summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/raid56.c
blob: 57a2ac721985062661329ffffc27e623eac5bcc4 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2012 Fusion-io  All rights reserved.
 * Copyright (C) 2012 Intel Corp. All rights reserved.
 */

#include <linux/sched.h>
#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/raid/pq.h>
#include <linux/hash.h>
#include <linux/list_sort.h>
#include <linux/raid/xor.h>
#include <linux/mm.h>
#include "ctree.h"
#include "disk-io.h"
#include "volumes.h"
#include "raid56.h"
#include "async-thread.h"

/* set when additional merges to this rbio are not allowed */
#define RBIO_RMW_LOCKED_BIT	1

/*
 * set when this rbio is sitting in the hash, but it is just a cache
 * of past RMW
 */
#define RBIO_CACHE_BIT		2

/*
 * set when it is safe to trust the stripe_pages for caching
 */
#define RBIO_CACHE_READY_BIT	3

#define RBIO_CACHE_SIZE 1024

#define BTRFS_STRIPE_HASH_TABLE_BITS				11

/* Used by the raid56 code to lock stripes for read/modify/write */
struct btrfs_stripe_hash {
	struct list_head hash_list;
	spinlock_t lock;
};

/* Used by the raid56 code to lock stripes for read/modify/write */
struct btrfs_stripe_hash_table {
	struct list_head stripe_cache;
	spinlock_t cache_lock;
	int cache_size;
	struct btrfs_stripe_hash table[];
};

enum btrfs_rbio_ops {
	BTRFS_RBIO_WRITE,
	BTRFS_RBIO_READ_REBUILD,
	BTRFS_RBIO_PARITY_SCRUB,
	BTRFS_RBIO_REBUILD_MISSING,
};

struct btrfs_raid_bio {
	struct btrfs_fs_info *fs_info;
	struct btrfs_bio *bbio;

	/* while we're doing rmw on a stripe
	 * we put it into a hash table so we can
	 * lock the stripe and merge more rbios
	 * into it.
	 */
	struct list_head hash_list;

	/*
	 * LRU list for the stripe cache
	 */
	struct list_head stripe_cache;

	/*
	 * for scheduling work in the helper threads
	 */
	struct btrfs_work work;

	/*
	 * bio list and bio_list_lock are used
	 * to add more bios into the stripe
	 * in hopes of avoiding the full rmw
	 */
	struct bio_list bio_list;
	spinlock_t bio_list_lock;

	/* also protected by the bio_list_lock, the
	 * plug list is used by the plugging code
	 * to collect partial bios while plugged.  The
	 * stripe locking code also uses it to hand off
	 * the stripe lock to the next pending IO
	 */
	struct list_head plug_list;

	/*
	 * flags that tell us if it is safe to
	 * merge with this bio
	 */
	unsigned long flags;

	/* size of each individual stripe on disk */
	int stripe_len;

	/* number of data stripes (no p/q) */
	int nr_data;

	int real_stripes;

	int stripe_npages;
	/*
	 * set if we're doing a parity rebuild
	 * for a read from higher up, which is handled
	 * differently from a parity rebuild as part of
	 * rmw
	 */
	enum btrfs_rbio_ops operation;

	/* first bad stripe */
	int faila;

	/* second bad stripe (for raid6 use) */
	int failb;

	int scrubp;
	/*
	 * number of pages needed to represent the full
	 * stripe
	 */
	int nr_pages;

	/*
	 * size of all the bios in the bio_list.  This
	 * helps us decide if the rbio maps to a full
	 * stripe or not
	 */
	int bio_list_bytes;

	int generic_bio_cnt;

	refcount_t refs;

	atomic_t stripes_pending;

	atomic_t error;
	/*
	 * these are two arrays of pointers.  We allocate the
	 * rbio big enough to hold them both and setup their
	 * locations when the rbio is allocated
	 */

	/* pointers to pages that we allocated for
	 * reading/writing stripes directly from the disk (including P/Q)
	 */
	struct page **stripe_pages;

	/*
	 * pointers to the pages in the bio_list.  Stored
	 * here for faster lookup
	 */
	struct page **bio_pages;

	/*
	 * bitmap to record which horizontal stripe has data
	 */
	unsigned long *dbitmap;

	/* allocated with real_stripes-many pointers for finish_*() calls */
	void **finish_pointers;

	/* allocated with stripe_npages-many bits for finish_*() calls */
	unsigned long *finish_pbitmap;
};

static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
static void rmw_work(struct btrfs_work *work);
static void read_rebuild_work(struct btrfs_work *work);
static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio);
static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed);
static void __free_raid_bio(struct btrfs_raid_bio *rbio);
static void index_rbio_pages(struct btrfs_raid_bio *rbio);
static int alloc_rbio_pages(struct btrfs_raid_bio *rbio);

static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
					 int need_check);
static void scrub_parity_work(struct btrfs_work *work);

static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
{
	btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
}

/*
 * the stripe hash table is used for locking, and to collect
 * bios in hopes of making a full stripe
 */
int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info)
{
	struct btrfs_stripe_hash_table *table;
	struct btrfs_stripe_hash_table *x;
	struct btrfs_stripe_hash *cur;
	struct btrfs_stripe_hash *h;
	int num_entries = 1 << BTRFS_STRIPE_HASH_TABLE_BITS;
	int i;
	int table_size;

	if (info->stripe_hash_table)
		return 0;

	/*
	 * The table is large, starting with order 4 and can go as high as
	 * order 7 in case lock debugging is turned on.
	 *
	 * Try harder to allocate and fallback to vmalloc to lower the chance
	 * of a failing mount.
	 */
	table_size = sizeof(*table) + sizeof(*h) * num_entries;
	table = kvzalloc(table_size, GFP_KERNEL);
	if (!table)
		return -ENOMEM;

	spin_lock_init(&table->cache_lock);
	INIT_LIST_HEAD(&table->stripe_cache);

	h = table->table;

	for (i = 0; i < num_entries; i++) {
		cur = h + i;
		INIT_LIST_HEAD(&cur->hash_list);
		spin_lock_init(&cur->lock);
	}

	x = cmpxchg(&info->stripe_hash_table, NULL, table);
	if (x)
		kvfree(x);
	return 0;
}

/*
 * caching an rbio means to copy anything from the
 * bio_pages array into the stripe_pages array.  We
 * use the page uptodate bit in the stripe cache array
 * to indicate if it has valid data
 *
 * once the caching is done, we set the cache ready
 * bit.
 */
static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
{
	int i;
	char *s;
	char *d;
	int ret;

	ret = alloc_rbio_pages(rbio);
	if (ret)
		return;

	for (i = 0; i < rbio->nr_pages; i++) {
		if (!rbio->bio_pages[i])
			continue;

		s = kmap(rbio->bio_pages[i]);
		d = kmap(rbio->stripe_pages[i]);

		copy_page(d, s);

		kunmap(rbio->bio_pages[i]);
		kunmap(rbio->stripe_pages[i]);
		SetPageUptodate(rbio->stripe_pages[i]);
	}
	set_bit(RBIO_CACHE_READY_BIT, &rbio->flags);
}

/*
 * we hash on the first logical address of the stripe
 */
static int rbio_bucket(struct btrfs_raid_bio *rbio)
{
	u64 num = rbio->bbio->raid_map[0];

	/*
	 * we shift down quite a bit.  We're using byte
	 * addressing, and most of the lower bits are zeros.
	 * This tends to upset hash_64, and it consistently
	 * returns just one or two different values.
	 *
	 * shifting off the lower bits fixes things.
	 */
	return hash_64(num >> 16, BTRFS_STRIPE_HASH_TABLE_BITS);
}

/*
 * stealing an rbio means taking all the uptodate pages from the stripe
 * array in the source rbio and putting them into the destination rbio
 */
static void steal_rbio(struct btrfs_raid_bio *src, struct btrfs_raid_bio *dest)
{
	int i;
	struct page *s;
	struct page *d;

	if (!test_bit(RBIO_CACHE_READY_BIT, &src->flags))
		return;

	for (i = 0; i < dest->nr_pages; i++) {
		s = src->stripe_pages[i];
		if (!s || !PageUptodate(s)) {
			continue;
		}

		d = dest->stripe_pages[i];
		if (d)
			__free_page(d);

		dest->stripe_pages[i] = s;
		src->stripe_pages[i] = NULL;
	}
}

/*
 * merging means we take the bio_list from the victim and
 * splice it into the destination.  The victim should
 * be discarded afterwards.
 *
 * must be called with dest->rbio_list_lock held
 */
static void merge_rbio(struct btrfs_raid_bio *dest,
		       struct btrfs_raid_bio *victim)
{
	bio_list_merge(&dest->bio_list, &victim->bio_list);
	dest->bio_list_bytes += victim->bio_list_bytes;
	dest->generic_bio_cnt += victim->generic_bio_cnt;
	bio_list_init(&victim->bio_list);
}

/*
 * used to prune items that are in the cache.  The caller
 * must hold the hash table lock.
 */
static void __remove_rbio_from_cache(struct btrfs_raid_bio *rbio)
{
	int bucket = rbio_bucket(rbio);
	struct btrfs_stripe_hash_table *table;
	struct btrfs_stripe_hash *h;
	int freeit = 0;

	/*
	 * check the bit again under the hash table lock.
	 */
	if (!test_bit(RBIO_CACHE_BIT, &rbio->flags))
		return;

	table = rbio->fs_info->stripe_hash_table;
	h = table->table + bucket;

	/* hold the lock for the bucket because we may be
	 * removing it from the hash table
	 */
	spin_lock(&h->lock);

	/*
	 * hold the lock for the bio list because we need
	 * to make sure the bio list is empty
	 */
	spin_lock(&rbio->bio_list_lock);

	if (test_and_clear_bit(RBIO_CACHE_BIT, &rbio->flags)) {
		list_del_init(&rbio->stripe_cache);
		table->cache_size -= 1;
		freeit = 1;

		/* if the bio list isn't empty, this rbio is
		 * still involved in an IO.  We take it out
		 * of the cache list, and drop the ref that
		 * was held for the list.
		 *
		 * If the bio_list was empty, we also remove
		 * the rbio from the hash_table, and drop
		 * the corresponding ref
		 */
		if (bio_list_empty(&rbio->bio_list)) {
			if (!list_empty(&rbio->hash_list)) {
				list_del_init(&rbio->hash_list);
				refcount_dec(&rbio->refs);
				BUG_ON(!list_empty(&rbio->plug_list));
			}
		}
	}

	spin_unlock(&rbio->bio_list_lock);
	spin_unlock(&h->lock);

	if (freeit)
		__free_raid_bio(rbio);
}

/*
 * prune a given rbio from the cache
 */
static void remove_rbio_from_cache(struct btrfs_raid_bio *rbio)
{
	struct btrfs_stripe_hash_table *table;
	unsigned long flags;

	if (!test_bit(RBIO_CACHE_BIT, &rbio->flags))
		return;

	table = rbio->fs_info->stripe_hash_table;

	spin_lock_irqsave(&table->cache_lock, flags);
	__remove_rbio_from_cache(rbio);
	spin_unlock_irqrestore(&table->cache_lock, flags);
}

/*
 * remove everything in the cache
 */
static void btrfs_clear_rbio_cache(struct btrfs_fs_info *info)
{
	struct btrfs_stripe_hash_table *table;
	unsigned long flags;
	struct btrfs_raid_bio *rbio;

	table = info->stripe_hash_table;

	spin_lock_irqsave(&table->cache_lock, flags);
	while (!list_empty(&table->stripe_cache)) {
		rbio = list_entry(table->stripe_cache.next,
				  struct btrfs_raid_bio,
				  stripe_cache);
		__remove_rbio_from_cache(rbio);
	}
	spin_unlock_irqrestore(&table->cache_lock, flags);
}

/*
 * remove all cached entries and free the hash table
 * used by unmount
 */
void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info)
{
	if (!info->stripe_hash_table)
		return;
	btrfs_clear_rbio_cache(info);
	kvfree(info->stripe_hash_table);
	info->stripe_hash_table = NULL;
}

/*
 * insert an rbio into the stripe cache.  It
 * must have already been prepared by calling
 * cache_rbio_pages
 *
 * If this rbio was already cached, it gets
 * moved to the front of the lru.
 *
 * If the size of the rbio cache is too big, we
 * prune an item.
 */
static void cache_rbio(struct btrfs_raid_bio *rbio)
{
	struct btrfs_stripe_hash_table *table;
	unsigned long flags;

	if (!test_bit(RBIO_CACHE_READY_BIT, &rbio->flags))
		return;

	table = rbio->fs_info->stripe_hash_table;

	spin_lock_irqsave(&table->cache_lock, flags);
	spin_lock(&rbio->bio_list_lock);

	/* bump our ref if we were not in the list before */
	if (!test_and_set_bit(RBIO_CACHE_BIT, &rbio->flags))
		refcount_inc(&rbio->refs);

	if (!list_empty(&rbio->stripe_cache)){
		list_move(&rbio->stripe_cache, &table->stripe_cache);
	} else {
		list_add(&rbio->stripe_cache, &table->stripe_cache);
		table->cache_size += 1;
	}

	spin_unlock(&rbio->bio_list_lock);

	if (table->cache_size > RBIO_CACHE_SIZE) {
		struct btrfs_raid_bio *found;

		found = list_entry(table->stripe_cache.prev,
				  struct btrfs_raid_bio,
				  stripe_cache);

		if (found != rbio)
			__remove_rbio_from_cache(found);
	}

	spin_unlock_irqrestore(&table->cache_lock, flags);
}

/*
 * helper function to run the xor_blocks api.  It is only
 * able to do MAX_XOR_BLOCKS at a time, so we need to
 * loop through.
 */
static void run_xor(void **pages, int src_cnt, ssize_t len)
{
	int src_off = 0;
	int xor_src_cnt = 0;
	void *dest = pages[src_cnt];

	while(src_cnt > 0) {
		xor_src_cnt = min(src_cnt, MAX_XOR_BLOCKS);
		xor_blocks(xor_src_cnt, len, dest, pages + src_off);

		src_cnt -= xor_src_cnt;
		src_off += xor_src_cnt;
	}
}

/*
 * Returns true if the bio list inside this rbio covers an entire stripe (no
 * rmw required).
 */
static int rbio_is_full(struct btrfs_raid_bio *rbio)
{
	unsigned long flags;
	unsigned long size = rbio->bio_list_bytes;
	int ret = 1;

	spin_lock_irqsave(&rbio->bio_list_lock, flags);
	if (size != rbio->nr_data * rbio->stripe_len)
		ret = 0;
	BUG_ON(size > rbio->nr_data * rbio->stripe_len);
	spin_unlock_irqrestore(&rbio->bio_list_lock, flags);

	return ret;
}

/*
 * returns 1 if it is safe to merge two rbios together.
 * The merging is safe if the two rbios correspond to
 * the same stripe and if they are both going in the same
 * direction (read vs write), and if neither one is
 * locked for final IO
 *
 * The caller is responsible for locking such that
 * rmw_locked is safe to test
 */
static int rbio_can_merge(struct btrfs_raid_bio *last,
			  struct btrfs_raid_bio *cur)
{
	if (test_bit(RBIO_RMW_LOCKED_BIT, &last->flags) ||
	    test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags))
		return 0;

	/*
	 * we can't merge with cached rbios, since the
	 * idea is that when we merge the destination
	 * rbio is going to run our IO for us.  We can
	 * steal from cached rbios though, other functions
	 * handle that.
	 */
	if (test_bit(RBIO_CACHE_BIT, &last->flags) ||
	    test_bit(RBIO_CACHE_BIT, &cur->flags))
		return 0;

	if (last->bbio->raid_map[0] !=
	    cur->bbio->raid_map[0])
		return 0;

	/* we can't merge with different operations */
	if (last->operation != cur->operation)
		return 0;
	/*
	 * We've need read the full stripe from the drive.
	 * check and repair the parity and write the new results.
	 *
	 * We're not allowed to add any new bios to the
	 * bio list here, anyone else that wants to
	 * change this stripe needs to do their own rmw.
	 */
	if (last->operation == BTRFS_RBIO_PARITY_SCRUB)
		return 0;

	if (last->operation == BTRFS_RBIO_REBUILD_MISSING)
		return 0;

	if (last->operation == BTRFS_RBIO_READ_REBUILD) {
		int fa = last->faila;
		int fb = last->failb;
		int cur_fa = cur->faila;
		int cur_fb = cur->failb;

		if (last->faila >= last->failb) {
			fa = last->failb;
			fb = last->faila;
		}

		if (cur->faila >= cur->failb) {
			cur_fa = cur->failb;
			cur_fb = cur->faila;
		}

		if (fa != cur_fa || fb != cur_fb)
			return 0;
	}
	return 1;
}

static int rbio_stripe_page_index(struct btrfs_raid_bio *rbio, int stripe,
				  int index)
{
	return stripe * rbio->stripe_npages + index;
}

/*
 * these are just the pages from the rbio array, not from anything
 * the FS sent down to us
 */
static struct page *rbio_stripe_page(struct btrfs_raid_bio *rbio, int stripe,
				     int index)
{
	return rbio->stripe_pages[rbio_stripe_page_index(rbio, stripe, index)];
}

/*
 * helper to index into the pstripe
 */
static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
{
	return rbio_stripe_page(rbio, rbio->nr_data, index);
}

/*
 * helper to index into the qstripe, returns null
 * if there is no qstripe
 */
static struct page *rbio_qstripe_page(struct btrfs_raid_bio *rbio, int index)
{
	if (rbio->nr_data + 1 == rbio->real_stripes)
		return NULL;
	return rbio_stripe_page(rbio, rbio->nr_data + 1, index);
}

/*
 * The first stripe in the table for a logical address
 * has the lock.  rbios are added in one of three ways:
 *
 * 1) Nobody has the stripe locked yet.  The rbio is given
 * the lock and 0 is returned.  The caller must start the IO
 * themselves.
 *
 * 2) Someone has the stripe locked, but we're able to merge
 * with the lock owner.  The rbio is freed and the IO will
 * start automatically along with the existing rbio.  1 is returned.
 *
 * 3) Someone has the stripe locked, but we're not able to merge.
 * The rbio is added to the lock owner's plug list, or merged into
 * an rbio already on the plug list.  When the lock owner unlocks,
 * the next rbio on the list is run and the IO is started automatically.
 * 1 is returned
 *
 * If we return 0, the caller still owns the rbio and must continue with
 * IO submission.  If we return 1, the caller must assume the rbio has
 * already been freed.
 */
static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
{
	int bucket = rbio_bucket(rbio);
	struct btrfs_stripe_hash *h = rbio->fs_info->stripe_hash_table->table + bucket;
	struct btrfs_raid_bio *cur;
	struct btrfs_raid_bio *pending;
	unsigned long flags;
	struct btrfs_raid_bio *freeit = NULL;
	struct btrfs_raid_bio *cache_drop = NULL;
	int ret = 0;

	spin_lock_irqsave(&h->lock, flags);
	list_for_each_entry(cur, &h->hash_list, hash_list) {
		if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) {
			spin_lock(&cur->bio_list_lock);

			/* can we steal this cached rbio's pages? */
			if (bio_list_empty(&cur->bio_list) &&
			    list_empty(&cur->plug_list) &&
			    test_bit(RBIO_CACHE_BIT, &cur->flags) &&
			    !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
				list_del_init(&cur->hash_list);
				refcount_dec(&cur->refs);

				steal_rbio(cur, rbio);
				cache_drop = cur;
				spin_unlock(&cur->bio_list_lock);

				goto lockit;
			}

			/* can we merge into the lock owner? */
			if (rbio_can_merge(cur, rbio)) {
				merge_rbio(cur, rbio);
				spin_unlock(&cur->bio_list_lock);
				freeit = rbio;
				ret = 1;
				goto out;
			}


			/*
			 * we couldn't merge with the running
			 * rbio, see if we can merge with the
			 * pending ones.  We don't have to
			 * check for rmw_locked because there
			 * is no way they are inside finish_rmw
			 * right now
			 */
			list_for_each_entry(pending, &cur->plug_list,
					    plug_list) {
				if (rbio_can_merge(pending, rbio)) {
					merge_rbio(pending, rbio);
					spin_unlock(&cur->bio_list_lock);
					freeit = rbio;
					ret = 1;
					goto out;
				}
			}

			/* no merging, put us on the tail of the plug list,
			 * our rbio will be started with the currently
			 * running rbio unlocks
			 */
			list_add_tail(&rbio->plug_list, &cur->plug_list);
			spin_unlock(&cur->bio_list_lock);
			ret = 1;
			goto out;
		}
	}
lockit:
	refcount_inc(&rbio->refs);
	list_add(&rbio->hash_list, &h->hash_list);
out:
	spin_unlock_irqrestore(&h->lock, flags);
	if (cache_drop)
		remove_rbio_from_cache(cache_drop);
	if (freeit)
		__free_raid_bio(freeit);
	return ret;
}

/*
 * called as rmw or parity rebuild is completed.  If the plug list has more
 * rbios waiting for this stripe, the next one on the list will be started
 */
static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
{
	int bucket;
	struct btrfs_stripe_hash *h;
	unsigned long flags;
	int keep_cache = 0;

	bucket = rbio_bucket(rbio);
	h = rbio->fs_info->stripe_hash_table->table + bucket;

	if (list_empty(&rbio->plug_list))
		cache_rbio(rbio);

	spin_lock_irqsave(&h->lock, flags);
	spin_lock(&rbio->bio_list_lock);

	if (!list_empty(&rbio->hash_list)) {
		/*
		 * if we're still cached and there is no other IO
		 * to perform, just leave this rbio here for others
		 * to steal from later
		 */
		if (list_empty(&rbio->plug_list) &&
		    test_bit(RBIO_CACHE_BIT, &rbio->flags)) {
			keep_cache = 1;
			clear_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
			BUG_ON(!bio_list_empty(&rbio->bio_list));
			goto done;
		}

		list_del_init(&rbio->hash_list);
		refcount_dec(&rbio->refs);

		/*
		 * we use the plug list to hold all the rbios
		 * waiting for the chance to lock this stripe.
		 * hand the lock over to one of them.
		 */
		if (!list_empty(&rbio->plug_list)) {
			struct btrfs_raid_bio *next;
			struct list_head *head = rbio->plug_list.next;

			next = list_entry(head, struct btrfs_raid_bio,
					  plug_list);

			list_del_init(&rbio->plug_list);

			list_add(&next->hash_list, &h->hash_list);
			refcount_inc(&next->refs);
			spin_unlock(&rbio->bio_list_lock);
			spin_unlock_irqrestore(&h->lock, flags);

			if (next->operation == BTRFS_RBIO_READ_REBUILD)
				start_async_work(next, read_rebuild_work);
			else if (next->operation == BTRFS_RBIO_REBUILD_MISSING) {
				steal_rbio(rbio, next);
				start_async_work(next, read_rebuild_work);
			} else if (next->operation == BTRFS_RBIO_WRITE) {
				steal_rbio(rbio, next);
				start_async_work(next, rmw_work);
			} else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) {
				steal_rbio(rbio, next);
				start_async_work(next, scrub_parity_work);
			}

			goto done_nolock;
		}
	}
done:
	spin_unlock(&rbio->bio_list_lock);
	spin_unlock_irqrestore(&h->lock, flags);

done_nolock:
	if (!keep_cache)
		remove_rbio_from_cache(rbio);
}

static void __free_raid_bio(struct btrfs_raid_bio *rbio)
{
	int i;

	if (!refcount_dec_and_test(&rbio->refs))
		return;

	WARN_ON(!list_empty(&rbio->stripe_cache));
	WARN_ON(!list_empty(&rbio->hash_list));
	WARN_ON(!bio_list_empty(&rbio->bio_list));

	for (i = 0; i < rbio->nr_pages; i++) {
		if (rbio->stripe_pages[i]) {
			__free_page(rbio->stripe_pages[i]);
			rbio->stripe_pages[i] = NULL;
		}
	}

	btrfs_put_bbio(rbio->bbio);
	kfree(rbio);
}

static void rbio_endio_bio_list(struct bio *cur, blk_status_t err)
{
	struct bio *next;

	while (cur) {
		next = cur->bi_next;
		cur->bi_next = NULL;
		cur->bi_status = err;
		bio_endio(cur);
		cur = next;
	}
}

/*
 * this frees the rbio and runs through all the bios in the
 * bio_list and calls end_io on them
 */
static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err)
{
	struct bio *cur = bio_list_get(&rbio->bio_list);
	struct bio *extra;

	if (rbio->generic_bio_cnt)
		btrfs_bio_counter_sub(rbio->fs_info, rbio->generic_bio_cnt);

	/*
	 * At this moment, rbio->bio_list is empty, however since rbio does not
	 * always have RBIO_RMW_LOCKED_BIT set and rbio is still linked on the
	 * hash list, rbio may be merged with others so that rbio->bio_list
	 * becomes non-empty.
	 * Once unlock_stripe() is done, rbio->bio_list will not be updated any
	 * more and we can call bio_endio() on all queued bios.
	 */
	unlock_stripe(rbio);
	extra = bio_list_get(&rbio->bio_list);
	__free_raid_bio(rbio);

	rbio_endio_bio_list(cur, err);
	if (extra)
		rbio_endio_bio_list(extra, err);
}

/*
 * end io function used by finish_rmw.  When we finally
 * get here, we've written a full stripe
 */
static void raid_write_end_io(struct bio *bio)
{
	struct btrfs_raid_bio *rbio = bio->bi_private;
	blk_status_t err = bio->bi_status;
	int max_errors;

	if (err)
		fail_bio_stripe(rbio, bio);

	bio_put(bio);

	if (!atomic_dec_and_test(&rbio->stripes_pending))
		return;

	err = BLK_STS_OK;

	/* OK, we have read all the stripes we need to. */
	max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
		     0 : rbio->bbio->max_errors;
	if (atomic_read(&rbio->error) > max_errors)
		err = BLK_STS_IOERR;

	rbio_orig_end_io(rbio, err);
}

/*
 * the read/modify/write code wants to use the original bio for
 * any pages it included, and then use the rbio for everything
 * else.  This function decides if a given index (stripe number)
 * and page number in that stripe fall inside the original bio
 * or the rbio.
 *
 * if you set bio_list_only, you'll get a NULL back for any ranges
 * that are outside the bio_list
 *
 * This doesn't take any refs on anything, you get a bare page pointer
 * and the caller must bump refs as required.
 *
 * You must call index_rbio_pages once before you can trust
 * the answers from this function.
 */
static struct page *page_in_rbio(struct btrfs_raid_bio *rbio,
				 int index, int pagenr, int bio_list_only)
{
	int chunk_page;
	struct page *p = NULL;

	chunk_page = index * (rbio->stripe_len >> PAGE_SHIFT) + pagenr;

	spin_lock_irq(&rbio->bio_list_lock);
	p = rbio->bio_pages[chunk_page];
	spin_unlock_irq(&rbio->bio_list_lock);

	if (p || bio_list_only)
		return p;

	return rbio->stripe_pages[chunk_page];
}

/*
 * number of pages we need for the entire stripe across all the
 * drives
 */
static unsigned long rbio_nr_pages(unsigned long stripe_len, int nr_stripes)
{
	return DIV_ROUND_UP(stripe_len, PAGE_SIZE) * nr_stripes;
}

/*
 * allocation and initial setup for the btrfs_raid_bio.  Not
 * this does not allocate any pages for rbio->pages.
 */
static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
					 struct btrfs_bio *bbio,
					 u64 stripe_len)
{
	struct btrfs_raid_bio *rbio;
	int nr_data = 0;
	int real_stripes = bbio->num_stripes - bbio->num_tgtdevs;
	int num_pages = rbio_nr_pages(stripe_len, real_stripes);
	int stripe_npages = DIV_ROUND_UP(stripe_len, PAGE_SIZE);
	void *p;

	rbio = kzalloc(sizeof(*rbio) +
		       sizeof(*rbio->stripe_pages) * num_pages +
		       sizeof(*rbio->bio_pages) * num_pages +
		       sizeof(*rbio->finish_pointers) * real_stripes +
		       sizeof(*rbio->dbitmap) * BITS_TO_LONGS(stripe_npages) +
		       sizeof(*rbio->finish_pbitmap) *
				BITS_TO_LONGS(stripe_npages),
		       GFP_NOFS);
	if (!rbio)
		return ERR_PTR(-ENOMEM);

	bio_list_init(&rbio->bio_list);
	INIT_LIST_HEAD(&rbio->plug_list);
	spin_lock_init(&rbio->bio_list_lock);
	INIT_LIST_HEAD(&rbio->stripe_cache);
	INIT_LIST_HEAD(&rbio->hash_list);
	rbio->bbio = bbio;
	rbio->fs_info = fs_info;
	rbio->stripe_len = stripe_len;
	rbio->nr_pages = num_pages;
	rbio->real_stripes = real_stripes;
	rbio->stripe_npages = stripe_npages;
	rbio->faila = -1;
	rbio->failb = -1;
	refcount_set(&rbio->refs, 1);
	atomic_set(&rbio->error, 0);
	atomic_set(&rbio->stripes_pending, 0);

	/*
	 * the stripe_pages, bio_pages, etc arrays point to the extra
	 * memory we allocated past the end of the rbio
	 */
	p = rbio + 1;
#define CONSUME_ALLOC(ptr, count)	do {				\
		ptr = p;						\
		p = (unsigned char *)p + sizeof(*(ptr)) * (count);	\
	} while (0)
	CONSUME_ALLOC(rbio->stripe_pages, num_pages);
	CONSUME_ALLOC(rbio->bio_pages, num_pages);
	CONSUME_ALLOC(rbio->finish_pointers, real_stripes);
	CONSUME_ALLOC(rbio->dbitmap, BITS_TO_LONGS(stripe_npages));
	CONSUME_ALLOC(rbio->finish_pbitmap, BITS_TO_LONGS(stripe_npages));
#undef  CONSUME_ALLOC

	if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID5)
		nr_data = real_stripes - 1;
	else if (bbio->map_type & BTRFS_BLOCK_GROUP_RAID6)
		nr_data = real_stripes - 2;
	else
		BUG();

	rbio->nr_data = nr_data;
	return rbio;
}

/* allocate pages for all the stripes in the bio, including parity */
static int alloc_rbio_pages(struct btrfs_raid_bio *rbio)
{
	int i;
	struct page *page;

	for (i = 0; i < rbio->nr_pages; i++) {
		if (rbio->stripe_pages[i])
			continue;
		page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
		if (!page)
			return -ENOMEM;
		rbio->stripe_pages[i] = page;
	}
	return 0;
}

/* only allocate pages for p/q stripes */
static int alloc_rbio_parity_pages(struct btrfs_raid_bio *rbio)
{
	int i;
	struct page *page;

	i = rbio_stripe_page_index(rbio, rbio->nr_data, 0);

	for (; i < rbio->nr_pages; i++) {
		if (rbio->stripe_pages[i])
			continue;
		page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
		if (!page)
			return -ENOMEM;
		rbio->stripe_pages[i] = page;
	}
	return 0;
}

/*
 * add a single page from a specific stripe into our list of bios for IO
 * this will try to merge into existing bios if possible, and returns
 * zero if all went well.
 */
static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
			    struct bio_list *bio_list,
			    struct page *page,
			    int stripe_nr,
			    unsigned long page_index,
			    unsigned long bio_max_len)
{
	struct bio *last = bio_list->tail;
	u64 last_end = 0;
	int ret;
	struct bio *bio;
	struct btrfs_bio_stripe *stripe;
	u64 disk_start;

	stripe = &rbio->bbio->stripes[stripe_nr];
	disk_start = stripe->physical + (page_index << PAGE_SHIFT);

	/* if the device is missing, just fail this stripe */
	if (!stripe->dev->bdev)
		return fail_rbio_index(rbio, stripe_nr);

	/* see if we can add this page onto our existing bio */
	if (last) {
		last_end = (u64)last->bi_iter.bi_sector << 9;
		last_end += last->bi_iter.bi_size;

		/*
		 * we can't merge these if they are from different
		 * devices or if they are not contiguous
		 */
		if (last_end == disk_start && stripe->dev->bdev &&
		    !last->bi_status &&
		    last->bi_disk == stripe->dev->bdev->bd_disk &&
		    last->bi_partno == stripe->dev->bdev->bd_partno) {
			ret = bio_add_page(last, page, PAGE_SIZE, 0);
			if (ret == PAGE_SIZE)
				return 0;
		}
	}

	/* put a new bio on the list */
	bio = btrfs_io_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1);
	bio->bi_iter.bi_size = 0;
	bio_set_dev(bio, stripe->dev->bdev);
	bio->bi_iter.bi_sector = disk_start >> 9;

	bio_add_page(bio, page, PAGE_SIZE, 0);
	bio_list_add(bio_list, bio);
	return 0;
}

/*
 * while we're doing the read/modify/write cycle, we could
 * have errors in reading pages off the disk.  This checks
 * for errors and if we're not able to read the page it'll
 * trigger parity reconstruction.  The rmw will be finished
 * after we've reconstructed the failed stripes
 */
static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
{
	if (rbio->faila >= 0 || rbio->failb >= 0) {
		BUG_ON(rbio->faila == rbio->real_stripes - 1);
		__raid56_parity_recover(rbio);
	} else {
		finish_rmw(rbio);
	}
}

/*
 * helper function to walk our bio list and populate the bio_pages array with
 * the result.  This seems expensive, but it is faster than constantly
 * searching through the bio list as we setup the IO in finish_rmw or stripe
 * reconstruction.
 *
 * This must be called before you trust the answers from page_in_rbio
 */
static void index_rbio_pages(struct btrfs_raid_bio *rbio)
{
	struct bio *bio;
	u64 start;
	unsigned long stripe_offset;
	unsigned long page_index;

	spin_lock_irq(&rbio->bio_list_lock);
	bio_list_for_each(bio, &rbio->bio_list) {
		struct bio_vec bvec;
		struct bvec_iter iter;
		int i = 0;

		start = (u64)bio->bi_iter.bi_sector << 9;
		stripe_offset = start - rbio->bbio->raid_map[0];
		page_index = stripe_offset >> PAGE_SHIFT;

		if (bio_flagged(bio, BIO_CLONED))
			bio->bi_iter = btrfs_io_bio(bio)->iter;

		bio_for_each_segment(bvec, bio, iter) {
			rbio->bio_pages[page_index + i] = bvec.bv_page;
			i++;
		}
	}
	spin_unlock_irq(&rbio->bio_list_lock);
}

/*
 * this is called from one of two situations.  We either
 * have a full stripe from the higher layers, or we've read all
 * the missing bits off disk.
 *
 * This will calculate the parity and then send down any
 * changed blocks.
 */
static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
{
	struct btrfs_bio *bbio = rbio->bbio;
	void **pointers = rbio->finish_pointers;
	int nr_data = rbio->nr_data;
	int stripe;
	int pagenr;
	int p_stripe = -1;
	int q_stripe = -1;
	struct bio_list bio_list;
	struct bio *bio;
	int ret;

	bio_list_init(&bio_list);

	if (rbio->real_stripes - rbio->nr_data == 1) {
		p_stripe = rbio->real_stripes - 1;
	} else if (rbio->real_stripes - rbio->nr_data == 2) {
		p_stripe = rbio->real_stripes - 2;
		q_stripe = rbio->real_stripes - 1;
	} else {
		BUG();
	}

	/* at this point we either have a full stripe,
	 * or we've read the full stripe from the drive.
	 * recalculate the parity and write the new results.
	 *
	 * We're not allowed to add any new bios to the
	 * bio list here, anyone else that wants to
	 * change this stripe needs to do their own rmw.
	 */
	spin_lock_irq(&rbio->bio_list_lock);
	set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
	spin_unlock_irq(&rbio->bio_list_lock);

	atomic_set(&rbio->error, 0);

	/*
	 * now that we've set rmw_locked, run through the
	 * bio list one last time and map the page pointers
	 *
	 * We don't cache full rbios because we're assuming
	 * the higher layers are unlikely to use this area of
	 * the disk again soon.  If they do use it again,
	 * hopefully they will send another full bio.
	 */
	index_rbio_pages(rbio);
	if (!rbio_is_full(rbio))
		cache_rbio_pages(rbio);
	else
		clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);

	for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
		struct page *p;
		/* first collect one page from each data stripe */
		for (stripe = 0; stripe < nr_data; stripe++) {
			p = page_in_rbio(rbio, stripe, pagenr, 0);
			pointers[stripe] = kmap(p);
		}

		/* then add the parity stripe */
		p = rbio_pstripe_page(rbio, pagenr);
		SetPageUptodate(p);
		pointers[stripe++] = kmap(p);

		if (q_stripe != -1) {

			/*
			 * raid6, add the qstripe and call the
			 * library function to fill in our p/q
			 */
			p = rbio_qstripe_page(rbio, pagenr);
			SetPageUptodate(p);
			pointers[stripe++] = kmap(p);

			raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE,
						pointers);
		} else {
			/* raid5 */
			copy_page(pointers[nr_data], pointers[0]);
			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
		}


		for (stripe = 0; stripe < rbio->real_stripes; stripe++)
			kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
	}

	/*
	 * time to start writing.  Make bios for everything from the
	 * higher layers (the bio_list in our rbio) and our p/q.  Ignore
	 * everything else.
	 */
	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
			struct page *page;
			if (stripe < rbio->nr_data) {
				page = page_in_rbio(rbio, stripe, pagenr, 1);
				if (!page)
					continue;
			} else {
			       page = rbio_stripe_page(rbio, stripe, pagenr);
			}

			ret = rbio_add_io_page(rbio, &bio_list,
				       page, stripe, pagenr, rbio->stripe_len);
			if (ret)
				goto cleanup;
		}
	}

	if (likely(!bbio->num_tgtdevs))
		goto write_data;

	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
		if (!bbio->tgtdev_map[stripe])
			continue;

		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
			struct page *page;
			if (stripe < rbio->nr_data) {
				page = page_in_rbio(rbio, stripe, pagenr, 1);
				if (!page)
					continue;
			} else {
			       page = rbio_stripe_page(rbio, stripe, pagenr);
			}

			ret = rbio_add_io_page(rbio, &bio_list, page,
					       rbio->bbio->tgtdev_map[stripe],
					       pagenr, rbio->stripe_len);
			if (ret)
				goto cleanup;
		}
	}

write_data:
	atomic_set(&rbio->stripes_pending, bio_list_size(&bio_list));
	BUG_ON(atomic_read(&rbio->stripes_pending) == 0);

	while (1) {
		bio = bio_list_pop(&bio_list);
		if (!bio)
			break;

		bio->bi_private = rbio;
		bio->bi_end_io = raid_write_end_io;
		bio->bi_opf = REQ_OP_WRITE;

		submit_bio(bio);
	}
	return;

cleanup:
	rbio_orig_end_io(rbio, BLK_STS_IOERR);

	while ((bio = bio_list_pop(&bio_list)))
		bio_put(bio);
}

/*
 * helper to find the stripe number for a given bio.  Used to figure out which
 * stripe has failed.  This expects the bio to correspond to a physical disk,
 * so it looks up based on physical sector numbers.
 */
static int find_bio_stripe(struct btrfs_raid_bio *rbio,
			   struct bio *bio)
{
	u64 physical = bio->bi_iter.bi_sector;
	u64 stripe_start;
	int i;
	struct btrfs_bio_stripe *stripe;

	physical <<= 9;

	for (i = 0; i < rbio->bbio->num_stripes; i++) {
		stripe = &rbio->bbio->stripes[i];
		stripe_start = stripe->physical;
		if (physical >= stripe_start &&
		    physical < stripe_start + rbio->stripe_len &&
		    stripe->dev->bdev &&
		    bio->bi_disk == stripe->dev->bdev->bd_disk &&
		    bio->bi_partno == stripe->dev->bdev->bd_partno) {
			return i;
		}
	}
	return -1;
}

/*
 * helper to find the stripe number for a given
 * bio (before mapping).  Used to figure out which stripe has
 * failed.  This looks up based on logical block numbers.
 */
static int find_logical_bio_stripe(struct btrfs_raid_bio *rbio,
				   struct bio *bio)
{
	u64 logical = bio->bi_iter.bi_sector;
	u64 stripe_start;
	int i;

	logical <<= 9;

	for (i = 0; i < rbio->nr_data; i++) {
		stripe_start = rbio->bbio->raid_map[i];
		if (logical >= stripe_start &&
		    logical < stripe_start + rbio->stripe_len) {
			return i;
		}
	}
	return -1;
}

/*
 * returns -EIO if we had too many failures
 */
static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed)
{
	unsigned long flags;
	int ret = 0;

	spin_lock_irqsave(&rbio->bio_list_lock, flags);

	/* we already know this stripe is bad, move on */
	if (rbio->faila == failed || rbio->failb == failed)
		goto out;

	if (rbio->faila == -1) {
		/* first failure on this rbio */
		rbio->faila = failed;
		atomic_inc(&rbio->error);
	} else if (rbio->failb == -1) {
		/* second failure on this rbio */
		rbio->failb = failed;
		atomic_inc(&rbio->error);
	} else {
		ret = -EIO;
	}
out:
	spin_unlock_irqrestore(&rbio->bio_list_lock, flags);

	return ret;
}

/*
 * helper to fail a stripe based on a physical disk
 * bio.
 */
static int fail_bio_stripe(struct btrfs_raid_bio *rbio,
			   struct bio *bio)
{
	int failed = find_bio_stripe(rbio, bio);

	if (failed < 0)
		return -EIO;

	return fail_rbio_index(rbio, failed);
}

/*
 * this sets each page in the bio uptodate.  It should only be used on private
 * rbio pages, nothing that comes in from the higher layers
 */
static void set_bio_pages_uptodate(struct bio *bio)
{
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;

	ASSERT(!bio_flagged(bio, BIO_CLONED));

	bio_for_each_segment_all(bvec, bio, iter_all)
		SetPageUptodate(bvec->bv_page);
}

/*
 * end io for the read phase of the rmw cycle.  All the bios here are physical
 * stripe bios we've read from the disk so we can recalculate the parity of the
 * stripe.
 *
 * This will usually kick off finish_rmw once all the bios are read in, but it
 * may trigger parity reconstruction if we had any errors along the way
 */
static void raid_rmw_end_io(struct bio *bio)
{
	struct btrfs_raid_bio *rbio = bio->bi_private;

	if (bio->bi_status)
		fail_bio_stripe(rbio, bio);
	else
		set_bio_pages_uptodate(bio);

	bio_put(bio);

	if (!atomic_dec_and_test(&rbio->stripes_pending))
		return;

	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
		goto cleanup;

	/*
	 * this will normally call finish_rmw to start our write
	 * but if there are any failed stripes we'll reconstruct
	 * from parity first
	 */
	validate_rbio_for_rmw(rbio);
	return;

cleanup:

	rbio_orig_end_io(rbio, BLK_STS_IOERR);
}

/*
 * the stripe must be locked by the caller.  It will
 * unlock after all the writes are done
 */
static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
{
	int bios_to_read = 0;
	struct bio_list bio_list;
	int ret;
	int pagenr;
	int stripe;
	struct bio *bio;

	bio_list_init(&bio_list);

	ret = alloc_rbio_pages(rbio);
	if (ret)
		goto cleanup;

	index_rbio_pages(rbio);

	atomic_set(&rbio->error, 0);
	/*
	 * build a list of bios to read all the missing parts of this
	 * stripe
	 */
	for (stripe = 0; stripe < rbio->nr_data; stripe++) {
		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
			struct page *page;
			/*
			 * we want to find all the pages missing from
			 * the rbio and read them from the disk.  If
			 * page_in_rbio finds a page in the bio list
			 * we don't need to read it off the stripe.
			 */
			page = page_in_rbio(rbio, stripe, pagenr, 1);
			if (page)
				continue;

			page = rbio_stripe_page(rbio, stripe, pagenr);
			/*
			 * the bio cache may have handed us an uptodate
			 * page.  If so, be happy and use it
			 */
			if (PageUptodate(page))
				continue;

			ret = rbio_add_io_page(rbio, &bio_list, page,
				       stripe, pagenr, rbio->stripe_len);
			if (ret)
				goto cleanup;
		}
	}

	bios_to_read = bio_list_size(&bio_list);
	if (!bios_to_read) {
		/*
		 * this can happen if others have merged with
		 * us, it means there is nothing left to read.
		 * But if there are missing devices it may not be
		 * safe to do the full stripe write yet.
		 */
		goto finish;
	}

	/*
	 * the bbio may be freed once we submit the last bio.  Make sure
	 * not to touch it after that
	 */
	atomic_set(&rbio->stripes_pending, bios_to_read);
	while (1) {
		bio = bio_list_pop(&bio_list);
		if (!bio)
			break;

		bio->bi_private = rbio;
		bio->bi_end_io = raid_rmw_end_io;
		bio->bi_opf = REQ_OP_READ;

		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);

		submit_bio(bio);
	}
	/* the actual write will happen once the reads are done */
	return 0;

cleanup:
	rbio_orig_end_io(rbio, BLK_STS_IOERR);

	while ((bio = bio_list_pop(&bio_list)))
		bio_put(bio);

	return -EIO;

finish:
	validate_rbio_for_rmw(rbio);
	return 0;
}

/*
 * if the upper layers pass in a full stripe, we thank them by only allocating
 * enough pages to hold the parity, and sending it all down quickly.
 */
static int full_stripe_write(struct btrfs_raid_bio *rbio)
{
	int ret;

	ret = alloc_rbio_parity_pages(rbio);
	if (ret) {
		__free_raid_bio(rbio);
		return ret;
	}

	ret = lock_stripe_add(rbio);
	if (ret == 0)
		finish_rmw(rbio);
	return 0;
}

/*
 * partial stripe writes get handed over to async helpers.
 * We're really hoping to merge a few more writes into this
 * rbio before calculating new parity
 */
static int partial_stripe_write(struct btrfs_raid_bio *rbio)
{
	int ret;

	ret = lock_stripe_add(rbio);
	if (ret == 0)
		start_async_work(rbio, rmw_work);
	return 0;
}

/*
 * sometimes while we were reading from the drive to
 * recalculate parity, enough new bios come into create
 * a full stripe.  So we do a check here to see if we can
 * go directly to finish_rmw
 */
static int __raid56_parity_write(struct btrfs_raid_bio *rbio)
{
	/* head off into rmw land if we don't have a full stripe */
	if (!rbio_is_full(rbio))
		return partial_stripe_write(rbio);
	return full_stripe_write(rbio);
}

/*
 * We use plugging call backs to collect full stripes.
 * Any time we get a partial stripe write while plugged
 * we collect it into a list.  When the unplug comes down,
 * we sort the list by logical block number and merge
 * everything we can into the same rbios
 */
struct btrfs_plug_cb {
	struct blk_plug_cb cb;
	struct btrfs_fs_info *info;
	struct list_head rbio_list;
	struct btrfs_work work;
};

/*
 * rbios on the plug list are sorted for easier merging.
 */
static int plug_cmp(void *priv, struct list_head *a, struct list_head *b)
{
	struct btrfs_raid_bio *ra = container_of(a, struct btrfs_raid_bio,
						 plug_list);
	struct btrfs_raid_bio *rb = container_of(b, struct btrfs_raid_bio,
						 plug_list);
	u64 a_sector = ra->bio_list.head->bi_iter.bi_sector;
	u64 b_sector = rb->bio_list.head->bi_iter.bi_sector;

	if (a_sector < b_sector)
		return -1;
	if (a_sector > b_sector)
		return 1;
	return 0;
}

static void run_plug(struct btrfs_plug_cb *plug)
{
	struct btrfs_raid_bio *cur;
	struct btrfs_raid_bio *last = NULL;

	/*
	 * sort our plug list then try to merge
	 * everything we can in hopes of creating full
	 * stripes.
	 */
	list_sort(NULL, &plug->rbio_list, plug_cmp);
	while (!list_empty(&plug->rbio_list)) {
		cur = list_entry(plug->rbio_list.next,
				 struct btrfs_raid_bio, plug_list);
		list_del_init(&cur->plug_list);

		if (rbio_is_full(cur)) {
			int ret;

			/* we have a full stripe, send it down */
			ret = full_stripe_write(cur);
			BUG_ON(ret);
			continue;
		}
		if (last) {
			if (rbio_can_merge(last, cur)) {
				merge_rbio(last, cur);
				__free_raid_bio(cur);
				continue;

			}
			__raid56_parity_write(last);
		}
		last = cur;
	}
	if (last) {
		__raid56_parity_write(last);
	}
	kfree(plug);
}

/*
 * if the unplug comes from schedule, we have to push the
 * work off to a helper thread
 */
static void unplug_work(struct btrfs_work *work)
{
	struct btrfs_plug_cb *plug;
	plug = container_of(work, struct btrfs_plug_cb, work);
	run_plug(plug);
}

static void btrfs_raid_unplug(struct blk_plug_cb *cb, bool from_schedule)
{
	struct btrfs_plug_cb *plug;
	plug = container_of(cb, struct btrfs_plug_cb, cb);

	if (from_schedule) {
		btrfs_init_work(&plug->work, btrfs_rmw_helper,
				unplug_work, NULL, NULL);
		btrfs_queue_work(plug->info->rmw_workers,
				 &plug->work);
		return;
	}
	run_plug(plug);
}

/*
 * our main entry point for writes from the rest of the FS.
 */
int raid56_parity_write(struct btrfs_fs_info *fs_info, struct bio *bio,
			struct btrfs_bio *bbio, u64 stripe_len)
{
	struct btrfs_raid_bio *rbio;
	struct btrfs_plug_cb *plug = NULL;
	struct blk_plug_cb *cb;
	int ret;

	rbio = alloc_rbio(fs_info, bbio, stripe_len);
	if (IS_ERR(rbio)) {
		btrfs_put_bbio(bbio);
		return PTR_ERR(rbio);
	}
	bio_list_add(&rbio->bio_list, bio);
	rbio->bio_list_bytes = bio->bi_iter.bi_size;
	rbio->operation = BTRFS_RBIO_WRITE;

	btrfs_bio_counter_inc_noblocked(fs_info);
	rbio->generic_bio_cnt = 1;

	/*
	 * don't plug on full rbios, just get them out the door
	 * as quickly as we can
	 */
	if (rbio_is_full(rbio)) {
		ret = full_stripe_write(rbio);
		if (ret)
			btrfs_bio_counter_dec(fs_info);
		return ret;
	}

	cb = blk_check_plugged(btrfs_raid_unplug, fs_info, sizeof(*plug));
	if (cb) {
		plug = container_of(cb, struct btrfs_plug_cb, cb);
		if (!plug->info) {
			plug->info = fs_info;
			INIT_LIST_HEAD(&plug->rbio_list);
		}
		list_add_tail(&rbio->plug_list, &plug->rbio_list);
		ret = 0;
	} else {
		ret = __raid56_parity_write(rbio);
		if (ret)
			btrfs_bio_counter_dec(fs_info);
	}
	return ret;
}

/*
 * all parity reconstruction happens here.  We've read in everything
 * we can find from the drives and this does the heavy lifting of
 * sorting the good from the bad.
 */
static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
{
	int pagenr, stripe;
	void **pointers;
	int faila = -1, failb = -1;
	struct page *page;
	blk_status_t err;
	int i;

	pointers = kcalloc(rbio->real_stripes, sizeof(void *), GFP_NOFS);
	if (!pointers) {
		err = BLK_STS_RESOURCE;
		goto cleanup_io;
	}

	faila = rbio->faila;
	failb = rbio->failb;

	if (rbio->operation == BTRFS_RBIO_READ_REBUILD ||
	    rbio->operation == BTRFS_RBIO_REBUILD_MISSING) {
		spin_lock_irq(&rbio->bio_list_lock);
		set_bit(RBIO_RMW_LOCKED_BIT, &rbio->flags);
		spin_unlock_irq(&rbio->bio_list_lock);
	}

	index_rbio_pages(rbio);

	for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
		/*
		 * Now we just use bitmap to mark the horizontal stripes in
		 * which we have data when doing parity scrub.
		 */
		if (rbio->operation == BTRFS_RBIO_PARITY_SCRUB &&
		    !test_bit(pagenr, rbio->dbitmap))
			continue;

		/* setup our array of pointers with pages
		 * from each stripe
		 */
		for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
			/*
			 * if we're rebuilding a read, we have to use
			 * pages from the bio list
			 */
			if ((rbio->operation == BTRFS_RBIO_READ_REBUILD ||
			     rbio->operation == BTRFS_RBIO_REBUILD_MISSING) &&
			    (stripe == faila || stripe == failb)) {
				page = page_in_rbio(rbio, stripe, pagenr, 0);
			} else {
				page = rbio_stripe_page(rbio, stripe, pagenr);
			}
			pointers[stripe] = kmap(page);
		}

		/* all raid6 handling here */
		if (rbio->bbio->map_type & BTRFS_BLOCK_GROUP_RAID6) {
			/*
			 * single failure, rebuild from parity raid5
			 * style
			 */
			if (failb < 0) {
				if (faila == rbio->nr_data) {
					/*
					 * Just the P stripe has failed, without
					 * a bad data or Q stripe.
					 * TODO, we should redo the xor here.
					 */
					err = BLK_STS_IOERR;
					goto cleanup;
				}
				/*
				 * a single failure in raid6 is rebuilt
				 * in the pstripe code below
				 */
				goto pstripe;
			}

			/* make sure our ps and qs are in order */
			if (faila > failb) {
				int tmp = failb;
				failb = faila;
				faila = tmp;
			}

			/* if the q stripe is failed, do a pstripe reconstruction
			 * from the xors.
			 * If both the q stripe and the P stripe are failed, we're
			 * here due to a crc mismatch and we can't give them the
			 * data they want
			 */
			if (rbio->bbio->raid_map[failb] == RAID6_Q_STRIPE) {
				if (rbio->bbio->raid_map[faila] ==
				    RAID5_P_STRIPE) {
					err = BLK_STS_IOERR;
					goto cleanup;
				}
				/*
				 * otherwise we have one bad data stripe and
				 * a good P stripe.  raid5!
				 */
				goto pstripe;
			}

			if (rbio->bbio->raid_map[failb] == RAID5_P_STRIPE) {
				raid6_datap_recov(rbio->real_stripes,
						  PAGE_SIZE, faila, pointers);
			} else {
				raid6_2data_recov(rbio->real_stripes,
						  PAGE_SIZE, faila, failb,
						  pointers);
			}
		} else {
			void *p;

			/* rebuild from P stripe here (raid5 or raid6) */
			BUG_ON(failb != -1);
pstripe:
			/* Copy parity block into failed block to start with */
			copy_page(pointers[faila], pointers[rbio->nr_data]);

			/* rearrange the pointer array */
			p = pointers[faila];
			for (stripe = faila; stripe < rbio->nr_data - 1; stripe++)
				pointers[stripe] = pointers[stripe + 1];
			pointers[rbio->nr_data - 1] = p;

			/* xor in the rest */
			run_xor(pointers, rbio->nr_data - 1, PAGE_SIZE);
		}
		/* if we're doing this rebuild as part of an rmw, go through
		 * and set all of our private rbio pages in the
		 * failed stripes as uptodate.  This way finish_rmw will
		 * know they can be trusted.  If this was a read reconstruction,
		 * other endio functions will fiddle the uptodate bits
		 */
		if (rbio->operation == BTRFS_RBIO_WRITE) {
			for (i = 0;  i < rbio->stripe_npages; i++) {
				if (faila != -1) {
					page = rbio_stripe_page(rbio, faila, i);
					SetPageUptodate(page);
				}
				if (failb != -1) {
					page = rbio_stripe_page(rbio, failb, i);
					SetPageUptodate(page);
				}
			}
		}
		for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
			/*
			 * if we're rebuilding a read, we have to use
			 * pages from the bio list
			 */
			if ((rbio->operation == BTRFS_RBIO_READ_REBUILD ||
			     rbio->operation == BTRFS_RBIO_REBUILD_MISSING) &&
			    (stripe == faila || stripe == failb)) {
				page = page_in_rbio(rbio, stripe, pagenr, 0);
			} else {
				page = rbio_stripe_page(rbio, stripe, pagenr);
			}
			kunmap(page);
		}
	}

	err = BLK_STS_OK;
cleanup:
	kfree(pointers);

cleanup_io:
	/*
	 * Similar to READ_REBUILD, REBUILD_MISSING at this point also has a
	 * valid rbio which is consistent with ondisk content, thus such a
	 * valid rbio can be cached to avoid further disk reads.
	 */
	if (rbio->operation == BTRFS_RBIO_READ_REBUILD ||
	    rbio->operation == BTRFS_RBIO_REBUILD_MISSING) {
		/*
		 * - In case of two failures, where rbio->failb != -1:
		 *
		 *   Do not cache this rbio since the above read reconstruction
		 *   (raid6_datap_recov() or raid6_2data_recov()) may have
		 *   changed some content of stripes which are not identical to
		 *   on-disk content any more, otherwise, a later write/recover
		 *   may steal stripe_pages from this rbio and end up with
		 *   corruptions or rebuild failures.
		 *
		 * - In case of single failure, where rbio->failb == -1:
		 *
		 *   Cache this rbio iff the above read reconstruction is
		 *   executed without problems.
		 */
		if (err == BLK_STS_OK && rbio->failb < 0)
			cache_rbio_pages(rbio);
		else
			clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);

		rbio_orig_end_io(rbio, err);
	} else if (err == BLK_STS_OK) {
		rbio->faila = -1;
		rbio->failb = -1;

		if (rbio->operation == BTRFS_RBIO_WRITE)
			finish_rmw(rbio);
		else if (rbio->operation == BTRFS_RBIO_PARITY_SCRUB)
			finish_parity_scrub(rbio, 0);
		else
			BUG();
	} else {
		rbio_orig_end_io(rbio, err);
	}
}

/*
 * This is called only for stripes we've read from disk to
 * reconstruct the parity.
 */
static void raid_recover_end_io(struct bio *bio)
{
	struct btrfs_raid_bio *rbio = bio->bi_private;

	/*
	 * we only read stripe pages off the disk, set them
	 * up to date if there were no errors
	 */
	if (bio->bi_status)
		fail_bio_stripe(rbio, bio);
	else
		set_bio_pages_uptodate(bio);
	bio_put(bio);

	if (!atomic_dec_and_test(&rbio->stripes_pending))
		return;

	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
		rbio_orig_end_io(rbio, BLK_STS_IOERR);
	else
		__raid_recover_end_io(rbio);
}

/*
 * reads everything we need off the disk to reconstruct
 * the parity. endio handlers trigger final reconstruction
 * when the IO is done.
 *
 * This is used both for reads from the higher layers and for
 * parity construction required to finish a rmw cycle.
 */
static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
{
	int bios_to_read = 0;
	struct bio_list bio_list;
	int ret;
	int pagenr;
	int stripe;
	struct bio *bio;

	bio_list_init(&bio_list);

	ret = alloc_rbio_pages(rbio);
	if (ret)
		goto cleanup;

	atomic_set(&rbio->error, 0);

	/*
	 * read everything that hasn't failed.  Thanks to the
	 * stripe cache, it is possible that some or all of these
	 * pages are going to be uptodate.
	 */
	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
		if (rbio->faila == stripe || rbio->failb == stripe) {
			atomic_inc(&rbio->error);
			continue;
		}

		for (pagenr = 0; pagenr < rbio->stripe_npages; pagenr++) {
			struct page *p;

			/*
			 * the rmw code may have already read this
			 * page in
			 */
			p = rbio_stripe_page(rbio, stripe, pagenr);
			if (PageUptodate(p))
				continue;

			ret = rbio_add_io_page(rbio, &bio_list,
				       rbio_stripe_page(rbio, stripe, pagenr),
				       stripe, pagenr, rbio->stripe_len);
			if (ret < 0)
				goto cleanup;
		}
	}

	bios_to_read = bio_list_size(&bio_list);
	if (!bios_to_read) {
		/*
		 * we might have no bios to read just because the pages
		 * were up to date, or we might have no bios to read because
		 * the devices were gone.
		 */
		if (atomic_read(&rbio->error) <= rbio->bbio->max_errors) {
			__raid_recover_end_io(rbio);
			goto out;
		} else {
			goto cleanup;
		}
	}

	/*
	 * the bbio may be freed once we submit the last bio.  Make sure
	 * not to touch it after that
	 */
	atomic_set(&rbio->stripes_pending, bios_to_read);
	while (1) {
		bio = bio_list_pop(&bio_list);
		if (!bio)
			break;

		bio->bi_private = rbio;
		bio->bi_end_io = raid_recover_end_io;
		bio->bi_opf = REQ_OP_READ;

		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);

		submit_bio(bio);
	}
out:
	return 0;

cleanup:
	if (rbio->operation == BTRFS_RBIO_READ_REBUILD ||
	    rbio->operation == BTRFS_RBIO_REBUILD_MISSING)
		rbio_orig_end_io(rbio, BLK_STS_IOERR);

	while ((bio = bio_list_pop(&bio_list)))
		bio_put(bio);

	return -EIO;
}

/*
 * the main entry point for reads from the higher layers.  This
 * is really only called when the normal read path had a failure,
 * so we assume the bio they send down corresponds to a failed part
 * of the drive.
 */
int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
			  struct btrfs_bio *bbio, u64 stripe_len,
			  int mirror_num, int generic_io)
{
	struct btrfs_raid_bio *rbio;
	int ret;

	if (generic_io) {
		ASSERT(bbio->mirror_num == mirror_num);
		btrfs_io_bio(bio)->mirror_num = mirror_num;
	}

	rbio = alloc_rbio(fs_info, bbio, stripe_len);
	if (IS_ERR(rbio)) {
		if (generic_io)
			btrfs_put_bbio(bbio);
		return PTR_ERR(rbio);
	}

	rbio->operation = BTRFS_RBIO_READ_REBUILD;
	bio_list_add(&rbio->bio_list, bio);
	rbio->bio_list_bytes = bio->bi_iter.bi_size;

	rbio->faila = find_logical_bio_stripe(rbio, bio);
	if (rbio->faila == -1) {
		btrfs_warn(fs_info,
	"%s could not find the bad stripe in raid56 so that we cannot recover any more (bio has logical %llu len %llu, bbio has map_type %llu)",
			   __func__, (u64)bio->bi_iter.bi_sector << 9,
			   (u64)bio->bi_iter.bi_size, bbio->map_type);
		if (generic_io)
			btrfs_put_bbio(bbio);
		kfree(rbio);
		return -EIO;
	}

	if (generic_io) {
		btrfs_bio_counter_inc_noblocked(fs_info);
		rbio->generic_bio_cnt = 1;
	} else {
		btrfs_get_bbio(bbio);
	}

	/*
	 * Loop retry:
	 * for 'mirror == 2', reconstruct from all other stripes.
	 * for 'mirror_num > 2', select a stripe to fail on every retry.
	 */
	if (mirror_num > 2) {
		/*
		 * 'mirror == 3' is to fail the p stripe and
		 * reconstruct from the q stripe.  'mirror > 3' is to
		 * fail a data stripe and reconstruct from p+q stripe.
		 */
		rbio->failb = rbio->real_stripes - (mirror_num - 1);
		ASSERT(rbio->failb > 0);
		if (rbio->failb <= rbio->faila)
			rbio->failb--;
	}

	ret = lock_stripe_add(rbio);

	/*
	 * __raid56_parity_recover will end the bio with
	 * any errors it hits.  We don't want to return
	 * its error value up the stack because our caller
	 * will end up calling bio_endio with any nonzero
	 * return
	 */
	if (ret == 0)
		__raid56_parity_recover(rbio);
	/*
	 * our rbio has been added to the list of
	 * rbios that will be handled after the
	 * currently lock owner is done
	 */
	return 0;

}

static void rmw_work(struct btrfs_work *work)
{
	struct btrfs_raid_bio *rbio;

	rbio = container_of(work, struct btrfs_raid_bio, work);
	raid56_rmw_stripe(rbio);
}

static void read_rebuild_work(struct btrfs_work *work)
{
	struct btrfs_raid_bio *rbio;

	rbio = container_of(work, struct btrfs_raid_bio, work);
	__raid56_parity_recover(rbio);
}

/*
 * The following code is used to scrub/replace the parity stripe
 *
 * Caller must have already increased bio_counter for getting @bbio.
 *
 * Note: We need make sure all the pages that add into the scrub/replace
 * raid bio are correct and not be changed during the scrub/replace. That
 * is those pages just hold metadata or file data with checksum.
 */

struct btrfs_raid_bio *
raid56_parity_alloc_scrub_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
			       struct btrfs_bio *bbio, u64 stripe_len,
			       struct btrfs_device *scrub_dev,
			       unsigned long *dbitmap, int stripe_nsectors)
{
	struct btrfs_raid_bio *rbio;
	int i;

	rbio = alloc_rbio(fs_info, bbio, stripe_len);
	if (IS_ERR(rbio))
		return NULL;
	bio_list_add(&rbio->bio_list, bio);
	/*
	 * This is a special bio which is used to hold the completion handler
	 * and make the scrub rbio is similar to the other types
	 */
	ASSERT(!bio->bi_iter.bi_size);
	rbio->operation = BTRFS_RBIO_PARITY_SCRUB;

	/*
	 * After mapping bbio with BTRFS_MAP_WRITE, parities have been sorted
	 * to the end position, so this search can start from the first parity
	 * stripe.
	 */
	for (i = rbio->nr_data; i < rbio->real_stripes; i++) {
		if (bbio->stripes[i].dev == scrub_dev) {
			rbio->scrubp = i;
			break;
		}
	}
	ASSERT(i < rbio->real_stripes);

	/* Now we just support the sectorsize equals to page size */
	ASSERT(fs_info->sectorsize == PAGE_SIZE);
	ASSERT(rbio->stripe_npages == stripe_nsectors);
	bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors);

	/*
	 * We have already increased bio_counter when getting bbio, record it
	 * so we can free it at rbio_orig_end_io().
	 */
	rbio->generic_bio_cnt = 1;

	return rbio;
}

/* Used for both parity scrub and missing. */
void raid56_add_scrub_pages(struct btrfs_raid_bio *rbio, struct page *page,
			    u64 logical)
{
	int stripe_offset;
	int index;

	ASSERT(logical >= rbio->bbio->raid_map[0]);
	ASSERT(logical + PAGE_SIZE <= rbio->bbio->raid_map[0] +
				rbio->stripe_len * rbio->nr_data);
	stripe_offset = (int)(logical - rbio->bbio->raid_map[0]);
	index = stripe_offset >> PAGE_SHIFT;
	rbio->bio_pages[index] = page;
}

/*
 * We just scrub the parity that we have correct data on the same horizontal,
 * so we needn't allocate all pages for all the stripes.
 */
static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio)
{
	int i;
	int bit;
	int index;
	struct page *page;

	for_each_set_bit(bit, rbio->dbitmap, rbio->stripe_npages) {
		for (i = 0; i < rbio->real_stripes; i++) {
			index = i * rbio->stripe_npages + bit;
			if (rbio->stripe_pages[index])
				continue;

			page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
			if (!page)
				return -ENOMEM;
			rbio->stripe_pages[index] = page;
		}
	}
	return 0;
}

static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
					 int need_check)
{
	struct btrfs_bio *bbio = rbio->bbio;
	void **pointers = rbio->finish_pointers;
	unsigned long *pbitmap = rbio->finish_pbitmap;
	int nr_data = rbio->nr_data;
	int stripe;
	int pagenr;
	int p_stripe = -1;
	int q_stripe = -1;
	struct page *p_page = NULL;
	struct page *q_page = NULL;
	struct bio_list bio_list;
	struct bio *bio;
	int is_replace = 0;
	int ret;

	bio_list_init(&bio_list);

	if (rbio->real_stripes - rbio->nr_data == 1) {
		p_stripe = rbio->real_stripes - 1;
	} else if (rbio->real_stripes - rbio->nr_data == 2) {
		p_stripe = rbio->real_stripes - 2;
		q_stripe = rbio->real_stripes - 1;
	} else {
		BUG();
	}

	if (bbio->num_tgtdevs && bbio->tgtdev_map[rbio->scrubp]) {
		is_replace = 1;
		bitmap_copy(pbitmap, rbio->dbitmap, rbio->stripe_npages);
	}

	/*
	 * Because the higher layers(scrubber) are unlikely to
	 * use this area of the disk again soon, so don't cache
	 * it.
	 */
	clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags);

	if (!need_check)
		goto writeback;

	p_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
	if (!p_page)
		goto cleanup;
	SetPageUptodate(p_page);

	if (q_stripe != -1) {
		q_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
		if (!q_page) {
			__free_page(p_page);
			goto cleanup;
		}
		SetPageUptodate(q_page);
	}

	atomic_set(&rbio->error, 0);

	for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
		struct page *p;
		void *parity;
		/* first collect one page from each data stripe */
		for (stripe = 0; stripe < nr_data; stripe++) {
			p = page_in_rbio(rbio, stripe, pagenr, 0);
			pointers[stripe] = kmap(p);
		}

		/* then add the parity stripe */
		pointers[stripe++] = kmap(p_page);

		if (q_stripe != -1) {

			/*
			 * raid6, add the qstripe and call the
			 * library function to fill in our p/q
			 */
			pointers[stripe++] = kmap(q_page);

			raid6_call.gen_syndrome(rbio->real_stripes, PAGE_SIZE,
						pointers);
		} else {
			/* raid5 */
			copy_page(pointers[nr_data], pointers[0]);
			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
		}

		/* Check scrubbing parity and repair it */
		p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
		parity = kmap(p);
		if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
			copy_page(parity, pointers[rbio->scrubp]);
		else
			/* Parity is right, needn't writeback */
			bitmap_clear(rbio->dbitmap, pagenr, 1);
		kunmap(p);

		for (stripe = 0; stripe < nr_data; stripe++)
			kunmap(page_in_rbio(rbio, stripe, pagenr, 0));
		kunmap(p_page);
	}

	__free_page(p_page);
	if (q_page)
		__free_page(q_page);

writeback:
	/*
	 * time to start writing.  Make bios for everything from the
	 * higher layers (the bio_list in our rbio) and our p/q.  Ignore
	 * everything else.
	 */
	for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
		struct page *page;

		page = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
		ret = rbio_add_io_page(rbio, &bio_list,
			       page, rbio->scrubp, pagenr, rbio->stripe_len);
		if (ret)
			goto cleanup;
	}

	if (!is_replace)
		goto submit_write;

	for_each_set_bit(pagenr, pbitmap, rbio->stripe_npages) {
		struct page *page;

		page = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
		ret = rbio_add_io_page(rbio, &bio_list, page,
				       bbio->tgtdev_map[rbio->scrubp],
				       pagenr, rbio->stripe_len);
		if (ret)
			goto cleanup;
	}

submit_write:
	nr_data = bio_list_size(&bio_list);
	if (!nr_data) {
		/* Every parity is right */
		rbio_orig_end_io(rbio, BLK_STS_OK);
		return;
	}

	atomic_set(&rbio->stripes_pending, nr_data);

	while (1) {
		bio = bio_list_pop(&bio_list);
		if (!bio)
			break;

		bio->bi_private = rbio;
		bio->bi_end_io = raid_write_end_io;
		bio->bi_opf = REQ_OP_WRITE;

		submit_bio(bio);
	}
	return;

cleanup:
	rbio_orig_end_io(rbio, BLK_STS_IOERR);

	while ((bio = bio_list_pop(&bio_list)))
		bio_put(bio);
}

static inline int is_data_stripe(struct btrfs_raid_bio *rbio, int stripe)
{
	if (stripe >= 0 && stripe < rbio->nr_data)
		return 1;
	return 0;
}

/*
 * While we're doing the parity check and repair, we could have errors
 * in reading pages off the disk.  This checks for errors and if we're
 * not able to read the page it'll trigger parity reconstruction.  The
 * parity scrub will be finished after we've reconstructed the failed
 * stripes
 */
static void validate_rbio_for_parity_scrub(struct btrfs_raid_bio *rbio)
{
	if (atomic_read(&rbio->error) > rbio->bbio->max_errors)
		goto cleanup;

	if (rbio->faila >= 0 || rbio->failb >= 0) {
		int dfail = 0, failp = -1;

		if (is_data_stripe(rbio, rbio->faila))
			dfail++;
		else if (is_parity_stripe(rbio->faila))
			failp = rbio->faila;

		if (is_data_stripe(rbio, rbio->failb))
			dfail++;
		else if (is_parity_stripe(rbio->failb))
			failp = rbio->failb;

		/*
		 * Because we can not use a scrubbing parity to repair
		 * the data, so the capability of the repair is declined.
		 * (In the case of RAID5, we can not repair anything)
		 */
		if (dfail > rbio->bbio->max_errors - 1)
			goto cleanup;

		/*
		 * If all data is good, only parity is correctly, just
		 * repair the parity.
		 */
		if (dfail == 0) {
			finish_parity_scrub(rbio, 0);
			return;
		}

		/*
		 * Here means we got one corrupted data stripe and one
		 * corrupted parity on RAID6, if the corrupted parity
		 * is scrubbing parity, luckily, use the other one to repair
		 * the data, or we can not repair the data stripe.
		 */
		if (failp != rbio->scrubp)
			goto cleanup;

		__raid_recover_end_io(rbio);
	} else {
		finish_parity_scrub(rbio, 1);
	}
	return;

cleanup:
	rbio_orig_end_io(rbio, BLK_STS_IOERR);
}

/*
 * end io for the read phase of the rmw cycle.  All the bios here are physical
 * stripe bios we've read from the disk so we can recalculate the parity of the
 * stripe.
 *
 * This will usually kick off finish_rmw once all the bios are read in, but it
 * may trigger parity reconstruction if we had any errors along the way
 */
static void raid56_parity_scrub_end_io(struct bio *bio)
{
	struct btrfs_raid_bio *rbio = bio->bi_private;

	if (bio->bi_status)
		fail_bio_stripe(rbio, bio);
	else
		set_bio_pages_uptodate(bio);

	bio_put(bio);

	if (!atomic_dec_and_test(&rbio->stripes_pending))
		return;

	/*
	 * this will normally call finish_rmw to start our write
	 * but if there are any failed stripes we'll reconstruct
	 * from parity first
	 */
	validate_rbio_for_parity_scrub(rbio);
}

static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
{
	int bios_to_read = 0;
	struct bio_list bio_list;
	int ret;
	int pagenr;
	int stripe;
	struct bio *bio;

	bio_list_init(&bio_list);

	ret = alloc_rbio_essential_pages(rbio);
	if (ret)
		goto cleanup;

	atomic_set(&rbio->error, 0);
	/*
	 * build a list of bios to read all the missing parts of this
	 * stripe
	 */
	for (stripe = 0; stripe < rbio->real_stripes; stripe++) {
		for_each_set_bit(pagenr, rbio->dbitmap, rbio->stripe_npages) {
			struct page *page;
			/*
			 * we want to find all the pages missing from
			 * the rbio and read them from the disk.  If
			 * page_in_rbio finds a page in the bio list
			 * we don't need to read it off the stripe.
			 */
			page = page_in_rbio(rbio, stripe, pagenr, 1);
			if (page)
				continue;

			page = rbio_stripe_page(rbio, stripe, pagenr);
			/*
			 * the bio cache may have handed us an uptodate
			 * page.  If so, be happy and use it
			 */
			if (PageUptodate(page))
				continue;

			ret = rbio_add_io_page(rbio, &bio_list, page,
				       stripe, pagenr, rbio->stripe_len);
			if (ret)
				goto cleanup;
		}
	}

	bios_to_read = bio_list_size(&bio_list);
	if (!bios_to_read) {
		/*
		 * this can happen if others have merged with
		 * us, it means there is nothing left to read.
		 * But if there are missing devices it may not be
		 * safe to do the full stripe write yet.
		 */
		goto finish;
	}

	/*
	 * the bbio may be freed once we submit the last bio.  Make sure
	 * not to touch it after that
	 */
	atomic_set(&rbio->stripes_pending, bios_to_read);
	while (1) {
		bio = bio_list_pop(&bio_list);
		if (!bio)
			break;

		bio->bi_private = rbio;
		bio->bi_end_io = raid56_parity_scrub_end_io;
		bio->bi_opf = REQ_OP_READ;

		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);

		submit_bio(bio);
	}
	/* the actual write will happen once the reads are done */
	return;

cleanup:
	rbio_orig_end_io(rbio, BLK_STS_IOERR);

	while ((bio = bio_list_pop(&bio_list)))
		bio_put(bio);

	return;

finish:
	validate_rbio_for_parity_scrub(rbio);
}

static void scrub_parity_work(struct btrfs_work *work)
{
	struct btrfs_raid_bio *rbio;

	rbio = container_of(work, struct btrfs_raid_bio, work);
	raid56_parity_scrub_stripe(rbio);
}

void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
{
	if (!lock_stripe_add(rbio))
		start_async_work(rbio, scrub_parity_work);
}

/* The following code is used for dev replace of a missing RAID 5/6 device. */

struct btrfs_raid_bio *
raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
			  struct btrfs_bio *bbio, u64 length)
{
	struct btrfs_raid_bio *rbio;

	rbio = alloc_rbio(fs_info, bbio, length);
	if (IS_ERR(rbio))
		return NULL;

	rbio->operation = BTRFS_RBIO_REBUILD_MISSING;
	bio_list_add(&rbio->bio_list, bio);
	/*
	 * This is a special bio which is used to hold the completion handler
	 * and make the scrub rbio is similar to the other types
	 */
	ASSERT(!bio->bi_iter.bi_size);

	rbio->faila = find_logical_bio_stripe(rbio, bio);
	if (rbio->faila == -1) {
		BUG();
		kfree(rbio);
		return NULL;
	}

	/*
	 * When we get bbio, we have already increased bio_counter, record it
	 * so we can free it at rbio_orig_end_io()
	 */
	rbio->generic_bio_cnt = 1;

	return rbio;
}

void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio)
{
	if (!lock_stripe_add(rbio))
		start_async_work(rbio, read_rebuild_work);
}