summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/raid56.c
blob: d02510f349363f358cac8fbb54211bba533cad28 (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
/*
 * Copyright (C) 2012 Fusion-io  All rights reserved.
 * Copyright (C) 2012 Intel Corp. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/random.h>
#include <linux/iocontext.h>
#include <linux/capability.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/hash.h>
#include <linux/list_sort.h>
#include <linux/raid/xor.h>
#include <asm/div64.h>
#include "compat.h"
#include "ctree.h"
#include "extent_map.h"
#include "disk-io.h"
#include "transaction.h"
#include "print-tree.h"
#include "volumes.h"
#include "raid56.h"
#include "async-thread.h"
#include "check-integrity.h"
#include "rcu-string.h"

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

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

	/*
	 * logical block numbers for the start of each stripe
	 * The last one or two are p/q.  These are sorted,
	 * so raid_map[0] is the start of our full stripe
	 */
	u64 *raid_map;

	/* 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;

	/*
	 * 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
	 * stripe locking code uses plug_list 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;

	/*
	 * 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
	 */
	int read_rebuild;

	/* first bad stripe */
	int faila;

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

	/*
	 * 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;

	atomic_t refs;

	/*
	 * 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;
};

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 void async_rmw_stripe(struct btrfs_raid_bio *rbio);
static void async_read_rebuild(struct btrfs_raid_bio *rbio);
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);

/*
 * 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;

	if (info->stripe_hash_table)
		return 0;

	table = kzalloc(sizeof(*table) + sizeof(*h) * num_entries, GFP_NOFS);
	if (!table)
		return -ENOMEM;

	table->table = (void *)(table + 1);
	h = table->table;

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

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

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

/*
 * 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;
	bio_list_init(&victim->bio_list);
}

/*
 * free the hash table used by unmount
 */
void btrfs_free_stripe_hash_table(struct btrfs_fs_info *info)
{
	if (!info->stripe_hash_table)
		return;
	kfree(info->stripe_hash_table);
	info->stripe_hash_table = NULL;
}

/*
 * 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).
 * Must be called with the bio list lock held, or
 * at a time when you know it is impossible to add
 * new bios into the list
 */
static int __rbio_is_full(struct btrfs_raid_bio *rbio)
{
	unsigned long size = rbio->bio_list_bytes;
	int ret = 1;

	if (size != rbio->nr_data * rbio->stripe_len)
		ret = 0;

	BUG_ON(size > rbio->nr_data * rbio->stripe_len);
	return ret;
}

static int rbio_is_full(struct btrfs_raid_bio *rbio)
{
	unsigned long flags;
	int ret;

	spin_lock_irqsave(&rbio->bio_list_lock, flags);
	ret = __rbio_is_full(rbio);
	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;

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

	/* reads can't merge with writes */
	if (last->read_rebuild !=
	    cur->read_rebuild) {
		return 0;
	}

	return 1;
}

/*
 * helper to index into the pstripe
 */
static struct page *rbio_pstripe_page(struct btrfs_raid_bio *rbio, int index)
{
	index += (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;
	return rbio->stripe_pages[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->bbio->num_stripes)
		return NULL;

	index += ((rbio->nr_data + 1) * rbio->stripe_len) >>
		PAGE_CACHE_SHIFT;
	return rbio->stripe_pages[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;
	DEFINE_WAIT(wait);
	struct btrfs_raid_bio *freeit = NULL;
	int ret = 0;
	int walk = 0;

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

			/* 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;
		}
	}

	atomic_inc(&rbio->refs);
	list_add(&rbio->hash_list, &h->hash_list);
out:
	spin_unlock_irqrestore(&h->lock, flags);
	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;

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

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

	if (!list_empty(&rbio->hash_list)) {

		list_del_init(&rbio->hash_list);
		atomic_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);
			atomic_inc(&next->refs);
			spin_unlock(&rbio->bio_list_lock);
			spin_unlock_irqrestore(&h->lock, flags);

			if (next->read_rebuild)
				async_read_rebuild(next);
			else
				async_rmw_stripe(next);

			goto done_nolock;

		} else  if (waitqueue_active(&h->wait)) {
			spin_unlock(&rbio->bio_list_lock);
			spin_unlock_irqrestore(&h->lock, flags);
			wake_up(&h->wait);
			goto done_nolock;
		}
	}
	spin_unlock(&rbio->bio_list_lock);
	spin_unlock_irqrestore(&h->lock, flags);

done_nolock:
	return;
}

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

	WARN_ON(atomic_read(&rbio->refs) < 0);
	if (!atomic_dec_and_test(&rbio->refs))
		return;

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

static void free_raid_bio(struct btrfs_raid_bio *rbio)
{
	unlock_stripe(rbio);
	__free_raid_bio(rbio);
}

/*
 * 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, int err, int uptodate)
{
	struct bio *cur = bio_list_get(&rbio->bio_list);
	struct bio *next;
	free_raid_bio(rbio);

	while (cur) {
		next = cur->bi_next;
		cur->bi_next = NULL;
		if (uptodate)
			set_bit(BIO_UPTODATE, &cur->bi_flags);
		bio_endio(cur, err);
		cur = next;
	}
}

/*
 * 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, int err)
{
	struct btrfs_raid_bio *rbio = bio->bi_private;

	if (err)
		fail_bio_stripe(rbio, bio);

	bio_put(bio);

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

	err = 0;

	/* OK, we have read all the stripes we need to. */
	if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
		err = -EIO;

	rbio_orig_end_io(rbio, err, 0);
	return;
}

/*
 * 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)
{
	unsigned long nr = stripe_len * nr_stripes;
	return (nr + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
}

/*
 * 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_root *root,
			  struct btrfs_bio *bbio, u64 *raid_map,
			  u64 stripe_len)
{
	struct btrfs_raid_bio *rbio;
	int nr_data = 0;
	int num_pages = rbio_nr_pages(stripe_len, bbio->num_stripes);
	void *p;

	rbio = kzalloc(sizeof(*rbio) + num_pages * sizeof(struct page *) * 2,
			GFP_NOFS);
	if (!rbio) {
		kfree(raid_map);
		kfree(bbio);
		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->hash_list);
	rbio->bbio = bbio;
	rbio->raid_map = raid_map;
	rbio->fs_info = root->fs_info;
	rbio->stripe_len = stripe_len;
	rbio->nr_pages = num_pages;
	rbio->faila = -1;
	rbio->failb = -1;
	atomic_set(&rbio->refs, 1);

	/*
	 * the stripe_pages and bio_pages array point to the extra
	 * memory we allocated past the end of the rbio
	 */
	p = rbio + 1;
	rbio->stripe_pages = p;
	rbio->bio_pages = p + sizeof(struct page *) * num_pages;

	if (raid_map[bbio->num_stripes - 1] == RAID6_Q_STRIPE)
		nr_data = bbio->num_stripes - 2;
	else
		nr_data = bbio->num_stripes - 1;

	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;
		ClearPageUptodate(page);
	}
	return 0;
}

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

	i = (rbio->nr_data * rbio->stripe_len) >> PAGE_CACHE_SHIFT;

	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.
 */
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_CACHE_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_sector << 9;
		last_end += last->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 &&
		    test_bit(BIO_UPTODATE, &last->bi_flags) &&
		    last->bi_bdev == stripe->dev->bdev) {
			ret = bio_add_page(last, page, PAGE_CACHE_SIZE, 0);
			if (ret == PAGE_CACHE_SIZE)
				return 0;
		}
	}

	/* put a new bio on the list */
	bio = bio_alloc(GFP_NOFS, bio_max_len >> PAGE_SHIFT?:1);
	if (!bio)
		return -ENOMEM;

	bio->bi_size = 0;
	bio->bi_bdev = stripe->dev->bdev;
	bio->bi_sector = disk_start >> 9;
	set_bit(BIO_UPTODATE, &bio->bi_flags);

	bio_add_page(bio, page, PAGE_CACHE_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->bbio->num_stripes - 1);
		__raid56_parity_recover(rbio);
	} else {
		finish_rmw(rbio);
	}
}

/*
 * 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 page)
{
	int index;
	index = stripe * (rbio->stripe_len >> PAGE_CACHE_SHIFT);
	index += page;
	return rbio->stripe_pages[index];
}

/*
 * 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;
	struct page *p;
	int i;

	spin_lock_irq(&rbio->bio_list_lock);
	bio_list_for_each(bio, &rbio->bio_list) {
		start = (u64)bio->bi_sector << 9;
		stripe_offset = start - rbio->raid_map[0];
		page_index = stripe_offset >> PAGE_CACHE_SHIFT;

		for (i = 0; i < bio->bi_vcnt; i++) {
			p = bio->bi_io_vec[i].bv_page;
			rbio->bio_pages[page_index + i] = p;
		}
	}
	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[bbio->num_stripes];
	int stripe_len = rbio->stripe_len;
	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 pages_per_stripe = stripe_len >> PAGE_CACHE_SHIFT;
	int ret;

	bio_list_init(&bio_list);

	if (bbio->num_stripes - rbio->nr_data == 1) {
		p_stripe = bbio->num_stripes - 1;
	} else if (bbio->num_stripes - rbio->nr_data == 2) {
		p_stripe = bbio->num_stripes - 2;
		q_stripe = bbio->num_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->bbio->error, 0);

	/*
	 * now that we've set rmw_locked, run through the
	 * bio list one last time and map the page pointers
	 */
	index_rbio_pages(rbio);

	for (pagenr = 0; pagenr < pages_per_stripe; 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(bbio->num_stripes, PAGE_SIZE,
						pointers);
		} else {
			/* raid5 */
			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
			run_xor(pointers + 1, nr_data - 1, PAGE_CACHE_SIZE);
		}


		for (stripe = 0; stripe < bbio->num_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 < bbio->num_stripes; stripe++) {
		for (pagenr = 0; pagenr < pages_per_stripe; 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;
		}
	}

	atomic_set(&bbio->stripes_pending, bio_list_size(&bio_list));
	BUG_ON(atomic_read(&bbio->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;
		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
		submit_bio(WRITE, bio);
	}
	return;

cleanup:
	rbio_orig_end_io(rbio, -EIO, 0);
}

/*
 * 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_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) {
			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_sector;
	u64 stripe_start;
	int i;

	logical <<= 9;

	for (i = 0; i < rbio->nr_data; i++) {
		stripe_start = rbio->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->bbio->error);
	} else if (rbio->failb == -1) {
		/* second failure on this rbio */
		rbio->failb = failed;
		atomic_inc(&rbio->bbio->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)
{
	int i;
	struct page *p;

	for (i = 0; i < bio->bi_vcnt; i++) {
		p = bio->bi_io_vec[i].bv_page;
		SetPageUptodate(p);
	}
}

/*
 * 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, int err)
{
	struct btrfs_raid_bio *rbio = bio->bi_private;

	if (err)
		fail_bio_stripe(rbio, bio);
	else
		set_bio_pages_uptodate(bio);

	bio_put(bio);

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

	err = 0;
	if (atomic_read(&rbio->bbio->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, -EIO, 0);
}

static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
{
	rbio->work.flags = 0;
	rbio->work.func = rmw_work;

	btrfs_queue_worker(&rbio->fs_info->rmw_workers,
			   &rbio->work);
}

static void async_read_rebuild(struct btrfs_raid_bio *rbio)
{
	rbio->work.flags = 0;
	rbio->work.func = read_rebuild_work;

	btrfs_queue_worker(&rbio->fs_info->rmw_workers,
			   &rbio->work);
}

/*
 * 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 btrfs_bio *bbio = rbio->bbio;
	struct bio_list bio_list;
	int ret;
	int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	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->bbio->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 < nr_pages; 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);
			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(&bbio->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;

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

		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
		submit_bio(READ, bio);
	}
	/* the actual write will happen once the reads are done */
	return 0;

cleanup:
	rbio_orig_end_io(rbio, -EIO, 0);
	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)
		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)
		async_rmw_stripe(rbio);
	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);
}

/*
 * our main entry point for writes from the rest of the FS.
 */
int raid56_parity_write(struct btrfs_root *root, struct bio *bio,
			struct btrfs_bio *bbio, u64 *raid_map,
			u64 stripe_len)
{
	struct btrfs_raid_bio *rbio;

	rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
	if (IS_ERR(rbio)) {
		kfree(raid_map);
		kfree(bbio);
		return PTR_ERR(rbio);
	}
	bio_list_add(&rbio->bio_list, bio);
	rbio->bio_list_bytes = bio->bi_size;
	return __raid56_parity_write(rbio);
}

/*
 * 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;
	int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	struct page *page;
	int err;
	int i;

	pointers = kzalloc(rbio->bbio->num_stripes * sizeof(void *),
			   GFP_NOFS);
	if (!pointers) {
		err = -ENOMEM;
		goto cleanup_io;
	}

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

	if (rbio->read_rebuild) {
		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 < nr_pages; pagenr++) {
		/* setup our array of pointers with pages
		 * from each stripe
		 */
		for (stripe = 0; stripe < rbio->bbio->num_stripes; stripe++) {
			/*
			 * if we're rebuilding a read, we have to use
			 * pages from the bio list
			 */
			if (rbio->read_rebuild &&
			    (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->raid_map[rbio->bbio->num_stripes - 1] ==
		    RAID6_Q_STRIPE) {

			/*
			 * 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 = -EIO;
					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->raid_map[failb] == RAID6_Q_STRIPE) {
				if (rbio->raid_map[faila] == RAID5_P_STRIPE) {
					err = -EIO;
					goto cleanup;
				}
				/*
				 * otherwise we have one bad data stripe and
				 * a good P stripe.  raid5!
				 */
				goto pstripe;
			}

			if (rbio->raid_map[failb] == RAID5_P_STRIPE) {
				raid6_datap_recov(rbio->bbio->num_stripes,
						  PAGE_SIZE, faila, pointers);
			} else {
				raid6_2data_recov(rbio->bbio->num_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 */
			memcpy(pointers[faila],
			       pointers[rbio->nr_data],
			       PAGE_CACHE_SIZE);

			/* 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_CACHE_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->read_rebuild) {
			for (i = 0;  i < nr_pages; 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->bbio->num_stripes; stripe++) {
			/*
			 * if we're rebuilding a read, we have to use
			 * pages from the bio list
			 */
			if (rbio->read_rebuild &&
			    (stripe == faila || stripe == failb)) {
				page = page_in_rbio(rbio, stripe, pagenr, 0);
			} else {
				page = rbio_stripe_page(rbio, stripe, pagenr);
			}
			kunmap(page);
		}
	}

	err = 0;
cleanup:
	kfree(pointers);

cleanup_io:

	if (rbio->read_rebuild) {
		rbio_orig_end_io(rbio, err, err == 0);
	} else if (err == 0) {
		rbio->faila = -1;
		rbio->failb = -1;
		finish_rmw(rbio);
	} else {
		rbio_orig_end_io(rbio, err, 0);
	}
}

/*
 * This is called only for stripes we've read from disk to
 * reconstruct the parity.
 */
static void raid_recover_end_io(struct bio *bio, int err)
{
	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 (err)
		fail_bio_stripe(rbio, bio);
	else
		set_bio_pages_uptodate(bio);
	bio_put(bio);

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

	if (atomic_read(&rbio->bbio->error) > rbio->bbio->max_errors)
		rbio_orig_end_io(rbio, -EIO, 0);
	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 btrfs_bio *bbio = rbio->bbio;
	struct bio_list bio_list;
	int ret;
	int nr_pages = (rbio->stripe_len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
	int pagenr;
	int stripe;
	struct bio *bio;

	bio_list_init(&bio_list);

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

	atomic_set(&rbio->bbio->error, 0);

	/*
	 * read everything that hasn't failed.
	 */
	for (stripe = 0; stripe < bbio->num_stripes; stripe++) {
		if (rbio->faila == stripe ||
		    rbio->failb == stripe)
			continue;

		for (pagenr = 0; pagenr < nr_pages; 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->bbio->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(&bbio->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;

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

		BUG_ON(!test_bit(BIO_UPTODATE, &bio->bi_flags));
		submit_bio(READ, bio);
	}
out:
	return 0;

cleanup:
	if (rbio->read_rebuild)
		rbio_orig_end_io(rbio, -EIO, 0);
	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_root *root, struct bio *bio,
			  struct btrfs_bio *bbio, u64 *raid_map,
			  u64 stripe_len, int mirror_num)
{
	struct btrfs_raid_bio *rbio;
	int ret;

	rbio = alloc_rbio(root, bbio, raid_map, stripe_len);
	if (IS_ERR(rbio)) {
		return PTR_ERR(rbio);
	}

	rbio->read_rebuild = 1;
	bio_list_add(&rbio->bio_list, bio);
	rbio->bio_list_bytes = bio->bi_size;

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

	/*
	 * reconstruct from the q stripe if they are
	 * asking for mirror 3
	 */
	if (mirror_num == 3)
		rbio->failb = bbio->num_stripes - 2;

	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);
}
OpenPOWER on IntegriCloud