-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcommands-linux.c
2244 lines (1962 loc) · 66.8 KB
/
commands-linux.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 Guest Agent Linux-specific command implementations
*
* Copyright IBM Corp. 2011
*
* Authors:
* Michael Roth <[email protected]>
* Michal Privoznik <[email protected]>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "qga-qapi-commands.h"
#include "qapi/error.h"
#include "commands-common.h"
#include "cutils.h"
#include <mntent.h>
#include <sys/ioctl.h>
#include <mntent.h>
#include <linux/nvme_ioctl.h>
#include "block/nvme.h"
#ifdef CONFIG_LIBUDEV
#include <libudev.h>
#endif
#ifdef HAVE_GETIFADDRS
#include <net/if.h>
#endif
#include <sys/statvfs.h>
#if defined(CONFIG_FSFREEZE) || defined(CONFIG_FSTRIM)
static int dev_major_minor(const char *devpath,
unsigned int *devmajor, unsigned int *devminor)
{
struct stat st;
*devmajor = 0;
*devminor = 0;
if (stat(devpath, &st) < 0) {
slog("failed to stat device file '%s': %s", devpath, strerror(errno));
return -1;
}
if (S_ISDIR(st.st_mode)) {
/* It is bind mount */
return -2;
}
if (S_ISBLK(st.st_mode)) {
*devmajor = major(st.st_rdev);
*devminor = minor(st.st_rdev);
return 0;
}
return -1;
}
/*
* Check if we already have the devmajor:devminor in the mounts
* If thats the case return true.
*/
static bool dev_exists(FsMountList *mounts, unsigned int devmajor, unsigned int devminor)
{
FsMount *mount;
QTAILQ_FOREACH(mount, mounts, next) {
if (mount->devmajor == devmajor && mount->devminor == devminor) {
return true;
}
}
return false;
}
static bool build_fs_mount_list_from_mtab(FsMountList *mounts, Error **errp)
{
struct mntent *ment;
FsMount *mount;
char const *mtab = "/proc/self/mounts";
FILE *fp;
unsigned int devmajor, devminor;
fp = setmntent(mtab, "r");
if (!fp) {
error_setg(errp, "failed to open mtab file: '%s'", mtab);
return false;
}
while ((ment = getmntent(fp))) {
/*
* An entry which device name doesn't start with a '/' is
* either a dummy file system or a network file system.
* Add special handling for smbfs and cifs as is done by
* coreutils as well.
*/
if ((ment->mnt_fsname[0] != '/') ||
(strcmp(ment->mnt_type, "smbfs") == 0) ||
(strcmp(ment->mnt_type, "cifs") == 0)) {
continue;
}
if (dev_major_minor(ment->mnt_fsname, &devmajor, &devminor) == -2) {
/* Skip bind mounts */
continue;
}
if (dev_exists(mounts, devmajor, devminor)) {
/* Skip already existing devices (bind mounts) */
continue;
}
mount = g_new0(FsMount, 1);
mount->dirname = g_strdup(ment->mnt_dir);
mount->devtype = g_strdup(ment->mnt_type);
mount->devmajor = devmajor;
mount->devminor = devminor;
QTAILQ_INSERT_TAIL(mounts, mount, next);
}
endmntent(fp);
return true;
}
static void decode_mntname(char *name, int len)
{
int i, j = 0;
for (i = 0; i <= len; i++) {
if (name[i] != '\\') {
name[j++] = name[i];
} else if (name[i + 1] == '\\') {
name[j++] = '\\';
i++;
} else if (name[i + 1] >= '0' && name[i + 1] <= '3' &&
name[i + 2] >= '0' && name[i + 2] <= '7' &&
name[i + 3] >= '0' && name[i + 3] <= '7') {
name[j++] = (name[i + 1] - '0') * 64 +
(name[i + 2] - '0') * 8 +
(name[i + 3] - '0');
i += 3;
} else {
name[j++] = name[i];
}
}
}
/*
* Walk the mount table and build a list of local file systems
*/
bool build_fs_mount_list(FsMountList *mounts, Error **errp)
{
FsMount *mount;
char const *mountinfo = "/proc/self/mountinfo";
FILE *fp;
char *line = NULL, *dash;
size_t n;
char check;
unsigned int devmajor, devminor;
int ret, dir_s, dir_e, type_s, type_e, dev_s, dev_e;
fp = fopen(mountinfo, "r");
if (!fp) {
return build_fs_mount_list_from_mtab(mounts, errp);
}
while (getline(&line, &n, fp) != -1) {
ret = sscanf(line, "%*u %*u %u:%u %*s %n%*s%n%c",
&devmajor, &devminor, &dir_s, &dir_e, &check);
if (ret < 3) {
continue;
}
dash = strstr(line + dir_e, " - ");
if (!dash) {
continue;
}
ret = sscanf(dash, " - %n%*s%n %n%*s%n%c",
&type_s, &type_e, &dev_s, &dev_e, &check);
if (ret < 1) {
continue;
}
line[dir_e] = 0;
dash[type_e] = 0;
dash[dev_e] = 0;
decode_mntname(line + dir_s, dir_e - dir_s);
decode_mntname(dash + dev_s, dev_e - dev_s);
if (devmajor == 0) {
/* btrfs reports major number = 0 */
if (strcmp("btrfs", dash + type_s) != 0 ||
dev_major_minor(dash + dev_s, &devmajor, &devminor) < 0) {
continue;
}
}
if (dev_exists(mounts, devmajor, devminor)) {
/* Skip already existing devices (bind mounts) */
continue;
}
mount = g_new0(FsMount, 1);
mount->dirname = g_strdup(line + dir_s);
mount->devtype = g_strdup(dash + type_s);
mount->devmajor = devmajor;
mount->devminor = devminor;
QTAILQ_INSERT_TAIL(mounts, mount, next);
}
free(line);
fclose(fp);
return true;
}
#endif /* CONFIG_FSFREEZE || CONFIG_FSTRIM */
#ifdef CONFIG_FSFREEZE
/*
* Walk list of mounted file systems in the guest, and freeze the ones which
* are real local file systems.
*/
int64_t qmp_guest_fsfreeze_do_freeze_list(bool has_mountpoints,
strList *mountpoints,
FsMountList mounts,
Error **errp)
{
struct FsMount *mount;
strList *list;
int fd, ret, i = 0;
QTAILQ_FOREACH_REVERSE(mount, &mounts, next) {
/* To issue fsfreeze in the reverse order of mounts, check if the
* mount is listed in the list here */
if (has_mountpoints) {
for (list = mountpoints; list; list = list->next) {
if (strcmp(list->value, mount->dirname) == 0) {
break;
}
}
if (!list) {
continue;
}
}
fd = qga_open_cloexec(mount->dirname, O_RDONLY, 0);
if (fd == -1) {
error_setg_errno(errp, errno, "failed to open %s", mount->dirname);
return -1;
}
/* we try to cull filesystems we know won't work in advance, but other
* filesystems may not implement fsfreeze for less obvious reasons.
* these will report EOPNOTSUPP. we simply ignore these when tallying
* the number of frozen filesystems.
* if a filesystem is mounted more than once (aka bind mount) a
* consecutive attempt to freeze an already frozen filesystem will
* return EBUSY.
*
* any other error means a failure to freeze a filesystem we
* expect to be freezable, so return an error in those cases
* and return system to thawed state.
*/
ret = ioctl(fd, FIFREEZE);
if (ret == -1) {
if (errno != EOPNOTSUPP && errno != EBUSY) {
error_setg_errno(errp, errno, "failed to freeze %s",
mount->dirname);
close(fd);
return -1;
}
} else {
i++;
}
close(fd);
}
return i;
}
int qmp_guest_fsfreeze_do_thaw(Error **errp)
{
int ret;
FsMountList mounts;
FsMount *mount;
int fd, i = 0, logged;
Error *local_err = NULL;
QTAILQ_INIT(&mounts);
if (!build_fs_mount_list(&mounts, &local_err)) {
error_propagate(errp, local_err);
return -1;
}
QTAILQ_FOREACH(mount, &mounts, next) {
logged = false;
fd = qga_open_cloexec(mount->dirname, O_RDONLY, 0);
if (fd == -1) {
continue;
}
/* we have no way of knowing whether a filesystem was actually unfrozen
* as a result of a successful call to FITHAW, only that if an error
* was returned the filesystem was *not* unfrozen by that particular
* call.
*
* since multiple preceding FIFREEZEs require multiple calls to FITHAW
* to unfreeze, continuing issuing FITHAW until an error is returned,
* in which case either the filesystem is in an unfreezable state, or,
* more likely, it was thawed previously (and remains so afterward).
*
* also, since the most recent successful call is the one that did
* the actual unfreeze, we can use this to provide an accurate count
* of the number of filesystems unfrozen by guest-fsfreeze-thaw, which
* may * be useful for determining whether a filesystem was unfrozen
* during the freeze/thaw phase by a process other than qemu-ga.
*/
do {
ret = ioctl(fd, FITHAW);
if (ret == 0 && !logged) {
i++;
logged = true;
}
} while (ret == 0);
close(fd);
}
free_fs_mount_list(&mounts);
return i;
}
#endif /* CONFIG_FSFREEZE */
#if defined(CONFIG_FSFREEZE)
static char *get_pci_driver(char const *syspath, int pathlen, Error **errp)
{
char *path;
char *dpath;
char *driver = NULL;
char buf[PATH_MAX];
ssize_t len;
path = g_strndup(syspath, pathlen);
dpath = g_strdup_printf("%s/driver", path);
len = readlink(dpath, buf, sizeof(buf) - 1);
if (len != -1) {
buf[len] = 0;
driver = g_path_get_basename(buf);
}
g_free(dpath);
g_free(path);
return driver;
}
static int compare_uint(const void *_a, const void *_b)
{
unsigned int a = *(unsigned int *)_a;
unsigned int b = *(unsigned int *)_b;
return a < b ? -1 : a > b ? 1 : 0;
}
/* Walk the specified sysfs and build a sorted list of host or ata numbers */
static int build_hosts(char const *syspath, char const *host, bool ata,
unsigned int *hosts, int hosts_max, Error **errp)
{
char *path;
DIR *dir;
struct dirent *entry;
int i = 0;
path = g_strndup(syspath, host - syspath);
dir = opendir(path);
if (!dir) {
error_setg_errno(errp, errno, "opendir(\"%s\")", path);
g_free(path);
return -1;
}
while (i < hosts_max) {
entry = readdir(dir);
if (!entry) {
break;
}
if (ata && sscanf(entry->d_name, "ata%d", hosts + i) == 1) {
++i;
} else if (!ata && sscanf(entry->d_name, "host%d", hosts + i) == 1) {
++i;
}
}
qsort(hosts, i, sizeof(hosts[0]), compare_uint);
g_free(path);
closedir(dir);
return i;
}
/*
* Store disk device info for devices on the PCI bus.
* Returns true if information has been stored, or false for failure.
*/
static bool build_guest_fsinfo_for_pci_dev(char const *syspath,
GuestDiskAddress *disk,
Error **errp)
{
unsigned int pci[4], host, hosts[8], tgt[3];
int i, nhosts = 0, pcilen;
GuestPCIAddress *pciaddr = disk->pci_controller;
bool has_ata = false, has_host = false, has_tgt = false;
char *p, *q, *driver = NULL;
bool ret = false;
p = strstr(syspath, "/devices/pci");
if (!p || sscanf(p + 12, "%*x:%*x/%x:%x:%x.%x%n",
pci, pci + 1, pci + 2, pci + 3, &pcilen) < 4) {
g_debug("only pci device is supported: sysfs path '%s'", syspath);
return false;
}
p += 12 + pcilen;
while (true) {
driver = get_pci_driver(syspath, p - syspath, errp);
if (driver && (g_str_equal(driver, "ata_piix") ||
g_str_equal(driver, "sym53c8xx") ||
g_str_equal(driver, "virtio-pci") ||
g_str_equal(driver, "ahci") ||
g_str_equal(driver, "nvme") ||
g_str_equal(driver, "xhci_hcd") ||
g_str_equal(driver, "ehci-pci"))) {
break;
}
g_free(driver);
if (sscanf(p, "/%x:%x:%x.%x%n",
pci, pci + 1, pci + 2, pci + 3, &pcilen) == 4) {
p += pcilen;
continue;
}
g_debug("unsupported driver or sysfs path '%s'", syspath);
return false;
}
p = strstr(syspath, "/target");
if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u",
tgt, tgt + 1, tgt + 2) == 3) {
has_tgt = true;
}
p = strstr(syspath, "/ata");
if (p) {
q = p + 4;
has_ata = true;
} else {
p = strstr(syspath, "/host");
q = p + 5;
}
if (p && sscanf(q, "%u", &host) == 1) {
has_host = true;
nhosts = build_hosts(syspath, p, has_ata, hosts,
ARRAY_SIZE(hosts), errp);
if (nhosts < 0) {
goto cleanup;
}
}
pciaddr->domain = pci[0];
pciaddr->bus = pci[1];
pciaddr->slot = pci[2];
pciaddr->function = pci[3];
if (strcmp(driver, "ata_piix") == 0) {
/* a host per ide bus, target*:0:<unit>:0 */
if (!has_host || !has_tgt) {
g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
goto cleanup;
}
for (i = 0; i < nhosts; i++) {
if (host == hosts[i]) {
disk->bus_type = GUEST_DISK_BUS_TYPE_IDE;
disk->bus = i;
disk->unit = tgt[1];
break;
}
}
if (i >= nhosts) {
g_debug("no host for '%s' (driver '%s')", syspath, driver);
goto cleanup;
}
} else if (strcmp(driver, "sym53c8xx") == 0) {
/* scsi(LSI Logic): target*:0:<unit>:0 */
if (!has_tgt) {
g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
goto cleanup;
}
disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI;
disk->unit = tgt[1];
} else if (strcmp(driver, "virtio-pci") == 0) {
if (has_tgt) {
/* virtio-scsi: target*:0:0:<unit> */
disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI;
disk->unit = tgt[2];
} else {
/* virtio-blk: 1 disk per 1 device */
disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO;
}
} else if (strcmp(driver, "ahci") == 0) {
/* ahci: 1 host per 1 unit */
if (!has_host || !has_tgt) {
g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
goto cleanup;
}
for (i = 0; i < nhosts; i++) {
if (host == hosts[i]) {
disk->unit = i;
disk->bus_type = GUEST_DISK_BUS_TYPE_SATA;
break;
}
}
if (i >= nhosts) {
g_debug("no host for '%s' (driver '%s')", syspath, driver);
goto cleanup;
}
} else if (strcmp(driver, "nvme") == 0) {
disk->bus_type = GUEST_DISK_BUS_TYPE_NVME;
} else if (strcmp(driver, "ehci-pci") == 0 || strcmp(driver, "xhci_hcd") == 0) {
disk->bus_type = GUEST_DISK_BUS_TYPE_USB;
} else {
g_debug("unknown driver '%s' (sysfs path '%s')", driver, syspath);
goto cleanup;
}
ret = true;
cleanup:
g_free(driver);
return ret;
}
/*
* Store disk device info for non-PCI virtio devices (for example s390x
* channel I/O devices). Returns true if information has been stored, or
* false for failure.
*/
static bool build_guest_fsinfo_for_nonpci_virtio(char const *syspath,
GuestDiskAddress *disk,
Error **errp)
{
unsigned int tgt[3];
char *p;
if (!strstr(syspath, "/virtio") || !strstr(syspath, "/block")) {
g_debug("Unsupported virtio device '%s'", syspath);
return false;
}
p = strstr(syspath, "/target");
if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u",
&tgt[0], &tgt[1], &tgt[2]) == 3) {
/* virtio-scsi: target*:0:<target>:<unit> */
disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI;
disk->bus = tgt[0];
disk->target = tgt[1];
disk->unit = tgt[2];
} else {
/* virtio-blk: 1 disk per 1 device */
disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO;
}
return true;
}
/*
* Store disk device info for CCW devices (s390x channel I/O devices).
* Returns true if information has been stored, or false for failure.
*/
static bool build_guest_fsinfo_for_ccw_dev(char const *syspath,
GuestDiskAddress *disk,
Error **errp)
{
unsigned int cssid, ssid, subchno, devno;
char *p;
p = strstr(syspath, "/devices/css");
if (!p || sscanf(p + 12, "%*x/%x.%x.%x/%*x.%*x.%x/",
&cssid, &ssid, &subchno, &devno) < 4) {
g_debug("could not parse ccw device sysfs path: %s", syspath);
return false;
}
disk->ccw_address = g_new0(GuestCCWAddress, 1);
disk->ccw_address->cssid = cssid;
disk->ccw_address->ssid = ssid;
disk->ccw_address->subchno = subchno;
disk->ccw_address->devno = devno;
if (strstr(p, "/virtio")) {
build_guest_fsinfo_for_nonpci_virtio(syspath, disk, errp);
}
return true;
}
/* Store disk device info specified by @sysfs into @fs */
static void build_guest_fsinfo_for_real_device(char const *syspath,
GuestFilesystemInfo *fs,
Error **errp)
{
GuestDiskAddress *disk;
GuestPCIAddress *pciaddr;
bool has_hwinf;
#ifdef CONFIG_LIBUDEV
struct udev *udev = NULL;
struct udev_device *udevice = NULL;
#endif
pciaddr = g_new0(GuestPCIAddress, 1);
pciaddr->domain = -1; /* -1 means field is invalid */
pciaddr->bus = -1;
pciaddr->slot = -1;
pciaddr->function = -1;
disk = g_new0(GuestDiskAddress, 1);
disk->pci_controller = pciaddr;
disk->bus_type = GUEST_DISK_BUS_TYPE_UNKNOWN;
#ifdef CONFIG_LIBUDEV
udev = udev_new();
udevice = udev_device_new_from_syspath(udev, syspath);
if (udev == NULL || udevice == NULL) {
g_debug("failed to query udev");
} else {
const char *devnode, *serial;
devnode = udev_device_get_devnode(udevice);
if (devnode != NULL) {
disk->dev = g_strdup(devnode);
}
serial = udev_device_get_property_value(udevice, "ID_SERIAL");
if (serial != NULL && *serial != 0) {
disk->serial = g_strdup(serial);
}
}
udev_unref(udev);
udev_device_unref(udevice);
#endif
if (strstr(syspath, "/devices/pci")) {
has_hwinf = build_guest_fsinfo_for_pci_dev(syspath, disk, errp);
} else if (strstr(syspath, "/devices/css")) {
has_hwinf = build_guest_fsinfo_for_ccw_dev(syspath, disk, errp);
} else if (strstr(syspath, "/virtio")) {
has_hwinf = build_guest_fsinfo_for_nonpci_virtio(syspath, disk, errp);
} else {
g_debug("Unsupported device type for '%s'", syspath);
has_hwinf = false;
}
if (has_hwinf || disk->dev || disk->serial) {
QAPI_LIST_PREPEND(fs->disk, disk);
} else {
qapi_free_GuestDiskAddress(disk);
}
}
static void build_guest_fsinfo_for_device(char const *devpath,
GuestFilesystemInfo *fs,
Error **errp);
/* Store a list of slave devices of virtual volume specified by @syspath into
* @fs */
static void build_guest_fsinfo_for_virtual_device(char const *syspath,
GuestFilesystemInfo *fs,
Error **errp)
{
Error *err = NULL;
DIR *dir;
char *dirpath;
struct dirent *entry;
dirpath = g_strdup_printf("%s/slaves", syspath);
dir = opendir(dirpath);
if (!dir) {
if (errno != ENOENT) {
error_setg_errno(errp, errno, "opendir(\"%s\")", dirpath);
}
g_free(dirpath);
return;
}
for (;;) {
errno = 0;
entry = readdir(dir);
if (entry == NULL) {
if (errno) {
error_setg_errno(errp, errno, "readdir(\"%s\")", dirpath);
}
break;
}
if (entry->d_type == DT_LNK) {
char *path;
g_debug(" slave device '%s'", entry->d_name);
path = g_strdup_printf("%s/slaves/%s", syspath, entry->d_name);
build_guest_fsinfo_for_device(path, fs, &err);
g_free(path);
if (err) {
error_propagate(errp, err);
break;
}
}
}
g_free(dirpath);
closedir(dir);
}
static bool is_disk_virtual(const char *devpath, Error **errp)
{
g_autofree char *syspath = realpath(devpath, NULL);
if (!syspath) {
error_setg_errno(errp, errno, "realpath(\"%s\")", devpath);
return false;
}
return strstr(syspath, "/devices/virtual/block/") != NULL;
}
/* Dispatch to functions for virtual/real device */
static void build_guest_fsinfo_for_device(char const *devpath,
GuestFilesystemInfo *fs,
Error **errp)
{
ERRP_GUARD();
g_autofree char *syspath = NULL;
bool is_virtual = false;
syspath = realpath(devpath, NULL);
if (!syspath) {
if (errno != ENOENT) {
error_setg_errno(errp, errno, "realpath(\"%s\")", devpath);
return;
}
/* ENOENT: This devpath may not exist because of container config */
if (!fs->name) {
fs->name = g_path_get_basename(devpath);
}
return;
}
if (!fs->name) {
fs->name = g_path_get_basename(syspath);
}
g_debug(" parse sysfs path '%s'", syspath);
is_virtual = is_disk_virtual(syspath, errp);
if (*errp != NULL) {
return;
}
if (is_virtual) {
build_guest_fsinfo_for_virtual_device(syspath, fs, errp);
} else {
build_guest_fsinfo_for_real_device(syspath, fs, errp);
}
}
#ifdef CONFIG_LIBUDEV
/*
* Wrapper around build_guest_fsinfo_for_device() for getting just
* the disk address.
*/
static GuestDiskAddress *get_disk_address(const char *syspath, Error **errp)
{
g_autoptr(GuestFilesystemInfo) fs = NULL;
fs = g_new0(GuestFilesystemInfo, 1);
build_guest_fsinfo_for_device(syspath, fs, errp);
if (fs->disk != NULL) {
return g_steal_pointer(&fs->disk->value);
}
return NULL;
}
static char *get_alias_for_syspath(const char *syspath)
{
struct udev *udev = NULL;
struct udev_device *udevice = NULL;
char *ret = NULL;
udev = udev_new();
if (udev == NULL) {
g_debug("failed to query udev");
goto out;
}
udevice = udev_device_new_from_syspath(udev, syspath);
if (udevice == NULL) {
g_debug("failed to query udev for path: %s", syspath);
goto out;
} else {
const char *alias = udev_device_get_property_value(
udevice, "DM_NAME");
/*
* NULL means there was an error and empty string means there is no
* alias. In case of no alias we return NULL instead of empty string.
*/
if (alias == NULL) {
g_debug("failed to query udev for device alias for: %s",
syspath);
} else if (*alias != 0) {
ret = g_strdup(alias);
}
}
out:
udev_unref(udev);
udev_device_unref(udevice);
return ret;
}
static char *get_device_for_syspath(const char *syspath)
{
struct udev *udev = NULL;
struct udev_device *udevice = NULL;
char *ret = NULL;
udev = udev_new();
if (udev == NULL) {
g_debug("failed to query udev");
goto out;
}
udevice = udev_device_new_from_syspath(udev, syspath);
if (udevice == NULL) {
g_debug("failed to query udev for path: %s", syspath);
goto out;
} else {
ret = g_strdup(udev_device_get_devnode(udevice));
}
out:
udev_unref(udev);
udev_device_unref(udevice);
return ret;
}
static void get_disk_deps(const char *disk_dir, GuestDiskInfo *disk)
{
g_autofree char *deps_dir = NULL;
const gchar *dep;
GDir *dp_deps = NULL;
/* List dependent disks */
deps_dir = g_strdup_printf("%s/slaves", disk_dir);
g_debug(" listing entries in: %s", deps_dir);
dp_deps = g_dir_open(deps_dir, 0, NULL);
if (dp_deps == NULL) {
g_debug("failed to list entries in %s", deps_dir);
return;
}
disk->has_dependencies = true;
while ((dep = g_dir_read_name(dp_deps)) != NULL) {
g_autofree char *dep_dir = NULL;
char *dev_name;
/* Add dependent disks */
dep_dir = g_strdup_printf("%s/%s", deps_dir, dep);
dev_name = get_device_for_syspath(dep_dir);
if (dev_name != NULL) {
g_debug(" adding dependent device: %s", dev_name);
QAPI_LIST_PREPEND(disk->dependencies, dev_name);
}
}
g_dir_close(dp_deps);
}
/*
* Detect partitions subdirectory, name is "<disk_name><number>" or
* "<disk_name>p<number>"
*
* @disk_name -- last component of /sys path (e.g. sda)
* @disk_dir -- sys path of the disk (e.g. /sys/block/sda)
* @disk_dev -- device node of the disk (e.g. /dev/sda)
*/
static GuestDiskInfoList *get_disk_partitions(
GuestDiskInfoList *list,
const char *disk_name, const char *disk_dir,
const char *disk_dev)
{
GuestDiskInfoList *ret = list;
struct dirent *de_disk;
DIR *dp_disk = NULL;
size_t len = strlen(disk_name);
dp_disk = opendir(disk_dir);
while ((de_disk = readdir(dp_disk)) != NULL) {
g_autofree char *partition_dir = NULL;
char *dev_name;
GuestDiskInfo *partition;
if (!(de_disk->d_type & DT_DIR)) {
continue;
}
if (!(strncmp(disk_name, de_disk->d_name, len) == 0 &&
((*(de_disk->d_name + len) == 'p' &&
isdigit(*(de_disk->d_name + len + 1))) ||
isdigit(*(de_disk->d_name + len))))) {
continue;
}
partition_dir = g_strdup_printf("%s/%s",
disk_dir, de_disk->d_name);
dev_name = get_device_for_syspath(partition_dir);
if (dev_name == NULL) {
g_debug("Failed to get device name for syspath: %s",
disk_dir);
continue;
}
partition = g_new0(GuestDiskInfo, 1);
partition->name = dev_name;
partition->partition = true;
partition->has_dependencies = true;
/* Add parent disk as dependent for easier tracking of hierarchy */
QAPI_LIST_PREPEND(partition->dependencies, g_strdup(disk_dev));
QAPI_LIST_PREPEND(ret, partition);
}
closedir(dp_disk);
return ret;
}
static void get_nvme_smart(GuestDiskInfo *disk)
{
int fd;
GuestNVMeSmart *smart;
NvmeSmartLog log = {0};
struct nvme_admin_cmd cmd = {
.opcode = NVME_ADM_CMD_GET_LOG_PAGE,
.nsid = NVME_NSID_BROADCAST,
.addr = (uintptr_t)&log,
.data_len = sizeof(log),
.cdw10 = NVME_LOG_SMART_INFO | (1 << 15) /* RAE bit */
| (((sizeof(log) >> 2) - 1) << 16)
};
fd = qga_open_cloexec(disk->name, O_RDONLY, 0);
if (fd == -1) {
g_debug("Failed to open device: %s: %s", disk->name, g_strerror(errno));
return;
}
if (ioctl(fd, NVME_IOCTL_ADMIN_CMD, &cmd)) {
g_debug("Failed to get smart: %s: %s", disk->name, g_strerror(errno));
close(fd);
return;
}
disk->smart = g_new0(GuestDiskSmart, 1);
disk->smart->type = GUEST_DISK_BUS_TYPE_NVME;
smart = &disk->smart->u.nvme;
smart->critical_warning = log.critical_warning;
smart->temperature = lduw_le_p(&log.temperature); /* unaligned field */
smart->available_spare = log.available_spare;
smart->available_spare_threshold = log.available_spare_threshold;
smart->percentage_used = log.percentage_used;
smart->data_units_read_lo = le64_to_cpu(log.data_units_read[0]);
smart->data_units_read_hi = le64_to_cpu(log.data_units_read[1]);
smart->data_units_written_lo = le64_to_cpu(log.data_units_written[0]);
smart->data_units_written_hi = le64_to_cpu(log.data_units_written[1]);
smart->host_read_commands_lo = le64_to_cpu(log.host_read_commands[0]);
smart->host_read_commands_hi = le64_to_cpu(log.host_read_commands[1]);
smart->host_write_commands_lo = le64_to_cpu(log.host_write_commands[0]);
smart->host_write_commands_hi = le64_to_cpu(log.host_write_commands[1]);
smart->controller_busy_time_lo = le64_to_cpu(log.controller_busy_time[0]);
smart->controller_busy_time_hi = le64_to_cpu(log.controller_busy_time[1]);
smart->power_cycles_lo = le64_to_cpu(log.power_cycles[0]);
smart->power_cycles_hi = le64_to_cpu(log.power_cycles[1]);
smart->power_on_hours_lo = le64_to_cpu(log.power_on_hours[0]);
smart->power_on_hours_hi = le64_to_cpu(log.power_on_hours[1]);
smart->unsafe_shutdowns_lo = le64_to_cpu(log.unsafe_shutdowns[0]);
smart->unsafe_shutdowns_hi = le64_to_cpu(log.unsafe_shutdowns[1]);
smart->media_errors_lo = le64_to_cpu(log.media_errors[0]);
smart->media_errors_hi = le64_to_cpu(log.media_errors[1]);
smart->number_of_error_log_entries_lo =
le64_to_cpu(log.number_of_error_log_entries[0]);
smart->number_of_error_log_entries_hi =
le64_to_cpu(log.number_of_error_log_entries[1]);
close(fd);
}
static void get_disk_smart(GuestDiskInfo *disk)
{
if (disk->address
&& (disk->address->bus_type == GUEST_DISK_BUS_TYPE_NVME)) {
get_nvme_smart(disk);
}
}