemu_log_flush(); } } while (0)
#else
#define DEBUG_BLOCK_PRINT(formatCstr, args...)
#endif
/* OS X does not have O_DSYNC */
#ifndef O_DSYNC
#define O_DSYNC O_SYNC
#endif
/* Approximate O_DIRECT with O_DSYNC if O_DIRECT isn't available */
#ifndef O_DIRECT
#define O_DIRECT O_DSYNC
#endif
#define FTYPE_FILE 0
#define FTYPE_CD 1
#define FTYPE_FD 2
#define ALIGNED_BUFFER_SIZE (32 * 512)
/* if the FD is not accessed during that time (in ms), we try to
reopen it to see if the disk has been changed */
#define FD_OPEN_TIMEOUT 1000
typedef struct BDRVRawState {
int fd;
int type;
unsigned int lseek_err_cnt;
#if defined(__linux__)
/* linux floppy specific */
int fd_open_flags;
int64_t fd_open_time;
int64_t fd_error_time;
int fd_got_error;
int fd_media_changed;
#endif
uint8_t* aligned_buf;
} BDRVRawState;
static int posix_aio_init(void);
static int fd_open(BlockDriverState *bs);
static int raw_open(BlockDriverState *bs, const char *filename, int flags)
{
BDRVRawState *s = bs->opaque;
int fd, open_flags, ret;
posix_aio_init();
s->lseek_err_cnt = 0;
open_flags = O_BINARY;
if ((flags & BDRV_O_ACCESS) == O_RDWR) {
open_flags |= O_RDWR;
} else {
open_flags |= O_RDONLY;
bs->read_only = 1;
}
if (flags & BDRV_O_CREAT)
open_flags |= O_CREAT | O_TRUNC;
/* Use O_DSYNC for write-through caching, no flags for write-back caching,
* and O_DIRECT for no caching. */
if ((flags & BDRV_O_NOCACHE))
open_flags |= O_DIRECT;
else if (!(flags & BDRV_O_CACHE_WB))
open_flags |= O_DSYNC;
s->type = FTYPE_FILE;
fd = open(filename, open_flags, 0644);
if (fd < 0) {
ret = -errno;
if (ret == -EROFS)
ret = -EACCES;
return ret;
}
s->fd = fd;
s->aligned_buf = NULL;
if ((flags & BDRV_O_NOCACHE)) {
s->aligned_buf = qemu_memalign(512, ALIGNED_BUFFER_SIZE);
if (s->aligned_buf == NULL) {
ret = -errno;
close(fd);
return ret;
}
}
return 0;
}
/* XXX: use host sector size if necessary with:
#ifdef DIOCGSECTORSIZE
{
unsigned int sectorsize = 512;
if (!ioctl(fd, DIOCGSECTORSIZE, §orsize) &&
sectorsize > bufsize)
bufsize = sectorsize;
}
#endif
#ifdef CONFIG_COCOA
u_int32_t blockSize = 512;
if ( !ioctl( fd, DKIOCGETBLOCKSIZE, &blockSize ) && blockSize > bufsize) {
bufsize = blockSize;
}
#endif
*/
/*
* offset and count are in bytes, but must be multiples of 512 for files
* opened with O_DIRECT. buf must be aligned to 512 bytes then.
*
* This function may be called without alignment if the caller ensures
* that O_DIRECT is not in effect.
*/
static int raw_pread_aligned(BlockDriverState *bs, int64_t offset,
uint8_t *buf, int count)
{
BDRVRawState *s = bs->opaque;
int ret;
ret = fd_open(bs);
if (ret < 0)
return ret;
if (offset >= 0 && lseek(s->fd, offset, SEEK_SET) == (off_t)-1) {
++(s->lseek_err_cnt);
if(s->lseek_err_cnt <= 10) {
DEBUG_BLOCK_PRINT("raw_pread(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
"] lseek failed : %d = %s\n",
s->fd, bs->filename, offset, buf, count,
bs->total_sectors, errno, strerror(errno));
}
return -1;
}
s->lseek_err_cnt=0;
ret = read(s->fd, buf, count);
if (ret == count)
goto label__raw_read__success;
DEBUG_BLOCK_PRINT("raw_pread(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
"] read failed %d : %d = %s\n",
s->fd, bs->filename, offset, buf, count,
bs->total_sectors, ret, errno, strerror(errno));
/* Try harder for CDrom. */
if (bs->type == BDRV_TYPE_CDROM) {
lseek(s->fd, offset, SEEK_SET);
ret = read(s->fd, buf, count);
if (ret == count)
goto label__raw_read__success;
lseek(s->fd, offset, SEEK_SET);
ret = read(s->fd, buf, count);
if (ret == count)
goto label__raw_read__success;
DEBUG_BLOCK_PRINT("raw_pread(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
"] retry read failed %d : %d = %s\n",
s->fd, bs->filename, offset, buf, count,
bs->total_sectors, ret, errno, strerror(errno));
}
label__raw_read__success:
return ret;
}
/*
* offset and count are in bytes, but must be multiples of 512 for files
* opened with O_DIRECT. buf must be aligned to 512 bytes then.
*
* This function may be called without alignment if the caller ensures
* that O_DIRECT is not in effect.
*/
static int raw_pwrite_aligned(BlockDriverState *bs, int64_t offset,
const uint8_t *buf, int count)
{
BDRVRawState *s = bs->opaque;
int ret;
ret = fd_open(bs);
if (ret < 0)
return -errno;
if (offset >= 0 && lseek(s->fd, offset, SEEK_SET) == (off_t)-1) {
++(s->lseek_err_cnt);
if(s->lseek_err_cnt) {
DEBUG_BLOCK_PRINT("raw_pwrite(%d:%s, %" PRId64 ", %p, %d) [%"
PRId64 "] lseek failed : %d = %s\n",
s->fd, bs->filename, offset, buf, count,
bs->total_sectors, errno, strerror(errno));
}
return -EIO;
}
s->lseek_err_cnt = 0;
ret = write(s->fd, buf, count);
if (ret == count)
goto label__raw_write__success;
DEBUG_BLOCK_PRINT("raw_pwrite(%d:%s, %" PRId64 ", %p, %d) [%" PRId64
"] write failed %d : %d = %s\n",
s->fd, bs->filename, offset, buf, count,
bs->total_sectors, ret, errno, strerror(errno));
label__raw_write__success:
return (ret < 0) ? -errno : ret;
}
/*
* offset and count are in bytes and possibly not aligned. For files opened
* with O_DIRECT, necessary alignments are ensured before calling
* raw_pread_aligned to do the actual read.
*/
static int raw_pread(BlockDriverState *bs, int64_t offset,
uint8_t *buf, int count)
{
BDRVRawState *s = bs->opaque;
int size, ret, shift, sum;
sum = 0;
if (s->aligned_buf != NULL) {
if (offset & 0x1ff) {
/* align offset on a 512 bytes boundary */
shift = offset & 0x1ff;
size = (shift + count + 0x1ff) & ~0x1ff;
if (size > ALIGNED_BUFFER_SIZE)
size = ALIGNED_BUFFER_SIZE;
ret = raw_pread_aligned(bs, offset - shift, s->aligned_buf, size);
if (ret < 0)
return ret;
size = 512 - shift;
if (size > count)
size = count;
memcpy(buf, s->aligned_buf + shift, size);
buf += size;
offset += size;
count -= size;
sum += size;
if (count == 0)
return sum;
}
if (count & 0x1ff || (uintptr_t) buf & 0x1ff) {
/* read on aligned buffer */
while (count) {
size = (count + 0x1ff) & ~0x1ff;
if (size > ALIGNED_BUFFER_SIZE)
size = ALIGNED_BUFFER_SIZE;
ret = raw_pread_aligned(bs, offset, s->aligned_buf, size);
if (ret < 0)
return ret;
size = ret;
if (size > count)
size = count;
memcpy(buf, s->aligned_buf, size);
buf += size;
offset += size;
count -= size;
sum += size;
}
return sum;
}
}
return raw_pread_aligned(bs, offset, buf, count) + sum;
}
/*
* offset and count are in bytes and possibly not aligned. For files opened
* with O_DIRECT, necessary alignments are ensured before calling
* raw_pwrite_aligned to do the actual write.
*/
static int raw_pwrite(BlockDriverState *bs, int64_t offset,
const uint8_t *buf, int count)
{
BDRVRawState *s = bs->opaque;
int size, ret, shift, sum;
sum = 0;
if (s->aligned_buf != NULL) {
if (offset & 0x1ff) {
/* align offset on a 512 bytes boundary */
shift = offset & 0x1ff;
ret = raw_pread_aligned(bs, offset - shift, s->aligned_buf, 512);
if (ret < 0)
return ret;
size = 512 - shift;
if (size > count)
size = count;
memcpy(s->aligned_buf + shift, buf, size);
ret = raw_pwrite_aligned(bs, offset - shift, s->aligned_buf, 512);
if (ret < 0)
return ret;
buf += size;
offset += size;
count -= size;
sum += size;
if (count == 0)
return sum;
}
if (count & 0x1ff || (uintptr_t) buf & 0x1ff) {
while ((size = (count & ~0x1ff)) != 0) {
if (size > ALIGNED_BUFFER_SIZE)
size = ALIGNED_BUFFER_SIZE;
memcpy(s->aligned_buf, buf, size);
ret = raw_pwrite_aligned(bs, offset, s->aligned_buf, size);
if (ret < 0)
return ret;
buf += ret;
offset += ret;
count -= ret;
sum += ret;
}
/* here, count < 512 because (count & ~0x1ff) == 0 */
if (count) {
ret = raw_pread_aligned(bs, offset, s->aligned_buf, 512);
if (ret < 0)
return ret;
memcpy(s->aligned_buf, buf, count);
ret = raw_pwrite_aligned(bs, offset, s->aligned_buf, 512);
if (ret < 0)
return ret;
if (count < ret)
ret = count;
sum += ret;
}
return sum;
}
}
return raw_pwrite_aligned(bs, offset, buf, count) + sum;
}
#ifdef CONFIG_AIO
/***********************************************************/
/* Unix AIO using POSIX AIO */
typedef struct RawAIOCB {
BlockDriverAIOCB common;
struct qemu_paiocb aiocb;
struct RawAIOCB *next;
int ret;
} RawAIOCB;
typedef struct PosixAioState
{
int rfd, wfd;
RawAIOCB *first_aio;
} PosixAioState;
static void posix_aio_read(void *opaque)
{
PosixAioState *s = opaque;
RawAIOCB *acb, **pacb;
int ret;
ssize_t len;
/* read all bytes from signal pipe */
for (;;) {
char bytes[16];
len = read(s->rfd, bytes, sizeof(bytes));
if (len == -1 && errno == EINTR)
continue; /* try again */
if (len == sizeof(bytes))
continue; /* more to read */
break;
}
for(;;) {
pacb = &s->first_aio;
for(;;) {
acb = *pacb;
if (!acb)
goto the_end;
ret = qemu_paio_error(&acb->aiocb);
if (ret == ECANCELED) {
/* remove the request */
*pacb = acb->next;
qemu_aio_release(acb);
} else if (ret != EINPROGRESS) {
/* end of aio */
if (ret == 0) {
ret = qemu_paio_return(&acb->aiocb);
if (ret == acb->aiocb.aio_nbytes)
ret = 0;
else
ret = -EINVAL;
} else {
ret = -ret;
}
/* remove the request */
*pacb = acb->next;
/* call the callback */
acb->common.cb(acb->common.opaque, ret);
qemu_aio_release(acb);
break;
} else {
pacb = &acb->next;
}
}
}
the_end: ;
}
static int posix_aio_flush(void *opaque)
{
PosixAioState *s = opaque;
return !!s->first_aio;
}
static PosixAioState *posix_aio_state;
static void aio_signal_handler(int signum)
{
if (posix_aio_state) {
char byte = 0;
write(posix_aio_state->wfd, &byte, sizeof(byte));
}
qemu_service_io();
}
static int posix_aio_init(void)
{
struct sigaction act;
PosixAioState *s;
int fds[2];
struct qemu_paioinit ai;
if (posix_aio_state)
return 0;
s = qemu_malloc(sizeof(PosixAioState));
sigfillset(&act.sa_mask);
act.sa_flags = 0; /* do not restart syscalls to interrupt select() */
act.sa_handler = aio_signal_handler;
sigaction(SIGUSR2, &act, NULL);
s->first_aio = NULL;
if (pipe(fds) == -1) {
fprintf(stderr, "failed to create pipe\n");
return -errno;
}
s->rfd = fds[0];
s->wfd = fds[1];
fcntl(s->rfd, F_SETFL, O_NONBLOCK);
fcntl(s->wfd, F_SETFL, O_NONBLOCK);
qemu_aio_set_fd_handler(s->rfd, posix_aio_read, NULL, posix_aio_flush, s);
memset(&ai, 0, sizeof(ai));
ai.aio_threads = 64;
ai.aio_num = 64;
qemu_paio_init(&ai);
posix_aio_state = s;
return 0;
}
static RawAIOCB *raw_aio_setup(BlockDriverState *bs,
int64_t sector_num, uint8_t *buf, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
BDRVRawState *s = bs->opaque;
RawAIOCB *acb;
if (fd_open(bs) < 0)
return NULL;
acb = qemu_aio_get(bs, cb, opaque);
if (!acb)
return NULL;
acb->aiocb.aio_fildes = s->fd;
acb->aiocb.ev_signo = SIGUSR2;
acb->aiocb.aio_buf = buf;
if (nb_sectors < 0)
acb->aiocb.aio_nbytes = -nb_sectors;
else
acb->aiocb.aio_nbytes = nb_sectors * 512;
acb->aiocb.aio_offset = sector_num * 512;
acb->next = posix_aio_state->first_aio;
posix_aio_state->first_aio = acb;
return acb;
}
static void raw_aio_em_cb(void* opaque)
{
RawAIOCB *acb = opaque;
acb->common.cb(acb->common.opaque, acb->ret);
qemu_aio_release(acb);
}
static void raw_aio_remove(RawAIOCB *acb)
{
RawAIOCB **pacb;
/* remove the callback from the queue */
pacb = &posix_aio_state->first_aio;
for(;;) {
if (*pacb == NULL) {
fprintf(stderr, "raw_aio_remove: aio request not found!\n");
break;
} else if (*pacb == acb) {
*pacb = acb->next;
qemu_aio_release(acb);
break;
}
pacb = &(*pacb)->next;
}
}
static BlockDriverAIOCB *raw_aio_read(BlockDriverState *bs,
int64_t sector_num, uint8_t *buf, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
RawAIOCB *acb;
/*
* If O_DIRECT is used and the buffer is not aligned fall back
* to synchronous IO.
*/
BDRVRawState *s = bs->opaque;
if (unlikely(s->aligned_buf != NULL && ((uintptr_t) buf % 512))) {
QEMUBH *bh;
acb = qemu_aio_get(bs, cb, opaque);
acb->ret = raw_pread(bs, 512 * sector_num, buf, 512 * nb_sectors);
bh = qemu_bh_new(raw_aio_em_cb, acb);
qemu_bh_schedule(bh);
return &acb->common;
}
acb = raw_aio_setup(bs, sector_num, buf, nb_sectors, cb, opaque);
if (!acb)
return NULL;
if (qemu_paio_read(&acb->aiocb) < 0) {
raw_aio_remove(acb);
return NULL;
}
return &acb->common;
}
static BlockDriverAIOCB *raw_aio_write(BlockDriverState *bs,
int64_t sector_num, const uint8_t *buf, int nb_sectors,
BlockDriverCompletionFunc *cb, void *opaque)
{
RawAIOCB *acb;
/*
* If O_DIRECT is used and the buffer is not aligned fall back
* to synchronous IO.
*/
BDRVRawState *s = bs->opaque;
if (unlikely(s->aligned_buf != NULL && ((uintptr_t) buf % 512))) {
QEMUBH *bh;
acb = qemu_aio_get(bs, cb, opaque);
acb->ret = raw_pwrite(bs, 512 * sector_num, buf, 512 * nb_sectors);
bh = qemu_bh_new(raw_aio_em_cb, acb);
qemu_bh_schedule(bh);
return &acb->common;
}
acb = raw_aio_setup(bs, sector_num, (uint8_t*)buf, nb_sectors, cb, opaque);
if (!acb)
return NULL;
if (qemu_paio_write(&acb->aiocb) < 0) {
raw_aio_remove(acb);
return NULL;
}
return &acb->common;
}
static void raw_aio_cancel(BlockDriverAIOCB *blockacb)
{
int ret;
RawAIOCB *acb = (RawAIOCB *)blockacb;
ret = qemu_paio_cancel(acb->aiocb.aio_fildes, &acb->aiocb);
if (ret == QEMU_PAIO_NOTCANCELED) {
/* fail safe: if the aio could not be canceled, we wait for
it */
while (qemu_paio_error(&acb->aiocb) == EINPROGRESS);
}
raw_aio_remove(acb);
}
#else /* CONFIG_AIO */
static int posix_aio_init(void)
{
return 0;
}
#endif /* CONFIG_AIO */
static void raw_close(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
if (s->fd >= 0) {
close(s->fd);
s->fd = -1;
if (s->aligned_buf != NULL)
qemu_free(s->aligned_buf);
}
}
static int raw_truncate(BlockDriverState *bs, int64_t offset)
{
BDRVRawState *s = bs->opaque;
if (s->type != FTYPE_FILE)
return -ENOTSUP;
if (ftruncate(s->fd, offset) < 0)
return -errno;
return 0;
}
#ifdef __OpenBSD__
static int64_t raw_getlength(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
int fd = s->fd;
struct stat st;
if (fstat(fd, &st))
return -1;
if (S_ISCHR(st.st_mode) || S_ISBLK(st.st_mode)) {
struct disklabel dl;
if (ioctl(fd, DIOCGDINFO, &dl))
return -1;
return (uint64_t)dl.d_secsize *
dl.d_partitions[DISKPART(st.st_rdev)].p_size;
} else
return st.st_size;
}
#else /* !__OpenBSD__ */
static int64_t raw_getlength(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
int fd = s->fd;
int64_t size;
#ifdef _BSD
struct stat sb;
#endif
#ifdef __sun__
struct dk_minfo minfo;
int rv;
#endif
int ret;
ret = fd_open(bs);
if (ret < 0)
return ret;
#ifdef _BSD
if (!fstat(fd, &sb) && (S_IFCHR & sb.st_mode)) {
#ifdef DIOCGMEDIASIZE
if (ioctl(fd, DIOCGMEDIASIZE, (off_t *)&size))
#elif defined(DIOCGPART)
{
struct partinfo pi;
if (ioctl(fd, DIOCGPART, &pi) == 0)
size = pi.media_size;
else
size = 0;
}
if (size == 0)
#endif
#ifdef CONFIG_COCOA
size = LONG_LONG_MAX;
#else
size = lseek(fd, 0LL, SEEK_END);
#endif
} else
#endif
#ifdef __sun__
/*
* use the DKIOCGMEDIAINFO ioctl to read the size.
*/
rv = ioctl ( fd, DKIOCGMEDIAINFO, &minfo );
if ( rv != -1 ) {
size = minfo.dki_lbsize * minfo.dki_capacity;
} else /* there are reports that lseek on some devices
fails, but irc discussion said that contingency
on contingency was overkill */
#endif
{
size = lseek(fd, 0, SEEK_END);
}
return size;
}
#endif
static int raw_create(const char *filename, int64_t total_size,
const char *backing_file, int flags)
{
int fd;
if (flags || backing_file)
return -ENOTSUP;
fd = open(filename, O_WRONLY | O_CREAT | O_TRUNC | O_BINARY,
0644);
if (fd < 0)
return -EIO;
ftruncate(fd, total_size * 512);
close(fd);
return 0;
}
static void raw_flush(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
fsync(s->fd);
}
BlockDriver bdrv_raw = {
"raw",
sizeof(BDRVRawState),
NULL, /* no probe for protocols */
raw_open,
NULL,
NULL,
raw_close,
raw_create,
raw_flush,
#ifdef CONFIG_AIO
.bdrv_aio_read = raw_aio_read,
.bdrv_aio_write = raw_aio_write,
.bdrv_aio_cancel = raw_aio_cancel,
.aiocb_size = sizeof(RawAIOCB),
#endif
.bdrv_pread = raw_pread,
.bdrv_pwrite = raw_pwrite,
.bdrv_truncate = raw_truncate,
.bdrv_getlength = raw_getlength,
};
/***********************************************/
/* host device */
#ifdef CONFIG_COCOA
static kern_return_t FindEjectableCDMedia( io_iterator_t *mediaIterator );
static kern_return_t GetBSDPath( io_iterator_t mediaIterator, char *bsdPath, CFIndex maxPathSize );
kern_return_t FindEjectableCDMedia( io_iterator_t *mediaIterator )
{
kern_return_t kernResult;
mach_port_t masterPort;
CFMutableDictionaryRef classesToMatch;
kernResult = IOMasterPort( MACH_PORT_NULL, &masterPort );
if ( KERN_SUCCESS != kernResult ) {
printf( "IOMasterPort returned %d\n", kernResult );
}
classesToMatch = IOServiceMatching( kIOCDMediaClass );
if ( classesToMatch == NULL ) {
printf( "IOServiceMatching returned a NULL dictionary.\n" );
} else {
CFDictionarySetValue( classesToMatch, CFSTR( kIOMediaEjectableKey ), kCFBooleanTrue );
}
kernResult = IOServiceGetMatchingServices( masterPort, classesToMatch, mediaIterator );
if ( KERN_SUCCESS != kernResult )
{
printf( "IOServiceGetMatchingServices returned %d\n", kernResult );
}
return kernResult;
}
kern_return_t GetBSDPath( io_iterator_t mediaIterator, char *bsdPath, CFIndex maxPathSize )
{
io_object_t nextMedia;
kern_return_t kernResult = KERN_FAILURE;
*bsdPath = '\0';
nextMedia = IOIteratorNext( mediaIterator );
if ( nextMedia )
{
CFTypeRef bsdPathAsCFString;
bsdPathAsCFString = IORegistryEntryCreateCFProperty( nextMedia, CFSTR( kIOBSDNameKey ), kCFAllocatorDefault, 0 );
if ( bsdPathAsCFString ) {
size_t devPathLength;
strcpy( bsdPath, _PATH_DEV );
strcat( bsdPath, "r" );
devPathLength = strlen( bsdPath );
if ( CFStringGetCString( bsdPathAsCFString, bsdPath + devPathLength, maxPathSize - devPathLength, kCFStringEncodingASCII ) ) {
kernResult = KERN_SUCCESS;
}
CFRelease( bsdPathAsCFString );
}
IOObjectRelease( nextMedia );
}
return kernResult;
}
#endif
static int hdev_open(BlockDriverState *bs, const char *filename, int flags)
{
BDRVRawState *s = bs->opaque;
int fd, open_flags, ret;
posix_aio_init();
#ifdef CONFIG_COCOA
if (strstart(filename, "/dev/cdrom", NULL)) {
kern_return_t kernResult;
io_iterator_t mediaIterator;
char bsdPath[ MAXPATHLEN ];
int fd;
kernResult = FindEjectableCDMedia( &mediaIterator );
kernResult = GetBSDPath( mediaIterator, bsdPath, sizeof( bsdPath ) );
if ( bsdPath[ 0 ] != '\0' ) {
strcat(bsdPath,"s0");
/* some CDs don't have a partition 0 */
fd = open(bsdPath, O_RDONLY | O_BINARY | O_LARGEFILE);
if (fd < 0) {
bsdPath[strlen(bsdPath)-1] = '1';
} else {
close(fd);
}
filename = bsdPath;
}
if ( mediaIterator )
IOObjectRelease( mediaIterator );
}
#endif
open_flags = O_BINARY;
if ((flags & BDRV_O_ACCESS) == O_RDWR) {
open_flags |= O_RDWR;
} else {
open_flags |= O_RDONLY;
bs->read_only = 1;
}
/* Use O_DSYNC for write-through caching, no flags for write-back caching,
* and O_DIRECT for no caching. */
if ((flags & BDRV_O_NOCACHE))
open_flags |= O_DIRECT;
else if (!(flags & BDRV_O_CACHE_WB))
open_flags |= O_DSYNC;
s->type = FTYPE_FILE;
#if defined(__linux__)
if (strstart(filename, "/dev/cd", NULL)) {
/* open will not fail even if no CD is inserted */
open_flags |= O_NONBLOCK;
s->type = FTYPE_CD;
} else if (strstart(filename, "/dev/fd", NULL)) {
s->type = FTYPE_FD;
s->fd_open_flags = open_flags;
/* open will not fail even if no floppy is inserted */
open_flags |= O_NONBLOCK;
} else if (strstart(filename, "/dev/sg", NULL)) {
bs->sg = 1;
}
#endif
fd = open(filename, open_flags, 0644);
if (fd < 0) {
ret = -errno;
if (ret == -EROFS)
ret = -EACCES;
return ret;
}
s->fd = fd;
#if defined(__linux__)
/* close fd so that we can reopen it as needed */
if (s->type == FTYPE_FD) {
close(s->fd);
s->fd = -1;
s->fd_media_changed = 1;
}
#endif
return 0;
}
#if defined(__linux__)
/* Note: we do not have a reliable method to detect if the floppy is
present. The current method is to try to open the floppy at every
I/O and to keep it opened during a few hundreds of ms. */
static int fd_open(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
int last_media_present;
if (s->type != FTYPE_FD)
return 0;
last_media_present = (s->fd >= 0);
if (s->fd >= 0 &&
(qemu_get_clock(rt_clock) - s->fd_open_time) >= FD_OPEN_TIMEOUT) {
close(s->fd);
s->fd = -1;
#ifdef DEBUG_FLOPPY
printf("Floppy closed\n");
#endif
}
if (s->fd < 0) {
if (s->fd_got_error &&
(qemu_get_clock(rt_clock) - s->fd_error_time) < FD_OPEN_TIMEOUT) {
#ifdef DEBUG_FLOPPY
printf("No floppy (open delayed)\n");
#endif
return -EIO;
}
s->fd = open(bs->filename, s->fd_open_flags);
if (s->fd < 0) {
s->fd_error_time = qemu_get_clock(rt_clock);
s->fd_got_error = 1;
if (last_media_present)
s->fd_media_changed = 1;
#ifdef DEBUG_FLOPPY
printf("No floppy\n");
#endif
return -EIO;
}
#ifdef DEBUG_FLOPPY
printf("Floppy opened\n");
#endif
}
if (!last_media_present)
s->fd_media_changed = 1;
s->fd_open_time = qemu_get_clock(rt_clock);
s->fd_got_error = 0;
return 0;
}
static int raw_is_inserted(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
int ret;
switch(s->type) {
case FTYPE_CD:
ret = ioctl(s->fd, CDROM_DRIVE_STATUS, CDSL_CURRENT);
if (ret == CDS_DISC_OK)
return 1;
else
return 0;
break;
case FTYPE_FD:
ret = fd_open(bs);
return (ret >= 0);
default:
return 1;
}
}
/* currently only used by fdc.c, but a CD version would be good too */
static int raw_media_changed(BlockDriverState *bs)
{
BDRVRawState *s = bs->opaque;
switch(s->type) {
case FTYPE_FD:
{
int ret;
/* XXX: we do not have a true media changed indication. It
does not work if the floppy is changed without trying
to read it */
fd_open(bs);
ret = s->fd_media_changed;
s->fd_media_changed = 0;
#ifdef DEBUG_FLOPPY
printf("Floppy changed=%d\n", ret);
#endif
return ret;
}
default:
return -ENOTSUP;
}
}
static int raw_eject(BlockDriverState *bs, int eject_flag)
{
BDRVRawState *s = bs->opaque;
switch(s->type) {
case FTYPE_CD:
if (eject_flag) {
if (ioctl (s->fd, CDROMEJECT, NULL) < 0)
perror("CDROMEJECT");
} else {
if (ioctl (s->fd, CDROMCLOSETRAY, NULL) < 0)
perror("CDROMEJECT");
}
break;
case FTYPE_FD:
{
int fd;
if (s->fd >= 0) {
close(s->fd);
s->fd = -1;
}
fd = open(bs->filename, s->fd_open_flags | O_NONBLOCK);
if (fd >= 0) {
if (ioctl(fd, FDEJECT, 0) < 0)
perror("FDEJECT");
close(fd);
}
}
break;
default:
return -ENOTSUP;
}
return 0;
}
static int raw_set_locked(BlockDriverState *bs, int locked)
{
BDRVRawState *s = bs->opaque;
switch(s->type) {
case FTYPE_CD:
if (ioctl (s->fd, CDROM_LOCKDOOR, locked) < 0) {
/* Note: an error can happen if the distribution automatically
mounts the CD-ROM */
// perror("CDROM_LOCKDOOR");
}
break;
default:
return -ENOTSUP;
}
return 0;
}
static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
{
BDRVRawState *s = bs->opaque;
return ioctl(s->fd, req, buf);
}
#else
static int fd_open(BlockDriverState *bs)
{
return 0;
}
static int raw_is_inserted(BlockDriverState *bs)
{
return 1;
}
static int raw_media_changed(BlockDriverState *bs)
{
return -ENOTSUP;
}
static int raw_eject(BlockDriverState *bs, int eject_flag)
{
return -ENOTSUP;
}
static int raw_set_locked(BlockDriverState *bs, int locked)
{
return -ENOTSUP;
}
static int raw_ioctl(BlockDriverState *bs, unsigned long int req, void *buf)
{
return -ENOTSUP;
}
#endif /* !linux */
BlockDriver bdrv_host_device = {
"host_device",
sizeof(BDRVRawState),
NULL, /* no probe for protocols */
hdev_open,
NULL,
NULL,
raw_close,
NULL,
raw_flush,
#ifdef CONFIG_AIO
.bdrv_aio_read = raw_aio_read,
.bdrv_aio_write = raw_aio_write,
.bdrv_aio_cancel = raw_aio_cancel,
.aiocb_size = sizeof(RawAIOCB),
#endif
.bdrv_pread = raw_pread,
.bdrv_pwrite = raw_pwrite,
.bdrv_getlength = raw_getlength,
/* removable device support */
.bdrv_is_inserted = raw_is_inserted,
.bdrv_media_changed = raw_media_changed,
.bdrv_eject = raw_eject,
.bdrv_set_locked = raw_set_locked,
/* generic scsi device */
.bdrv_ioctl = raw_ioctl,
};
|