aboutsummaryrefslogtreecommitdiff
path: root/sys/cddl/contrib/opensolaris/uts/common/fs/zfs/vdev.c
blob: 6043adee0241fa831ba90a93c0d1f2db2f39a6b4 (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
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
/*
 * 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) 2011, 2018 by Delphix. All rights reserved.
 * Copyright 2017 Nexenta Systems, Inc.
 * Copyright 2013 Martin Matuska <mm@FreeBSD.org>. All rights reserved.
 * Copyright (c) 2014 Integros [integros.com]
 * Copyright 2016 Toomas Soome <tsoome@me.com>
 * Copyright 2019 Joyent, Inc.
 * Copyright (c) 2017, Intel Corporation.
 */

#include <sys/zfs_context.h>
#include <sys/fm/fs/zfs.h>
#include <sys/spa.h>
#include <sys/spa_impl.h>
#include <sys/bpobj.h>
#include <sys/dmu.h>
#include <sys/dmu_tx.h>
#include <sys/dsl_dir.h>
#include <sys/vdev_impl.h>
#include <sys/uberblock_impl.h>
#include <sys/metaslab.h>
#include <sys/metaslab_impl.h>
#include <sys/space_map.h>
#include <sys/space_reftree.h>
#include <sys/zio.h>
#include <sys/zap.h>
#include <sys/fs/zfs.h>
#include <sys/arc.h>
#include <sys/zil.h>
#include <sys/dsl_scan.h>
#include <sys/abd.h>
#include <sys/trim_map.h>
#include <sys/vdev_initialize.h>

SYSCTL_DECL(_vfs_zfs);
SYSCTL_NODE(_vfs_zfs, OID_AUTO, vdev, CTLFLAG_RW | CTLFLAG_MPSAFE, 0,
    "ZFS VDEV");

/*
 * Virtual device management.
 */

/*
 * The limit for ZFS to automatically increase a top-level vdev's ashift
 * from logical ashift to physical ashift.
 *
 * Example: one or more 512B emulation child vdevs
 *          child->vdev_ashift = 9 (512 bytes)
 *          child->vdev_physical_ashift = 12 (4096 bytes)
 *          zfs_max_auto_ashift = 11 (2048 bytes)
 *          zfs_min_auto_ashift = 9 (512 bytes)
 *
 * On pool creation or the addition of a new top-level vdev, ZFS will
 * increase the ashift of the top-level vdev to 2048 as limited by
 * zfs_max_auto_ashift.
 *
 * Example: one or more 512B emulation child vdevs
 *          child->vdev_ashift = 9 (512 bytes)
 *          child->vdev_physical_ashift = 12 (4096 bytes)
 *          zfs_max_auto_ashift = 13 (8192 bytes)
 *          zfs_min_auto_ashift = 9 (512 bytes)
 *
 * On pool creation or the addition of a new top-level vdev, ZFS will
 * increase the ashift of the top-level vdev to 4096 to match the
 * max vdev_physical_ashift.
 *
 * Example: one or more 512B emulation child vdevs
 *          child->vdev_ashift = 9 (512 bytes)
 *          child->vdev_physical_ashift = 9 (512 bytes)
 *          zfs_max_auto_ashift = 13 (8192 bytes)
 *          zfs_min_auto_ashift = 12 (4096 bytes)
 *
 * On pool creation or the addition of a new top-level vdev, ZFS will
 * increase the ashift of the top-level vdev to 4096 to match the
 * zfs_min_auto_ashift.
 */
static uint64_t zfs_max_auto_ashift = SPA_MAXASHIFT;
static uint64_t zfs_min_auto_ashift = SPA_MINASHIFT;

static int
sysctl_vfs_zfs_max_auto_ashift(SYSCTL_HANDLER_ARGS)
{
	uint64_t val;
	int err;

	val = zfs_max_auto_ashift;
	err = sysctl_handle_64(oidp, &val, 0, req);
	if (err != 0 || req->newptr == NULL)
		return (err);

	if (val > SPA_MAXASHIFT || val < zfs_min_auto_ashift)
		return (EINVAL);

	zfs_max_auto_ashift = val;

	return (0);
}
SYSCTL_PROC(_vfs_zfs, OID_AUTO, max_auto_ashift,
    CTLTYPE_U64 | CTLFLAG_MPSAFE | CTLFLAG_RW, 0, sizeof(uint64_t),
    sysctl_vfs_zfs_max_auto_ashift, "QU",
    "Max ashift used when optimising for logical -> physical sectors size on "
    "new top-level vdevs.");

static int
sysctl_vfs_zfs_min_auto_ashift(SYSCTL_HANDLER_ARGS)
{
	uint64_t val;
	int err;

	val = zfs_min_auto_ashift;
	err = sysctl_handle_64(oidp, &val, 0, req);
	if (err != 0 || req->newptr == NULL)
		return (err);

	if (val < SPA_MINASHIFT || val > zfs_max_auto_ashift)
		return (EINVAL);

	zfs_min_auto_ashift = val;

	return (0);
}
SYSCTL_PROC(_vfs_zfs, OID_AUTO, min_auto_ashift,
    CTLTYPE_U64 | CTLFLAG_MPSAFE | CTLFLAG_RW, 0, sizeof(uint64_t),
    sysctl_vfs_zfs_min_auto_ashift, "QU",
    "Min ashift used when creating new top-level vdevs.");

static vdev_ops_t *vdev_ops_table[] = {
	&vdev_root_ops,
	&vdev_raidz_ops,
	&vdev_mirror_ops,
	&vdev_replacing_ops,
	&vdev_spare_ops,
#ifdef _KERNEL
	&vdev_geom_ops,
#else
	&vdev_disk_ops,
#endif
	&vdev_file_ops,
	&vdev_missing_ops,
	&vdev_hole_ops,
	&vdev_indirect_ops,
	NULL
};


/* default target for number of metaslabs per top-level vdev */
int zfs_vdev_default_ms_count = 200;
SYSCTL_INT(_vfs_zfs_vdev, OID_AUTO, default_ms_count, CTLFLAG_RWTUN,
    &zfs_vdev_default_ms_count, 0,
    "Target number of metaslabs per top-level vdev");

/* minimum number of metaslabs per top-level vdev */
int zfs_vdev_min_ms_count = 16;
SYSCTL_INT(_vfs_zfs_vdev, OID_AUTO, min_ms_count, CTLFLAG_RWTUN,
    &zfs_vdev_min_ms_count, 0,
    "Minimum number of metaslabs per top-level vdev");

/* practical upper limit of total metaslabs per top-level vdev */
int zfs_vdev_ms_count_limit = 1ULL << 17;
SYSCTL_INT(_vfs_zfs_vdev, OID_AUTO, max_ms_count_limit, CTLFLAG_RWTUN,
    &zfs_vdev_ms_count_limit, 0,
    "Maximum number of metaslabs per top-level vdev");

/* lower limit for metaslab size (512M) */
int zfs_vdev_default_ms_shift = 29;
SYSCTL_INT(_vfs_zfs_vdev, OID_AUTO, default_ms_shift, CTLFLAG_RWTUN,
    &zfs_vdev_default_ms_shift, 0,
    "Default shift between vdev size and number of metaslabs");

/* upper limit for metaslab size (16G) */
int zfs_vdev_max_ms_shift = 34;
SYSCTL_INT(_vfs_zfs_vdev, OID_AUTO, max_ms_shift, CTLFLAG_RWTUN,
    &zfs_vdev_max_ms_shift, 0,
    "Maximum shift between vdev size and number of metaslabs");

boolean_t vdev_validate_skip = B_FALSE;
SYSCTL_INT(_vfs_zfs_vdev, OID_AUTO, validate_skip, CTLFLAG_RWTUN,
    &vdev_validate_skip, 0,
    "Bypass vdev validation");

/*
 * Since the DTL space map of a vdev is not expected to have a lot of
 * entries, we default its block size to 4K.
 */
int vdev_dtl_sm_blksz = (1 << 12);
SYSCTL_INT(_vfs_zfs, OID_AUTO, dtl_sm_blksz, CTLFLAG_RDTUN,
    &vdev_dtl_sm_blksz, 0,
    "Block size for DTL space map.  Power of 2 and greater than 4096.");

/*
 * vdev-wide space maps that have lots of entries written to them at
 * the end of each transaction can benefit from a higher I/O bandwidth
 * (e.g. vdev_obsolete_sm), thus we default their block size to 128K.
 */
int vdev_standard_sm_blksz = (1 << 17);
SYSCTL_INT(_vfs_zfs, OID_AUTO, standard_sm_blksz, CTLFLAG_RDTUN,
    &vdev_standard_sm_blksz, 0,
    "Block size for standard space map.  Power of 2 and greater than 4096.");

/*
 * Tunable parameter for debugging or performance analysis. Setting this
 * will cause pool corruption on power loss if a volatile out-of-order
 * write cache is enabled.
 */
boolean_t zfs_nocacheflush = B_FALSE;
SYSCTL_INT(_vfs_zfs, OID_AUTO, cache_flush_disable, CTLFLAG_RWTUN,
    &zfs_nocacheflush, 0, "Disable cache flush");

/*PRINTFLIKE2*/
void
vdev_dbgmsg(vdev_t *vd, const char *fmt, ...)
{
	va_list adx;
	char buf[256];

	va_start(adx, fmt);
	(void) vsnprintf(buf, sizeof (buf), fmt, adx);
	va_end(adx);

	if (vd->vdev_path != NULL) {
		zfs_dbgmsg("%s vdev '%s': %s", vd->vdev_ops->vdev_op_type,
		    vd->vdev_path, buf);
	} else {
		zfs_dbgmsg("%s-%llu vdev (guid %llu): %s",
		    vd->vdev_ops->vdev_op_type,
		    (u_longlong_t)vd->vdev_id,
		    (u_longlong_t)vd->vdev_guid, buf);
	}
}

void
vdev_dbgmsg_print_tree(vdev_t *vd, int indent)
{
	char state[20];

	if (vd->vdev_ishole || vd->vdev_ops == &vdev_missing_ops) {
		zfs_dbgmsg("%*svdev %u: %s", indent, "", vd->vdev_id,
		    vd->vdev_ops->vdev_op_type);
		return;
	}

	switch (vd->vdev_state) {
	case VDEV_STATE_UNKNOWN:
		(void) snprintf(state, sizeof (state), "unknown");
		break;
	case VDEV_STATE_CLOSED:
		(void) snprintf(state, sizeof (state), "closed");
		break;
	case VDEV_STATE_OFFLINE:
		(void) snprintf(state, sizeof (state), "offline");
		break;
	case VDEV_STATE_REMOVED:
		(void) snprintf(state, sizeof (state), "removed");
		break;
	case VDEV_STATE_CANT_OPEN:
		(void) snprintf(state, sizeof (state), "can't open");
		break;
	case VDEV_STATE_FAULTED:
		(void) snprintf(state, sizeof (state), "faulted");
		break;
	case VDEV_STATE_DEGRADED:
		(void) snprintf(state, sizeof (state), "degraded");
		break;
	case VDEV_STATE_HEALTHY:
		(void) snprintf(state, sizeof (state), "healthy");
		break;
	default:
		(void) snprintf(state, sizeof (state), "<state %u>",
		    (uint_t)vd->vdev_state);
	}

	zfs_dbgmsg("%*svdev %u: %s%s, guid: %llu, path: %s, %s", indent,
	    "", (int)vd->vdev_id, vd->vdev_ops->vdev_op_type,
	    vd->vdev_islog ? " (log)" : "",
	    (u_longlong_t)vd->vdev_guid,
	    vd->vdev_path ? vd->vdev_path : "N/A", state);

	for (uint64_t i = 0; i < vd->vdev_children; i++)
		vdev_dbgmsg_print_tree(vd->vdev_child[i], indent + 2);
}

/*
 * Given a vdev type, return the appropriate ops vector.
 */
static vdev_ops_t *
vdev_getops(const char *type)
{
	vdev_ops_t *ops, **opspp;

	for (opspp = vdev_ops_table; (ops = *opspp) != NULL; opspp++)
		if (strcmp(ops->vdev_op_type, type) == 0)
			break;

	return (ops);
}

/*
 * Derive the enumerated alloction bias from string input.
 * String origin is either the per-vdev zap or zpool(1M).
 */
static vdev_alloc_bias_t
vdev_derive_alloc_bias(const char *bias)
{
	vdev_alloc_bias_t alloc_bias = VDEV_BIAS_NONE;

	if (strcmp(bias, VDEV_ALLOC_BIAS_LOG) == 0)
		alloc_bias = VDEV_BIAS_LOG;
	else if (strcmp(bias, VDEV_ALLOC_BIAS_SPECIAL) == 0)
		alloc_bias = VDEV_BIAS_SPECIAL;
	else if (strcmp(bias, VDEV_ALLOC_BIAS_DEDUP) == 0)
		alloc_bias = VDEV_BIAS_DEDUP;

	return (alloc_bias);
}

/* ARGSUSED */
void
vdev_default_xlate(vdev_t *vd, const range_seg_t *in, range_seg_t *res)
{
	res->rs_start = in->rs_start;
	res->rs_end = in->rs_end;
}

/*
 * Default asize function: return the MAX of psize with the asize of
 * all children.  This is what's used by anything other than RAID-Z.
 */
uint64_t
vdev_default_asize(vdev_t *vd, uint64_t psize)
{
	uint64_t asize = P2ROUNDUP(psize, 1ULL << vd->vdev_top->vdev_ashift);
	uint64_t csize;

	for (int c = 0; c < vd->vdev_children; c++) {
		csize = vdev_psize_to_asize(vd->vdev_child[c], psize);
		asize = MAX(asize, csize);
	}

	return (asize);
}

/*
 * Get the minimum allocatable size. We define the allocatable size as
 * the vdev's asize rounded to the nearest metaslab. This allows us to
 * replace or attach devices which don't have the same physical size but
 * can still satisfy the same number of allocations.
 */
uint64_t
vdev_get_min_asize(vdev_t *vd)
{
	vdev_t *pvd = vd->vdev_parent;

	/*
	 * If our parent is NULL (inactive spare or cache) or is the root,
	 * just return our own asize.
	 */
	if (pvd == NULL)
		return (vd->vdev_asize);

	/*
	 * The top-level vdev just returns the allocatable size rounded
	 * to the nearest metaslab.
	 */
	if (vd == vd->vdev_top)
		return (P2ALIGN(vd->vdev_asize, 1ULL << vd->vdev_ms_shift));

	/*
	 * The allocatable space for a raidz vdev is N * sizeof(smallest child),
	 * so each child must provide at least 1/Nth of its asize.
	 */
	if (pvd->vdev_ops == &vdev_raidz_ops)
		return ((pvd->vdev_min_asize + pvd->vdev_children - 1) /
		    pvd->vdev_children);

	return (pvd->vdev_min_asize);
}

void
vdev_set_min_asize(vdev_t *vd)
{
	vd->vdev_min_asize = vdev_get_min_asize(vd);

	for (int c = 0; c < vd->vdev_children; c++)
		vdev_set_min_asize(vd->vdev_child[c]);
}

vdev_t *
vdev_lookup_top(spa_t *spa, uint64_t vdev)
{
	vdev_t *rvd = spa->spa_root_vdev;

	ASSERT(spa_config_held(spa, SCL_ALL, RW_READER) != 0);

	if (vdev < rvd->vdev_children) {
		ASSERT(rvd->vdev_child[vdev] != NULL);
		return (rvd->vdev_child[vdev]);
	}

	return (NULL);
}

vdev_t *
vdev_lookup_by_guid(vdev_t *vd, uint64_t guid)
{
	vdev_t *mvd;

	if (vd->vdev_guid == guid)
		return (vd);

	for (int c = 0; c < vd->vdev_children; c++)
		if ((mvd = vdev_lookup_by_guid(vd->vdev_child[c], guid)) !=
		    NULL)
			return (mvd);

	return (NULL);
}

static int
vdev_count_leaves_impl(vdev_t *vd)
{
	int n = 0;

	if (vd->vdev_ops->vdev_op_leaf)
		return (1);

	for (int c = 0; c < vd->vdev_children; c++)
		n += vdev_count_leaves_impl(vd->vdev_child[c]);

	return (n);
}

int
vdev_count_leaves(spa_t *spa)
{
	return (vdev_count_leaves_impl(spa->spa_root_vdev));
}

void
vdev_add_child(vdev_t *pvd, vdev_t *cvd)
{
	size_t oldsize, newsize;
	uint64_t id = cvd->vdev_id;
	vdev_t **newchild;
	spa_t *spa = cvd->vdev_spa;

	ASSERT(spa_config_held(spa, SCL_ALL, RW_WRITER) == SCL_ALL);
	ASSERT(cvd->vdev_parent == NULL);

	cvd->vdev_parent = pvd;

	if (pvd == NULL)
		return;

	ASSERT(id >= pvd->vdev_children || pvd->vdev_child[id] == NULL);

	oldsize = pvd->vdev_children * sizeof (vdev_t *);
	pvd->vdev_children = MAX(pvd->vdev_children, id + 1);
	newsize = pvd->vdev_children * sizeof (vdev_t *);

	newchild = kmem_zalloc(newsize, KM_SLEEP);
	if (pvd->vdev_child != NULL) {
		bcopy(pvd->vdev_child, newchild, oldsize);
		kmem_free(pvd->vdev_child, oldsize);
	}

	pvd->vdev_child = newchild;
	pvd->vdev_child[id] = cvd;

	cvd->vdev_top = (pvd->vdev_top ? pvd->vdev_top: cvd);
	ASSERT(cvd->vdev_top->vdev_parent->vdev_parent == NULL);

	/*
	 * Walk up all ancestors to update guid sum.
	 */
	for (; pvd != NULL; pvd = pvd->vdev_parent)
		pvd->vdev_guid_sum += cvd->vdev_guid_sum;

	if (cvd->vdev_ops->vdev_op_leaf) {
		list_insert_head(&cvd->vdev_spa->spa_leaf_list, cvd);
		cvd->vdev_spa->spa_leaf_list_gen++;
	}
}

void
vdev_remove_child(vdev_t *pvd, vdev_t *cvd)
{
	int c;
	uint_t id = cvd->vdev_id;

	ASSERT(cvd->vdev_parent == pvd);

	if (pvd == NULL)
		return;

	ASSERT(id < pvd->vdev_children);
	ASSERT(pvd->vdev_child[id] == cvd);

	pvd->vdev_child[id] = NULL;
	cvd->vdev_parent = NULL;

	for (c = 0; c < pvd->vdev_children; c++)
		if (pvd->vdev_child[c])
			break;

	if (c == pvd->vdev_children) {
		kmem_free(pvd->vdev_child, c * sizeof (vdev_t *));
		pvd->vdev_child = NULL;
		pvd->vdev_children = 0;
	}

	if (cvd->vdev_ops->vdev_op_leaf) {
		spa_t *spa = cvd->vdev_spa;
		list_remove(&spa->spa_leaf_list, cvd);
		spa->spa_leaf_list_gen++;
	}

	/*
	 * Walk up all ancestors to update guid sum.
	 */
	for (; pvd != NULL; pvd = pvd->vdev_parent)
		pvd->vdev_guid_sum -= cvd->vdev_guid_sum;
}

/*
 * Remove any holes in the child array.
 */
void
vdev_compact_children(vdev_t *pvd)
{
	vdev_t **newchild, *cvd;
	int oldc = pvd->vdev_children;
	int newc;

	ASSERT(spa_config_held(pvd->vdev_spa, SCL_ALL, RW_WRITER) == SCL_ALL);

	if (oldc == 0)
		return;

	for (int c = newc = 0; c < oldc; c++)
		if (pvd->vdev_child[c])
			newc++;

	if (newc > 0) {
		newchild = kmem_alloc(newc * sizeof (vdev_t *), KM_SLEEP);

		for (int c = newc = 0; c < oldc; c++) {
			if ((cvd = pvd->vdev_child[c]) != NULL) {
				newchild[newc] = cvd;
				cvd->vdev_id = newc++;
			}
		}
	} else {
		newchild = NULL;
	}

	kmem_free(pvd->vdev_child, oldc * sizeof (vdev_t *));
	pvd->vdev_child = newchild;
	pvd->vdev_children = newc;
}

/*
 * Allocate and minimally initialize a vdev_t.
 */
vdev_t *
vdev_alloc_common(spa_t *spa, uint_t id, uint64_t guid, vdev_ops_t *ops)
{
	vdev_t *vd;
	vdev_indirect_config_t *vic;

	vd = kmem_zalloc(sizeof (vdev_t), KM_SLEEP);
	vic = &vd->vdev_indirect_config;

	if (spa->spa_root_vdev == NULL) {
		ASSERT(ops == &vdev_root_ops);
		spa->spa_root_vdev = vd;
		spa->spa_load_guid = spa_generate_guid(NULL);
	}

	if (guid == 0 && ops != &vdev_hole_ops) {
		if (spa->spa_root_vdev == vd) {
			/*
			 * The root vdev's guid will also be the pool guid,
			 * which must be unique among all pools.
			 */
			guid = spa_generate_guid(NULL);
		} else {
			/*
			 * Any other vdev's guid must be unique within the pool.
			 */
			guid = spa_generate_guid(spa);
		}
		ASSERT(!spa_guid_exists(spa_guid(spa), guid));
	}

	vd->vdev_spa = spa;
	vd->vdev_id = id;
	vd->vdev_guid = guid;
	vd->vdev_guid_sum = guid;
	vd->vdev_ops = ops;
	vd->vdev_state = VDEV_STATE_CLOSED;
	vd->vdev_ishole = (ops == &vdev_hole_ops);
	vic->vic_prev_indirect_vdev = UINT64_MAX;

	rw_init(&vd->vdev_indirect_rwlock, NULL, RW_DEFAULT, NULL);
	mutex_init(&vd->vdev_obsolete_lock, NULL, MUTEX_DEFAULT, NULL);
	vd->vdev_obsolete_segments = range_tree_create(NULL, NULL);

	list_link_init(&vd->vdev_leaf_node);
	mutex_init(&vd->vdev_dtl_lock, NULL, MUTEX_DEFAULT, NULL);
	mutex_init(&vd->vdev_stat_lock, NULL, MUTEX_DEFAULT, NULL);
	mutex_init(&vd->vdev_probe_lock, NULL, MUTEX_DEFAULT, NULL);
	mutex_init(&vd->vdev_scan_io_queue_lock, NULL, MUTEX_DEFAULT, NULL);
	mutex_init(&vd->vdev_initialize_lock, NULL, MUTEX_DEFAULT, NULL);
	mutex_init(&vd->vdev_initialize_io_lock, NULL, MUTEX_DEFAULT, NULL);
	cv_init(&vd->vdev_initialize_cv, NULL, CV_DEFAULT, NULL);
	cv_init(&vd->vdev_initialize_io_cv, NULL, CV_DEFAULT, NULL);

	for (int t = 0; t < DTL_TYPES; t++) {
		vd->vdev_dtl[t] = range_tree_create(NULL, NULL);
	}
	txg_list_create(&vd->vdev_ms_list, spa,
	    offsetof(struct metaslab, ms_txg_node));
	txg_list_create(&vd->vdev_dtl_list, spa,
	    offsetof(struct vdev, vdev_dtl_node));
	vd->vdev_stat.vs_timestamp = gethrtime();
	vdev_queue_init(vd);
	vdev_cache_init(vd);

	return (vd);
}

/*
 * Allocate a new vdev.  The 'alloctype' is used to control whether we are
 * creating a new vdev or loading an existing one - the behavior is slightly
 * different for each case.
 */
int
vdev_alloc(spa_t *spa, vdev_t **vdp, nvlist_t *nv, vdev_t *parent, uint_t id,
    int alloctype)
{
	vdev_ops_t *ops;
	char *type;
	uint64_t guid = 0, islog, nparity;
	vdev_t *vd;
	vdev_indirect_config_t *vic;
	vdev_alloc_bias_t alloc_bias = VDEV_BIAS_NONE;
	boolean_t top_level = (parent && !parent->vdev_parent);

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

	if (nvlist_lookup_string(nv, ZPOOL_CONFIG_TYPE, &type) != 0)
		return (SET_ERROR(EINVAL));

	if ((ops = vdev_getops(type)) == NULL)
		return (SET_ERROR(EINVAL));

	/*
	 * If this is a load, get the vdev guid from the nvlist.
	 * Otherwise, vdev_alloc_common() will generate one for us.
	 */
	if (alloctype == VDEV_ALLOC_LOAD) {
		uint64_t label_id;

		if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_ID, &label_id) ||
		    label_id != id)
			return (SET_ERROR(EINVAL));

		if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &guid) != 0)
			return (SET_ERROR(EINVAL));
	} else if (alloctype == VDEV_ALLOC_SPARE) {
		if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &guid) != 0)
			return (SET_ERROR(EINVAL));
	} else if (alloctype == VDEV_ALLOC_L2CACHE) {
		if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &guid) != 0)
			return (SET_ERROR(EINVAL));
	} else if (alloctype == VDEV_ALLOC_ROOTPOOL) {
		if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_GUID, &guid) != 0)
			return (SET_ERROR(EINVAL));
	}

	/*
	 * The first allocated vdev must be of type 'root'.
	 */
	if (ops != &vdev_root_ops && spa->spa_root_vdev == NULL)
		return (SET_ERROR(EINVAL));

	/*
	 * Determine whether we're a log vdev.
	 */
	islog = 0;
	(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_IS_LOG, &islog);
	if (islog && spa_version(spa) < SPA_VERSION_SLOGS)
		return (SET_ERROR(ENOTSUP));

	if (ops == &vdev_hole_ops && spa_version(spa) < SPA_VERSION_HOLES)
		return (SET_ERROR(ENOTSUP));

	/*
	 * Set the nparity property for RAID-Z vdevs.
	 */
	nparity = -1ULL;
	if (ops == &vdev_raidz_ops) {
		if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_NPARITY,
		    &nparity) == 0) {
			if (nparity == 0 || nparity > VDEV_RAIDZ_MAXPARITY)
				return (SET_ERROR(EINVAL));
			/*
			 * Previous versions could only support 1 or 2 parity
			 * device.
			 */
			if (nparity > 1 &&
			    spa_version(spa) < SPA_VERSION_RAIDZ2)
				return (SET_ERROR(ENOTSUP));
			if (nparity > 2 &&
			    spa_version(spa) < SPA_VERSION_RAIDZ3)
				return (SET_ERROR(ENOTSUP));
		} else {
			/*
			 * We require the parity to be specified for SPAs that
			 * support multiple parity levels.
			 */
			if (spa_version(spa) >= SPA_VERSION_RAIDZ2)
				return (SET_ERROR(EINVAL));
			/*
			 * Otherwise, we default to 1 parity device for RAID-Z.
			 */
			nparity = 1;
		}
	} else {
		nparity = 0;
	}
	ASSERT(nparity != -1ULL);

	/*
	 * If creating a top-level vdev, check for allocation classes input
	 */
	if (top_level && alloctype == VDEV_ALLOC_ADD) {
		char *bias;

		if (nvlist_lookup_string(nv, ZPOOL_CONFIG_ALLOCATION_BIAS,
		    &bias) == 0) {
			alloc_bias = vdev_derive_alloc_bias(bias);

			/* spa_vdev_add() expects feature to be enabled */
			if (alloc_bias != VDEV_BIAS_LOG &&
			    spa->spa_load_state != SPA_LOAD_CREATE &&
			    !spa_feature_is_enabled(spa,
			    SPA_FEATURE_ALLOCATION_CLASSES)) {
				return (SET_ERROR(ENOTSUP));
			}
		}
	}

	vd = vdev_alloc_common(spa, id, guid, ops);
	vic = &vd->vdev_indirect_config;

	vd->vdev_islog = islog;
	vd->vdev_nparity = nparity;
	if (top_level && alloc_bias != VDEV_BIAS_NONE)
		vd->vdev_alloc_bias = alloc_bias;

	if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PATH, &vd->vdev_path) == 0)
		vd->vdev_path = spa_strdup(vd->vdev_path);
	if (nvlist_lookup_string(nv, ZPOOL_CONFIG_DEVID, &vd->vdev_devid) == 0)
		vd->vdev_devid = spa_strdup(vd->vdev_devid);
	if (nvlist_lookup_string(nv, ZPOOL_CONFIG_PHYS_PATH,
	    &vd->vdev_physpath) == 0)
		vd->vdev_physpath = spa_strdup(vd->vdev_physpath);
	if (nvlist_lookup_string(nv, ZPOOL_CONFIG_FRU, &vd->vdev_fru) == 0)
		vd->vdev_fru = spa_strdup(vd->vdev_fru);

	/*
	 * Set the whole_disk property.  If it's not specified, leave the value
	 * as -1.
	 */
	if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_WHOLE_DISK,
	    &vd->vdev_wholedisk) != 0)
		vd->vdev_wholedisk = -1ULL;

	ASSERT0(vic->vic_mapping_object);
	(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_INDIRECT_OBJECT,
	    &vic->vic_mapping_object);
	ASSERT0(vic->vic_births_object);
	(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_INDIRECT_BIRTHS,
	    &vic->vic_births_object);
	ASSERT3U(vic->vic_prev_indirect_vdev, ==, UINT64_MAX);
	(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_PREV_INDIRECT_VDEV,
	    &vic->vic_prev_indirect_vdev);

	/*
	 * Look for the 'not present' flag.  This will only be set if the device
	 * was not present at the time of import.
	 */
	(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_NOT_PRESENT,
	    &vd->vdev_not_present);

	/*
	 * Get the alignment requirement.
	 */
	(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_ASHIFT, &vd->vdev_ashift);

	/*
	 * Retrieve the vdev creation time.
	 */
	(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_CREATE_TXG,
	    &vd->vdev_crtxg);

	/*
	 * If we're a top-level vdev, try to load the allocation parameters.
	 */
	if (top_level &&
	    (alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_SPLIT)) {
		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_METASLAB_ARRAY,
		    &vd->vdev_ms_array);
		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_METASLAB_SHIFT,
		    &vd->vdev_ms_shift);
		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_ASIZE,
		    &vd->vdev_asize);
		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_REMOVING,
		    &vd->vdev_removing);
		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_VDEV_TOP_ZAP,
		    &vd->vdev_top_zap);
	} else {
		ASSERT0(vd->vdev_top_zap);
	}

	if (top_level && alloctype != VDEV_ALLOC_ATTACH) {
		ASSERT(alloctype == VDEV_ALLOC_LOAD ||
		    alloctype == VDEV_ALLOC_ADD ||
		    alloctype == VDEV_ALLOC_SPLIT ||
		    alloctype == VDEV_ALLOC_ROOTPOOL);
		/* Note: metaslab_group_create() is now deferred */
	}

	if (vd->vdev_ops->vdev_op_leaf &&
	    (alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_SPLIT)) {
		(void) nvlist_lookup_uint64(nv,
		    ZPOOL_CONFIG_VDEV_LEAF_ZAP, &vd->vdev_leaf_zap);
	} else {
		ASSERT0(vd->vdev_leaf_zap);
	}

	/*
	 * If we're a leaf vdev, try to load the DTL object and other state.
	 */

	if (vd->vdev_ops->vdev_op_leaf &&
	    (alloctype == VDEV_ALLOC_LOAD || alloctype == VDEV_ALLOC_L2CACHE ||
	    alloctype == VDEV_ALLOC_ROOTPOOL)) {
		if (alloctype == VDEV_ALLOC_LOAD) {
			(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_DTL,
			    &vd->vdev_dtl_object);
			(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_UNSPARE,
			    &vd->vdev_unspare);
		}

		if (alloctype == VDEV_ALLOC_ROOTPOOL) {
			uint64_t spare = 0;

			if (nvlist_lookup_uint64(nv, ZPOOL_CONFIG_IS_SPARE,
			    &spare) == 0 && spare)
				spa_spare_add(vd);
		}

		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_OFFLINE,
		    &vd->vdev_offline);

		(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_RESILVER_TXG,
		    &vd->vdev_resilver_txg);

		/*
		 * When importing a pool, we want to ignore the persistent fault
		 * state, as the diagnosis made on another system may not be
		 * valid in the current context.  Local vdevs will
		 * remain in the faulted state.
		 */
		if (spa_load_state(spa) == SPA_LOAD_OPEN) {
			(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_FAULTED,
			    &vd->vdev_faulted);
			(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_DEGRADED,
			    &vd->vdev_degraded);
			(void) nvlist_lookup_uint64(nv, ZPOOL_CONFIG_REMOVED,
			    &vd->vdev_removed);

			if (vd->vdev_faulted || vd->vdev_degraded) {
				char *aux;

				vd->vdev_label_aux =
				    VDEV_AUX_ERR_EXCEEDED;
				if (nvlist_lookup_string(nv,
				    ZPOOL_CONFIG_AUX_STATE, &aux) == 0 &&
				    strcmp(aux, "external") == 0)
					vd->vdev_label_aux = VDEV_AUX_EXTERNAL;
			}
		}
	}

	/*
	 * Add ourselves to the parent's list of children.
	 */
	vdev_add_child(parent, vd);

	*vdp = vd;

	return (0);
}

void
vdev_free(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	ASSERT3P(vd->vdev_initialize_thread, ==, NULL);

	/*
	 * Scan queues are normally destroyed at the end of a scan. If the
	 * queue exists here, that implies the vdev is being removed while
	 * the scan is still running.
	 */
	if (vd->vdev_scan_io_queue != NULL) {
		mutex_enter(&vd->vdev_scan_io_queue_lock);
		dsl_scan_io_queue_destroy(vd->vdev_scan_io_queue);
		vd->vdev_scan_io_queue = NULL;
		mutex_exit(&vd->vdev_scan_io_queue_lock);
	}

	/*
	 * vdev_free() implies closing the vdev first.  This is simpler than
	 * trying to ensure complicated semantics for all callers.
	 */
	vdev_close(vd);

	ASSERT(!list_link_active(&vd->vdev_config_dirty_node));
	ASSERT(!list_link_active(&vd->vdev_state_dirty_node));

	/*
	 * Free all children.
	 */
	for (int c = 0; c < vd->vdev_children; c++)
		vdev_free(vd->vdev_child[c]);

	ASSERT(vd->vdev_child == NULL);
	ASSERT(vd->vdev_guid_sum == vd->vdev_guid);
	ASSERT(vd->vdev_initialize_thread == NULL);

	/*
	 * Discard allocation state.
	 */
	if (vd->vdev_mg != NULL) {
		vdev_metaslab_fini(vd);
		metaslab_group_destroy(vd->vdev_mg);
	}

	ASSERT0(vd->vdev_stat.vs_space);
	ASSERT0(vd->vdev_stat.vs_dspace);
	ASSERT0(vd->vdev_stat.vs_alloc);

	/*
	 * Remove this vdev from its parent's child list.
	 */
	vdev_remove_child(vd->vdev_parent, vd);

	ASSERT(vd->vdev_parent == NULL);
	ASSERT(!list_link_active(&vd->vdev_leaf_node));

	/*
	 * Clean up vdev structure.
	 */
	vdev_queue_fini(vd);
	vdev_cache_fini(vd);

	if (vd->vdev_path)
		spa_strfree(vd->vdev_path);
	if (vd->vdev_devid)
		spa_strfree(vd->vdev_devid);
	if (vd->vdev_physpath)
		spa_strfree(vd->vdev_physpath);
	if (vd->vdev_fru)
		spa_strfree(vd->vdev_fru);

	if (vd->vdev_isspare)
		spa_spare_remove(vd);
	if (vd->vdev_isl2cache)
		spa_l2cache_remove(vd);

	txg_list_destroy(&vd->vdev_ms_list);
	txg_list_destroy(&vd->vdev_dtl_list);

	mutex_enter(&vd->vdev_dtl_lock);
	space_map_close(vd->vdev_dtl_sm);
	for (int t = 0; t < DTL_TYPES; t++) {
		range_tree_vacate(vd->vdev_dtl[t], NULL, NULL);
		range_tree_destroy(vd->vdev_dtl[t]);
	}
	mutex_exit(&vd->vdev_dtl_lock);

	EQUIV(vd->vdev_indirect_births != NULL,
	    vd->vdev_indirect_mapping != NULL);
	if (vd->vdev_indirect_births != NULL) {
		vdev_indirect_mapping_close(vd->vdev_indirect_mapping);
		vdev_indirect_births_close(vd->vdev_indirect_births);
	}

	if (vd->vdev_obsolete_sm != NULL) {
		ASSERT(vd->vdev_removing ||
		    vd->vdev_ops == &vdev_indirect_ops);
		space_map_close(vd->vdev_obsolete_sm);
		vd->vdev_obsolete_sm = NULL;
	}
	range_tree_destroy(vd->vdev_obsolete_segments);
	rw_destroy(&vd->vdev_indirect_rwlock);
	mutex_destroy(&vd->vdev_obsolete_lock);

	mutex_destroy(&vd->vdev_dtl_lock);
	mutex_destroy(&vd->vdev_stat_lock);
	mutex_destroy(&vd->vdev_probe_lock);
	mutex_destroy(&vd->vdev_scan_io_queue_lock);
	mutex_destroy(&vd->vdev_initialize_lock);
	mutex_destroy(&vd->vdev_initialize_io_lock);
	cv_destroy(&vd->vdev_initialize_io_cv);
	cv_destroy(&vd->vdev_initialize_cv);

	if (vd == spa->spa_root_vdev)
		spa->spa_root_vdev = NULL;

	kmem_free(vd, sizeof (vdev_t));
}

/*
 * Transfer top-level vdev state from svd to tvd.
 */
static void
vdev_top_transfer(vdev_t *svd, vdev_t *tvd)
{
	spa_t *spa = svd->vdev_spa;
	metaslab_t *msp;
	vdev_t *vd;
	int t;

	ASSERT(tvd == tvd->vdev_top);

	tvd->vdev_ms_array = svd->vdev_ms_array;
	tvd->vdev_ms_shift = svd->vdev_ms_shift;
	tvd->vdev_ms_count = svd->vdev_ms_count;
	tvd->vdev_top_zap = svd->vdev_top_zap;

	svd->vdev_ms_array = 0;
	svd->vdev_ms_shift = 0;
	svd->vdev_ms_count = 0;
	svd->vdev_top_zap = 0;

	if (tvd->vdev_mg)
		ASSERT3P(tvd->vdev_mg, ==, svd->vdev_mg);
	tvd->vdev_mg = svd->vdev_mg;
	tvd->vdev_ms = svd->vdev_ms;

	svd->vdev_mg = NULL;
	svd->vdev_ms = NULL;

	if (tvd->vdev_mg != NULL)
		tvd->vdev_mg->mg_vd = tvd;

	tvd->vdev_checkpoint_sm = svd->vdev_checkpoint_sm;
	svd->vdev_checkpoint_sm = NULL;

	tvd->vdev_alloc_bias = svd->vdev_alloc_bias;
	svd->vdev_alloc_bias = VDEV_BIAS_NONE;

	tvd->vdev_stat.vs_alloc = svd->vdev_stat.vs_alloc;
	tvd->vdev_stat.vs_space = svd->vdev_stat.vs_space;
	tvd->vdev_stat.vs_dspace = svd->vdev_stat.vs_dspace;

	svd->vdev_stat.vs_alloc = 0;
	svd->vdev_stat.vs_space = 0;
	svd->vdev_stat.vs_dspace = 0;

	/*
	 * State which may be set on a top-level vdev that's in the
	 * process of being removed.
	 */
	ASSERT0(tvd->vdev_indirect_config.vic_births_object);
	ASSERT0(tvd->vdev_indirect_config.vic_mapping_object);
	ASSERT3U(tvd->vdev_indirect_config.vic_prev_indirect_vdev, ==, -1ULL);
	ASSERT3P(tvd->vdev_indirect_mapping, ==, NULL);
	ASSERT3P(tvd->vdev_indirect_births, ==, NULL);
	ASSERT3P(tvd->vdev_obsolete_sm, ==, NULL);
	ASSERT0(tvd->vdev_removing);
	tvd->vdev_removing = svd->vdev_removing;
	tvd->vdev_indirect_config = svd->vdev_indirect_config;
	tvd->vdev_indirect_mapping = svd->vdev_indirect_mapping;
	tvd->vdev_indirect_births = svd->vdev_indirect_births;
	range_tree_swap(&svd->vdev_obsolete_segments,
	    &tvd->vdev_obsolete_segments);
	tvd->vdev_obsolete_sm = svd->vdev_obsolete_sm;
	svd->vdev_indirect_config.vic_mapping_object = 0;
	svd->vdev_indirect_config.vic_births_object = 0;
	svd->vdev_indirect_config.vic_prev_indirect_vdev = -1ULL;
	svd->vdev_indirect_mapping = NULL;
	svd->vdev_indirect_births = NULL;
	svd->vdev_obsolete_sm = NULL;
	svd->vdev_removing = 0;

	for (t = 0; t < TXG_SIZE; t++) {
		while ((msp = txg_list_remove(&svd->vdev_ms_list, t)) != NULL)
			(void) txg_list_add(&tvd->vdev_ms_list, msp, t);
		while ((vd = txg_list_remove(&svd->vdev_dtl_list, t)) != NULL)
			(void) txg_list_add(&tvd->vdev_dtl_list, vd, t);
		if (txg_list_remove_this(&spa->spa_vdev_txg_list, svd, t))
			(void) txg_list_add(&spa->spa_vdev_txg_list, tvd, t);
	}

	if (list_link_active(&svd->vdev_config_dirty_node)) {
		vdev_config_clean(svd);
		vdev_config_dirty(tvd);
	}

	if (list_link_active(&svd->vdev_state_dirty_node)) {
		vdev_state_clean(svd);
		vdev_state_dirty(tvd);
	}

	tvd->vdev_deflate_ratio = svd->vdev_deflate_ratio;
	svd->vdev_deflate_ratio = 0;

	tvd->vdev_islog = svd->vdev_islog;
	svd->vdev_islog = 0;

	dsl_scan_io_queue_vdev_xfer(svd, tvd);
}

static void
vdev_top_update(vdev_t *tvd, vdev_t *vd)
{
	if (vd == NULL)
		return;

	vd->vdev_top = tvd;

	for (int c = 0; c < vd->vdev_children; c++)
		vdev_top_update(tvd, vd->vdev_child[c]);
}

/*
 * Add a mirror/replacing vdev above an existing vdev.
 */
vdev_t *
vdev_add_parent(vdev_t *cvd, vdev_ops_t *ops)
{
	spa_t *spa = cvd->vdev_spa;
	vdev_t *pvd = cvd->vdev_parent;
	vdev_t *mvd;

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

	mvd = vdev_alloc_common(spa, cvd->vdev_id, 0, ops);

	mvd->vdev_asize = cvd->vdev_asize;
	mvd->vdev_min_asize = cvd->vdev_min_asize;
	mvd->vdev_max_asize = cvd->vdev_max_asize;
	mvd->vdev_psize = cvd->vdev_psize;
	mvd->vdev_ashift = cvd->vdev_ashift;
	mvd->vdev_logical_ashift = cvd->vdev_logical_ashift;
	mvd->vdev_physical_ashift = cvd->vdev_physical_ashift;
	mvd->vdev_state = cvd->vdev_state;
	mvd->vdev_crtxg = cvd->vdev_crtxg;

	vdev_remove_child(pvd, cvd);
	vdev_add_child(pvd, mvd);
	cvd->vdev_id = mvd->vdev_children;
	vdev_add_child(mvd, cvd);
	vdev_top_update(cvd->vdev_top, cvd->vdev_top);

	if (mvd == mvd->vdev_top)
		vdev_top_transfer(cvd, mvd);

	return (mvd);
}

/*
 * Remove a 1-way mirror/replacing vdev from the tree.
 */
void
vdev_remove_parent(vdev_t *cvd)
{
	vdev_t *mvd = cvd->vdev_parent;
	vdev_t *pvd = mvd->vdev_parent;

	ASSERT(spa_config_held(cvd->vdev_spa, SCL_ALL, RW_WRITER) == SCL_ALL);

	ASSERT(mvd->vdev_children == 1);
	ASSERT(mvd->vdev_ops == &vdev_mirror_ops ||
	    mvd->vdev_ops == &vdev_replacing_ops ||
	    mvd->vdev_ops == &vdev_spare_ops);
	cvd->vdev_ashift = mvd->vdev_ashift;
	cvd->vdev_logical_ashift = mvd->vdev_logical_ashift;
	cvd->vdev_physical_ashift = mvd->vdev_physical_ashift;

	vdev_remove_child(mvd, cvd);
	vdev_remove_child(pvd, mvd);

	/*
	 * If cvd will replace mvd as a top-level vdev, preserve mvd's guid.
	 * Otherwise, we could have detached an offline device, and when we
	 * go to import the pool we'll think we have two top-level vdevs,
	 * instead of a different version of the same top-level vdev.
	 */
	if (mvd->vdev_top == mvd) {
		uint64_t guid_delta = mvd->vdev_guid - cvd->vdev_guid;
		cvd->vdev_orig_guid = cvd->vdev_guid;
		cvd->vdev_guid += guid_delta;
		cvd->vdev_guid_sum += guid_delta;
	}
	cvd->vdev_id = mvd->vdev_id;
	vdev_add_child(pvd, cvd);
	vdev_top_update(cvd->vdev_top, cvd->vdev_top);

	if (cvd == cvd->vdev_top)
		vdev_top_transfer(mvd, cvd);

	ASSERT(mvd->vdev_children == 0);
	vdev_free(mvd);
}

static void
vdev_metaslab_group_create(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;

	/*
	 * metaslab_group_create was delayed until allocation bias was available
	 */
	if (vd->vdev_mg == NULL) {
		metaslab_class_t *mc;

		if (vd->vdev_islog && vd->vdev_alloc_bias == VDEV_BIAS_NONE)
			vd->vdev_alloc_bias = VDEV_BIAS_LOG;

		ASSERT3U(vd->vdev_islog, ==,
		    (vd->vdev_alloc_bias == VDEV_BIAS_LOG));

		switch (vd->vdev_alloc_bias) {
		case VDEV_BIAS_LOG:
			mc = spa_log_class(spa);
			break;
		case VDEV_BIAS_SPECIAL:
			mc = spa_special_class(spa);
			break;
		case VDEV_BIAS_DEDUP:
			mc = spa_dedup_class(spa);
			break;
		default:
			mc = spa_normal_class(spa);
		}

		vd->vdev_mg = metaslab_group_create(mc, vd,
		    spa->spa_alloc_count);

		/*
		 * The spa ashift values currently only reflect the
		 * general vdev classes. Class destination is late
		 * binding so ashift checking had to wait until now
		 */
		if (vd->vdev_top == vd && vd->vdev_ashift != 0 &&
		    mc == spa_normal_class(spa) && vd->vdev_aux == NULL) {
			if (vd->vdev_ashift > spa->spa_max_ashift)
				spa->spa_max_ashift = vd->vdev_ashift;
			if (vd->vdev_ashift < spa->spa_min_ashift)
				spa->spa_min_ashift = vd->vdev_ashift;
		}
	}
}

int
vdev_metaslab_init(vdev_t *vd, uint64_t txg)
{
	spa_t *spa = vd->vdev_spa;
	objset_t *mos = spa->spa_meta_objset;
	uint64_t m;
	uint64_t oldc = vd->vdev_ms_count;
	uint64_t newc = vd->vdev_asize >> vd->vdev_ms_shift;
	metaslab_t **mspp;
	int error;
	boolean_t expanding = (oldc != 0);

	ASSERT(txg == 0 || spa_config_held(spa, SCL_ALLOC, RW_WRITER));

	/*
	 * This vdev is not being allocated from yet or is a hole.
	 */
	if (vd->vdev_ms_shift == 0)
		return (0);

	ASSERT(!vd->vdev_ishole);

	ASSERT(oldc <= newc);

	mspp = kmem_zalloc(newc * sizeof (*mspp), KM_SLEEP);

	if (expanding) {
		bcopy(vd->vdev_ms, mspp, oldc * sizeof (*mspp));
		kmem_free(vd->vdev_ms, oldc * sizeof (*mspp));
	}

	vd->vdev_ms = mspp;
	vd->vdev_ms_count = newc;
	for (m = oldc; m < newc; m++) {
		uint64_t object = 0;

		/*
		 * vdev_ms_array may be 0 if we are creating the "fake"
		 * metaslabs for an indirect vdev for zdb's leak detection.
		 * See zdb_leak_init().
		 */
		if (txg == 0 && vd->vdev_ms_array != 0) {
			error = dmu_read(mos, vd->vdev_ms_array,
			    m * sizeof (uint64_t), sizeof (uint64_t), &object,
			    DMU_READ_PREFETCH);
			if (error != 0) {
				vdev_dbgmsg(vd, "unable to read the metaslab "
				    "array [error=%d]", error);
				return (error);
			}
		}

#ifndef _KERNEL
		/*
		 * To accomodate zdb_leak_init() fake indirect
		 * metaslabs, we allocate a metaslab group for
		 * indirect vdevs which normally don't have one.
		 */
		if (vd->vdev_mg == NULL) {
			ASSERT0(vdev_is_concrete(vd));
			vdev_metaslab_group_create(vd);
		}
#endif
		error = metaslab_init(vd->vdev_mg, m, object, txg,
		    &(vd->vdev_ms[m]));
		if (error != 0) {
			vdev_dbgmsg(vd, "metaslab_init failed [error=%d]",
			    error);
			return (error);
		}
	}

	if (txg == 0)
		spa_config_enter(spa, SCL_ALLOC, FTAG, RW_WRITER);

	/*
	 * If the vdev is being removed we don't activate
	 * the metaslabs since we want to ensure that no new
	 * allocations are performed on this device.
	 */
	if (!expanding && !vd->vdev_removing) {
		metaslab_group_activate(vd->vdev_mg);
	}

	if (txg == 0)
		spa_config_exit(spa, SCL_ALLOC, FTAG);

	return (0);
}

void
vdev_metaslab_fini(vdev_t *vd)
{
	if (vd->vdev_checkpoint_sm != NULL) {
		ASSERT(spa_feature_is_active(vd->vdev_spa,
		    SPA_FEATURE_POOL_CHECKPOINT));
		space_map_close(vd->vdev_checkpoint_sm);
		/*
		 * Even though we close the space map, we need to set its
		 * pointer to NULL. The reason is that vdev_metaslab_fini()
		 * may be called multiple times for certain operations
		 * (i.e. when destroying a pool) so we need to ensure that
		 * this clause never executes twice. This logic is similar
		 * to the one used for the vdev_ms clause below.
		 */
		vd->vdev_checkpoint_sm = NULL;
	}

	if (vd->vdev_ms != NULL) {
		metaslab_group_t *mg = vd->vdev_mg;
		metaslab_group_passivate(mg);

		uint64_t count = vd->vdev_ms_count;
		for (uint64_t m = 0; m < count; m++) {
			metaslab_t *msp = vd->vdev_ms[m];
			if (msp != NULL)
				metaslab_fini(msp);
		}
		kmem_free(vd->vdev_ms, count * sizeof (metaslab_t *));
		vd->vdev_ms = NULL;

		vd->vdev_ms_count = 0;

		for (int i = 0; i < RANGE_TREE_HISTOGRAM_SIZE; i++)
			ASSERT0(mg->mg_histogram[i]);
	}
	ASSERT0(vd->vdev_ms_count);
}

typedef struct vdev_probe_stats {
	boolean_t	vps_readable;
	boolean_t	vps_writeable;
	int		vps_flags;
} vdev_probe_stats_t;

static void
vdev_probe_done(zio_t *zio)
{
	spa_t *spa = zio->io_spa;
	vdev_t *vd = zio->io_vd;
	vdev_probe_stats_t *vps = zio->io_private;

	ASSERT(vd->vdev_probe_zio != NULL);

	if (zio->io_type == ZIO_TYPE_READ) {
		if (zio->io_error == 0)
			vps->vps_readable = 1;
		if (zio->io_error == 0 && spa_writeable(spa)) {
			zio_nowait(zio_write_phys(vd->vdev_probe_zio, vd,
			    zio->io_offset, zio->io_size, zio->io_abd,
			    ZIO_CHECKSUM_OFF, vdev_probe_done, vps,
			    ZIO_PRIORITY_SYNC_WRITE, vps->vps_flags, B_TRUE));
		} else {
			abd_free(zio->io_abd);
		}
	} else if (zio->io_type == ZIO_TYPE_WRITE) {
		if (zio->io_error == 0)
			vps->vps_writeable = 1;
		abd_free(zio->io_abd);
	} else if (zio->io_type == ZIO_TYPE_NULL) {
		zio_t *pio;

		vd->vdev_cant_read |= !vps->vps_readable;
		vd->vdev_cant_write |= !vps->vps_writeable;

		if (vdev_readable(vd) &&
		    (vdev_writeable(vd) || !spa_writeable(spa))) {
			zio->io_error = 0;
		} else {
			ASSERT(zio->io_error != 0);
			vdev_dbgmsg(vd, "failed probe");
			zfs_ereport_post(FM_EREPORT_ZFS_PROBE_FAILURE,
			    spa, vd, NULL, 0, 0);
			zio->io_error = SET_ERROR(ENXIO);
		}

		mutex_enter(&vd->vdev_probe_lock);
		ASSERT(vd->vdev_probe_zio == zio);
		vd->vdev_probe_zio = NULL;
		mutex_exit(&vd->vdev_probe_lock);

		zio_link_t *zl = NULL;
		while ((pio = zio_walk_parents(zio, &zl)) != NULL)
			if (!vdev_accessible(vd, pio))
				pio->io_error = SET_ERROR(ENXIO);

		kmem_free(vps, sizeof (*vps));
	}
}

/*
 * Determine whether this device is accessible.
 *
 * Read and write to several known locations: the pad regions of each
 * vdev label but the first, which we leave alone in case it contains
 * a VTOC.
 */
zio_t *
vdev_probe(vdev_t *vd, zio_t *zio)
{
	spa_t *spa = vd->vdev_spa;
	vdev_probe_stats_t *vps = NULL;
	zio_t *pio;

	ASSERT(vd->vdev_ops->vdev_op_leaf);

	/*
	 * Don't probe the probe.
	 */
	if (zio && (zio->io_flags & ZIO_FLAG_PROBE))
		return (NULL);

	/*
	 * To prevent 'probe storms' when a device fails, we create
	 * just one probe i/o at a time.  All zios that want to probe
	 * this vdev will become parents of the probe io.
	 */
	mutex_enter(&vd->vdev_probe_lock);

	if ((pio = vd->vdev_probe_zio) == NULL) {
		vps = kmem_zalloc(sizeof (*vps), KM_SLEEP);

		vps->vps_flags = ZIO_FLAG_CANFAIL | ZIO_FLAG_PROBE |
		    ZIO_FLAG_DONT_CACHE | ZIO_FLAG_DONT_AGGREGATE |
		    ZIO_FLAG_TRYHARD;

		if (spa_config_held(spa, SCL_ZIO, RW_WRITER)) {
			/*
			 * vdev_cant_read and vdev_cant_write can only
			 * transition from TRUE to FALSE when we have the
			 * SCL_ZIO lock as writer; otherwise they can only
			 * transition from FALSE to TRUE.  This ensures that
			 * any zio looking at these values can assume that
			 * failures persist for the life of the I/O.  That's
			 * important because when a device has intermittent
			 * connectivity problems, we want to ensure that
			 * they're ascribed to the device (ENXIO) and not
			 * the zio (EIO).
			 *
			 * Since we hold SCL_ZIO as writer here, clear both
			 * values so the probe can reevaluate from first
			 * principles.
			 */
			vps->vps_flags |= ZIO_FLAG_CONFIG_WRITER;
			vd->vdev_cant_read = B_FALSE;
			vd->vdev_cant_write = B_FALSE;
		}

		vd->vdev_probe_zio = pio = zio_null(NULL, spa, vd,
		    vdev_probe_done, vps,
		    vps->vps_flags | ZIO_FLAG_DONT_PROPAGATE);

		/*
		 * We can't change the vdev state in this context, so we
		 * kick off an async task to do it on our behalf.
		 */
		if (zio != NULL) {
			vd->vdev_probe_wanted = B_TRUE;
			spa_async_request(spa, SPA_ASYNC_PROBE);
		}
	}

	if (zio != NULL)
		zio_add_child(zio, pio);

	mutex_exit(&vd->vdev_probe_lock);

	if (vps == NULL) {
		ASSERT(zio != NULL);
		return (NULL);
	}

	for (int l = 1; l < VDEV_LABELS; l++) {
		zio_nowait(zio_read_phys(pio, vd,
		    vdev_label_offset(vd->vdev_psize, l,
		    offsetof(vdev_label_t, vl_be)), VDEV_PAD_SIZE,
		    abd_alloc_for_io(VDEV_PAD_SIZE, B_TRUE),
		    ZIO_CHECKSUM_OFF, vdev_probe_done, vps,
		    ZIO_PRIORITY_SYNC_READ, vps->vps_flags, B_TRUE));
	}

	if (zio == NULL)
		return (pio);

	zio_nowait(pio);
	return (NULL);
}

static void
vdev_open_child(void *arg)
{
	vdev_t *vd = arg;

	vd->vdev_open_thread = curthread;
	vd->vdev_open_error = vdev_open(vd);
	vd->vdev_open_thread = NULL;
}

boolean_t
vdev_uses_zvols(vdev_t *vd)
{
	if (vd->vdev_path && strncmp(vd->vdev_path, ZVOL_DIR,
	    strlen(ZVOL_DIR)) == 0)
		return (B_TRUE);
	for (int c = 0; c < vd->vdev_children; c++)
		if (vdev_uses_zvols(vd->vdev_child[c]))
			return (B_TRUE);
	return (B_FALSE);
}

void
vdev_open_children(vdev_t *vd)
{
	taskq_t *tq;
	int children = vd->vdev_children;

	vd->vdev_nonrot = B_TRUE;

	/*
	 * in order to handle pools on top of zvols, do the opens
	 * in a single thread so that the same thread holds the
	 * spa_namespace_lock
	 */
	if (B_TRUE || vdev_uses_zvols(vd)) {
		for (int c = 0; c < children; c++) {
			vd->vdev_child[c]->vdev_open_error =
			    vdev_open(vd->vdev_child[c]);
			vd->vdev_nonrot &= vd->vdev_child[c]->vdev_nonrot;
		}
		return;
	}
	tq = taskq_create("vdev_open", children, minclsyspri,
	    children, children, TASKQ_PREPOPULATE);

	for (int c = 0; c < children; c++)
		VERIFY(taskq_dispatch(tq, vdev_open_child, vd->vdev_child[c],
		    TQ_SLEEP) != 0);

	taskq_destroy(tq);

	for (int c = 0; c < children; c++)
		vd->vdev_nonrot &= vd->vdev_child[c]->vdev_nonrot;
}

/*
 * Compute the raidz-deflation ratio.  Note, we hard-code
 * in 128k (1 << 17) because it is the "typical" blocksize.
 * Even though SPA_MAXBLOCKSIZE changed, this algorithm can not change,
 * otherwise it would inconsistently account for existing bp's.
 */
static void
vdev_set_deflate_ratio(vdev_t *vd)
{
	if (vd == vd->vdev_top && !vd->vdev_ishole && vd->vdev_ashift != 0) {
		vd->vdev_deflate_ratio = (1 << 17) /
		    (vdev_psize_to_asize(vd, 1 << 17) >> SPA_MINBLOCKSHIFT);
	}
}

/*
 * Prepare a virtual device for access.
 */
int
vdev_open(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	int error;
	uint64_t osize = 0;
	uint64_t max_osize = 0;
	uint64_t asize, max_asize, psize;
	uint64_t logical_ashift = 0;
	uint64_t physical_ashift = 0;

	ASSERT(vd->vdev_open_thread == curthread ||
	    spa_config_held(spa, SCL_STATE_ALL, RW_WRITER) == SCL_STATE_ALL);
	ASSERT(vd->vdev_state == VDEV_STATE_CLOSED ||
	    vd->vdev_state == VDEV_STATE_CANT_OPEN ||
	    vd->vdev_state == VDEV_STATE_OFFLINE);

	vd->vdev_stat.vs_aux = VDEV_AUX_NONE;
	vd->vdev_cant_read = B_FALSE;
	vd->vdev_cant_write = B_FALSE;
	vd->vdev_notrim = B_FALSE;
	vd->vdev_min_asize = vdev_get_min_asize(vd);

	/*
	 * If this vdev is not removed, check its fault status.  If it's
	 * faulted, bail out of the open.
	 */
	if (!vd->vdev_removed && vd->vdev_faulted) {
		ASSERT(vd->vdev_children == 0);
		ASSERT(vd->vdev_label_aux == VDEV_AUX_ERR_EXCEEDED ||
		    vd->vdev_label_aux == VDEV_AUX_EXTERNAL);
		vdev_set_state(vd, B_TRUE, VDEV_STATE_FAULTED,
		    vd->vdev_label_aux);
		return (SET_ERROR(ENXIO));
	} else if (vd->vdev_offline) {
		ASSERT(vd->vdev_children == 0);
		vdev_set_state(vd, B_TRUE, VDEV_STATE_OFFLINE, VDEV_AUX_NONE);
		return (SET_ERROR(ENXIO));
	}

	error = vd->vdev_ops->vdev_op_open(vd, &osize, &max_osize,
	    &logical_ashift, &physical_ashift);

	/*
	 * Reset the vdev_reopening flag so that we actually close
	 * the vdev on error.
	 */
	vd->vdev_reopening = B_FALSE;
	if (zio_injection_enabled && error == 0)
		error = zio_handle_device_injection(vd, NULL, ENXIO);

	if (error) {
		if (vd->vdev_removed &&
		    vd->vdev_stat.vs_aux != VDEV_AUX_OPEN_FAILED)
			vd->vdev_removed = B_FALSE;

		if (vd->vdev_stat.vs_aux == VDEV_AUX_CHILDREN_OFFLINE) {
			vdev_set_state(vd, B_TRUE, VDEV_STATE_OFFLINE,
			    vd->vdev_stat.vs_aux);
		} else {
			vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
			    vd->vdev_stat.vs_aux);
		}
		return (error);
	}

	vd->vdev_removed = B_FALSE;

	/*
	 * Recheck the faulted flag now that we have confirmed that
	 * the vdev is accessible.  If we're faulted, bail.
	 */
	if (vd->vdev_faulted) {
		ASSERT(vd->vdev_children == 0);
		ASSERT(vd->vdev_label_aux == VDEV_AUX_ERR_EXCEEDED ||
		    vd->vdev_label_aux == VDEV_AUX_EXTERNAL);
		vdev_set_state(vd, B_TRUE, VDEV_STATE_FAULTED,
		    vd->vdev_label_aux);
		return (SET_ERROR(ENXIO));
	}

	if (vd->vdev_degraded) {
		ASSERT(vd->vdev_children == 0);
		vdev_set_state(vd, B_TRUE, VDEV_STATE_DEGRADED,
		    VDEV_AUX_ERR_EXCEEDED);
	} else {
		vdev_set_state(vd, B_TRUE, VDEV_STATE_HEALTHY, 0);
	}

	/*
	 * For hole or missing vdevs we just return success.
	 */
	if (vd->vdev_ishole || vd->vdev_ops == &vdev_missing_ops)
		return (0);

	if (zfs_trim_enabled && !vd->vdev_notrim && vd->vdev_ops->vdev_op_leaf)
		trim_map_create(vd);

	for (int c = 0; c < vd->vdev_children; c++) {
		if (vd->vdev_child[c]->vdev_state != VDEV_STATE_HEALTHY) {
			vdev_set_state(vd, B_TRUE, VDEV_STATE_DEGRADED,
			    VDEV_AUX_NONE);
			break;
		}
	}

	osize = P2ALIGN(osize, (uint64_t)sizeof (vdev_label_t));
	max_osize = P2ALIGN(max_osize, (uint64_t)sizeof (vdev_label_t));

	if (vd->vdev_children == 0) {
		if (osize < SPA_MINDEVSIZE) {
			vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_TOO_SMALL);
			return (SET_ERROR(EOVERFLOW));
		}
		psize = osize;
		asize = osize - (VDEV_LABEL_START_SIZE + VDEV_LABEL_END_SIZE);
		max_asize = max_osize - (VDEV_LABEL_START_SIZE +
		    VDEV_LABEL_END_SIZE);
	} else {
		if (vd->vdev_parent != NULL && osize < SPA_MINDEVSIZE -
		    (VDEV_LABEL_START_SIZE + VDEV_LABEL_END_SIZE)) {
			vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_TOO_SMALL);
			return (SET_ERROR(EOVERFLOW));
		}
		psize = 0;
		asize = osize;
		max_asize = max_osize;
	}

	vd->vdev_psize = psize;

	/*
	 * Make sure the allocatable size hasn't shrunk too much.
	 */
	if (asize < vd->vdev_min_asize) {
		vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_BAD_LABEL);
		return (SET_ERROR(EINVAL));
	}

	vd->vdev_physical_ashift =
	    MAX(physical_ashift, vd->vdev_physical_ashift);
	vd->vdev_logical_ashift = MAX(logical_ashift, vd->vdev_logical_ashift);
	vd->vdev_ashift = MAX(vd->vdev_logical_ashift, vd->vdev_ashift);

	if (vd->vdev_logical_ashift > SPA_MAXASHIFT) {
		vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_ASHIFT_TOO_BIG);
		return (EINVAL);
	}

	if (vd->vdev_asize == 0) {
		/*
		 * This is the first-ever open, so use the computed values.
		 * For testing purposes, a higher ashift can be requested.
		 */
		vd->vdev_asize = asize;
		vd->vdev_max_asize = max_asize;
	} else {
		/*
		 * Make sure the alignment requirement hasn't increased.
		 */
		if (vd->vdev_ashift > vd->vdev_top->vdev_ashift &&
		    vd->vdev_ops->vdev_op_leaf) {
			vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_BAD_LABEL);
			return (EINVAL);
		}
		vd->vdev_max_asize = max_asize;
	}

	/*
	 * If all children are healthy we update asize if either:
	 * The asize has increased, due to a device expansion caused by dynamic
	 * LUN growth or vdev replacement, and automatic expansion is enabled;
	 * making the additional space available.
	 *
	 * The asize has decreased, due to a device shrink usually caused by a
	 * vdev replace with a smaller device. This ensures that calculations
	 * based of max_asize and asize e.g. esize are always valid. It's safe
	 * to do this as we've already validated that asize is greater than
	 * vdev_min_asize.
	 */
	if (vd->vdev_state == VDEV_STATE_HEALTHY &&
	    ((asize > vd->vdev_asize &&
	    (vd->vdev_expanding || spa->spa_autoexpand)) ||
	    (asize < vd->vdev_asize)))
		vd->vdev_asize = asize;

	vdev_set_min_asize(vd);

	/*
	 * Ensure we can issue some IO before declaring the
	 * vdev open for business.
	 */
	if (vd->vdev_ops->vdev_op_leaf &&
	    (error = zio_wait(vdev_probe(vd, NULL))) != 0) {
		vdev_set_state(vd, B_TRUE, VDEV_STATE_FAULTED,
		    VDEV_AUX_ERR_EXCEEDED);
		return (error);
	}

	/*
	 * Track the min and max ashift values for normal data devices.
	 *
	 * DJB - TBD these should perhaps be tracked per allocation class
	 * (e.g. spa_min_ashift is used to round up post compression buffers)
	 */
	if (vd->vdev_top == vd && vd->vdev_ashift != 0 &&
	    vd->vdev_alloc_bias == VDEV_BIAS_NONE &&
	    vd->vdev_aux == NULL) {
		if (vd->vdev_ashift > spa->spa_max_ashift)
			spa->spa_max_ashift = vd->vdev_ashift;
		if (vd->vdev_ashift < spa->spa_min_ashift)
			spa->spa_min_ashift = vd->vdev_ashift;
	}

	/*
	 * If a leaf vdev has a DTL, and seems healthy, then kick off a
	 * resilver.  But don't do this if we are doing a reopen for a scrub,
	 * since this would just restart the scrub we are already doing.
	 */
	if (vd->vdev_ops->vdev_op_leaf && !spa->spa_scrub_reopen &&
	    vdev_resilver_needed(vd, NULL, NULL))
		spa_async_request(spa, SPA_ASYNC_RESILVER);

	return (0);
}

/*
 * Called once the vdevs are all opened, this routine validates the label
 * contents. This needs to be done before vdev_load() so that we don't
 * inadvertently do repair I/Os to the wrong device.
 *
 * This function will only return failure if one of the vdevs indicates that it
 * has since been destroyed or exported.  This is only possible if
 * /etc/zfs/zpool.cache was readonly at the time.  Otherwise, the vdev state
 * will be updated but the function will return 0.
 */
int
vdev_validate(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	nvlist_t *label;
	uint64_t guid = 0, aux_guid = 0, top_guid;
	uint64_t state;
	nvlist_t *nvl;
	uint64_t txg;

	if (vdev_validate_skip)
		return (0);

	for (uint64_t c = 0; c < vd->vdev_children; c++)
		if (vdev_validate(vd->vdev_child[c]) != 0)
			return (SET_ERROR(EBADF));

	/*
	 * If the device has already failed, or was marked offline, don't do
	 * any further validation.  Otherwise, label I/O will fail and we will
	 * overwrite the previous state.
	 */
	if (!vd->vdev_ops->vdev_op_leaf || !vdev_readable(vd))
		return (0);

	/*
	 * If we are performing an extreme rewind, we allow for a label that
	 * was modified at a point after the current txg.
	 * If config lock is not held do not check for the txg. spa_sync could
	 * be updating the vdev's label before updating spa_last_synced_txg.
	 */
	if (spa->spa_extreme_rewind || spa_last_synced_txg(spa) == 0 ||
	    spa_config_held(spa, SCL_CONFIG, RW_WRITER) != SCL_CONFIG)
		txg = UINT64_MAX;
	else
		txg = spa_last_synced_txg(spa);

	if ((label = vdev_label_read_config(vd, txg)) == NULL) {
		vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_BAD_LABEL);
		vdev_dbgmsg(vd, "vdev_validate: failed reading config for "
		    "txg %llu", (u_longlong_t)txg);
		return (0);
	}

	/*
	 * Determine if this vdev has been split off into another
	 * pool.  If so, then refuse to open it.
	 */
	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_SPLIT_GUID,
	    &aux_guid) == 0 && aux_guid == spa_guid(spa)) {
		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_SPLIT_POOL);
		nvlist_free(label);
		vdev_dbgmsg(vd, "vdev_validate: vdev split into other pool");
		return (0);
	}

	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_GUID, &guid) != 0) {
		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		nvlist_free(label);
		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
		    ZPOOL_CONFIG_POOL_GUID);
		return (0);
	}

	/*
	 * If config is not trusted then ignore the spa guid check. This is
	 * necessary because if the machine crashed during a re-guid the new
	 * guid might have been written to all of the vdev labels, but not the
	 * cached config. The check will be performed again once we have the
	 * trusted config from the MOS.
	 */
	if (spa->spa_trust_config && guid != spa_guid(spa)) {
		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		nvlist_free(label);
		vdev_dbgmsg(vd, "vdev_validate: vdev label pool_guid doesn't "
		    "match config (%llu != %llu)", (u_longlong_t)guid,
		    (u_longlong_t)spa_guid(spa));
		return (0);
	}

	if (nvlist_lookup_nvlist(label, ZPOOL_CONFIG_VDEV_TREE, &nvl)
	    != 0 || nvlist_lookup_uint64(nvl, ZPOOL_CONFIG_ORIG_GUID,
	    &aux_guid) != 0)
		aux_guid = 0;

	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_GUID, &guid) != 0) {
		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		nvlist_free(label);
		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
		    ZPOOL_CONFIG_GUID);
		return (0);
	}

	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_TOP_GUID, &top_guid)
	    != 0) {
		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		nvlist_free(label);
		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
		    ZPOOL_CONFIG_TOP_GUID);
		return (0);
	}

	/*
	 * If this vdev just became a top-level vdev because its sibling was
	 * detached, it will have adopted the parent's vdev guid -- but the
	 * label may or may not be on disk yet. Fortunately, either version
	 * of the label will have the same top guid, so if we're a top-level
	 * vdev, we can safely compare to that instead.
	 * However, if the config comes from a cachefile that failed to update
	 * after the detach, a top-level vdev will appear as a non top-level
	 * vdev in the config. Also relax the constraints if we perform an
	 * extreme rewind.
	 *
	 * If we split this vdev off instead, then we also check the
	 * original pool's guid. We don't want to consider the vdev
	 * corrupt if it is partway through a split operation.
	 */
	if (vd->vdev_guid != guid && vd->vdev_guid != aux_guid) {
		boolean_t mismatch = B_FALSE;
		if (spa->spa_trust_config && !spa->spa_extreme_rewind) {
			if (vd != vd->vdev_top || vd->vdev_guid != top_guid)
				mismatch = B_TRUE;
		} else {
			if (vd->vdev_guid != top_guid &&
			    vd->vdev_top->vdev_guid != guid)
				mismatch = B_TRUE;
		}

		if (mismatch) {
			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_CORRUPT_DATA);
			nvlist_free(label);
			vdev_dbgmsg(vd, "vdev_validate: config guid "
			    "doesn't match label guid");
			vdev_dbgmsg(vd, "CONFIG: guid %llu, top_guid %llu",
			    (u_longlong_t)vd->vdev_guid,
			    (u_longlong_t)vd->vdev_top->vdev_guid);
			vdev_dbgmsg(vd, "LABEL: guid %llu, top_guid %llu, "
			    "aux_guid %llu", (u_longlong_t)guid,
			    (u_longlong_t)top_guid, (u_longlong_t)aux_guid);
			return (0);
		}
	}

	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_STATE,
	    &state) != 0) {
		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		nvlist_free(label);
		vdev_dbgmsg(vd, "vdev_validate: '%s' missing from label",
		    ZPOOL_CONFIG_POOL_STATE);
		return (0);
	}

	nvlist_free(label);

	/*
	 * If this is a verbatim import, no need to check the
	 * state of the pool.
	 */
	if (!(spa->spa_import_flags & ZFS_IMPORT_VERBATIM) &&
	    spa_load_state(spa) == SPA_LOAD_OPEN &&
	    state != POOL_STATE_ACTIVE) {
		vdev_dbgmsg(vd, "vdev_validate: invalid pool state (%llu) "
		    "for spa %s", (u_longlong_t)state, spa->spa_name);
		return (SET_ERROR(EBADF));
	}

	/*
	 * If we were able to open and validate a vdev that was
	 * previously marked permanently unavailable, clear that state
	 * now.
	 */
	if (vd->vdev_not_present)
		vd->vdev_not_present = 0;

	return (0);
}

static void
vdev_copy_path_impl(vdev_t *svd, vdev_t *dvd)
{
	if (svd->vdev_path != NULL && dvd->vdev_path != NULL) {
		if (strcmp(svd->vdev_path, dvd->vdev_path) != 0) {
			zfs_dbgmsg("vdev_copy_path: vdev %llu: path changed "
			    "from '%s' to '%s'", (u_longlong_t)dvd->vdev_guid,
			    dvd->vdev_path, svd->vdev_path);
			spa_strfree(dvd->vdev_path);
			dvd->vdev_path = spa_strdup(svd->vdev_path);
		}
	} else if (svd->vdev_path != NULL) {
		dvd->vdev_path = spa_strdup(svd->vdev_path);
		zfs_dbgmsg("vdev_copy_path: vdev %llu: path set to '%s'",
		    (u_longlong_t)dvd->vdev_guid, dvd->vdev_path);
	}
}

/*
 * Recursively copy vdev paths from one vdev to another. Source and destination
 * vdev trees must have same geometry otherwise return error. Intended to copy
 * paths from userland config into MOS config.
 */
int
vdev_copy_path_strict(vdev_t *svd, vdev_t *dvd)
{
	if ((svd->vdev_ops == &vdev_missing_ops) ||
	    (svd->vdev_ishole && dvd->vdev_ishole) ||
	    (dvd->vdev_ops == &vdev_indirect_ops))
		return (0);

	if (svd->vdev_ops != dvd->vdev_ops) {
		vdev_dbgmsg(svd, "vdev_copy_path: vdev type mismatch: %s != %s",
		    svd->vdev_ops->vdev_op_type, dvd->vdev_ops->vdev_op_type);
		return (SET_ERROR(EINVAL));
	}

	if (svd->vdev_guid != dvd->vdev_guid) {
		vdev_dbgmsg(svd, "vdev_copy_path: guids mismatch (%llu != "
		    "%llu)", (u_longlong_t)svd->vdev_guid,
		    (u_longlong_t)dvd->vdev_guid);
		return (SET_ERROR(EINVAL));
	}

	if (svd->vdev_children != dvd->vdev_children) {
		vdev_dbgmsg(svd, "vdev_copy_path: children count mismatch: "
		    "%llu != %llu", (u_longlong_t)svd->vdev_children,
		    (u_longlong_t)dvd->vdev_children);
		return (SET_ERROR(EINVAL));
	}

	for (uint64_t i = 0; i < svd->vdev_children; i++) {
		int error = vdev_copy_path_strict(svd->vdev_child[i],
		    dvd->vdev_child[i]);
		if (error != 0)
			return (error);
	}

	if (svd->vdev_ops->vdev_op_leaf)
		vdev_copy_path_impl(svd, dvd);

	return (0);
}

static void
vdev_copy_path_search(vdev_t *stvd, vdev_t *dvd)
{
	ASSERT(stvd->vdev_top == stvd);
	ASSERT3U(stvd->vdev_id, ==, dvd->vdev_top->vdev_id);

	for (uint64_t i = 0; i < dvd->vdev_children; i++) {
		vdev_copy_path_search(stvd, dvd->vdev_child[i]);
	}

	if (!dvd->vdev_ops->vdev_op_leaf || !vdev_is_concrete(dvd))
		return;

	/*
	 * The idea here is that while a vdev can shift positions within
	 * a top vdev (when replacing, attaching mirror, etc.) it cannot
	 * step outside of it.
	 */
	vdev_t *vd = vdev_lookup_by_guid(stvd, dvd->vdev_guid);

	if (vd == NULL || vd->vdev_ops != dvd->vdev_ops)
		return;

	ASSERT(vd->vdev_ops->vdev_op_leaf);

	vdev_copy_path_impl(vd, dvd);
}

/*
 * Recursively copy vdev paths from one root vdev to another. Source and
 * destination vdev trees may differ in geometry. For each destination leaf
 * vdev, search a vdev with the same guid and top vdev id in the source.
 * Intended to copy paths from userland config into MOS config.
 */
void
vdev_copy_path_relaxed(vdev_t *srvd, vdev_t *drvd)
{
	uint64_t children = MIN(srvd->vdev_children, drvd->vdev_children);
	ASSERT(srvd->vdev_ops == &vdev_root_ops);
	ASSERT(drvd->vdev_ops == &vdev_root_ops);

	for (uint64_t i = 0; i < children; i++) {
		vdev_copy_path_search(srvd->vdev_child[i],
		    drvd->vdev_child[i]);
	}
}

/*
 * Close a virtual device.
 */
void
vdev_close(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	vdev_t *pvd = vd->vdev_parent;

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

	/*
	 * If our parent is reopening, then we are as well, unless we are
	 * going offline.
	 */
	if (pvd != NULL && pvd->vdev_reopening)
		vd->vdev_reopening = (pvd->vdev_reopening && !vd->vdev_offline);

	vd->vdev_ops->vdev_op_close(vd);

	vdev_cache_purge(vd);

	if (vd->vdev_ops->vdev_op_leaf)
		trim_map_destroy(vd);

	/*
	 * We record the previous state before we close it, so that if we are
	 * doing a reopen(), we don't generate FMA ereports if we notice that
	 * it's still faulted.
	 */
	vd->vdev_prevstate = vd->vdev_state;

	if (vd->vdev_offline)
		vd->vdev_state = VDEV_STATE_OFFLINE;
	else
		vd->vdev_state = VDEV_STATE_CLOSED;
	vd->vdev_stat.vs_aux = VDEV_AUX_NONE;
}

void
vdev_hold(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;

	ASSERT(spa_is_root(spa));
	if (spa->spa_state == POOL_STATE_UNINITIALIZED)
		return;

	for (int c = 0; c < vd->vdev_children; c++)
		vdev_hold(vd->vdev_child[c]);

	if (vd->vdev_ops->vdev_op_leaf)
		vd->vdev_ops->vdev_op_hold(vd);
}

void
vdev_rele(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;

	ASSERT(spa_is_root(spa));
	for (int c = 0; c < vd->vdev_children; c++)
		vdev_rele(vd->vdev_child[c]);

	if (vd->vdev_ops->vdev_op_leaf)
		vd->vdev_ops->vdev_op_rele(vd);
}

/*
 * Reopen all interior vdevs and any unopened leaves.  We don't actually
 * reopen leaf vdevs which had previously been opened as they might deadlock
 * on the spa_config_lock.  Instead we only obtain the leaf's physical size.
 * If the leaf has never been opened then open it, as usual.
 */
void
vdev_reopen(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;

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

	/* set the reopening flag unless we're taking the vdev offline */
	vd->vdev_reopening = !vd->vdev_offline;
	vdev_close(vd);
	(void) vdev_open(vd);

	/*
	 * Call vdev_validate() here to make sure we have the same device.
	 * Otherwise, a device with an invalid label could be successfully
	 * opened in response to vdev_reopen().
	 */
	if (vd->vdev_aux) {
		(void) vdev_validate_aux(vd);
		if (vdev_readable(vd) && vdev_writeable(vd) &&
		    vd->vdev_aux == &spa->spa_l2cache &&
		    !l2arc_vdev_present(vd))
			l2arc_add_vdev(spa, vd);
	} else {
		(void) vdev_validate(vd);
	}

	/*
	 * Reassess parent vdev's health.
	 */
	vdev_propagate_state(vd);
}

int
vdev_create(vdev_t *vd, uint64_t txg, boolean_t isreplacing)
{
	int error;

	/*
	 * Normally, partial opens (e.g. of a mirror) are allowed.
	 * For a create, however, we want to fail the request if
	 * there are any components we can't open.
	 */
	error = vdev_open(vd);

	if (error || vd->vdev_state != VDEV_STATE_HEALTHY) {
		vdev_close(vd);
		return (error ? error : ENXIO);
	}

	/*
	 * Recursively load DTLs and initialize all labels.
	 */
	if ((error = vdev_dtl_load(vd)) != 0 ||
	    (error = vdev_label_init(vd, txg, isreplacing ?
	    VDEV_LABEL_REPLACE : VDEV_LABEL_CREATE)) != 0) {
		vdev_close(vd);
		return (error);
	}

	return (0);
}

void
vdev_metaslab_set_size(vdev_t *vd)
{
	uint64_t asize = vd->vdev_asize;
	uint64_t ms_count = asize >> zfs_vdev_default_ms_shift;
	uint64_t ms_shift;

	/*
	 * There are two dimensions to the metaslab sizing calculation:
	 * the size of the metaslab and the count of metaslabs per vdev.
	 *
	 * The default values used below are a good balance between memory
	 * usage (larger metaslab size means more memory needed for loaded
	 * metaslabs; more metaslabs means more memory needed for the
	 * metaslab_t structs), metaslab load time (larger metaslabs take
	 * longer to load), and metaslab sync time (more metaslabs means
	 * more time spent syncing all of them).
	 *
	 * In general, we aim for zfs_vdev_default_ms_count (200) metaslabs.
	 * The range of the dimensions are as follows:
	 *
	 *	2^29 <= ms_size  <= 2^34
	 *	  16 <= ms_count <= 131,072
	 *
	 * On the lower end of vdev sizes, we aim for metaslabs sizes of
	 * at least 512MB (2^29) to minimize fragmentation effects when
	 * testing with smaller devices.  However, the count constraint
	 * of at least 16 metaslabs will override this minimum size goal.
	 *
	 * On the upper end of vdev sizes, we aim for a maximum metaslab
	 * size of 16GB.  However, we will cap the total count to 2^17
	 * metaslabs to keep our memory footprint in check and let the
	 * metaslab size grow from there if that limit is hit.
	 *
	 * The net effect of applying above constrains is summarized below.
	 *
	 *   vdev size	    metaslab count
	 *  --------------|-----------------
	 *	< 8GB		~16
	 *  8GB   - 100GB	one per 512MB
	 *  100GB - 3TB		~200
	 *  3TB   - 2PB		one per 16GB
	 *	> 2PB		~131,072
	 *  --------------------------------
	 *
	 *  Finally, note that all of the above calculate the initial
	 *  number of metaslabs. Expanding a top-level vdev will result
	 *  in additional metaslabs being allocated making it possible
	 *  to exceed the zfs_vdev_ms_count_limit.
	 */

	if (ms_count < zfs_vdev_min_ms_count)
		ms_shift = highbit64(asize / zfs_vdev_min_ms_count);
	else if (ms_count > zfs_vdev_default_ms_count)
		ms_shift = highbit64(asize / zfs_vdev_default_ms_count);
	else
		ms_shift = zfs_vdev_default_ms_shift;

	if (ms_shift < SPA_MAXBLOCKSHIFT) {
		ms_shift = SPA_MAXBLOCKSHIFT;
	} else if (ms_shift > zfs_vdev_max_ms_shift) {
		ms_shift = zfs_vdev_max_ms_shift;
		/* cap the total count to constrain memory footprint */
		if ((asize >> ms_shift) > zfs_vdev_ms_count_limit)
			ms_shift = highbit64(asize / zfs_vdev_ms_count_limit);
	}

	vd->vdev_ms_shift = ms_shift;
	ASSERT3U(vd->vdev_ms_shift, >=, SPA_MAXBLOCKSHIFT);
}

/*
 * Maximize performance by inflating the configured ashift for top level
 * vdevs to be as close to the physical ashift as possible while maintaining
 * administrator defined limits and ensuring it doesn't go below the
 * logical ashift.
 */
void
vdev_ashift_optimize(vdev_t *vd)
{
	if (vd == vd->vdev_top) {
		if (vd->vdev_ashift < vd->vdev_physical_ashift) {
			vd->vdev_ashift = MIN(
			    MAX(zfs_max_auto_ashift, vd->vdev_ashift),
			    MAX(zfs_min_auto_ashift, vd->vdev_physical_ashift));
		} else {
			/*
			 * Unusual case where logical ashift > physical ashift
			 * so we can't cap the calculated ashift based on max
			 * ashift as that would cause failures.
			 * We still check if we need to increase it to match
			 * the min ashift.
			 */
			vd->vdev_ashift = MAX(zfs_min_auto_ashift,
			    vd->vdev_ashift);
		}
	}
}

void
vdev_dirty(vdev_t *vd, int flags, void *arg, uint64_t txg)
{
	ASSERT(vd == vd->vdev_top);
	/* indirect vdevs don't have metaslabs or dtls */
	ASSERT(vdev_is_concrete(vd) || flags == 0);
	ASSERT(ISP2(flags));
	ASSERT(spa_writeable(vd->vdev_spa));

	if (flags & VDD_METASLAB)
		(void) txg_list_add(&vd->vdev_ms_list, arg, txg);

	if (flags & VDD_DTL)
		(void) txg_list_add(&vd->vdev_dtl_list, arg, txg);

	(void) txg_list_add(&vd->vdev_spa->spa_vdev_txg_list, vd, txg);
}

void
vdev_dirty_leaves(vdev_t *vd, int flags, uint64_t txg)
{
	for (int c = 0; c < vd->vdev_children; c++)
		vdev_dirty_leaves(vd->vdev_child[c], flags, txg);

	if (vd->vdev_ops->vdev_op_leaf)
		vdev_dirty(vd->vdev_top, flags, vd, txg);
}

/*
 * DTLs.
 *
 * A vdev's DTL (dirty time log) is the set of transaction groups for which
 * the vdev has less than perfect replication.  There are four kinds of DTL:
 *
 * DTL_MISSING: txgs for which the vdev has no valid copies of the data
 *
 * DTL_PARTIAL: txgs for which data is available, but not fully replicated
 *
 * DTL_SCRUB: the txgs that could not be repaired by the last scrub; upon
 *	scrub completion, DTL_SCRUB replaces DTL_MISSING in the range of
 *	txgs that was scrubbed.
 *
 * DTL_OUTAGE: txgs which cannot currently be read, whether due to
 *	persistent errors or just some device being offline.
 *	Unlike the other three, the DTL_OUTAGE map is not generally
 *	maintained; it's only computed when needed, typically to
 *	determine whether a device can be detached.
 *
 * For leaf vdevs, DTL_MISSING and DTL_PARTIAL are identical: the device
 * either has the data or it doesn't.
 *
 * For interior vdevs such as mirror and RAID-Z the picture is more complex.
 * A vdev's DTL_PARTIAL is the union of its children's DTL_PARTIALs, because
 * if any child is less than fully replicated, then so is its parent.
 * A vdev's DTL_MISSING is a modified union of its children's DTL_MISSINGs,
 * comprising only those txgs which appear in 'maxfaults' or more children;
 * those are the txgs we don't have enough replication to read.  For example,
 * double-parity RAID-Z can tolerate up to two missing devices (maxfaults == 2);
 * thus, its DTL_MISSING consists of the set of txgs that appear in more than
 * two child DTL_MISSING maps.
 *
 * It should be clear from the above that to compute the DTLs and outage maps
 * for all vdevs, it suffices to know just the leaf vdevs' DTL_MISSING maps.
 * Therefore, that is all we keep on disk.  When loading the pool, or after
 * a configuration change, we generate all other DTLs from first principles.
 */
void
vdev_dtl_dirty(vdev_t *vd, vdev_dtl_type_t t, uint64_t txg, uint64_t size)
{
	range_tree_t *rt = vd->vdev_dtl[t];

	ASSERT(t < DTL_TYPES);
	ASSERT(vd != vd->vdev_spa->spa_root_vdev);
	ASSERT(spa_writeable(vd->vdev_spa));

	mutex_enter(&vd->vdev_dtl_lock);
	if (!range_tree_contains(rt, txg, size))
		range_tree_add(rt, txg, size);
	mutex_exit(&vd->vdev_dtl_lock);
}

boolean_t
vdev_dtl_contains(vdev_t *vd, vdev_dtl_type_t t, uint64_t txg, uint64_t size)
{
	range_tree_t *rt = vd->vdev_dtl[t];
	boolean_t dirty = B_FALSE;

	ASSERT(t < DTL_TYPES);
	ASSERT(vd != vd->vdev_spa->spa_root_vdev);

	/*
	 * While we are loading the pool, the DTLs have not been loaded yet.
	 * Ignore the DTLs and try all devices.  This avoids a recursive
	 * mutex enter on the vdev_dtl_lock, and also makes us try hard
	 * when loading the pool (relying on the checksum to ensure that
	 * we get the right data -- note that we while loading, we are
	 * only reading the MOS, which is always checksummed).
	 */
	if (vd->vdev_spa->spa_load_state != SPA_LOAD_NONE)
		return (B_FALSE);

	mutex_enter(&vd->vdev_dtl_lock);
	if (!range_tree_is_empty(rt))
		dirty = range_tree_contains(rt, txg, size);
	mutex_exit(&vd->vdev_dtl_lock);

	return (dirty);
}

boolean_t
vdev_dtl_empty(vdev_t *vd, vdev_dtl_type_t t)
{
	range_tree_t *rt = vd->vdev_dtl[t];
	boolean_t empty;

	mutex_enter(&vd->vdev_dtl_lock);
	empty = range_tree_is_empty(rt);
	mutex_exit(&vd->vdev_dtl_lock);

	return (empty);
}

/*
 * Returns B_TRUE if vdev determines offset needs to be resilvered.
 */
boolean_t
vdev_dtl_need_resilver(vdev_t *vd, uint64_t offset, size_t psize)
{
        ASSERT(vd != vd->vdev_spa->spa_root_vdev);

        if (vd->vdev_ops->vdev_op_need_resilver == NULL ||
            vd->vdev_ops->vdev_op_leaf)
                return (B_TRUE);

        return (vd->vdev_ops->vdev_op_need_resilver(vd, offset, psize));
}

/*
 * Returns the lowest txg in the DTL range.
 */
static uint64_t
vdev_dtl_min(vdev_t *vd)
{
	range_seg_t *rs;

	ASSERT(MUTEX_HELD(&vd->vdev_dtl_lock));
	ASSERT3U(range_tree_space(vd->vdev_dtl[DTL_MISSING]), !=, 0);
	ASSERT0(vd->vdev_children);

	rs = avl_first(&vd->vdev_dtl[DTL_MISSING]->rt_root);
	return (rs->rs_start - 1);
}

/*
 * Returns the highest txg in the DTL.
 */
static uint64_t
vdev_dtl_max(vdev_t *vd)
{
	range_seg_t *rs;

	ASSERT(MUTEX_HELD(&vd->vdev_dtl_lock));
	ASSERT3U(range_tree_space(vd->vdev_dtl[DTL_MISSING]), !=, 0);
	ASSERT0(vd->vdev_children);

	rs = avl_last(&vd->vdev_dtl[DTL_MISSING]->rt_root);
	return (rs->rs_end);
}

/*
 * Determine if a resilvering vdev should remove any DTL entries from
 * its range. If the vdev was resilvering for the entire duration of the
 * scan then it should excise that range from its DTLs. Otherwise, this
 * vdev is considered partially resilvered and should leave its DTL
 * entries intact. The comment in vdev_dtl_reassess() describes how we
 * excise the DTLs.
 */
static boolean_t
vdev_dtl_should_excise(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	dsl_scan_t *scn = spa->spa_dsl_pool->dp_scan;

	ASSERT0(scn->scn_phys.scn_errors);
	ASSERT0(vd->vdev_children);

	if (vd->vdev_state < VDEV_STATE_DEGRADED)
		return (B_FALSE);

	if (vd->vdev_resilver_txg == 0 ||
	    range_tree_is_empty(vd->vdev_dtl[DTL_MISSING]))
		return (B_TRUE);

	/*
	 * When a resilver is initiated the scan will assign the scn_max_txg
	 * value to the highest txg value that exists in all DTLs. If this
	 * device's max DTL is not part of this scan (i.e. it is not in
	 * the range (scn_min_txg, scn_max_txg] then it is not eligible
	 * for excision.
	 */
	if (vdev_dtl_max(vd) <= scn->scn_phys.scn_max_txg) {
		ASSERT3U(scn->scn_phys.scn_min_txg, <=, vdev_dtl_min(vd));
		ASSERT3U(scn->scn_phys.scn_min_txg, <, vd->vdev_resilver_txg);
		ASSERT3U(vd->vdev_resilver_txg, <=, scn->scn_phys.scn_max_txg);
		return (B_TRUE);
	}
	return (B_FALSE);
}

/*
 * Reassess DTLs after a config change or scrub completion.
 */
void
vdev_dtl_reassess(vdev_t *vd, uint64_t txg, uint64_t scrub_txg, int scrub_done)
{
	spa_t *spa = vd->vdev_spa;
	avl_tree_t reftree;
	int minref;

	ASSERT(spa_config_held(spa, SCL_ALL, RW_READER) != 0);

	for (int c = 0; c < vd->vdev_children; c++)
		vdev_dtl_reassess(vd->vdev_child[c], txg,
		    scrub_txg, scrub_done);

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

	if (vd->vdev_ops->vdev_op_leaf) {
		dsl_scan_t *scn = spa->spa_dsl_pool->dp_scan;

		mutex_enter(&vd->vdev_dtl_lock);

		/*
		 * If we've completed a scan cleanly then determine
		 * if this vdev should remove any DTLs. We only want to
		 * excise regions on vdevs that were available during
		 * the entire duration of this scan.
		 */
		if (scrub_txg != 0 &&
		    (spa->spa_scrub_started ||
		    (scn != NULL && scn->scn_phys.scn_errors == 0)) &&
		    vdev_dtl_should_excise(vd)) {
			/*
			 * We completed a scrub up to scrub_txg.  If we
			 * did it without rebooting, then the scrub dtl
			 * will be valid, so excise the old region and
			 * fold in the scrub dtl.  Otherwise, leave the
			 * dtl as-is if there was an error.
			 *
			 * There's little trick here: to excise the beginning
			 * of the DTL_MISSING map, we put it into a reference
			 * tree and then add a segment with refcnt -1 that
			 * covers the range [0, scrub_txg).  This means
			 * that each txg in that range has refcnt -1 or 0.
			 * We then add DTL_SCRUB with a refcnt of 2, so that
			 * entries in the range [0, scrub_txg) will have a
			 * positive refcnt -- either 1 or 2.  We then convert
			 * the reference tree into the new DTL_MISSING map.
			 */
			space_reftree_create(&reftree);
			space_reftree_add_map(&reftree,
			    vd->vdev_dtl[DTL_MISSING], 1);
			space_reftree_add_seg(&reftree, 0, scrub_txg, -1);
			space_reftree_add_map(&reftree,
			    vd->vdev_dtl[DTL_SCRUB], 2);
			space_reftree_generate_map(&reftree,
			    vd->vdev_dtl[DTL_MISSING], 1);
			space_reftree_destroy(&reftree);
		}
		range_tree_vacate(vd->vdev_dtl[DTL_PARTIAL], NULL, NULL);
		range_tree_walk(vd->vdev_dtl[DTL_MISSING],
		    range_tree_add, vd->vdev_dtl[DTL_PARTIAL]);
		if (scrub_done)
			range_tree_vacate(vd->vdev_dtl[DTL_SCRUB], NULL, NULL);
		range_tree_vacate(vd->vdev_dtl[DTL_OUTAGE], NULL, NULL);
		if (!vdev_readable(vd))
			range_tree_add(vd->vdev_dtl[DTL_OUTAGE], 0, -1ULL);
		else
			range_tree_walk(vd->vdev_dtl[DTL_MISSING],
			    range_tree_add, vd->vdev_dtl[DTL_OUTAGE]);

		/*
		 * If the vdev was resilvering and no longer has any
		 * DTLs then reset its resilvering flag and dirty
		 * the top level so that we persist the change.
		 */
		if (vd->vdev_resilver_txg != 0 &&
		    range_tree_is_empty(vd->vdev_dtl[DTL_MISSING]) &&
		    range_tree_is_empty(vd->vdev_dtl[DTL_OUTAGE])) {
			vd->vdev_resilver_txg = 0;
			vdev_config_dirty(vd->vdev_top);
		}

		mutex_exit(&vd->vdev_dtl_lock);

		if (txg != 0)
			vdev_dirty(vd->vdev_top, VDD_DTL, vd, txg);
		return;
	}

	mutex_enter(&vd->vdev_dtl_lock);
	for (int t = 0; t < DTL_TYPES; t++) {
		/* account for child's outage in parent's missing map */
		int s = (t == DTL_MISSING) ? DTL_OUTAGE: t;
		if (t == DTL_SCRUB)
			continue;			/* leaf vdevs only */
		if (t == DTL_PARTIAL)
			minref = 1;			/* i.e. non-zero */
		else if (vd->vdev_nparity != 0)
			minref = vd->vdev_nparity + 1;	/* RAID-Z */
		else
			minref = vd->vdev_children;	/* any kind of mirror */
		space_reftree_create(&reftree);
		for (int c = 0; c < vd->vdev_children; c++) {
			vdev_t *cvd = vd->vdev_child[c];
			mutex_enter(&cvd->vdev_dtl_lock);
			space_reftree_add_map(&reftree, cvd->vdev_dtl[s], 1);
			mutex_exit(&cvd->vdev_dtl_lock);
		}
		space_reftree_generate_map(&reftree, vd->vdev_dtl[t], minref);
		space_reftree_destroy(&reftree);
	}
	mutex_exit(&vd->vdev_dtl_lock);
}

int
vdev_dtl_load(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	objset_t *mos = spa->spa_meta_objset;
	int error = 0;

	if (vd->vdev_ops->vdev_op_leaf && vd->vdev_dtl_object != 0) {
		ASSERT(vdev_is_concrete(vd));

		error = space_map_open(&vd->vdev_dtl_sm, mos,
		    vd->vdev_dtl_object, 0, -1ULL, 0);
		if (error)
			return (error);
		ASSERT(vd->vdev_dtl_sm != NULL);

		mutex_enter(&vd->vdev_dtl_lock);
		error = space_map_load(vd->vdev_dtl_sm,
		    vd->vdev_dtl[DTL_MISSING], SM_ALLOC);
		mutex_exit(&vd->vdev_dtl_lock);

		return (error);
	}

	for (int c = 0; c < vd->vdev_children; c++) {
		error = vdev_dtl_load(vd->vdev_child[c]);
		if (error != 0)
			break;
	}

	return (error);
}

static void
vdev_zap_allocation_data(vdev_t *vd, dmu_tx_t *tx)
{
	spa_t *spa = vd->vdev_spa;
	objset_t *mos = spa->spa_meta_objset;
	vdev_alloc_bias_t alloc_bias = vd->vdev_alloc_bias;
	const char *string;

	ASSERT(alloc_bias != VDEV_BIAS_NONE);

	string =
	    (alloc_bias == VDEV_BIAS_LOG) ? VDEV_ALLOC_BIAS_LOG :
	    (alloc_bias == VDEV_BIAS_SPECIAL) ? VDEV_ALLOC_BIAS_SPECIAL :
	    (alloc_bias == VDEV_BIAS_DEDUP) ? VDEV_ALLOC_BIAS_DEDUP : NULL;

	ASSERT(string != NULL);
	VERIFY0(zap_add(mos, vd->vdev_top_zap, VDEV_TOP_ZAP_ALLOCATION_BIAS,
	    1, strlen(string) + 1, string, tx));

	if (alloc_bias == VDEV_BIAS_SPECIAL || alloc_bias == VDEV_BIAS_DEDUP) {
		spa_activate_allocation_classes(spa, tx);
	}
}

void
vdev_destroy_unlink_zap(vdev_t *vd, uint64_t zapobj, dmu_tx_t *tx)
{
	spa_t *spa = vd->vdev_spa;

	VERIFY0(zap_destroy(spa->spa_meta_objset, zapobj, tx));
	VERIFY0(zap_remove_int(spa->spa_meta_objset, spa->spa_all_vdev_zaps,
	    zapobj, tx));
}

uint64_t
vdev_create_link_zap(vdev_t *vd, dmu_tx_t *tx)
{
	spa_t *spa = vd->vdev_spa;
	uint64_t zap = zap_create(spa->spa_meta_objset, DMU_OTN_ZAP_METADATA,
	    DMU_OT_NONE, 0, tx);

	ASSERT(zap != 0);
	VERIFY0(zap_add_int(spa->spa_meta_objset, spa->spa_all_vdev_zaps,
	    zap, tx));

	return (zap);
}

void
vdev_construct_zaps(vdev_t *vd, dmu_tx_t *tx)
{
	if (vd->vdev_ops != &vdev_hole_ops &&
	    vd->vdev_ops != &vdev_missing_ops &&
	    vd->vdev_ops != &vdev_root_ops &&
	    !vd->vdev_top->vdev_removing) {
		if (vd->vdev_ops->vdev_op_leaf && vd->vdev_leaf_zap == 0) {
			vd->vdev_leaf_zap = vdev_create_link_zap(vd, tx);
		}
		if (vd == vd->vdev_top && vd->vdev_top_zap == 0) {
			vd->vdev_top_zap = vdev_create_link_zap(vd, tx);
			if (vd->vdev_alloc_bias != VDEV_BIAS_NONE)
				vdev_zap_allocation_data(vd, tx);
		}
	}

	for (uint64_t i = 0; i < vd->vdev_children; i++) {
		vdev_construct_zaps(vd->vdev_child[i], tx);
	}
}

void
vdev_dtl_sync(vdev_t *vd, uint64_t txg)
{
	spa_t *spa = vd->vdev_spa;
	range_tree_t *rt = vd->vdev_dtl[DTL_MISSING];
	objset_t *mos = spa->spa_meta_objset;
	range_tree_t *rtsync;
	dmu_tx_t *tx;
	uint64_t object = space_map_object(vd->vdev_dtl_sm);

	ASSERT(vdev_is_concrete(vd));
	ASSERT(vd->vdev_ops->vdev_op_leaf);

	tx = dmu_tx_create_assigned(spa->spa_dsl_pool, txg);

	if (vd->vdev_detached || vd->vdev_top->vdev_removing) {
		mutex_enter(&vd->vdev_dtl_lock);
		space_map_free(vd->vdev_dtl_sm, tx);
		space_map_close(vd->vdev_dtl_sm);
		vd->vdev_dtl_sm = NULL;
		mutex_exit(&vd->vdev_dtl_lock);

		/*
		 * We only destroy the leaf ZAP for detached leaves or for
		 * removed log devices. Removed data devices handle leaf ZAP
		 * cleanup later, once cancellation is no longer possible.
		 */
		if (vd->vdev_leaf_zap != 0 && (vd->vdev_detached ||
		    vd->vdev_top->vdev_islog)) {
			vdev_destroy_unlink_zap(vd, vd->vdev_leaf_zap, tx);
			vd->vdev_leaf_zap = 0;
		}

		dmu_tx_commit(tx);
		return;
	}

	if (vd->vdev_dtl_sm == NULL) {
		uint64_t new_object;

		new_object = space_map_alloc(mos, vdev_dtl_sm_blksz, tx);
		VERIFY3U(new_object, !=, 0);

		VERIFY0(space_map_open(&vd->vdev_dtl_sm, mos, new_object,
		    0, -1ULL, 0));
		ASSERT(vd->vdev_dtl_sm != NULL);
	}

	rtsync = range_tree_create(NULL, NULL);

	mutex_enter(&vd->vdev_dtl_lock);
	range_tree_walk(rt, range_tree_add, rtsync);
	mutex_exit(&vd->vdev_dtl_lock);

	space_map_truncate(vd->vdev_dtl_sm, vdev_dtl_sm_blksz, tx);
	space_map_write(vd->vdev_dtl_sm, rtsync, SM_ALLOC, SM_NO_VDEVID, tx);
	range_tree_vacate(rtsync, NULL, NULL);

	range_tree_destroy(rtsync);

	/*
	 * If the object for the space map has changed then dirty
	 * the top level so that we update the config.
	 */
	if (object != space_map_object(vd->vdev_dtl_sm)) {
		vdev_dbgmsg(vd, "txg %llu, spa %s, DTL old object %llu, "
		    "new object %llu", (u_longlong_t)txg, spa_name(spa),
		    (u_longlong_t)object,
		    (u_longlong_t)space_map_object(vd->vdev_dtl_sm));
		vdev_config_dirty(vd->vdev_top);
	}

	dmu_tx_commit(tx);
}

/*
 * Determine whether the specified vdev can be offlined/detached/removed
 * without losing data.
 */
boolean_t
vdev_dtl_required(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	vdev_t *tvd = vd->vdev_top;
	uint8_t cant_read = vd->vdev_cant_read;
	boolean_t required;

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

	if (vd == spa->spa_root_vdev || vd == tvd)
		return (B_TRUE);

	/*
	 * Temporarily mark the device as unreadable, and then determine
	 * whether this results in any DTL outages in the top-level vdev.
	 * If not, we can safely offline/detach/remove the device.
	 */
	vd->vdev_cant_read = B_TRUE;
	vdev_dtl_reassess(tvd, 0, 0, B_FALSE);
	required = !vdev_dtl_empty(tvd, DTL_OUTAGE);
	vd->vdev_cant_read = cant_read;
	vdev_dtl_reassess(tvd, 0, 0, B_FALSE);

	if (!required && zio_injection_enabled)
		required = !!zio_handle_device_injection(vd, NULL, ECHILD);

	return (required);
}

/*
 * Determine if resilver is needed, and if so the txg range.
 */
boolean_t
vdev_resilver_needed(vdev_t *vd, uint64_t *minp, uint64_t *maxp)
{
	boolean_t needed = B_FALSE;
	uint64_t thismin = UINT64_MAX;
	uint64_t thismax = 0;

	if (vd->vdev_children == 0) {
		mutex_enter(&vd->vdev_dtl_lock);
		if (!range_tree_is_empty(vd->vdev_dtl[DTL_MISSING]) &&
		    vdev_writeable(vd)) {

			thismin = vdev_dtl_min(vd);
			thismax = vdev_dtl_max(vd);
			needed = B_TRUE;
		}
		mutex_exit(&vd->vdev_dtl_lock);
	} else {
		for (int c = 0; c < vd->vdev_children; c++) {
			vdev_t *cvd = vd->vdev_child[c];
			uint64_t cmin, cmax;

			if (vdev_resilver_needed(cvd, &cmin, &cmax)) {
				thismin = MIN(thismin, cmin);
				thismax = MAX(thismax, cmax);
				needed = B_TRUE;
			}
		}
	}

	if (needed && minp) {
		*minp = thismin;
		*maxp = thismax;
	}
	return (needed);
}

/*
 * Gets the checkpoint space map object from the vdev's ZAP.
 * Returns the spacemap object, or 0 if it wasn't in the ZAP
 * or the ZAP doesn't exist yet.
 */
int
vdev_checkpoint_sm_object(vdev_t *vd)
{
	ASSERT0(spa_config_held(vd->vdev_spa, SCL_ALL, RW_WRITER));
	if (vd->vdev_top_zap == 0) {
		return (0);
	}

	uint64_t sm_obj = 0;
	int err = zap_lookup(spa_meta_objset(vd->vdev_spa), vd->vdev_top_zap,
	    VDEV_TOP_ZAP_POOL_CHECKPOINT_SM, sizeof (uint64_t), 1, &sm_obj);

	ASSERT(err == 0 || err == ENOENT);

	return (sm_obj);
}

int
vdev_load(vdev_t *vd)
{
	int error = 0;
	/*
	 * Recursively load all children.
	 */
	for (int c = 0; c < vd->vdev_children; c++) {
		error = vdev_load(vd->vdev_child[c]);
		if (error != 0) {
			return (error);
		}
	}

	vdev_set_deflate_ratio(vd);

	/*
	 * On spa_load path, grab the allocation bias from our zap
	 */
	if (vd == vd->vdev_top && vd->vdev_top_zap != 0) {
		spa_t *spa = vd->vdev_spa;
		char bias_str[64];

		if (zap_lookup(spa->spa_meta_objset, vd->vdev_top_zap,
		    VDEV_TOP_ZAP_ALLOCATION_BIAS, 1, sizeof (bias_str),
		    bias_str) == 0) {
			ASSERT(vd->vdev_alloc_bias == VDEV_BIAS_NONE);
			vd->vdev_alloc_bias = vdev_derive_alloc_bias(bias_str);
		}
	}

	/*
	 * If this is a top-level vdev, initialize its metaslabs.
	 */
	if (vd == vd->vdev_top && vdev_is_concrete(vd)) {
		vdev_metaslab_group_create(vd);

		if (vd->vdev_ashift == 0 || vd->vdev_asize == 0) {
			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_CORRUPT_DATA);
			vdev_dbgmsg(vd, "vdev_load: invalid size. ashift=%llu, "
			    "asize=%llu", (u_longlong_t)vd->vdev_ashift,
			    (u_longlong_t)vd->vdev_asize);
			return (SET_ERROR(ENXIO));
		}

		error = vdev_metaslab_init(vd, 0);
		if (error != 0) {
			vdev_dbgmsg(vd, "vdev_load: metaslab_init failed "
			    "[error=%d]", error);
			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_CORRUPT_DATA);
			return (error);
		}

		uint64_t checkpoint_sm_obj = vdev_checkpoint_sm_object(vd);
		if (checkpoint_sm_obj != 0) {
			objset_t *mos = spa_meta_objset(vd->vdev_spa);
			ASSERT(vd->vdev_asize != 0);
			ASSERT3P(vd->vdev_checkpoint_sm, ==, NULL);

			error = space_map_open(&vd->vdev_checkpoint_sm,
			    mos, checkpoint_sm_obj, 0, vd->vdev_asize,
			    vd->vdev_ashift);
			if (error != 0) {
				vdev_dbgmsg(vd, "vdev_load: space_map_open "
				    "failed for checkpoint spacemap (obj %llu) "
				    "[error=%d]",
				    (u_longlong_t)checkpoint_sm_obj, error);
				return (error);
			}
			ASSERT3P(vd->vdev_checkpoint_sm, !=, NULL);

			/*
			 * Since the checkpoint_sm contains free entries
			 * exclusively we can use space_map_allocated() to
			 * indicate the cumulative checkpointed space that
			 * has been freed.
			 */
			vd->vdev_stat.vs_checkpoint_space =
			    -space_map_allocated(vd->vdev_checkpoint_sm);
			vd->vdev_spa->spa_checkpoint_info.sci_dspace +=
			    vd->vdev_stat.vs_checkpoint_space;
		}
	}

	/*
	 * If this is a leaf vdev, load its DTL.
	 */
	if (vd->vdev_ops->vdev_op_leaf && (error = vdev_dtl_load(vd)) != 0) {
		vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		vdev_dbgmsg(vd, "vdev_load: vdev_dtl_load failed "
		    "[error=%d]", error);
		return (error);
	}

	uint64_t obsolete_sm_object = vdev_obsolete_sm_object(vd);
	if (obsolete_sm_object != 0) {
		objset_t *mos = vd->vdev_spa->spa_meta_objset;
		ASSERT(vd->vdev_asize != 0);
		ASSERT3P(vd->vdev_obsolete_sm, ==, NULL);

		if ((error = space_map_open(&vd->vdev_obsolete_sm, mos,
		    obsolete_sm_object, 0, vd->vdev_asize, 0))) {
			vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_CORRUPT_DATA);
			vdev_dbgmsg(vd, "vdev_load: space_map_open failed for "
			    "obsolete spacemap (obj %llu) [error=%d]",
			    (u_longlong_t)obsolete_sm_object, error);
			return (error);
		}
	}

	return (0);
}

/*
 * The special vdev case is used for hot spares and l2cache devices.  Its
 * sole purpose it to set the vdev state for the associated vdev.  To do this,
 * we make sure that we can open the underlying device, then try to read the
 * label, and make sure that the label is sane and that it hasn't been
 * repurposed to another pool.
 */
int
vdev_validate_aux(vdev_t *vd)
{
	nvlist_t *label;
	uint64_t guid, version;
	uint64_t state;

	if (!vdev_readable(vd))
		return (0);

	if ((label = vdev_label_read_config(vd, -1ULL)) == NULL) {
		vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		return (-1);
	}

	if (nvlist_lookup_uint64(label, ZPOOL_CONFIG_VERSION, &version) != 0 ||
	    !SPA_VERSION_IS_SUPPORTED(version) ||
	    nvlist_lookup_uint64(label, ZPOOL_CONFIG_GUID, &guid) != 0 ||
	    guid != vd->vdev_guid ||
	    nvlist_lookup_uint64(label, ZPOOL_CONFIG_POOL_STATE, &state) != 0) {
		vdev_set_state(vd, B_TRUE, VDEV_STATE_CANT_OPEN,
		    VDEV_AUX_CORRUPT_DATA);
		nvlist_free(label);
		return (-1);
	}

	/*
	 * We don't actually check the pool state here.  If it's in fact in
	 * use by another pool, we update this fact on the fly when requested.
	 */
	nvlist_free(label);
	return (0);
}

/*
 * Free the objects used to store this vdev's spacemaps, and the array
 * that points to them.
 */
void
vdev_destroy_spacemaps(vdev_t *vd, dmu_tx_t *tx)
{
	if (vd->vdev_ms_array == 0)
		return;

	objset_t *mos = vd->vdev_spa->spa_meta_objset;
	uint64_t array_count = vd->vdev_asize >> vd->vdev_ms_shift;
	size_t array_bytes = array_count * sizeof (uint64_t);
	uint64_t *smobj_array = kmem_alloc(array_bytes, KM_SLEEP);
	VERIFY0(dmu_read(mos, vd->vdev_ms_array, 0,
	    array_bytes, smobj_array, 0));

	for (uint64_t i = 0; i < array_count; i++) {
		uint64_t smobj = smobj_array[i];
		if (smobj == 0)
			continue;

		space_map_free_obj(mos, smobj, tx);
	}

	kmem_free(smobj_array, array_bytes);
	VERIFY0(dmu_object_free(mos, vd->vdev_ms_array, tx));
	vd->vdev_ms_array = 0;
}

static void
vdev_remove_empty_log(vdev_t *vd, uint64_t txg)
{
	spa_t *spa = vd->vdev_spa;

	ASSERT(vd->vdev_islog);
	ASSERT(vd == vd->vdev_top);
	ASSERT3U(txg, ==, spa_syncing_txg(spa));

	dmu_tx_t *tx = dmu_tx_create_assigned(spa_get_dsl(spa), txg);

	vdev_destroy_spacemaps(vd, tx);
	if (vd->vdev_top_zap != 0) {
		vdev_destroy_unlink_zap(vd, vd->vdev_top_zap, tx);
		vd->vdev_top_zap = 0;
	}

	dmu_tx_commit(tx);
}

void
vdev_sync_done(vdev_t *vd, uint64_t txg)
{
	metaslab_t *msp;
	boolean_t reassess = !txg_list_empty(&vd->vdev_ms_list, TXG_CLEAN(txg));

	ASSERT(vdev_is_concrete(vd));

	while ((msp = txg_list_remove(&vd->vdev_ms_list, TXG_CLEAN(txg)))
	    != NULL)
		metaslab_sync_done(msp, txg);

	if (reassess)
		metaslab_sync_reassess(vd->vdev_mg);
}

void
vdev_sync(vdev_t *vd, uint64_t txg)
{
	spa_t *spa = vd->vdev_spa;
	vdev_t *lvd;
	metaslab_t *msp;

	ASSERT3U(txg, ==, spa->spa_syncing_txg);
	dmu_tx_t *tx = dmu_tx_create_assigned(spa->spa_dsl_pool, txg);
	if (range_tree_space(vd->vdev_obsolete_segments) > 0) {
		ASSERT(vd->vdev_removing ||
		    vd->vdev_ops == &vdev_indirect_ops);

		vdev_indirect_sync_obsolete(vd, tx);

		/*
		 * If the vdev is indirect, it can't have dirty
		 * metaslabs or DTLs.
		 */
		if (vd->vdev_ops == &vdev_indirect_ops) {
			ASSERT(txg_list_empty(&vd->vdev_ms_list, txg));
			ASSERT(txg_list_empty(&vd->vdev_dtl_list, txg));
			dmu_tx_commit(tx);
			return;
		}
	}

	ASSERT(vdev_is_concrete(vd));

	if (vd->vdev_ms_array == 0 && vd->vdev_ms_shift != 0 &&
	    !vd->vdev_removing) {
		ASSERT(vd == vd->vdev_top);
		ASSERT0(vd->vdev_indirect_config.vic_mapping_object);
		vd->vdev_ms_array = dmu_object_alloc(spa->spa_meta_objset,
		    DMU_OT_OBJECT_ARRAY, 0, DMU_OT_NONE, 0, tx);
		ASSERT(vd->vdev_ms_array != 0);
		vdev_config_dirty(vd);
	}

	while ((msp = txg_list_remove(&vd->vdev_ms_list, txg)) != NULL) {
		metaslab_sync(msp, txg);
		(void) txg_list_add(&vd->vdev_ms_list, msp, TXG_CLEAN(txg));
	}

	while ((lvd = txg_list_remove(&vd->vdev_dtl_list, txg)) != NULL)
		vdev_dtl_sync(lvd, txg);

	/*
	 * If this is an empty log device being removed, destroy the
	 * metadata associated with it.
	 */
	if (vd->vdev_islog && vd->vdev_stat.vs_alloc == 0 && vd->vdev_removing)
		vdev_remove_empty_log(vd, txg);

	(void) txg_list_add(&spa->spa_vdev_txg_list, vd, TXG_CLEAN(txg));
	dmu_tx_commit(tx);
}

uint64_t
vdev_psize_to_asize(vdev_t *vd, uint64_t psize)
{
	return (vd->vdev_ops->vdev_op_asize(vd, psize));
}

/*
 * Mark the given vdev faulted.  A faulted vdev behaves as if the device could
 * not be opened, and no I/O is attempted.
 */
int
vdev_fault(spa_t *spa, uint64_t guid, vdev_aux_t aux)
{
	vdev_t *vd, *tvd;

	spa_vdev_state_enter(spa, SCL_NONE);

	if ((vd = spa_lookup_by_guid(spa, guid, B_TRUE)) == NULL)
		return (spa_vdev_state_exit(spa, NULL, ENODEV));

	if (!vd->vdev_ops->vdev_op_leaf)
		return (spa_vdev_state_exit(spa, NULL, ENOTSUP));

	tvd = vd->vdev_top;

	/*
	 * We don't directly use the aux state here, but if we do a
	 * vdev_reopen(), we need this value to be present to remember why we
	 * were faulted.
	 */
	vd->vdev_label_aux = aux;

	/*
	 * Faulted state takes precedence over degraded.
	 */
	vd->vdev_delayed_close = B_FALSE;
	vd->vdev_faulted = 1ULL;
	vd->vdev_degraded = 0ULL;
	vdev_set_state(vd, B_FALSE, VDEV_STATE_FAULTED, aux);

	/*
	 * If this device has the only valid copy of the data, then
	 * back off and simply mark the vdev as degraded instead.
	 */
	if (!tvd->vdev_islog && vd->vdev_aux == NULL && vdev_dtl_required(vd)) {
		vd->vdev_degraded = 1ULL;
		vd->vdev_faulted = 0ULL;

		/*
		 * If we reopen the device and it's not dead, only then do we
		 * mark it degraded.
		 */
		vdev_reopen(tvd);

		if (vdev_readable(vd))
			vdev_set_state(vd, B_FALSE, VDEV_STATE_DEGRADED, aux);
	}

	return (spa_vdev_state_exit(spa, vd, 0));
}

/*
 * Mark the given vdev degraded.  A degraded vdev is purely an indication to the
 * user that something is wrong.  The vdev continues to operate as normal as far
 * as I/O is concerned.
 */
int
vdev_degrade(spa_t *spa, uint64_t guid, vdev_aux_t aux)
{
	vdev_t *vd;

	spa_vdev_state_enter(spa, SCL_NONE);

	if ((vd = spa_lookup_by_guid(spa, guid, B_TRUE)) == NULL)
		return (spa_vdev_state_exit(spa, NULL, ENODEV));

	if (!vd->vdev_ops->vdev_op_leaf)
		return (spa_vdev_state_exit(spa, NULL, ENOTSUP));

	/*
	 * If the vdev is already faulted, then don't do anything.
	 */
	if (vd->vdev_faulted || vd->vdev_degraded)
		return (spa_vdev_state_exit(spa, NULL, 0));

	vd->vdev_degraded = 1ULL;
	if (!vdev_is_dead(vd))
		vdev_set_state(vd, B_FALSE, VDEV_STATE_DEGRADED,
		    aux);

	return (spa_vdev_state_exit(spa, vd, 0));
}

/*
 * Online the given vdev.
 *
 * If 'ZFS_ONLINE_UNSPARE' is set, it implies two things.  First, any attached
 * spare device should be detached when the device finishes resilvering.
 * Second, the online should be treated like a 'test' online case, so no FMA
 * events are generated if the device fails to open.
 */
int
vdev_online(spa_t *spa, uint64_t guid, uint64_t flags, vdev_state_t *newstate)
{
	vdev_t *vd, *tvd, *pvd, *rvd = spa->spa_root_vdev;
	boolean_t wasoffline;
	vdev_state_t oldstate;

	spa_vdev_state_enter(spa, SCL_NONE);

	if ((vd = spa_lookup_by_guid(spa, guid, B_TRUE)) == NULL)
		return (spa_vdev_state_exit(spa, NULL, ENODEV));

	if (!vd->vdev_ops->vdev_op_leaf)
		return (spa_vdev_state_exit(spa, NULL, ENOTSUP));

	wasoffline = (vd->vdev_offline || vd->vdev_tmpoffline);
	oldstate = vd->vdev_state;

	tvd = vd->vdev_top;
	vd->vdev_offline = B_FALSE;
	vd->vdev_tmpoffline = B_FALSE;
	vd->vdev_checkremove = !!(flags & ZFS_ONLINE_CHECKREMOVE);
	vd->vdev_forcefault = !!(flags & ZFS_ONLINE_FORCEFAULT);

	/* XXX - L2ARC 1.0 does not support expansion */
	if (!vd->vdev_aux) {
		for (pvd = vd; pvd != rvd; pvd = pvd->vdev_parent)
			pvd->vdev_expanding = !!(flags & ZFS_ONLINE_EXPAND);
	}

	vdev_reopen(tvd);
	vd->vdev_checkremove = vd->vdev_forcefault = B_FALSE;

	if (!vd->vdev_aux) {
		for (pvd = vd; pvd != rvd; pvd = pvd->vdev_parent)
			pvd->vdev_expanding = B_FALSE;
	}

	if (newstate)
		*newstate = vd->vdev_state;
	if ((flags & ZFS_ONLINE_UNSPARE) &&
	    !vdev_is_dead(vd) && vd->vdev_parent &&
	    vd->vdev_parent->vdev_ops == &vdev_spare_ops &&
	    vd->vdev_parent->vdev_child[0] == vd)
		vd->vdev_unspare = B_TRUE;

	if ((flags & ZFS_ONLINE_EXPAND) || spa->spa_autoexpand) {

		/* XXX - L2ARC 1.0 does not support expansion */
		if (vd->vdev_aux)
			return (spa_vdev_state_exit(spa, vd, ENOTSUP));
		spa_async_request(spa, SPA_ASYNC_CONFIG_UPDATE);
	}

	/* Restart initializing if necessary */
	mutex_enter(&vd->vdev_initialize_lock);
	if (vdev_writeable(vd) &&
	    vd->vdev_initialize_thread == NULL &&
	    vd->vdev_initialize_state == VDEV_INITIALIZE_ACTIVE) {
		(void) vdev_initialize(vd);
	}
	mutex_exit(&vd->vdev_initialize_lock);

	if (wasoffline ||
	    (oldstate < VDEV_STATE_DEGRADED &&
	    vd->vdev_state >= VDEV_STATE_DEGRADED))
		spa_event_notify(spa, vd, NULL, ESC_ZFS_VDEV_ONLINE);

	return (spa_vdev_state_exit(spa, vd, 0));
}

static int
vdev_offline_locked(spa_t *spa, uint64_t guid, uint64_t flags)
{
	vdev_t *vd, *tvd;
	int error = 0;
	uint64_t generation;
	metaslab_group_t *mg;

top:
	spa_vdev_state_enter(spa, SCL_ALLOC);

	if ((vd = spa_lookup_by_guid(spa, guid, B_TRUE)) == NULL)
		return (spa_vdev_state_exit(spa, NULL, ENODEV));

	if (!vd->vdev_ops->vdev_op_leaf)
		return (spa_vdev_state_exit(spa, NULL, ENOTSUP));

	tvd = vd->vdev_top;
	mg = tvd->vdev_mg;
	generation = spa->spa_config_generation + 1;

	/*
	 * If the device isn't already offline, try to offline it.
	 */
	if (!vd->vdev_offline) {
		/*
		 * If this device has the only valid copy of some data,
		 * don't allow it to be offlined. Log devices are always
		 * expendable.
		 */
		if (!tvd->vdev_islog && vd->vdev_aux == NULL &&
		    vdev_dtl_required(vd))
			return (spa_vdev_state_exit(spa, NULL, EBUSY));

		/*
		 * If the top-level is a slog and it has had allocations
		 * then proceed.  We check that the vdev's metaslab group
		 * is not NULL since it's possible that we may have just
		 * added this vdev but not yet initialized its metaslabs.
		 */
		if (tvd->vdev_islog && mg != NULL) {
			/*
			 * Prevent any future allocations.
			 */
			metaslab_group_passivate(mg);
			(void) spa_vdev_state_exit(spa, vd, 0);

			error = spa_reset_logs(spa);

			/*
			 * If the log device was successfully reset but has
			 * checkpointed data, do not offline it.
			 */
			if (error == 0 &&
			    tvd->vdev_checkpoint_sm != NULL) {
				error = ZFS_ERR_CHECKPOINT_EXISTS;
			}

			spa_vdev_state_enter(spa, SCL_ALLOC);

			/*
			 * Check to see if the config has changed.
			 */
			if (error || generation != spa->spa_config_generation) {
				metaslab_group_activate(mg);
				if (error)
					return (spa_vdev_state_exit(spa,
					    vd, error));
				(void) spa_vdev_state_exit(spa, vd, 0);
				goto top;
			}
			ASSERT0(tvd->vdev_stat.vs_alloc);
		}

		/*
		 * Offline this device and reopen its top-level vdev.
		 * If the top-level vdev is a log device then just offline
		 * it. Otherwise, if this action results in the top-level
		 * vdev becoming unusable, undo it and fail the request.
		 */
		vd->vdev_offline = B_TRUE;
		vdev_reopen(tvd);

		if (!tvd->vdev_islog && vd->vdev_aux == NULL &&
		    vdev_is_dead(tvd)) {
			vd->vdev_offline = B_FALSE;
			vdev_reopen(tvd);
			return (spa_vdev_state_exit(spa, NULL, EBUSY));
		}

		/*
		 * Add the device back into the metaslab rotor so that
		 * once we online the device it's open for business.
		 */
		if (tvd->vdev_islog && mg != NULL)
			metaslab_group_activate(mg);
	}

	vd->vdev_tmpoffline = !!(flags & ZFS_OFFLINE_TEMPORARY);

	return (spa_vdev_state_exit(spa, vd, 0));
}

int
vdev_offline(spa_t *spa, uint64_t guid, uint64_t flags)
{
	int error;

	mutex_enter(&spa->spa_vdev_top_lock);
	error = vdev_offline_locked(spa, guid, flags);
	mutex_exit(&spa->spa_vdev_top_lock);

	return (error);
}

/*
 * Clear the error counts associated with this vdev.  Unlike vdev_online() and
 * vdev_offline(), we assume the spa config is locked.  We also clear all
 * children.  If 'vd' is NULL, then the user wants to clear all vdevs.
 */
void
vdev_clear(spa_t *spa, vdev_t *vd)
{
	vdev_t *rvd = spa->spa_root_vdev;

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

	if (vd == NULL)
		vd = rvd;

	vd->vdev_stat.vs_read_errors = 0;
	vd->vdev_stat.vs_write_errors = 0;
	vd->vdev_stat.vs_checksum_errors = 0;

	for (int c = 0; c < vd->vdev_children; c++)
		vdev_clear(spa, vd->vdev_child[c]);

	if (vd == rvd) {
		for (int c = 0; c < spa->spa_l2cache.sav_count; c++)
			vdev_clear(spa, spa->spa_l2cache.sav_vdevs[c]);

		for (int c = 0; c < spa->spa_spares.sav_count; c++)
			vdev_clear(spa, spa->spa_spares.sav_vdevs[c]);
	}

	/*
	 * It makes no sense to "clear" an indirect vdev.
	 */
	if (!vdev_is_concrete(vd))
		return;

	/*
	 * If we're in the FAULTED state or have experienced failed I/O, then
	 * clear the persistent state and attempt to reopen the device.  We
	 * also mark the vdev config dirty, so that the new faulted state is
	 * written out to disk.
	 */
	if (vd->vdev_faulted || vd->vdev_degraded ||
	    !vdev_readable(vd) || !vdev_writeable(vd)) {

		/*
		 * When reopening in reponse to a clear event, it may be due to
		 * a fmadm repair request.  In this case, if the device is
		 * still broken, we want to still post the ereport again.
		 */
		vd->vdev_forcefault = B_TRUE;

		vd->vdev_faulted = vd->vdev_degraded = 0ULL;
		vd->vdev_cant_read = B_FALSE;
		vd->vdev_cant_write = B_FALSE;

		vdev_reopen(vd == rvd ? rvd : vd->vdev_top);

		vd->vdev_forcefault = B_FALSE;

		if (vd != rvd && vdev_writeable(vd->vdev_top))
			vdev_state_dirty(vd->vdev_top);

		if (vd->vdev_aux == NULL && !vdev_is_dead(vd))
			spa_async_request(spa, SPA_ASYNC_RESILVER);

		spa_event_notify(spa, vd, NULL, ESC_ZFS_VDEV_CLEAR);
	}

	/*
	 * When clearing a FMA-diagnosed fault, we always want to
	 * unspare the device, as we assume that the original spare was
	 * done in response to the FMA fault.
	 */
	if (!vdev_is_dead(vd) && vd->vdev_parent != NULL &&
	    vd->vdev_parent->vdev_ops == &vdev_spare_ops &&
	    vd->vdev_parent->vdev_child[0] == vd)
		vd->vdev_unspare = B_TRUE;
}

boolean_t
vdev_is_dead(vdev_t *vd)
{
	/*
	 * Holes and missing devices are always considered "dead".
	 * This simplifies the code since we don't have to check for
	 * these types of devices in the various code paths.
	 * Instead we rely on the fact that we skip over dead devices
	 * before issuing I/O to them.
	 */
	return (vd->vdev_state < VDEV_STATE_DEGRADED ||
	    vd->vdev_ops == &vdev_hole_ops ||
	    vd->vdev_ops == &vdev_missing_ops);
}

boolean_t
vdev_readable(vdev_t *vd)
{
	return (!vdev_is_dead(vd) && !vd->vdev_cant_read);
}

boolean_t
vdev_writeable(vdev_t *vd)
{
	return (!vdev_is_dead(vd) && !vd->vdev_cant_write &&
	    vdev_is_concrete(vd));
}

boolean_t
vdev_allocatable(vdev_t *vd)
{
	uint64_t state = vd->vdev_state;

	/*
	 * We currently allow allocations from vdevs which may be in the
	 * process of reopening (i.e. VDEV_STATE_CLOSED). If the device
	 * fails to reopen then we'll catch it later when we're holding
	 * the proper locks.  Note that we have to get the vdev state
	 * in a local variable because although it changes atomically,
	 * we're asking two separate questions about it.
	 */
	return (!(state < VDEV_STATE_DEGRADED && state != VDEV_STATE_CLOSED) &&
	    !vd->vdev_cant_write && vdev_is_concrete(vd) &&
	    vd->vdev_mg->mg_initialized);
}

boolean_t
vdev_accessible(vdev_t *vd, zio_t *zio)
{
	ASSERT(zio->io_vd == vd);

	if (vdev_is_dead(vd) || vd->vdev_remove_wanted)
		return (B_FALSE);

	if (zio->io_type == ZIO_TYPE_READ)
		return (!vd->vdev_cant_read);

	if (zio->io_type == ZIO_TYPE_WRITE)
		return (!vd->vdev_cant_write);

	return (B_TRUE);
}

boolean_t
vdev_is_spacemap_addressable(vdev_t *vd)
{
	if (spa_feature_is_active(vd->vdev_spa, SPA_FEATURE_SPACEMAP_V2))
		return (B_TRUE);

	/*
	 * If double-word space map entries are not enabled we assume
	 * 47 bits of the space map entry are dedicated to the entry's
	 * offset (see SM_OFFSET_BITS in space_map.h). We then use that
	 * to calculate the maximum address that can be described by a
	 * space map entry for the given device.
	 */
	uint64_t shift = vd->vdev_ashift + SM_OFFSET_BITS;

	if (shift >= 63) /* detect potential overflow */
		return (B_TRUE);

	return (vd->vdev_asize < (1ULL << shift));
}

/*
 * Get statistics for the given vdev.
 */
void
vdev_get_stats(vdev_t *vd, vdev_stat_t *vs)
{
	spa_t *spa = vd->vdev_spa;
	vdev_t *rvd = spa->spa_root_vdev;
	vdev_t *tvd = vd->vdev_top;

	ASSERT(spa_config_held(spa, SCL_ALL, RW_READER) != 0);

	mutex_enter(&vd->vdev_stat_lock);
	bcopy(&vd->vdev_stat, vs, sizeof (*vs));
	vs->vs_timestamp = gethrtime() - vs->vs_timestamp;
	vs->vs_state = vd->vdev_state;
	vs->vs_rsize = vdev_get_min_asize(vd);
	if (vd->vdev_ops->vdev_op_leaf) {
		vs->vs_rsize += VDEV_LABEL_START_SIZE + VDEV_LABEL_END_SIZE;
		/*
		 * Report intializing progress. Since we don't have the
		 * initializing locks held, this is only an estimate (although a
		 * fairly accurate one).
		 */
		vs->vs_initialize_bytes_done = vd->vdev_initialize_bytes_done;
		vs->vs_initialize_bytes_est = vd->vdev_initialize_bytes_est;
		vs->vs_initialize_state = vd->vdev_initialize_state;
		vs->vs_initialize_action_time = vd->vdev_initialize_action_time;
	}
	/*
	 * Report expandable space on top-level, non-auxillary devices only.
	 * The expandable space is reported in terms of metaslab sized units
	 * since that determines how much space the pool can expand.
	 */
	if (vd->vdev_aux == NULL && tvd != NULL && vd->vdev_max_asize != 0) {
		vs->vs_esize = P2ALIGN(vd->vdev_max_asize - vd->vdev_asize -
		    spa->spa_bootsize, 1ULL << tvd->vdev_ms_shift);
	}
	vs->vs_configured_ashift = vd->vdev_top != NULL
	    ? vd->vdev_top->vdev_ashift : vd->vdev_ashift;
	vs->vs_logical_ashift = vd->vdev_logical_ashift;
	vs->vs_physical_ashift = vd->vdev_physical_ashift;
	if (vd->vdev_aux == NULL && vd == vd->vdev_top &&
	    vdev_is_concrete(vd)) {
		vs->vs_fragmentation = (vd->vdev_mg != NULL) ?
		    vd->vdev_mg->mg_fragmentation : 0;
	}

	/*
	 * If we're getting stats on the root vdev, aggregate the I/O counts
	 * over all top-level vdevs (i.e. the direct children of the root).
	 */
	if (vd == rvd) {
		for (int c = 0; c < rvd->vdev_children; c++) {
			vdev_t *cvd = rvd->vdev_child[c];
			vdev_stat_t *cvs = &cvd->vdev_stat;

			for (int t = 0; t < ZIO_TYPES; t++) {
				vs->vs_ops[t] += cvs->vs_ops[t];
				vs->vs_bytes[t] += cvs->vs_bytes[t];
			}
			cvs->vs_scan_removing = cvd->vdev_removing;
		}
	}
	mutex_exit(&vd->vdev_stat_lock);
}

void
vdev_clear_stats(vdev_t *vd)
{
	mutex_enter(&vd->vdev_stat_lock);
	vd->vdev_stat.vs_space = 0;
	vd->vdev_stat.vs_dspace = 0;
	vd->vdev_stat.vs_alloc = 0;
	mutex_exit(&vd->vdev_stat_lock);
}

void
vdev_scan_stat_init(vdev_t *vd)
{
	vdev_stat_t *vs = &vd->vdev_stat;

	for (int c = 0; c < vd->vdev_children; c++)
		vdev_scan_stat_init(vd->vdev_child[c]);

	mutex_enter(&vd->vdev_stat_lock);
	vs->vs_scan_processed = 0;
	mutex_exit(&vd->vdev_stat_lock);
}

void
vdev_stat_update(zio_t *zio, uint64_t psize)
{
	spa_t *spa = zio->io_spa;
	vdev_t *rvd = spa->spa_root_vdev;
	vdev_t *vd = zio->io_vd ? zio->io_vd : rvd;
	vdev_t *pvd;
	uint64_t txg = zio->io_txg;
	vdev_stat_t *vs = &vd->vdev_stat;
	zio_type_t type = zio->io_type;
	int flags = zio->io_flags;

	/*
	 * If this i/o is a gang leader, it didn't do any actual work.
	 */
	if (zio->io_gang_tree)
		return;

	if (zio->io_error == 0) {
		/*
		 * If this is a root i/o, don't count it -- we've already
		 * counted the top-level vdevs, and vdev_get_stats() will
		 * aggregate them when asked.  This reduces contention on
		 * the root vdev_stat_lock and implicitly handles blocks
		 * that compress away to holes, for which there is no i/o.
		 * (Holes never create vdev children, so all the counters
		 * remain zero, which is what we want.)
		 *
		 * Note: this only applies to successful i/o (io_error == 0)
		 * because unlike i/o counts, errors are not additive.
		 * When reading a ditto block, for example, failure of
		 * one top-level vdev does not imply a root-level error.
		 */
		if (vd == rvd)
			return;

		ASSERT(vd == zio->io_vd);

		if (flags & ZIO_FLAG_IO_BYPASS)
			return;

		mutex_enter(&vd->vdev_stat_lock);

		if (flags & ZIO_FLAG_IO_REPAIR) {
			if (flags & ZIO_FLAG_SCAN_THREAD) {
				dsl_scan_phys_t *scn_phys =
				    &spa->spa_dsl_pool->dp_scan->scn_phys;
				uint64_t *processed = &scn_phys->scn_processed;

				/* XXX cleanup? */
				if (vd->vdev_ops->vdev_op_leaf)
					atomic_add_64(processed, psize);
				vs->vs_scan_processed += psize;
			}

			if (flags & ZIO_FLAG_SELF_HEAL)
				vs->vs_self_healed += psize;
		}

		vs->vs_ops[type]++;
		vs->vs_bytes[type] += psize;

		mutex_exit(&vd->vdev_stat_lock);
		return;
	}

	if (flags & ZIO_FLAG_SPECULATIVE)
		return;

	/*
	 * If this is an I/O error that is going to be retried, then ignore the
	 * error.  Otherwise, the user may interpret B_FAILFAST I/O errors as
	 * hard errors, when in reality they can happen for any number of
	 * innocuous reasons (bus resets, MPxIO link failure, etc).
	 */
	if (zio->io_error == EIO &&
	    !(zio->io_flags & ZIO_FLAG_IO_RETRY))
		return;

	/*
	 * Intent logs writes won't propagate their error to the root
	 * I/O so don't mark these types of failures as pool-level
	 * errors.
	 */
	if (zio->io_vd == NULL && (zio->io_flags & ZIO_FLAG_DONT_PROPAGATE))
		return;

	mutex_enter(&vd->vdev_stat_lock);
	if (type == ZIO_TYPE_READ && !vdev_is_dead(vd)) {
		if (zio->io_error == ECKSUM)
			vs->vs_checksum_errors++;
		else
			vs->vs_read_errors++;
	}
	if (type == ZIO_TYPE_WRITE && !vdev_is_dead(vd))
		vs->vs_write_errors++;
	mutex_exit(&vd->vdev_stat_lock);

	if (spa->spa_load_state == SPA_LOAD_NONE &&
	    type == ZIO_TYPE_WRITE && txg != 0 &&
	    (!(flags & ZIO_FLAG_IO_REPAIR) ||
	    (flags & ZIO_FLAG_SCAN_THREAD) ||
	    spa->spa_claiming)) {
		/*
		 * This is either a normal write (not a repair), or it's
		 * a repair induced by the scrub thread, or it's a repair
		 * made by zil_claim() during spa_load() in the first txg.
		 * In the normal case, we commit the DTL change in the same
		 * txg as the block was born.  In the scrub-induced repair
		 * case, we know that scrubs run in first-pass syncing context,
		 * so we commit the DTL change in spa_syncing_txg(spa).
		 * In the zil_claim() case, we commit in spa_first_txg(spa).
		 *
		 * We currently do not make DTL entries for failed spontaneous
		 * self-healing writes triggered by normal (non-scrubbing)
		 * reads, because we have no transactional context in which to
		 * do so -- and it's not clear that it'd be desirable anyway.
		 */
		if (vd->vdev_ops->vdev_op_leaf) {
			uint64_t commit_txg = txg;
			if (flags & ZIO_FLAG_SCAN_THREAD) {
				ASSERT(flags & ZIO_FLAG_IO_REPAIR);
				ASSERT(spa_sync_pass(spa) == 1);
				vdev_dtl_dirty(vd, DTL_SCRUB, txg, 1);
				commit_txg = spa_syncing_txg(spa);
			} else if (spa->spa_claiming) {
				ASSERT(flags & ZIO_FLAG_IO_REPAIR);
				commit_txg = spa_first_txg(spa);
			}
			ASSERT(commit_txg >= spa_syncing_txg(spa));
			if (vdev_dtl_contains(vd, DTL_MISSING, txg, 1))
				return;
			for (pvd = vd; pvd != rvd; pvd = pvd->vdev_parent)
				vdev_dtl_dirty(pvd, DTL_PARTIAL, txg, 1);
			vdev_dirty(vd->vdev_top, VDD_DTL, vd, commit_txg);
		}
		if (vd != rvd)
			vdev_dtl_dirty(vd, DTL_MISSING, txg, 1);
	}
}

int64_t
vdev_deflated_space(vdev_t *vd, int64_t space)
{
	ASSERT((space & (SPA_MINBLOCKSIZE-1)) == 0);
	ASSERT(vd->vdev_deflate_ratio != 0 || vd->vdev_isl2cache);

	return ((space >> SPA_MINBLOCKSHIFT) * vd->vdev_deflate_ratio);
}

/*
 * Update the in-core space usage stats for this vdev and the root vdev.
 */
void
vdev_space_update(vdev_t *vd, int64_t alloc_delta, int64_t defer_delta,
    int64_t space_delta)
{
	int64_t dspace_delta;
	spa_t *spa = vd->vdev_spa;
	vdev_t *rvd = spa->spa_root_vdev;

	ASSERT(vd == vd->vdev_top);

	/*
	 * Apply the inverse of the psize-to-asize (ie. RAID-Z) space-expansion
	 * factor.  We must calculate this here and not at the root vdev
	 * because the root vdev's psize-to-asize is simply the max of its
	 * childrens', thus not accurate enough for us.
	 */
	dspace_delta = vdev_deflated_space(vd, space_delta);

	mutex_enter(&vd->vdev_stat_lock);
	vd->vdev_stat.vs_alloc += alloc_delta;
	vd->vdev_stat.vs_space += space_delta;
	vd->vdev_stat.vs_dspace += dspace_delta;
	mutex_exit(&vd->vdev_stat_lock);

	/* every class but log contributes to root space stats */
	if (vd->vdev_mg != NULL && !vd->vdev_islog) {
		mutex_enter(&rvd->vdev_stat_lock);
		rvd->vdev_stat.vs_alloc += alloc_delta;
		rvd->vdev_stat.vs_space += space_delta;
		rvd->vdev_stat.vs_dspace += dspace_delta;
		mutex_exit(&rvd->vdev_stat_lock);
	}
	/* Note: metaslab_class_space_update moved to metaslab_space_update */
}

/*
 * Mark a top-level vdev's config as dirty, placing it on the dirty list
 * so that it will be written out next time the vdev configuration is synced.
 * If the root vdev is specified (vdev_top == NULL), dirty all top-level vdevs.
 */
void
vdev_config_dirty(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	vdev_t *rvd = spa->spa_root_vdev;
	int c;

	ASSERT(spa_writeable(spa));

	/*
	 * If this is an aux vdev (as with l2cache and spare devices), then we
	 * update the vdev config manually and set the sync flag.
	 */
	if (vd->vdev_aux != NULL) {
		spa_aux_vdev_t *sav = vd->vdev_aux;
		nvlist_t **aux;
		uint_t naux;

		for (c = 0; c < sav->sav_count; c++) {
			if (sav->sav_vdevs[c] == vd)
				break;
		}

		if (c == sav->sav_count) {
			/*
			 * We're being removed.  There's nothing more to do.
			 */
			ASSERT(sav->sav_sync == B_TRUE);
			return;
		}

		sav->sav_sync = B_TRUE;

		if (nvlist_lookup_nvlist_array(sav->sav_config,
		    ZPOOL_CONFIG_L2CACHE, &aux, &naux) != 0) {
			VERIFY(nvlist_lookup_nvlist_array(sav->sav_config,
			    ZPOOL_CONFIG_SPARES, &aux, &naux) == 0);
		}

		ASSERT(c < naux);

		/*
		 * Setting the nvlist in the middle if the array is a little
		 * sketchy, but it will work.
		 */
		nvlist_free(aux[c]);
		aux[c] = vdev_config_generate(spa, vd, B_TRUE, 0);

		return;
	}

	/*
	 * The dirty list is protected by the SCL_CONFIG lock.  The caller
	 * must either hold SCL_CONFIG as writer, or must be the sync thread
	 * (which holds SCL_CONFIG as reader).  There's only one sync thread,
	 * so this is sufficient to ensure mutual exclusion.
	 */
	ASSERT(spa_config_held(spa, SCL_CONFIG, RW_WRITER) ||
	    (dsl_pool_sync_context(spa_get_dsl(spa)) &&
	    spa_config_held(spa, SCL_CONFIG, RW_READER)));

	if (vd == rvd) {
		for (c = 0; c < rvd->vdev_children; c++)
			vdev_config_dirty(rvd->vdev_child[c]);
	} else {
		ASSERT(vd == vd->vdev_top);

		if (!list_link_active(&vd->vdev_config_dirty_node) &&
		    vdev_is_concrete(vd)) {
			list_insert_head(&spa->spa_config_dirty_list, vd);
		}
	}
}

void
vdev_config_clean(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;

	ASSERT(spa_config_held(spa, SCL_CONFIG, RW_WRITER) ||
	    (dsl_pool_sync_context(spa_get_dsl(spa)) &&
	    spa_config_held(spa, SCL_CONFIG, RW_READER)));

	ASSERT(list_link_active(&vd->vdev_config_dirty_node));
	list_remove(&spa->spa_config_dirty_list, vd);
}

/*
 * Mark a top-level vdev's state as dirty, so that the next pass of
 * spa_sync() can convert this into vdev_config_dirty().  We distinguish
 * the state changes from larger config changes because they require
 * much less locking, and are often needed for administrative actions.
 */
void
vdev_state_dirty(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;

	ASSERT(spa_writeable(spa));
	ASSERT(vd == vd->vdev_top);

	/*
	 * The state list is protected by the SCL_STATE lock.  The caller
	 * must either hold SCL_STATE as writer, or must be the sync thread
	 * (which holds SCL_STATE as reader).  There's only one sync thread,
	 * so this is sufficient to ensure mutual exclusion.
	 */
	ASSERT(spa_config_held(spa, SCL_STATE, RW_WRITER) ||
	    (dsl_pool_sync_context(spa_get_dsl(spa)) &&
	    spa_config_held(spa, SCL_STATE, RW_READER)));

	if (!list_link_active(&vd->vdev_state_dirty_node) &&
	    vdev_is_concrete(vd))
		list_insert_head(&spa->spa_state_dirty_list, vd);
}

void
vdev_state_clean(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;

	ASSERT(spa_config_held(spa, SCL_STATE, RW_WRITER) ||
	    (dsl_pool_sync_context(spa_get_dsl(spa)) &&
	    spa_config_held(spa, SCL_STATE, RW_READER)));

	ASSERT(list_link_active(&vd->vdev_state_dirty_node));
	list_remove(&spa->spa_state_dirty_list, vd);
}

/*
 * Propagate vdev state up from children to parent.
 */
void
vdev_propagate_state(vdev_t *vd)
{
	spa_t *spa = vd->vdev_spa;
	vdev_t *rvd = spa->spa_root_vdev;
	int degraded = 0, faulted = 0;
	int corrupted = 0;
	vdev_t *child;

	if (vd->vdev_children > 0) {
		for (int c = 0; c < vd->vdev_children; c++) {
			child = vd->vdev_child[c];

			/*
			 * Don't factor holes or indirect vdevs into the
			 * decision.
			 */
			if (!vdev_is_concrete(child))
				continue;

			if (!vdev_readable(child) ||
			    (!vdev_writeable(child) && spa_writeable(spa))) {
				/*
				 * Root special: if there is a top-level log
				 * device, treat the root vdev as if it were
				 * degraded.
				 */
				if (child->vdev_islog && vd == rvd)
					degraded++;
				else
					faulted++;
			} else if (child->vdev_state <= VDEV_STATE_DEGRADED) {
				degraded++;
			}

			if (child->vdev_stat.vs_aux == VDEV_AUX_CORRUPT_DATA)
				corrupted++;
		}

		vd->vdev_ops->vdev_op_state_change(vd, faulted, degraded);

		/*
		 * Root special: if there is a top-level vdev that cannot be
		 * opened due to corrupted metadata, then propagate the root
		 * vdev's aux state as 'corrupt' rather than 'insufficient
		 * replicas'.
		 */
		if (corrupted && vd == rvd &&
		    rvd->vdev_state == VDEV_STATE_CANT_OPEN)
			vdev_set_state(rvd, B_FALSE, VDEV_STATE_CANT_OPEN,
			    VDEV_AUX_CORRUPT_DATA);
	}

	if (vd->vdev_parent)
		vdev_propagate_state(vd->vdev_parent);
}

/*
 * Set a vdev's state.  If this is during an open, we don't update the parent
 * state, because we're in the process of opening children depth-first.
 * Otherwise, we propagate the change to the parent.
 *
 * If this routine places a device in a faulted state, an appropriate ereport is
 * generated.
 */
void
vdev_set_state(vdev_t *vd, boolean_t isopen, vdev_state_t state, vdev_aux_t aux)
{
	uint64_t save_state;
	spa_t *spa = vd->vdev_spa;

	if (state == vd->vdev_state) {
		vd->vdev_stat.vs_aux = aux;
		return;
	}

	save_state = vd->vdev_state;

	vd->vdev_state = state;
	vd->vdev_stat.vs_aux = aux;

	/*
	 * If we are setting the vdev state to anything but an open state, then
	 * always close the underlying device unless the device has requested
	 * a delayed close (i.e. we're about to remove or fault the device).
	 * Otherwise, we keep accessible but invalid devices open forever.
	 * We don't call vdev_close() itself, because that implies some extra
	 * checks (offline, etc) that we don't want here.  This is limited to
	 * leaf devices, because otherwise closing the device will affect other
	 * children.
	 */
	if (!vd->vdev_delayed_close && vdev_is_dead(vd) &&
	    vd->vdev_ops->vdev_op_leaf)
		vd->vdev_ops->vdev_op_close(vd);

	if (vd->vdev_removed &&
	    state == VDEV_STATE_CANT_OPEN &&
	    (aux == VDEV_AUX_OPEN_FAILED || vd->vdev_checkremove)) {
		/*
		 * If the previous state is set to VDEV_STATE_REMOVED, then this
		 * device was previously marked removed and someone attempted to
		 * reopen it.  If this failed due to a nonexistent device, then
		 * keep the device in the REMOVED state.  We also let this be if
		 * it is one of our special test online cases, which is only
		 * attempting to online the device and shouldn't generate an FMA
		 * fault.
		 */
		vd->vdev_state = VDEV_STATE_REMOVED;
		vd->vdev_stat.vs_aux = VDEV_AUX_NONE;
	} else if (state == VDEV_STATE_REMOVED) {
		vd->vdev_removed = B_TRUE;
	} else if (state == VDEV_STATE_CANT_OPEN) {
		/*
		 * If we fail to open a vdev during an import or recovery, we
		 * mark it as "not available", which signifies that it was
		 * never there to begin with.  Failure to open such a device
		 * is not considered an error.
		 */
		if ((spa_load_state(spa) == SPA_LOAD_IMPORT ||
		    spa_load_state(spa) == SPA_LOAD_RECOVER) &&
		    vd->vdev_ops->vdev_op_leaf)
			vd->vdev_not_present = 1;

		/*
		 * Post the appropriate ereport.  If the 'prevstate' field is
		 * set to something other than VDEV_STATE_UNKNOWN, it indicates
		 * that this is part of a vdev_reopen().  In this case, we don't
		 * want to post the ereport if the device was already in the
		 * CANT_OPEN state beforehand.
		 *
		 * If the 'checkremove' flag is set, then this is an attempt to
		 * online the device in response to an insertion event.  If we
		 * hit this case, then we have detected an insertion event for a
		 * faulted or offline device that wasn't in the removed state.
		 * In this scenario, we don't post an ereport because we are
		 * about to replace the device, or attempt an online with
		 * vdev_forcefault, which will generate the fault for us.
		 */
		if ((vd->vdev_prevstate != state || vd->vdev_forcefault) &&
		    !vd->vdev_not_present && !vd->vdev_checkremove &&
		    vd != spa->spa_root_vdev) {
			const char *class;

			switch (aux) {
			case VDEV_AUX_OPEN_FAILED:
				class = FM_EREPORT_ZFS_DEVICE_OPEN_FAILED;
				break;
			case VDEV_AUX_CORRUPT_DATA:
				class = FM_EREPORT_ZFS_DEVICE_CORRUPT_DATA;
				break;
			case VDEV_AUX_NO_REPLICAS:
				class = FM_EREPORT_ZFS_DEVICE_NO_REPLICAS;
				break;
			case VDEV_AUX_BAD_GUID_SUM:
				class = FM_EREPORT_ZFS_DEVICE_BAD_GUID_SUM;
				break;
			case VDEV_AUX_TOO_SMALL:
				class = FM_EREPORT_ZFS_DEVICE_TOO_SMALL;
				break;
			case VDEV_AUX_BAD_LABEL:
				class = FM_EREPORT_ZFS_DEVICE_BAD_LABEL;
				break;
			default:
				class = FM_EREPORT_ZFS_DEVICE_UNKNOWN;
			}

			zfs_ereport_post(class, spa, vd, NULL, save_state, 0);
		}

		/* Erase any notion of persistent removed state */
		vd->vdev_removed = B_FALSE;
	} else {
		vd->vdev_removed = B_FALSE;
	}

	/*
	* Notify the fmd of the state change.  Be verbose and post
	* notifications even for stuff that's not important; the fmd agent can
	* sort it out.  Don't emit state change events for non-leaf vdevs since
	* they can't change state on their own.  The FMD can check their state
	* if it wants to when it sees that a leaf vdev had a state change.
	*/
	if (vd->vdev_ops->vdev_op_leaf)
		zfs_post_state_change(spa, vd);

	if (!isopen && vd->vdev_parent)
		vdev_propagate_state(vd->vdev_parent);
}

boolean_t
vdev_children_are_offline(vdev_t *vd)
{
	ASSERT(!vd->vdev_ops->vdev_op_leaf);

	for (uint64_t i = 0; i < vd->vdev_children; i++) {
		if (vd->vdev_child[i]->vdev_state != VDEV_STATE_OFFLINE)
			return (B_FALSE);
	}

	return (B_TRUE);
}

/*
 * Check the vdev configuration to ensure that it's capable of supporting
 * a root pool. We do not support partial configuration.
 * In addition, only a single top-level vdev is allowed.
 *
 * FreeBSD does not have above limitations.
 */
boolean_t
vdev_is_bootable(vdev_t *vd)
{
#ifdef illumos
	if (!vd->vdev_ops->vdev_op_leaf) {
		char *vdev_type = vd->vdev_ops->vdev_op_type;

		if (strcmp(vdev_type, VDEV_TYPE_ROOT) == 0 &&
		    vd->vdev_children > 1) {
			return (B_FALSE);
		} else if (strcmp(vdev_type, VDEV_TYPE_MISSING) == 0 ||
		    strcmp(vdev_type, VDEV_TYPE_INDIRECT) == 0) {
			return (B_FALSE);
		}
	}

	for (int c = 0; c < vd->vdev_children; c++) {
		if (!vdev_is_bootable(vd->vdev_child[c]))
			return (B_FALSE);
	}
#endif	/* illumos */
	return (B_TRUE);
}

boolean_t
vdev_is_concrete(vdev_t *vd)
{
	vdev_ops_t *ops = vd->vdev_ops;
	if (ops == &vdev_indirect_ops || ops == &vdev_hole_ops ||
	    ops == &vdev_missing_ops || ops == &vdev_root_ops) {
		return (B_FALSE);
	} else {
		return (B_TRUE);
	}
}

/*
 * Determine if a log device has valid content.  If the vdev was
 * removed or faulted in the MOS config then we know that
 * the content on the log device has already been written to the pool.
 */
boolean_t
vdev_log_state_valid(vdev_t *vd)
{
	if (vd->vdev_ops->vdev_op_leaf && !vd->vdev_faulted &&
	    !vd->vdev_removed)
		return (B_TRUE);

	for (int c = 0; c < vd->vdev_children; c++)
		if (vdev_log_state_valid(vd->vdev_child[c]))
			return (B_TRUE);

	return (B_FALSE);
}

/*
 * Expand a vdev if possible.
 */
void
vdev_expand(vdev_t *vd, uint64_t txg)
{
	ASSERT(vd->vdev_top == vd);
	ASSERT(spa_config_held(vd->vdev_spa, SCL_ALL, RW_WRITER) == SCL_ALL);
	ASSERT(vdev_is_concrete(vd));

	vdev_set_deflate_ratio(vd);

	if ((vd->vdev_asize >> vd->vdev_ms_shift) > vd->vdev_ms_count &&
	    vdev_is_concrete(vd)) {
		vdev_metaslab_group_create(vd);
		VERIFY(vdev_metaslab_init(vd, txg) == 0);
		vdev_config_dirty(vd);
	}
}

/*
 * Split a vdev.
 */
void
vdev_split(vdev_t *vd)
{
	vdev_t *cvd, *pvd = vd->vdev_parent;

	vdev_remove_child(pvd, vd);
	vdev_compact_children(pvd);

	cvd = pvd->vdev_child[0];
	if (pvd->vdev_children == 1) {
		vdev_remove_parent(cvd);
		cvd->vdev_splitting = B_TRUE;
	}
	vdev_propagate_state(cvd);
}

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

		vdev_deadman(cvd);
	}

	if (vd->vdev_ops->vdev_op_leaf) {
		vdev_queue_t *vq = &vd->vdev_queue;

		mutex_enter(&vq->vq_lock);
		if (avl_numnodes(&vq->vq_active_tree) > 0) {
			spa_t *spa = vd->vdev_spa;
			zio_t *fio;
			uint64_t delta;

			/*
			 * Look at the head of all the pending queues,
			 * if any I/O has been outstanding for longer than
			 * the spa_deadman_synctime we panic the system.
			 */
			fio = avl_first(&vq->vq_active_tree);
			delta = gethrtime() - fio->io_timestamp;
			if (delta > spa_deadman_synctime(spa)) {
				vdev_dbgmsg(vd, "SLOW IO: zio timestamp "
				    "%lluns, delta %lluns, last io %lluns",
				    fio->io_timestamp, (u_longlong_t)delta,
				    vq->vq_io_complete_ts);
				fm_panic("I/O to pool '%s' appears to be "
				    "hung on vdev guid %llu at '%s'.",
				    spa_name(spa),
				    (long long unsigned int) vd->vdev_guid,
				    vd->vdev_path);
			}
		}
		mutex_exit(&vq->vq_lock);
	}
}