/
libzfs_import.c
1598 lines (1385 loc) · 38.5 KB
/
libzfs_import.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
/*
* CDDL HEADER START
*
* The contents of this file are subject to the terms of the
* Common Development and Distribution License (the "License").
* You may not use this file except in compliance with the License.
*
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
* or http://www.opensolaris.org/os/licensing.
* See the License for the specific language governing permissions
* and limitations under the License.
*
* When distributing Covered Code, include this CDDL HEADER in each
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
* If applicable, add the following below this CDDL HEADER, with the
* fields enclosed by brackets "[]" replaced with your own identifying
* information: Portions Copyright [yyyy] [name of copyright owner]
*
* CDDL HEADER END
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
* Copyright (c) 2011 by Delphix. All rights reserved.
*/
/*
* Pool import support functions.
*
* To import a pool, we rely on reading the configuration information from the
* ZFS label of each device. If we successfully read the label, then we
* organize the configuration information in the following hierarchy:
*
* pool guid -> toplevel vdev guid -> label txg
*
* Duplicate entries matching this same tuple will be discarded. Once we have
* examined every device, we pick the best label txg config for each toplevel
* vdev. We then arrange these toplevel vdevs into a complete pool config, and
* update any paths that have changed. Finally, we attempt to import the pool
* using our derived config, and record the results.
*/
#include <ctype.h>
#include <devid.h>
#include <dirent.h>
#include <errno.h>
#include <libintl.h>
#include <stddef.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <unistd.h>
#include <fcntl.h>
#include <sys/vtoc.h>
#include <sys/dktp/fdisk.h>
#include <sys/efi_partition.h>
#include <sys/vdev_impl.h>
#ifdef HAVE_LIBBLKID
#include <blkid/blkid.h>
#endif
#include "libzfs.h"
#include "libzfs_impl.h"
/*
* Intermediate structures used to gather configuration information.
*/
typedef struct config_entry {
uint64_t ce_txg;
nvlist_t *ce_config;
struct config_entry *ce_next;
} config_entry_t;
typedef struct vdev_entry {
uint64_t ve_guid;
config_entry_t *ve_configs;
struct vdev_entry *ve_next;
} vdev_entry_t;
typedef struct pool_entry {
uint64_t pe_guid;
vdev_entry_t *pe_vdevs;
struct pool_entry *pe_next;
} pool_entry_t;
typedef struct name_entry {
char *ne_name;
uint64_t ne_guid;
struct name_entry *ne_next;
} name_entry_t;
typedef struct pool_list {
pool_entry_t *pools;
name_entry_t *names;
} pool_list_t;
static char *
get_devid(const char *path)
{
int fd;
ddi_devid_t devid;
char *minor, *ret;
if ((fd = open(path, O_RDONLY)) < 0)
return (NULL);
minor = NULL;
ret = NULL;
if (devid_get(fd, &devid) == 0) {
if (devid_get_minor_name(fd, &minor) == 0)
ret = devid_str_encode(devid, minor);
if (minor != NULL)
devid_str_free(minor);
devid_free(devid);
}
(void) close(fd);
return (ret);
}
/*
* Go through and fix up any path and/or devid information for the given vdev
* configuration.
*/
static int
fix_paths(nvlist_t *nv, name_entry_t *names)
{
nvlist_t **child;
uint_t c, children;
uint64_t guid;
name_entry_t *ne, *best;
char *path, *devid;
int matched;
if (nvlist_lookup_nvlist_array(nv, ZPOOL_CONFIG_CHILDREN,
&child, &children) == 0) {
for (c = 0; c < children; c++)
if (fix_paths(child[c], names) != 0)
return (-1);
return (0);
}
/*
* This is a leaf (file or disk) vdev. In either case, go through
* the name list and see if we find a matching guid. If so, replace
* the path and see if we can calculate a new devid.
*
* There may be multiple names associated with a particular guid, in
* which case we have overlapping slices or multiple paths to the same
* disk. If this is the case, then we want to pick the path that is
* the most similar to the original, where "most similar" is the number
* of matching characters starting from the end of the path. This will
* preserve slice numbers even if the disks have been reorganized, and
* will also catch preferred disk names if multiple paths exist.
*/
verify(nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &guid) == 0);
if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PATH, &path) != 0)
path = NULL;
matched = 0;
best = NULL;
for (ne = names; ne != NULL; ne = ne->ne_next) {
if (ne->ne_guid == guid) {
const char *src, *dst;
int count;
if (path == NULL) {
best = ne;
break;
}
src = ne->ne_name + strlen(ne->ne_name) - 1;
dst = path + strlen(path) - 1;
for (count = 0; src >= ne->ne_name && dst >= path;
src--, dst--, count++)
if (*src != *dst)
break;
/*
* At this point, 'count' is the number of characters
* matched from the end.
*/
if (count > matched || best == NULL) {
best = ne;
matched = count;
}
}
}
if (best == NULL)
return (0);
if (nvlist_add_string(nv, ZPOOL_CONFIG_PATH, best->ne_name) != 0)
return (-1);
if ((devid = get_devid(best->ne_name)) == NULL) {
(void) nvlist_remove_all(nv, ZPOOL_CONFIG_DEVID);
} else {
if (nvlist_add_string(nv, ZPOOL_CONFIG_DEVID, devid) != 0)
return (-1);
devid_str_free(devid);
}
return (0);
}
/*
* Add the given configuration to the list of known devices.
*/
static int
add_config(libzfs_handle_t *hdl, pool_list_t *pl, const char *path,
nvlist_t *config)
{
uint64_t pool_guid, vdev_guid, top_guid, txg, state;
pool_entry_t *pe;
vdev_entry_t *ve;
config_entry_t *ce;
name_entry_t *ne;
/*
* If this is a hot spare not currently in use or level 2 cache
* device, add it to the list of names to translate, but don't do
* anything else.
*/
if (nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_STATE,
&state) == 0 &&
(state == POOL_STATE_SPARE || state == POOL_STATE_L2CACHE) &&
nvlist_lookup_uint64(config, ZPOOL_CONFIG_GUID, &vdev_guid) == 0) {
if ((ne = zfs_alloc(hdl, sizeof (name_entry_t))) == NULL)
return (-1);
if ((ne->ne_name = zfs_strdup(hdl, path)) == NULL) {
free(ne);
return (-1);
}
ne->ne_guid = vdev_guid;
ne->ne_next = pl->names;
pl->names = ne;
return (0);
}
/*
* If we have a valid config but cannot read any of these fields, then
* it means we have a half-initialized label. In vdev_label_init()
* we write a label with txg == 0 so that we can identify the device
* in case the user refers to the same disk later on. If we fail to
* create the pool, we'll be left with a label in this state
* which should not be considered part of a valid pool.
*/
if (nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_GUID,
&pool_guid) != 0 ||
nvlist_lookup_uint64(config, ZPOOL_CONFIG_GUID,
&vdev_guid) != 0 ||
nvlist_lookup_uint64(config, ZPOOL_CONFIG_TOP_GUID,
&top_guid) != 0 ||
nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_TXG,
&txg) != 0 || txg == 0) {
nvlist_free(config);
return (0);
}
/*
* First, see if we know about this pool. If not, then add it to the
* list of known pools.
*/
for (pe = pl->pools; pe != NULL; pe = pe->pe_next) {
if (pe->pe_guid == pool_guid)
break;
}
if (pe == NULL) {
if ((pe = zfs_alloc(hdl, sizeof (pool_entry_t))) == NULL) {
nvlist_free(config);
return (-1);
}
pe->pe_guid = pool_guid;
pe->pe_next = pl->pools;
pl->pools = pe;
}
/*
* Second, see if we know about this toplevel vdev. Add it if its
* missing.
*/
for (ve = pe->pe_vdevs; ve != NULL; ve = ve->ve_next) {
if (ve->ve_guid == top_guid)
break;
}
if (ve == NULL) {
if ((ve = zfs_alloc(hdl, sizeof (vdev_entry_t))) == NULL) {
nvlist_free(config);
return (-1);
}
ve->ve_guid = top_guid;
ve->ve_next = pe->pe_vdevs;
pe->pe_vdevs = ve;
}
/*
* Third, see if we have a config with a matching transaction group. If
* so, then we do nothing. Otherwise, add it to the list of known
* configs.
*/
for (ce = ve->ve_configs; ce != NULL; ce = ce->ce_next) {
if (ce->ce_txg == txg)
break;
}
if (ce == NULL) {
if ((ce = zfs_alloc(hdl, sizeof (config_entry_t))) == NULL) {
nvlist_free(config);
return (-1);
}
ce->ce_txg = txg;
ce->ce_config = config;
ce->ce_next = ve->ve_configs;
ve->ve_configs = ce;
} else {
nvlist_free(config);
}
/*
* At this point we've successfully added our config to the list of
* known configs. The last thing to do is add the vdev guid -> path
* mappings so that we can fix up the configuration as necessary before
* doing the import.
*/
if ((ne = zfs_alloc(hdl, sizeof (name_entry_t))) == NULL)
return (-1);
if ((ne->ne_name = zfs_strdup(hdl, path)) == NULL) {
free(ne);
return (-1);
}
ne->ne_guid = vdev_guid;
ne->ne_next = pl->names;
pl->names = ne;
return (0);
}
/*
* Returns true if the named pool matches the given GUID.
*/
static int
pool_active(libzfs_handle_t *hdl, const char *name, uint64_t guid,
boolean_t *isactive)
{
zpool_handle_t *zhp;
uint64_t theguid;
if (zpool_open_silent(hdl, name, &zhp) != 0)
return (-1);
if (zhp == NULL) {
*isactive = B_FALSE;
return (0);
}
verify(nvlist_lookup_uint64(zhp->zpool_config, ZPOOL_CONFIG_POOL_GUID,
&theguid) == 0);
zpool_close(zhp);
*isactive = (theguid == guid);
return (0);
}
static nvlist_t *
refresh_config(libzfs_handle_t *hdl, nvlist_t *config)
{
nvlist_t *nvl;
zfs_cmd_t zc = { "\0", "\0", "\0", "\0", 0 };
int err;
if (zcmd_write_conf_nvlist(hdl, &zc, config) != 0)
return (NULL);
if (zcmd_alloc_dst_nvlist(hdl, &zc,
zc.zc_nvlist_conf_size * 2) != 0) {
zcmd_free_nvlists(&zc);
return (NULL);
}
while ((err = ioctl(hdl->libzfs_fd, ZFS_IOC_POOL_TRYIMPORT,
&zc)) != 0 && errno == ENOMEM) {
if (zcmd_expand_dst_nvlist(hdl, &zc) != 0) {
zcmd_free_nvlists(&zc);
return (NULL);
}
}
if (err) {
zcmd_free_nvlists(&zc);
return (NULL);
}
if (zcmd_read_dst_nvlist(hdl, &zc, &nvl) != 0) {
zcmd_free_nvlists(&zc);
return (NULL);
}
zcmd_free_nvlists(&zc);
return (nvl);
}
/*
* Determine if the vdev id is a hole in the namespace.
*/
boolean_t
vdev_is_hole(uint64_t *hole_array, uint_t holes, uint_t id)
{
int c;
for (c = 0; c < holes; c++) {
/* Top-level is a hole */
if (hole_array[c] == id)
return (B_TRUE);
}
return (B_FALSE);
}
/*
* Convert our list of pools into the definitive set of configurations. We
* start by picking the best config for each toplevel vdev. Once that's done,
* we assemble the toplevel vdevs into a full config for the pool. We make a
* pass to fix up any incorrect paths, and then add it to the main list to
* return to the user.
*/
static nvlist_t *
get_configs(libzfs_handle_t *hdl, pool_list_t *pl, boolean_t active_ok)
{
pool_entry_t *pe;
vdev_entry_t *ve;
config_entry_t *ce;
nvlist_t *ret = NULL, *config = NULL, *tmp = NULL, *nvtop, *nvroot;
nvlist_t **spares, **l2cache;
uint_t i, nspares, nl2cache;
boolean_t config_seen;
uint64_t best_txg;
char *name, *hostname, *comment;
uint64_t version, guid;
uint_t children = 0;
nvlist_t **child = NULL;
uint_t holes;
uint64_t *hole_array, max_id;
uint_t c;
boolean_t isactive;
uint64_t hostid;
nvlist_t *nvl;
boolean_t found_one = B_FALSE;
boolean_t valid_top_config = B_FALSE;
if (nvlist_alloc(&ret, 0, 0) != 0)
goto nomem;
for (pe = pl->pools; pe != NULL; pe = pe->pe_next) {
uint64_t id, max_txg = 0;
if (nvlist_alloc(&config, NV_UNIQUE_NAME, 0) != 0)
goto nomem;
config_seen = B_FALSE;
/*
* Iterate over all toplevel vdevs. Grab the pool configuration
* from the first one we find, and then go through the rest and
* add them as necessary to the 'vdevs' member of the config.
*/
for (ve = pe->pe_vdevs; ve != NULL; ve = ve->ve_next) {
/*
* Determine the best configuration for this vdev by
* selecting the config with the latest transaction
* group.
*/
best_txg = 0;
for (ce = ve->ve_configs; ce != NULL;
ce = ce->ce_next) {
if (ce->ce_txg > best_txg) {
tmp = ce->ce_config;
best_txg = ce->ce_txg;
}
}
/*
* We rely on the fact that the max txg for the
* pool will contain the most up-to-date information
* about the valid top-levels in the vdev namespace.
*/
if (best_txg > max_txg) {
(void) nvlist_remove(config,
ZPOOL_CONFIG_VDEV_CHILDREN,
DATA_TYPE_UINT64);
(void) nvlist_remove(config,
ZPOOL_CONFIG_HOLE_ARRAY,
DATA_TYPE_UINT64_ARRAY);
max_txg = best_txg;
hole_array = NULL;
holes = 0;
max_id = 0;
valid_top_config = B_FALSE;
if (nvlist_lookup_uint64(tmp,
ZPOOL_CONFIG_VDEV_CHILDREN, &max_id) == 0) {
verify(nvlist_add_uint64(config,
ZPOOL_CONFIG_VDEV_CHILDREN,
max_id) == 0);
valid_top_config = B_TRUE;
}
if (nvlist_lookup_uint64_array(tmp,
ZPOOL_CONFIG_HOLE_ARRAY, &hole_array,
&holes) == 0) {
verify(nvlist_add_uint64_array(config,
ZPOOL_CONFIG_HOLE_ARRAY,
hole_array, holes) == 0);
}
}
if (!config_seen) {
/*
* Copy the relevant pieces of data to the pool
* configuration:
*
* version
* pool guid
* name
* comment (if available)
* pool state
* hostid (if available)
* hostname (if available)
*/
uint64_t state;
verify(nvlist_lookup_uint64(tmp,
ZPOOL_CONFIG_VERSION, &version) == 0);
if (nvlist_add_uint64(config,
ZPOOL_CONFIG_VERSION, version) != 0)
goto nomem;
verify(nvlist_lookup_uint64(tmp,
ZPOOL_CONFIG_POOL_GUID, &guid) == 0);
if (nvlist_add_uint64(config,
ZPOOL_CONFIG_POOL_GUID, guid) != 0)
goto nomem;
verify(nvlist_lookup_string(tmp,
ZPOOL_CONFIG_POOL_NAME, &name) == 0);
if (nvlist_add_string(config,
ZPOOL_CONFIG_POOL_NAME, name) != 0)
goto nomem;
/*
* COMMENT is optional, don't bail if it's not
* there, instead, set it to NULL.
*/
if (nvlist_lookup_string(tmp,
ZPOOL_CONFIG_COMMENT, &comment) != 0)
comment = NULL;
else if (nvlist_add_string(config,
ZPOOL_CONFIG_COMMENT, comment) != 0)
goto nomem;
verify(nvlist_lookup_uint64(tmp,
ZPOOL_CONFIG_POOL_STATE, &state) == 0);
if (nvlist_add_uint64(config,
ZPOOL_CONFIG_POOL_STATE, state) != 0)
goto nomem;
hostid = 0;
if (nvlist_lookup_uint64(tmp,
ZPOOL_CONFIG_HOSTID, &hostid) == 0) {
if (nvlist_add_uint64(config,
ZPOOL_CONFIG_HOSTID, hostid) != 0)
goto nomem;
verify(nvlist_lookup_string(tmp,
ZPOOL_CONFIG_HOSTNAME,
&hostname) == 0);
if (nvlist_add_string(config,
ZPOOL_CONFIG_HOSTNAME,
hostname) != 0)
goto nomem;
}
config_seen = B_TRUE;
}
/*
* Add this top-level vdev to the child array.
*/
verify(nvlist_lookup_nvlist(tmp,
ZPOOL_CONFIG_VDEV_TREE, &nvtop) == 0);
verify(nvlist_lookup_uint64(nvtop, ZPOOL_CONFIG_ID,
&id) == 0);
if (id >= children) {
nvlist_t **newchild;
newchild = zfs_alloc(hdl, (id + 1) *
sizeof (nvlist_t *));
if (newchild == NULL)
goto nomem;
for (c = 0; c < children; c++)
newchild[c] = child[c];
free(child);
child = newchild;
children = id + 1;
}
if (nvlist_dup(nvtop, &child[id], 0) != 0)
goto nomem;
}
/*
* If we have information about all the top-levels then
* clean up the nvlist which we've constructed. This
* means removing any extraneous devices that are
* beyond the valid range or adding devices to the end
* of our array which appear to be missing.
*/
if (valid_top_config) {
if (max_id < children) {
for (c = max_id; c < children; c++)
nvlist_free(child[c]);
children = max_id;
} else if (max_id > children) {
nvlist_t **newchild;
newchild = zfs_alloc(hdl, (max_id) *
sizeof (nvlist_t *));
if (newchild == NULL)
goto nomem;
for (c = 0; c < children; c++)
newchild[c] = child[c];
free(child);
child = newchild;
children = max_id;
}
}
verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_GUID,
&guid) == 0);
/*
* The vdev namespace may contain holes as a result of
* device removal. We must add them back into the vdev
* tree before we process any missing devices.
*/
if (holes > 0) {
ASSERT(valid_top_config);
for (c = 0; c < children; c++) {
nvlist_t *holey;
if (child[c] != NULL ||
!vdev_is_hole(hole_array, holes, c))
continue;
if (nvlist_alloc(&holey, NV_UNIQUE_NAME,
0) != 0)
goto nomem;
/*
* Holes in the namespace are treated as
* "hole" top-level vdevs and have a
* special flag set on them.
*/
if (nvlist_add_string(holey,
ZPOOL_CONFIG_TYPE,
VDEV_TYPE_HOLE) != 0 ||
nvlist_add_uint64(holey,
ZPOOL_CONFIG_ID, c) != 0 ||
nvlist_add_uint64(holey,
ZPOOL_CONFIG_GUID, 0ULL) != 0)
goto nomem;
child[c] = holey;
}
}
/*
* Look for any missing top-level vdevs. If this is the case,
* create a faked up 'missing' vdev as a placeholder. We cannot
* simply compress the child array, because the kernel performs
* certain checks to make sure the vdev IDs match their location
* in the configuration.
*/
for (c = 0; c < children; c++) {
if (child[c] == NULL) {
nvlist_t *missing;
if (nvlist_alloc(&missing, NV_UNIQUE_NAME,
0) != 0)
goto nomem;
if (nvlist_add_string(missing,
ZPOOL_CONFIG_TYPE,
VDEV_TYPE_MISSING) != 0 ||
nvlist_add_uint64(missing,
ZPOOL_CONFIG_ID, c) != 0 ||
nvlist_add_uint64(missing,
ZPOOL_CONFIG_GUID, 0ULL) != 0) {
nvlist_free(missing);
goto nomem;
}
child[c] = missing;
}
}
/*
* Put all of this pool's top-level vdevs into a root vdev.
*/
if (nvlist_alloc(&nvroot, NV_UNIQUE_NAME, 0) != 0)
goto nomem;
if (nvlist_add_string(nvroot, ZPOOL_CONFIG_TYPE,
VDEV_TYPE_ROOT) != 0 ||
nvlist_add_uint64(nvroot, ZPOOL_CONFIG_ID, 0ULL) != 0 ||
nvlist_add_uint64(nvroot, ZPOOL_CONFIG_GUID, guid) != 0 ||
nvlist_add_nvlist_array(nvroot, ZPOOL_CONFIG_CHILDREN,
child, children) != 0) {
nvlist_free(nvroot);
goto nomem;
}
for (c = 0; c < children; c++)
nvlist_free(child[c]);
free(child);
children = 0;
child = NULL;
/*
* Go through and fix up any paths and/or devids based on our
* known list of vdev GUID -> path mappings.
*/
if (fix_paths(nvroot, pl->names) != 0) {
nvlist_free(nvroot);
goto nomem;
}
/*
* Add the root vdev to this pool's configuration.
*/
if (nvlist_add_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
nvroot) != 0) {
nvlist_free(nvroot);
goto nomem;
}
nvlist_free(nvroot);
/*
* zdb uses this path to report on active pools that were
* imported or created using -R.
*/
if (active_ok)
goto add_pool;
/*
* Determine if this pool is currently active, in which case we
* can't actually import it.
*/
verify(nvlist_lookup_string(config, ZPOOL_CONFIG_POOL_NAME,
&name) == 0);
verify(nvlist_lookup_uint64(config, ZPOOL_CONFIG_POOL_GUID,
&guid) == 0);
if (pool_active(hdl, name, guid, &isactive) != 0)
goto error;
if (isactive) {
nvlist_free(config);
config = NULL;
continue;
}
if ((nvl = refresh_config(hdl, config)) == NULL) {
nvlist_free(config);
config = NULL;
continue;
}
nvlist_free(config);
config = nvl;
/*
* Go through and update the paths for spares, now that we have
* them.
*/
verify(nvlist_lookup_nvlist(config, ZPOOL_CONFIG_VDEV_TREE,
&nvroot) == 0);
if (nvlist_lookup_nvlist_array(nvroot, ZPOOL_CONFIG_SPARES,
&spares, &nspares) == 0) {
for (i = 0; i < nspares; i++) {
if (fix_paths(spares[i], pl->names) != 0)
goto nomem;
}
}
/*
* Update the paths for l2cache devices.
*/
if (nvlist_lookup_nvlist_array(nvroot, ZPOOL_CONFIG_L2CACHE,
&l2cache, &nl2cache) == 0) {
for (i = 0; i < nl2cache; i++) {
if (fix_paths(l2cache[i], pl->names) != 0)
goto nomem;
}
}
/*
* Restore the original information read from the actual label.
*/
(void) nvlist_remove(config, ZPOOL_CONFIG_HOSTID,
DATA_TYPE_UINT64);
(void) nvlist_remove(config, ZPOOL_CONFIG_HOSTNAME,
DATA_TYPE_STRING);
if (hostid != 0) {
verify(nvlist_add_uint64(config, ZPOOL_CONFIG_HOSTID,
hostid) == 0);
verify(nvlist_add_string(config, ZPOOL_CONFIG_HOSTNAME,
hostname) == 0);
}
add_pool:
/*
* Add this pool to the list of configs.
*/
verify(nvlist_lookup_string(config, ZPOOL_CONFIG_POOL_NAME,
&name) == 0);
if (nvlist_add_nvlist(ret, name, config) != 0)
goto nomem;
found_one = B_TRUE;
nvlist_free(config);
config = NULL;
}
if (!found_one) {
nvlist_free(ret);
ret = NULL;
}
return (ret);
nomem:
(void) no_memory(hdl);
error:
nvlist_free(config);
nvlist_free(ret);
for (c = 0; c < children; c++)
nvlist_free(child[c]);
free(child);
return (NULL);
}
/*
* Return the offset of the given label.
*/
static uint64_t
label_offset(uint64_t size, int l)
{
ASSERT(P2PHASE_TYPED(size, sizeof (vdev_label_t), uint64_t) == 0);
return (l * sizeof (vdev_label_t) + (l < VDEV_LABELS / 2 ?
0 : size - VDEV_LABELS * sizeof (vdev_label_t)));
}
/*
* Given a file descriptor, read the label information and return an nvlist
* describing the configuration, if there is one.
*/
int
zpool_read_label(int fd, nvlist_t **config)
{
struct stat64 statbuf;
int l;
vdev_label_t *label;
uint64_t state, txg, size;
*config = NULL;
if (fstat64(fd, &statbuf) == -1)
return (0);
size = P2ALIGN_TYPED(statbuf.st_size, sizeof (vdev_label_t), uint64_t);
if ((label = malloc(sizeof (vdev_label_t))) == NULL)
return (-1);
for (l = 0; l < VDEV_LABELS; l++) {
if (pread64(fd, label, sizeof (vdev_label_t),
label_offset(size, l)) != sizeof (vdev_label_t))
continue;
if (nvlist_unpack(label->vl_vdev_phys.vp_nvlist,
sizeof (label->vl_vdev_phys.vp_nvlist), config, 0) != 0)
continue;
if (nvlist_lookup_uint64(*config, ZPOOL_CONFIG_POOL_STATE,
&state) != 0 || state > POOL_STATE_L2CACHE) {
nvlist_free(*config);
continue;
}
if (state != POOL_STATE_SPARE && state != POOL_STATE_L2CACHE &&
(nvlist_lookup_uint64(*config, ZPOOL_CONFIG_POOL_TXG,
&txg) != 0 || txg == 0)) {
nvlist_free(*config);
continue;
}
free(label);
return (0);
}
free(label);
*config = NULL;
return (0);
}
#ifdef HAVE_LIBBLKID
/*
* Use libblkid to quickly search for zfs devices
*/
static int
zpool_find_import_blkid(libzfs_handle_t *hdl, pool_list_t *pools)
{
blkid_cache cache;
blkid_dev_iterate iter;
blkid_dev dev;
const char *devname;
nvlist_t *config;
int fd, err;
err = blkid_get_cache(&cache, NULL);
if (err != 0) {
(void) zfs_error_fmt(hdl, EZFS_BADCACHE,
dgettext(TEXT_DOMAIN, "blkid_get_cache() %d"), err);
goto err_blkid1;
}
err = blkid_probe_all(cache);
if (err != 0) {
(void) zfs_error_fmt(hdl, EZFS_BADCACHE,
dgettext(TEXT_DOMAIN, "blkid_probe_all() %d"), err);
goto err_blkid2;
}
iter = blkid_dev_iterate_begin(cache);
if (iter == NULL) {
(void) zfs_error_fmt(hdl, EZFS_BADCACHE,
dgettext(TEXT_DOMAIN, "blkid_dev_iterate_begin()"));
goto err_blkid2;
}
err = blkid_dev_set_search(iter, "TYPE", "zfs");
if (err != 0) {
(void) zfs_error_fmt(hdl, EZFS_BADCACHE,
dgettext(TEXT_DOMAIN, "blkid_dev_set_search() %d"), err);
goto err_blkid3;
}
while (blkid_dev_next(iter, &dev) == 0) {
devname = blkid_dev_devname(dev);
if ((fd = open64(devname, O_RDONLY)) < 0)
continue;
err = zpool_read_label(fd, &config);
(void) close(fd);
if (err != 0) {
(void) no_memory(hdl);
goto err_blkid3;
}
if (config != NULL) {
err = add_config(hdl, pools, devname, config);
if (err != 0)
goto err_blkid3;
}
}
err_blkid3:
blkid_dev_iterate_end(iter);
err_blkid2:
blkid_put_cache(cache);
err_blkid1:
return err;
}
#endif /* HAVE_LIBBLKID */
/*
* Given a list of directories to search, find all pools stored on disk. This
* includes partial pools which are not available to import. If no args are
* given (argc is 0), then the default directory (/dev/dsk) is searched.
* poolname or guid (but not both) are provided by the caller when trying