aboutsummaryrefslogtreecommitdiffstats
path: root/module/zfs/vdev_label.c
blob: 7fab7d0d795054eae72dc533c8017b8b427c0ebc (plain) (blame)
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
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
/*
 * 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 (c) 2012, 2020 by Delphix. All rights reserved.
 * Copyright (c) 2017, Intel Corporation.
 */

/*
 * Virtual Device Labels
 * ---------------------
 *
 * The vdev label serves several distinct purposes:
 *
 *	1. Uniquely identify this device as part of a ZFS pool and confirm its
 *	   identity within the pool.
 *
 *	2. Verify that all the devices given in a configuration are present
 *         within the pool.
 *
 *	3. Determine the uberblock for the pool.
 *
 *	4. In case of an import operation, determine the configuration of the
 *         toplevel vdev of which it is a part.
 *
 *	5. If an import operation cannot find all the devices in the pool,
 *         provide enough information to the administrator to determine which
 *         devices are missing.
 *
 * It is important to note that while the kernel is responsible for writing the
 * label, it only consumes the information in the first three cases.  The
 * latter information is only consumed in userland when determining the
 * configuration to import a pool.
 *
 *
 * Label Organization
 * ------------------
 *
 * Before describing the contents of the label, it's important to understand how
 * the labels are written and updated with respect to the uberblock.
 *
 * When the pool configuration is altered, either because it was newly created
 * or a device was added, we want to update all the labels such that we can deal
 * with fatal failure at any point.  To this end, each disk has two labels which
 * are updated before and after the uberblock is synced.  Assuming we have
 * labels and an uberblock with the following transaction groups:
 *
 *              L1          UB          L2
 *           +------+    +------+    +------+
 *           |      |    |      |    |      |
 *           | t10  |    | t10  |    | t10  |
 *           |      |    |      |    |      |
 *           +------+    +------+    +------+
 *
 * In this stable state, the labels and the uberblock were all updated within
 * the same transaction group (10).  Each label is mirrored and checksummed, so
 * that we can detect when we fail partway through writing the label.
 *
 * In order to identify which labels are valid, the labels are written in the
 * following manner:
 *
 *	1. For each vdev, update 'L1' to the new label
 *	2. Update the uberblock
 *	3. For each vdev, update 'L2' to the new label
 *
 * Given arbitrary failure, we can determine the correct label to use based on
 * the transaction group.  If we fail after updating L1 but before updating the
 * UB, we will notice that L1's transaction group is greater than the uberblock,
 * so L2 must be valid.  If we fail after writing the uberblock but before
 * writing L2, we will notice that L2's transaction group is less than L1, and
 * therefore L1 is valid.
 *
 * Another added complexity is that not every label is updated when the config
 * is synced.  If we add a single device, we do not want to have to re-write
 * every label for every device in the pool.  This means that both L1 and L2 may
 * be older than the pool uberblock, because the necessary information is stored
 * on another vdev.
 *
 *
 * On-disk Format
 * --------------
 *
 * The vdev label consists of two distinct parts, and is wrapped within the
 * vdev_label_t structure.  The label includes 8k of padding to permit legacy
 * VTOC disk labels, but is otherwise ignored.
 *
 * The first half of the label is a packed nvlist which contains pool wide
 * properties, per-vdev properties, and configuration information.  It is
 * described in more detail below.
 *
 * The latter half of the label consists of a redundant array of uberblocks.
 * These uberblocks are updated whenever a transaction group is committed,
 * or when the configuration is updated.  When a pool is loaded, we scan each
 * vdev for the 'best' uberblock.
 *
 *
 * Configuration Information
 * -------------------------
 *
 * The nvlist describing the pool and vdev contains the following elements:
 *
 *	version		ZFS on-disk version
 *	name		Pool name
 *	state		Pool state
 *	txg		Transaction group in which this label was written
 *	pool_guid	Unique identifier for this pool
 *	vdev_tree	An nvlist describing vdev tree.
 *	features_for_read
 *			An nvlist of the features necessary for reading the MOS.
 *
 * Each leaf device label also contains the following:
 *
 *	top_guid	Unique ID for top-level vdev in which this is contained
 *	guid		Unique ID for the leaf vdev
 *
 * The 'vs' configuration follows the format described in 'spa_config.c'.
 */

#include <sys/zfs_context.h>
#include <sys/spa.h>
#include <sys/spa_impl.h>
#include <sys/dmu.h>
#include <sys/zap.h>
#include <sys/vdev.h>
#include <sys/vdev_impl.h>
#include <sys/uberblock_impl.h>
#include <sys/metaslab.h>
#include <sys/metaslab_impl.h>
#include <sys/zio.h>
#include <sys/dsl_scan.h>
#include <sys/abd.h>
#include <sys/fs/zfs.h>
#include <sys/byteorder.h>
#include <sys/zfs_bootenv.h>

/*
 * Basic routines to read and write from a vdev label.
 * Used throughout the rest of this file.
 */
uint64_t
vdev_label_offset(uint64_t psize, int l, uint64_t offset)
{
	ASSERT(offset < sizeof (vdev_label_t));
	ASSERT(P2PHASE_TYPED(psize, sizeof (vdev_label_t), uint64_t) == 0);

	return (offset + l * sizeof (vdev_label_t) + (l < VDEV_LABELS / 2 ?
	    0 : psize - VDEV_LABELS * sizeof (vdev_label_t)));
}

/*
 * Returns back the vdev label associated with the passed in offset.
 */
int
vdev_label_number(uint64_t psize, uint64_t offset)
{
	int l;

	if (offset >= psize - VDEV_LABEL_END_SIZE) {
		offset -= psize - VDEV_LABEL_END_SIZE;
		offset += (VDEV_LABELS / 2) * sizeof (vdev_label_t);
	}
	l = offset / sizeof (vdev_label_t);
	return (l < VDEV_LABELS ? l : -1);
}

static void
vdev_label_read(zio_t *zio, vdev_t *vd, int l, abd_t *buf, uint64_t offset,
    uint64_t size, zio_done_func_t *done, void *private, int flags)
{
	ASSERT(
	    spa_config_held(zio->io_spa, SCL_STATE, RW_READER) == SCL_STATE ||
	    spa_config_held(zio->io_spa, SCL_STATE, RW_WRITER) == SCL_STATE);
	ASSERT(flags & ZIO_FLAG_CONFIG_WRITER);

	zio_nowait(zio_read_phys(zio, vd,
	    vdev_label_offset(vd->vdev_psize, l, offset),
	    size, buf, ZIO_CHECKSUM_LABEL, done, private,
	    ZIO_PRIORITY_SYNC_READ, flags, B_TRUE));
}

void
vdev_label_write(zio_t *zio, vdev_t *vd, int l, abd_t *buf, uint64_t offset,
    uint64_t size, zio_done_func_t *done, void *private, int flags)
{
	ASSERT(
	    spa_config_held(zio->io_spa, SCL_STATE, RW_READER) == SCL_STATE ||
	    spa_config_held(zio->io_spa, SCL_STATE, RW_WRITER) == SCL_STATE);
	ASSERT(flags & ZIO_FLAG_CONFIG_WRITER);

	zio_nowait(zio_write_phys(zio, vd,
	    vdev_label_offset(vd->vdev_psize, l, offset),
	    size, buf, ZIO_CHECKSUM_LABEL, done, private,
	    ZIO_PRIORITY_SYNC_WRITE, flags, B_TRUE));
}

/*
 * Generate the nvlist representing this vdev's stats
 */
void
vdev_config_generate_stats(vdev_t *vd, nvlist_t *nv)
{
	nvlist_t *nvx;
	vdev_stat_t *vs;
	vdev_stat_ex_t *vsx;

	vs = kmem_alloc(sizeof (*vs), KM_SLEEP);
	vsx = kmem_alloc(sizeof (*vsx), KM_SLEEP);

	vdev_get_stats_ex(vd, vs, vsx);
	fnvlist_add_uint64_array(nv, ZPOOL_CONFIG_VDEV_STATS,
	    (uint64_t *)vs, sizeof (*vs) / sizeof (uint64_t));

	/*
	 * Add extended stats into a special extended stats nvlist.  This keeps
	 * all the extended stats nicely grouped together.  The extended stats
	 * nvlist is then added to the main nvlist.
	 */
	nvx = fnvlist_alloc();

	/* ZIOs in flight to disk */
	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SYNC_R_ACTIVE_QUEUE,
	    vsx->vsx_active_queue[ZIO_PRIORITY_SYNC_READ]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SYNC_W_ACTIVE_QUEUE,
	    vsx->vsx_active_queue[ZIO_PRIORITY_SYNC_WRITE]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_ASYNC_R_ACTIVE_QUEUE,
	    vsx->vsx_active_queue[ZIO_PRIORITY_ASYNC_READ]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_ASYNC_W_ACTIVE_QUEUE,
	    vsx->vsx_active_queue[ZIO_PRIORITY_ASYNC_WRITE]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SCRUB_ACTIVE_QUEUE,
	    vsx->vsx_active_queue[ZIO_PRIORITY_SCRUB]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_TRIM_ACTIVE_QUEUE,
	    vsx->vsx_active_queue[ZIO_PRIORITY_TRIM]);

	/* ZIOs pending */
	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SYNC_R_PEND_QUEUE,
	    vsx->vsx_pend_queue[ZIO_PRIORITY_SYNC_READ]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SYNC_W_PEND_QUEUE,
	    vsx->vsx_pend_queue[ZIO_PRIORITY_SYNC_WRITE]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_ASYNC_R_PEND_QUEUE,
	    vsx->vsx_pend_queue[ZIO_PRIORITY_ASYNC_READ]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_ASYNC_W_PEND_QUEUE,
	    vsx->vsx_pend_queue[ZIO_PRIORITY_ASYNC_WRITE]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SCRUB_PEND_QUEUE,
	    vsx->vsx_pend_queue[ZIO_PRIORITY_SCRUB]);

	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_TRIM_PEND_QUEUE,
	    vsx->vsx_pend_queue[ZIO_PRIORITY_TRIM]);

	/* Histograms */
	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_TOT_R_LAT_HISTO,
	    vsx->vsx_total_histo[ZIO_TYPE_READ],
	    ARRAY_SIZE(vsx->vsx_total_histo[ZIO_TYPE_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_TOT_W_LAT_HISTO,
	    vsx->vsx_total_histo[ZIO_TYPE_WRITE],
	    ARRAY_SIZE(vsx->vsx_total_histo[ZIO_TYPE_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_DISK_R_LAT_HISTO,
	    vsx->vsx_disk_histo[ZIO_TYPE_READ],
	    ARRAY_SIZE(vsx->vsx_disk_histo[ZIO_TYPE_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_DISK_W_LAT_HISTO,
	    vsx->vsx_disk_histo[ZIO_TYPE_WRITE],
	    ARRAY_SIZE(vsx->vsx_disk_histo[ZIO_TYPE_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_SYNC_R_LAT_HISTO,
	    vsx->vsx_queue_histo[ZIO_PRIORITY_SYNC_READ],
	    ARRAY_SIZE(vsx->vsx_queue_histo[ZIO_PRIORITY_SYNC_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_SYNC_W_LAT_HISTO,
	    vsx->vsx_queue_histo[ZIO_PRIORITY_SYNC_WRITE],
	    ARRAY_SIZE(vsx->vsx_queue_histo[ZIO_PRIORITY_SYNC_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_ASYNC_R_LAT_HISTO,
	    vsx->vsx_queue_histo[ZIO_PRIORITY_ASYNC_READ],
	    ARRAY_SIZE(vsx->vsx_queue_histo[ZIO_PRIORITY_ASYNC_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_ASYNC_W_LAT_HISTO,
	    vsx->vsx_queue_histo[ZIO_PRIORITY_ASYNC_WRITE],
	    ARRAY_SIZE(vsx->vsx_queue_histo[ZIO_PRIORITY_ASYNC_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_SCRUB_LAT_HISTO,
	    vsx->vsx_queue_histo[ZIO_PRIORITY_SCRUB],
	    ARRAY_SIZE(vsx->vsx_queue_histo[ZIO_PRIORITY_SCRUB]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_TRIM_LAT_HISTO,
	    vsx->vsx_queue_histo[ZIO_PRIORITY_TRIM],
	    ARRAY_SIZE(vsx->vsx_queue_histo[ZIO_PRIORITY_TRIM]));

	/* Request sizes */
	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_SYNC_IND_R_HISTO,
	    vsx->vsx_ind_histo[ZIO_PRIORITY_SYNC_READ],
	    ARRAY_SIZE(vsx->vsx_ind_histo[ZIO_PRIORITY_SYNC_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_SYNC_IND_W_HISTO,
	    vsx->vsx_ind_histo[ZIO_PRIORITY_SYNC_WRITE],
	    ARRAY_SIZE(vsx->vsx_ind_histo[ZIO_PRIORITY_SYNC_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_ASYNC_IND_R_HISTO,
	    vsx->vsx_ind_histo[ZIO_PRIORITY_ASYNC_READ],
	    ARRAY_SIZE(vsx->vsx_ind_histo[ZIO_PRIORITY_ASYNC_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_ASYNC_IND_W_HISTO,
	    vsx->vsx_ind_histo[ZIO_PRIORITY_ASYNC_WRITE],
	    ARRAY_SIZE(vsx->vsx_ind_histo[ZIO_PRIORITY_ASYNC_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_IND_SCRUB_HISTO,
	    vsx->vsx_ind_histo[ZIO_PRIORITY_SCRUB],
	    ARRAY_SIZE(vsx->vsx_ind_histo[ZIO_PRIORITY_SCRUB]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_IND_TRIM_HISTO,
	    vsx->vsx_ind_histo[ZIO_PRIORITY_TRIM],
	    ARRAY_SIZE(vsx->vsx_ind_histo[ZIO_PRIORITY_TRIM]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_SYNC_AGG_R_HISTO,
	    vsx->vsx_agg_histo[ZIO_PRIORITY_SYNC_READ],
	    ARRAY_SIZE(vsx->vsx_agg_histo[ZIO_PRIORITY_SYNC_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_SYNC_AGG_W_HISTO,
	    vsx->vsx_agg_histo[ZIO_PRIORITY_SYNC_WRITE],
	    ARRAY_SIZE(vsx->vsx_agg_histo[ZIO_PRIORITY_SYNC_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_ASYNC_AGG_R_HISTO,
	    vsx->vsx_agg_histo[ZIO_PRIORITY_ASYNC_READ],
	    ARRAY_SIZE(vsx->vsx_agg_histo[ZIO_PRIORITY_ASYNC_READ]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_ASYNC_AGG_W_HISTO,
	    vsx->vsx_agg_histo[ZIO_PRIORITY_ASYNC_WRITE],
	    ARRAY_SIZE(vsx->vsx_agg_histo[ZIO_PRIORITY_ASYNC_WRITE]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_AGG_SCRUB_HISTO,
	    vsx->vsx_agg_histo[ZIO_PRIORITY_SCRUB],
	    ARRAY_SIZE(vsx->vsx_agg_histo[ZIO_PRIORITY_SCRUB]));

	fnvlist_add_uint64_array(nvx, ZPOOL_CONFIG_VDEV_AGG_TRIM_HISTO,
	    vsx->vsx_agg_histo[ZIO_PRIORITY_TRIM],
	    ARRAY_SIZE(vsx->vsx_agg_histo[ZIO_PRIORITY_TRIM]));

	/* IO delays */
	fnvlist_add_uint64(nvx, ZPOOL_CONFIG_VDEV_SLOW_IOS, vs->vs_slow_ios);

	/* Add extended stats nvlist to main nvlist */
	fnvlist_add_nvlist(nv, ZPOOL_CONFIG_VDEV_STATS_EX, nvx);

	fnvlist_free(nvx);
	kmem_free(vs, sizeof (*vs));
	kmem_free(vsx, sizeof (*vsx));
}

static void
root_vdev_actions_getprogress(vdev_t *vd, nvlist_t *nvl)
{
	spa_t *spa = vd->vdev_spa;

	if (vd != spa->spa_root_vdev)
		return;

	/* provide either current or previous scan information */
	pool_scan_stat_t ps;
	if (spa_scan_get_stats(spa, &ps) == 0) {
		fnvlist_add_uint64_array(nvl,
		    ZPOOL_CONFIG_SCAN_STATS, (uint64_t *)&ps,
		    sizeof (pool_scan_stat_t) / sizeof (uint64_t));
	}

	pool_removal_stat_t prs;
	if (spa_removal_get_stats(spa, &prs) == 0) {
		fnvlist_add_uint64_array(nvl,
		    ZPOOL_CONFIG_REMOVAL_STATS, (uint64_t *)&prs,
		    sizeof (prs) / sizeof (uint64_t));
	}

	pool_checkpoint_stat_t pcs;
	if (spa_checkpoint_get_stats(spa, &pcs) == 0) {
		fnvlist_add_uint64_array(nvl,
		    ZPOOL_CONFIG_CHECKPOINT_STATS, (uint64_t *)&pcs,
		    sizeof (pcs) / sizeof (uint64_t));
	}
}

static void
top_vdev_actions_getprogress(vdev_t *vd, nvlist_t *nvl)
{
	if (vd == vd->vdev_top) {
		vdev_rebuild_stat_t vrs;
		if (vdev_rebuild_get_stats(vd, &vrs) == 0) {
			fnvlist_add_uint64_array(nvl,
			    ZPOOL_CONFIG_REBUILD_STATS, (uint64_t *)&vrs,
			    sizeof (vrs) / sizeof (uint64_t));
		}
	}
}

/*
 * Generate the nvlist representing this vdev's config.
 */
nvlist_t *
vdev_config_generate(spa_t *spa, vdev_t *vd, boolean_t getstats,
    vdev_config_flag_t flags)
{
	nvlist_t *nv = NULL;
	vdev_indirect_config_t *vic = &vd->vdev_indirect_config;

	nv = fnvlist_alloc();

	fnvlist_add_string(nv, ZPOOL_CONFIG_TYPE, vd->vdev_ops->vdev_op_type);
	if (!(flags & (VDEV_CONFIG_SPARE | VDEV_CONFIG_L2CACHE)))
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_ID, vd->vdev_id);
	fnvlist_add_uint64(nv, ZPOOL_CONFIG_GUID, vd->vdev_guid);

	if (vd->vdev_path != NULL)
		fnvlist_add_string(nv, ZPOOL_CONFIG_PATH, vd->vdev_path);

	if (vd->vdev_devid != NULL)
		fnvlist_add_string(nv, ZPOOL_CONFIG_DEVID, vd->vdev_devid);

	if (vd->vdev_physpath != NULL)
		fnvlist_add_string(nv, ZPOOL_CONFIG_PHYS_PATH,
		    vd->vdev_physpath);

	if (vd->vdev_enc_sysfs_path != NULL)
		fnvlist_add_string(nv, ZPOOL_CONFIG_VDEV_ENC_SYSFS_PATH,
		    vd->vdev_enc_sysfs_path);

	if (vd->vdev_fru != NULL)
		fnvlist_add_string(nv, ZPOOL_CONFIG_FRU, vd->vdev_fru);

	if (vd->vdev_nparity != 0) {
		ASSERT(strcmp(vd->vdev_ops->vdev_op_type,
		    VDEV_TYPE_RAIDZ) == 0);

		/*
		 * Make sure someone hasn't managed to sneak a fancy new vdev
		 * into a crufty old storage pool.
		 */
		ASSERT(vd->vdev_nparity == 1 ||
		    (vd->vdev_nparity <= 2 &&
		    spa_version(spa) >= SPA_VERSION_RAIDZ2) ||
		    (vd->vdev_nparity <= 3 &&
		    spa_version(spa) >= SPA_VERSION_RAIDZ3));

		/*
		 * Note that we'll add the nparity tag even on storage pools
		 * that only support a single parity device -- older software
		 * will just ignore it.
		 */
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_NPARITY, vd->vdev_nparity);
	}

	if (vd->vdev_wholedisk != -1ULL)
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
		    vd->vdev_wholedisk);

	if (vd->vdev_not_present && !(flags & VDEV_CONFIG_MISSING))
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_NOT_PRESENT, 1);

	if (vd->vdev_isspare)
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_IS_SPARE, 1);

	if (!(flags & (VDEV_CONFIG_SPARE | VDEV_CONFIG_L2CACHE)) &&
	    vd == vd->vdev_top) {
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_METASLAB_ARRAY,
		    vd->vdev_ms_array);
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_METASLAB_SHIFT,
		    vd->vdev_ms_shift);
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_ASHIFT, vd->vdev_ashift);
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_ASIZE,
		    vd->vdev_asize);
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_IS_LOG, vd->vdev_islog);
		if (vd->vdev_removing) {
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_REMOVING,
			    vd->vdev_removing);
		}

		/* zpool command expects alloc class data */
		if (getstats && vd->vdev_alloc_bias != VDEV_BIAS_NONE) {
			const char *bias = NULL;

			switch (vd->vdev_alloc_bias) {
			case VDEV_BIAS_LOG:
				bias = VDEV_ALLOC_BIAS_LOG;
				break;
			case VDEV_BIAS_SPECIAL:
				bias = VDEV_ALLOC_BIAS_SPECIAL;
				break;
			case VDEV_BIAS_DEDUP:
				bias = VDEV_ALLOC_BIAS_DEDUP;
				break;
			default:
				ASSERT3U(vd->vdev_alloc_bias, ==,
				    VDEV_BIAS_NONE);
			}
			fnvlist_add_string(nv, ZPOOL_CONFIG_ALLOCATION_BIAS,
			    bias);
		}
	}

	if (vd->vdev_dtl_sm != NULL) {
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_DTL,
		    space_map_object(vd->vdev_dtl_sm));
	}

	if (vic->vic_mapping_object != 0) {
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_OBJECT,
		    vic->vic_mapping_object);
	}

	if (vic->vic_births_object != 0) {
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_BIRTHS,
		    vic->vic_births_object);
	}

	if (vic->vic_prev_indirect_vdev != UINT64_MAX) {
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_PREV_INDIRECT_VDEV,
		    vic->vic_prev_indirect_vdev);
	}

	if (vd->vdev_crtxg)
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_CREATE_TXG, vd->vdev_crtxg);

	if (vd->vdev_expansion_time)
		fnvlist_add_uint64(nv, ZPOOL_CONFIG_EXPANSION_TIME,
		    vd->vdev_expansion_time);

	if (flags & VDEV_CONFIG_MOS) {
		if (vd->vdev_leaf_zap != 0) {
			ASSERT(vd->vdev_ops->vdev_op_leaf);
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_VDEV_LEAF_ZAP,
			    vd->vdev_leaf_zap);
		}

		if (vd->vdev_top_zap != 0) {
			ASSERT(vd == vd->vdev_top);
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_VDEV_TOP_ZAP,
			    vd->vdev_top_zap);
		}

		if (vd->vdev_resilver_deferred) {
			ASSERT(vd->vdev_ops->vdev_op_leaf);
			ASSERT(spa->spa_resilver_deferred);
			fnvlist_add_boolean(nv, ZPOOL_CONFIG_RESILVER_DEFER);
		}
	}

	if (getstats) {
		vdev_config_generate_stats(vd, nv);

		root_vdev_actions_getprogress(vd, nv);
		top_vdev_actions_getprogress(vd, nv);

		/*
		 * Note: this can be called from open context
		 * (spa_get_stats()), so we need the rwlock to prevent
		 * the mapping from being changed by condensing.
		 */
		rw_enter(&vd->vdev_indirect_rwlock, RW_READER);
		if (vd->vdev_indirect_mapping != NULL) {
			ASSERT(vd->vdev_indirect_births != NULL);
			vdev_indirect_mapping_t *vim =
			    vd->vdev_indirect_mapping;
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_SIZE,
			    vdev_indirect_mapping_size(vim));
		}
		rw_exit(&vd->vdev_indirect_rwlock);
		if (vd->vdev_mg != NULL &&
		    vd->vdev_mg->mg_fragmentation != ZFS_FRAG_INVALID) {
			/*
			 * Compute approximately how much memory would be used
			 * for the indirect mapping if this device were to
			 * be removed.
			 *
			 * Note: If the frag metric is invalid, then not
			 * enough metaslabs have been converted to have
			 * histograms.
			 */
			uint64_t seg_count = 0;
			uint64_t to_alloc = vd->vdev_stat.vs_alloc;

			/*
			 * There are the same number of allocated segments
			 * as free segments, so we will have at least one
			 * entry per free segment.  However, small free
			 * segments (smaller than vdev_removal_max_span)
			 * will be combined with adjacent allocated segments
			 * as a single mapping.
			 */
			for (int i = 0; i < RANGE_TREE_HISTOGRAM_SIZE; i++) {
				if (1ULL << (i + 1) < vdev_removal_max_span) {
					to_alloc +=
					    vd->vdev_mg->mg_histogram[i] <<
					    (i + 1);
				} else {
					seg_count +=
					    vd->vdev_mg->mg_histogram[i];
				}
			}

			/*
			 * The maximum length of a mapping is
			 * zfs_remove_max_segment, so we need at least one entry
			 * per zfs_remove_max_segment of allocated data.
			 */
			seg_count += to_alloc / spa_remove_max_segment(spa);

			fnvlist_add_uint64(nv, ZPOOL_CONFIG_INDIRECT_SIZE,
			    seg_count *
			    sizeof (vdev_indirect_mapping_entry_phys_t));
		}
	}

	if (!vd->vdev_ops->vdev_op_leaf) {
		nvlist_t **child;
		int c, idx;

		ASSERT(!vd->vdev_ishole);

		child = kmem_alloc(vd->vdev_children * sizeof (nvlist_t *),
		    KM_SLEEP);

		for (c = 0, idx = 0; c < vd->vdev_children; c++) {
			vdev_t *cvd = vd->vdev_child[c];

			/*
			 * If we're generating an nvlist of removing
			 * vdevs then skip over any device which is
			 * not being removed.
			 */
			if ((flags & VDEV_CONFIG_REMOVING) &&
			    !cvd->vdev_removing)
				continue;

			child[idx++] = vdev_config_generate(spa, cvd,
			    getstats, flags);
		}

		if (idx) {
			fnvlist_add_nvlist_array(nv, ZPOOL_CONFIG_CHILDREN,
			    child, idx);
		}

		for (c = 0; c < idx; c++)
			nvlist_free(child[c]);

		kmem_free(child, vd->vdev_children * sizeof (nvlist_t *));

	} else {
		const char *aux = NULL;

		if (vd->vdev_offline && !vd->vdev_tmpoffline)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_OFFLINE, B_TRUE);
		if (vd->vdev_resilver_txg != 0)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_RESILVER_TXG,
			    vd->vdev_resilver_txg);
		if (vd->vdev_rebuild_txg != 0)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_REBUILD_TXG,
			    vd->vdev_rebuild_txg);
		if (vd->vdev_faulted)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_FAULTED, B_TRUE);
		if (vd->vdev_degraded)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_DEGRADED, B_TRUE);
		if (vd->vdev_removed)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_REMOVED, B_TRUE);
		if (vd->vdev_unspare)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_UNSPARE, B_TRUE);
		if (vd->vdev_ishole)
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_IS_HOLE, B_TRUE);

		/* Set the reason why we're FAULTED/DEGRADED. */
		switch (vd->vdev_stat.vs_aux) {
		case VDEV_AUX_ERR_EXCEEDED:
			aux = "err_exceeded";
			break;

		case VDEV_AUX_EXTERNAL:
			aux = "external";
			break;
		}

		if (aux != NULL && !vd->vdev_tmpoffline) {
			fnvlist_add_string(nv, ZPOOL_CONFIG_AUX_STATE, aux);
		} else {
			/*
			 * We're healthy - clear any previous AUX_STATE values.
			 */
			if (nvlist_exists(nv, ZPOOL_CONFIG_AUX_STATE))
				nvlist_remove_all(nv, ZPOOL_CONFIG_AUX_STATE);
		}

		if (vd->vdev_splitting && vd->vdev_orig_guid != 0LL) {
			fnvlist_add_uint64(nv, ZPOOL_CONFIG_ORIG_GUID,
			    vd->vdev_orig_guid);
		}
	}

	return (nv);
}

/*
 * Generate a view of the top-level vdevs.  If we currently have holes
 * in the namespace, then generate an array which contains a list of holey
 * vdevs.  Additionally, add the number of top-level children that currently
 * exist.
 */
void
vdev_top_config_generate(spa_t *spa, nvlist_t *config)
{
	vdev_t *rvd = spa->spa_root_vdev;
	uint64_t *array;
	uint_t c, idx;

	array = kmem_alloc(rvd->vdev_children * sizeof (uint64_t), KM_SLEEP);

	for (c = 0, idx = 0; c < rvd->vdev_children; c++) {
		vdev_t *tvd = rvd->vdev_child[c];

		if (tvd->vdev_ishole) {
			array[idx++] = c;
		}
	}

	if (idx) {
		VERIFY(nvlist_add_uint64_array(config, ZPOOL_CONFIG_HOLE_ARRAY,
		    array, idx) == 0);
	}

	VERIFY(nvlist_add_uint64(config, ZPOOL_CONFIG_VDEV_CHILDREN,
	    rvd->vdev_children) == 0);

	kmem_free(array, rvd->vdev_children * sizeof (uint64_t));
}

/*
 * Returns the configuration from the label of the given vdev. For vdevs
 * which don't have a txg value stored on their label (i.e. spares/cache)
 * or have not been completely initialized (txg = 0) just return
 * the configuration from the first valid label we find. Otherwise,
 * find the most up-to-date label that does not exceed the specified
 * 'txg' value.
 */
nvlist_t *
vdev_label_read_config(vdev_t *vd, uint64_t txg)
{
	spa_t *spa = vd->vdev_spa;
	nvlist_t *config = NULL;
	vdev_phys_t *vp;
	abd_t *vp_abd;
	zio_t *zio;
	uint64_t best_txg = 0;
	uint64_t label_txg = 0;
	int error = 0;
	int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL |
	    ZIO_FLAG_SPECULATIVE;

	ASSERT(spa_config_held(spa, SCL_STATE_ALL, RW_WRITER) == SCL_STATE_ALL);

	if (!vdev_readable(vd))
		return (NULL);

	vp_abd = abd_alloc_linear(sizeof (vdev_phys_t), B_TRUE);
	vp = abd_to_buf(vp_abd);

retry:
	for (int l = 0; l < VDEV_LABELS; l++) {
		nvlist_t *label = NULL;

		zio = zio_root(spa, NULL, NULL, flags);

		vdev_label_read(zio, vd, l, vp_abd,
		    offsetof(vdev_label_t, vl_vdev_phys),
		    sizeof (vdev_phys_t), NULL, NULL, flags);

		if (zio_wait(zio) == 0 &&
		    nvlist_unpack(vp->vp_nvlist, sizeof (vp->vp_nvlist),
		    &label, 0) == 0) {
			/*
			 * Auxiliary vdevs won't have txg values in their
			 * labels and newly added vdevs may not have been
			 * completely initialized so just return the
			 * configuration from the first valid label we
			 * encounter.
			 */
			error = nvlist_lookup_uint64(label,
			    ZPOOL_CONFIG_POOL_TXG, &label_txg);
			if ((error || label_txg == 0) && !config) {
				config = label;
				break;
			} else if (label_txg <= txg && label_txg > best_txg) {
				best_txg = label_txg;
				nvlist_free(config);
				config = fnvlist_dup(label);
			}
		}

		if (label != NULL) {
			nvlist_free(label);
			label = NULL;
		}
	}

	if (config == NULL && !(flags & ZIO_FLAG_TRYHARD)) {
		flags |= ZIO_FLAG_TRYHARD;
		goto retry;
	}

	/*
	 * We found a valid label but it didn't pass txg restrictions.
	 */
	if (config == NULL && label_txg != 0) {
		vdev_dbgmsg(vd, "label discarded as txg is too large "
		    "(%llu > %llu)", (u_longlong_t)label_txg,
		    (u_longlong_t)txg);
	}

	abd_free(vp_abd);

	return (config);
}

/*
 * Determine if a device is in use.  The 'spare_guid' parameter will be filled
 * in with the device guid if this spare is active elsewhere on the system.
 */
static boolean_t
vdev_inuse(vdev_t *vd, uint64_t crtxg, vdev_labeltype_t reason,
    uint64_t *spare_guid, uint64_t *l2cache_guid)
{
	spa_t *spa = vd->vdev_spa;
	uint64_t state, pool_guid, device_guid, txg, spare_pool;
	uint64_t vdtxg = 0;
	nvlist_t *label;

	if (spare_guid)
		*spare_guid = 0ULL;
	if (l2cache_guid)
		*l2cache_guid = 0ULL;

	/*
	 * Read the label, if any, and perform some basic sanity checks.
	 */
	if ((label = vdev_label_read_config(vd, -1ULL)) == NULL)
		return (B_FALSE);

	(void) nvlist_lookup_uint64(label, ZPOOL_CONFIG_CREATE_TXG,
	    &vdtxg);

	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_STATE,
	    &state) != 0 ||
	    nvlist_lookup_uint64(label, ZPOOL_CONFIG_GUID,
	    &device_guid) != 0) {
		nvlist_free(label);
		return (B_FALSE);
	}

	if (state != POOL_STATE_SPARE && state != POOL_STATE_L2CACHE &&
	    (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_GUID,
	    &pool_guid) != 0 ||
	    nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_TXG,
	    &txg) != 0)) {
		nvlist_free(label);
		return (B_FALSE);
	}

	nvlist_free(label);

	/*
	 * Check to see if this device indeed belongs to the pool it claims to
	 * be a part of.  The only way this is allowed is if the device is a hot
	 * spare (which we check for later on).
	 */
	if (state != POOL_STATE_SPARE && state != POOL_STATE_L2CACHE &&
	    !spa_guid_exists(pool_guid, device_guid) &&
	    !spa_spare_exists(device_guid, NULL, NULL) &&
	    !spa_l2cache_exists(device_guid, NULL))
		return (B_FALSE);

	/*
	 * If the transaction group is zero, then this an initialized (but
	 * unused) label.  This is only an error if the create transaction
	 * on-disk is the same as the one we're using now, in which case the
	 * user has attempted to add the same vdev multiple times in the same
	 * transaction.
	 */
	if (state != POOL_STATE_SPARE && state != POOL_STATE_L2CACHE &&
	    txg == 0 && vdtxg == crtxg)
		return (B_TRUE);

	/*
	 * Check to see if this is a spare device.  We do an explicit check for
	 * spa_has_spare() here because it may be on our pending list of spares
	 * to add.  We also check if it is an l2cache device.
	 */
	if (spa_spare_exists(device_guid, &spare_pool, NULL) ||
	    spa_has_spare(spa, device_guid)) {
		if (spare_guid)
			*spare_guid = device_guid;

		switch (reason) {
		case VDEV_LABEL_CREATE:
		case VDEV_LABEL_L2CACHE:
			return (B_TRUE);

		case VDEV_LABEL_REPLACE:
			return (!spa_has_spare(spa, device_guid) ||
			    spare_pool != 0ULL);

		case VDEV_LABEL_SPARE:
			return (spa_has_spare(spa, device_guid));
		default:
			break;
		}
	}

	/*
	 * Check to see if this is an l2cache device.
	 */
	if (spa_l2cache_exists(device_guid, NULL))
		return (B_TRUE);

	/*
	 * We can't rely on a pool's state if it's been imported
	 * read-only.  Instead we look to see if the pools is marked
	 * read-only in the namespace and set the state to active.
	 */
	if (state != POOL_STATE_SPARE && state != POOL_STATE_L2CACHE &&
	    (spa = spa_by_guid(pool_guid, device_guid)) != NULL &&
	    spa_mode(spa) == SPA_MODE_READ)
		state = POOL_STATE_ACTIVE;

	/*
	 * If the device is marked ACTIVE, then this device is in use by another
	 * pool on the system.
	 */
	return (state == POOL_STATE_ACTIVE);
}

/*
 * Initialize a vdev label.  We check to make sure each leaf device is not in
 * use, and writable.  We put down an initial label which we will later
 * overwrite with a complete label.  Note that it's important to do this
 * sequentially, not in parallel, so that we catch cases of multiple use of the
 * same leaf vdev in the vdev we're creating -- e.g. mirroring a disk with
 * itself.
 */
int
vdev_label_init(vdev_t *vd, uint64_t crtxg, vdev_labeltype_t reason)
{
	spa_t *spa = vd->vdev_spa;
	nvlist_t *label;
	vdev_phys_t *vp;
	abd_t *vp_abd;
	abd_t *bootenv;
	uberblock_t *ub;
	abd_t *ub_abd;
	zio_t *zio;
	char *buf;
	size_t buflen;
	int error;
	uint64_t spare_guid = 0, l2cache_guid = 0;
	int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL;

	ASSERT(spa_config_held(spa, SCL_ALL, RW_WRITER) == SCL_ALL);

	for (int c = 0; c < vd->vdev_children; c++)
		if ((error = vdev_label_init(vd->vdev_child[c],
		    crtxg, reason)) != 0)
			return (error);

	/* Track the creation time for this vdev */
	vd->vdev_crtxg = crtxg;

	if (!vd->vdev_ops->vdev_op_leaf || !spa_writeable(spa))
		return (0);

	/*
	 * Dead vdevs cannot be initialized.
	 */
	if (vdev_is_dead(vd))
		return (SET_ERROR(EIO));

	/*
	 * Determine if the vdev is in use.
	 */
	if (reason != VDEV_LABEL_REMOVE && reason != VDEV_LABEL_SPLIT &&
	    vdev_inuse(vd, crtxg, reason, &spare_guid, &l2cache_guid))
		return (SET_ERROR(EBUSY));

	/*
	 * If this is a request to add or replace a spare or l2cache device
	 * that is in use elsewhere on the system, then we must update the
	 * guid (which was initialized to a random value) to reflect the
	 * actual GUID (which is shared between multiple pools).
	 */
	if (reason != VDEV_LABEL_REMOVE && reason != VDEV_LABEL_L2CACHE &&
	    spare_guid != 0ULL) {
		uint64_t guid_delta = spare_guid - vd->vdev_guid;

		vd->vdev_guid += guid_delta;

		for (vdev_t *pvd = vd; pvd != NULL; pvd = pvd->vdev_parent)
			pvd->vdev_guid_sum += guid_delta;

		/*
		 * If this is a replacement, then we want to fallthrough to the
		 * rest of the code.  If we're adding a spare, then it's already
		 * labeled appropriately and we can just return.
		 */
		if (reason == VDEV_LABEL_SPARE)
			return (0);
		ASSERT(reason == VDEV_LABEL_REPLACE ||
		    reason == VDEV_LABEL_SPLIT);
	}

	if (reason != VDEV_LABEL_REMOVE && reason != VDEV_LABEL_SPARE &&
	    l2cache_guid != 0ULL) {
		uint64_t guid_delta = l2cache_guid - vd->vdev_guid;

		vd->vdev_guid += guid_delta;

		for (vdev_t *pvd = vd; pvd != NULL; pvd = pvd->vdev_parent)
			pvd->vdev_guid_sum += guid_delta;

		/*
		 * If this is a replacement, then we want to fallthrough to the
		 * rest of the code.  If we're adding an l2cache, then it's
		 * already labeled appropriately and we can just return.
		 */
		if (reason == VDEV_LABEL_L2CACHE)
			return (0);
		ASSERT(reason == VDEV_LABEL_REPLACE);
	}

	/*
	 * Initialize its label.
	 */
	vp_abd = abd_alloc_linear(sizeof (vdev_phys_t), B_TRUE);
	abd_zero(vp_abd, sizeof (vdev_phys_t));
	vp = abd_to_buf(vp_abd);

	/*
	 * Generate a label describing the pool and our top-level vdev.
	 * We mark it as being from txg 0 to indicate that it's not
	 * really part of an active pool just yet.  The labels will
	 * be written again with a meaningful txg by spa_sync().
	 */
	if (reason == VDEV_LABEL_SPARE ||
	    (reason == VDEV_LABEL_REMOVE && vd->vdev_isspare)) {
		/*
		 * For inactive hot spares, we generate a special label that
		 * identifies as a mutually shared hot spare.  We write the
		 * label if we are adding a hot spare, or if we are removing an
		 * active hot spare (in which case we want to revert the
		 * labels).
		 */
		VERIFY(nvlist_alloc(&label, NV_UNIQUE_NAME, KM_SLEEP) == 0);

		VERIFY(nvlist_add_uint64(label, ZPOOL_CONFIG_VERSION,
		    spa_version(spa)) == 0);
		VERIFY(nvlist_add_uint64(label, ZPOOL_CONFIG_POOL_STATE,
		    POOL_STATE_SPARE) == 0);
		VERIFY(nvlist_add_uint64(label, ZPOOL_CONFIG_GUID,
		    vd->vdev_guid) == 0);
	} else if (reason == VDEV_LABEL_L2CACHE ||
	    (reason == VDEV_LABEL_REMOVE && vd->vdev_isl2cache)) {
		/*
		 * For level 2 ARC devices, add a special label.
		 */
		VERIFY(nvlist_alloc(&label, NV_UNIQUE_NAME, KM_SLEEP) == 0);

		VERIFY(nvlist_add_uint64(label, ZPOOL_CONFIG_VERSION,
		    spa_version(spa)) == 0);
		VERIFY(nvlist_add_uint64(label, ZPOOL_CONFIG_POOL_STATE,
		    POOL_STATE_L2CACHE) == 0);
		VERIFY(nvlist_add_uint64(label, ZPOOL_CONFIG_GUID,
		    vd->vdev_guid) == 0);
	} else {
		uint64_t txg = 0ULL;

		if (reason == VDEV_LABEL_SPLIT)
			txg = spa->spa_uberblock.ub_txg;
		label = spa_config_generate(spa, vd, txg, B_FALSE);

		/*
		 * Add our creation time.  This allows us to detect multiple
		 * vdev uses as described above, and automatically expires if we
		 * fail.
		 */
		VERIFY(nvlist_add_uint64(label, ZPOOL_CONFIG_CREATE_TXG,
		    crtxg) == 0);
	}

	buf = vp->vp_nvlist;
	buflen = sizeof (vp->vp_nvlist);

	error = nvlist_pack(label, &buf, &buflen, NV_ENCODE_XDR, KM_SLEEP);
	if (error != 0) {
		nvlist_free(label);
		abd_free(vp_abd);
		/* EFAULT means nvlist_pack ran out of room */
		return (SET_ERROR(error == EFAULT ? ENAMETOOLONG : EINVAL));
	}

	/*
	 * Initialize uberblock template.
	 */
	ub_abd = abd_alloc_linear(VDEV_UBERBLOCK_RING, B_TRUE);
	abd_zero(ub_abd, VDEV_UBERBLOCK_RING);
	abd_copy_from_buf(ub_abd, &spa->spa_uberblock, sizeof (uberblock_t));
	ub = abd_to_buf(ub_abd);
	ub->ub_txg = 0;

	/* Initialize the 2nd padding area. */
	bootenv = abd_alloc_for_io(VDEV_PAD_SIZE, B_TRUE);
	abd_zero(bootenv, VDEV_PAD_SIZE);

	/*
	 * Write everything in parallel.
	 */
retry:
	zio = zio_root(spa, NULL, NULL, flags);

	for (int l = 0; l < VDEV_LABELS; l++) {

		vdev_label_write(zio, vd, l, vp_abd,
		    offsetof(vdev_label_t, vl_vdev_phys),
		    sizeof (vdev_phys_t), NULL, NULL, flags);

		/*
		 * Skip the 1st padding area.
		 * Zero out the 2nd padding area where it might have
		 * left over data from previous filesystem format.
		 */
		vdev_label_write(zio, vd, l, bootenv,
		    offsetof(vdev_label_t, vl_be),
		    VDEV_PAD_SIZE, NULL, NULL, flags);

		vdev_label_write(zio, vd, l, ub_abd,
		    offsetof(vdev_label_t, vl_uberblock),
		    VDEV_UBERBLOCK_RING, NULL, NULL, flags);
	}

	error = zio_wait(zio);

	if (error != 0 && !(flags & ZIO_FLAG_TRYHARD)) {
		flags |= ZIO_FLAG_TRYHARD;
		goto retry;
	}

	nvlist_free(label);
	abd_free(bootenv);
	abd_free(ub_abd);
	abd_free(vp_abd);

	/*
	 * If this vdev hasn't been previously identified as a spare, then we
	 * mark it as such only if a) we are labeling it as a spare, or b) it
	 * exists as a spare elsewhere in the system.  Do the same for
	 * level 2 ARC devices.
	 */
	if (error == 0 && !vd->vdev_isspare &&
	    (reason == VDEV_LABEL_SPARE ||
	    spa_spare_exists(vd->vdev_guid, NULL, NULL)))
		spa_spare_add(vd);

	if (error == 0 && !vd->vdev_isl2cache &&
	    (reason == VDEV_LABEL_L2CACHE ||
	    spa_l2cache_exists(vd->vdev_guid, NULL)))
		spa_l2cache_add(vd);

	return (error);
}

/*
 * Done callback for vdev_label_read_bootenv_impl. If this is the first
 * callback to finish, store our abd in the callback pointer. Otherwise, we
 * just free our abd and return.
 */
static void
vdev_label_read_bootenv_done(zio_t *zio)
{
	zio_t *rio = zio->io_private;
	abd_t **cbp = rio->io_private;

	ASSERT3U(zio->io_size, ==, VDEV_PAD_SIZE);

	if (zio->io_error == 0) {
		mutex_enter(&rio->io_lock);
		if (*cbp == NULL) {
			/* Will free this buffer in vdev_label_read_bootenv. */
			*cbp = zio->io_abd;
		} else {
			abd_free(zio->io_abd);
		}
		mutex_exit(&rio->io_lock);
	} else {
		abd_free(zio->io_abd);
	}
}

static void
vdev_label_read_bootenv_impl(zio_t *zio, vdev_t *vd, int flags)
{
	for (int c = 0; c < vd->vdev_children; c++)
		vdev_label_read_bootenv_impl(zio, vd->vdev_child[c], flags);

	/*
	 * We just use the first label that has a correct checksum; the
	 * bootloader should have rewritten them all to be the same on boot,
	 * and any changes we made since boot have been the same across all
	 * labels.
	 */
	if (vd->vdev_ops->vdev_op_leaf && vdev_readable(vd)) {
		for (int l = 0; l < VDEV_LABELS; l++) {
			vdev_label_read(zio, vd, l,
			    abd_alloc_linear(VDEV_PAD_SIZE, B_FALSE),
			    offsetof(vdev_label_t, vl_be), VDEV_PAD_SIZE,
			    vdev_label_read_bootenv_done, zio, flags);
		}
	}
}

int
vdev_label_read_bootenv(vdev_t *rvd, nvlist_t *bootenv)
{
	nvlist_t *config;
	spa_t *spa = rvd->vdev_spa;
	abd_t *abd = NULL;
	int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL |
	    ZIO_FLAG_SPECULATIVE | ZIO_FLAG_TRYHARD;

	ASSERT(bootenv);
	ASSERT(spa_config_held(spa, SCL_ALL, RW_WRITER) == SCL_ALL);

	zio_t *zio = zio_root(spa, NULL, &abd, flags);
	vdev_label_read_bootenv_impl(zio, rvd, flags);
	int err = zio_wait(zio);

	if (abd != NULL) {
		char *buf;
		vdev_boot_envblock_t *vbe = abd_to_buf(abd);

		vbe->vbe_version = ntohll(vbe->vbe_version);
		switch (vbe->vbe_version) {
		case VB_RAW:
			/*
			 * if we have textual data in vbe_bootenv, create nvlist
			 * with key "envmap".
			 */
			fnvlist_add_uint64(bootenv, BOOTENV_VERSION, VB_RAW);
			vbe->vbe_bootenv[sizeof (vbe->vbe_bootenv) - 1] = '\0';
			fnvlist_add_string(bootenv, GRUB_ENVMAP,
			    vbe->vbe_bootenv);
			break;

		case VB_NVLIST:
			err = nvlist_unpack(vbe->vbe_bootenv,
			    sizeof (vbe->vbe_bootenv), &config, 0);
			if (err == 0) {
				fnvlist_merge(bootenv, config);
				nvlist_free(config);
				break;
			}
			/* FALLTHROUGH */
		default:
			/* Check for FreeBSD zfs bootonce command string */
			buf = abd_to_buf(abd);
			if (*buf == '\0') {
				fnvlist_add_uint64(bootenv, BOOTENV_VERSION,
				    VB_NVLIST);
				break;
			}
			fnvlist_add_string(bootenv, FREEBSD_BOOTONCE, buf);
		}

		/*
		 * abd was allocated in vdev_label_read_bootenv_impl()
		 */
		abd_free(abd);
		/*
		 * If we managed to read any successfully,
		 * return success.
		 */
		return (0);
	}
	return (err);
}

int
vdev_label_write_bootenv(vdev_t *vd, nvlist_t *env)
{
	zio_t *zio;
	spa_t *spa = vd->vdev_spa;
	vdev_boot_envblock_t *bootenv;
	int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL;
	int error;
	size_t nvsize;
	char *nvbuf;

	error = nvlist_size(env, &nvsize, NV_ENCODE_XDR);
	if (error != 0)
		return (SET_ERROR(error));

	if (nvsize >= sizeof (bootenv->vbe_bootenv)) {
		return (SET_ERROR(E2BIG));
	}

	ASSERT(spa_config_held(spa, SCL_ALL, RW_WRITER) == SCL_ALL);

	error = ENXIO;
	for (int c = 0; c < vd->vdev_children; c++) {
		int child_err;

		child_err = vdev_label_write_bootenv(vd->vdev_child[c], env);
		/*
		 * As long as any of the disks managed to write all of their
		 * labels successfully, return success.
		 */
		if (child_err == 0)
			error = child_err;
	}

	if (!vd->vdev_ops->vdev_op_leaf || vdev_is_dead(vd) ||
	    !vdev_writeable(vd)) {
		return (error);
	}
	ASSERT3U(sizeof (*bootenv), ==, VDEV_PAD_SIZE);
	abd_t *abd = abd_alloc_for_io(VDEV_PAD_SIZE, B_TRUE);
	abd_zero(abd, VDEV_PAD_SIZE);

	bootenv = abd_borrow_buf_copy(abd, VDEV_PAD_SIZE);
	nvbuf = bootenv->vbe_bootenv;
	nvsize = sizeof (bootenv->vbe_bootenv);

	bootenv->vbe_version = fnvlist_lookup_uint64(env, BOOTENV_VERSION);
	switch (bootenv->vbe_version) {
	case VB_RAW:
		if (nvlist_lookup_string(env, GRUB_ENVMAP, &nvbuf) == 0) {
			(void) strlcpy(bootenv->vbe_bootenv, nvbuf, nvsize);
		}
		error = 0;
		break;

	case VB_NVLIST:
		error = nvlist_pack(env, &nvbuf, &nvsize, NV_ENCODE_XDR,
		    KM_SLEEP);
		break;

	default:
		error = EINVAL;
		break;
	}

	if (error == 0) {
		bootenv->vbe_version = htonll(bootenv->vbe_version);
		abd_return_buf_copy(abd, bootenv, VDEV_PAD_SIZE);
	} else {
		abd_free(abd);
		return (SET_ERROR(error));
	}

retry:
	zio = zio_root(spa, NULL, NULL, flags);
	for (int l = 0; l < VDEV_LABELS; l++) {
		vdev_label_write(zio, vd, l, abd,
		    offsetof(vdev_label_t, vl_be),
		    VDEV_PAD_SIZE, NULL, NULL, flags);
	}

	error = zio_wait(zio);
	if (error != 0 && !(flags & ZIO_FLAG_TRYHARD)) {
		flags |= ZIO_FLAG_TRYHARD;
		goto retry;
	}

	abd_free(abd);
	return (error);
}

/*
 * ==========================================================================
 * uberblock load/sync
 * ==========================================================================
 */

/*
 * Consider the following situation: txg is safely synced to disk.  We've
 * written the first uberblock for txg + 1, and then we lose power.  When we
 * come back up, we fail to see the uberblock for txg + 1 because, say,
 * it was on a mirrored device and the replica to which we wrote txg + 1
 * is now offline.  If we then make some changes and sync txg + 1, and then
 * the missing replica comes back, then for a few seconds we'll have two
 * conflicting uberblocks on disk with the same txg.  The solution is simple:
 * among uberblocks with equal txg, choose the one with the latest timestamp.
 */
static int
vdev_uberblock_compare(const uberblock_t *ub1, const uberblock_t *ub2)
{
	int cmp = TREE_CMP(ub1->ub_txg, ub2->ub_txg);

	if (likely(cmp))
		return (cmp);

	cmp = TREE_CMP(ub1->ub_timestamp, ub2->ub_timestamp);
	if (likely(cmp))
		return (cmp);

	/*
	 * If MMP_VALID(ub) && MMP_SEQ_VALID(ub) then the host has an MMP-aware
	 * ZFS, e.g. zfsonlinux >= 0.7.
	 *
	 * If one ub has MMP and the other does not, they were written by
	 * different hosts, which matters for MMP.  So we treat no MMP/no SEQ as
	 * a 0 value.
	 *
	 * Since timestamp and txg are the same if we get this far, either is
	 * acceptable for importing the pool.
	 */
	unsigned int seq1 = 0;
	unsigned int seq2 = 0;

	if (MMP_VALID(ub1) && MMP_SEQ_VALID(ub1))
		seq1 = MMP_SEQ(ub1);

	if (MMP_VALID(ub2) && MMP_SEQ_VALID(ub2))
		seq2 = MMP_SEQ(ub2);

	return (TREE_CMP(seq1, seq2));
}

struct ubl_cbdata {
	uberblock_t	*ubl_ubbest;	/* Best uberblock */
	vdev_t		*ubl_vd;	/* vdev associated with the above */
};

static void
vdev_uberblock_load_done(zio_t *zio)
{
	vdev_t *vd = zio->io_vd;
	spa_t *spa = zio->io_spa;
	zio_t *rio = zio->io_private;
	uberblock_t *ub = abd_to_buf(zio->io_abd);
	struct ubl_cbdata *cbp = rio->io_private;

	ASSERT3U(zio->io_size, ==, VDEV_UBERBLOCK_SIZE(vd));

	if (zio->io_error == 0 && uberblock_verify(ub) == 0) {
		mutex_enter(&rio->io_lock);
		if (ub->ub_txg <= spa->spa_load_max_txg &&
		    vdev_uberblock_compare(ub, cbp->ubl_ubbest) > 0) {
			/*
			 * Keep track of the vdev in which this uberblock
			 * was found. We will use this information later
			 * to obtain the config nvlist associated with
			 * this uberblock.
			 */
			*cbp->ubl_ubbest = *ub;
			cbp->ubl_vd = vd;
		}
		mutex_exit(&rio->io_lock);
	}

	abd_free(zio->io_abd);
}

static void
vdev_uberblock_load_impl(zio_t *zio, vdev_t *vd, int flags,
    struct ubl_cbdata *cbp)
{
	for (int c = 0; c < vd->vdev_children; c++)
		vdev_uberblock_load_impl(zio, vd->vdev_child[c], flags, cbp);

	if (vd->vdev_ops->vdev_op_leaf && vdev_readable(vd)) {
		for (int l = 0; l < VDEV_LABELS; l++) {
			for (int n = 0; n < VDEV_UBERBLOCK_COUNT(vd); n++) {
				vdev_label_read(zio, vd, l,
				    abd_alloc_linear(VDEV_UBERBLOCK_SIZE(vd),
				    B_TRUE), VDEV_UBERBLOCK_OFFSET(vd, n),
				    VDEV_UBERBLOCK_SIZE(vd),
				    vdev_uberblock_load_done, zio, flags);
			}
		}
	}
}

/*
 * Reads the 'best' uberblock from disk along with its associated
 * configuration. First, we read the uberblock array of each label of each
 * vdev, keeping track of the uberblock with the highest txg in each array.
 * Then, we read the configuration from the same vdev as the best uberblock.
 */
void
vdev_uberblock_load(vdev_t *rvd, uberblock_t *ub, nvlist_t **config)
{
	zio_t *zio;
	spa_t *spa = rvd->vdev_spa;
	struct ubl_cbdata cb;
	int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL |
	    ZIO_FLAG_SPECULATIVE | ZIO_FLAG_TRYHARD;

	ASSERT(ub);
	ASSERT(config);

	bzero(ub, sizeof (uberblock_t));
	*config = NULL;

	cb.ubl_ubbest = ub;
	cb.ubl_vd = NULL;

	spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
	zio = zio_root(spa, NULL, &cb, flags);
	vdev_uberblock_load_impl(zio, rvd, flags, &cb);
	(void) zio_wait(zio);

	/*
	 * It's possible that the best uberblock was discovered on a label
	 * that has a configuration which was written in a future txg.
	 * Search all labels on this vdev to find the configuration that
	 * matches the txg for our uberblock.
	 */
	if (cb.ubl_vd != NULL) {
		vdev_dbgmsg(cb.ubl_vd, "best uberblock found for spa %s. "
		    "txg %llu", spa->spa_name, (u_longlong_t)ub->ub_txg);

		*config = vdev_label_read_config(cb.ubl_vd, ub->ub_txg);
		if (*config == NULL && spa->spa_extreme_rewind) {
			vdev_dbgmsg(cb.ubl_vd, "failed to read label config. "
			    "Trying again without txg restrictions.");
			*config = vdev_label_read_config(cb.ubl_vd, UINT64_MAX);
		}
		if (*config == NULL) {
			vdev_dbgmsg(cb.ubl_vd, "failed to read label config");
		}
	}
	spa_config_exit(spa, SCL_ALL, FTAG);
}

/*
 * For use when a leaf vdev is expanded.
 * The location of labels 2 and 3 changed, and at the new location the
 * uberblock rings are either empty or contain garbage.  The sync will write
 * new configs there because the vdev is dirty, but expansion also needs the
 * uberblock rings copied.  Read them from label 0 which did not move.
 *
 * Since the point is to populate labels {2,3} with valid uberblocks,
 * we zero uberblocks we fail to read or which are not valid.
 */

static void
vdev_copy_uberblocks(vdev_t *vd)
{
	abd_t *ub_abd;
	zio_t *write_zio;
	int locks = (SCL_L2ARC | SCL_ZIO);
	int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL |
	    ZIO_FLAG_SPECULATIVE;

	ASSERT(spa_config_held(vd->vdev_spa, SCL_STATE, RW_READER) ==
	    SCL_STATE);
	ASSERT(vd->vdev_ops->vdev_op_leaf);

	spa_config_enter(vd->vdev_spa, locks, FTAG, RW_READER);

	ub_abd = abd_alloc_linear(VDEV_UBERBLOCK_SIZE(vd), B_TRUE);

	write_zio = zio_root(vd->vdev_spa, NULL, NULL, flags);
	for (int n = 0; n < VDEV_UBERBLOCK_COUNT(vd); n++) {
		const int src_label = 0;
		zio_t *zio;

		zio = zio_root(vd->vdev_spa, NULL, NULL, flags);
		vdev_label_read(zio, vd, src_label, ub_abd,
		    VDEV_UBERBLOCK_OFFSET(vd, n), VDEV_UBERBLOCK_SIZE(vd),
		    NULL, NULL, flags);

		if (zio_wait(zio) || uberblock_verify(abd_to_buf(ub_abd)))
			abd_zero(ub_abd, VDEV_UBERBLOCK_SIZE(vd));

		for (int l = 2; l < VDEV_LABELS; l++)
			vdev_label_write(write_zio, vd, l, ub_abd,
			    VDEV_UBERBLOCK_OFFSET(vd, n),
			    VDEV_UBERBLOCK_SIZE(vd), NULL, NULL,
			    flags | ZIO_FLAG_DONT_PROPAGATE);
	}
	(void) zio_wait(write_zio);

	spa_config_exit(vd->vdev_spa, locks, FTAG);

	abd_free(ub_abd);
}

/*
 * On success, increment root zio's count of good writes.
 * We only get credit for writes to known-visible vdevs; see spa_vdev_add().
 */
static void
vdev_uberblock_sync_done(zio_t *zio)
{
	uint64_t *good_writes = zio->io_private;

	if (zio->io_error == 0 && zio->io_vd->vdev_top->vdev_ms_array != 0)
		atomic_inc_64(good_writes);
}

/*
 * Write the uberblock to all labels of all leaves of the specified vdev.
 */
static void
vdev_uberblock_sync(zio_t *zio, uint64_t *good_writes,
    uberblock_t *ub, vdev_t *vd, int flags)
{
	for (uint64_t c = 0; c < vd->vdev_children; c++) {
		vdev_uberblock_sync(zio, good_writes,
		    ub, vd->vdev_child[c], flags);
	}

	if (!vd->vdev_ops->vdev_op_leaf)
		return;

	if (!vdev_writeable(vd))
		return;

	/* If the vdev was expanded, need to copy uberblock rings. */
	if (vd->vdev_state == VDEV_STATE_HEALTHY &&
	    vd->vdev_copy_uberblocks == B_TRUE) {
		vdev_copy_uberblocks(vd);
		vd->vdev_copy_uberblocks = B_FALSE;
	}

	int m = spa_multihost(vd->vdev_spa) ? MMP_BLOCKS_PER_LABEL : 0;
	int n = ub->ub_txg % (VDEV_UBERBLOCK_COUNT(vd) - m);

	/* Copy the uberblock_t into the ABD */
	abd_t *ub_abd = abd_alloc_for_io(VDEV_UBERBLOCK_SIZE(vd), B_TRUE);
	abd_zero(ub_abd, VDEV_UBERBLOCK_SIZE(vd));
	abd_copy_from_buf(ub_abd, ub, sizeof (uberblock_t));

	for (int l = 0; l < VDEV_LABELS; l++)
		vdev_label_write(zio, vd, l, ub_abd,
		    VDEV_UBERBLOCK_OFFSET(vd, n), VDEV_UBERBLOCK_SIZE(vd),
		    vdev_uberblock_sync_done, good_writes,
		    flags | ZIO_FLAG_DONT_PROPAGATE);

	abd_free(ub_abd);
}

/* Sync the uberblocks to all vdevs in svd[] */
static int
vdev_uberblock_sync_list(vdev_t **svd, int svdcount, uberblock_t *ub, int flags)
{
	spa_t *spa = svd[0]->vdev_spa;
	zio_t *zio;
	uint64_t good_writes = 0;

	zio = zio_root(spa, NULL, NULL, flags);

	for (int v = 0; v < svdcount; v++)
		vdev_uberblock_sync(zio, &good_writes, ub, svd[v], flags);

	(void) zio_wait(zio);

	/*
	 * Flush the uberblocks to disk.  This ensures that the odd labels
	 * are no longer needed (because the new uberblocks and the even
	 * labels are safely on disk), so it is safe to overwrite them.
	 */
	zio = zio_root(spa, NULL, NULL, flags);

	for (int v = 0; v < svdcount; v++) {
		if (vdev_writeable(svd[v])) {
			zio_flush(zio, svd[v]);
		}
	}

	(void) zio_wait(zio);

	return (good_writes >= 1 ? 0 : EIO);
}

/*
 * On success, increment the count of good writes for our top-level vdev.
 */
static void
vdev_label_sync_done(zio_t *zio)
{
	uint64_t *good_writes = zio->io_private;

	if (zio->io_error == 0)
		atomic_inc_64(good_writes);
}

/*
 * If there weren't enough good writes, indicate failure to the parent.
 */
static void
vdev_label_sync_top_done(zio_t *zio)
{
	uint64_t *good_writes = zio->io_private;

	if (*good_writes == 0)
		zio->io_error = SET_ERROR(EIO);

	kmem_free(good_writes, sizeof (uint64_t));
}

/*
 * We ignore errors for log and cache devices, simply free the private data.
 */
static void
vdev_label_sync_ignore_done(zio_t *zio)
{
	kmem_free(zio->io_private, sizeof (uint64_t));
}

/*
 * Write all even or odd labels to all leaves of the specified vdev.
 */
static void
vdev_label_sync(zio_t *zio, uint64_t *good_writes,
    vdev_t *vd, int l, uint64_t txg, int flags)
{
	nvlist_t *label;
	vdev_phys_t *vp;
	abd_t *vp_abd;
	char *buf;
	size_t buflen;

	for (int c = 0; c < vd->vdev_children; c++) {
		vdev_label_sync(zio, good_writes,
		    vd->vdev_child[c], l, txg, flags);
	}

	if (!vd->vdev_ops->vdev_op_leaf)
		return;

	if (!vdev_writeable(vd))
		return;

	/*
	 * Generate a label describing the top-level config to which we belong.
	 */
	label = spa_config_generate(vd->vdev_spa, vd, txg, B_FALSE);

	vp_abd = abd_alloc_linear(sizeof (vdev_phys_t), B_TRUE);
	abd_zero(vp_abd, sizeof (vdev_phys_t));
	vp = abd_to_buf(vp_abd);

	buf = vp->vp_nvlist;
	buflen = sizeof (vp->vp_nvlist);

	if (!nvlist_pack(label, &buf, &buflen, NV_ENCODE_XDR, KM_SLEEP)) {
		for (; l < VDEV_LABELS; l += 2) {
			vdev_label_write(zio, vd, l, vp_abd,
			    offsetof(vdev_label_t, vl_vdev_phys),
			    sizeof (vdev_phys_t),
			    vdev_label_sync_done, good_writes,
			    flags | ZIO_FLAG_DONT_PROPAGATE);
		}
	}

	abd_free(vp_abd);
	nvlist_free(label);
}

static int
vdev_label_sync_list(spa_t *spa, int l, uint64_t txg, int flags)
{
	list_t *dl = &spa->spa_config_dirty_list;
	vdev_t *vd;
	zio_t *zio;
	int error;

	/*
	 * Write the new labels to disk.
	 */
	zio = zio_root(spa, NULL, NULL, flags);

	for (vd = list_head(dl); vd != NULL; vd = list_next(dl, vd)) {
		uint64_t *good_writes;

		ASSERT(!vd->vdev_ishole);

		good_writes = kmem_zalloc(sizeof (uint64_t), KM_SLEEP);
		zio_t *vio = zio_null(zio, spa, NULL,
		    (vd->vdev_islog || vd->vdev_aux != NULL) ?
		    vdev_label_sync_ignore_done : vdev_label_sync_top_done,
		    good_writes, flags);
		vdev_label_sync(vio, good_writes, vd, l, txg, flags);
		zio_nowait(vio);
	}

	error = zio_wait(zio);

	/*
	 * Flush the new labels to disk.
	 */
	zio = zio_root(spa, NULL, NULL, flags);

	for (vd = list_head(dl); vd != NULL; vd = list_next(dl, vd))
		zio_flush(zio, vd);

	(void) zio_wait(zio);

	return (error);
}

/*
 * Sync the uberblock and any changes to the vdev configuration.
 *
 * The order of operations is carefully crafted to ensure that
 * if the system panics or loses power at any time, the state on disk
 * is still transactionally consistent.  The in-line comments below
 * describe the failure semantics at each stage.
 *
 * Moreover, vdev_config_sync() is designed to be idempotent: if it fails
 * at any time, you can just call it again, and it will resume its work.
 */
int
vdev_config_sync(vdev_t **svd, int svdcount, uint64_t txg)
{
	spa_t *spa = svd[0]->vdev_spa;
	uberblock_t *ub = &spa->spa_uberblock;
	int error = 0;
	int flags = ZIO_FLAG_CONFIG_WRITER | ZIO_FLAG_CANFAIL;

	ASSERT(svdcount != 0);
retry:
	/*
	 * Normally, we don't want to try too hard to write every label and
	 * uberblock.  If there is a flaky disk, we don't want the rest of the
	 * sync process to block while we retry.  But if we can't write a
	 * single label out, we should retry with ZIO_FLAG_TRYHARD before
	 * bailing out and declaring the pool faulted.
	 */
	if (error != 0) {
		if ((flags & ZIO_FLAG_TRYHARD) != 0)
			return (error);
		flags |= ZIO_FLAG_TRYHARD;
	}

	ASSERT(ub->ub_txg <= txg);

	/*
	 * If this isn't a resync due to I/O errors,
	 * and nothing changed in this transaction group,
	 * and the vdev configuration hasn't changed,
	 * then there's nothing to do.
	 */
	if (ub->ub_txg < txg) {
		boolean_t changed = uberblock_update(ub, spa->spa_root_vdev,
		    txg, spa->spa_mmp.mmp_delay);

		if (!changed && list_is_empty(&spa->spa_config_dirty_list))
			return (0);
	}

	if (txg > spa_freeze_txg(spa))
		return (0);

	ASSERT(txg <= spa->spa_final_txg);

	/*
	 * Flush the write cache of every disk that's been written to
	 * in this transaction group.  This ensures that all blocks
	 * written in this txg will be committed to stable storage
	 * before any uberblock that references them.
	 */
	zio_t *zio = zio_root(spa, NULL, NULL, flags);

	for (vdev_t *vd =
	    txg_list_head(&spa->spa_vdev_txg_list, TXG_CLEAN(txg)); vd != NULL;
	    vd = txg_list_next(&spa->spa_vdev_txg_list, vd, TXG_CLEAN(txg)))
		zio_flush(zio, vd);

	(void) zio_wait(zio);

	/*
	 * Sync out the even labels (L0, L2) for every dirty vdev.  If the
	 * system dies in the middle of this process, that's OK: all of the
	 * even labels that made it to disk will be newer than any uberblock,
	 * and will therefore be considered invalid.  The odd labels (L1, L3),
	 * which have not yet been touched, will still be valid.  We flush
	 * the new labels to disk to ensure that all even-label updates
	 * are committed to stable storage before the uberblock update.
	 */
	if ((error = vdev_label_sync_list(spa, 0, txg, flags)) != 0) {
		if ((flags & ZIO_FLAG_TRYHARD) != 0) {
			zfs_dbgmsg("vdev_label_sync_list() returned error %d "
			    "for pool '%s' when syncing out the even labels "
			    "of dirty vdevs", error, spa_name(spa));
		}
		goto retry;
	}

	/*
	 * Sync the uberblocks to all vdevs in svd[].
	 * If the system dies in the middle of this step, there are two cases
	 * to consider, and the on-disk state is consistent either way:
	 *
	 * (1)	If none of the new uberblocks made it to disk, then the
	 *	previous uberblock will be the newest, and the odd labels
	 *	(which had not yet been touched) will be valid with respect
	 *	to that uberblock.
	 *
	 * (2)	If one or more new uberblocks made it to disk, then they
	 *	will be the newest, and the even labels (which had all
	 *	been successfully committed) will be valid with respect
	 *	to the new uberblocks.
	 */
	if ((error = vdev_uberblock_sync_list(svd, svdcount, ub, flags)) != 0) {
		if ((flags & ZIO_FLAG_TRYHARD) != 0) {
			zfs_dbgmsg("vdev_uberblock_sync_list() returned error "
			    "%d for pool '%s'", error, spa_name(spa));
		}
		goto retry;
	}

	if (spa_multihost(spa))
		mmp_update_uberblock(spa, ub);

	/*
	 * Sync out odd labels for every dirty vdev.  If the system dies
	 * in the middle of this process, the even labels and the new
	 * uberblocks will suffice to open the pool.  The next time
	 * the pool is opened, the first thing we'll do -- before any
	 * user data is modified -- is mark every vdev dirty so that
	 * all labels will be brought up to date.  We flush the new labels
	 * to disk to ensure that all odd-label updates are committed to
	 * stable storage before the next transaction group begins.
	 */
	if ((error = vdev_label_sync_list(spa, 1, txg, flags)) != 0) {
		if ((flags & ZIO_FLAG_TRYHARD) != 0) {
			zfs_dbgmsg("vdev_label_sync_list() returned error %d "
			    "for pool '%s' when syncing out the odd labels of "
			    "dirty vdevs", error, spa_name(spa));
		}
		goto retry;
	}

	return (0);
}