summaryrefslogtreecommitdiff
path: root/super1.c
blob: 87a74cb945083b7ca82e5d24293015267ac95de4 (plain)
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
/*
 * mdadm - manage Linux "md" devices aka RAID arrays.
 *
 * Copyright (C) 2001-2016 Neil Brown <neilb@suse.com>
 *
 *
 *    This program is free software; you can redistribute it and/or modify
 *    it under the terms of the GNU General Public License as published by
 *    the Free Software Foundation; either version 2 of the License, or
 *    (at your option) any later version.
 *
 *    This program is distributed in the hope that it will be useful,
 *    but WITHOUT ANY WARRANTY; without even the implied warranty of
 *    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *    GNU General Public License for more details.
 *
 *    You should have received a copy of the GNU General Public License
 *    along with this program; if not, write to the Free Software
 *    Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
 *
 *    Author: Neil Brown
 *    Email: <neilb@suse.de>
 */

#include <stddef.h>
#include "mdadm.h"
/*
 * The version-1 superblock :
 * All numeric fields are little-endian.
 *
 * total size: 256 bytes plus 2 per device.
 *  1K allows 384 devices.
 */
struct mdp_superblock_1 {
	/* constant array information - 128 bytes */
	__u32	magic;		/* MD_SB_MAGIC: 0xa92b4efc - little endian */
	__u32	major_version;	/* 1 */
	__u32	feature_map;	/* 0 for now */
	__u32	pad0;		/* always set to 0 when writing */

	__u8	set_uuid[16];	/* user-space generated. */
	char	set_name[32];	/* set and interpreted by user-space */

	__u64	ctime;		/* lo 40 bits are seconds, top 24 are microseconds or 0*/
	__u32	level;		/* -4 (multipath), -1 (linear), 0,1,4,5 */
	__u32	layout;		/* only for raid5 currently */
	__u64	size;		/* used size of component devices, in 512byte sectors */

	__u32	chunksize;	/* in 512byte sectors */
	__u32	raid_disks;
	__u32	bitmap_offset;	/* sectors after start of superblock that bitmap starts
				 * NOTE: signed, so bitmap can be before superblock
				 * only meaningful of feature_map[0] is set.
				 */

	/* These are only valid with feature bit '4' */
	__u32	new_level;	/* new level we are reshaping to		*/
	__u64	reshape_position;	/* next address in array-space for reshape */
	__u32	delta_disks;	/* change in number of raid_disks		*/
	__u32	new_layout;	/* new layout					*/
	__u32	new_chunk;	/* new chunk size (sectors)			*/
	__u32	new_offset;	/* signed number to add to data_offset in new
				 * layout.  0 == no-change.  This can be
				 * different on each device in the array.
				 */

	/* constant this-device information - 64 bytes */
	__u64	data_offset;	/* sector start of data, often 0 */
	__u64	data_size;	/* sectors in this device that can be used for data */
	__u64	super_offset;	/* sector start of this superblock */
	union {
		__u64	recovery_offset;/* sectors before this offset (from data_offset) have been recovered */
		__u64	journal_tail;/* journal tail of journal device (from data_offset) */
	};
	__u32	dev_number;	/* permanent identifier of this  device - not role in raid */
	__u32	cnt_corrected_read; /* number of read errors that were corrected by re-writing */
	__u8	device_uuid[16]; /* user-space setable, ignored by kernel */
	__u8    devflags;        /* per-device flags.  Only one defined...*/
#define WriteMostly1    1        /* mask for writemostly flag in above */
#define FailFast1	2        /* Device should get FailFast requests */
	/* bad block log.  If there are any bad blocks the feature flag is set.
	 * if offset and size are non-zero, that space is reserved and available.
	 */
	__u8	bblog_shift;	/* shift from sectors to block size for badblocklist */
	__u16	bblog_size;	/* number of sectors reserved for badblocklist */
	__u32	bblog_offset;	/* sector offset from superblock to bblog, signed */

	/* array state information - 64 bytes */
	__u64	utime;		/* 40 bits second, 24 btes microseconds */
	__u64	events;		/* incremented when superblock updated */
	__u64	resync_offset;	/* data before this offset (from data_offset) known to be in sync */
	__u32	sb_csum;	/* checksum upto dev_roles[max_dev] */
	__u32	max_dev;	/* size of dev_roles[] array to consider */
	__u8	pad3[64-32];	/* set to 0 when writing */

	/* device state information. Indexed by dev_number.
	 * 2 bytes per device
	 * Note there are no per-device state flags. State information is rolled
	 * into the 'roles' value.  If a device is spare or faulty, then it doesn't
	 * have a meaningful role.
	 */
	__u16	dev_roles[0];	/* role in array, or 0xffff for a spare, or 0xfffe for faulty */
};

#define MAX_SB_SIZE 4096
/* bitmap super size is 256, but we round up to a sector for alignment */
#define BM_SUPER_SIZE 512
#define MAX_DEVS ((int)(MAX_SB_SIZE - sizeof(struct mdp_superblock_1)) / 2)
#define SUPER1_SIZE	(MAX_SB_SIZE + BM_SUPER_SIZE \
			 + sizeof(struct misc_dev_info))

struct misc_dev_info {
	__u64 device_size;
};

/* feature_map bits */
#define MD_FEATURE_BITMAP_OFFSET	1
#define	MD_FEATURE_RECOVERY_OFFSET	2 /* recovery_offset is present and
					   * must be honoured
					   */
#define	MD_FEATURE_RESHAPE_ACTIVE	4
#define	MD_FEATURE_BAD_BLOCKS		8 /* badblock list is not empty */
#define	MD_FEATURE_REPLACEMENT		16 /* This device is replacing an
					    * active device with same 'role'.
					    * 'recovery_offset' is also set.
					    */
#define	MD_FEATURE_RESHAPE_BACKWARDS	32 /* Reshape doesn't change number
					    * of devices, but is going
					    * backwards anyway.
					    */
#define	MD_FEATURE_NEW_OFFSET		64 /* new_offset must be honoured */
#define	MD_FEATURE_BITMAP_VERSIONED	256 /* bitmap version number checked properly */
#define	MD_FEATURE_JOURNAL		512 /* support write journal */
#define	MD_FEATURE_ALL			(MD_FEATURE_BITMAP_OFFSET	\
					|MD_FEATURE_RECOVERY_OFFSET	\
					|MD_FEATURE_RESHAPE_ACTIVE	\
					|MD_FEATURE_BAD_BLOCKS		\
					|MD_FEATURE_REPLACEMENT		\
					|MD_FEATURE_RESHAPE_BACKWARDS	\
					|MD_FEATURE_NEW_OFFSET		\
					|MD_FEATURE_BITMAP_VERSIONED	\
					|MD_FEATURE_JOURNAL		\
					)

#ifndef MDASSEMBLE
static int role_from_sb(struct mdp_superblock_1 *sb)
{
	unsigned int d;
	int role;

	d = __le32_to_cpu(sb->dev_number);
	if (d < __le32_to_cpu(sb->max_dev))
		role = __le16_to_cpu(sb->dev_roles[d]);
	else
		role = MD_DISK_ROLE_SPARE;
	return role;
}
#endif

/* return how many bytes are needed for bitmap, for cluster-md each node
 * should have it's own bitmap */
static unsigned int calc_bitmap_size(bitmap_super_t *bms, unsigned int boundary)
{
	unsigned long long bits, bytes;

	bits = bitmap_bits(__le64_to_cpu(bms->sync_size),
			   __le32_to_cpu(bms->chunksize));
	bytes = (bits+7) >> 3;
	bytes += sizeof(bitmap_super_t);
	bytes = ROUND_UP(bytes, boundary);

	return bytes;
}

static unsigned int calc_sb_1_csum(struct mdp_superblock_1 * sb)
{
	unsigned int disk_csum, csum;
	unsigned long long newcsum;
	int size = sizeof(*sb) + __le32_to_cpu(sb->max_dev)*2;
	unsigned int *isuper = (unsigned int*)sb;

/* make sure I can count... */
	if (offsetof(struct mdp_superblock_1,data_offset) != 128 ||
	    offsetof(struct mdp_superblock_1, utime) != 192 ||
	    sizeof(struct mdp_superblock_1) != 256) {
		fprintf(stderr, "WARNING - superblock isn't sized correctly\n");
	}

	disk_csum = sb->sb_csum;
	sb->sb_csum = 0;
	newcsum = 0;
	for (; size>=4; size -= 4 ) {
		newcsum += __le32_to_cpu(*isuper);
		isuper++;
	}

	if (size == 2)
		newcsum += __le16_to_cpu(*(unsigned short*) isuper);

	csum = (newcsum & 0xffffffff) + (newcsum >> 32);
	sb->sb_csum = disk_csum;
	return __cpu_to_le32(csum);
}

/*
 * Information related to file descriptor used for aligned reads/writes.
 * Cache the block size.
 */
struct align_fd {
	int fd;
	int blk_sz;
};

static void init_afd(struct align_fd *afd, int fd)
{
	afd->fd = fd;
	if (!get_dev_sector_size(afd->fd, NULL, (unsigned int *)&afd->blk_sz))
		afd->blk_sz = 512;
}

static char abuf[4096+4096];
static int aread(struct align_fd *afd, void *buf, int len)
{
	/* aligned read.
	 * On devices with a 4K sector size, we need to read
	 * the full sector and copy relevant bits into
	 * the buffer
	 */
	int bsize, iosize;
	char *b;
	int n;

	bsize = afd->blk_sz;

	if (!bsize || bsize > 4096 || len > 4096) {
		if (!bsize)
			fprintf(stderr, "WARNING - aread() called with invalid block size\n");
		return -1;
	}
	b = ROUND_UP_PTR((char *)abuf, 4096);

	for (iosize = 0; iosize < len; iosize += bsize)
		;
	n = read(afd->fd, b, iosize);
	if (n <= 0)
		return n;
	lseek(afd->fd, len - n, 1);
	if (n > len)
		n = len;
	memcpy(buf, b, n);
	return n;
}

static int awrite(struct align_fd *afd, void *buf, int len)
{
	/* aligned write.
	 * On devices with a 4K sector size, we need to write
	 * the full sector.  We pre-read if the sector is larger
	 * than the write.
	 * The address must be sector-aligned.
	 */
	int bsize, iosize;
	char *b;
	int n;

	bsize = afd->blk_sz;
	if (!bsize || bsize > 4096 || len > 4096) {
		if (!bsize)
			fprintf(stderr, "WARNING - awrite() called with invalid block size\n");
		return -1;
	}
	b = ROUND_UP_PTR((char *)abuf, 4096);

	for (iosize = 0; iosize < len ; iosize += bsize)
		;

	if (len != iosize) {
		n = read(afd->fd, b, iosize);
		if (n <= 0)
			return n;
		lseek(afd->fd, -n, 1);
	}

	memcpy(b, buf, len);
	n = write(afd->fd, b, iosize);
	if (n <= 0)
		return n;
	lseek(afd->fd, len - n, 1);
	return len;
}

#ifndef MDASSEMBLE
static void examine_super1(struct supertype *st, char *homehost)
{
	struct mdp_superblock_1 *sb = st->sb;
	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb)+MAX_SB_SIZE);
	time_t atime;
	unsigned int d;
	int role;
	int delta_extra = 0;
	int i;
	char *c;
	int l = homehost ? strlen(homehost) : 0;
	int layout;
	unsigned long long sb_offset;
	struct mdinfo info;

	printf("          Magic : %08x\n", __le32_to_cpu(sb->magic));
	printf("        Version : 1");
	sb_offset = __le64_to_cpu(sb->super_offset);
	if (sb_offset <= 4)
		printf(".1\n");
	else if (sb_offset <= 8)
		printf(".2\n");
	else
		printf(".0\n");
	printf("    Feature Map : 0x%x\n", __le32_to_cpu(sb->feature_map));
	printf("     Array UUID : ");
	for (i=0; i<16; i++) {
		if ((i&3)==0 && i != 0) printf(":");
		printf("%02x", sb->set_uuid[i]);
	}
	printf("\n");
	printf("           Name : %.32s", sb->set_name);
	if (l > 0 && l < 32 &&
	    sb->set_name[l] == ':' &&
	    strncmp(sb->set_name, homehost, l) == 0)
		printf("  (local to host %s)", homehost);
	printf("\n");
	if (bms->nodes > 0 && (__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET))
		printf("   Cluster Name : %-64s\n", bms->cluster_name);
	atime = __le64_to_cpu(sb->ctime) & 0xFFFFFFFFFFULL;
	printf("  Creation Time : %.24s\n", ctime(&atime));
	c=map_num(pers, __le32_to_cpu(sb->level));
	printf("     Raid Level : %s\n", c?c:"-unknown-");
	printf("   Raid Devices : %d\n", __le32_to_cpu(sb->raid_disks));
	printf("\n");
	printf(" Avail Dev Size : %llu%s\n",
	       (unsigned long long)__le64_to_cpu(sb->data_size),
	       human_size(__le64_to_cpu(sb->data_size)<<9));
	if (__le32_to_cpu(sb->level) > 0) {
		int ddsks = 0, ddsks_denom = 1;
		switch(__le32_to_cpu(sb->level)) {
		case 1: ddsks=1;break;
		case 4:
		case 5: ddsks = __le32_to_cpu(sb->raid_disks)-1; break;
		case 6: ddsks = __le32_to_cpu(sb->raid_disks)-2; break;
		case 10:
			layout = __le32_to_cpu(sb->layout);
			ddsks = __le32_to_cpu(sb->raid_disks);
			ddsks_denom = (layout&255) * ((layout>>8)&255);
		}
		if (ddsks) {
			long long asize = __le64_to_cpu(sb->size);
			asize = (asize << 9) * ddsks / ddsks_denom;
			printf("     Array Size : %llu%s\n",
			       asize >> 10,  human_size(asize));
		}
		if (sb->size != sb->data_size)
			printf("  Used Dev Size : %llu%s\n",
			       (unsigned long long)__le64_to_cpu(sb->size),
			       human_size(__le64_to_cpu(sb->size)<<9));
	}
	if (sb->data_offset)
		printf("    Data Offset : %llu sectors\n",
		       (unsigned long long)__le64_to_cpu(sb->data_offset));
	if (sb->new_offset &&
	    (__le32_to_cpu(sb->feature_map) & MD_FEATURE_NEW_OFFSET)) {
		unsigned long long offset = __le64_to_cpu(sb->data_offset);
		offset += (signed)(int32_t)__le32_to_cpu(sb->new_offset);
		printf("     New Offset : %llu sectors\n", offset);
	}
	printf("   Super Offset : %llu sectors\n",
	       (unsigned long long)__le64_to_cpu(sb->super_offset));
	if (__le32_to_cpu(sb->feature_map) & MD_FEATURE_RECOVERY_OFFSET)
		printf("Recovery Offset : %llu sectors\n", (unsigned long long)__le64_to_cpu(sb->recovery_offset));

	st->ss->getinfo_super(st, &info, NULL);
	if (info.space_after != 1 &&
	    !(__le32_to_cpu(sb->feature_map) & MD_FEATURE_NEW_OFFSET))
		printf("   Unused Space : before=%llu sectors, after=%llu sectors\n",
		       info.space_before, info.space_after);

	printf("          State : %s\n", (__le64_to_cpu(sb->resync_offset)+1)? "active":"clean");
	printf("    Device UUID : ");
	for (i=0; i<16; i++) {
		if ((i&3)==0 && i != 0) printf(":");
		printf("%02x", sb->device_uuid[i]);
	}
	printf("\n");
	printf("\n");
	if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
		printf("Internal Bitmap : %ld sectors from superblock\n",
		       (long)(int32_t)__le32_to_cpu(sb->bitmap_offset));
	}
	if (sb->feature_map & __cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE)) {
		printf("  Reshape pos'n : %llu%s\n", (unsigned long long)__le64_to_cpu(sb->reshape_position)/2,
		       human_size(__le64_to_cpu(sb->reshape_position)<<9));
		if (__le32_to_cpu(sb->delta_disks)) {
			printf("  Delta Devices : %d", __le32_to_cpu(sb->delta_disks));
			printf(" (%d->%d)\n",
			       __le32_to_cpu(sb->raid_disks)-__le32_to_cpu(sb->delta_disks),
			       __le32_to_cpu(sb->raid_disks));
			if ((int)__le32_to_cpu(sb->delta_disks) < 0)
				delta_extra = -__le32_to_cpu(sb->delta_disks);
		}
		if (__le32_to_cpu(sb->new_level) != __le32_to_cpu(sb->level)) {
			c = map_num(pers, __le32_to_cpu(sb->new_level));
			printf("      New Level : %s\n", c?c:"-unknown-");
		}
		if (__le32_to_cpu(sb->new_layout) != __le32_to_cpu(sb->layout)) {
			if (__le32_to_cpu(sb->level) == 5) {
				c = map_num(r5layout, __le32_to_cpu(sb->new_layout));
				printf("     New Layout : %s\n", c?c:"-unknown-");
			}
			if (__le32_to_cpu(sb->level) == 6) {
				c = map_num(r6layout, __le32_to_cpu(sb->new_layout));
				printf("     New Layout : %s\n", c?c:"-unknown-");
			}
			if (__le32_to_cpu(sb->level) == 10) {
				printf("     New Layout :");
				print_r10_layout(__le32_to_cpu(sb->new_layout));
				printf("\n");
			}
		}
		if (__le32_to_cpu(sb->new_chunk) != __le32_to_cpu(sb->chunksize))
			printf("  New Chunksize : %dK\n", __le32_to_cpu(sb->new_chunk)/2);
		printf("\n");
	}
	if (sb->devflags) {
		printf("          Flags :");
		if (sb->devflags & WriteMostly1)
			printf(" write-mostly");
		if (sb->devflags & FailFast1)
			printf(" failfast");
		printf("\n");
	}

	atime = __le64_to_cpu(sb->utime) & 0xFFFFFFFFFFULL;
	printf("    Update Time : %.24s\n", ctime(&atime));

	if (sb->bblog_size && sb->bblog_offset) {
		printf("  Bad Block Log : %d entries available at offset %ld sectors",
		       __le16_to_cpu(sb->bblog_size)*512/8,
		       (long)(int32_t)__le32_to_cpu(sb->bblog_offset));
		if (sb->feature_map &
		    __cpu_to_le32(MD_FEATURE_BAD_BLOCKS))
			printf(" - bad blocks present.");
		printf("\n");
	}

	if (calc_sb_1_csum(sb) == sb->sb_csum)
		printf("       Checksum : %x - correct\n", __le32_to_cpu(sb->sb_csum));
	else
		printf("       Checksum : %x - expected %x\n", __le32_to_cpu(sb->sb_csum),
		       __le32_to_cpu(calc_sb_1_csum(sb)));
	printf("         Events : %llu\n", (unsigned long long)__le64_to_cpu(sb->events));
	printf("\n");
	if (__le32_to_cpu(sb->level) == 5) {
		c = map_num(r5layout, __le32_to_cpu(sb->layout));
		printf("         Layout : %s\n", c?c:"-unknown-");
	}
	if (__le32_to_cpu(sb->level) == 6) {
		c = map_num(r6layout, __le32_to_cpu(sb->layout));
		printf("         Layout : %s\n", c?c:"-unknown-");
	}
	if (__le32_to_cpu(sb->level) == 10) {
		int lo = __le32_to_cpu(sb->layout);
		printf("         Layout :");
		print_r10_layout(lo);
		printf("\n");
	}
	switch(__le32_to_cpu(sb->level)) {
	case 0:
	case 4:
	case 5:
	case 6:
	case 10:
		printf("     Chunk Size : %dK\n", __le32_to_cpu(sb->chunksize)/2);
		break;
	case -1:
		printf("       Rounding : %dK\n", __le32_to_cpu(sb->chunksize)/2);
		break;
	default: break;
	}
	printf("\n");
#if 0
	/* This turns out to just be confusing */
	printf("    Array Slot : %d (", __le32_to_cpu(sb->dev_number));
	for (i= __le32_to_cpu(sb->max_dev); i> 0 ; i--)
		if (__le16_to_cpu(sb->dev_roles[i-1]) != MD_DISK_ROLE_SPARE)
			break;
	for (d=0; d < i; d++) {
		int role = __le16_to_cpu(sb->dev_roles[d]);
		if (d) printf(", ");
		if (role == MD_DISK_ROLE_SPARE) printf("empty");
		else if(role == MD_DISK_ROLE_FAULTY) printf("failed");
		else printf("%d", role);
	}
	printf(")\n");
#endif
	printf("   Device Role : ");
	role = role_from_sb(sb);
	if (role >= MD_DISK_ROLE_FAULTY)
		printf("spare\n");
	else if (role == MD_DISK_ROLE_JOURNAL)
		printf("Journal\n");
	else if (sb->feature_map & __cpu_to_le32(MD_FEATURE_REPLACEMENT))
		printf("Replacement device %d\n", role);
	else
		printf("Active device %d\n", role);

	printf("   Array State : ");
	for (d=0; d<__le32_to_cpu(sb->raid_disks) + delta_extra; d++) {
		int cnt = 0;
		unsigned int i;
		for (i=0; i< __le32_to_cpu(sb->max_dev); i++) {
			unsigned int role = __le16_to_cpu(sb->dev_roles[i]);
			if (role == d)
				cnt++;
		}
		if (cnt == 2)
			printf("R");
		else if (cnt == 1)
			printf("A");
		else if (cnt == 0)
			printf(".");
		else
			printf("?");
	}
#if 0
	/* This is confusing too */
	faulty = 0;
	for (i=0; i< __le32_to_cpu(sb->max_dev); i++) {
		int role = __le16_to_cpu(sb->dev_roles[i]);
		if (role == MD_DISK_ROLE_FAULTY)
			faulty++;
	}
	if (faulty) printf(" %d failed", faulty);
#endif
	printf(" ('A' == active, '.' == missing, 'R' == replacing)");
	printf("\n");
}

static void brief_examine_super1(struct supertype *st, int verbose)
{
	struct mdp_superblock_1 *sb = st->sb;
	int i;
	unsigned long long sb_offset;
	char *nm;
	char *c=map_num(pers, __le32_to_cpu(sb->level));

	nm = strchr(sb->set_name, ':');
	if (nm)
		nm++;
	else if (sb->set_name[0])
		nm = sb->set_name;
	else
		nm = NULL;

	printf("ARRAY ");
	if (nm) {
		printf("/dev/md/");
		print_escape(nm);
		putchar(' ');
	}
	if (verbose && c)
		printf(" level=%s", c);
	sb_offset = __le64_to_cpu(sb->super_offset);
	if (sb_offset <= 4)
		printf(" metadata=1.1 ");
	else if (sb_offset <= 8)
		printf(" metadata=1.2 ");
	else
		printf(" metadata=1.0 ");
	if (verbose)
		printf("num-devices=%d ", __le32_to_cpu(sb->raid_disks));
	printf("UUID=");
	for (i=0; i<16; i++) {
		if ((i&3)==0 && i != 0) printf(":");
		printf("%02x", sb->set_uuid[i]);
	}
	if (sb->set_name[0]) {
		printf(" name=");
		print_quoted(sb->set_name);
	}
	printf("\n");
}

static void export_examine_super1(struct supertype *st)
{
	struct mdp_superblock_1 *sb = st->sb;
	int i;
	int len = 32;
	int layout;

	printf("MD_LEVEL=%s\n", map_num(pers, __le32_to_cpu(sb->level)));
	printf("MD_DEVICES=%d\n", __le32_to_cpu(sb->raid_disks));
	for (i=0; i<32; i++)
		if (sb->set_name[i] == '\n' ||
		    sb->set_name[i] == '\0') {
			len = i;
			break;
		}
	if (len)
		printf("MD_NAME=%.*s\n", len, sb->set_name);
	if (__le32_to_cpu(sb->level) > 0) {
		int ddsks = 0, ddsks_denom = 1;
		switch(__le32_to_cpu(sb->level)) {
			case 1: ddsks=1;break;
			case 4:
			case 5: ddsks = __le32_to_cpu(sb->raid_disks)-1; break;
			case 6: ddsks = __le32_to_cpu(sb->raid_disks)-2; break;
			case 10:
				layout = __le32_to_cpu(sb->layout);
				ddsks = __le32_to_cpu(sb->raid_disks);
				ddsks_denom = (layout&255) * ((layout>>8)&255);
			}
		if (ddsks) {
			long long asize = __le64_to_cpu(sb->size);
			asize = (asize << 9) * ddsks / ddsks_denom;
			printf("MD_ARRAY_SIZE=%s\n",human_size_brief(asize,JEDEC));
		}
	}
	printf("MD_UUID=");
	for (i=0; i<16; i++) {
		if ((i&3)==0 && i != 0) printf(":");
		printf("%02x", sb->set_uuid[i]);
	}
	printf("\n");
	printf("MD_UPDATE_TIME=%llu\n",
	       __le64_to_cpu(sb->utime) & 0xFFFFFFFFFFULL);
	printf("MD_DEV_UUID=");
	for (i=0; i<16; i++) {
		if ((i&3)==0 && i != 0) printf(":");
		printf("%02x", sb->device_uuid[i]);
	}
	printf("\n");
	printf("MD_EVENTS=%llu\n",
	       (unsigned long long)__le64_to_cpu(sb->events));
}

static int copy_metadata1(struct supertype *st, int from, int to)
{
	/* Read superblock.  If it looks good, write it out.
	 * Then if a bitmap is present, copy that.
	 * And if a bad-block-list is present, copy that too.
	 */
	void *buf;
	unsigned long long dsize, sb_offset;
	const int bufsize = 4*1024;
	struct mdp_superblock_1 super, *sb;

	if (posix_memalign(&buf, 4096, bufsize) != 0)
		return 1;

	if (!get_dev_size(from, NULL, &dsize))
		goto err;

	dsize >>= 9;
	if (dsize < 24)
		goto err;
	switch(st->minor_version) {
	case 0:
		sb_offset = dsize;
		sb_offset -= 8*2;
		sb_offset &= ~(4*2-1);
		break;
	case 1:
		sb_offset = 0;
		break;
	case 2:
		sb_offset = 4*2;
		break;
	default:
		goto err;
	}

	if (lseek64(from, sb_offset << 9, 0) < 0LL)
		goto err;
	if (read(from, buf, bufsize) != bufsize)
		goto err;

	sb = buf;
	super = *sb; // save most of sb for when we reuse buf

	if (__le32_to_cpu(super.magic) != MD_SB_MAGIC ||
	    __le32_to_cpu(super.major_version) != 1 ||
	    __le64_to_cpu(super.super_offset) != sb_offset ||
	    calc_sb_1_csum(sb) != super.sb_csum)
		goto err;

	if (lseek64(to, sb_offset << 9, 0) < 0LL)
		goto err;
	if (write(to, buf, bufsize) != bufsize)
		goto err;

	if (super.feature_map & __le32_to_cpu(MD_FEATURE_BITMAP_OFFSET)) {
		unsigned long long bitmap_offset = sb_offset;
		int bytes = 4096; // just an estimate.
		int written = 0;
		struct align_fd afrom, ato;

		init_afd(&afrom, from);
		init_afd(&ato, to);

		bitmap_offset += (int32_t)__le32_to_cpu(super.bitmap_offset);

		if (lseek64(from, bitmap_offset<<9, 0) < 0)
			goto err;
		if (lseek64(to, bitmap_offset<<9, 0) < 0)
			goto err;

		for (written = 0; written < bytes ; ) {
			int n = bytes - written;
			if (n > 4096)
				n = 4096;
			if (aread(&afrom, buf, n) != n)
				goto err;
			if (written == 0) {
				/* have the header, can calculate
				 * correct bitmap bytes */
				bitmap_super_t *bms;
				bms = (void*)buf;
				bytes = calc_bitmap_size(bms, 512);
				if (n > bytes)
					n =  bytes;
			}
			if (awrite(&ato, buf, n) != n)
				goto err;
			written += n;
		}
	}

	if (super.bblog_size != 0 &&
	    __le16_to_cpu(super.bblog_size) <= 100 &&
	    super.bblog_offset != 0 &&
	    (super.feature_map & __le32_to_cpu(MD_FEATURE_BAD_BLOCKS))) {
		/* There is a bad block log */
		unsigned long long bb_offset = sb_offset;
		int bytes = __le16_to_cpu(super.bblog_size) * 512;
		int written = 0;
		struct align_fd afrom, ato;

		init_afd(&afrom, from);
		init_afd(&ato, to);

		bb_offset += (int32_t)__le32_to_cpu(super.bblog_offset);

		if (lseek64(from, bb_offset<<9, 0) < 0)
			goto err;
		if (lseek64(to, bb_offset<<9, 0) < 0)
			goto err;

		for (written = 0; written < bytes ; ) {
			int n = bytes - written;
			if (n > 4096)
				n = 4096;
			if (aread(&afrom, buf, n) != n)
				goto err;

			if (awrite(&ato, buf, n) != n)
				goto err;
			written += n;
		}
	}

	free(buf);
	return 0;

err:
	free(buf);
	return 1;
}

static void detail_super1(struct supertype *st, char *homehost)
{
	struct mdp_superblock_1 *sb = st->sb;
	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
	int i;
	int l = homehost ? strlen(homehost) : 0;

	printf("           Name : %.32s", sb->set_name);
	if (l > 0 && l < 32 &&
	    sb->set_name[l] == ':' &&
	    strncmp(sb->set_name, homehost, l) == 0)
		printf("  (local to host %s)", homehost);
	if (bms->nodes > 0 && (__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET))
	    printf("\n   Cluster Name : %-64s", bms->cluster_name);
	printf("\n           UUID : ");
	for (i=0; i<16; i++) {
		if ((i&3)==0 && i != 0) printf(":");
		printf("%02x", sb->set_uuid[i]);
	}
	printf("\n         Events : %llu\n\n", (unsigned long long)__le64_to_cpu(sb->events));
}

static void brief_detail_super1(struct supertype *st)
{
	struct mdp_superblock_1 *sb = st->sb;
	int i;

	if (sb->set_name[0]) {
		printf(" name=");
		print_quoted(sb->set_name);
	}
	printf(" UUID=");
	for (i=0; i<16; i++) {
		if ((i&3)==0 && i != 0) printf(":");
		printf("%02x", sb->set_uuid[i]);
	}
}

static void export_detail_super1(struct supertype *st)
{
	struct mdp_superblock_1 *sb = st->sb;
	int i;
	int len = 32;

	for (i=0; i<32; i++)
		if (sb->set_name[i] == '\n' ||
		    sb->set_name[i] == '\0') {
			len = i;
			break;
		}
	if (len)
		printf("MD_NAME=%.*s\n", len, sb->set_name);
}

static int examine_badblocks_super1(struct supertype *st, int fd, char *devname)
{
	struct mdp_superblock_1 *sb = st->sb;
	unsigned long long offset;
	int size;
	__u64 *bbl, *bbp;
	int i;

	if  (!sb->bblog_size || __le16_to_cpu(sb->bblog_size) > 100
	     || !sb->bblog_offset){
		printf("No bad-blocks list configured on %s\n", devname);
		return 0;
	}
	if ((sb->feature_map & __cpu_to_le32(MD_FEATURE_BAD_BLOCKS))
	    == 0) {
		printf("Bad-blocks list is empty in %s\n", devname);
		return 0;
	}

	size = __le16_to_cpu(sb->bblog_size)* 512;
	if (posix_memalign((void**)&bbl, 4096, size) != 0) {
		pr_err("could not allocate badblocks list\n");
		return 0;
	}
	offset = __le64_to_cpu(sb->super_offset) +
		(int)__le32_to_cpu(sb->bblog_offset);
	offset <<= 9;
	if (lseek64(fd, offset, 0) < 0) {
		pr_err("Cannot seek to bad-blocks list\n");
		return 1;
	}
	if (read(fd, bbl, size) != size) {
		pr_err("Cannot read bad-blocks list\n");
		return 1;
	}
	/* 64bits per entry. 10 bits is block-count, 54 bits is block
	 * offset.  Blocks are sectors unless bblog->shift makes them bigger
	 */
	bbp = (__u64*)bbl;
	printf("Bad-blocks on %s:\n", devname);
	for (i = 0; i < size/8; i++, bbp++) {
		__u64 bb = __le64_to_cpu(*bbp);
		int count = bb & 0x3ff;
		unsigned long long sector = bb >> 10;

		if (bb + 1 == 0)
			break;

		sector <<= sb->bblog_shift;
		count <<= sb->bblog_shift;

		printf("%20llu for %d sectors\n", sector, count);
	}
	return 0;
}

#endif

static int match_home1(struct supertype *st, char *homehost)
{
	struct mdp_superblock_1 *sb = st->sb;
	int l = homehost ? strlen(homehost) : 0;

	return (l > 0 && l < 32 &&
		sb->set_name[l] == ':' &&
		strncmp(sb->set_name, homehost, l) == 0);
}

static void uuid_from_super1(struct supertype *st, int uuid[4])
{
	struct mdp_superblock_1 *super = st->sb;
	char *cuuid = (char*)uuid;
	int i;
	for (i=0; i<16; i++)
		cuuid[i] = super->set_uuid[i];
}

static void getinfo_super1(struct supertype *st, struct mdinfo *info, char *map)
{
	struct mdp_superblock_1 *sb = st->sb;
	struct bitmap_super_s *bsb = (void*)(((char*)sb)+MAX_SB_SIZE);
	struct misc_dev_info *misc = (void*)(((char*)sb)+MAX_SB_SIZE+BM_SUPER_SIZE);
	int working = 0;
	unsigned int i;
	unsigned int role;
	unsigned int map_disks = info->array.raid_disks;
	unsigned long long super_offset;
	unsigned long long data_size;

	memset(info, 0, sizeof(*info));
	info->array.major_version = 1;
	info->array.minor_version = st->minor_version;
	info->array.patch_version = 0;
	info->array.raid_disks = __le32_to_cpu(sb->raid_disks);
	info->array.level = __le32_to_cpu(sb->level);
	info->array.layout = __le32_to_cpu(sb->layout);
	info->array.md_minor = -1;
	info->array.ctime = __le64_to_cpu(sb->ctime);
	info->array.utime = __le64_to_cpu(sb->utime);
	info->array.chunk_size = __le32_to_cpu(sb->chunksize)*512;
	info->array.state =
		(__le64_to_cpu(sb->resync_offset) == MaxSector)
		? 1 : 0;
	if (__le32_to_cpu(bsb->nodes) > 1)
		info->array.state |= (1 << MD_SB_CLUSTERED);

	info->data_offset = __le64_to_cpu(sb->data_offset);
	info->component_size = __le64_to_cpu(sb->size);
	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_BITMAP_OFFSET))
		info->bitmap_offset = (int32_t)__le32_to_cpu(sb->bitmap_offset);

	info->disk.major = 0;
	info->disk.minor = 0;
	info->disk.number = __le32_to_cpu(sb->dev_number);
	if (__le32_to_cpu(sb->dev_number) >= __le32_to_cpu(sb->max_dev) ||
	    __le32_to_cpu(sb->dev_number) >= MAX_DEVS)
		role = MD_DISK_ROLE_FAULTY;
	else
		role = __le16_to_cpu(sb->dev_roles[__le32_to_cpu(sb->dev_number)]);

	super_offset = __le64_to_cpu(sb->super_offset);
	if (info->array.level <= 0)
		data_size = __le64_to_cpu(sb->data_size);
	else
		data_size = __le64_to_cpu(sb->size);
	if (info->data_offset < super_offset) {
		unsigned long long end;
		info->space_before = info->data_offset;
		end = super_offset;

		if (sb->bblog_offset && sb->bblog_size) {
			unsigned long long bboffset = super_offset;
			bboffset += (int32_t)__le32_to_cpu(sb->bblog_offset);
			if (bboffset < end)
				end = bboffset;
		}

		if (super_offset + info->bitmap_offset < end)
			end = super_offset + info->bitmap_offset;

		if (info->data_offset + data_size < end)
			info->space_after = end - data_size - info->data_offset;
		else
			info->space_after = 0;
	} else {
		unsigned long long earliest;
		earliest = super_offset + (32+4)*2; /* match kernel */
		if (info->bitmap_offset > 0) {
			unsigned long long bmend = info->bitmap_offset;
			unsigned long long size = calc_bitmap_size(bsb, 4096);
			size /= 512;
			bmend += size;
			if (bmend > earliest)
				earliest = bmend;
		}
		if (sb->bblog_offset && sb->bblog_size) {
			unsigned long long bbend = super_offset;
			bbend += (int32_t)__le32_to_cpu(sb->bblog_offset);
			bbend += __le16_to_cpu(sb->bblog_size);
			if (bbend > earliest)
				earliest = bbend;
		}
		if (earliest < info->data_offset)
			info->space_before = info->data_offset - earliest;
		else
			info->space_before = 0;
		info->space_after = misc->device_size - data_size - info->data_offset;
	}
	if (info->space_before == 0 && info->space_after == 0) {
		/* It will look like we don't support data_offset changes,
		 * be we do - it's just that there is no room.
		 * A change that reduced the number of devices should
		 * still be allowed, so set the otherwise useless value of '1'
		 */
		info->space_after = 1;
	}

	info->disk.raid_disk = -1;
	switch(role) {
	case MD_DISK_ROLE_SPARE:
		info->disk.state = 0; /* spare: not active, not sync, not faulty */
		break;
	case MD_DISK_ROLE_FAULTY:
		info->disk.state = 1; /* faulty */
		break;
	case MD_DISK_ROLE_JOURNAL:
		info->disk.state = (1 << MD_DISK_JOURNAL);
		info->disk.raid_disk = role;
		info->space_after = (misc->device_size - info->data_offset) % 8; /* journal uses all 4kB blocks*/
		break;
	default:
		info->disk.state = 6; /* active and in sync */
		info->disk.raid_disk = role;
	}
	if (sb->devflags & WriteMostly1)
		info->disk.state |= (1 << MD_DISK_WRITEMOSTLY);
	if (sb->devflags & FailFast1)
		info->disk.state |= (1 << MD_DISK_FAILFAST);
	info->events = __le64_to_cpu(sb->events);
	sprintf(info->text_version, "1.%d", st->minor_version);
	info->safe_mode_delay = 200;

	memcpy(info->uuid, sb->set_uuid, 16);

	strncpy(info->name, sb->set_name, 32);
	info->name[32] = 0;

	if ((__le32_to_cpu(sb->feature_map)&MD_FEATURE_REPLACEMENT)) {
		info->disk.state &= ~(1 << MD_DISK_SYNC);
		info->disk.state |=  1 << MD_DISK_REPLACEMENT;
	}

	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_RECOVERY_OFFSET))
		info->recovery_start = __le32_to_cpu(sb->recovery_offset);
	else
		info->recovery_start = MaxSector;

	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_RESHAPE_ACTIVE)) {
		info->reshape_active = 1;
		if ((sb->feature_map & __le32_to_cpu(MD_FEATURE_NEW_OFFSET)) &&
		    sb->new_offset != 0)
			info->reshape_active |= RESHAPE_NO_BACKUP;
		info->reshape_progress = __le64_to_cpu(sb->reshape_position);
		info->new_level = __le32_to_cpu(sb->new_level);
		info->delta_disks = __le32_to_cpu(sb->delta_disks);
		info->new_layout = __le32_to_cpu(sb->new_layout);
		info->new_chunk = __le32_to_cpu(sb->new_chunk)<<9;
		if (info->delta_disks < 0)
			info->array.raid_disks -= info->delta_disks;
	} else
		info->reshape_active = 0;

	info->recovery_blocked = info->reshape_active;

	if (map)
		for (i=0; i<map_disks; i++)
			map[i] = 0;
	for (i = 0; i < __le32_to_cpu(sb->max_dev); i++) {
		role = __le16_to_cpu(sb->dev_roles[i]);
		if (/*role == MD_DISK_ROLE_SPARE || */role < (unsigned) info->array.raid_disks) {
			working++;
			if (map && role < map_disks)
				map[role] = 1;
		}
	}

	info->array.working_disks = working;
	if (sb->feature_map & __le32_to_cpu(MD_FEATURE_JOURNAL))
		info->journal_device_required = 1;
	info->journal_clean = 0;
}

static struct mdinfo *container_content1(struct supertype *st, char *subarray)
{
	struct mdinfo *info;

	if (subarray)
		return NULL;

	info = xmalloc(sizeof(*info));
	getinfo_super1(st, info, NULL);
	return info;
}

static int update_super1(struct supertype *st, struct mdinfo *info,
			 char *update,
			 char *devname, int verbose,
			 int uuid_set, char *homehost)
{
	/* NOTE: for 'assemble' and 'force' we need to return non-zero
	 * if any change was made.  For others, the return value is
	 * ignored.
	 */
	int rv = 0;
	int lockid;
	struct mdp_superblock_1 *sb = st->sb;
	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);

	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready()) {
		rv = cluster_get_dlmlock(&lockid);
		if (rv) {
			pr_err("Cannot get dlmlock in %s return %d\n", __func__, rv);
			cluster_release_dlmlock(lockid);
			return rv;
		}
	}

	if (strcmp(update, "homehost") == 0 &&
	    homehost) {
		/* Note that 'homehost' is special as it is really
		 * a "name" update.
		 */
		char *c;
		update = "name";
		c = strchr(sb->set_name, ':');
		if (c)
			strncpy(info->name, c+1, 31 - (c-sb->set_name));
		else
			strncpy(info->name, sb->set_name, 32);
		info->name[32] = 0;
	}

	if (strcmp(update, "force-one")==0) {
		/* Not enough devices for a working array,
		 * so bring this one up-to-date
		 */
		if (sb->events != __cpu_to_le64(info->events))
			rv = 1;
		sb->events = __cpu_to_le64(info->events);
	} else if (strcmp(update, "force-array")==0) {
		/* Degraded array and 'force' requests to
		 * maybe need to mark it 'clean'.
		 */
		switch(__le32_to_cpu(sb->level)) {
		case 5: case 4: case 6:
			/* need to force clean */
			if (sb->resync_offset != MaxSector)
				rv = 1;
			sb->resync_offset = MaxSector;
		}
	} else if (strcmp(update, "assemble")==0) {
		int d = info->disk.number;
		int want;
		if (info->disk.state & (1<<MD_DISK_ACTIVE))
			want = info->disk.raid_disk;
		else if (info->disk.state & (1<<MD_DISK_JOURNAL))
			want = MD_DISK_ROLE_JOURNAL;
		else
			want = MD_DISK_ROLE_SPARE;
		if (sb->dev_roles[d] != __cpu_to_le16(want)) {
			sb->dev_roles[d] = __cpu_to_le16(want);
			rv = 1;
		}
		if (info->reshape_active &&
		    sb->feature_map & __le32_to_cpu(MD_FEATURE_RESHAPE_ACTIVE) &&
		    info->delta_disks >= 0 &&
		    info->reshape_progress < __le64_to_cpu(sb->reshape_position)) {
			sb->reshape_position = __cpu_to_le64(info->reshape_progress);
			rv = 1;
		}
		if (info->reshape_active &&
		    sb->feature_map & __le32_to_cpu(MD_FEATURE_RESHAPE_ACTIVE) &&
		    info->delta_disks < 0 &&
		    info->reshape_progress > __le64_to_cpu(sb->reshape_position)) {
			sb->reshape_position = __cpu_to_le64(info->reshape_progress);
			rv = 1;
		}
	} else if (strcmp(update, "linear-grow-new") == 0) {
		unsigned int i;
		int fd;
		unsigned int max = __le32_to_cpu(sb->max_dev);

		for (i=0 ; i < max ; i++)
			if (__le16_to_cpu(sb->dev_roles[i]) >= MD_DISK_ROLE_FAULTY)
				break;
		sb->dev_number = __cpu_to_le32(i);
		info->disk.number = i;
		if (max >= __le32_to_cpu(sb->max_dev))
			sb->max_dev = __cpu_to_le32(max+1);

		random_uuid(sb->device_uuid);

		sb->dev_roles[i] =
			__cpu_to_le16(info->disk.raid_disk);

		fd = open(devname, O_RDONLY);
		if (fd >= 0) {
			unsigned long long ds;
			get_dev_size(fd, devname, &ds);
			close(fd);
			ds >>= 9;
			if (__le64_to_cpu(sb->super_offset) <
			    __le64_to_cpu(sb->data_offset)) {
				sb->data_size = __cpu_to_le64(
					ds - __le64_to_cpu(sb->data_offset));
			} else {
				ds -= 8*2;
				ds &= ~(unsigned long long)(4*2-1);
				sb->super_offset = __cpu_to_le64(ds);
				sb->data_size = __cpu_to_le64(
					ds - __le64_to_cpu(sb->data_offset));
			}
		}
	} else if (strcmp(update, "linear-grow-update") == 0) {
		sb->raid_disks = __cpu_to_le32(info->array.raid_disks);
		sb->dev_roles[info->disk.number] =
			__cpu_to_le16(info->disk.raid_disk);
	} else if (strcmp(update, "resync") == 0) {
		/* make sure resync happens */
		sb->resync_offset = 0ULL;
	} else if (strcmp(update, "uuid") == 0) {
		copy_uuid(sb->set_uuid, info->uuid, super1.swapuuid);

		if (__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET)
			memcpy(bms->uuid, sb->set_uuid, 16);
	} else if (strcmp(update, "no-bitmap") == 0) {
		sb->feature_map &= ~__cpu_to_le32(MD_FEATURE_BITMAP_OFFSET);
	} else if (strcmp(update, "bbl") == 0) {
		/* only possible if there is room after the bitmap, or if
		 * there is no bitmap
		 */
		unsigned long long sb_offset = __le64_to_cpu(sb->super_offset);
		unsigned long long data_offset = __le64_to_cpu(sb->data_offset);
		long bitmap_offset = 0;
		long bm_sectors = 0;
		long space;

#ifndef MDASSEMBLE
		if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
			bitmap_offset = (long)__le32_to_cpu(sb->bitmap_offset);
			bm_sectors = calc_bitmap_size(bms, 4096) >> 9;
		}
#endif
		if (sb_offset < data_offset) {
			/* 1.1 or 1.2.  Put bbl after bitmap leaving at least 32K
			 */
			long bb_offset;
			bb_offset = sb_offset + 8;
			if (bm_sectors && bitmap_offset > 0)
				bb_offset = bitmap_offset + bm_sectors;
			while (bb_offset < (long)sb_offset + 8 + 32*2
			       && bb_offset + 8+8 <= (long)data_offset)
				/* too close to bitmap, and room to grow */
				bb_offset += 8;
			if (bb_offset + 8 <= (long)data_offset) {
				sb->bblog_size = __cpu_to_le16(8);
				sb->bblog_offset = __cpu_to_le32(bb_offset);
			}
		} else {
			/* 1.0 - Put bbl just before super block */
			if (bm_sectors && bitmap_offset < 0)
				space = -bitmap_offset - bm_sectors;
			else
				space = sb_offset - data_offset -
					__le64_to_cpu(sb->data_size);
			if (space >= 8) {
				sb->bblog_size = __cpu_to_le16(8);
				sb->bblog_offset = __cpu_to_le32((unsigned)-8);
			}
		}
	} else if (strcmp(update, "no-bbl") == 0) {
		if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BAD_BLOCKS))
			pr_err("Cannot remove active bbl from %s\n",devname);
		else {
			sb->bblog_size = 0;
			sb->bblog_shift = 0;
			sb->bblog_offset = 0;
		}
	} else if (strcmp(update, "force-no-bbl") == 0) {
		sb->feature_map &= ~ __cpu_to_le32(MD_FEATURE_BAD_BLOCKS);
		sb->bblog_size = 0;
		sb->bblog_shift = 0;
		sb->bblog_offset = 0;
	} else if (strcmp(update, "name") == 0) {
		if (info->name[0] == 0)
			sprintf(info->name, "%d", info->array.md_minor);
		memset(sb->set_name, 0, sizeof(sb->set_name));
		if (homehost &&
		    strchr(info->name, ':') == NULL &&
		    strlen(homehost)+1+strlen(info->name) < 32) {
			strcpy(sb->set_name, homehost);
			strcat(sb->set_name, ":");
			strcat(sb->set_name, info->name);
		} else
			strncpy(sb->set_name, info->name, sizeof(sb->set_name));
	} else if (strcmp(update, "devicesize") == 0 &&
	    __le64_to_cpu(sb->super_offset) <
	    __le64_to_cpu(sb->data_offset)) {
		/* set data_size to device size less data_offset */
		struct misc_dev_info *misc = (struct misc_dev_info*)
			(st->sb + MAX_SB_SIZE + BM_SUPER_SIZE);
		sb->data_size = __cpu_to_le64(
			misc->device_size - __le64_to_cpu(sb->data_offset));
	} else if (strncmp(update, "revert-reshape", 14) == 0) {
		rv = -2;
		if (!(sb->feature_map & __cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE)))
			pr_err("No active reshape to revert on %s\n",
			       devname);
		else {
			__u32 temp;
			unsigned long long reshape_sectors;
			long reshape_chunk;
			rv = 0;
			/* If the reshape hasn't started, just stop it.
			 * It is conceivable that a stripe was modified but
			 * the metadata not updated.  In that case the backup
			 * should have been used to get passed the critical stage.
			 * If that couldn't happen, the "-nobackup" version
			 * will be used.
			 */
			if (strcmp(update, "revert-reshape-nobackup") == 0 &&
			    sb->reshape_position == 0 &&
			    (__le32_to_cpu(sb->delta_disks) > 0 ||
			     (__le32_to_cpu(sb->delta_disks) == 0 &&
			      !(sb->feature_map & __cpu_to_le32(MD_FEATURE_RESHAPE_BACKWARDS))))) {
				sb->feature_map &= ~__cpu_to_le32(MD_FEATURE_RESHAPE_ACTIVE);
				sb->raid_disks = __cpu_to_le32(__le32_to_cpu(sb->raid_disks) -
							       __le32_to_cpu(sb->delta_disks));
				sb->delta_disks = 0;
				goto done;
			}
			/* reshape_position is a little messy.
			 * Its value must be a multiple of the larger
			 * chunk size, and of the "after" data disks.
			 * So when reverting we need to change it to
			 * be a multiple of the new "after" data disks,
			 * which is the old "before".
			 * If it isn't already a multiple of 'before',
			 * the only thing we could do would be
			 * copy some block around on the disks, which
			 * is easy to get wrong.
			 * So we reject a revert-reshape unless the
			 * alignment is good.
			 */
			if (__le32_to_cpu(sb->level) >= 4 &&
			    __le32_to_cpu(sb->level) <= 6) {
				reshape_sectors = __le64_to_cpu(sb->reshape_position);
				reshape_chunk = __le32_to_cpu(sb->new_chunk);
				reshape_chunk *= __le32_to_cpu(sb->raid_disks) - __le32_to_cpu(sb->delta_disks) -
					(__le32_to_cpu(sb->level)==6 ? 2 : 1);
				if (reshape_sectors % reshape_chunk) {
					pr_err("Reshape position is not suitably aligned.\n");
					pr_err("Try normal assembly and stop again\n");
					return -2;
				}
			}
			sb->raid_disks = __cpu_to_le32(__le32_to_cpu(sb->raid_disks) -
						       __le32_to_cpu(sb->delta_disks));
			if (sb->delta_disks == 0)
				sb->feature_map ^= __cpu_to_le32(MD_FEATURE_RESHAPE_BACKWARDS);
			else
				sb->delta_disks = __cpu_to_le32(-__le32_to_cpu(sb->delta_disks));

			temp = sb->new_layout;
			sb->new_layout = sb->layout;
			sb->layout = temp;

			temp = sb->new_chunk;
			sb->new_chunk = sb->chunksize;
			sb->chunksize = temp;

			if (sb->feature_map & __cpu_to_le32(MD_FEATURE_NEW_OFFSET)) {
				long offset_delta = (int32_t)__le32_to_cpu(sb->new_offset);
				sb->data_offset = __cpu_to_le64(__le64_to_cpu(sb->data_offset) + offset_delta);
				sb->new_offset = __cpu_to_le32(-offset_delta);
				sb->data_size = __cpu_to_le64(__le64_to_cpu(sb->data_size) - offset_delta);
			}
		done:;
		}
	} else if (strcmp(update, "_reshape_progress")==0)
		sb->reshape_position = __cpu_to_le64(info->reshape_progress);
	else if (strcmp(update, "writemostly")==0)
		sb->devflags |= WriteMostly1;
	else if (strcmp(update, "readwrite")==0)
		sb->devflags &= ~WriteMostly1;
	else if (strcmp(update, "failfast") == 0)
		sb->devflags |= FailFast1;
	else if (strcmp(update, "nofailfast") == 0)
		sb->devflags &= ~FailFast1;
	else
		rv = -1;

	sb->sb_csum = calc_sb_1_csum(sb);
	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready())
		cluster_release_dlmlock(lockid);

	return rv;
}

static int init_super1(struct supertype *st, mdu_array_info_t *info,
		       unsigned long long size, char *name, char *homehost,
		       int *uuid, unsigned long long data_offset)
{
	struct mdp_superblock_1 *sb;
	int spares;
	char defname[10];
	int sbsize;

	if (posix_memalign((void**)&sb, 4096, SUPER1_SIZE) != 0) {
		pr_err("could not allocate superblock\n");
		return 0;
	}
	memset(sb, 0, SUPER1_SIZE);

	st->sb = sb;
	if (info == NULL) {
		/* zeroing superblock */
		return 0;
	}

	spares = info->working_disks - info->active_disks;
	if (info->raid_disks + spares  > MAX_DEVS) {
		pr_err("too many devices requested: %d+%d > %d\n",
			info->raid_disks , spares, MAX_DEVS);
		return 0;
	}

	sb->magic = __cpu_to_le32(MD_SB_MAGIC);
	sb->major_version = __cpu_to_le32(1);
	sb->feature_map = 0;
	sb->pad0 = 0;

	if (uuid)
		copy_uuid(sb->set_uuid, uuid, super1.swapuuid);
	else
		random_uuid(sb->set_uuid);;

	if (name == NULL || *name == 0) {
		sprintf(defname, "%d", info->md_minor);
		name = defname;
	}
	if (homehost &&
	    strchr(name, ':')== NULL &&
	    strlen(homehost)+1+strlen(name) < 32) {
		strcpy(sb->set_name, homehost);
		strcat(sb->set_name, ":");
		strcat(sb->set_name, name);
	} else
		strncpy(sb->set_name, name, sizeof(sb->set_name));

	sb->ctime = __cpu_to_le64((unsigned long long)time(0));
	sb->level = __cpu_to_le32(info->level);
	sb->layout = __cpu_to_le32(info->layout);
	sb->size = __cpu_to_le64(size*2ULL);
	sb->chunksize = __cpu_to_le32(info->chunk_size>>9);
	sb->raid_disks = __cpu_to_le32(info->raid_disks);

	sb->data_offset = __cpu_to_le64(data_offset);
	sb->data_size = __cpu_to_le64(0);
	sb->super_offset = __cpu_to_le64(0);
	sb->recovery_offset = __cpu_to_le64(0);

	sb->utime = sb->ctime;
	sb->events = __cpu_to_le64(1);
	if (info->state & (1<<MD_SB_CLEAN))
		sb->resync_offset = MaxSector;
	else
		sb->resync_offset = 0;
	sbsize = sizeof(struct mdp_superblock_1) + 2 * (info->raid_disks + spares);
	sbsize = ROUND_UP(sbsize, 512);
	sb->max_dev = __cpu_to_le32((sbsize - sizeof(struct mdp_superblock_1)) / 2);

	memset(sb->dev_roles, 0xff, MAX_SB_SIZE - sizeof(struct mdp_superblock_1));

	return 1;
}

struct devinfo {
	int fd;
	char *devname;
	long long data_offset;
	mdu_disk_info_t disk;
	struct devinfo *next;
};
#ifndef MDASSEMBLE
/* Add a device to the superblock being created */
static int add_to_super1(struct supertype *st, mdu_disk_info_t *dk,
			 int fd, char *devname, unsigned long long data_offset)
{
	struct mdp_superblock_1 *sb = st->sb;
	__u16 *rp = sb->dev_roles + dk->number;
	struct devinfo *di, **dip;
	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
	int rv, lockid;

	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready()) {
		rv = cluster_get_dlmlock(&lockid);
		if (rv) {
			pr_err("Cannot get dlmlock in %s return %d\n", __func__, rv);
			cluster_release_dlmlock(lockid);
			return rv;
		}
	}

	if ((dk->state & 6) == 6) /* active, sync */
		*rp = __cpu_to_le16(dk->raid_disk);
	else if (dk->state & (1<<MD_DISK_JOURNAL))
                *rp = MD_DISK_ROLE_JOURNAL;
	else if ((dk->state & ~2) == 0) /* active or idle -> spare */
		*rp = MD_DISK_ROLE_SPARE;
	else
		*rp = MD_DISK_ROLE_FAULTY;

	if (dk->number >= (int)__le32_to_cpu(sb->max_dev) &&
	    __le32_to_cpu(sb->max_dev) < MAX_DEVS)
		sb->max_dev = __cpu_to_le32(dk->number+1);

	sb->dev_number = __cpu_to_le32(dk->number);
	sb->devflags = 0; /* don't copy another disks flags */
	sb->sb_csum = calc_sb_1_csum(sb);

	dip = (struct devinfo **)&st->info;
	while (*dip)
		dip = &(*dip)->next;
	di = xmalloc(sizeof(struct devinfo));
	di->fd = fd;
	di->devname = devname;
	di->disk = *dk;
	di->data_offset = data_offset;
	di->next = NULL;
	*dip = di;

	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready())
		cluster_release_dlmlock(lockid);

	return 0;
}
#endif

static int locate_bitmap1(struct supertype *st, int fd, int node_num);

static int store_super1(struct supertype *st, int fd)
{
	struct mdp_superblock_1 *sb = st->sb;
	unsigned long long sb_offset;
	struct align_fd afd;
	int sbsize;
	unsigned long long dsize;
	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
	int rv, lockid;

	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready()) {
		rv = cluster_get_dlmlock(&lockid);
		if (rv) {
			pr_err("Cannot get dlmlock in %s return %d\n", __func__, rv);
			cluster_release_dlmlock(lockid);
			return rv;
		}
	}

	if (!get_dev_size(fd, NULL, &dsize))
		return 1;

	dsize >>= 9;

	if (dsize < 24)
		return 2;

	init_afd(&afd, fd);

	/*
	 * Calculate the position of the superblock.
	 * It is always aligned to a 4K boundary and
	 * depending on minor_version, it can be:
	 * 0: At least 8K, but less than 12K, from end of device
	 * 1: At start of device
	 * 2: 4K from start of device.
	 */
	switch(st->minor_version) {
	case 0:
		sb_offset = dsize;
		sb_offset -= 8*2;
		sb_offset &= ~(4*2-1);
		break;
	case 1:
		sb_offset = 0;
		break;
	case 2:
		sb_offset = 4*2;
		break;
	default:
		return -EINVAL;
	}

	if (sb_offset != __le64_to_cpu(sb->super_offset) &&
	    0 != __le64_to_cpu(sb->super_offset)
		) {
		pr_err("internal error - sb_offset is wrong\n");
		abort();
	}

	if (lseek64(fd, sb_offset << 9, 0)< 0LL)
		return 3;

	sbsize = ROUND_UP(sizeof(*sb) + 2 * __le32_to_cpu(sb->max_dev), 512);

	if (awrite(&afd, sb, sbsize) != sbsize)
		return 4;

	if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
		struct bitmap_super_s *bm = (struct bitmap_super_s*)
			(((char*)sb)+MAX_SB_SIZE);
		if (__le32_to_cpu(bm->magic) == BITMAP_MAGIC) {
			locate_bitmap1(st, fd, 0);
			if (awrite(&afd, bm, sizeof(*bm)) != sizeof(*bm))
				return 5;
		}
	}
	fsync(fd);
	if (bms->version == BITMAP_MAJOR_CLUSTERED && dlm_funs_ready())
		cluster_release_dlmlock(lockid);

	return 0;
}

static int load_super1(struct supertype *st, int fd, char *devname);

static unsigned long choose_bm_space(unsigned long devsize)
{
	/* if the device is bigger than 8Gig, save 64k for bitmap usage,
	 * if bigger than 200Gig, save 128k
	 * NOTE: result must be multiple of 4K else bad things happen
	 * on 4K-sector devices.
	 */
	if (devsize < 64*2)
		return 0;
	if (devsize - 64*2 >= 200*1024*1024*2)
		return 128*2;
	if (devsize - 4*2 > 8*1024*1024*2)
		return 64*2;
	return 4*2;
}

static void free_super1(struct supertype *st);

#define META_BLOCK_SIZE 4096
__u32 crc32c_le(__u32 crc, unsigned char const *p, size_t len);

#ifndef MDASSEMBLE
static int write_empty_r5l_meta_block(struct supertype *st, int fd)
{
	struct r5l_meta_block *mb;
	struct mdp_superblock_1 *sb = st->sb;
	struct align_fd afd;
	__u32 crc;

	init_afd(&afd, fd);

	if (posix_memalign((void**)&mb, 4096, META_BLOCK_SIZE) != 0) {
		pr_err("Could not allocate memory for the meta block.\n");
		return 1;
	}

	memset(mb, 0, META_BLOCK_SIZE);

	mb->magic = __cpu_to_le32(R5LOG_MAGIC);
	mb->version = R5LOG_VERSION;
	mb->meta_size = __cpu_to_le32(sizeof(struct r5l_meta_block));
	mb->seq = __cpu_to_le64(random32());
	mb->position = __cpu_to_le64(0);

	crc = crc32c_le(0xffffffff, sb->set_uuid, sizeof(sb->set_uuid));
	crc = crc32c_le(crc, (void *)mb, META_BLOCK_SIZE);
	mb->checksum = crc;

	if (lseek64(fd, (sb->data_offset) * 512, 0) < 0LL) {
		pr_err("cannot seek to offset of the meta block\n");
		goto fail_to_write;
	}

	if (awrite(&afd, mb, META_BLOCK_SIZE) != META_BLOCK_SIZE) {
		pr_err("failed to store write the meta block \n");
		goto fail_to_write;
	}
	fsync(fd);

	free(mb);
	return 0;

fail_to_write:
	free(mb);
	return 1;
}

static int write_init_super1(struct supertype *st)
{
	struct mdp_superblock_1 *sb = st->sb;
	struct supertype *refst;
	int rv = 0;
	unsigned long long bm_space;
	struct devinfo *di;
	unsigned long long dsize, array_size;
	unsigned long long sb_offset;
	unsigned long long data_offset;
	long bm_offset;

	for (di = st->info; di; di = di->next) {
		if (di->disk.state & (1 << MD_DISK_JOURNAL))
			sb->feature_map |= MD_FEATURE_JOURNAL;
	}

	for (di = st->info; di; di = di->next) {
		if (di->disk.state & (1 << MD_DISK_FAULTY))
			continue;
		if (di->fd < 0)
			continue;

		while (Kill(di->devname, NULL, 0, -1, 1) == 0)
			;

		sb->dev_number = __cpu_to_le32(di->disk.number);
		if (di->disk.state & (1<<MD_DISK_WRITEMOSTLY))
			sb->devflags |= WriteMostly1;
		else
			sb->devflags &= ~WriteMostly1;
		if (di->disk.state & (1<<MD_DISK_FAILFAST))
			sb->devflags |= FailFast1;
		else
			sb->devflags &= ~FailFast1;

		random_uuid(sb->device_uuid);

		if (!(di->disk.state & (1<<MD_DISK_JOURNAL)))
			sb->events = 0;

		refst = dup_super(st);
		if (load_super1(refst, di->fd, NULL)==0) {
			struct mdp_superblock_1 *refsb = refst->sb;

			memcpy(sb->device_uuid, refsb->device_uuid, 16);
			if (memcmp(sb->set_uuid, refsb->set_uuid, 16)==0) {
				/* same array, so preserve events and
				 * dev_number */
				sb->events = refsb->events;
				/* bugs in 2.6.17 and earlier mean the
				 * dev_number chosen in Manage must be preserved
				 */
				if (get_linux_version() >= 2006018)
					sb->dev_number = refsb->dev_number;
			}
			free_super1(refst);
		}
		free(refst);

		if (!get_dev_size(di->fd, NULL, &dsize)) {
			rv = 1;
			goto error_out;
		}
		dsize >>= 9;

		if (dsize < 24) {
			close(di->fd);
			rv = 2;
			goto error_out;
		}

		/*
		 * Calculate the position of the superblock.
		 * It is always aligned to a 4K boundary and
		 * depending on minor_version, it can be:
		 * 0: At least 8K, but less than 12K, from end of device
		 * 1: At start of device
		 * 2: 4K from start of device.
		 * data_offset has already been set.
		 */
		array_size = __le64_to_cpu(sb->size);

		/* work out how much space we left for a bitmap */
		if (sb->feature_map & __cpu_to_le32(MD_FEATURE_BITMAP_OFFSET)) {
			bitmap_super_t *bms = (bitmap_super_t *)
					(((char *)sb) + MAX_SB_SIZE);
			bm_space = calc_bitmap_size(bms, 4096) >> 9;
			bm_offset = (long)__le32_to_cpu(sb->bitmap_offset);
		} else {
			bm_space = choose_bm_space(array_size);
			bm_offset = 8;
		}

		data_offset = di->data_offset;
		if (data_offset == INVALID_SECTORS)
			data_offset = st->data_offset;
		switch(st->minor_version) {
		case 0:
			/* Add 8 sectors for bad block log */
			bm_space += 8;
			if (data_offset == INVALID_SECTORS)
				data_offset = 0;
			sb_offset = dsize;
			sb_offset -= 8*2;
			sb_offset &= ~(4*2-1);
			sb->data_offset = __cpu_to_le64(data_offset);
			sb->super_offset = __cpu_to_le64(sb_offset);
			if (sb_offset < array_size + bm_space)
				bm_space = sb_offset - array_size;
			sb->data_size = __cpu_to_le64(sb_offset - bm_space);
			if (bm_space >= 8) {
				sb->bblog_size = __cpu_to_le16(8);
				sb->bblog_offset = __cpu_to_le32((unsigned)-8);
			}
			break;
		case 1:
		case 2:
			sb_offset = st->minor_version == 2 ? 8 : 0;
			sb->super_offset = __cpu_to_le64(sb_offset);
			if (data_offset == INVALID_SECTORS)
				data_offset = sb_offset + 16;

			sb->data_offset = __cpu_to_le64(data_offset);
			sb->data_size = __cpu_to_le64(dsize - data_offset);
			if (data_offset >= sb_offset+bm_offset+bm_space+8) {
				sb->bblog_size = __cpu_to_le16(8);
				sb->bblog_offset = __cpu_to_le32(bm_offset +
								 bm_space);
			} else if (data_offset >= sb_offset + 16) {
				sb->bblog_size = __cpu_to_le16(8);
				/* '8' sectors for the bblog, and 'sb_offset'
				 * because we want offset from superblock, not
				 * start of device.
				 */
				sb->bblog_offset = __cpu_to_le32(data_offset -
								 8 - sb_offset);
			}
			break;
		default:
			pr_err("Failed to write invalid metadata format 1.%i to %s\n",
			       st->minor_version, di->devname);
			rv = -EINVAL;
			goto out;
		}
		/* Disable badblock log on clusters, or when explicitly requested */
		if (st->nodes > 0 || conf_get_create_info()->bblist == 0) {
			sb->bblog_size = 0;
			sb->bblog_offset = 0;
		}

		sb->sb_csum = calc_sb_1_csum(sb);
		rv = store_super1(st, di->fd);

		if (rv == 0 && (di->disk.state & (1 << MD_DISK_JOURNAL))) {
			rv = write_empty_r5l_meta_block(st, di->fd);
			if (rv)
				goto error_out;
		}

		if (rv == 0 && (__le32_to_cpu(sb->feature_map) & 1))
			rv = st->ss->write_bitmap(st, di->fd, NodeNumUpdate);
		close(di->fd);
		di->fd = -1;
		if (rv)
			goto error_out;
	}
error_out:
	if (rv)
		pr_err("Failed to write metadata to %s\n",
		       di->devname);
out:
	return rv;
}
#endif

static int compare_super1(struct supertype *st, struct supertype *tst)
{
	/*
	 * return:
	 *  0 same, or first was empty, and second was copied
	 *  1 second had wrong number
	 *  2 wrong uuid
	 *  3 wrong other info
	 */
	struct mdp_superblock_1 *first = st->sb;
	struct mdp_superblock_1 *second = tst->sb;

	if (second->magic != __cpu_to_le32(MD_SB_MAGIC))
		return 1;
	if (second->major_version != __cpu_to_le32(1))
		return 1;

	if (!first) {
		if (posix_memalign((void**)&first, 4096, SUPER1_SIZE) != 0) {
			pr_err("could not allocate superblock\n");
			return 1;
		}
		memcpy(first, second, SUPER1_SIZE);
		st->sb = first;
		return 0;
	}
	if (memcmp(first->set_uuid, second->set_uuid, 16)!= 0)
		return 2;

	if (first->ctime      != second->ctime     ||
	    first->level      != second->level     ||
	    first->layout     != second->layout    ||
	    first->size       != second->size      ||
	    first->chunksize  != second->chunksize ||
	    first->raid_disks != second->raid_disks)
		return 3;
	return 0;
}

static int load_super1(struct supertype *st, int fd, char *devname)
{
	unsigned long long dsize;
	unsigned long long sb_offset;
	struct mdp_superblock_1 *super;
	int uuid[4];
	struct bitmap_super_s *bsb;
	struct misc_dev_info *misc;
	struct align_fd afd;

	free_super1(st);

	init_afd(&afd, fd);

	if (st->ss == NULL || st->minor_version == -1) {
		int bestvers = -1;
		struct supertype tst;
		__u64 bestctime = 0;
		/* guess... choose latest ctime */
		memset(&tst, 0, sizeof(tst));
		tst.ss = &super1;
		for (tst.minor_version = 0; tst.minor_version <= 2 ; tst.minor_version++) {
			switch(load_super1(&tst, fd, devname)) {
			case 0: super = tst.sb;
				if (bestvers == -1 ||
				    bestctime < __le64_to_cpu(super->ctime)) {
					bestvers = tst.minor_version;
					bestctime = __le64_to_cpu(super->ctime);
				}
				free(super);
				tst.sb = NULL;
				break;
			case 1: return 1; /*bad device */
			case 2: break; /* bad, try next */
			}
		}
		if (bestvers != -1) {
			int rv;
			tst.minor_version = bestvers;
			tst.ss = &super1;
			tst.max_devs = MAX_DEVS;
			rv = load_super1(&tst, fd, devname);
			if (rv == 0)
				*st = tst;
			return rv;
		}
		return 2;
	}
	if (!get_dev_size(fd, devname, &dsize))
		return 1;
	dsize >>= 9;

	if (dsize < 24) {
		if (devname)
			pr_err("%s is too small for md: size is %llu sectors.\n",
				devname, dsize);
		return 1;
	}

	/*
	 * Calculate the position of the superblock.
	 * It is always aligned to a 4K boundary and
	 * depending on minor_version, it can be:
	 * 0: At least 8K, but less than 12K, from end of device
	 * 1: At start of device
	 * 2: 4K from start of device.
	 */
	switch(st->minor_version) {
	case 0:
		sb_offset = dsize;
		sb_offset -= 8*2;
		sb_offset &= ~(4*2-1);
		break;
	case 1:
		sb_offset = 0;
		break;
	case 2:
		sb_offset = 4*2;
		break;
	default:
		return -EINVAL;
	}

	if (lseek64(fd, sb_offset << 9, 0)< 0LL) {
		if (devname)
			pr_err("Cannot seek to superblock on %s: %s\n",
				devname, strerror(errno));
		return 1;
	}

	if (posix_memalign((void**)&super, 4096, SUPER1_SIZE) != 0) {
		pr_err("could not allocate superblock\n");
		return 1;
	}

	memset(super, 0, SUPER1_SIZE);

	if (aread(&afd, super, MAX_SB_SIZE) != MAX_SB_SIZE) {
		if (devname)
			pr_err("Cannot read superblock on %s\n",
				devname);
		free(super);
		return 1;
	}

	if (__le32_to_cpu(super->magic) != MD_SB_MAGIC) {
		if (devname)
			pr_err("No super block found on %s (Expected magic %08x, got %08x)\n",
				devname, MD_SB_MAGIC, __le32_to_cpu(super->magic));
		free(super);
		return 2;
	}

	if (__le32_to_cpu(super->major_version) != 1) {
		if (devname)
			pr_err("Cannot interpret superblock on %s - version is %d\n",
				devname, __le32_to_cpu(super->major_version));
		free(super);
		return 2;
	}
	if (__le64_to_cpu(super->super_offset) != sb_offset) {
		if (devname)
			pr_err("No superblock found on %s (super_offset is wrong)\n",
				devname);
		free(super);
		return 2;
	}
	st->sb = super;

	bsb = (struct bitmap_super_s *)(((char*)super)+MAX_SB_SIZE);

	misc = (struct misc_dev_info*) (((char*)super)+MAX_SB_SIZE+BM_SUPER_SIZE);
	misc->device_size = dsize;
	if (st->data_offset == INVALID_SECTORS)
		st->data_offset = __le64_to_cpu(super->data_offset);

	/* Now check on the bitmap superblock */
	if ((__le32_to_cpu(super->feature_map)&MD_FEATURE_BITMAP_OFFSET) == 0)
		return 0;
	/* Read the bitmap superblock and make sure it looks
	 * valid.  If it doesn't clear the bit.  An --assemble --force
	 * should get that written out.
	 */
	locate_bitmap1(st, fd, 0);
	if (aread(&afd, bsb, 512) != 512)
		goto no_bitmap;

	uuid_from_super1(st, uuid);
	if (__le32_to_cpu(bsb->magic) != BITMAP_MAGIC ||
	    memcmp(bsb->uuid, uuid, 16) != 0)
		goto no_bitmap;
	return 0;

 no_bitmap:
	super->feature_map = __cpu_to_le32(__le32_to_cpu(super->feature_map)
					   & ~MD_FEATURE_BITMAP_OFFSET);
	return 0;
}

static struct supertype *match_metadata_desc1(char *arg)
{
	struct supertype *st = xcalloc(1, sizeof(*st));

	st->container_devnm[0] = 0;
	st->ss = &super1;
	st->max_devs = MAX_DEVS;
	st->sb = NULL;
	st->data_offset = INVALID_SECTORS;
	/* leading zeros can be safely ignored.  --detail generates them. */
	while (*arg == '0')
		arg++;
	if (strcmp(arg, "1.0") == 0 ||
	    strcmp(arg, "1.00") == 0) {
		st->minor_version = 0;
		return st;
	}
	if (strcmp(arg, "1.1") == 0 ||
	    strcmp(arg, "1.01") == 0
		) {
		st->minor_version = 1;
		return st;
	}
	if (strcmp(arg, "1.2") == 0 ||
#ifndef DEFAULT_OLD_METADATA /* ifdef in super0.c */
	    strcmp(arg, "default") == 0 ||
#endif /* DEFAULT_OLD_METADATA */
	    strcmp(arg, "1.02") == 0) {
		st->minor_version = 2;
		return st;
	}
	if (strcmp(arg, "1") == 0 ||
	    strcmp(arg, "default") == 0) {
		st->minor_version = -1;
		return st;
	}

	free(st);
	return NULL;
}

/* find available size on device with this devsize, using
 * superblock type st, and reserving 'reserve' sectors for
 * a possible bitmap
 */
static __u64 avail_size1(struct supertype *st, __u64 devsize,
			 unsigned long long data_offset)
{
	struct mdp_superblock_1 *super = st->sb;
	int bmspace = 0;
	int bbspace = 0;
	if (devsize < 24)
		return 0;

#ifndef MDASSEMBLE
	if (__le32_to_cpu(super->feature_map)&MD_FEATURE_BITMAP_OFFSET) {
		/* hot-add. allow for actual size of bitmap */
		struct bitmap_super_s *bsb;
		bsb = (struct bitmap_super_s *)(((char*)super)+MAX_SB_SIZE);
		bmspace = calc_bitmap_size(bsb, 4096) >> 9;
	}
#endif
	/* Allow space for bad block log */
	if (super->bblog_size)
		bbspace = __le16_to_cpu(super->bblog_size);

	if (st->minor_version < 0)
		/* not specified, so time to set default */
		st->minor_version = 2;

	if (data_offset == INVALID_SECTORS)
		data_offset = st->data_offset;

	if (data_offset != INVALID_SECTORS)
		switch(st->minor_version) {
		case 0:
			return devsize - data_offset - 8*2 - bbspace;
		case 1:
		case 2:
			return devsize - data_offset;
		default:
			return 0;
		}

	devsize -= bmspace;

	switch(st->minor_version) {
	case 0:
		/* at end */
		return ((devsize - 8*2 - bbspace ) & ~(4*2-1));
	case 1:
		/* at start, 4K for superblock and possible bitmap */
		return devsize - 4*2 - bbspace;
	case 2:
		/* 4k from start, 4K for superblock and possible bitmap */
		return devsize - (4+4)*2 - bbspace;
	}
	return 0;
}

static int
add_internal_bitmap1(struct supertype *st,
		     int *chunkp, int delay, int write_behind,
		     unsigned long long size,
		     int may_change, int major)
{
	/*
	 * If not may_change, then this is a 'Grow' without sysfs support for
	 * bitmaps, and the bitmap must fit after the superblock at 1K offset.
	 * If may_change, then this is create or a Grow with sysfs syupport,
	 * and we can put the bitmap wherever we like.
	 *
	 * size is in sectors,  chunk is in bytes !!!
	 */

	unsigned long long bits;
	unsigned long long max_bits;
	unsigned long long min_chunk;
	long offset;
	long bbl_offset, bbl_size;
	unsigned long long chunk = *chunkp;
	int room = 0;
	int creating = 0;
	int len;
	struct mdp_superblock_1 *sb = st->sb;
	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb) + MAX_SB_SIZE);
	int uuid[4];

	if (__le64_to_cpu(sb->data_size) == 0)
		/* Must be creating the array, else data_size would be non-zero */
		creating = 1;
	switch(st->minor_version) {
	case 0:
		/* either 3K after the superblock (when hot-add),
		 * or some amount of space before.
		 */
		if (creating) {
			/* We are creating array, so we *know* how much room has
			 * been left.
			 */
			offset = 0;
			bbl_size = 8;
			room = choose_bm_space(__le64_to_cpu(sb->size)) + bbl_size;
		} else {
			room = __le64_to_cpu(sb->super_offset)
				- __le64_to_cpu(sb->data_offset)
				- __le64_to_cpu(sb->data_size);
			bbl_size = __le16_to_cpu(sb->bblog_size);
			if (bbl_size < 8)
				bbl_size = 8;
			bbl_offset = (__s32)__le32_to_cpu(sb->bblog_offset);
			if (bbl_size < -bbl_offset)
				bbl_size = -bbl_offset;

			if (!may_change || (room < 3*2 &&
					    __le32_to_cpu(sb->max_dev) <= 384)) {
				room = 3*2;
				offset = 1*2;
				bbl_size = 0;
			} else {
				offset = 0; /* means movable offset */
			}
		}
		break;
	case 1:
	case 2: /* between superblock and data */
		if (creating) {
			offset = 4*2;
			bbl_size = 8;
			room = choose_bm_space(__le64_to_cpu(sb->size)) + bbl_size;
		} else {
			room = __le64_to_cpu(sb->data_offset)
				- __le64_to_cpu(sb->super_offset);
			bbl_size = __le16_to_cpu(sb->bblog_size);
			if (bbl_size)
				room = __le32_to_cpu(sb->bblog_offset) + bbl_size;
			else
				bbl_size = 8;

			if (!may_change) {
				room -= 2; /* Leave 1K for superblock */
				offset = 2;
				bbl_size = 0;
			} else {
				room -= 4*2; /* leave 4K for superblock */
				offset = 4*2;
			}
		}
		break;
	default:
		return -ENOSPC;
	}

	room -= bbl_size;
	if (chunk == UnSet && room > 128*2)
		/* Limit to 128K of bitmap when chunk size not requested */
		room = 128*2;

	if (room <= 1)
		/* No room for a bitmap */
		return -ENOSPC;

	max_bits = (room * 512 - sizeof(bitmap_super_t)) * 8;

	min_chunk = 4096; /* sub-page chunks don't work yet.. */
	bits = (size*512)/min_chunk +1;
	while (bits > max_bits) {
		min_chunk *= 2;
		bits = (bits+1)/2;
	}
	if (chunk == UnSet) {
		/* For practical purpose, 64Meg is a good
		 * default chunk size for internal bitmaps.
		 */
		chunk = min_chunk;
		if (chunk < 64*1024*1024)
			chunk = 64*1024*1024;
	} else if (chunk < min_chunk)
		return -EINVAL; /* chunk size too small */
	if (chunk == 0) /* rounding problem */
		return -EINVAL;

	if (offset == 0) {
		/* start bitmap on a 4K boundary with enough space for
		 * the bitmap
		 */
		bits = (size*512) / chunk + 1;
		room = ((bits+7)/8 + sizeof(bitmap_super_t) +4095)/4096;
		room *= 8; /* convert 4K blocks to sectors */
		offset = -room - bbl_size;
	}

	sb->bitmap_offset = (int32_t)__cpu_to_le32(offset);

	sb->feature_map = __cpu_to_le32(__le32_to_cpu(sb->feature_map)
					| MD_FEATURE_BITMAP_OFFSET);
	memset(bms, 0, sizeof(*bms));
	bms->magic = __cpu_to_le32(BITMAP_MAGIC);
	bms->version = __cpu_to_le32(major);
	uuid_from_super1(st, uuid);
	memcpy(bms->uuid, uuid, 16);
	bms->chunksize = __cpu_to_le32(chunk);
	bms->daemon_sleep = __cpu_to_le32(delay);
	bms->sync_size = __cpu_to_le64(size);
	bms->write_behind = __cpu_to_le32(write_behind);
	bms->nodes = __cpu_to_le32(st->nodes);
	if (st->nodes)
		sb->feature_map = __cpu_to_le32(__le32_to_cpu(sb->feature_map)
						| MD_FEATURE_BITMAP_VERSIONED);
	if (st->cluster_name) {
		len = sizeof(bms->cluster_name);
		strncpy((char *)bms->cluster_name, st->cluster_name, len);
		bms->cluster_name[len - 1] = '\0';
	}

	*chunkp = chunk;
	return 0;
}

static int locate_bitmap1(struct supertype *st, int fd, int node_num)
{
	unsigned long long offset;
	struct mdp_superblock_1 *sb;
	int mustfree = 0;
	int ret;

	if (!st->sb) {
		if (st->ss->load_super(st, fd, NULL))
			return -1; /* no error I hope... */
		mustfree = 1;
	}
	sb = st->sb;

	if ((__le32_to_cpu(sb->feature_map) & MD_FEATURE_BITMAP_OFFSET))
		ret = 0;
	else
		ret = -1;
	offset = __le64_to_cpu(sb->super_offset);
	offset += (int32_t) __le32_to_cpu(sb->bitmap_offset) * (node_num + 1);
	if (mustfree)
		free(sb);
	lseek64(fd, offset<<9, 0);
	return ret;
}

static int write_bitmap1(struct supertype *st, int fd, enum bitmap_update update)
{
	struct mdp_superblock_1 *sb = st->sb;
	bitmap_super_t *bms = (bitmap_super_t*)(((char*)sb)+MAX_SB_SIZE);
	int rv = 0;
	void *buf;
	int towrite, n, len;
	struct align_fd afd;
	unsigned int i = 0;
	unsigned long long total_bm_space, bm_space_per_node;

	switch (update) {
	case NameUpdate:
		/* update cluster name */
		if (st->cluster_name) {
			len = sizeof(bms->cluster_name);
			memset((char *)bms->cluster_name, 0, len);
			strncpy((char *)bms->cluster_name,
				st->cluster_name, len);
			bms->cluster_name[len - 1] = '\0';
		}
		break;
	case NodeNumUpdate:
		/* cluster md only supports superblock 1.2 now */
		if (st->minor_version != 2 && bms->version == BITMAP_MAJOR_CLUSTERED) {
			pr_err("Warning: cluster md only works with superblock 1.2\n");
			return -EINVAL;
		}

		if (bms->version == BITMAP_MAJOR_CLUSTERED) {
			if (st->nodes == 1) {
				/* the parameter for nodes is not valid */
				pr_err("Warning: cluster-md at least needs two nodes\n");
				return -EINVAL;
			} else if (st->nodes == 0)
				/* --nodes is not specified */
				break;
			else if (__cpu_to_le32(st->nodes) < bms->nodes) {
				/* Since the nodes num is not increased, no need to check the space
				 * is enough or not, just update bms->nodes */
				bms->nodes = __cpu_to_le32(st->nodes);
				break;
			}
		} else {
			/* no need to change bms->nodes for other bitmap types */
			if (st->nodes)
				pr_err("Warning: --nodes option is only suitable for clustered bitmap\n");
			break;
		}

		/* Each node has an independent bitmap, it is necessary to calculate the
		 * space is enough or not, first get how many bytes for the total bitmap */
		bm_space_per_node = calc_bitmap_size(bms, 4096);

		total_bm_space = 512 * (__le64_to_cpu(sb->data_offset) - __le64_to_cpu(sb->super_offset));
		total_bm_space = total_bm_space - 4096; /* leave another 4k for superblock */

		if (bm_space_per_node * st->nodes > total_bm_space) {
			pr_err("Warning: The max num of nodes can't exceed %llu\n",
				total_bm_space / bm_space_per_node);
			return -ENOMEM;
		}

		bms->nodes = __cpu_to_le32(st->nodes);
		break;
	case NoUpdate:
	default:
		break;
	}

	init_afd(&afd, fd);

	locate_bitmap1(st, fd, 0);

	if (posix_memalign(&buf, 4096, 4096))
		return -ENOMEM;

	do {
		/* Only the bitmap[0] should resync
		 * whole device on initial assembly
		 */
		if (i)
			memset(buf, 0x00, 4096);
		else
			memset(buf, 0xff, 4096);
		memcpy(buf, (char *)bms, sizeof(bitmap_super_t));

		/*
		 * use 4096 boundary if bitmap_offset is aligned
		 * with 8 sectors, then it should compatible with
		 * older mdadm.
		 */
		if (__le32_to_cpu(sb->bitmap_offset) & 7)
			towrite = calc_bitmap_size(bms, 512);
		else
			towrite = calc_bitmap_size(bms, 4096);
		while (towrite > 0) {
			n = towrite;
			if (n > 4096)
				n = 4096;
			n = awrite(&afd, buf, n);
			if (n > 0)
				towrite -= n;
			else
				break;
			if (i)
				memset(buf, 0x00, 4096);
			else
				memset(buf, 0xff, 4096);
		}
		fsync(fd);
		if (towrite) {
			rv = -2;
			break;
		}
	} while (++i < __le32_to_cpu(bms->nodes));

	free(buf);
	return rv;
}

static void free_super1(struct supertype *st)
{

	if (st->sb)
		free(st->sb);
	while (st->info) {
		struct devinfo *di = st->info;
		st->info = di->next;
		if (di->fd >= 0)
			close(di->fd);
		free(di);
	}
	st->sb = NULL;
}

#ifndef MDASSEMBLE
static int validate_geometry1(struct supertype *st, int level,
			      int layout, int raiddisks,
			      int *chunk, unsigned long long size,
			      unsigned long long data_offset,
			      char *subdev, unsigned long long *freesize,
			      int verbose)
{
	unsigned long long ldsize, devsize;
	int bmspace;
	unsigned long long headroom;
	int fd;

	if (level == LEVEL_CONTAINER) {
		if (verbose)
			pr_err("1.x metadata does not support containers\n");
		return 0;
	}
	if (*chunk == UnSet)
		*chunk = DEFAULT_CHUNK;

	if (!subdev)
		return 1;

	if (st->minor_version < 0)
		/* not specified, so time to set default */
		st->minor_version = 2;

	fd = open(subdev, O_RDONLY|O_EXCL, 0);
	if (fd < 0) {
		if (verbose)
			pr_err("super1.x cannot open %s: %s\n",
				subdev, strerror(errno));
		return 0;
	}

	if (!get_dev_size(fd, subdev, &ldsize)) {
		close(fd);
		return 0;
	}
	close(fd);

	devsize = ldsize >> 9;
	if (devsize < 24) {
		*freesize = 0;
		return 0;
	}

	/* creating:  allow suitable space for bitmap */
	bmspace = choose_bm_space(devsize);

	if (data_offset == INVALID_SECTORS)
		data_offset = st->data_offset;
	if (data_offset == INVALID_SECTORS)
		switch (st->minor_version) {
		case 0:
			data_offset = 0;
			break;
		case 1:
		case 2:
			/* Choose data offset appropriate for this device
			 * and use as default for whole array.
			 * The data_offset must allow for bitmap space
			 * and base metadata, should allow for some headroom
			 * for reshape, and should be rounded to multiple
			 * of 1M.
			 * Headroom is limited to 128M, but aim for about 0.1%
			 */
			headroom = 128*1024*2;
			while ((headroom << 10) > devsize &&
			       (*chunk == 0 ||
				headroom / 2 >= ((unsigned)(*chunk)*2)*2))
				headroom >>= 1;
			data_offset = 12*2 + bmspace + headroom;
			#define ONE_MEG (2*1024)
			if (data_offset > ONE_MEG)
				data_offset = (data_offset / ONE_MEG) * ONE_MEG;
			break;
		}
	if (st->data_offset == INVALID_SECTORS)
		st->data_offset = data_offset;
	switch(st->minor_version) {
	case 0: /* metadata at end.  Round down and subtract space to reserve */
		devsize = (devsize & ~(4ULL*2-1));
		/* space for metadata, bblog, bitmap */
		devsize -= 8*2 + 8 + bmspace;
		break;
	case 1:
	case 2:
		devsize -= data_offset;
		break;
	}
	*freesize = devsize;
	return 1;
}
#endif /* MDASSEMBLE */

void *super1_make_v0(struct supertype *st, struct mdinfo *info, mdp_super_t *sb0)
{
	/* Create a v1.0 superblock based on 'info'*/
	void *ret;
	struct mdp_superblock_1 *sb;
	int i;
	unsigned long long offset;

	if (posix_memalign(&ret, 4096, 1024) != 0)
		return NULL;
	sb = ret;
	memset(ret, 0, 1024);
	sb->magic = __cpu_to_le32(MD_SB_MAGIC);
	sb->major_version = __cpu_to_le32(1);

	copy_uuid(sb->set_uuid, info->uuid, super1.swapuuid);
	sprintf(sb->set_name, "%d", sb0->md_minor);
	sb->ctime = __cpu_to_le32(info->array.ctime+1);
	sb->level = __cpu_to_le32(info->array.level);
	sb->layout = __cpu_to_le32(info->array.layout);
	sb->size = __cpu_to_le64(info->component_size);
	sb->chunksize = __cpu_to_le32(info->array.chunk_size/512);
	sb->raid_disks = __cpu_to_le32(info->array.raid_disks);
	if (info->array.level > 0)
		sb->data_size = sb->size;
	else
		sb->data_size = st->ss->avail_size(st, st->devsize/512, 0);
	sb->resync_offset = MaxSector;
	sb->max_dev = __cpu_to_le32(MD_SB_DISKS);
	sb->dev_number = __cpu_to_le32(info->disk.number);
	sb->utime = __cpu_to_le64(info->array.utime);

	offset = st->devsize/512 - 8*2;
	offset &= ~(4*2-1);
	sb->super_offset = __cpu_to_le64(offset);
	//*(__u64*)(st->other + 128 + 8 + 8) = __cpu_to_le64(offset);

	random_uuid(sb->device_uuid);

	for (i = 0; i < MD_SB_DISKS; i++) {
		int state = sb0->disks[i].state;
		sb->dev_roles[i] = MD_DISK_ROLE_SPARE;
		if ((state & (1<<MD_DISK_SYNC)) &&
		    !(state & (1<<MD_DISK_FAULTY)))
			sb->dev_roles[i] = __cpu_to_le16(sb0->disks[i].raid_disk);
	}
	sb->sb_csum = calc_sb_1_csum(sb);
	return ret;
}

struct superswitch super1 = {
#ifndef MDASSEMBLE
	.examine_super = examine_super1,
	.brief_examine_super = brief_examine_super1,
	.export_examine_super = export_examine_super1,
	.detail_super = detail_super1,
	.brief_detail_super = brief_detail_super1,
	.export_detail_super = export_detail_super1,
	.write_init_super = write_init_super1,
	.validate_geometry = validate_geometry1,
	.add_to_super = add_to_super1,
	.examine_badblocks = examine_badblocks_super1,
	.copy_metadata = copy_metadata1,
#endif
	.match_home = match_home1,
	.uuid_from_super = uuid_from_super1,
	.getinfo_super = getinfo_super1,
	.container_content = container_content1,
	.update_super = update_super1,
	.init_super = init_super1,
	.store_super = store_super1,
	.compare_super = compare_super1,
	.load_super = load_super1,
	.match_metadata_desc = match_metadata_desc1,
	.avail_size = avail_size1,
	.add_internal_bitmap = add_internal_bitmap1,
	.locate_bitmap = locate_bitmap1,
	.write_bitmap = write_bitmap1,
	.free_super = free_super1,
#if __BYTE_ORDER == BIG_ENDIAN
	.swapuuid = 0,
#else
	.swapuuid = 1,
#endif
	.name = "1.x",
};