1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
|
/*
* raid1.c : Multiple Devices driver for Linux
*
* Copyright (C) 1999, 2000, 2001 Ingo Molnar, Red Hat
*
* Copyright (C) 1996, 1997, 1998 Ingo Molnar, Miguel de Icaza, Gadi Oxman
*
* RAID-1 management functions.
*
* Better read-balancing code written by Mika Kuoppala <miku@iki.fi>, 2000
*
* Fixes to reconstruction by Jakob Østergaard" <jakob@ostenfeld.dk>
* Various fixes by Neil Brown <neilb@cse.unsw.edu.au>
*
* Changes by Peter T. Breuer <ptb@it.uc3m.es> 31/1/2003 to support
* bitmapped intelligence in resync:
*
* - bitmap marked during normal i/o
* - bitmap used to skip nondirty blocks during sync
*
* Additions to bitmap code, (C) 2003-2004 Paul Clements, SteelEye Technology:
* - persistent bitmap code
*
* 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/module.h>
#include <linux/seq_file.h>
#include <linux/ratelimit.h>
#include <trace/events/block.h>
#include "md.h"
#include "raid1.h"
#include "md-bitmap.h"
#define UNSUPPORTED_MDDEV_FLAGS \
((1L << MD_HAS_JOURNAL) | \
(1L << MD_JOURNAL_CLEAN) | \
(1L << MD_HAS_PPL) | \
(1L << MD_HAS_MULTIPLE_PPLS))
/*
* Number of guaranteed r1bios in case of extreme VM load:
*/
#define NR_RAID1_BIOS 256
/* when we get a read error on a read-only array, we redirect to another
* device without failing the first device, or trying to over-write to
* correct the read error. To keep track of bad blocks on a per-bio
* level, we store IO_BLOCKED in the appropriate 'bios' pointer
*/
#define IO_BLOCKED ((struct bio *)1)
/* When we successfully write to a known bad-block, we need to remove the
* bad-block marking which must be done from process context. So we record
* the success by setting devs[n].bio to IO_MADE_GOOD
*/
#define IO_MADE_GOOD ((struct bio *)2)
#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
/* When there are this many requests queue to be written by
* the raid1 thread, we become 'congested' to provide back-pressure
* for writeback.
*/
static int max_queued_requests = 1024;
static void allow_barrier(struct r1conf *conf, sector_t sector_nr);
static void lower_barrier(struct r1conf *conf, sector_t sector_nr);
#define raid1_log(md, fmt, args...) \
do { if ((md)->queue) blk_add_trace_msg((md)->queue, "raid1 " fmt, ##args); } while (0)
#include "raid1-10.c"
/*
* for resync bio, r1bio pointer can be retrieved from the per-bio
* 'struct resync_pages'.
*/
static inline struct r1bio *get_resync_r1bio(struct bio *bio)
{
return get_resync_pages(bio)->raid_bio;
}
static void * r1bio_pool_alloc(gfp_t gfp_flags, void *data)
{
struct pool_info *pi = data;
int size = offsetof(struct r1bio, bios[pi->raid_disks]);
/* allocate a r1bio with room for raid_disks entries in the bios array */
return kzalloc(size, gfp_flags);
}
static void r1bio_pool_free(void *r1_bio, void *data)
{
kfree(r1_bio);
}
#define RESYNC_DEPTH 32
#define RESYNC_SECTORS (RESYNC_BLOCK_SIZE >> 9)
#define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH)
#define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9)
#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW)
#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9)
static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
{
struct pool_info *pi = data;
struct r1bio *r1_bio;
struct bio *bio;
int need_pages;
int j;
struct resync_pages *rps;
r1_bio = r1bio_pool_alloc(gfp_flags, pi);
if (!r1_bio)
return NULL;
rps = kmalloc_array(pi->raid_disks, sizeof(struct resync_pages),
gfp_flags);
if (!rps)
goto out_free_r1bio;
/*
* Allocate bios : 1 for reading, n-1 for writing
*/
for (j = pi->raid_disks ; j-- ; ) {
bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
if (!bio)
goto out_free_bio;
r1_bio->bios[j] = bio;
}
/*
* Allocate RESYNC_PAGES data pages and attach them to
* the first bio.
* If this is a user-requested check/repair, allocate
* RESYNC_PAGES for each bio.
*/
if (test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery))
need_pages = pi->raid_disks;
else
need_pages = 1;
for (j = 0; j < pi->raid_disks; j++) {
struct resync_pages *rp = &rps[j];
bio = r1_bio->bios[j];
if (j < need_pages) {
if (resync_alloc_pages(rp, gfp_flags))
goto out_free_pages;
} else {
memcpy(rp, &rps[0], sizeof(*rp));
resync_get_all_pages(rp);
}
rp->raid_bio = r1_bio;
bio->bi_private = rp;
}
r1_bio->master_bio = NULL;
return r1_bio;
out_free_pages:
while (--j >= 0)
resync_free_pages(&rps[j]);
out_free_bio:
while (++j < pi->raid_disks)
bio_put(r1_bio->bios[j]);
kfree(rps);
out_free_r1bio:
r1bio_pool_free(r1_bio, data);
return NULL;
}
static void r1buf_pool_free(void *__r1_bio, void *data)
{
struct pool_info *pi = data;
int i;
struct r1bio *r1bio = __r1_bio;
struct resync_pages *rp = NULL;
for (i = pi->raid_disks; i--; ) {
rp = get_resync_pages(r1bio->bios[i]);
resync_free_pages(rp);
bio_put(r1bio->bios[i]);
}
/* resync pages array stored in the 1st bio's .bi_private */
kfree(rp);
r1bio_pool_free(r1bio, data);
}
static void put_all_bios(struct r1conf *conf, struct r1bio *r1_bio)
{
int i;
for (i = 0; i < conf->raid_disks * 2; i++) {
struct bio **bio = r1_bio->bios + i;
if (!BIO_SPECIAL(*bio))
bio_put(*bio);
*bio = NULL;
}
}
static void free_r1bio(struct r1bio *r1_bio)
{
struct r1conf *conf = r1_bio->mddev->private;
put_all_bios(conf, r1_bio);
mempool_free(r1_bio, &conf->r1bio_pool);
}
static void put_buf(struct r1bio *r1_bio)
{
struct r1conf *conf = r1_bio->mddev->private;
sector_t sect = r1_bio->sector;
int i;
for (i = 0; i < conf->raid_disks * 2; i++) {
struct bio *bio = r1_bio->bios[i];
if (bio->bi_end_io)
rdev_dec_pending(conf->mirrors[i].rdev, r1_bio->mddev);
}
mempool_free(r1_bio, &conf->r1buf_pool);
lower_barrier(conf, sect);
}
static void reschedule_retry(struct r1bio *r1_bio)
{
unsigned long flags;
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
int idx;
idx = sector_to_idx(r1_bio->sector);
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&r1_bio->retry_list, &conf->retry_list);
atomic_inc(&conf->nr_queued[idx]);
spin_unlock_irqrestore(&conf->device_lock, flags);
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 call_bio_endio(struct r1bio *r1_bio)
{
struct bio *bio = r1_bio->master_bio;
struct r1conf *conf = r1_bio->mddev->private;
if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
bio->bi_status = BLK_STS_IOERR;
bio_endio(bio);
/*
* Wake up any possible resync thread that waits for the device
* to go idle.
*/
allow_barrier(conf, r1_bio->sector);
}
static void raid_end_bio_io(struct r1bio *r1_bio)
{
struct bio *bio = r1_bio->master_bio;
/* if nobody has done the final endio yet, do it now */
if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
pr_debug("raid1: sync end %s on sectors %llu-%llu\n",
(bio_data_dir(bio) == WRITE) ? "write" : "read",
(unsigned long long) bio->bi_iter.bi_sector,
(unsigned long long) bio_end_sector(bio) - 1);
call_bio_endio(r1_bio);
}
free_r1bio(r1_bio);
}
/*
* Update disk head position estimator based on IRQ completion info.
*/
static inline void update_head_pos(int disk, struct r1bio *r1_bio)
{
struct r1conf *conf = r1_bio->mddev->private;
conf->mirrors[disk].head_position =
r1_bio->sector + (r1_bio->sectors);
}
/*
* Find the disk number which triggered given bio
*/
static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio)
{
int mirror;
struct r1conf *conf = r1_bio->mddev->private;
int raid_disks = conf->raid_disks;
for (mirror = 0; mirror < raid_disks * 2; mirror++)
if (r1_bio->bios[mirror] == bio)
break;
BUG_ON(mirror == raid_disks * 2);
update_head_pos(mirror, r1_bio);
return mirror;
}
static void raid1_end_read_request(struct bio *bio)
{
int uptodate = !bio->bi_status;
struct r1bio *r1_bio = bio->bi_private;
struct r1conf *conf = r1_bio->mddev->private;
struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
update_head_pos(r1_bio->read_disk, r1_bio);
if (uptodate)
set_bit(R1BIO_Uptodate, &r1_bio->state);
else if (test_bit(FailFast, &rdev->flags) &&
test_bit(R1BIO_FailFast, &r1_bio->state))
/* This was a fail-fast read so we definitely
* want to retry */
;
else {
/* If all other devices have failed, we want to return
* the error upwards rather than fail the last device.
* Here we redefine "uptodate" to mean "Don't want to retry"
*/
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
if (r1_bio->mddev->degraded == conf->raid_disks ||
(r1_bio->mddev->degraded == conf->raid_disks-1 &&
test_bit(In_sync, &rdev->flags)))
uptodate = 1;
spin_unlock_irqrestore(&conf->device_lock, flags);
}
if (uptodate) {
raid_end_bio_io(r1_bio);
rdev_dec_pending(rdev, conf->mddev);
} else {
/*
* oops, read error:
*/
char b[BDEVNAME_SIZE];
pr_err_ratelimited("md/raid1:%s: %s: rescheduling sector %llu\n",
mdname(conf->mddev),
bdevname(rdev->bdev, b),
(unsigned long long)r1_bio->sector);
set_bit(R1BIO_ReadError, &r1_bio->state);
reschedule_retry(r1_bio);
/* don't drop the reference on read_disk yet */
}
}
static void close_write(struct r1bio *r1_bio)
{
/* it really is the end of this request */
if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
bio_free_pages(r1_bio->behind_master_bio);
bio_put(r1_bio->behind_master_bio);
r1_bio->behind_master_bio = NULL;
}
/* clear the bitmap if all writes complete successfully */
md_bitmap_endwrite(r1_bio->mddev->bitmap, r1_bio->sector,
r1_bio->sectors,
!test_bit(R1BIO_Degraded, &r1_bio->state),
test_bit(R1BIO_BehindIO, &r1_bio->state));
md_write_end(r1_bio->mddev);
}
static void r1_bio_write_done(struct r1bio *r1_bio)
{
if (!atomic_dec_and_test(&r1_bio->remaining))
return;
if (test_bit(R1BIO_WriteError, &r1_bio->state))
reschedule_retry(r1_bio);
else {
close_write(r1_bio);
if (test_bit(R1BIO_MadeGood, &r1_bio->state))
reschedule_retry(r1_bio);
else
raid_end_bio_io(r1_bio);
}
}
static void raid1_end_write_request(struct bio *bio)
{
struct r1bio *r1_bio = bio->bi_private;
int behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
struct r1conf *conf = r1_bio->mddev->private;
struct bio *to_put = NULL;
int mirror = find_bio_disk(r1_bio, bio);
struct md_rdev *rdev = conf->mirrors[mirror].rdev;
bool discard_error;
discard_error = bio->bi_status && bio_op(bio) == REQ_OP_DISCARD;
/*
* 'one mirror IO has finished' event handler:
*/
if (bio->bi_status && !discard_error) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
conf->mddev->recovery);
if (test_bit(FailFast, &rdev->flags) &&
(bio->bi_opf & MD_FAILFAST) &&
/* We never try FailFast to WriteMostly devices */
!test_bit(WriteMostly, &rdev->flags)) {
md_error(r1_bio->mddev, rdev);
}
/*
* When the device is faulty, it is not necessary to
* handle write error.
* For failfast, this is the only remaining device,
* We need to retry the write without FailFast.
*/
if (!test_bit(Faulty, &rdev->flags))
set_bit(R1BIO_WriteError, &r1_bio->state);
else {
/* Finished with this branch */
r1_bio->bios[mirror] = NULL;
to_put = bio;
}
} else {
/*
* Set R1BIO_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;
r1_bio->bios[mirror] = NULL;
to_put = bio;
/*
* Do not set R1BIO_Uptodate if the current device is
* rebuilding or Faulty. This is because we cannot use
* such device for properly reading the data back (we could
* potentially use it, if the current write would have felt
* before rdev->recovery_offset, but for simplicity we don't
* check this here.
*/
if (test_bit(In_sync, &rdev->flags) &&
!test_bit(Faulty, &rdev->flags))
set_bit(R1BIO_Uptodate, &r1_bio->state);
/* Maybe we can clear some bad blocks. */
if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
&first_bad, &bad_sectors) && !discard_error) {
r1_bio->bios[mirror] = IO_MADE_GOOD;
set_bit(R1BIO_MadeGood, &r1_bio->state);
}
}
if (behind) {
if (test_bit(WriteMostly, &rdev->flags))
atomic_dec(&r1_bio->behind_remaining);
/*
* In behind mode, we ACK the master bio once the I/O
* has safely reached all non-writemostly
* disks. Setting the Returned bit ensures that this
* gets done only once -- we don't ever want to return
* -EIO here, instead we'll wait
*/
if (atomic_read(&r1_bio->behind_remaining) >= (atomic_read(&r1_bio->remaining)-1) &&
test_bit(R1BIO_Uptodate, &r1_bio->state)) {
/* Maybe we can return now */
if (!test_and_set_bit(R1BIO_Returned, &r1_bio->state)) {
struct bio *mbio = r1_bio->master_bio;
pr_debug("raid1: behind end write sectors"
" %llu-%llu\n",
(unsigned long long) mbio->bi_iter.bi_sector,
(unsigned long long) bio_end_sector(mbio) - 1);
call_bio_endio(r1_bio);
}
}
}
if (r1_bio->bios[mirror] == NULL)
rdev_dec_pending(rdev, conf->mddev);
/*
* Let's see if all mirrored write operations have finished
* already.
*/
r1_bio_write_done(r1_bio);
if (to_put)
bio_put(to_put);
}
static sector_t align_to_barrier_unit_end(sector_t start_sector,
sector_t sectors)
{
sector_t len;
WARN_ON(sectors == 0);
/*
* len is the number of sectors from start_sector to end of the
* barrier unit which start_sector belongs to.
*/
len = round_up(start_sector + 1, BARRIER_UNIT_SECTOR_SIZE) -
start_sector;
if (len > sectors)
len = sectors;
return len;
}
/*
* 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.
*/
static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sectors)
{
const sector_t this_sector = r1_bio->sector;
int sectors;
int best_good_sectors;
int best_disk, best_dist_disk, best_pending_disk;
int has_nonrot_disk;
int disk;
sector_t best_dist;
unsigned int min_pending;
struct md_rdev *rdev;
int choose_first;
int choose_next_idle;
rcu_read_lock();
/*
* Check if we can balance. We can balance on the whole
* device if no resync is going on, or below the resync window.
* We take the first readable disk when above the resync window.
*/
retry:
sectors = r1_bio->sectors;
best_disk = -1;
best_dist_disk = -1;
best_dist = MaxSector;
best_pending_disk = -1;
min_pending = UINT_MAX;
best_good_sectors = 0;
has_nonrot_disk = 0;
choose_next_idle = 0;
clear_bit(R1BIO_FailFast, &r1_bio->state);
if ((conf->mddev->recovery_cp < this_sector + sectors) ||
(mddev_is_clustered(conf->mddev) &&
md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
this_sector + sectors)))
choose_first = 1;
else
choose_first = 0;
for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
sector_t dist;
sector_t first_bad;
int bad_sectors;
unsigned int pending;
bool nonrot;
rdev = rcu_dereference(conf->mirrors[disk].rdev);
if (r1_bio->bios[disk] == IO_BLOCKED
|| rdev == NULL
|| test_bit(Faulty, &rdev->flags))
continue;
if (!test_bit(In_sync, &rdev->flags) &&
rdev->recovery_offset < this_sector + sectors)
continue;
if (test_bit(WriteMostly, &rdev->flags)) {
/* Don't balance among write-mostly, just
* use the first as a last resort */
if (best_dist_disk < 0) {
if (is_badblock(rdev, this_sector, sectors,
&first_bad, &bad_sectors)) {
if (first_bad <= this_sector)
/* Cannot use this */
continue;
best_good_sectors = first_bad - this_sector;
} else
best_good_sectors = sectors;
best_dist_disk = disk;
best_pending_disk = disk;
}
continue;
}
/* This is a reasonable device to use. It might
* even be best.
*/
if (is_badblock(rdev, this_sector, sectors,
&first_bad, &bad_sectors)) {
if (best_dist < MaxSector)
/* already have a better device */
continue;
if (first_bad <= this_sector) {
/* cannot read here. If this is the 'primary'
* device, then we must not read beyond
* bad_sectors from another device..
*/
bad_sectors -= (this_sector - first_bad);
if (choose_first && sectors > bad_sectors)
sectors = bad_sectors;
if (best_good_sectors > sectors)
best_good_sectors = sectors;
} else {
sector_t good_sectors = first_bad - this_sector;
if (good_sectors > best_good_sectors) {
best_good_sectors = good_sectors;
best_disk = disk;
}
if (choose_first)
break;
}
continue;
} else {
if ((sectors > best_good_sectors) && (best_disk >= 0))
best_disk = -1;
best_good_sectors = sectors;
}
if (best_disk >= 0)
/* At least two disks to choose from so failfast is OK */
set_bit(R1BIO_FailFast, &r1_bio->state);
nonrot = blk_queue_nonrot(bdev_get_queue(rdev->bdev));
has_nonrot_disk |= nonrot;
pending = atomic_read(&rdev->nr_pending);
dist = abs(this_sector - conf->mirrors[disk].head_position);
if (choose_first) {
best_disk = disk;
break;
}
/* Don't change to another disk for sequential reads */
if (conf->mirrors[disk].next_seq_sect == this_sector
|| dist == 0) {
int opt_iosize = bdev_io_opt(rdev->bdev) >> 9;
struct raid1_info *mirror = &conf->mirrors[disk];
best_disk = disk;
/*
* If buffered sequential IO size exceeds optimal
* iosize, check if there is idle disk. If yes, choose
* the idle disk. read_balance could already choose an
* idle disk before noticing it's a sequential IO in
* this disk. This doesn't matter because this disk
* will idle, next time it will be utilized after the
* first disk has IO size exceeds optimal iosize. In
* this way, iosize of the first disk will be optimal
* iosize at least. iosize of the second disk might be
* small, but not a big deal since when the second disk
* starts IO, the first disk is likely still busy.
*/
if (nonrot && opt_iosize > 0 &&
mirror->seq_start != MaxSector &&
mirror->next_seq_sect > opt_iosize &&
mirror->next_seq_sect - opt_iosize >=
mirror->seq_start) {
choose_next_idle = 1;
continue;
}
break;
}
if (choose_next_idle)
continue;
if (min_pending > pending) {
min_pending = pending;
best_pending_disk = disk;
}
if (dist < best_dist) {
best_dist = dist;
best_dist_disk = disk;
}
}
/*
* If all disks are rotational, choose the closest disk. If any disk is
* non-rotational, choose the disk with less pending request even the
* disk is rotational, which might/might not be optimal for raids with
* mixed ratation/non-rotational disks depending on workload.
*/
if (best_disk == -1) {
if (has_nonrot_disk || min_pending == 0)
best_disk = best_pending_disk;
else
best_disk = best_dist_disk;
}
if (best_disk >= 0) {
rdev = rcu_dereference(conf->mirrors[best_disk].rdev);
if (!rdev)
goto retry;
atomic_inc(&rdev->nr_pending);
sectors = best_good_sectors;
if (conf->mirrors[best_disk].next_seq_sect != this_sector)
conf->mirrors[best_disk].seq_start = this_sector;
conf->mirrors[best_disk].next_seq_sect = this_sector + sectors;
}
rcu_read_unlock();
*max_sectors = sectors;
return best_disk;
}
static int raid1_congested(struct mddev *mddev, int bits)
{
struct r1conf *conf = mddev->private;
int i, ret = 0;
if ((bits & (1 << WB_async_congested)) &&
conf->pending_count >= max_queued_requests)
return 1;
rcu_read_lock();
for (i = 0; i < conf->raid_disks * 2; i++) {
struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q = bdev_get_queue(rdev->bdev);
BUG_ON(!q);
/* Note the '|| 1' - when read_balance prefers
* non-congested targets, it can be removed
*/
if ((bits & (1 << WB_async_congested)) || 1)
ret |= bdi_congested(q->backing_dev_info, bits);
else
ret &= bdi_congested(q->backing_dev_info, bits);
}
}
rcu_read_unlock();
return ret;
}
static void flush_bio_list(struct r1conf *conf, struct bio *bio)
{
/* flush any pending bitmap writes to disk before proceeding w/ I/O */
md_bitmap_unplug(conf->mddev->bitmap);
wake_up(&conf->wait_barrier);
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
struct md_rdev *rdev = (void *)bio->bi_disk;
bio->bi_next = NULL;
bio_set_dev(bio, rdev->bdev);
if (test_bit(Faulty, &rdev->flags)) {
bio_io_error(bio);
} else if (unlikely((bio_op(bio) == REQ_OP_DISCARD) &&
!blk_queue_discard(bio->bi_disk->queue)))
/* Just ignore it */
bio_endio(bio);
else
generic_make_request(bio);
bio = next;
}
}
static void flush_pending_writes(struct r1conf *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 blk_plug plug;
struct bio *bio;
bio = bio_list_get(&conf->pending_bio_list);
conf->pending_count = 0;
spin_unlock_irq(&conf->device_lock);
/*
* As this is called in a wait_event() loop (see freeze_array),
* current->state might be TASK_UNINTERRUPTIBLE which will
* cause a warning when we prepare to wait again. As it is
* rare that this path is taken, it is perfectly safe to force
* us to go around the wait_event() loop again, so the warning
* is a false-positive. Silence the warning by resetting
* thread state
*/
__set_current_state(TASK_RUNNING);
blk_start_plug(&plug);
flush_bio_list(conf, bio);
blk_finish_plug(&plug);
} 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 sector_t raise_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
spin_lock_irq(&conf->resync_lock);
/* Wait until no block IO is waiting */
wait_event_lock_irq(conf->wait_barrier,
!atomic_read(&conf->nr_waiting[idx]),
conf->resync_lock);
/* block any new IO from starting */
atomic_inc(&conf->barrier[idx]);
/*
* In raise_barrier() we firstly increase conf->barrier[idx] then
* check conf->nr_pending[idx]. In _wait_barrier() we firstly
* increase conf->nr_pending[idx] then check conf->barrier[idx].
* A memory barrier here to make sure conf->nr_pending[idx] won't
* be fetched before conf->barrier[idx] is increased. Otherwise
* there will be a race between raise_barrier() and _wait_barrier().
*/
smp_mb__after_atomic();
/* For these conditions we must wait:
* A: while the array is in frozen state
* B: while conf->nr_pending[idx] is not 0, meaning regular I/O
* existing in corresponding I/O barrier bucket.
* C: while conf->barrier[idx] >= RESYNC_DEPTH, meaning reaches
* max resync count which allowed on current I/O barrier bucket.
*/
wait_event_lock_irq(conf->wait_barrier,
(!conf->array_frozen &&
!atomic_read(&conf->nr_pending[idx]) &&
atomic_read(&conf->barrier[idx]) < RESYNC_DEPTH) ||
test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery),
conf->resync_lock);
if (test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
atomic_dec(&conf->barrier[idx]);
spin_unlock_irq(&conf->resync_lock);
wake_up(&conf->wait_barrier);
return -EINTR;
}
atomic_inc(&conf->nr_sync_pending);
spin_unlock_irq(&conf->resync_lock);
return 0;
}
static void lower_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
BUG_ON(atomic_read(&conf->barrier[idx]) <= 0);
atomic_dec(&conf->barrier[idx]);
atomic_dec(&conf->nr_sync_pending);
wake_up(&conf->wait_barrier);
}
static void _wait_barrier(struct r1conf *conf, int idx)
{
/*
* We need to increase conf->nr_pending[idx] very early here,
* then raise_barrier() can be blocked when it waits for
* conf->nr_pending[idx] to be 0. Then we can avoid holding
* conf->resync_lock when there is no barrier raised in same
* barrier unit bucket. Also if the array is frozen, I/O
* should be blocked until array is unfrozen.
*/
atomic_inc(&conf->nr_pending[idx]);
/*
* In _wait_barrier() we firstly increase conf->nr_pending[idx], then
* check conf->barrier[idx]. In raise_barrier() we firstly increase
* conf->barrier[idx], then check conf->nr_pending[idx]. A memory
* barrier is necessary here to make sure conf->barrier[idx] won't be
* fetched before conf->nr_pending[idx] is increased. Otherwise there
* will be a race between _wait_barrier() and raise_barrier().
*/
smp_mb__after_atomic();
/*
* Don't worry about checking two atomic_t variables at same time
* here. If during we check conf->barrier[idx], the array is
* frozen (conf->array_frozen is 1), and chonf->barrier[idx] is
* 0, it is safe to return and make the I/O continue. Because the
* array is frozen, all I/O returned here will eventually complete
* or be queued, no race will happen. See code comment in
* frozen_array().
*/
if (!READ_ONCE(conf->array_frozen) &&
!atomic_read(&conf->barrier[idx]))
return;
/*
* After holding conf->resync_lock, conf->nr_pending[idx]
* should be decreased before waiting for barrier to drop.
* Otherwise, we may encounter a race condition because
* raise_barrer() might be waiting for conf->nr_pending[idx]
* to be 0 at same time.
*/
spin_lock_irq(&conf->resync_lock);
atomic_inc(&conf->nr_waiting[idx]);
atomic_dec(&conf->nr_pending[idx]);
/*
* In case freeze_array() is waiting for
* get_unqueued_pending() == extra
*/
wake_up(&conf->wait_barrier);
/* Wait for the barrier in same barrier unit bucket to drop. */
wait_event_lock_irq(conf->wait_barrier,
!conf->array_frozen &&
!atomic_read(&conf->barrier[idx]),
conf->resync_lock);
atomic_inc(&conf->nr_pending[idx]);
atomic_dec(&conf->nr_waiting[idx]);
spin_unlock_irq(&conf->resync_lock);
}
static void wait_read_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
/*
* Very similar to _wait_barrier(). The difference is, for read
* I/O we don't need wait for sync I/O, but if the whole array
* is frozen, the read I/O still has to wait until the array is
* unfrozen. Since there is no ordering requirement with
* conf->barrier[idx] here, memory barrier is unnecessary as well.
*/
atomic_inc(&conf->nr_pending[idx]);
if (!READ_ONCE(conf->array_frozen))
return;
spin_lock_irq(&conf->resync_lock);
atomic_inc(&conf->nr_waiting[idx]);
atomic_dec(&conf->nr_pending[idx]);
/*
* In case freeze_array() is waiting for
* get_unqueued_pending() == extra
*/
wake_up(&conf->wait_barrier);
/* Wait for array to be unfrozen */
wait_event_lock_irq(conf->wait_barrier,
!conf->array_frozen,
conf->resync_lock);
atomic_inc(&conf->nr_pending[idx]);
atomic_dec(&conf->nr_waiting[idx]);
spin_unlock_irq(&conf->resync_lock);
}
static void wait_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
_wait_barrier(conf, idx);
}
static void _allow_barrier(struct r1conf *conf, int idx)
{
atomic_dec(&conf->nr_pending[idx]);
wake_up(&conf->wait_barrier);
}
static void allow_barrier(struct r1conf *conf, sector_t sector_nr)
{
int idx = sector_to_idx(sector_nr);
_allow_barrier(conf, idx);
}
/* conf->resync_lock should be held */
static int get_unqueued_pending(struct r1conf *conf)
{
int idx, ret;
ret = atomic_read(&conf->nr_sync_pending);
for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++)
ret += atomic_read(&conf->nr_pending[idx]) -
atomic_read(&conf->nr_queued[idx]);
return ret;
}
static void freeze_array(struct r1conf *conf, int extra)
{
/* Stop sync I/O and normal I/O and wait for everything to
* go quiet.
* This is called in two situations:
* 1) management command handlers (reshape, remove disk, quiesce).
* 2) one normal I/O request failed.
* After array_frozen is set to 1, new sync IO will be blocked at
* raise_barrier(), and new normal I/O will blocked at _wait_barrier()
* or wait_read_barrier(). The flying I/Os will either complete or be
* queued. When everything goes quite, there are only queued I/Os left.
* Every flying I/O contributes to a conf->nr_pending[idx], idx is the
* barrier bucket index which this I/O request hits. When all sync and
* normal I/O are queued, sum of all conf->nr_pending[] will match sum
* of all conf->nr_queued[]. But normal I/O failure is an exception,
* in handle_read_error(), we may call freeze_array() before trying to
* fix the read error. In this case, the error read I/O is not queued,
* so get_unqueued_pending() == 1.
*
* Therefore before this function returns, we need to wait until
* get_unqueued_pendings(conf) gets equal to extra. For
* normal I/O context, extra is 1, in rested situations extra is 0.
*/
spin_lock_irq(&conf->resync_lock);
conf->array_frozen = 1;
raid1_log(conf->mddev, "wait freeze");
wait_event_lock_irq_cmd(
conf->wait_barrier,
get_unqueued_pending(conf) == extra,
conf->resync_lock,
flush_pending_writes(conf));
spin_unlock_irq(&conf->resync_lock);
}
static void unfreeze_array(struct r1conf *conf)
{
/* reverse the effect of the freeze */
spin_lock_irq(&conf->resync_lock);
conf->array_frozen = 0;
spin_unlock_irq(&conf->resync_lock);
wake_up(&conf->wait_barrier);
}
static void alloc_behind_master_bio(struct r1bio *r1_bio,
struct bio *bio)
{
int size = bio->bi_iter.bi_size;
unsigned vcnt = (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
int i = 0;
struct bio *behind_bio = NULL;
behind_bio = bio_alloc_mddev(GFP_NOIO, vcnt, r1_bio->mddev);
if (!behind_bio)
return;
/* discard op, we don't support writezero/writesame yet */
if (!bio_has_data(bio)) {
behind_bio->bi_iter.bi_size = size;
goto skip_copy;
}
behind_bio->bi_write_hint = bio->bi_write_hint;
while (i < vcnt && size) {
struct page *page;
int len = min_t(int, PAGE_SIZE, size);
page = alloc_page(GFP_NOIO);
if (unlikely(!page))
goto free_pages;
bio_add_page(behind_bio, page, len, 0);
size -= len;
i++;
}
bio_copy_data(behind_bio, bio);
skip_copy:
r1_bio->behind_master_bio = behind_bio;
set_bit(R1BIO_BehindIO, &r1_bio->state);
return;
free_pages:
pr_debug("%dB behind alloc failed, doing sync I/O\n",
bio->bi_iter.bi_size);
bio_free_pages(behind_bio);
bio_put(behind_bio);
}
struct raid1_plug_cb {
struct blk_plug_cb cb;
struct bio_list pending;
int pending_cnt;
};
static void raid1_unplug(struct blk_plug_cb *cb, bool from_schedule)
{
struct raid1_plug_cb *plug = container_of(cb, struct raid1_plug_cb,
cb);
struct mddev *mddev = plug->cb.data;
struct r1conf *conf = mddev->private;
struct bio *bio;
if (from_schedule || current->bio_list) {
spin_lock_irq(&conf->device_lock);
bio_list_merge(&conf->pending_bio_list, &plug->pending);
conf->pending_count += plug->pending_cnt;
spin_unlock_irq(&conf->device_lock);
wake_up(&conf->wait_barrier);
md_wakeup_thread(mddev->thread);
kfree(plug);
return;
}
/* we aren't scheduling, so we can do the write-out directly. */
bio = bio_list_get(&plug->pending);
flush_bio_list(conf, bio);
kfree(plug);
}
static void init_r1bio(struct r1bio *r1_bio, struct mddev *mddev, struct bio *bio)
{
r1_bio->master_bio = bio;
r1_bio->sectors = bio_sectors(bio);
r1_bio->state = 0;
r1_bio->mddev = mddev;
r1_bio->sector = bio->bi_iter.bi_sector;
}
static inline struct r1bio *
alloc_r1bio(struct mddev *mddev, struct bio *bio)
{
struct r1conf *conf = mddev->private;
struct r1bio *r1_bio;
r1_bio = mempool_alloc(&conf->r1bio_pool, GFP_NOIO);
/* Ensure no bio records IO_BLOCKED */
memset(r1_bio->bios, 0, conf->raid_disks * sizeof(r1_bio->bios[0]));
init_r1bio(r1_bio, mddev, bio);
return r1_bio;
}
static void raid1_read_request(struct mddev *mddev, struct bio *bio,
int max_read_sectors, struct r1bio *r1_bio)
{
struct r1conf *conf = mddev->private;
struct raid1_info *mirror;
struct bio *read_bio;
struct bitmap *bitmap = mddev->bitmap;
const int op = bio_op(bio);
const unsigned long do_sync = (bio->bi_opf & REQ_SYNC);
int max_sectors;
int rdisk;
bool print_msg = !!r1_bio;
char b[BDEVNAME_SIZE];
/*
* If r1_bio is set, we are blocking the raid1d thread
* so there is a tiny risk of deadlock. So ask for
* emergency memory if needed.
*/
gfp_t gfp = r1_bio ? (GFP_NOIO | __GFP_HIGH) : GFP_NOIO;
if (print_msg) {
/* Need to get the block device name carefully */
struct md_rdev *rdev;
rcu_read_lock();
rdev = rcu_dereference(conf->mirrors[r1_bio->read_disk].rdev);
if (rdev)
bdevname(rdev->bdev, b);
else
strcpy(b, "???");
rcu_read_unlock();
}
/*
* Still need barrier for READ in case that whole
* array is frozen.
*/
wait_read_barrier(conf, bio->bi_iter.bi_sector);
if (!r1_bio)
r1_bio = alloc_r1bio(mddev, bio);
else
init_r1bio(r1_bio, mddev, bio);
r1_bio->sectors = max_read_sectors;
/*
* make_request() can abort the operation when read-ahead is being
* used and no empty request is available.
*/
rdisk = read_balance(conf, r1_bio, &max_sectors);
if (rdisk < 0) {
/* couldn't find anywhere to read from */
if (print_msg) {
pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
mdname(mddev),
b,
(unsigned long long)r1_bio->sector);
}
raid_end_bio_io(r1_bio);
return;
}
mirror = conf->mirrors + rdisk;
if (print_msg)
pr_info_ratelimited("md/raid1:%s: redirecting sector %llu to other mirror: %s\n",
mdname(mddev),
(unsigned long long)r1_bio->sector,
bdevname(mirror->rdev->bdev, b));
if (test_bit(WriteMostly, &mirror->rdev->flags) &&
bitmap) {
/*
* Reading from a write-mostly device must take care not to
* over-take any writes that are 'behind'
*/
raid1_log(mddev, "wait behind writes");
wait_event(bitmap->behind_wait,
atomic_read(&bitmap->behind_writes) == 0);
}
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
gfp, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
r1_bio->master_bio = bio;
r1_bio->sectors = max_sectors;
}
r1_bio->read_disk = rdisk;
read_bio = bio_clone_fast(bio, gfp, &mddev->bio_set);
r1_bio->bios[rdisk] = read_bio;
read_bio->bi_iter.bi_sector = r1_bio->sector +
mirror->rdev->data_offset;
bio_set_dev(read_bio, mirror->rdev->bdev);
read_bio->bi_end_io = raid1_end_read_request;
bio_set_op_attrs(read_bio, op, do_sync);
if (test_bit(FailFast, &mirror->rdev->flags) &&
test_bit(R1BIO_FailFast, &r1_bio->state))
read_bio->bi_opf |= MD_FAILFAST;
read_bio->bi_private = r1_bio;
if (mddev->gendisk)
trace_block_bio_remap(read_bio->bi_disk->queue, read_bio,
disk_devt(mddev->gendisk), r1_bio->sector);
generic_make_request(read_bio);
}
static void raid1_write_request(struct mddev *mddev, struct bio *bio,
int max_write_sectors)
{
struct r1conf *conf = mddev->private;
struct r1bio *r1_bio;
int i, disks;
struct bitmap *bitmap = mddev->bitmap;
unsigned long flags;
struct md_rdev *blocked_rdev;
struct blk_plug_cb *cb;
struct raid1_plug_cb *plug = NULL;
int first_clone;
int max_sectors;
if (mddev_is_clustered(mddev) &&
md_cluster_ops->area_resyncing(mddev, WRITE,
bio->bi_iter.bi_sector, bio_end_sector(bio))) {
DEFINE_WAIT(w);
for (;;) {
prepare_to_wait(&conf->wait_barrier,
&w, TASK_IDLE);
if (!md_cluster_ops->area_resyncing(mddev, WRITE,
bio->bi_iter.bi_sector,
bio_end_sector(bio)))
break;
schedule();
}
finish_wait(&conf->wait_barrier, &w);
}
/*
* 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, bio->bi_iter.bi_sector);
r1_bio = alloc_r1bio(mddev, bio);
r1_bio->sectors = max_write_sectors;
if (conf->pending_count >= max_queued_requests) {
md_wakeup_thread(mddev->thread);
raid1_log(mddev, "wait queued");
wait_event(conf->wait_barrier,
conf->pending_count < max_queued_requests);
}
/* 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 those
* blocks.
* This potentially requires several writes to write around
* the bad blocks. Each set of writes gets it's own r1bio
* with a set of bios attached.
*/
disks = conf->raid_disks * 2;
retry_write:
blocked_rdev = NULL;
rcu_read_lock();
max_sectors = r1_bio->sectors;
for (i = 0; i < disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && unlikely(test_bit(Blocked, &rdev->flags))) {
atomic_inc(&rdev->nr_pending);
blocked_rdev = rdev;
break;
}
r1_bio->bios[i] = NULL;
if (!rdev || test_bit(Faulty, &rdev->flags)) {
if (i < conf->raid_disks)
set_bit(R1BIO_Degraded, &r1_bio->state);
continue;
}
atomic_inc(&rdev->nr_pending);
if (test_bit(WriteErrorSeen, &rdev->flags)) {
sector_t first_bad;
int bad_sectors;
int is_bad;
is_bad = is_badblock(rdev, r1_bio->sector, max_sectors,
&first_bad, &bad_sectors);
if (is_bad < 0) {
/* mustn't write here until the bad block is
* acknowledged*/
set_bit(BlockedBadBlocks, &rdev->flags);
blocked_rdev = rdev;
break;
}
if (is_bad && first_bad <= r1_bio->sector) {
/* Cannot write here at all */
bad_sectors -= (r1_bio->sector - first_bad);
if (bad_sectors < max_sectors)
/* mustn't write more than bad_sectors
* to other devices yet
*/
max_sectors = bad_sectors;
rdev_dec_pending(rdev, mddev);
/* We don't set R1BIO_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 - r1_bio->sector;
if (good_sectors < max_sectors)
max_sectors = good_sectors;
}
}
r1_bio->bios[i] = bio;
}
rcu_read_unlock();
if (unlikely(blocked_rdev)) {
/* Wait for this device to become unblocked */
int j;
for (j = 0; j < i; j++)
if (r1_bio->bios[j])
rdev_dec_pending(conf->mirrors[j].rdev, mddev);
r1_bio->state = 0;
allow_barrier(conf, bio->bi_iter.bi_sector);
raid1_log(mddev, "wait rdev %d blocked", blocked_rdev->raid_disk);
md_wait_for_blocked_rdev(blocked_rdev, mddev);
wait_barrier(conf, bio->bi_iter.bi_sector);
goto retry_write;
}
if (max_sectors < bio_sectors(bio)) {
struct bio *split = bio_split(bio, max_sectors,
GFP_NOIO, &conf->bio_split);
bio_chain(split, bio);
generic_make_request(bio);
bio = split;
r1_bio->master_bio = bio;
r1_bio->sectors = max_sectors;
}
atomic_set(&r1_bio->remaining, 1);
atomic_set(&r1_bio->behind_remaining, 0);
first_clone = 1;
for (i = 0; i < disks; i++) {
struct bio *mbio = NULL;
if (!r1_bio->bios[i])
continue;
if (first_clone) {
/* do behind I/O ?
* Not if there are too many, or cannot
* allocate memory, or a reader on WriteMostly
* is waiting for behind writes to flush */
if (bitmap &&
(atomic_read(&bitmap->behind_writes)
< mddev->bitmap_info.max_write_behind) &&
!waitqueue_active(&bitmap->behind_wait)) {
alloc_behind_master_bio(r1_bio, bio);
}
md_bitmap_startwrite(bitmap, r1_bio->sector, r1_bio->sectors,
test_bit(R1BIO_BehindIO, &r1_bio->state));
first_clone = 0;
}
if (r1_bio->behind_master_bio)
mbio = bio_clone_fast(r1_bio->behind_master_bio,
GFP_NOIO, &mddev->bio_set);
else
mbio = bio_clone_fast(bio, GFP_NOIO, &mddev->bio_set);
if (r1_bio->behind_master_bio) {
if (test_bit(WriteMostly, &conf->mirrors[i].rdev->flags))
atomic_inc(&r1_bio->behind_remaining);
}
r1_bio->bios[i] = mbio;
mbio->bi_iter.bi_sector = (r1_bio->sector +
conf->mirrors[i].rdev->data_offset);
bio_set_dev(mbio, conf->mirrors[i].rdev->bdev);
mbio->bi_end_io = raid1_end_write_request;
mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA));
if (test_bit(FailFast, &conf->mirrors[i].rdev->flags) &&
!test_bit(WriteMostly, &conf->mirrors[i].rdev->flags) &&
conf->raid_disks - mddev->degraded > 1)
mbio->bi_opf |= MD_FAILFAST;
mbio->bi_private = r1_bio;
atomic_inc(&r1_bio->remaining);
if (mddev->gendisk)
trace_block_bio_remap(mbio->bi_disk->queue,
mbio, disk_devt(mddev->gendisk),
r1_bio->sector);
/* flush_pending_writes() needs access to the rdev so...*/
mbio->bi_disk = (void *)conf->mirrors[i].rdev;
cb = blk_check_plugged(raid1_unplug, mddev, sizeof(*plug));
if (cb)
plug = container_of(cb, struct raid1_plug_cb, cb);
else
plug = NULL;
if (plug) {
bio_list_add(&plug->pending, mbio);
plug->pending_cnt++;
} else {
spin_lock_irqsave(&conf->device_lock, flags);
bio_list_add(&conf->pending_bio_list, mbio);
conf->pending_count++;
spin_unlock_irqrestore(&conf->device_lock, flags);
md_wakeup_thread(mddev->thread);
}
}
r1_bio_write_done(r1_bio);
/* In case raid1d snuck in to freeze_array */
wake_up(&conf->wait_barrier);
}
static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
{
sector_t sectors;
if (unlikely(bio->bi_opf & REQ_PREFLUSH)) {
md_flush_request(mddev, bio);
return true;
}
/*
* There is a limit to the maximum size, but
* the read/write handler might find a lower limit
* due to bad blocks. To avoid multiple splits,
* we pass the maximum number of sectors down
* and let the lower level perform the split.
*/
sectors = align_to_barrier_unit_end(
bio->bi_iter.bi_sector, bio_sectors(bio));
if (bio_data_dir(bio) == READ)
raid1_read_request(mddev, bio, sectors, NULL);
else {
if (!md_write_start(mddev,bio))
return false;
raid1_write_request(mddev, bio, sectors);
}
return true;
}
static void raid1_status(struct seq_file *seq, struct mddev *mddev)
{
struct r1conf *conf = mddev->private;
int i;
seq_printf(seq, " [%d/%d] [", conf->raid_disks,
conf->raid_disks - mddev->degraded);
rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
seq_printf(seq, "%s",
rdev && test_bit(In_sync, &rdev->flags) ? "U" : "_");
}
rcu_read_unlock();
seq_printf(seq, "]");
}
static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
{
char b[BDEVNAME_SIZE];
struct r1conf *conf = mddev->private;
unsigned long flags;
/*
* 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
*/
spin_lock_irqsave(&conf->device_lock, flags);
if (test_bit(In_sync, &rdev->flags)
&& (conf->raid_disks - mddev->degraded) == 1) {
/*
* Don't fail the drive, act as though we were just a
* normal single drive.
* However don't try a recovery from this drive as
* it is very likely to fail.
*/
conf->recovery_disabled = mddev->recovery_disabled;
spin_unlock_irqrestore(&conf->device_lock, flags);
return;
}
set_bit(Blocked, &rdev->flags);
if (test_and_clear_bit(In_sync, &rdev->flags)) {
mddev->degraded++;
set_bit(Faulty, &rdev->flags);
} else
set_bit(Faulty, &rdev->flags);
spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery is running, make sure it aborts.
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_mask_bits(&mddev->sb_flags, 0,
BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
pr_crit("md/raid1:%s: Disk failure on %s, disabling device.\n"
"md/raid1:%s: Operation continuing on %d devices.\n",
mdname(mddev), bdevname(rdev->bdev, b),
mdname(mddev), conf->raid_disks - mddev->degraded);
}
static void print_conf(struct r1conf *conf)
{
int i;
pr_debug("RAID1 conf printout:\n");
if (!conf) {
pr_debug("(!conf)\n");
return;
}
pr_debug(" --- wd:%d rd:%d\n", conf->raid_disks - conf->mddev->degraded,
conf->raid_disks);
rcu_read_lock();
for (i = 0; i < conf->raid_disks; i++) {
char b[BDEVNAME_SIZE];
struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev)
pr_debug(" disk %d, wo:%d, o:%d, dev:%s\n",
i, !test_bit(In_sync, &rdev->flags),
!test_bit(Faulty, &rdev->flags),
bdevname(rdev->bdev,b));
}
rcu_read_unlock();
}
static void close_sync(struct r1conf *conf)
{
int idx;
for (idx = 0; idx < BARRIER_BUCKETS_NR; idx++) {
_wait_barrier(conf, idx);
_allow_barrier(conf, idx);
}
mempool_exit(&conf->r1buf_pool);
}
static int raid1_spare_active(struct mddev *mddev)
{
int i;
struct r1conf *conf = mddev->private;
int count = 0;
unsigned long flags;
/*
* Find all failed disks within the RAID1 configuration
* and mark them readable.
* Called under mddev lock, so rcu protection not needed.
* device_lock used to avoid races with raid1_end_read_request
* which expects 'In_sync' flags and ->degraded to be consistent.
*/
spin_lock_irqsave(&conf->device_lock, flags);
for (i = 0; i < conf->raid_disks; i++) {
struct md_rdev *rdev = conf->mirrors[i].rdev;
struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
if (repl
&& !test_bit(Candidate, &repl->flags)
&& repl->recovery_offset == MaxSector
&& !test_bit(Faulty, &repl->flags)
&& !test_and_set_bit(In_sync, &repl->flags)) {
/* replacement has just become active */
if (!rdev ||
!test_and_clear_bit(In_sync, &rdev->flags))
count++;
if (rdev) {
/* Replaced device not technically
* faulty, but we need to be sure
* it gets removed and never re-added
*/
set_bit(Faulty, &rdev->flags);
sysfs_notify_dirent_safe(
rdev->sysfs_state);
}
}
if (rdev
&& rdev->recovery_offset == MaxSector
&& !test_bit(Faulty, &rdev->flags)
&& !test_and_set_bit(In_sync, &rdev->flags)) {
count++;
sysfs_notify_dirent_safe(rdev->sysfs_state);
}
}
mddev->degraded -= count;
spin_unlock_irqrestore(&conf->device_lock, flags);
print_conf(conf);
return count;
}
static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct r1conf *conf = mddev->private;
int err = -EEXIST;
int mirror = 0;
struct raid1_info *p;
int first = 0;
int last = conf->raid_disks - 1;
if (mddev->recovery_disabled == conf->recovery_disabled)
return -EBUSY;
if (md_integrity_add_rdev(rdev, mddev))
return -ENXIO;
if (rdev->raid_disk >= 0)
first = last = rdev->raid_disk;
/*
* find the disk ... but prefer rdev->saved_raid_disk
* if possible.
*/
if (rdev->saved_raid_disk >= 0 &&
rdev->saved_raid_disk >= first &&
rdev->saved_raid_disk < conf->raid_disks &&
conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
first = last = rdev->saved_raid_disk;
for (mirror = first; mirror <= last; mirror++) {
p = conf->mirrors+mirror;
if (!p->rdev) {
if (mddev->gendisk)
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
p->head_position = 0;
rdev->raid_disk = mirror;
err = 0;
/* As all devices are equivalent, we don't need a full recovery
* if this was recently any drive of the array
*/
if (rdev->saved_raid_disk < 0)
conf->fullsync = 1;
rcu_assign_pointer(p->rdev, rdev);
break;
}
if (test_bit(WantReplacement, &p->rdev->flags) &&
p[conf->raid_disks].rdev == NULL) {
/* Add this device as a replacement */
clear_bit(In_sync, &rdev->flags);
set_bit(Replacement, &rdev->flags);
rdev->raid_disk = mirror;
err = 0;
conf->fullsync = 1;
rcu_assign_pointer(p[conf->raid_disks].rdev, rdev);
break;
}
}
if (mddev->queue && blk_queue_discard(bdev_get_queue(rdev->bdev)))
blk_queue_flag_set(QUEUE_FLAG_DISCARD, mddev->queue);
print_conf(conf);
return err;
}
static int raid1_remove_disk(struct mddev *mddev, struct md_rdev *rdev)
{
struct r1conf *conf = mddev->private;
int err = 0;
int number = rdev->raid_disk;
struct raid1_info *p = conf->mirrors + number;
if (rdev != p->rdev)
p = conf->mirrors + conf->raid_disks + number;
print_conf(conf);
if (rdev == p->rdev) {
if (test_bit(In_sync, &rdev->flags) ||
atomic_read(&rdev->nr_pending)) {
err = -EBUSY;
goto abort;
}
/* Only remove non-faulty devices if recovery
* is not possible.
*/
if (!test_bit(Faulty, &rdev->flags) &&
mddev->recovery_disabled != conf->recovery_disabled &&
mddev->degraded < conf->raid_disks) {
err = -EBUSY;
goto abort;
}
p->rdev = NULL;
if (!test_bit(RemoveSynchronized, &rdev->flags)) {
synchronize_rcu();
if (atomic_read(&rdev->nr_pending)) {
/* lost the race, try later */
err = -EBUSY;
p->rdev = rdev;
goto abort;
}
}
if (conf->mirrors[conf->raid_disks + number].rdev) {
/* We just removed a device that is being replaced.
* Move down the replacement. We drain all IO before
* doing this to avoid confusion.
*/
struct md_rdev *repl =
conf->mirrors[conf->raid_disks + number].rdev;
freeze_array(conf, 0);
if (atomic_read(&repl->nr_pending)) {
/* It means that some queued IO of retry_list
* hold repl. Thus, we cannot set replacement
* as NULL, avoiding rdev NULL pointer
* dereference in sync_request_write and
* handle_write_finished.
*/
err = -EBUSY;
unfreeze_array(conf);
goto abort;
}
clear_bit(Replacement, &repl->flags);
p->rdev = repl;
conf->mirrors[conf->raid_disks + number].rdev = NULL;
unfreeze_array(conf);
}
clear_bit(WantReplacement, &rdev->flags);
err = md_integrity_register(mddev);
}
abort:
print_conf(conf);
return err;
}
static void end_sync_read(struct bio *bio)
{
struct r1bio *r1_bio = get_resync_r1bio(bio);
update_head_pos(r1_bio->read_disk, r1_bio);
/*
* we have read a block, now it needs to be re-written,
* or re-read if the read failed.
* We don't do much here, just schedule handling by raid1d
*/
if (!bio->bi_status)
set_bit(R1BIO_Uptodate, &r1_bio->state);
if (atomic_dec_and_test(&r1_bio->remaining))
reschedule_retry(r1_bio);
}
static void abort_sync_write(struct mddev *mddev, struct r1bio *r1_bio)
{
sector_t sync_blocks = 0;
sector_t s = r1_bio->sector;
long sectors_to_go = r1_bio->sectors;
/* make sure these bits don't get cleared. */
do {
md_bitmap_end_sync(mddev->bitmap, s, &sync_blocks, 1);
s += sync_blocks;
sectors_to_go -= sync_blocks;
} while (sectors_to_go > 0);
}
static void end_sync_write(struct bio *bio)
{
int uptodate = !bio->bi_status;
struct r1bio *r1_bio = get_resync_r1bio(bio);
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
sector_t first_bad;
int bad_sectors;
struct md_rdev *rdev = conf->mirrors[find_bio_disk(r1_bio, bio)].rdev;
if (!uptodate) {
abort_sync_write(mddev, r1_bio);
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
mddev->recovery);
set_bit(R1BIO_WriteError, &r1_bio->state);
} else if (is_badblock(rdev, r1_bio->sector, r1_bio->sectors,
&first_bad, &bad_sectors) &&
!is_badblock(conf->mirrors[r1_bio->read_disk].rdev,
r1_bio->sector,
r1_bio->sectors,
&first_bad, &bad_sectors)
)
set_bit(R1BIO_MadeGood, &r1_bio->state);
if (atomic_dec_and_test(&r1_bio->remaining)) {
int s = r1_bio->sectors;
if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
test_bit(R1BIO_WriteError, &r1_bio->state))
reschedule_retry(r1_bio);
else {
put_buf(r1_bio);
md_done_sync(mddev, s, uptodate);
}
}
}
static int r1_sync_page_io(struct md_rdev *rdev, sector_t sector,
int sectors, struct page *page, int rw)
{
if (sync_page_io(rdev, sector, sectors << 9, page, rw, 0, false))
/* success */
return 1;
if (rw == WRITE) {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement,
&rdev->flags))
set_bit(MD_RECOVERY_NEEDED, &
rdev->mddev->recovery);
}
/* 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;
}
static int fix_sync_read_error(struct r1bio *r1_bio)
{
/* Try some synchronous reads of other devices to get
* good data, much like with normal read errors. Only
* read into the pages we already have so we don't
* need to re-issue the read request.
* We don't need to freeze the array, because being in an
* active sync request, there is no normal IO, and
* no overlapping syncs.
* We don't need to check is_badblock() again as we
* made sure that anything with a bad block in range
* will have bi_end_io clear.
*/
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
struct bio *bio = r1_bio->bios[r1_bio->read_disk];
struct page **pages = get_resync_pages(bio)->pages;
sector_t sect = r1_bio->sector;
int sectors = r1_bio->sectors;
int idx = 0;
struct md_rdev *rdev;
rdev = conf->mirrors[r1_bio->read_disk].rdev;
if (test_bit(FailFast, &rdev->flags)) {
/* Don't try recovering from here - just fail it
* ... unless it is the last working device of course */
md_error(mddev, rdev);
if (test_bit(Faulty, &rdev->flags))
/* Don't try to read from here, but make sure
* put_buf does it's thing
*/
bio->bi_end_io = end_sync_write;
}
while(sectors) {
int s = sectors;
int d = r1_bio->read_disk;
int success = 0;
int start;
if (s > (PAGE_SIZE>>9))
s = PAGE_SIZE >> 9;
do {
if (r1_bio->bios[d]->bi_end_io == end_sync_read) {
/* No rcu protection needed here devices
* can only be removed when no resync is
* active, and resync is currently active
*/
rdev = conf->mirrors[d].rdev;
if (sync_page_io(rdev, sect, s<<9,
pages[idx],
REQ_OP_READ, 0, false)) {
success = 1;
break;
}
}
d++;
if (d == conf->raid_disks * 2)
d = 0;
} while (!success && d != r1_bio->read_disk);
if (!success) {
char b[BDEVNAME_SIZE];
int abort = 0;
/* Cannot read from anywhere, this block is lost.
* Record a bad block on each device. If that doesn't
* work just disable and interrupt the recovery.
* Don't fail devices as that won't really help.
*/
pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
mdname(mddev), bio_devname(bio, b),
(unsigned long long)r1_bio->sector);
for (d = 0; d < conf->raid_disks * 2; d++) {
rdev = conf->mirrors[d].rdev;
if (!rdev || test_bit(Faulty, &rdev->flags))
continue;
if (!rdev_set_badblocks(rdev, sect, s, 0))
abort = 1;
}
if (abort) {
conf->recovery_disabled =
mddev->recovery_disabled;
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
md_done_sync(mddev, r1_bio->sectors, 0);
put_buf(r1_bio);
return 0;
}
/* Try next page */
sectors -= s;
sect += s;
idx++;
continue;
}
start = d;
/* write it back and re-read */
while (d != r1_bio->read_disk) {
if (d == 0)
d = conf->raid_disks * 2;
d--;
if (r1_bio->bios[d]->bi_end_io != end_sync_read)
continue;
rdev = conf->mirrors[d].rdev;
if (r1_sync_page_io(rdev, sect, s,
pages[idx],
WRITE) == 0) {
r1_bio->bios[d]->bi_end_io = NULL;
rdev_dec_pending(rdev, mddev);
}
}
d = start;
while (d != r1_bio->read_disk) {
if (d == 0)
d = conf->raid_disks * 2;
d--;
if (r1_bio->bios[d]->bi_end_io != end_sync_read)
continue;
rdev = conf->mirrors[d].rdev;
if (r1_sync_page_io(rdev, sect, s,
pages[idx],
READ) != 0)
atomic_add(s, &rdev->corrected_errors);
}
sectors -= s;
sect += s;
idx ++;
}
set_bit(R1BIO_Uptodate, &r1_bio->state);
bio->bi_status = 0;
return 1;
}
static void process_checks(struct r1bio *r1_bio)
{
/* We have read all readable devices. If we haven't
* got the block, then there is no hope left.
* If we have, then we want to do a comparison
* and skip the write if everything is the same.
* If any blocks failed to read, then we need to
* attempt an over-write
*/
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
int primary;
int i;
int vcnt;
/* Fix variable parts of all bios */
vcnt = (r1_bio->sectors + PAGE_SIZE / 512 - 1) >> (PAGE_SHIFT - 9);
for (i = 0; i < conf->raid_disks * 2; i++) {
blk_status_t status;
struct bio *b = r1_bio->bios[i];
struct resync_pages *rp = get_resync_pages(b);
if (b->bi_end_io != end_sync_read)
continue;
/* fixup the bio for reuse, but preserve errno */
status = b->bi_status;
bio_reset(b);
b->bi_status = status;
b->bi_iter.bi_sector = r1_bio->sector +
conf->mirrors[i].rdev->data_offset;
bio_set_dev(b, conf->mirrors[i].rdev->bdev);
b->bi_end_io = end_sync_read;
rp->raid_bio = r1_bio;
b->bi_private = rp;
/* initialize bvec table again */
md_bio_reset_resync_pages(b, rp, r1_bio->sectors << 9);
}
for (primary = 0; primary < conf->raid_disks * 2; primary++)
if (r1_bio->bios[primary]->bi_end_io == end_sync_read &&
!r1_bio->bios[primary]->bi_status) {
r1_bio->bios[primary]->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[primary].rdev, mddev);
break;
}
r1_bio->read_disk = primary;
for (i = 0; i < conf->raid_disks * 2; i++) {
int j;
struct bio *pbio = r1_bio->bios[primary];
struct bio *sbio = r1_bio->bios[i];
blk_status_t status = sbio->bi_status;
struct page **ppages = get_resync_pages(pbio)->pages;
struct page **spages = get_resync_pages(sbio)->pages;
struct bio_vec *bi;
int page_len[RESYNC_PAGES] = { 0 };
if (sbio->bi_end_io != end_sync_read)
continue;
/* Now we can 'fixup' the error value */
sbio->bi_status = 0;
bio_for_each_segment_all(bi, sbio, j)
page_len[j] = bi->bv_len;
if (!status) {
for (j = vcnt; j-- ; ) {
if (memcmp(page_address(ppages[j]),
page_address(spages[j]),
page_len[j]))
break;
}
} else
j = 0;
if (j >= 0)
atomic64_add(r1_bio->sectors, &mddev->resync_mismatches);
if (j < 0 || (test_bit(MD_RECOVERY_CHECK, &mddev->recovery)
&& !status)) {
/* No need to write to this device. */
sbio->bi_end_io = NULL;
rdev_dec_pending(conf->mirrors[i].rdev, mddev);
continue;
}
bio_copy_data(sbio, pbio);
}
}
static void sync_request_write(struct mddev *mddev, struct r1bio *r1_bio)
{
struct r1conf *conf = mddev->private;
int i;
int disks = conf->raid_disks * 2;
struct bio *wbio;
if (!test_bit(R1BIO_Uptodate, &r1_bio->state))
/* ouch - failed to read all of that. */
if (!fix_sync_read_error(r1_bio))
return;
if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
process_checks(r1_bio);
/*
* schedule writes
*/
atomic_set(&r1_bio->remaining, 1);
for (i = 0; i < disks ; i++) {
wbio = r1_bio->bios[i];
if (wbio->bi_end_io == NULL ||
(wbio->bi_end_io == end_sync_read &&
(i == r1_bio->read_disk ||
!test_bit(MD_RECOVERY_SYNC, &mddev->recovery))))
continue;
if (test_bit(Faulty, &conf->mirrors[i].rdev->flags)) {
abort_sync_write(mddev, r1_bio);
continue;
}
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
if (test_bit(FailFast, &conf->mirrors[i].rdev->flags))
wbio->bi_opf |= MD_FAILFAST;
wbio->bi_end_io = end_sync_write;
atomic_inc(&r1_bio->remaining);
md_sync_acct(conf->mirrors[i].rdev->bdev, bio_sectors(wbio));
generic_make_request(wbio);
}
if (atomic_dec_and_test(&r1_bio->remaining)) {
/* if we're here, all write(s) have completed, so clean up */
int s = r1_bio->sectors;
if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
test_bit(R1BIO_WriteError, &r1_bio->state))
reschedule_retry(r1_bio);
else {
put_buf(r1_bio);
md_done_sync(mddev, s, 1);
}
}
}
/*
* 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(struct r1conf *conf, int read_disk,
sector_t sect, int sectors)
{
struct mddev *mddev = conf->mddev;
while(sectors) {
int s = sectors;
int d = read_disk;
int success = 0;
int start;
struct md_rdev *rdev;
if (s > (PAGE_SIZE>>9))
s = PAGE_SIZE >> 9;
do {
sector_t first_bad;
int bad_sectors;
rcu_read_lock();
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
(test_bit(In_sync, &rdev->flags) ||
(!test_bit(Faulty, &rdev->flags) &&
rdev->recovery_offset >= sect + s)) &&
is_badblock(rdev, sect, s,
&first_bad, &bad_sectors) == 0) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
if (sync_page_io(rdev, sect, s<<9,
conf->tmppage, REQ_OP_READ, 0, false))
success = 1;
rdev_dec_pending(rdev, mddev);
if (success)
break;
} else
rcu_read_unlock();
d++;
if (d == conf->raid_disks * 2)
d = 0;
} while (!success && d != read_disk);
if (!success) {
/* Cannot read from anywhere - mark it bad */
struct md_rdev *rdev = conf->mirrors[read_disk].rdev;
if (!rdev_set_badblocks(rdev, sect, s, 0))
md_error(mddev, rdev);
break;
}
/* write it back and re-read */
start = d;
while (d != read_disk) {
if (d==0)
d = conf->raid_disks * 2;
d--;
rcu_read_lock();
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
!test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
r1_sync_page_io(rdev, sect, s,
conf->tmppage, WRITE);
rdev_dec_pending(rdev, mddev);
} else
rcu_read_unlock();
}
d = start;
while (d != read_disk) {
char b[BDEVNAME_SIZE];
if (d==0)
d = conf->raid_disks * 2;
d--;
rcu_read_lock();
rdev = rcu_dereference(conf->mirrors[d].rdev);
if (rdev &&
!test_bit(Faulty, &rdev->flags)) {
atomic_inc(&rdev->nr_pending);
rcu_read_unlock();
if (r1_sync_page_io(rdev, sect, s,
conf->tmppage, READ)) {
atomic_add(s, &rdev->corrected_errors);
pr_info("md/raid1:%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));
}
rdev_dec_pending(rdev, mddev);
} else
rcu_read_unlock();
}
sectors -= s;
sect += s;
}
}
static int narrow_write_error(struct r1bio *r1_bio, int i)
{
struct mddev *mddev = r1_bio->mddev;
struct r1conf *conf = mddev->private;
struct md_rdev *rdev = conf->mirrors[i].rdev;
/* bio has the data to be written to device '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 somehow.
*
* We currently own a reference on the rdev.
*/
int block_sectors;
sector_t sector;
int sectors;
int sect_to_write = r1_bio->sectors;
int ok = 1;
if (rdev->badblocks.shift < 0)
return 0;
block_sectors = roundup(1 << rdev->badblocks.shift,
bdev_logical_block_size(rdev->bdev) >> 9);
sector = r1_bio->sector;
sectors = ((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'*/
if (test_bit(R1BIO_BehindIO, &r1_bio->state)) {
wbio = bio_clone_fast(r1_bio->behind_master_bio,
GFP_NOIO,
&mddev->bio_set);
} else {
wbio = bio_clone_fast(r1_bio->master_bio, GFP_NOIO,
&mddev->bio_set);
}
bio_set_op_attrs(wbio, REQ_OP_WRITE, 0);
wbio->bi_iter.bi_sector = r1_bio->sector;
wbio->bi_iter.bi_size = r1_bio->sectors << 9;
bio_trim(wbio, sector - r1_bio->sector, sectors);
wbio->bi_iter.bi_sector += rdev->data_offset;
bio_set_dev(wbio, rdev->bdev);
if (submit_bio_wait(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_sync_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
{
int m;
int s = r1_bio->sectors;
for (m = 0; m < conf->raid_disks * 2 ; m++) {
struct md_rdev *rdev = conf->mirrors[m].rdev;
struct bio *bio = r1_bio->bios[m];
if (bio->bi_end_io == NULL)
continue;
if (!bio->bi_status &&
test_bit(R1BIO_MadeGood, &r1_bio->state)) {
rdev_clear_badblocks(rdev, r1_bio->sector, s, 0);
}
if (bio->bi_status &&
test_bit(R1BIO_WriteError, &r1_bio->state)) {
if (!rdev_set_badblocks(rdev, r1_bio->sector, s, 0))
md_error(conf->mddev, rdev);
}
}
put_buf(r1_bio);
md_done_sync(conf->mddev, s, 1);
}
static void handle_write_finished(struct r1conf *conf, struct r1bio *r1_bio)
{
int m, idx;
bool fail = false;
for (m = 0; m < conf->raid_disks * 2 ; m++)
if (r1_bio->bios[m] == IO_MADE_GOOD) {
struct md_rdev *rdev = conf->mirrors[m].rdev;
rdev_clear_badblocks(rdev,
r1_bio->sector,
r1_bio->sectors, 0);
rdev_dec_pending(rdev, conf->mddev);
} else if (r1_bio->bios[m] != NULL) {
/* This drive got a write error. We need to
* narrow down and record precise write
* errors.
*/
fail = true;
if (!narrow_write_error(r1_bio, m)) {
md_error(conf->mddev,
conf->mirrors[m].rdev);
/* an I/O failed, we can't clear the bitmap */
set_bit(R1BIO_Degraded, &r1_bio->state);
}
rdev_dec_pending(conf->mirrors[m].rdev,
conf->mddev);
}
if (fail) {
spin_lock_irq(&conf->device_lock);
list_add(&r1_bio->retry_list, &conf->bio_end_io_list);
idx = sector_to_idx(r1_bio->sector);
atomic_inc(&conf->nr_queued[idx]);
spin_unlock_irq(&conf->device_lock);
/*
* In case freeze_array() is waiting for condition
* get_unqueued_pending() == extra to be true.
*/
wake_up(&conf->wait_barrier);
md_wakeup_thread(conf->mddev->thread);
} else {
if (test_bit(R1BIO_WriteError, &r1_bio->state))
close_write(r1_bio);
raid_end_bio_io(r1_bio);
}
}
static void handle_read_error(struct r1conf *conf, struct r1bio *r1_bio)
{
struct mddev *mddev = conf->mddev;
struct bio *bio;
struct md_rdev *rdev;
clear_bit(R1BIO_ReadError, &r1_bio->state);
/* 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
*/
bio = r1_bio->bios[r1_bio->read_disk];
bio_put(bio);
r1_bio->bios[r1_bio->read_disk] = NULL;
rdev = conf->mirrors[r1_bio->read_disk].rdev;
if (mddev->ro == 0
&& !test_bit(FailFast, &rdev->flags)) {
freeze_array(conf, 1);
fix_read_error(conf, r1_bio->read_disk,
r1_bio->sector, r1_bio->sectors);
unfreeze_array(conf);
} else if (mddev->ro == 0 && test_bit(FailFast, &rdev->flags)) {
md_error(mddev, rdev);
} else {
r1_bio->bios[r1_bio->read_disk] = IO_BLOCKED;
}
rdev_dec_pending(rdev, conf->mddev);
allow_barrier(conf, r1_bio->sector);
bio = r1_bio->master_bio;
/* Reuse the old r1_bio so that the IO_BLOCKED settings are preserved */
r1_bio->state = 0;
raid1_read_request(mddev, bio, r1_bio->sectors, r1_bio);
}
static void raid1d(struct md_thread *thread)
{
struct mddev *mddev = thread->mddev;
struct r1bio *r1_bio;
unsigned long flags;
struct r1conf *conf = mddev->private;
struct list_head *head = &conf->retry_list;
struct blk_plug plug;
int idx;
md_check_recovery(mddev);
if (!list_empty_careful(&conf->bio_end_io_list) &&
!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
LIST_HEAD(tmp);
spin_lock_irqsave(&conf->device_lock, flags);
if (!test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags))
list_splice_init(&conf->bio_end_io_list, &tmp);
spin_unlock_irqrestore(&conf->device_lock, flags);
while (!list_empty(&tmp)) {
r1_bio = list_first_entry(&tmp, struct r1bio,
retry_list);
list_del(&r1_bio->retry_list);
idx = sector_to_idx(r1_bio->sector);
atomic_dec(&conf->nr_queued[idx]);
if (mddev->degraded)
set_bit(R1BIO_Degraded, &r1_bio->state);
if (test_bit(R1BIO_WriteError, &r1_bio->state))
close_write(r1_bio);
raid_end_bio_io(r1_bio);
}
}
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;
}
r1_bio = list_entry(head->prev, struct r1bio, retry_list);
list_del(head->prev);
idx = sector_to_idx(r1_bio->sector);
atomic_dec(&conf->nr_queued[idx]);
spin_unlock_irqrestore(&conf->device_lock, flags);
mddev = r1_bio->mddev;
conf = mddev->private;
if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
test_bit(R1BIO_WriteError, &r1_bio->state))
handle_sync_write_finished(conf, r1_bio);
else
sync_request_write(mddev, r1_bio);
} else if (test_bit(R1BIO_MadeGood, &r1_bio->state) ||
test_bit(R1BIO_WriteError, &r1_bio->state))
handle_write_finished(conf, r1_bio);
else if (test_bit(R1BIO_ReadError, &r1_bio->state))
handle_read_error(conf, r1_bio);
else
WARN_ON_ONCE(1);
cond_resched();
if (mddev->sb_flags & ~(1<<MD_SB_CHANGE_PENDING))
md_check_recovery(mddev);
}
blk_finish_plug(&plug);
}
static int init_resync(struct r1conf *conf)
{
int buffs;
buffs = RESYNC_WINDOW / RESYNC_BLOCK_SIZE;
BUG_ON(mempool_initialized(&conf->r1buf_pool));
return mempool_init(&conf->r1buf_pool, buffs, r1buf_pool_alloc,
r1buf_pool_free, conf->poolinfo);
}
static struct r1bio *raid1_alloc_init_r1buf(struct r1conf *conf)
{
struct r1bio *r1bio = mempool_alloc(&conf->r1buf_pool, GFP_NOIO);
struct resync_pages *rps;
struct bio *bio;
int i;
for (i = conf->poolinfo->raid_disks; i--; ) {
bio = r1bio->bios[i];
rps = bio->bi_private;
bio_reset(bio);
bio->bi_private = rps;
}
r1bio->master_bio = NULL;
return r1bio;
}
/*
* 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.
*/
static sector_t raid1_sync_request(struct mddev *mddev, sector_t sector_nr,
int *skipped)
{
struct r1conf *conf = mddev->private;
struct r1bio *r1_bio;
struct bio *bio;
sector_t max_sector, nr_sectors;
int disk = -1;
int i;
int wonly = -1;
int write_targets = 0, read_targets = 0;
sector_t sync_blocks;
int still_degraded = 0;
int good_sectors = RESYNC_SECTORS;
int min_bad = 0; /* number of sectors that are bad in all devices */
int idx = sector_to_idx(sector_nr);
int page_idx = 0;
if (!mempool_initialized(&conf->r1buf_pool))
if (init_resync(conf))
return 0;
max_sector = mddev->dev_sectors;
if (sector_nr >= max_sector) {
/* If we aborted, we need to abort the
* sync on the 'current' bitmap chunk (there will
* only be one in raid1 resync.
* We can find the current addess in mddev->curr_resync
*/
if (mddev->curr_resync < max_sector) /* aborted */
md_bitmap_end_sync(mddev->bitmap, mddev->curr_resync,
&sync_blocks, 1);
else /* completed sync */
conf->fullsync = 0;
md_bitmap_close_sync(mddev->bitmap);
close_sync(conf);
if (mddev_is_clustered(mddev)) {
conf->cluster_sync_low = 0;
conf->cluster_sync_high = 0;
}
return 0;
}
if (mddev->bitmap == NULL &&
mddev->recovery_cp == MaxSector &&
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery) &&
conf->fullsync == 0) {
*skipped = 1;
return max_sector - sector_nr;
}
/* before building a request, check if we can skip these blocks..
* This call the bitmap_start_sync doesn't actually record anything
*/
if (!md_bitmap_start_sync(mddev->bitmap, sector_nr, &sync_blocks, 1) &&
!conf->fullsync && !test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
/* We can skip this block, and probably several more */
*skipped = 1;
return sync_blocks;
}
/*
* If there is non-resync activity waiting for a turn, then let it
* though before starting on this new sync request.
*/
if (atomic_read(&conf->nr_waiting[idx]))
schedule_timeout_uninterruptible(1);
/* we are incrementing sector_nr below. To be safe, we check against
* sector_nr + two times RESYNC_SECTORS
*/
md_bitmap_cond_end_sync(mddev->bitmap, sector_nr,
mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
if (raise_barrier(conf, sector_nr))
return 0;
r1_bio = raid1_alloc_init_r1buf(conf);
rcu_read_lock();
/*
* If we get a correctably read error during resync or recovery,
* we might want to read from a different device. So we
* flag all drives that could conceivably be read from for READ,
* and any others (which will be non-In_sync devices) for WRITE.
* If a read fails, we try reading from something else for which READ
* is OK.
*/
r1_bio->mddev = mddev;
r1_bio->sector = sector_nr;
r1_bio->state = 0;
set_bit(R1BIO_IsSync, &r1_bio->state);
/* make sure good_sectors won't go across barrier unit boundary */
good_sectors = align_to_barrier_unit_end(sector_nr, good_sectors);
for (i = 0; i < conf->raid_disks * 2; i++) {
struct md_rdev *rdev;
bio = r1_bio->bios[i];
rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev == NULL ||
test_bit(Faulty, &rdev->flags)) {
if (i < conf->raid_disks)
still_degraded = 1;
} else if (!test_bit(In_sync, &rdev->flags)) {
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_end_io = end_sync_write;
write_targets ++;
} else {
/* may need to read from here */
sector_t first_bad = MaxSector;
int bad_sectors;
if (is_badblock(rdev, sector_nr, good_sectors,
&first_bad, &bad_sectors)) {
if (first_bad > sector_nr)
good_sectors = first_bad - sector_nr;
else {
bad_sectors -= (sector_nr - first_bad);
if (min_bad == 0 ||
min_bad > bad_sectors)
min_bad = bad_sectors;
}
}
if (sector_nr < first_bad) {
if (test_bit(WriteMostly, &rdev->flags)) {
if (wonly < 0)
wonly = i;
} else {
if (disk < 0)
disk = i;
}
bio_set_op_attrs(bio, REQ_OP_READ, 0);
bio->bi_end_io = end_sync_read;
read_targets++;
} else if (!test_bit(WriteErrorSeen, &rdev->flags) &&
test_bit(MD_RECOVERY_SYNC, &mddev->recovery) &&
!test_bit(MD_RECOVERY_CHECK, &mddev->recovery)) {
/*
* The device is suitable for reading (InSync),
* but has bad block(s) here. Let's try to correct them,
* if we are doing resync or repair. Otherwise, leave
* this device alone for this sync request.
*/
bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
bio->bi_end_io = end_sync_write;
write_targets++;
}
}
if (bio->bi_end_io) {
atomic_inc(&rdev->nr_pending);
bio->bi_iter.bi_sector = sector_nr + rdev->data_offset;
bio_set_dev(bio, rdev->bdev);
if (test_bit(FailFast, &rdev->flags))
bio->bi_opf |= MD_FAILFAST;
}
}
rcu_read_unlock();
if (disk < 0)
disk = wonly;
r1_bio->read_disk = disk;
if (read_targets == 0 && min_bad > 0) {
/* These sectors are bad on all InSync devices, so we
* need to mark them bad on all write targets
*/
int ok = 1;
for (i = 0 ; i < conf->raid_disks * 2 ; i++)
if (r1_bio->bios[i]->bi_end_io == end_sync_write) {
struct md_rdev *rdev = conf->mirrors[i].rdev;
ok = rdev_set_badblocks(rdev, sector_nr,
min_bad, 0
) && ok;
}
set_bit(MD_SB_CHANGE_DEVS, &mddev->sb_flags);
*skipped = 1;
put_buf(r1_bio);
if (!ok) {
/* Cannot record the badblocks, so need to
* abort the resync.
* If there are multiple read targets, could just
* fail the really bad ones ???
*/
conf->recovery_disabled = mddev->recovery_disabled;
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
return 0;
} else
return min_bad;
}
if (min_bad > 0 && min_bad < good_sectors) {
/* only resync enough to reach the next bad->good
* transition */
good_sectors = min_bad;
}
if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery) && read_targets > 0)
/* extra read targets are also write targets */
write_targets += read_targets-1;
if (write_targets == 0 || read_targets == 0) {
/* There is nowhere to write, so all non-sync
* drives must be failed - so we are finished
*/
sector_t rv;
if (min_bad > 0)
max_sector = sector_nr + min_bad;
rv = max_sector - sector_nr;
*skipped = 1;
put_buf(r1_bio);
return rv;
}
if (max_sector > mddev->resync_max)
max_sector = mddev->resync_max; /* Don't do IO beyond here */
if (max_sector > sector_nr + good_sectors)
max_sector = sector_nr + good_sectors;
nr_sectors = 0;
sync_blocks = 0;
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;
if (sync_blocks == 0) {
if (!md_bitmap_start_sync(mddev->bitmap, sector_nr,
&sync_blocks, still_degraded) &&
!conf->fullsync &&
!test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery))
break;
if ((len >> 9) > sync_blocks)
len = sync_blocks<<9;
}
for (i = 0 ; i < conf->raid_disks * 2; i++) {
struct resync_pages *rp;
bio = r1_bio->bios[i];
rp = get_resync_pages(bio);
if (bio->bi_end_io) {
page = resync_fetch_page(rp, page_idx);
/*
* won't fail because the vec table is big
* enough to hold all these pages
*/
bio_add_page(bio, page, len, 0);
}
}
nr_sectors += len>>9;
sector_nr += len>>9;
sync_blocks -= (len>>9);
} while (++page_idx < RESYNC_PAGES);
r1_bio->sectors = nr_sectors;
if (mddev_is_clustered(mddev) &&
conf->cluster_sync_high < sector_nr + nr_sectors) {
conf->cluster_sync_low = mddev->curr_resync_completed;
conf->cluster_sync_high = conf->cluster_sync_low + CLUSTER_RESYNC_WINDOW_SECTORS;
/* Send resync message */
md_cluster_ops->resync_info_update(mddev,
conf->cluster_sync_low,
conf->cluster_sync_high);
}
/* For a user-requested sync, we read all readable devices and do a
* compare
*/
if (test_bit(MD_RECOVERY_REQUESTED, &mddev->recovery)) {
atomic_set(&r1_bio->remaining, read_targets);
for (i = 0; i < conf->raid_disks * 2 && read_targets; i++) {
bio = r1_bio->bios[i];
if (bio->bi_end_io == end_sync_read) {
read_targets--;
md_sync_acct_bio(bio, nr_sectors);
if (read_targets == 1)
bio->bi_opf &= ~MD_FAILFAST;
generic_make_request(bio);
}
}
} else {
atomic_set(&r1_bio->remaining, 1);
bio = r1_bio->bios[r1_bio->read_disk];
md_sync_acct_bio(bio, nr_sectors);
if (read_targets == 1)
bio->bi_opf &= ~MD_FAILFAST;
generic_make_request(bio);
}
return nr_sectors;
}
static sector_t raid1_size(struct mddev *mddev, sector_t sectors, int raid_disks)
{
if (sectors)
return sectors;
return mddev->dev_sectors;
}
static struct r1conf *setup_conf(struct mddev *mddev)
{
struct r1conf *conf;
int i;
struct raid1_info *disk;
struct md_rdev *rdev;
int err = -ENOMEM;
conf = kzalloc(sizeof(struct r1conf), GFP_KERNEL);
if (!conf)
goto abort;
conf->nr_pending = kcalloc(BARRIER_BUCKETS_NR,
sizeof(atomic_t), GFP_KERNEL);
if (!conf->nr_pending)
goto abort;
conf->nr_waiting = kcalloc(BARRIER_BUCKETS_NR,
sizeof(atomic_t), GFP_KERNEL);
if (!conf->nr_waiting)
goto abort;
conf->nr_queued = kcalloc(BARRIER_BUCKETS_NR,
sizeof(atomic_t), GFP_KERNEL);
if (!conf->nr_queued)
goto abort;
conf->barrier = kcalloc(BARRIER_BUCKETS_NR,
sizeof(atomic_t), GFP_KERNEL);
if (!conf->barrier)
goto abort;
conf->mirrors = kzalloc(array3_size(sizeof(struct raid1_info),
mddev->raid_disks, 2),
GFP_KERNEL);
if (!conf->mirrors)
goto abort;
conf->tmppage = alloc_page(GFP_KERNEL);
if (!conf->tmppage)
goto abort;
conf->poolinfo = kzalloc(sizeof(*conf->poolinfo), GFP_KERNEL);
if (!conf->poolinfo)
goto abort;
conf->poolinfo->raid_disks = mddev->raid_disks * 2;
err = mempool_init(&conf->r1bio_pool, NR_RAID1_BIOS, r1bio_pool_alloc,
r1bio_pool_free, conf->poolinfo);
if (err)
goto abort;
err = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
if (err)
goto abort;
conf->poolinfo->mddev = mddev;
err = -EINVAL;
spin_lock_init(&conf->device_lock);
rdev_for_each(rdev, mddev) {
int disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
continue;
if (test_bit(Replacement, &rdev->flags))
disk = conf->mirrors + mddev->raid_disks + disk_idx;
else
disk = conf->mirrors + disk_idx;
if (disk->rdev)
goto abort;
disk->rdev = rdev;
disk->head_position = 0;
disk->seq_start = MaxSector;
}
conf->raid_disks = mddev->raid_disks;
conf->mddev = mddev;
INIT_LIST_HEAD(&conf->retry_list);
INIT_LIST_HEAD(&conf->bio_end_io_list);
spin_lock_init(&conf->resync_lock);
init_waitqueue_head(&conf->wait_barrier);
bio_list_init(&conf->pending_bio_list);
conf->pending_count = 0;
conf->recovery_disabled = mddev->recovery_disabled - 1;
err = -EIO;
for (i = 0; i < conf->raid_disks * 2; i++) {
disk = conf->mirrors + i;
if (i < conf->raid_disks &&
disk[conf->raid_disks].rdev) {
/* This slot has a replacement. */
if (!disk->rdev) {
/* No original, just make the replacement
* a recovering spare
*/
disk->rdev =
disk[conf->raid_disks].rdev;
disk[conf->raid_disks].rdev = NULL;
} else if (!test_bit(In_sync, &disk->rdev->flags))
/* Original is not in_sync - bad */
goto abort;
}
if (!disk->rdev ||
!test_bit(In_sync, &disk->rdev->flags)) {
disk->head_position = 0;
if (disk->rdev &&
(disk->rdev->saved_raid_disk < 0))
conf->fullsync = 1;
}
}
err = -ENOMEM;
conf->thread = md_register_thread(raid1d, mddev, "raid1");
if (!conf->thread)
goto abort;
return conf;
abort:
if (conf) {
mempool_exit(&conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
kfree(conf->nr_pending);
kfree(conf->nr_waiting);
kfree(conf->nr_queued);
kfree(conf->barrier);
bioset_exit(&conf->bio_split);
kfree(conf);
}
return ERR_PTR(err);
}
static void raid1_free(struct mddev *mddev, void *priv);
static int raid1_run(struct mddev *mddev)
{
struct r1conf *conf;
int i;
struct md_rdev *rdev;
int ret;
bool discard_supported = false;
if (mddev->level != 1) {
pr_warn("md/raid1:%s: raid level not set to mirroring (%d)\n",
mdname(mddev), mddev->level);
return -EIO;
}
if (mddev->reshape_position != MaxSector) {
pr_warn("md/raid1:%s: reshape_position set but not supported\n",
mdname(mddev));
return -EIO;
}
if (mddev_init_writes_pending(mddev) < 0)
return -ENOMEM;
/*
* copy the already verified devices into our private RAID1
* bookkeeping area. [whatever we allocate in run(),
* should be freed in raid1_free()]
*/
if (mddev->private == NULL)
conf = setup_conf(mddev);
else
conf = mddev->private;
if (IS_ERR(conf))
return PTR_ERR(conf);
if (mddev->queue) {
blk_queue_max_write_same_sectors(mddev->queue, 0);
blk_queue_max_write_zeroes_sectors(mddev->queue, 0);
}
rdev_for_each(rdev, mddev) {
if (!mddev->gendisk)
continue;
disk_stack_limits(mddev->gendisk, rdev->bdev,
rdev->data_offset << 9);
if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
discard_supported = true;
}
mddev->degraded = 0;
for (i=0; i < conf->raid_disks; i++)
if (conf->mirrors[i].rdev == NULL ||
!test_bit(In_sync, &conf->mirrors[i].rdev->flags) ||
test_bit(Faulty, &conf->mirrors[i].rdev->flags))
mddev->degraded++;
if (conf->raid_disks - mddev->degraded == 1)
mddev->recovery_cp = MaxSector;
if (mddev->recovery_cp != MaxSector)
pr_info("md/raid1:%s: not clean -- starting background reconstruction\n",
mdname(mddev));
pr_info("md/raid1:%s: active with %d out of %d mirrors\n",
mdname(mddev), mddev->raid_disks - mddev->degraded,
mddev->raid_disks);
/*
* Ok, everything is just fine now
*/
mddev->thread = conf->thread;
conf->thread = NULL;
mddev->private = conf;
set_bit(MD_FAILFAST_SUPPORTED, &mddev->flags);
md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
if (mddev->queue) {
if (discard_supported)
blk_queue_flag_set(QUEUE_FLAG_DISCARD,
mddev->queue);
else
blk_queue_flag_clear(QUEUE_FLAG_DISCARD,
mddev->queue);
}
ret = md_integrity_register(mddev);
if (ret) {
md_unregister_thread(&mddev->thread);
raid1_free(mddev, conf);
}
return ret;
}
static void raid1_free(struct mddev *mddev, void *priv)
{
struct r1conf *conf = priv;
mempool_exit(&conf->r1bio_pool);
kfree(conf->mirrors);
safe_put_page(conf->tmppage);
kfree(conf->poolinfo);
kfree(conf->nr_pending);
kfree(conf->nr_waiting);
kfree(conf->nr_queued);
kfree(conf->barrier);
bioset_exit(&conf->bio_split);
kfree(conf);
}
static int raid1_resize(struct mddev *mddev, sector_t sectors)
{
/* no resync is happening, and there is enough space
* on all devices, so we can resize.
* We need to make sure resync covers any new space.
* If the array is shrinking we should possibly wait until
* any io in the removed space completes, but it hardly seems
* worth it.
*/
sector_t newsize = raid1_size(mddev, sectors, 0);
if (mddev->external_size &&
mddev->array_sectors > newsize)
return -EINVAL;
if (mddev->bitmap) {
int ret = md_bitmap_resize(mddev->bitmap, newsize, 0, 0);
if (ret)
return ret;
}
md_set_array_sectors(mddev, newsize);
if (sectors > mddev->dev_sectors &&
mddev->recovery_cp > mddev->dev_sectors) {
mddev->recovery_cp = mddev->dev_sectors;
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}
mddev->dev_sectors = sectors;
mddev->resync_max_sectors = sectors;
return 0;
}
static int raid1_reshape(struct mddev *mddev)
{
/* We need to:
* 1/ resize the r1bio_pool
* 2/ resize conf->mirrors
*
* We allocate a new r1bio_pool if we can.
* Then raise a device barrier and wait until all IO stops.
* Then resize conf->mirrors and swap in the new r1bio pool.
*
* At the same time, we "pack" the devices so that all the missing
* devices have the higher raid_disk numbers.
*/
mempool_t newpool, oldpool;
struct pool_info *newpoolinfo;
struct raid1_info *newmirrors;
struct r1conf *conf = mddev->private;
int cnt, raid_disks;
unsigned long flags;
int d, d2;
int ret;
memset(&newpool, 0, sizeof(newpool));
memset(&oldpool, 0, sizeof(oldpool));
/* Cannot change chunk_size, layout, or level */
if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
mddev->layout != mddev->new_layout ||
mddev->level != mddev->new_level) {
mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->new_layout = mddev->layout;
mddev->new_level = mddev->level;
return -EINVAL;
}
if (!mddev_is_clustered(mddev))
md_allow_write(mddev);
raid_disks = mddev->raid_disks + mddev->delta_disks;
if (raid_disks < conf->raid_disks) {
cnt=0;
for (d= 0; d < conf->raid_disks; d++)
if (conf->mirrors[d].rdev)
cnt++;
if (cnt > raid_disks)
return -EBUSY;
}
newpoolinfo = kmalloc(sizeof(*newpoolinfo), GFP_KERNEL);
if (!newpoolinfo)
return -ENOMEM;
newpoolinfo->mddev = mddev;
newpoolinfo->raid_disks = raid_disks * 2;
ret = mempool_init(&newpool, NR_RAID1_BIOS, r1bio_pool_alloc,
r1bio_pool_free, newpoolinfo);
if (ret) {
kfree(newpoolinfo);
return ret;
}
newmirrors = kzalloc(array3_size(sizeof(struct raid1_info),
raid_disks, 2),
GFP_KERNEL);
if (!newmirrors) {
kfree(newpoolinfo);
mempool_exit(&newpool);
return -ENOMEM;
}
freeze_array(conf, 0);
/* ok, everything is stopped */
oldpool = conf->r1bio_pool;
conf->r1bio_pool = newpool;
for (d = d2 = 0; d < conf->raid_disks; d++) {
struct md_rdev *rdev = conf->mirrors[d].rdev;
if (rdev && rdev->raid_disk != d2) {
sysfs_unlink_rdev(mddev, rdev);
rdev->raid_disk = d2;
sysfs_unlink_rdev(mddev, rdev);
if (sysfs_link_rdev(mddev, rdev))
pr_warn("md/raid1:%s: cannot register rd%d\n",
mdname(mddev), rdev->raid_disk);
}
if (rdev)
newmirrors[d2++].rdev = rdev;
}
kfree(conf->mirrors);
conf->mirrors = newmirrors;
kfree(conf->poolinfo);
conf->poolinfo = newpoolinfo;
spin_lock_irqsave(&conf->device_lock, flags);
mddev->degraded += (raid_disks - conf->raid_disks);
spin_unlock_irqrestore(&conf->device_lock, flags);
conf->raid_disks = mddev->raid_disks = raid_disks;
mddev->delta_disks = 0;
unfreeze_array(conf);
set_bit(MD_RECOVERY_RECOVER, &mddev->recovery);
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
md_wakeup_thread(mddev->thread);
mempool_exit(&oldpool);
return 0;
}
static void raid1_quiesce(struct mddev *mddev, int quiesce)
{
struct r1conf *conf = mddev->private;
if (quiesce)
freeze_array(conf, 0);
else
unfreeze_array(conf);
}
static void *raid1_takeover(struct mddev *mddev)
{
/* raid1 can take over:
* raid5 with 2 devices, any layout or chunk size
*/
if (mddev->level == 5 && mddev->raid_disks == 2) {
struct r1conf *conf;
mddev->new_level = 1;
mddev->new_layout = 0;
mddev->new_chunk_sectors = 0;
conf = setup_conf(mddev);
if (!IS_ERR(conf)) {
/* Array must appear to be quiesced */
conf->array_frozen = 1;
mddev_clear_unsupported_flags(mddev,
UNSUPPORTED_MDDEV_FLAGS);
}
return conf;
}
return ERR_PTR(-EINVAL);
}
static struct md_personality raid1_personality =
{
.name = "raid1",
.level = 1,
.owner = THIS_MODULE,
.make_request = raid1_make_request,
.run = raid1_run,
.free = raid1_free,
.status = raid1_status,
.error_handler = raid1_error,
.hot_add_disk = raid1_add_disk,
.hot_remove_disk= raid1_remove_disk,
.spare_active = raid1_spare_active,
.sync_request = raid1_sync_request,
.resize = raid1_resize,
.size = raid1_size,
.check_reshape = raid1_reshape,
.quiesce = raid1_quiesce,
.takeover = raid1_takeover,
.congested = raid1_congested,
};
static int __init raid_init(void)
{
return register_md_personality(&raid1_personality);
}
static void raid_exit(void)
{
unregister_md_personality(&raid1_personality);
}
module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("RAID1 (mirroring) personality for MD");
MODULE_ALIAS("md-personality-3"); /* RAID1 */
MODULE_ALIAS("md-raid1");
MODULE_ALIAS("md-level-1");
module_param(max_queued_requests, int, S_IRUGO|S_IWUSR);
|