aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/raid10.c
blob: 8b29cd4f01c89f8213d7dcc43cd1aaf6dd5799c7 (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
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
/*
 * raid10.c : Multiple Devices driver for Linux
 *
 * Copyright (C) 2000-2004 Neil Brown
 *
 * RAID-10 support for md.
 *
 * Base on code in raid1.c.  See raid1.c for further copyright information.
 *
 *
 * 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, or (at your option)
 * any later version.
 *
 * You should have received a copy of the GNU General Public License
 * (for example /usr/src/linux/COPYING); if not, write to the Free
 * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 */

#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/blkdev.h>
#include <linux/seq_file.h>
#include <linux/ratelimit.h>
#include "md.h"
#include "raid10.h"
#include "raid0.h"
#include "bitmap.h"

/*
 * RAID10 provides a combination of RAID0 and RAID1 functionality.
 * The layout of data is defined by
 *    chunk_size
 *    raid_disks
 *    near_copies (stored in low byte of layout)
 *    far_copies (stored in second byte of layout)
 *    far_offset (stored in bit 16 of layout )
 *
 * The data to be stored is divided into chunks using chunksize.
 * Each device is divided into far_copies sections.
 * In each section, chunks are laid out in a style similar to raid0, but
 * near_copies copies of each chunk is stored (each on a different drive).
 * The starting device for each section is offset near_copies from the starting
 * device of the previous section.
 * Thus they are (near_copies*far_copies) of each chunk, and each is on a different
 * drive.
 * near_copies and far_copies must be at least one, and their product is at most
 * raid_disks.
 *
 * If far_offset is true, then the far_copies are handled a bit differently.
 * The copies are still in different stripes, but instead of be very far apart
 * on disk, there are adjacent stripes.
 */

/*
 * Number of guaranteed r10bios in case of extreme VM load:
 */
#define	NR_RAID10_BIOS 256

static void allow_barrier(conf_t *conf);
static void lower_barrier(conf_t *conf);

static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
{
	conf_t *conf = data;
	int size = offsetof(struct r10bio_s, devs[conf->copies]);

	/* allocate a r10bio with room for raid_disks entries in the bios array */
	return kzalloc(size, gfp_flags);
}

static void r10bio_pool_free(void *r10_bio, void *data)
{
	kfree(r10_bio);
}

/* Maximum size of each resync request */
#define RESYNC_BLOCK_SIZE (64*1024)
#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
/* amount of memory to reserve for resync requests */
#define RESYNC_WINDOW (1024*1024)
/* maximum number of concurrent requests, memory permitting */
#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)

/*
 * When performing a resync, we need to read and compare, so
 * we need as many pages are there are copies.
 * When performing a recovery, we need 2 bios, one for read,
 * one for write (we recover only one drive per r10buf)
 *
 */
static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
{
	conf_t *conf = data;
	struct page *page;
	r10bio_t *r10_bio;
	struct bio *bio;
	int i, j;
	int nalloc;

	r10_bio = r10bio_pool_alloc(gfp_flags, conf);
	if (!r10_bio)
		return NULL;

	if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery))
		nalloc = conf->copies; /* resync */
	else
		nalloc = 2; /* recovery */

	/*
	 * Allocate bios.
	 */
	for (j = nalloc ; j-- ; ) {
		bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
		if (!bio)
			goto out_free_bio;
		r10_bio->devs[j].bio = bio;
	}
	/*
	 * Allocate RESYNC_PAGES data pages and attach them
	 * where needed.
	 */
	for (j = 0 ; j < nalloc; j++) {
		bio = r10_bio->devs[j].bio;
		for (i = 0; i < RESYNC_PAGES; i++) {
			if (j == 1 && !test_bit(MD_RECOVERY_SYNC,
						&conf->mddev->recovery)) {
				/* we can share bv_page's during recovery */
				struct bio *rbio = r10_bio->devs[0].bio;
				page = rbio->bi_io_vec[i].bv_page;
				get_page(page);
			} else
				page = alloc_page(gfp_flags);
			if (unlikely(!page))
				goto out_free_pages;

			bio->bi_io_vec[i].bv_page = page;
		}
	}

	return r10_bio;

out_free_pages:
	for ( ; i > 0 ; i--)
		safe_put_page(bio->bi_io_vec[i-1].bv_page);
	while (j--)
		for (i = 0; i < RESYNC_PAGES ; i++)
			safe_put_page(r10_bio->devs[j].bio->bi_io_vec[i].bv_page);
	j = -1;
out_free_bio:
	while ( ++j < nalloc )
		bio_put(r10_bio->devs[j].bio);
	r10bio_pool_free(r10_bio, conf);
	return NULL;
}

static void r10buf_pool_free(void *__r10_bio, void *data)
{
	int i;
	conf_t *conf = data;
	r10bio_t *r10bio = __r10_bio;
	int j;

	for (j=0; j < conf->copies; j++) {
		struct bio *bio = r10bio->devs[j].bio;
		if (bio) {
			for (i = 0; i < RESYNC_PAGES; i++) {
				safe_put_page(bio->bi_io_vec[i].bv_page);
				bio->bi_io_vec[i].bv_page = NULL;
			}
			bio_put(bio);
		}
	}
	r10bio_pool_free(r10bio, conf);
}

static void put_all_bios(conf_t *conf, r10bio_t *r10_bio)
{
	int i;

	for (i = 0; i < conf->copies; i++) {
		struct bio **bio = & r10_bio->devs[i].bio;
		if (!BIO_SPECIAL(*bio))
			bio_put(*bio);
		*bio = NULL;
	}
}

static void free_r10bio(r10bio_t *r10_bio)
{
	conf_t *conf = r10_bio->mddev->private;

	put_all_bios(conf, r10_bio);
	mempool_free(r10_bio, conf->r10bio_pool);
}

static void put_buf(r10bio_t *r10_bio)
{
	conf_t *conf = r10_bio->mddev->private;

	mempool_free(r10_bio, conf->r10buf_pool);

	lower_barrier(conf);
}

static void reschedule_retry(r10bio_t *r10_bio)
{
	unsigned long flags;
	mddev_t *mddev = r10_bio->mddev;
	conf_t *conf = mddev->private;

	spin_lock_irqsave(&conf->device_lock, flags);
	list_add(&r10_bio->retry_list, &conf->retry_list);
	conf->nr_queued ++;
	spin_unlock_irqrestore(&conf->device_lock, flags);

	/* wake up frozen array... */
	wake_up(&conf->wait_barrier);

	md_wakeup_thread(mddev->thread);
}

/*
 * raid_end_bio_io() is called when we have finished servicing a mirrored
 * operation and are ready to return a success/failure code to the buffer
 * cache layer.
 */
static void raid_end_bio_io(r10bio_t *r10_bio)
{
	struct bio *bio = r10_bio->master_bio;
	int done;
	conf_t *conf = r10_bio->mddev->private;

	if (bio->bi_phys_segments) {
		unsigned long flags;
		spin_lock_irqsave(&conf->device_lock, flags);
		bio->bi_phys_segments--;
		done = (bio->bi_phys_segments == 0);
		spin_unlock_irqrestore(&conf->device_lock, flags);
	} else
		done = 1;
	if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
		clear_bit(BIO_UPTODATE, &bio->bi_flags);
	if (done) {
		bio_endio(bio, 0);
		/*
		 * Wake up any possible resync thread that waits for the device
		 * to go idle.
		 */
		allow_barrier(conf);
	}
	free_r10bio(r10_bio);
}

/*
 * Update disk head position estimator based on IRQ completion info.
 */
static inline void update_head_pos(int slot, r10bio_t *r10_bio)
{
	conf_t *conf = r10_bio->mddev->private;

	conf->mirrors[r10_bio->devs[slot].devnum].head_position =
		r10_bio->devs[slot].addr + (r10_bio->sectors);
}

/*
 * Find the disk number which triggered given bio
 */
static int find_bio_disk(conf_t *conf, r10bio_t *r10_bio,
			 struct bio *bio, int *slotp)
{
	int slot;

	for (slot = 0; slot < conf->copies; slot++)
		if (r10_bio->devs[slot].bio == bio)
			break;

	BUG_ON(slot == conf->copies);
	update_head_pos(slot, r10_bio);

	if (slotp)
		*slotp = slot;
	return r10_bio->devs[slot].devnum;
}

static void raid10_end_read_request(struct bio *bio, int error)
{
	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	r10bio_t *r10_bio = bio->bi_private;
	int slot, dev;
	conf_t *conf = r10_bio->mddev->private;


	slot = r10_bio->read_slot;
	dev = r10_bio->devs[slot].devnum;
	/*
	 * this branch is our 'one mirror IO has finished' event handler:
	 */
	update_head_pos(slot, r10_bio);

	if (uptodate) {
		/*
		 * Set R10BIO_Uptodate in our master bio, so that
		 * we will return a good error code to the higher
		 * levels even if IO on some other mirrored buffer fails.
		 *
		 * The 'master' represents the composite IO operation to
		 * user-side. So if something waits for IO, then it will
		 * wait for the 'master' bio.
		 */
		set_bit(R10BIO_Uptodate, &r10_bio->state);
		raid_end_bio_io(r10_bio);
		rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
	} else {
		/*
		 * oops, read error - keep the refcount on the rdev
		 */
		char b[BDEVNAME_SIZE];
		printk_ratelimited(KERN_ERR
				   "md/raid10:%s: %s: rescheduling sector %llu\n",
				   mdname(conf->mddev),
				   bdevname(conf->mirrors[dev].rdev->bdev, b),
				   (unsigned long long)r10_bio->sector);
		set_bit(R10BIO_ReadError, &r10_bio->state);
		reschedule_retry(r10_bio);
	}
}

static void close_write(r10bio_t *r10_bio)
{
	/* clear the bitmap if all writes complete successfully */
	bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
			r10_bio->sectors,
			!test_bit(R10BIO_Degraded, &r10_bio->state),
			0);
	md_write_end(r10_bio->mddev);
}

static void raid10_end_write_request(struct bio *bio, int error)
{
	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	r10bio_t *r10_bio = bio->bi_private;
	int dev;
	int dec_rdev = 1;
	conf_t *conf = r10_bio->mddev->private;
	int slot;

	dev = find_bio_disk(conf, r10_bio, bio, &slot);

	/*
	 * this branch is our 'one mirror IO has finished' event handler:
	 */
	if (!uptodate) {
		set_bit(WriteErrorSeen,	&conf->mirrors[dev].rdev->flags);
		set_bit(R10BIO_WriteError, &r10_bio->state);
		dec_rdev = 0;
	} else {
		/*
		 * Set R10BIO_Uptodate in our master bio, so that
		 * we will return a good error code for to the higher
		 * levels even if IO on some other mirrored buffer fails.
		 *
		 * The 'master' represents the composite IO operation to
		 * user-side. So if something waits for IO, then it will
		 * wait for the 'master' bio.
		 */
		sector_t first_bad;
		int bad_sectors;

		set_bit(R10BIO_Uptodate, &r10_bio->state);

		/* Maybe we can clear some bad blocks. */
		if (is_badblock(conf->mirrors[dev].rdev,
				r10_bio->devs[slot].addr,
				r10_bio->sectors,
				&first_bad, &bad_sectors)) {
			bio_put(bio);
			r10_bio->devs[slot].bio = IO_MADE_GOOD;
			dec_rdev = 0;
			set_bit(R10BIO_MadeGood, &r10_bio->state);
		}
	}

	/*
	 *
	 * Let's see if all mirrored write operations have finished
	 * already.
	 */
	if (atomic_dec_and_test(&r10_bio->remaining)) {
		if (test_bit(R10BIO_WriteError, &r10_bio->state))
			reschedule_retry(r10_bio);
		else {
			close_write(r10_bio);
			if (test_bit(R10BIO_MadeGood, &r10_bio->state))
				reschedule_retry(r10_bio);
			else
				raid_end_bio_io(r10_bio);
		}
	}
	if (dec_rdev)
		rdev_dec_pending(conf->mirrors[dev].rdev, conf->mddev);
}


/*
 * RAID10 layout manager
 * As well as the chunksize and raid_disks count, there are two
 * parameters: near_copies and far_copies.
 * near_copies * far_copies must be <= raid_disks.
 * Normally one of these will be 1.
 * If both are 1, we get raid0.
 * If near_copies == raid_disks, we get raid1.
 *
 * Chunks are laid out in raid0 style with near_copies copies of the
 * first chunk, followed by near_copies copies of the next chunk and
 * so on.
 * If far_copies > 1, then after 1/far_copies of the array has been assigned
 * as described above, we start again with a device offset of near_copies.
 * So we effectively have another copy of the whole array further down all
 * the drives, but with blocks on different drives.
 * With this layout, and block is never stored twice on the one device.
 *
 * raid10_find_phys finds the sector offset of a given virtual sector
 * on each device that it is on.
 *
 * raid10_find_virt does the reverse mapping, from a device and a
 * sector offset to a virtual address
 */

static void raid10_find_phys(conf_t *conf, r10bio_t *r10bio)
{
	int n,f;
	sector_t sector;
	sector_t chunk;
	sector_t stripe;
	int dev;

	int slot = 0;

	/* now calculate first sector/dev */
	chunk = r10bio->sector >> conf->chunk_shift;
	sector = r10bio->sector & conf->chunk_mask;

	chunk *= conf->near_copies;
	stripe = chunk;
	dev = sector_div(stripe, conf->raid_disks);
	if (conf->far_offset)
		stripe *= conf->far_copies;

	sector += stripe << conf->chunk_shift;

	/* and calculate all the others */
	for (n=0; n < conf->near_copies; n++) {
		int d = dev;
		sector_t s = sector;
		r10bio->devs[slot].addr = sector;
		r10bio->devs[slot].devnum = d;
		slot++;

		for (f = 1; f < conf->far_copies; f++) {
			d += conf->near_copies;
			if (d >= conf->raid_disks)
				d -= conf->raid_disks;
			s += conf->stride;
			r10bio->devs[slot].devnum = d;
			r10bio->devs[slot].addr = s;
			slot++;
		}
		dev++;
		if (dev >= conf->raid_disks) {
			dev = 0;
			sector += (conf->chunk_mask + 1);
		}
	}
	BUG_ON(slot != conf->copies);
}

static sector_t raid10_find_virt(conf_t *conf, sector_t sector, int dev)
{
	sector_t offset, chunk, vchunk;

	offset = sector & conf->chunk_mask;
	if (conf->far_offset) {
		int fc;
		chunk = sector >> conf->chunk_shift;
		fc = sector_div(chunk, conf->far_copies);
		dev -= fc * conf->near_copies;
		if (dev < 0)
			dev += conf->raid_disks;
	} else {
		while (sector >= conf->stride) {
			sector -= conf->stride;
			if (dev < conf->near_copies)
				dev += conf->raid_disks - conf->near_copies;
			else
				dev -= conf->near_copies;
		}
		chunk = sector >> conf->chunk_shift;
	}
	vchunk = chunk * conf->raid_disks + dev;
	sector_div(vchunk, conf->near_copies);
	return (vchunk << conf->chunk_shift) + offset;
}

/**
 *	raid10_mergeable_bvec -- tell bio layer if a two requests can be merged
 *	@q: request queue
 *	@bvm: properties of new bio
 *	@biovec: the request that could be merged to it.
 *
 *	Return amount of bytes we can accept at this offset
 *      If near_copies == raid_disk, there are no striping issues,
 *      but in that case, the function isn't called at all.
 */
static int raid10_mergeable_bvec(struct request_queue *q,
				 struct bvec_merge_data *bvm,
				 struct bio_vec *biovec)
{
	mddev_t *mddev = q->queuedata;
	sector_t sector = bvm->bi_sector + get_start_sect(bvm->bi_bdev);
	int max;
	unsigned int chunk_sectors = mddev->chunk_sectors;
	unsigned int bio_sectors = bvm->bi_size >> 9;

	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
	if (max < 0) max = 0; /* bio_add cannot handle a negative return */
	if (max <= biovec->bv_len && bio_sectors == 0)
		return biovec->bv_len;
	else
		return max;
}

/*
 * This routine returns the disk from which the requested read should
 * be done. There is a per-array 'next expected sequential IO' sector
 * number - if this matches on the next IO then we use the last disk.
 * There is also a per-disk 'last know head position' sector that is
 * maintained from IRQ contexts, both the normal and the resync IO
 * completion handlers update this position correctly. If there is no
 * perfect sequential match then we pick the disk whose head is closest.
 *
 * If there are 2 mirrors in the same 2 devices, performance degrades
 * because position is mirror, not device based.
 *
 * The rdev for the device selected will have nr_pending incremented.
 */

/*
 * FIXME: possibly should rethink readbalancing and do it differently
 * depending on near_copies / far_copies geometry.
 */
static int read_balance(conf_t *conf, r10bio_t *r10_bio, int *max_sectors)
{
	const sector_t this_sector = r10_bio->sector;
	int disk, slot;
	int sectors = r10_bio->sectors;
	int best_good_sectors;
	sector_t new_distance, best_dist;
	mdk_rdev_t *rdev;
	int do_balance;
	int best_slot;

	raid10_find_phys(conf, r10_bio);
	rcu_read_lock();
retry:
	sectors = r10_bio->sectors;
	best_slot = -1;
	best_dist = MaxSector;
	best_good_sectors = 0;
	do_balance = 1;
	/*
	 * Check if we can balance. We can balance on the whole
	 * device if no resync is going on (recovery is ok), or below
	 * the resync window. We take the first readable disk when
	 * above the resync window.
	 */
	if (conf->mddev->recovery_cp < MaxSector
	    && (this_sector + sectors >= conf->next_resync))
		do_balance = 0;

	for (slot = 0; slot < conf->copies ; slot++) {
		sector_t first_bad;
		int bad_sectors;
		sector_t dev_sector;

		if (r10_bio->devs[slot].bio == IO_BLOCKED)
			continue;
		disk = r10_bio->devs[slot].devnum;
		rdev = rcu_dereference(conf->mirrors[disk].rdev);
		if (rdev == NULL)
			continue;
		if (!test_bit(In_sync, &rdev->flags))
			continue;

		dev_sector = r10_bio->devs[slot].addr;
		if (is_badblock(rdev, dev_sector, sectors,
				&first_bad, &bad_sectors)) {
			if (best_dist < MaxSector)
				/* Already have a better slot */
				continue;
			if (first_bad <= dev_sector) {
				/* Cannot read here.  If this is the
				 * 'primary' device, then we must not read
				 * beyond 'bad_sectors' from another device.
				 */
				bad_sectors -= (dev_sector - first_bad);
				if (!do_balance && sectors > bad_sectors)
					sectors = bad_sectors;
				if (best_good_sectors > sectors)
					best_good_sectors = sectors;
			} else {
				sector_t good_sectors =
					first_bad - dev_sector;
				if (good_sectors > best_good_sectors) {
					best_good_sectors = good_sectors;
					best_slot = slot;
				}
				if (!do_balance)
					/* Must read from here */
					break;
			}
			continue;
		} else
			best_good_sectors = sectors;

		if (!do_balance)
			break;

		/* This optimisation is debatable, and completely destroys
		 * sequential read speed for 'far copies' arrays.  So only
		 * keep it for 'near' arrays, and review those later.
		 */
		if (conf->near_copies > 1 && !atomic_read(&rdev->nr_pending))
			break;

		/* for far > 1 always use the lowest address */
		if (conf->far_copies > 1)
			new_distance = r10_bio->devs[slot].addr;
		else
			new_distance = abs(r10_bio->devs[slot].addr -
					   conf->mirrors[disk].head_position);
		if (new_distance < best_dist) {
			best_dist = new_distance;
			best_slot = slot;
		}
	}
	if (slot == conf->copies)
		slot = best_slot;

	if (slot >= 0) {
		disk = r10_bio->devs[slot].devnum;
		rdev = rcu_dereference(conf->mirrors[disk].rdev);
		if (!rdev)
			goto retry;
		atomic_inc(&rdev->nr_pending);
		if (test_bit(Faulty, &rdev->flags)) {
			/* Cannot risk returning a device that failed
			 * before we inc'ed nr_pending
			 */
			rdev_dec_pending(rdev, conf->mddev);
			goto retry;
		}
		r10_bio->read_slot = slot;
	} else
		disk = -1;
	rcu_read_unlock();
	*max_sectors = best_good_sectors;

	return disk;
}

static int raid10_congested(void *data, int bits)
{
	mddev_t *mddev = data;
	conf_t *conf = mddev->private;
	int i, ret = 0;

	if (mddev_congested(mddev, bits))
		return 1;
	rcu_read_lock();
	for (i = 0; i < conf->raid_disks && ret == 0; i++) {
		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
		if (rdev && !test_bit(Faulty, &rdev->flags)) {
			struct request_queue *q = bdev_get_queue(rdev->bdev);

			ret |= bdi_congested(&q->backing_dev_info, bits);
		}
	}
	rcu_read_unlock();
	return ret;
}

static void flush_pending_writes(conf_t *conf)
{
	/* Any writes that have been queued but are awaiting
	 * bitmap updates get flushed here.
	 */
	spin_lock_irq(&conf->device_lock);

	if (conf->pending_bio_list.head) {
		struct bio *bio;
		bio = bio_list_get(&conf->pending_bio_list);
		spin_unlock_irq(&conf->device_lock);
		/* flush any pending bitmap writes to disk
		 * before proceeding w/ I/O */
		bitmap_unplug(conf->mddev->bitmap);

		while (bio) { /* submit pending writes */
			struct bio *next = bio->bi_next;
			bio->bi_next = NULL;
			generic_make_request(bio);
			bio = next;
		}
	} else
		spin_unlock_irq(&conf->device_lock);
}

/* Barriers....
 * Sometimes we need to suspend IO while we do something else,
 * either some resync/recovery, or reconfigure the array.
 * To do this we raise a 'barrier'.
 * The 'barrier' is a counter that can be raised multiple times
 * to count how many activities are happening which preclude
 * normal IO.
 * We can only raise the barrier if there is no pending IO.
 * i.e. if nr_pending == 0.
 * We choose only to raise the barrier if no-one is waiting for the
 * barrier to go down.  This means that as soon as an IO request
 * is ready, no other operations which require a barrier will start
 * until the IO request has had a chance.
 *
 * So: regular IO calls 'wait_barrier'.  When that returns there
 *    is no backgroup IO happening,  It must arrange to call
 *    allow_barrier when it has finished its IO.
 * backgroup IO calls must call raise_barrier.  Once that returns
 *    there is no normal IO happeing.  It must arrange to call
 *    lower_barrier when the particular background IO completes.
 */

static void raise_barrier(conf_t *conf, int force)
{
	BUG_ON(force && !conf->barrier);
	spin_lock_irq(&conf->resync_lock);

	/* Wait until no block IO is waiting (unless 'force') */
	wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
			    conf->resync_lock, );

	/* block any new IO from starting */
	conf->barrier++;

	/* Now wait for all pending IO to complete */
	wait_event_lock_irq(conf->wait_barrier,
			    !conf->nr_pending && conf->barrier < RESYNC_DEPTH,
			    conf->resync_lock, );

	spin_unlock_irq(&conf->resync_lock);
}

static void lower_barrier(conf_t *conf)
{
	unsigned long flags;
	spin_lock_irqsave(&conf->resync_lock, flags);
	conf->barrier--;
	spin_unlock_irqrestore(&conf->resync_lock, flags);
	wake_up(&conf->wait_barrier);
}

static void wait_barrier(conf_t *conf)
{
	spin_lock_irq(&conf->resync_lock);
	if (conf->barrier) {
		conf->nr_waiting++;
		wait_event_lock_irq(conf->wait_barrier, !conf->barrier,
				    conf->resync_lock,
				    );
		conf->nr_waiting--;
	}
	conf->nr_pending++;
	spin_unlock_irq(&conf->resync_lock);
}

static void allow_barrier(conf_t *conf)
{
	unsigned long flags;
	spin_lock_irqsave(&conf->resync_lock, flags);
	conf->nr_pending--;
	spin_unlock_irqrestore(&conf->resync_lock, flags);
	wake_up(&conf->wait_barrier);
}

static void freeze_array(conf_t *conf)
{
	/* stop syncio and normal IO and wait for everything to
	 * go quiet.
	 * We increment barrier and nr_waiting, and then
	 * wait until nr_pending match nr_queued+1
	 * This is called in the context of one normal IO request
	 * that has failed. Thus any sync request that might be pending
	 * will be blocked by nr_pending, and we need to wait for
	 * pending IO requests to complete or be queued for re-try.
	 * Thus the number queued (nr_queued) plus this request (1)
	 * must match the number of pending IOs (nr_pending) before
	 * we continue.
	 */
	spin_lock_irq(&conf->resync_lock);
	conf->barrier++;
	conf->nr_waiting++;
	wait_event_lock_irq(conf->wait_barrier,
			    conf->nr_pending == conf->nr_queued+1,
			    conf->resync_lock,
			    flush_pending_writes(conf));

	spin_unlock_irq(&conf->resync_lock);
}

static void unfreeze_array(conf_t *conf)
{
	/* reverse the effect of the freeze */
	spin_lock_irq(&conf->resync_lock);
	conf->barrier--;
	conf->nr_waiting--;
	wake_up(&conf->wait_barrier);
	spin_unlock_irq(&conf->resync_lock);
}

static int make_request(mddev_t *mddev, struct bio * bio)
{
	conf_t *conf = mddev->private;
	mirror_info_t *mirror;
	r10bio_t *r10_bio;
	struct bio *read_bio;
	int i;
	int chunk_sects = conf->chunk_mask + 1;
	const int rw = bio_data_dir(bio);
	const unsigned long do_sync = (bio->bi_rw & REQ_SYNC);
	const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
	unsigned long flags;
	mdk_rdev_t *blocked_rdev;
	int plugged;
	int sectors_handled;
	int max_sectors;

	if (unlikely(bio->bi_rw & REQ_FLUSH)) {
		md_flush_request(mddev, bio);
		return 0;
	}

	/* If this request crosses a chunk boundary, we need to
	 * split it.  This will only happen for 1 PAGE (or less) requests.
	 */
	if (unlikely( (bio->bi_sector & conf->chunk_mask) + (bio->bi_size >> 9)
		      > chunk_sects &&
		    conf->near_copies < conf->raid_disks)) {
		struct bio_pair *bp;
		/* Sanity check -- queue functions should prevent this happening */
		if (bio->bi_vcnt != 1 ||
		    bio->bi_idx != 0)
			goto bad_map;
		/* This is a one page bio that upper layers
		 * refuse to split for us, so we need to split it.
		 */
		bp = bio_split(bio,
			       chunk_sects - (bio->bi_sector & (chunk_sects - 1)) );

		/* Each of these 'make_request' calls will call 'wait_barrier'.
		 * If the first succeeds but the second blocks due to the resync
		 * thread raising the barrier, we will deadlock because the
		 * IO to the underlying device will be queued in generic_make_request
		 * and will never complete, so will never reduce nr_pending.
		 * So increment nr_waiting here so no new raise_barriers will
		 * succeed, and so the second wait_barrier cannot block.
		 */
		spin_lock_irq(&conf->resync_lock);
		conf->nr_waiting++;
		spin_unlock_irq(&conf->resync_lock);

		if (make_request(mddev, &bp->bio1))
			generic_make_request(&bp->bio1);
		if (make_request(mddev, &bp->bio2))
			generic_make_request(&bp->bio2);

		spin_lock_irq(&conf->resync_lock);
		conf->nr_waiting--;
		wake_up(&conf->wait_barrier);
		spin_unlock_irq(&conf->resync_lock);

		bio_pair_release(bp);
		return 0;
	bad_map:
		printk("md/raid10:%s: make_request bug: can't convert block across chunks"
		       " or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2,
		       (unsigned long long)bio->bi_sector, bio->bi_size >> 10);

		bio_io_error(bio);
		return 0;
	}

	md_write_start(mddev, bio);

	/*
	 * Register the new request and wait if the reconstruction
	 * thread has put up a bar for new requests.
	 * Continue immediately if no resync is active currently.
	 */
	wait_barrier(conf);

	r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);

	r10_bio->master_bio = bio;
	r10_bio->sectors = bio->bi_size >> 9;

	r10_bio->mddev = mddev;
	r10_bio->sector = bio->bi_sector;
	r10_bio->state = 0;

	/* We might need to issue multiple reads to different
	 * devices if there are bad blocks around, so we keep
	 * track of the number of reads in bio->bi_phys_segments.
	 * If this is 0, there is only one r10_bio and no locking
	 * will be needed when the request completes.  If it is
	 * non-zero, then it is the number of not-completed requests.
	 */
	bio->bi_phys_segments = 0;
	clear_bit(BIO_SEG_VALID, &bio->bi_flags);

	if (rw == READ) {
		/*
		 * read balancing logic:
		 */
		int disk;
		int slot;

read_again:
		disk = read_balance(conf, r10_bio, &max_sectors);
		slot = r10_bio->read_slot;
		if (disk < 0) {
			raid_end_bio_io(r10_bio);
			return 0;
		}
		mirror = conf->mirrors + disk;

		read_bio = bio_clone_mddev(bio, GFP_NOIO, mddev);
		md_trim_bio(read_bio, r10_bio->sector - bio->bi_sector,
			    max_sectors);

		r10_bio->devs[slot].bio = read_bio;

		read_bio->bi_sector = r10_bio->devs[slot].addr +
			mirror->rdev->data_offset;
		read_bio->bi_bdev = mirror->rdev->bdev;
		read_bio->bi_end_io = raid10_end_read_request;
		read_bio->bi_rw = READ | do_sync;
		read_bio->bi_private = r10_bio;

		if (max_sectors < r10_bio->sectors) {
			/* Could not read all from this device, so we will
			 * need another r10_bio.
			 */
			sectors_handled = (r10_bio->sectors + max_sectors
					   - bio->bi_sector);
			r10_bio->sectors = max_sectors;
			spin_lock_irq(&conf->device_lock);
			if (bio->bi_phys_segments == 0)
				bio->bi_phys_segments = 2;
			else
				bio->bi_phys_segments++;
			spin_unlock(&conf->device_lock);
			/* Cannot call generic_make_request directly
			 * as that will be queued in __generic_make_request
			 * and subsequent mempool_alloc might block
			 * waiting for it.  so hand bio over to raid10d.
			 */
			reschedule_retry(r10_bio);

			r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);

			r10_bio->master_bio = bio;
			r10_bio->sectors = ((bio->bi_size >> 9)
					    - sectors_handled);
			r10_bio->state = 0;
			r10_bio->mddev = mddev;
			r10_bio->sector = bio->bi_sector + sectors_handled;
			goto read_again;
		} else
			generic_make_request(read_bio);
		return 0;
	}

	/*
	 * WRITE:
	 */
	/* first select target devices under rcu_lock and
	 * inc refcount on their rdev.  Record them by setting
	 * bios[x] to bio
	 * If there are known/acknowledged bad blocks on any device
	 * on which we have seen a write error, we want to avoid
	 * writing to those blocks.  This potentially requires several
	 * writes to write around the bad blocks.  Each set of writes
	 * gets its own r10_bio with a set of bios attached.  The number
	 * of r10_bios is recored in bio->bi_phys_segments just as with
	 * the read case.
	 */
	plugged = mddev_check_plugged(mddev);

	raid10_find_phys(conf, r10_bio);
retry_write:
	blocked_rdev = NULL;
	rcu_read_lock();
	max_sectors = r10_bio->sectors;

	for (i = 0;  i < conf->copies; i++) {
		int d = r10_bio->devs[i].devnum;
		mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[d].rdev);
		if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
			atomic_inc(&rdev->nr_pending);
			blocked_rdev = rdev;
			break;
		}
		r10_bio->devs[i].bio = NULL;
		if (!rdev || test_bit(Faulty, &rdev->flags)) {
			set_bit(R10BIO_Degraded, &r10_bio->state);
			continue;
		}
		if (test_bit(WriteErrorSeen, &rdev->flags)) {
			sector_t first_bad;
			sector_t dev_sector = r10_bio->devs[i].addr;
			int bad_sectors;
			int is_bad;

			is_bad = is_badblock(rdev, dev_sector,
					     max_sectors,
					     &first_bad, &bad_sectors);
			if (is_bad < 0) {
				/* Mustn't write here until the bad block
				 * is acknowledged
				 */
				atomic_inc(&rdev->nr_pending);
				set_bit(BlockedBadBlocks, &rdev->flags);
				blocked_rdev = rdev;
				break;
			}
			if (is_bad && first_bad <= dev_sector) {
				/* Cannot write here at all */
				bad_sectors -= (dev_sector - first_bad);
				if (bad_sectors < max_sectors)
					/* Mustn't write more than bad_sectors
					 * to other devices yet
					 */
					max_sectors = bad_sectors;
				/* We don't set R10BIO_Degraded as that
				 * only applies if the disk is missing,
				 * so it might be re-added, and we want to
				 * know to recover this chunk.
				 * In this case the device is here, and the
				 * fact that this chunk is not in-sync is
				 * recorded in the bad block log.
				 */
				continue;
			}
			if (is_bad) {
				int good_sectors = first_bad - dev_sector;
				if (good_sectors < max_sectors)
					max_sectors = good_sectors;
			}
		}
		r10_bio->devs[i].bio = bio;
		atomic_inc(&rdev->nr_pending);
	}
	rcu_read_unlock();

	if (unlikely(blocked_rdev)) {
		/* Have to wait for this device to get unblocked, then retry */
		int j;
		int d;

		for (j = 0; j < i; j++)
			if (r10_bio->devs[j].bio) {
				d = r10_bio->devs[j].devnum;
				rdev_dec_pending(conf->mirrors[d].rdev, mddev);
			}
		allow_barrier(conf);
		md_wait_for_blocked_rdev(blocked_rdev, mddev);
		wait_barrier(conf);
		goto retry_write;
	}

	if (max_sectors < r10_bio->sectors) {
		/* We are splitting this into multiple parts, so
		 * we need to prepare for allocating another r10_bio.
		 */
		r10_bio->sectors = max_sectors;
		spin_lock_irq(&conf->device_lock);
		if (bio->bi_phys_segments == 0)
			bio->bi_phys_segments = 2;
		else
			bio->bi_phys_segments++;
		spin_unlock_irq(&conf->device_lock);
	}
	sectors_handled = r10_bio->sector + max_sectors - bio->bi_sector;

	atomic_set(&r10_bio->remaining, 1);
	bitmap_startwrite(mddev->bitmap, r10_bio->sector, r10_bio->sectors, 0);

	for (i = 0; i < conf->copies; i++) {
		struct bio *mbio;
		int d = r10_bio->devs[i].devnum;
		if (!r10_bio->devs[i].bio)
			continue;

		mbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
		md_trim_bio(mbio, r10_bio->sector - bio->bi_sector,
			    max_sectors);
		r10_bio->devs[i].bio = mbio;

		mbio->bi_sector	= (r10_bio->devs[i].addr+
				   conf->mirrors[d].rdev->data_offset);
		mbio->bi_bdev = conf->mirrors[d].rdev->bdev;
		mbio->bi_end_io	= raid10_end_write_request;
		mbio->bi_rw = WRITE | do_sync | do_fua;
		mbio->bi_private = r10_bio;

		atomic_inc(&r10_bio->remaining);
		spin_lock_irqsave(&conf->device_lock, flags);
		bio_list_add(&conf->pending_bio_list, mbio);
		spin_unlock_irqrestore(&conf->device_lock, flags);
	}

	if (atomic_dec_and_test(&r10_bio->remaining)) {
		/* This matches the end of raid10_end_write_request() */
		bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
				r10_bio->sectors,
				!test_bit(R10BIO_Degraded, &r10_bio->state),
				0);
		md_write_end(mddev);
		raid_end_bio_io(r10_bio);
	}

	/* In case raid10d snuck in to freeze_array */
	wake_up(&conf->wait_barrier);

	if (sectors_handled < (bio->bi_size >> 9)) {
		/* We need another r10_bio.  It has already been counted
		 * in bio->bi_phys_segments.
		 */
		r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);

		r10_bio->master_bio = bio;
		r10_bio->sectors = (bio->bi_size >> 9) - sectors_handled;

		r10_bio->mddev = mddev;
		r10_bio->sector = bio->bi_sector + sectors_handled;
		r10_bio->state = 0;
		goto retry_write;
	}

	if (do_sync || !mddev->bitmap || !plugged)
		md_wakeup_thread(mddev->thread);
	return 0;
}

static void status(struct seq_file *seq, mddev_t *mddev)
{
	conf_t *conf = mddev->private;
	int i;

	if (conf->near_copies < conf->raid_disks)
		seq_printf(seq, " %dK chunks", mddev->chunk_sectors / 2);
	if (conf->near_copies > 1)
		seq_printf(seq, " %d near-copies", conf->near_copies);
	if (conf->far_copies > 1) {
		if (conf->far_offset)
			seq_printf(seq, " %d offset-copies", conf->far_copies);
		else
			seq_printf(seq, " %d far-copies", conf->far_copies);
	}
	seq_printf(seq, " [%d/%d] [", conf->raid_disks,
					conf->raid_disks - mddev->degraded);
	for (i = 0; i < conf->raid_disks; i++)
		seq_printf(seq, "%s",
			      conf->mirrors[i].rdev &&
			      test_bit(In_sync, &conf->mirrors[i].rdev->flags) ? "U" : "_");
	seq_printf(seq, "]");
}

/* check if there are enough drives for
 * every block to appear on atleast one.
 * Don't consider the device numbered 'ignore'
 * as we might be about to remove it.
 */
static int enough(conf_t *conf, int ignore)
{
	int first = 0;

	do {
		int n = conf->copies;
		int cnt = 0;
		while (n--) {
			if (conf->mirrors[first].rdev &&
			    first != ignore)
				cnt++;
			first = (first+1) % conf->raid_disks;
		}
		if (cnt == 0)
			return 0;
	} while (first != 0);
	return 1;
}

static void error(mddev_t *mddev, mdk_rdev_t *rdev)
{
	char b[BDEVNAME_SIZE];
	conf_t *conf = mddev->private;

	/*
	 * If it is not operational, then we have already marked it as dead
	 * else if it is the last working disks, ignore the error, let the
	 * next level up know.
	 * else mark the drive as failed
	 */
	if (test_bit(In_sync, &rdev->flags)
	    && !enough(conf, rdev->raid_disk))
		/*
		 * Don't fail the drive, just return an IO error.
		 */
		return;
	if (test_and_clear_bit(In_sync, &rdev->flags)) {
		unsigned long flags;
		spin_lock_irqsave(&conf->device_lock, flags);
		mddev->degraded++;
		spin_unlock_irqrestore(&conf->device_lock, flags);
		/*
		 * if recovery is running, make sure it aborts.
		 */
		set_bit(MD_RECOVERY_INTR, &mddev->recovery);
	}
	set_bit(Blocked, &rdev->flags);
	set_bit(Faulty, &rdev->flags);
	set_bit(MD_CHANGE_DEVS, &mddev->flags);
	printk(KERN_ALERT
	       "md/raid10:%s: Disk failure on %s, disabling device.\n"
	       "md/raid10:%s: Operation continuing on %d devices.\n",
	       mdname(mddev), bdevname(rdev->bdev, b),
	       mdname(mddev), conf->raid_disks - mddev->degraded);
}

static void print_conf(conf_t *conf)
{
	int i;
	mirror_info_t *tmp;

	printk(KERN_DEBUG "RAID10 conf printout:\n");
	if (!conf) {
		printk(KERN_DEBUG "(!conf)\n");
		return;
	}
	printk(KERN_DEBUG " --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
		conf->raid_disks);

	for (i = 0; i < conf->raid_disks; i++) {
		char b[BDEVNAME_SIZE];
		tmp = conf->mirrors + i;
		if (tmp->rdev)
			printk(KERN_DEBUG " disk %d, wo:%d, o:%d, dev:%s\n",
				i, !test_bit(In_sync, &tmp->rdev->flags),
			        !test_bit(Faulty, &tmp->rdev->flags),
				bdevname(tmp->rdev->bdev,b));
	}
}

static void close_sync(conf_t *conf)
{
	wait_barrier(conf);
	allow_barrier(conf);

	mempool_destroy(conf->r10buf_pool);
	conf->r10buf_pool = NULL;
}

static int raid10_spare_active(mddev_t *mddev)
{
	int i;
	conf_t *conf = mddev->private;
	mirror_info_t *tmp;
	int count = 0;
	unsigned long flags;

	/*
	 * Find all non-in_sync disks within the RAID10 configuration
	 * and mark them in_sync
	 */
	for (i = 0; i < conf->raid_disks; i++) {
		tmp = conf->mirrors + i;
		if (tmp->rdev
		    && !test_bit(Faulty, &tmp->rdev->flags)
		    && !test_and_set_bit(In_sync, &tmp->rdev->flags)) {
			count++;
			sysfs_notify_dirent(tmp->rdev->sysfs_state);
		}
	}
	spin_lock_irqsave(&conf->device_lock, flags);
	mddev->degraded -= count;
	spin_unlock_irqrestore(&conf->device_lock, flags);

	print_conf(conf);
	return count;
}


static int raid10_add_disk(mddev_t *mddev, mdk_rdev_t *rdev)
{
	conf_t *conf = mddev->private;
	int err = -EEXIST;
	int mirror;
	int first = 0;
	int last = conf->raid_disks - 1;

	if (mddev->recovery_cp < MaxSector)
		/* only hot-add to in-sync arrays, as recovery is
		 * very different from resync
		 */
		return -EBUSY;
	if (!enough(conf, -1))
		return -EINVAL;

	if (rdev->raid_disk >= 0)
		first = last = rdev->raid_disk;

	if (rdev->saved_raid_disk >= first &&
	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
		mirror = rdev->saved_raid_disk;
	else
		mirror = first;
	for ( ; mirror <= last ; mirror++) {
		mirror_info_t *p = &conf->mirrors[mirror];
		if (p->recovery_disabled == mddev->recovery_disabled)
			continue;
		if (!p->rdev)
			continue;

		disk_stack_limits(mddev->gendisk, rdev->bdev,
				  rdev->data_offset << 9);
		/* as we don't honour merge_bvec_fn, we must
		 * never risk violating it, so limit
		 * ->max_segments to one lying with a single
		 * page, as a one page request is never in
		 * violation.
		 */
		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
			blk_queue_max_segments(mddev->queue, 1);
			blk_queue_segment_boundary(mddev->queue,
						   PAGE_CACHE_SIZE - 1);
		}

		p->head_position = 0;
		rdev->raid_disk = mirror;
		err = 0;
		if (rdev->saved_raid_disk != mirror)
			conf->fullsync = 1;
		rcu_assign_pointer(p->rdev, rdev);
		break;
	}

	md_integrity_add_rdev(rdev, mddev);
	print_conf(conf);
	return err;
}

static int raid10_remove_disk(mddev_t *mddev, int number)
{
	conf_t *conf = mddev->private;
	int err = 0;
	mdk_rdev_t *rdev;
	mirror_info_t *p = conf->mirrors+ number;

	print_conf(conf);
	rdev = p->rdev;
	if (rdev) {
		if (test_bit(In_sync, &rdev->flags) ||
		    atomic_read(&rdev->nr_pending)) {
			err = -EBUSY;
			goto abort;
		}
		/* Only remove faulty devices in recovery
		 * is not possible.
		 */
		if (!test_bit(Faulty, &rdev->flags) &&
		    mddev->recovery_disabled != p->recovery_disabled &&
		    enough(conf, -1)) {
			err = -EBUSY;
			goto abort;
		}
		p->rdev = NULL;
		synchronize_rcu();
		if (atomic_read(&rdev->nr_pending)) {
			/* lost the race, try later */
			err = -EBUSY;
			p->rdev = rdev;
			goto abort;
		}
		err = md_integrity_register(mddev);
	}
abort:

	print_conf(conf);
	return err;
}


static void end_sync_read(struct bio *bio, int error)
{
	r10bio_t *r10_bio = bio->bi_private;
	conf_t *conf = r10_bio->mddev->private;
	int d;

	d = find_bio_disk(conf, r10_bio, bio, NULL);

	if (test_bit(BIO_UPTODATE, &bio->bi_flags))
		set_bit(R10BIO_Uptodate, &r10_bio->state);
	else
		/* The write handler will notice the lack of
		 * R10BIO_Uptodate and record any errors etc
		 */
		atomic_add(r10_bio->sectors,
			   &conf->mirrors[d].rdev->corrected_errors);

	/* for reconstruct, we always reschedule after a read.
	 * for resync, only after all reads
	 */
	rdev_dec_pending(conf->mirrors[d].rdev, conf->mddev);
	if (test_bit(R10BIO_IsRecover, &r10_bio->state) ||
	    atomic_dec_and_test(&r10_bio->remaining)) {
		/* we have read all the blocks,
		 * do the comparison in process context in raid10d
		 */
		reschedule_retry(r10_bio);
	}
}

static void end_sync_request(r10bio_t *r10_bio)
{
	mddev_t *mddev = r10_bio->mddev;

	while (atomic_dec_and_test(&r10_bio->remaining)) {
		if (r10_bio->master_bio == NULL) {
			/* the primary of several recovery bios */
			sector_t s = r10_bio->sectors;
			if (test_bit(R10BIO_MadeGood, &r10_bio->state) ||
			    test_bit(R10BIO_WriteError, &r10_bio->state))
				reschedule_retry(r10_bio);
			else
				put_buf(r10_bio);
			md_done_sync(mddev, s, 1);
			break;
		} else {
			r10bio_t *r10_bio2 = (r10bio_t *)r10_bio->master_bio;
			if (test_bit(R10BIO_MadeGood, &r10_bio->state) ||
			    test_bit(R10BIO_WriteError, &r10_bio->state))
				reschedule_retry(r10_bio);
			else
				put_buf(r10_bio);
			r10_bio = r10_bio2;
		}
	}
}

static void end_sync_write(struct bio *bio, int error)
{
	int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
	r10bio_t *r10_bio = bio->bi_private;
	mddev_t *mddev = r10_bio->mddev;
	conf_t *conf = mddev->private;
	int d;
	sector_t first_bad;
	int bad_sectors;
	int slot;

	d = find_bio_disk(conf, r10_bio, bio, &slot);

	if (!uptodate) {
		set_bit(WriteErrorSeen, &conf->mirrors[d].rdev->flags);
		set_bit(R10BIO_WriteError, &r10_bio->state);
	} else if (is_badblock(conf->mirrors[d].rdev,
			     r10_bio->devs[slot].addr,
			     r10_bio->sectors,
			     &first_bad, &bad_sectors))
		set_bit(R10BIO_MadeGood, &r10_bio->state);

	rdev_dec_pending(conf->mirrors[d].rdev, mddev);

	end_sync_request(r10_bio);
}

/*
 * Note: sync and recover and handled very differently for raid10
 * This code is for resync.
 * For resync, we read through virtual addresses and read all blocks.
 * If there is any error, we schedule a write.  The lowest numbered
 * drive is authoritative.
 * However requests come for physical address, so we need to map.
 * For every physical address there are raid_disks/copies virtual addresses,
 * which is always are least one, but is not necessarly an integer.
 * This means that a physical address can span multiple chunks, so we may
 * have to submit multiple io requests for a single sync request.
 */
/*
 * We check if all blocks are in-sync and only write to blocks that
 * aren't in sync
 */
static void sync_request_write(mddev_t *mddev, r10bio_t *r10_bio)
{
	conf_t *conf = mddev->private;
	int i, first;
	struct bio *tbio, *fbio;

	atomic_set(&r10_bio->remaining, 1);

	/* find the first device with a block */
	for (i=0; i<conf->copies; i++)
		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags))
			break;

	if (i == conf->copies)
		goto done;

	first = i;
	fbio = r10_bio->devs[i].bio;

	/* now find blocks with errors */
	for (i=0 ; i < conf->copies ; i++) {
		int  j, d;
		int vcnt = r10_bio->sectors >> (PAGE_SHIFT-9);

		tbio = r10_bio->devs[i].bio;

		if (tbio->bi_end_io != end_sync_read)
			continue;
		if (i == first)
			continue;
		if (test_bit(BIO_UPTODATE, &r10_bio->devs[i].bio->bi_flags)) {
			/* We know that the bi_io_vec layout is the same for
			 * both 'first' and 'i', so we just compare them.
			 * All vec entries are PAGE_SIZE;
			 */
			for (j = 0; j < vcnt; j++)
				if (memcmp(page_address(fbio->bi_io_vec[j].bv_page),
					   page_address(tbio->bi_io_vec[j].bv_page),
					   PAGE_SIZE))
					break;
			if (j == vcnt)
				continue;
			mddev->resync_mismatches += r10_bio->sectors;
			if (test_bit(MD_RECOVERY_CHECK, &mddev->recovery))
				/* Don't fix anything. */
				continue;
		}
		/* Ok, we need to write this bio, either to correct an
		 * inconsistency or to correct an unreadable block.
		 * First we need to fixup bv_offset, bv_len and
		 * bi_vecs, as the read request might have corrupted these
		 */
		tbio->bi_vcnt = vcnt;
		tbio->bi_size = r10_bio->sectors << 9;
		tbio->bi_idx = 0;
		tbio->bi_phys_segments = 0;
		tbio->bi_flags &= ~(BIO_POOL_MASK - 1);
		tbio->bi_flags |= 1 << BIO_UPTODATE;
		tbio->bi_next = NULL;
		tbio->bi_rw = WRITE;
		tbio->bi_private = r10_bio;
		tbio->bi_sector = r10_bio->devs[i].addr;

		for (j=0; j < vcnt ; j++) {
			tbio->bi_io_vec[j].bv_offset = 0;
			tbio->bi_io_vec[j].bv_len = PAGE_SIZE;

			memcpy(page_address(tbio->bi_io_vec[j].bv_page),
			       page_address(fbio->bi_io_vec[j].bv_page),
			       PAGE_SIZE);
		}
		tbio->bi_end_io = end_sync_write;

		d = r10_bio->devs[i].devnum;
		atomic_inc(&conf->mirrors[d].rdev->nr_pending);
		atomic_inc(&r10_bio->remaining);
		md_sync_acct(conf->mirrors[d].rdev->bdev, tbio->bi_size >> 9);

		tbio->bi_sector += conf->mirrors[d].rdev->data_offset;
		tbio->bi_bdev = conf->mirrors[d].rdev->bdev;
		generic_make_request(tbio);
	}

done:
	if (atomic_dec_and_test(&r10_bio->remaining)) {
		md_done_sync(mddev, r10_bio->sectors, 1);
		put_buf(r10_bio);
	}
}

/*
 * Now for the recovery code.
 * Recovery happens across physical sectors.
 * We recover all non-is_sync drives by finding the virtual address of
 * each, and then choose a working drive that also has that virt address.
 * There is a separate r10_bio for each non-in_sync drive.
 * Only the first two slots are in use. The first for reading,
 * The second for writing.
 *
 */
static void fix_recovery_read_error(r10bio_t *r10_bio)
{
	/* We got a read error during recovery.
	 * We repeat the read in smaller page-sized sections.
	 * If a read succeeds, write it to the new device or record
	 * a bad block if we cannot.
	 * If a read fails, record a bad block on both old and
	 * new devices.
	 */
	mddev_t *mddev = r10_bio->mddev;
	conf_t *conf = mddev->private;
	struct bio *bio = r10_bio->devs[0].bio;
	sector_t sect = 0;
	int sectors = r10_bio->sectors;
	int idx = 0;
	int dr = r10_bio->devs[0].devnum;
	int dw = r10_bio->devs[1].devnum;

	while (sectors) {
		int s = sectors;
		mdk_rdev_t *rdev;
		sector_t addr;
		int ok;

		if (s > (PAGE_SIZE>>9))
			s = PAGE_SIZE >> 9;

		rdev = conf->mirrors[dr].rdev;
		addr = r10_bio->devs[0].addr + sect,
		ok = sync_page_io(rdev,
				  addr,
				  s << 9,
				  bio->bi_io_vec[idx].bv_page,
				  READ, false);
		if (ok) {
			rdev = conf->mirrors[dw].rdev;
			addr = r10_bio->devs[1].addr + sect;
			ok = sync_page_io(rdev,
					  addr,
					  s << 9,
					  bio->bi_io_vec[idx].bv_page,
					  WRITE, false);
			if (!ok)
				set_bit(WriteErrorSeen, &rdev->flags);
		}
		if (!ok) {
			/* We don't worry if we cannot set a bad block -
			 * it really is bad so there is no loss in not
			 * recording it yet
			 */
			rdev_set_badblocks(rdev, addr, s, 0);

			if (rdev != conf->mirrors[dw].rdev) {
				/* need bad block on destination too */
				mdk_rdev_t *rdev2 = conf->mirrors[dw].rdev;
				addr = r10_bio->devs[1].addr + sect;
				ok = rdev_set_badblocks(rdev2, addr, s, 0);
				if (!ok) {
					/* just abort the recovery */
					printk(KERN_NOTICE
					       "md/raid10:%s: recovery aborted"
					       " due to read error\n",
					       mdname(mddev));

					conf->mirrors[dw].recovery_disabled
						= mddev->recovery_disabled;
					set_bit(MD_RECOVERY_INTR,
						&mddev->recovery);
					break;
				}
			}
		}

		sectors -= s;
		sect += s;
		idx++;
	}
}

static void recovery_request_write(mddev_t *mddev, r10bio_t *r10_bio)
{
	conf_t *conf = mddev->private;
	int d;
	struct bio *wbio;

	if (!test_bit(R10BIO_Uptodate, &r10_bio->state)) {
		fix_recovery_read_error(r10_bio);
		end_sync_request(r10_bio);
		return;
	}

	/*
	 * share the pages with the first bio
	 * and submit the write request
	 */
	wbio = r10_bio->devs[1].bio;
	d = r10_bio->devs[1].devnum;

	atomic_inc(&conf->mirrors[d].rdev->nr_pending);
	md_sync_acct(conf->mirrors[d].rdev->bdev, wbio->bi_size >> 9);
	generic_make_request(wbio);
}


/*
 * Used by fix_read_error() to decay the per rdev read_errors.
 * We halve the read error count for every hour that has elapsed
 * since the last recorded read error.
 *
 */
static void check_decay_read_errors(mddev_t *mddev, mdk_rdev_t *rdev)
{
	struct timespec cur_time_mon;
	unsigned long hours_since_last;
	unsigned int read_errors = atomic_read(&rdev->read_errors);

	ktime_get_ts(&cur_time_mon);

	if (rdev->last_read_error.tv_sec == 0 &&
	    rdev->last_read_error.tv_nsec == 0) {
		/* first time we've seen a read error */
		rdev->last_read_error = cur_time_mon;
		return;
	}

	hours_since_last = (cur_time_mon.tv_sec -
			    rdev->last_read_error.tv_sec) / 3600;

	rdev->last_read_error = cur_time_mon;

	/*
	 * if hours_since_last is > the number of bits in read_errors
	 * just set read errors to 0. We do this to avoid
	 * overflowing the shift of read_errors by hours_since_last.
	 */
	if (hours_since_last >= 8 * sizeof(read_errors))
		atomic_set(&rdev->read_errors, 0);
	else
		atomic_set(&rdev->read_errors, read_errors >> hours_since_last);
}

static int r10_sync_page_io(mdk_rdev_t *rdev, sector_t sector,
			    int sectors, struct page *page, int rw)
{
	sector_t first_bad;
	int bad_sectors;

	if (is_badblock(rdev, sector, sectors, &first_bad, &bad_sectors)
	    && (rw == READ || test_bit(WriteErrorSeen, &rdev->flags)))
		return -1;
	if (sync_page_io(rdev, sector, sectors << 9, page, rw, false))
		/* success */
		return 1;
	if (rw == WRITE)
		set_bit(WriteErrorSeen, &rdev->flags);
	/* need to record an error - either for the block or the device */
	if (!rdev_set_badblocks(rdev, sector, sectors, 0))
		md_error(rdev->mddev, rdev);
	return 0;
}

/*
 * This is a kernel thread which:
 *
 *	1.	Retries failed read operations on working mirrors.
 *	2.	Updates the raid superblock when problems encounter.
 *	3.	Performs writes following reads for array synchronising.
 */

static void fix_read_error(conf_t *conf, mddev_t *mddev, r10bio_t *r10_bio)
{
	int sect = 0; /* Offset from r10_bio->sector */
	int sectors = r10_bio->sectors;
	mdk_rdev_t*rdev;
	int max_read_errors = atomic_read(&mddev->max_corr_read_errors);
	int d = r10_bio->devs[r10_bio->read_slot].devnum;

	/* still own a reference to this rdev, so it cannot
	 * have been cleared recently.
	 */
	rdev = conf->mirrors[d].rdev;

	if (test_bit(Faulty, &rdev->flags))
		/* drive has already been failed, just ignore any
		   more fix_read_error() attempts */
		return;

	check_decay_read_errors(mddev, rdev);
	atomic_inc(&rdev->read_errors);
	if (atomic_read(&rdev->read_errors) > max_read_errors) {
		char b[BDEVNAME_SIZE];
		bdevname(rdev->bdev, b);

		printk(KERN_NOTICE
		       "md/raid10:%s: %s: Raid device exceeded "
		       "read_error threshold [cur %d:max %d]\n",
		       mdname(mddev), b,
		       atomic_read(&rdev->read_errors), max_read_errors);
		printk(KERN_NOTICE
		       "md/raid10:%s: %s: Failing raid device\n",
		       mdname(mddev), b);
		md_error(mddev, conf->mirrors[d].rdev);
		return;
	}

	while(sectors) {
		int s = sectors;
		int sl = r10_bio->read_slot;
		int success = 0;
		int start;

		if (s > (PAGE_SIZE>>9))
			s = PAGE_SIZE >> 9;

		rcu_read_lock();
		do {
			sector_t first_bad;
			int bad_sectors;

			d = r10_bio->devs[sl].devnum;
			rdev = rcu_dereference(conf->mirrors[d].rdev);
			if (rdev &&
			    test_bit(In_sync, &rdev->flags) &&
			    is_badblock(rdev, r10_bio->devs[sl].addr + sect, s,
					&first_bad, &bad_sectors) == 0) {
				atomic_inc(&rdev->nr_pending);
				rcu_read_unlock();
				success = sync_page_io(rdev,
						       r10_bio->devs[sl].addr +
						       sect,
						       s<<9,
						       conf->tmppage, READ, false);
				rdev_dec_pending(rdev, mddev);
				rcu_read_lock();
				if (success)
					break;
			}
			sl++;
			if (sl == conf->copies)
				sl = 0;
		} while (!success && sl != r10_bio->read_slot);
		rcu_read_unlock();

		if (!success) {
			/* Cannot read from anywhere, just mark the block
			 * as bad on the first device to discourage future
			 * reads.
			 */
			int dn = r10_bio->devs[r10_bio->read_slot].devnum;
			rdev = conf->mirrors[dn].rdev;

			if (!rdev_set_badblocks(
				    rdev,
				    r10_bio->devs[r10_bio->read_slot].addr
				    + sect,
				    s, 0))
				md_error(mddev, rdev);
			break;
		}

		start = sl;
		/* write it back and re-read */
		rcu_read_lock();
		while (sl != r10_bio->read_slot) {
			char b[BDEVNAME_SIZE];

			if (sl==0)
				sl = conf->copies;
			sl--;
			d = r10_bio->devs[sl].devnum;
			rdev = rcu_dereference(conf->mirrors[d].rdev);
			if (!rdev ||
			    !test_bit(In_sync, &rdev->flags))
				continue;

			atomic_inc(&rdev->nr_pending);
			rcu_read_unlock();
			if (r10_sync_page_io(rdev,
					     r10_bio->devs[sl].addr +
					     sect,
					     s<<9, conf->tmppage, WRITE)
			    == 0) {
				/* Well, this device is dead */
				printk(KERN_NOTICE
				       "md/raid10:%s: read correction "
				       "write failed"
				       " (%d sectors at %llu on %s)\n",
				       mdname(mddev), s,
				       (unsigned long long)(
					       sect + rdev->data_offset),
				       bdevname(rdev->bdev, b));
				printk(KERN_NOTICE "md/raid10:%s: %s: failing "
				       "drive\n",
				       mdname(mddev),
				       bdevname(rdev->bdev, b));
			}
			rdev_dec_pending(rdev, mddev);
			rcu_read_lock();
		}
		sl = start;
		while (sl != r10_bio->read_slot) {
			char b[BDEVNAME_SIZE];

			if (sl==0)
				sl = conf->copies;
			sl--;
			d = r10_bio->devs[sl].devnum;
			rdev = rcu_dereference(conf->mirrors[d].rdev);
			if (!rdev ||
			    !test_bit(In_sync, &rdev->flags))
				continue;

			atomic_inc(&rdev->nr_pending);
			rcu_read_unlock();
			switch (r10_sync_page_io(rdev,
					     r10_bio->devs[sl].addr +
					     sect,
					     s<<9, conf->tmppage,
						 READ)) {
			case 0:
				/* Well, this device is dead */
				printk(KERN_NOTICE
				       "md/raid10:%s: unable to read back "
				       "corrected sectors"
				       " (%d sectors at %llu on %s)\n",
				       mdname(mddev), s,
				       (unsigned long long)(
					       sect + rdev->data_offset),
				       bdevname(rdev->bdev, b));
				printk(KERN_NOTICE "md/raid10:%s: %s: failing "
				       "drive\n",
				       mdname(mddev),
				       bdevname(rdev->bdev, b));
				break;
			case 1:
				printk(KERN_INFO
				       "md/raid10:%s: read error corrected"
				       " (%d sectors at %llu on %s)\n",
				       mdname(mddev), s,
				       (unsigned long long)(
					       sect + rdev->data_offset),
				       bdevname(rdev->bdev, b));
				atomic_add(s, &rdev->corrected_errors);
			}

			rdev_dec_pending(rdev, mddev);
			rcu_read_lock();
		}
		rcu_read_unlock();

		sectors -= s;
		sect += s;
	}
}

static void bi_complete(struct bio *bio, int error)
{
	complete((struct completion *)bio->bi_private);
}

static int submit_bio_wait(int rw, struct bio *bio)
{
	struct completion event;
	rw |= REQ_SYNC;

	init_completion(&event);
	bio->bi_private = &event;
	bio->bi_end_io = bi_complete;
	submit_bio(rw, bio);
	wait_for_completion(&event);

	return test_bit(BIO_UPTODATE, &bio->bi_flags);
}

static int narrow_write_error(r10bio_t *r10_bio, int i)
{
	struct bio *bio = r10_bio->master_bio;
	mddev_t *mddev = r10_bio->mddev;
	conf_t *conf = mddev->private;
	mdk_rdev_t *rdev = conf->mirrors[r10_bio->devs[i].devnum].rdev;
	/* bio has the data to be written to slot 'i' where
	 * we just recently had a write error.
	 * We repeatedly clone the bio and trim down to one block,
	 * then try the write.  Where the write fails we record
	 * a bad block.
	 * It is conceivable that the bio doesn't exactly align with
	 * blocks.  We must handle this.
	 *
	 * We currently own a reference to the rdev.
	 */

	int block_sectors;
	sector_t sector;
	int sectors;
	int sect_to_write = r10_bio->sectors;
	int ok = 1;

	if (rdev->badblocks.shift < 0)
		return 0;

	block_sectors = 1 << rdev->badblocks.shift;
	sector = r10_bio->sector;
	sectors = ((r10_bio->sector + block_sectors)
		   & ~(sector_t)(block_sectors - 1))
		- sector;

	while (sect_to_write) {
		struct bio *wbio;
		if (sectors > sect_to_write)
			sectors = sect_to_write;
		/* Write at 'sector' for 'sectors' */
		wbio = bio_clone_mddev(bio, GFP_NOIO, mddev);
		md_trim_bio(wbio, sector - bio->bi_sector, sectors);
		wbio->bi_sector = (r10_bio->devs[i].addr+
				   rdev->data_offset+
				   (sector - r10_bio->sector));
		wbio->bi_bdev = rdev->bdev;
		if (submit_bio_wait(WRITE, wbio) == 0)
			/* Failure! */
			ok = rdev_set_badblocks(rdev, sector,
						sectors, 0)
				&& ok;

		bio_put(wbio);
		sect_to_write -= sectors;
		sector += sectors;
		sectors = block_sectors;
	}
	return ok;
}

static void handle_read_error(mddev_t *mddev, r10bio_t *r10_bio)
{
	int slot = r10_bio->read_slot;
	int mirror = r10_bio->devs[slot].devnum;
	struct bio *bio;
	conf_t *conf = mddev->private;
	mdk_rdev_t *rdev;
	char b[BDEVNAME_SIZE];
	unsigned long do_sync;
	int max_sectors;

	/* we got a read error. Maybe the drive is bad.  Maybe just
	 * the block and we can fix it.
	 * We freeze all other IO, and try reading the block from
	 * other devices.  When we find one, we re-write
	 * and check it that fixes the read error.
	 * This is all done synchronously while the array is
	 * frozen.
	 */
	if (mddev->ro == 0) {
		freeze_array(conf);
		fix_read_error(conf, mddev, r10_bio);
		unfreeze_array(conf);
	}
	rdev_dec_pending(conf->mirrors[mirror].rdev, mddev);

	bio = r10_bio->devs[slot].bio;
	bdevname(bio->bi_bdev, b);
	r10_bio->devs[slot].bio =
		mddev->ro ? IO_BLOCKED : NULL;
read_more:
	mirror = read_balance(conf, r10_bio, &max_sectors);
	if (mirror == -1) {
		printk(KERN_ALERT "md/raid10:%s: %s: unrecoverable I/O"
		       " read error for block %llu\n",
		       mdname(mddev), b,
		       (unsigned long long)r10_bio->sector);
		raid_end_bio_io(r10_bio);
		bio_put(bio);
		return;
	}

	do_sync = (r10_bio->master_bio->bi_rw & REQ_SYNC);
	if (bio)
		bio_put(bio);
	slot = r10_bio->read_slot;
	rdev = conf->mirrors[mirror].rdev;
	printk_ratelimited(
		KERN_ERR
		"md/raid10:%s: %s: redirecting"
		"sector %llu to another mirror\n",
		mdname(mddev),
		bdevname(rdev->bdev, b),
		(unsigned long long)r10_bio->sector);
	bio = bio_clone_mddev(r10_bio->master_bio,
			      GFP_NOIO, mddev);
	md_trim_bio(bio,
		    r10_bio->sector - bio->bi_sector,
		    max_sectors);
	r10_bio->devs[slot].bio = bio;
	bio->bi_sector = r10_bio->devs[slot].addr
		+ rdev->data_offset;
	bio->bi_bdev = rdev->bdev;
	bio->bi_rw = READ | do_sync;
	bio->bi_private = r10_bio;
	bio->bi_end_io = raid10_end_read_request;
	if (max_sectors < r10_bio->sectors) {
		/* Drat - have to split this up more */
		struct bio *mbio = r10_bio->master_bio;
		int sectors_handled =
			r10_bio->sector + max_sectors
			- mbio->bi_sector;
		r10_bio->sectors = max_sectors;
		spin_lock_irq(&conf->device_lock);
		if (mbio->bi_phys_segments == 0)
			mbio->bi_phys_segments = 2;
		else
			mbio->bi_phys_segments++;
		spin_unlock_irq(&conf->device_lock);
		generic_make_request(bio);
		bio = NULL;

		r10_bio = mempool_alloc(conf->r10bio_pool,
					GFP_NOIO);
		r10_bio->master_bio = mbio;
		r10_bio->sectors = (mbio->bi_size >> 9)
			- sectors_handled;
		r10_bio->state = 0;
		set_bit(R10BIO_ReadError,
			&r10_bio->state);
		r10_bio->mddev = mddev;
		r10_bio->sector = mbio->bi_sector
			+ sectors_handled;

		goto read_more;
	} else
		generic_make_request(bio);
}

static void handle_write_completed(conf_t *conf, r10bio_t *r10_bio)
{
	/* Some sort of write request has finished and it
	 * succeeded in writing where we thought there was a
	 * bad block.  So forget the bad block.
	 * Or possibly if failed and we need to record
	 * a bad block.
	 */
	int m;
	mdk_rdev_t *rdev;

	if (test_bit(R10BIO_IsSync, &r10_bio->state) ||
	    test_bit(R10BIO_IsRecover, &r10_bio->state)) {
		for (m = 0; m < conf->copies; m++) {
			int dev = r10_bio->devs[m].devnum;
			rdev = conf->mirrors[dev].rdev;
			if (r10_bio->devs[m].bio == NULL)
				continue;
			if (test_bit(BIO_UPTODATE,
				     &r10_bio->devs[m].bio->bi_flags)) {
				rdev_clear_badblocks(
					rdev,
					r10_bio->devs[m].addr,
					r10_bio->sectors);
			} else {
				if (!rdev_set_badblocks(
					    rdev,
					    r10_bio->devs[m].addr,
					    r10_bio->sectors, 0))
					md_error(conf->mddev, rdev);
			}
		}
		put_buf(r10_bio);
	} else {
		for (m = 0; m < conf->copies; m++) {
			int dev = r10_bio->devs[m].devnum;
			struct bio *bio = r10_bio->devs[m].bio;
			rdev = conf->mirrors[dev].rdev;
			if (bio == IO_MADE_GOOD) {
				rdev_clear_badblocks(
					rdev,
					r10_bio->devs[m].addr,
					r10_bio->sectors);
				rdev_dec_pending(rdev, conf->mddev);
			} else if (bio != NULL &&
				   !test_bit(BIO_UPTODATE, &bio->bi_flags)) {
				if (!narrow_write_error(r10_bio, m)) {
					md_error(conf->mddev, rdev);
					set_bit(R10BIO_Degraded,
						&r10_bio->state);
				}
				rdev_dec_pending(rdev, conf->mddev);
			}
		}
		if (test_bit(R10BIO_WriteError,
			     &r10_bio->state))
			close_write(r10_bio);
		raid_end_bio_io(r10_bio);
	}
}

static void raid10d(mddev_t *mddev)
{
	r10bio_t *r10_bio;
	unsigned long flags;
	conf_t *conf = mddev->private;
	struct list_head *head = &conf->retry_list;
	struct blk_plug plug;

	md_check_recovery(mddev);

	blk_start_plug(&plug);
	for (;;) {

		flush_pending_writes(conf);

		spin_lock_irqsave(&conf->device_lock, flags);
		if (list_empty(head)) {
			spin_unlock_irqrestore(&conf->device_lock, flags);
			break;
		}
		r10_bio = list_entry(head->prev, r10bio_t, retry_list);
		list_del(head->prev);
		conf->nr_queued--;
		spin_unlock_irqrestore(&conf->device_lock, flags);

		mddev = r10_bio->mddev;
		conf = mddev->private;
		if (test_bit(R10BIO_MadeGood, &r10_bio->state) ||
		    test_bit(R10BIO_WriteError, &r10_bio->state))
			handle_write_completed(conf, r10_bio);
		else if (test_bit(R10BIO_IsSync, &r10_bio->state))
			sync_request_write(mddev, r10_bio);
		else if (test_bit(R10BIO_IsRecover, &r10_bio->state))
			recovery_request_write(mddev, r10_bio);
		else if (test_bit(R10BIO_ReadError, &r10_bio->state))
			handle_read_error(mddev, r10_bio);
		else {
			/* just a partial read to be scheduled from a
			 * separate context
			 */
			int slot = r10_bio->read_slot;
			generic_make_request(r10_bio->devs[slot].bio);
		}

		cond_resched();
		if (mddev->flags & ~(1<<MD_CHANGE_PENDING))
			md_check_recovery(mddev);
	}
	blk_finish_plug(&plug);
}


static int init_resync(conf_t *conf)
{
	int buffs;

	buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
	BUG_ON(conf->r10buf_pool);
	conf->r10buf_pool = mempool_create(buffs, r10buf_pool_alloc, r10buf_pool_free, conf);
	if (!conf->r10buf_pool)
		return -ENOMEM;
	conf->next_resync = 0;
	return 0;
}

/*
 * perform a "sync" on one "block"
 *
 * We need to make sure that no normal I/O request - particularly write
 * requests - conflict with active sync requests.
 *
 * This is achieved by tracking pending requests and a 'barrier' concept
 * that can be installed to exclude normal IO requests.
 *
 * Resync and recovery are handled very differently.
 * We differentiate by looking at MD_RECOVERY_SYNC in mddev->recovery.
 *
 * For resync, we iterate over virtual addresses, read all copies,
 * and update if there are differences.  If only one copy is live,
 * skip it.
 * For recovery, we iterate over physical addresses, read a good
 * value for each non-in_sync drive, and over-write.
 *
 * So, for recovery we may have several outstanding complex requests for a
 * given address, one for each out-of-sync device.  We model this by allocating
 * a number of r10_bio structures, one for each out-of-sync device.
 * As we setup these structures, we collect all bio's together into a list
 * which we then process collectively to add pages, and then process again
 * to pass to generic_make_request.
 *
 * The r10_bio structures are linked using a borrowed master_bio pointer.
 * This link is counted in ->remaining.  When the r10_bio that points to NULL
 * has its remaining count decremented to 0, the whole complex operation
 * is complete.
 *
 */

static sector_t sync_request(mddev_t *mddev, sector_t sector_nr,
			     int *skipped, int go_faster)
{
	conf_t *conf = mddev->private;
	r10bio_t *r10_bio;
	struct bio *biolist = NULL, *bio;
	sector_t max_sector, nr_sectors;
	int i;
	int max_sync;
	sector_t sync_blocks;
	sector_t sectors_skipped = 0;
	int chunks_skipped = 0;

	if (!conf->r10buf_pool)
		if (init_resync(conf))
			return 0;

 skipped:
	max_sector = mddev->dev_sectors;
	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
		max_sector = mddev->resync_max_sectors;
	if (sector_nr >= max_sector) {
		/* If we aborted, we need to abort the
		 * sync on the 'current' bitmap chucks (there can
		 * be several when recovering multiple devices).
		 * as we may have started syncing it but not finished.
		 * We can find the current address in
		 * mddev->curr_resync, but for recovery,
		 * we need to convert that to several
		 * virtual addresses.
		 */
		if (mddev->curr_resync < max_sector) { /* aborted */
			if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
				bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
						&sync_blocks, 1);
			else for (i=0; i<conf->raid_disks; i++) {
				sector_t sect =
					raid10_find_virt(conf, mddev->curr_resync, i);
				bitmap_end_sync(mddev->bitmap, sect,
						&sync_blocks, 1);
			}
		} else /* completed sync */
			conf->fullsync = 0;

		bitmap_close_sync(mddev->bitmap);
		close_sync(conf);
		*skipped = 1;
		return sectors_skipped;
	}
	if (chunks_skipped >= conf->raid_disks) {
		/* if there has been nothing to do on any drive,
		 * then there is nothing to do at all..
		 */
		*skipped = 1;
		return (max_sector - sector_nr) + sectors_skipped;
	}

	if (max_sector > mddev->resync_max)
		max_sector = mddev->resync_max; /* Don't do IO beyond here */

	/* make sure whole request will fit in a chunk - if chunks
	 * are meaningful
	 */
	if (conf->near_copies < conf->raid_disks &&
	    max_sector > (sector_nr | conf->chunk_mask))
		max_sector = (sector_nr | conf->chunk_mask) + 1;
	/*
	 * If there is non-resync activity waiting for us then
	 * put in a delay to throttle resync.
	 */
	if (!go_faster && conf->nr_waiting)
		msleep_interruptible(1000);

	/* Again, very different code for resync and recovery.
	 * Both must result in an r10bio with a list of bios that
	 * have bi_end_io, bi_sector, bi_bdev set,
	 * and bi_private set to the r10bio.
	 * For recovery, we may actually create several r10bios
	 * with 2 bios in each, that correspond to the bios in the main one.
	 * In this case, the subordinate r10bios link back through a
	 * borrowed master_bio pointer, and the counter in the master
	 * includes a ref from each subordinate.
	 */
	/* First, we decide what to do and set ->bi_end_io
	 * To end_sync_read if we want to read, and
	 * end_sync_write if we will want to write.
	 */

	max_sync = RESYNC_PAGES << (PAGE_SHIFT-9);
	if (!test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
		/* recovery... the complicated one */
		int j;
		r10_bio = NULL;

		for (i=0 ; i<conf->raid_disks; i++) {
			int still_degraded;
			r10bio_t *rb2;
			sector_t sect;
			int must_sync;
			int any_working;

			if (conf->mirrors[i].rdev == NULL ||
			    test_bit(In_sync, &conf->mirrors[i].rdev->flags)) 
				continue;

			still_degraded = 0;
			/* want to reconstruct this device */
			rb2 = r10_bio;
			sect = raid10_find_virt(conf, sector_nr, i);
			/* Unless we are doing a full sync, we only need
			 * to recover the block if it is set in the bitmap
			 */
			must_sync = bitmap_start_sync(mddev->bitmap, sect,
						      &sync_blocks, 1);
			if (sync_blocks < max_sync)
				max_sync = sync_blocks;
			if (!must_sync &&
			    !conf->fullsync) {
				/* yep, skip the sync_blocks here, but don't assume
				 * that there will never be anything to do here
				 */
				chunks_skipped = -1;
				continue;
			}

			r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);
			raise_barrier(conf, rb2 != NULL);
			atomic_set(&r10_bio->remaining, 0);

			r10_bio->master_bio = (struct bio*)rb2;
			if (rb2)
				atomic_inc(&rb2->remaining);
			r10_bio->mddev = mddev;
			set_bit(R10BIO_IsRecover, &r10_bio->state);
			r10_bio->sector = sect;

			raid10_find_phys(conf, r10_bio);

			/* Need to check if the array will still be
			 * degraded
			 */
			for (j=0; j<conf->raid_disks; j++)
				if (conf->mirrors[j].rdev == NULL ||
				    test_bit(Faulty, &conf->mirrors[j].rdev->flags)) {
					still_degraded = 1;
					break;
				}

			must_sync = bitmap_start_sync(mddev->bitmap, sect,
						      &sync_blocks, still_degraded);

			any_working = 0;
			for (j=0; j<conf->copies;j++) {
				int k;
				int d = r10_bio->devs[j].devnum;
				sector_t from_addr, to_addr;
				mdk_rdev_t *rdev;
				sector_t sector, first_bad;
				int bad_sectors;
				if (!conf->mirrors[d].rdev ||
				    !test_bit(In_sync, &conf->mirrors[d].rdev->flags))
					continue;
				/* This is where we read from */
				any_working = 1;
				rdev = conf->mirrors[d].rdev;
				sector = r10_bio->devs[j].addr;

				if (is_badblock(rdev, sector, max_sync,
						&first_bad, &bad_sectors)) {
					if (first_bad > sector)
						max_sync = first_bad - sector;
					else {
						bad_sectors -= (sector
								- first_bad);
						if (max_sync > bad_sectors)
							max_sync = bad_sectors;
						continue;
					}
				}
				bio = r10_bio->devs[0].bio;
				bio->bi_next = biolist;
				biolist = bio;
				bio->bi_private = r10_bio;
				bio->bi_end_io = end_sync_read;
				bio->bi_rw = READ;
				from_addr = r10_bio->devs[j].addr;
				bio->bi_sector = from_addr +
					conf->mirrors[d].rdev->data_offset;
				bio->bi_bdev = conf->mirrors[d].rdev->bdev;
				atomic_inc(&conf->mirrors[d].rdev->nr_pending);
				atomic_inc(&r10_bio->remaining);
				/* and we write to 'i' */

				for (k=0; k<conf->copies; k++)
					if (r10_bio->devs[k].devnum == i)
						break;
				BUG_ON(k == conf->copies);
				bio = r10_bio->devs[1].bio;
				bio->bi_next = biolist;
				biolist = bio;
				bio->bi_private = r10_bio;
				bio->bi_end_io = end_sync_write;
				bio->bi_rw = WRITE;
				to_addr = r10_bio->devs[k].addr;
				bio->bi_sector = to_addr +
					conf->mirrors[i].rdev->data_offset;
				bio->bi_bdev = conf->mirrors[i].rdev->bdev;

				r10_bio->devs[0].devnum = d;
				r10_bio->devs[0].addr = from_addr;
				r10_bio->devs[1].devnum = i;
				r10_bio->devs[1].addr = to_addr;

				break;
			}
			if (j == conf->copies) {
				/* Cannot recover, so abort the recovery or
				 * record a bad block */
				put_buf(r10_bio);
				if (rb2)
					atomic_dec(&rb2->remaining);
				r10_bio = rb2;
				if (any_working) {
					/* problem is that there are bad blocks
					 * on other device(s)
					 */
					int k;
					for (k = 0; k < conf->copies; k++)
						if (r10_bio->devs[k].devnum == i)
							break;
					if (!rdev_set_badblocks(
						    conf->mirrors[i].rdev,
						    r10_bio->devs[k].addr,
						    max_sync, 0))
						any_working = 0;
				}
				if (!any_working)  {
					if (!test_and_set_bit(MD_RECOVERY_INTR,
							      &mddev->recovery))
						printk(KERN_INFO "md/raid10:%s: insufficient "
						       "working devices for recovery.\n",
						       mdname(mddev));
					conf->mirrors[i].recovery_disabled
						= mddev->recovery_disabled;
				}
				break;
			}
		}
		if (biolist == NULL) {
			while (r10_bio) {
				r10bio_t *rb2 = r10_bio;
				r10_bio = (r10bio_t*) rb2->master_bio;
				rb2->master_bio = NULL;
				put_buf(rb2);
			}
			goto giveup;
		}
	} else {
		/* resync. Schedule a read for every block at this virt offset */
		int count = 0;

		bitmap_cond_end_sync(mddev->bitmap, sector_nr);

		if (!bitmap_start_sync(mddev->bitmap, sector_nr,
				       &sync_blocks, mddev->degraded) &&
		    !conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED,
						 &mddev->recovery)) {
			/* We can skip this block */
			*skipped = 1;
			return sync_blocks + sectors_skipped;
		}
		if (sync_blocks < max_sync)
			max_sync = sync_blocks;
		r10_bio = mempool_alloc(conf->r10buf_pool, GFP_NOIO);

		r10_bio->mddev = mddev;
		atomic_set(&r10_bio->remaining, 0);
		raise_barrier(conf, 0);
		conf->next_resync = sector_nr;

		r10_bio->master_bio = NULL;
		r10_bio->sector = sector_nr;
		set_bit(R10BIO_IsSync, &r10_bio->state);
		raid10_find_phys(conf, r10_bio);
		r10_bio->sectors = (sector_nr | conf->chunk_mask) - sector_nr +1;

		for (i=0; i<conf->copies; i++) {
			int d = r10_bio->devs[i].devnum;
			sector_t first_bad, sector;
			int bad_sectors;

			bio = r10_bio->devs[i].bio;
			bio->bi_end_io = NULL;
			clear_bit(BIO_UPTODATE, &bio->bi_flags);
			if (conf->mirrors[d].rdev == NULL ||
			    test_bit(Faulty, &conf->mirrors[d].rdev->flags))
				continue;
			sector = r10_bio->devs[i].addr;
			if (is_badblock(conf->mirrors[d].rdev,
					sector, max_sync,
					&first_bad, &bad_sectors)) {
				if (first_bad > sector)
					max_sync = first_bad - sector;
				else {
					bad_sectors -= (sector - first_bad);
					if (max_sync > bad_sectors)
						max_sync = max_sync;
					continue;
				}
			}
			atomic_inc(&conf->mirrors[d].rdev->nr_pending);
			atomic_inc(&r10_bio->remaining);
			bio->bi_next = biolist;
			biolist = bio;
			bio->bi_private = r10_bio;
			bio->bi_end_io = end_sync_read;
			bio->bi_rw = READ;
			bio->bi_sector = sector +
				conf->mirrors[d].rdev->data_offset;
			bio->bi_bdev = conf->mirrors[d].rdev->bdev;
			count++;
		}

		if (count < 2) {
			for (i=0; i<conf->copies; i++) {
				int d = r10_bio->devs[i].devnum;
				if (r10_bio->devs[i].bio->bi_end_io)
					rdev_dec_pending(conf->mirrors[d].rdev,
							 mddev);
			}
			put_buf(r10_bio);
			biolist = NULL;
			goto giveup;
		}
	}

	for (bio = biolist; bio ; bio=bio->bi_next) {

		bio->bi_flags &= ~(BIO_POOL_MASK - 1);
		if (bio->bi_end_io)
			bio->bi_flags |= 1 << BIO_UPTODATE;
		bio->bi_vcnt = 0;
		bio->bi_idx = 0;
		bio->bi_phys_segments = 0;
		bio->bi_size = 0;
	}

	nr_sectors = 0;
	if (sector_nr + max_sync < max_sector)
		max_sector = sector_nr + max_sync;
	do {
		struct page *page;
		int len = PAGE_SIZE;
		if (sector_nr + (len>>9) > max_sector)
			len = (max_sector - sector_nr) << 9;
		if (len == 0)
			break;
		for (bio= biolist ; bio ; bio=bio->bi_next) {
			struct bio *bio2;
			page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
			if (bio_add_page(bio, page, len, 0))
				continue;

			/* stop here */
			bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
			for (bio2 = biolist;
			     bio2 && bio2 != bio;
			     bio2 = bio2->bi_next) {
				/* remove last page from this bio */
				bio2->bi_vcnt--;
				bio2->bi_size -= len;
				bio2->bi_flags &= ~(1<< BIO_SEG_VALID);
			}
			goto bio_full;
		}
		nr_sectors += len>>9;
		sector_nr += len>>9;
	} while (biolist->bi_vcnt < RESYNC_PAGES);
 bio_full:
	r10_bio->sectors = nr_sectors;

	while (biolist) {
		bio = biolist;
		biolist = biolist->bi_next;

		bio->bi_next = NULL;
		r10_bio = bio->bi_private;
		r10_bio->sectors = nr_sectors;

		if (bio->bi_end_io == end_sync_read) {
			md_sync_acct(bio->bi_bdev, nr_sectors);
			generic_make_request(bio);
		}
	}

	if (sectors_skipped)
		/* pretend they weren't skipped, it makes
		 * no important difference in this case
		 */
		md_done_sync(mddev, sectors_skipped, 1);

	return sectors_skipped + nr_sectors;
 giveup:
	/* There is nowhere to write, so all non-sync
	 * drives must be failed or in resync, all drives
	 * have a bad block, so try the next chunk...
	 */
	if (sector_nr + max_sync < max_sector)
		max_sector = sector_nr + max_sync;

	sectors_skipped += (max_sector - sector_nr);
	chunks_skipped ++;
	sector_nr = max_sector;
	goto skipped;
}

static sector_t
raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
{
	sector_t size;
	conf_t *conf = mddev->private;

	if (!raid_disks)
		raid_disks = conf->raid_disks;
	if (!sectors)
		sectors = conf->dev_sectors;

	size = sectors >> conf->chunk_shift;
	sector_div(size, conf->far_copies);
	size = size * raid_disks;
	sector_div(size, conf->near_copies);

	return size << conf->chunk_shift;
}


static conf_t *setup_conf(mddev_t *mddev)
{
	conf_t *conf = NULL;
	int nc, fc, fo;
	sector_t stride, size;
	int err = -EINVAL;

	if (mddev->new_chunk_sectors < (PAGE_SIZE >> 9) ||
	    !is_power_of_2(mddev->new_chunk_sectors)) {
		printk(KERN_ERR "md/raid10:%s: chunk size must be "
		       "at least PAGE_SIZE(%ld) and be a power of 2.\n",
		       mdname(mddev), PAGE_SIZE);
		goto out;
	}

	nc = mddev->new_layout & 255;
	fc = (mddev->new_layout >> 8) & 255;
	fo = mddev->new_layout & (1<<16);

	if ((nc*fc) <2 || (nc*fc) > mddev->raid_disks ||
	    (mddev->new_layout >> 17)) {
		printk(KERN_ERR "md/raid10:%s: unsupported raid10 layout: 0x%8x\n",
		       mdname(mddev), mddev->new_layout);
		goto out;
	}

	err = -ENOMEM;
	conf = kzalloc(sizeof(conf_t), GFP_KERNEL);
	if (!conf)
		goto out;

	conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks,
				GFP_KERNEL);
	if (!conf->mirrors)
		goto out;

	conf->tmppage = alloc_page(GFP_KERNEL);
	if (!conf->tmppage)
		goto out;


	conf->raid_disks = mddev->raid_disks;
	conf->near_copies = nc;
	conf->far_copies = fc;
	conf->copies = nc*fc;
	conf->far_offset = fo;
	conf->chunk_mask = mddev->new_chunk_sectors - 1;
	conf->chunk_shift = ffz(~mddev->new_chunk_sectors);

	conf->r10bio_pool = mempool_create(NR_RAID10_BIOS, r10bio_pool_alloc,
					   r10bio_pool_free, conf);
	if (!conf->r10bio_pool)
		goto out;

	size = mddev->dev_sectors >> conf->chunk_shift;
	sector_div(size, fc);
	size = size * conf->raid_disks;
	sector_div(size, nc);
	/* 'size' is now the number of chunks in the array */
	/* calculate "used chunks per device" in 'stride' */
	stride = size * conf->copies;

	/* We need to round up when dividing by raid_disks to
	 * get the stride size.
	 */
	stride += conf->raid_disks - 1;
	sector_div(stride, conf->raid_disks);

	conf->dev_sectors = stride << conf->chunk_shift;

	if (fo)
		stride = 1;
	else
		sector_div(stride, fc);
	conf->stride = stride << conf->chunk_shift;


	spin_lock_init(&conf->device_lock);
	INIT_LIST_HEAD(&conf->retry_list);

	spin_lock_init(&conf->resync_lock);
	init_waitqueue_head(&conf->wait_barrier);

	conf->thread = md_register_thread(raid10d, mddev, NULL);
	if (!conf->thread)
		goto out;

	conf->mddev = mddev;
	return conf;

 out:
	printk(KERN_ERR "md/raid10:%s: couldn't allocate memory.\n",
	       mdname(mddev));
	if (conf) {
		if (conf->r10bio_pool)
			mempool_destroy(conf->r10bio_pool);
		kfree(conf->mirrors);
		safe_put_page(conf->tmppage);
		kfree(conf);
	}
	return ERR_PTR(err);
}

static int run(mddev_t *mddev)
{
	conf_t *conf;
	int i, disk_idx, chunk_size;
	mirror_info_t *disk;
	mdk_rdev_t *rdev;
	sector_t size;

	/*
	 * copy the already verified devices into our private RAID10
	 * bookkeeping area. [whatever we allocate in run(),
	 * should be freed in stop()]
	 */

	if (mddev->private == NULL) {
		conf = setup_conf(mddev);
		if (IS_ERR(conf))
			return PTR_ERR(conf);
		mddev->private = conf;
	}
	conf = mddev->private;
	if (!conf)
		goto out;

	mddev->thread = conf->thread;
	conf->thread = NULL;

	chunk_size = mddev->chunk_sectors << 9;
	blk_queue_io_min(mddev->queue, chunk_size);
	if (conf->raid_disks % conf->near_copies)
		blk_queue_io_opt(mddev->queue, chunk_size * conf->raid_disks);
	else
		blk_queue_io_opt(mddev->queue, chunk_size *
				 (conf->raid_disks / conf->near_copies));

	list_for_each_entry(rdev, &mddev->disks, same_set) {

		disk_idx = rdev->raid_disk;
		if (disk_idx >= conf->raid_disks
		    || disk_idx < 0)
			continue;
		disk = conf->mirrors + disk_idx;

		disk->rdev = rdev;
		disk_stack_limits(mddev->gendisk, rdev->bdev,
				  rdev->data_offset << 9);
		/* as we don't honour merge_bvec_fn, we must never risk
		 * violating it, so limit max_segments to 1 lying
		 * within a single page.
		 */
		if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
			blk_queue_max_segments(mddev->queue, 1);
			blk_queue_segment_boundary(mddev->queue,
						   PAGE_CACHE_SIZE - 1);
		}

		disk->head_position = 0;
	}
	/* need to check that every block has at least one working mirror */
	if (!enough(conf, -1)) {
		printk(KERN_ERR "md/raid10:%s: not enough operational mirrors.\n",
		       mdname(mddev));
		goto out_free_conf;
	}

	mddev->degraded = 0;
	for (i = 0; i < conf->raid_disks; i++) {

		disk = conf->mirrors + i;

		if (!disk->rdev ||
		    !test_bit(In_sync, &disk->rdev->flags)) {
			disk->head_position = 0;
			mddev->degraded++;
			if (disk->rdev)
				conf->fullsync = 1;
		}
	}

	if (mddev->recovery_cp != MaxSector)
		printk(KERN_NOTICE "md/raid10:%s: not clean"
		       " -- starting background reconstruction\n",
		       mdname(mddev));
	printk(KERN_INFO
		"md/raid10:%s: active with %d out of %d devices\n",
		mdname(mddev), conf->raid_disks - mddev->degraded,
		conf->raid_disks);
	/*
	 * Ok, everything is just fine now
	 */
	mddev->dev_sectors = conf->dev_sectors;
	size = raid10_size(mddev, 0, 0);
	md_set_array_sectors(mddev, size);
	mddev->resync_max_sectors = size;

	mddev->queue->backing_dev_info.congested_fn = raid10_congested;
	mddev->queue->backing_dev_info.congested_data = mddev;

	/* Calculate max read-ahead size.
	 * We need to readahead at least twice a whole stripe....
	 * maybe...
	 */
	{
		int stripe = conf->raid_disks *
			((mddev->chunk_sectors << 9) / PAGE_SIZE);
		stripe /= conf->near_copies;
		if (mddev->queue->backing_dev_info.ra_pages < 2* stripe)
			mddev->queue->backing_dev_info.ra_pages = 2* stripe;
	}

	if (conf->near_copies < conf->raid_disks)
		blk_queue_merge_bvec(mddev->queue, raid10_mergeable_bvec);

	if (md_integrity_register(mddev))
		goto out_free_conf;

	return 0;

out_free_conf:
	md_unregister_thread(mddev->thread);
	if (conf->r10bio_pool)
		mempool_destroy(conf->r10bio_pool);
	safe_put_page(conf->tmppage);
	kfree(conf->mirrors);
	kfree(conf);
	mddev->private = NULL;
out:
	return -EIO;
}

static int stop(mddev_t *mddev)
{
	conf_t *conf = mddev->private;

	raise_barrier(conf, 0);
	lower_barrier(conf);

	md_unregister_thread(mddev->thread);
	mddev->thread = NULL;
	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
	if (conf->r10bio_pool)
		mempool_destroy(conf->r10bio_pool);
	kfree(conf->mirrors);
	kfree(conf);
	mddev->private = NULL;
	return 0;
}

static void raid10_quiesce(mddev_t *mddev, int state)
{
	conf_t *conf = mddev->private;

	switch(state) {
	case 1:
		raise_barrier(conf, 0);
		break;
	case 0:
		lower_barrier(conf);
		break;
	}
}

static void *raid10_takeover_raid0(mddev_t *mddev)
{
	mdk_rdev_t *rdev;
	conf_t *conf;

	if (mddev->degraded > 0) {
		printk(KERN_ERR "md/raid10:%s: Error: degraded raid0!\n",
		       mdname(mddev));
		return ERR_PTR(-EINVAL);
	}

	/* Set new parameters */
	mddev->new_level = 10;
	/* new layout: far_copies = 1, near_copies = 2 */
	mddev->new_layout = (1<<8) + 2;
	mddev->new_chunk_sectors = mddev->chunk_sectors;
	mddev->delta_disks = mddev->raid_disks;
	mddev->raid_disks *= 2;
	/* make sure it will be not marked as dirty */
	mddev->recovery_cp = MaxSector;

	conf = setup_conf(mddev);
	if (!IS_ERR(conf)) {
		list_for_each_entry(rdev, &mddev->disks, same_set)
			if (rdev->raid_disk >= 0)
				rdev->new_raid_disk = rdev->raid_disk * 2;
		conf->barrier = 1;
	}

	return conf;
}

static void *raid10_takeover(mddev_t *mddev)
{
	struct raid0_private_data *raid0_priv;

	/* raid10 can take over:
	 *  raid0 - providing it has only two drives
	 */
	if (mddev->level == 0) {
		/* for raid0 takeover only one zone is supported */
		raid0_priv = mddev->private;
		if (raid0_priv->nr_strip_zones > 1) {
			printk(KERN_ERR "md/raid10:%s: cannot takeover raid 0"
			       " with more than one zone.\n",
			       mdname(mddev));
			return ERR_PTR(-EINVAL);
		}
		return raid10_takeover_raid0(mddev);
	}
	return ERR_PTR(-EINVAL);
}

static struct mdk_personality raid10_personality =
{
	.name		= "raid10",
	.level		= 10,
	.owner		= THIS_MODULE,
	.make_request	= make_request,
	.run		= run,
	.stop		= stop,
	.status		= status,
	.error_handler	= error,
	.hot_add_disk	= raid10_add_disk,
	.hot_remove_disk= raid10_remove_disk,
	.spare_active	= raid10_spare_active,
	.sync_request	= sync_request,
	.quiesce	= raid10_quiesce,
	.size		= raid10_size,
	.takeover	= raid10_takeover,
};

static int __init raid_init(void)
{
	return register_md_personality(&raid10_personality);
}

static void raid_exit(void)
{
	unregister_md_personality(&raid10_personality);
}

module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("RAID10 (striped mirror) personality for MD");
MODULE_ALIAS("md-personality-9"); /* RAID10 */
MODULE_ALIAS("md-raid10");
MODULE_ALIAS("md-level-10");