aboutsummaryrefslogtreecommitdiff
path: root/block/badblocks.c
blob: fc92d4e18aa3c0557d2be62eaa1f9bcc37139bf9 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Bad block management
 *
 * - Heavily based on MD badblocks code from Neil Brown
 *
 * Copyright (c) 2015, Intel Corporation.
 */

#include <linux/badblocks.h>
#include <linux/seqlock.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/stddef.h>
#include <linux/types.h>
#include <linux/slab.h>

/*
 * The purpose of badblocks set/clear is to manage bad blocks ranges which are
 * identified by LBA addresses.
 *
 * When the caller of badblocks_set() wants to set a range of bad blocks, the
 * setting range can be acked or unacked. And the setting range may merge,
 * overwrite, skip the overlapped already set range, depends on who they are
 * overlapped or adjacent, and the acknowledgment type of the ranges. It can be
 * more complicated when the setting range covers multiple already set bad block
 * ranges, with restrictions of maximum length of each bad range and the bad
 * table space limitation.
 *
 * It is difficult and unnecessary to take care of all the possible situations,
 * for setting a large range of bad blocks, we can handle it by dividing the
 * large range into smaller ones when encounter overlap, max range length or
 * bad table full conditions. Every time only a smaller piece of the bad range
 * is handled with a limited number of conditions how it is interacted with
 * possible overlapped or adjacent already set bad block ranges. Then the hard
 * complicated problem can be much simpler to handle in proper way.
 *
 * When setting a range of bad blocks to the bad table, the simplified situations
 * to be considered are, (The already set bad blocks ranges are naming with
 *  prefix E, and the setting bad blocks range is naming with prefix S)
 *
 * 1) A setting range is not overlapped or adjacent to any other already set bad
 *    block range.
 *                         +--------+
 *                         |    S   |
 *                         +--------+
 *        +-------------+               +-------------+
 *        |      E1     |               |      E2     |
 *        +-------------+               +-------------+
 *    For this situation if the bad blocks table is not full, just allocate a
 *    free slot from the bad blocks table to mark the setting range S. The
 *    result is,
 *        +-------------+  +--------+   +-------------+
 *        |      E1     |  |    S   |   |      E2     |
 *        +-------------+  +--------+   +-------------+
 * 2) A setting range starts exactly at a start LBA of an already set bad blocks
 *    range.
 * 2.1) The setting range size < already set range size
 *        +--------+
 *        |    S   |
 *        +--------+
 *        +-------------+
 *        |      E      |
 *        +-------------+
 * 2.1.1) If S and E are both acked or unacked range, the setting range S can
 *    be merged into existing bad range E. The result is,
 *        +-------------+
 *        |      S      |
 *        +-------------+
 * 2.1.2) If S is unacked setting and E is acked, the setting will be denied, and
 *    the result is,
 *        +-------------+
 *        |      E      |
 *        +-------------+
 * 2.1.3) If S is acked setting and E is unacked, range S can overwrite on E.
 *    An extra slot from the bad blocks table will be allocated for S, and head
 *    of E will move to end of the inserted range S. The result is,
 *        +--------+----+
 *        |    S   | E  |
 *        +--------+----+
 * 2.2) The setting range size == already set range size
 * 2.2.1) If S and E are both acked or unacked range, the setting range S can
 *    be merged into existing bad range E. The result is,
 *        +-------------+
 *        |      S      |
 *        +-------------+
 * 2.2.2) If S is unacked setting and E is acked, the setting will be denied, and
 *    the result is,
 *        +-------------+
 *        |      E      |
 *        +-------------+
 * 2.2.3) If S is acked setting and E is unacked, range S can overwrite all of
      bad blocks range E. The result is,
 *        +-------------+
 *        |      S      |
 *        +-------------+
 * 2.3) The setting range size > already set range size
 *        +-------------------+
 *        |          S        |
 *        +-------------------+
 *        +-------------+
 *        |      E      |
 *        +-------------+
 *    For such situation, the setting range S can be treated as two parts, the
 *    first part (S1) is as same size as the already set range E, the second
 *    part (S2) is the rest of setting range.
 *        +-------------+-----+        +-------------+       +-----+
 *        |    S1       | S2  |        |     S1      |       | S2  |
 *        +-------------+-----+  ===>  +-------------+       +-----+
 *        +-------------+              +-------------+
 *        |      E      |              |      E      |
 *        +-------------+              +-------------+
 *    Now we only focus on how to handle the setting range S1 and already set
 *    range E, which are already explained in 2.2), for the rest S2 it will be
 *    handled later in next loop.
 * 3) A setting range starts before the start LBA of an already set bad blocks
 *    range.
 *        +-------------+
 *        |      S      |
 *        +-------------+
 *             +-------------+
 *             |      E      |
 *             +-------------+
 *    For this situation, the setting range S can be divided into two parts, the
 *    first (S1) ends at the start LBA of already set range E, the second part
 *    (S2) starts exactly at a start LBA of the already set range E.
 *        +----+---------+             +----+      +---------+
 *        | S1 |    S2   |             | S1 |      |    S2   |
 *        +----+---------+      ===>   +----+      +---------+
 *             +-------------+                     +-------------+
 *             |      E      |                     |      E      |
 *             +-------------+                     +-------------+
 *    Now only the first part S1 should be handled in this loop, which is in
 *    similar condition as 1). The rest part S2 has exact same start LBA address
 *    of the already set range E, they will be handled in next loop in one of
 *    situations in 2).
 * 4) A setting range starts after the start LBA of an already set bad blocks
 *    range.
 * 4.1) If the setting range S exactly matches the tail part of already set bad
 *    blocks range E, like the following chart shows,
 *            +---------+
 *            |   S     |
 *            +---------+
 *        +-------------+
 *        |      E      |
 *        +-------------+
 * 4.1.1) If range S and E have same acknowledge value (both acked or unacked),
 *    they will be merged into one, the result is,
 *        +-------------+
 *        |      S      |
 *        +-------------+
 * 4.1.2) If range E is acked and the setting range S is unacked, the setting
 *    request of S will be rejected, the result is,
 *        +-------------+
 *        |      E      |
 *        +-------------+
 * 4.1.3) If range E is unacked, and the setting range S is acked, then S may
 *    overwrite the overlapped range of E, the result is,
 *        +---+---------+
 *        | E |    S    |
 *        +---+---------+
 * 4.2) If the setting range S stays in middle of an already set range E, like
 *    the following chart shows,
 *             +----+
 *             | S  |
 *             +----+
 *        +--------------+
 *        |       E      |
 *        +--------------+
 * 4.2.1) If range S and E have same acknowledge value (both acked or unacked),
 *    they will be merged into one, the result is,
 *        +--------------+
 *        |       S      |
 *        +--------------+
 * 4.2.2) If range E is acked and the setting range S is unacked, the setting
 *    request of S will be rejected, the result is also,
 *        +--------------+
 *        |       E      |
 *        +--------------+
 * 4.2.3) If range E is unacked, and the setting range S is acked, then S will
 *    inserted into middle of E and split previous range E into two parts (E1
 *    and E2), the result is,
 *        +----+----+----+
 *        | E1 |  S | E2 |
 *        +----+----+----+
 * 4.3) If the setting bad blocks range S is overlapped with an already set bad
 *    blocks range E. The range S starts after the start LBA of range E, and
 *    ends after the end LBA of range E, as the following chart shows,
 *            +-------------------+
 *            |          S        |
 *            +-------------------+
 *        +-------------+
 *        |      E      |
 *        +-------------+
 *    For this situation the range S can be divided into two parts, the first
 *    part (S1) ends at end range E, and the second part (S2) has rest range of
 *    origin S.
 *            +---------+---------+            +---------+      +---------+
 *            |    S1   |    S2   |            |    S1   |      |    S2   |
 *            +---------+---------+  ===>      +---------+      +---------+
 *        +-------------+                  +-------------+
 *        |      E      |                  |      E      |
 *        +-------------+                  +-------------+
 *     Now in this loop the setting range S1 and already set range E can be
 *     handled as the situations 4.1), the rest range S2 will be handled in next
 *     loop and ignored in this loop.
 * 5) A setting bad blocks range S is adjacent to one or more already set bad
 *    blocks range(s), and they are all acked or unacked range.
 * 5.1) Front merge: If the already set bad blocks range E is before setting
 *    range S and they are adjacent,
 *                +------+
 *                |  S   |
 *                +------+
 *        +-------+
 *        |   E   |
 *        +-------+
 * 5.1.1) When total size of range S and E <= BB_MAX_LEN, and their acknowledge
 *    values are same, the setting range S can front merges into range E. The
 *    result is,
 *        +--------------+
 *        |       S      |
 *        +--------------+
 * 5.1.2) Otherwise these two ranges cannot merge, just insert the setting
 *    range S right after already set range E into the bad blocks table. The
 *    result is,
 *        +--------+------+
 *        |   E    |   S  |
 *        +--------+------+
 * 6) Special cases which above conditions cannot handle
 * 6.1) Multiple already set ranges may merge into less ones in a full bad table
 *        +-------------------------------------------------------+
 *        |                           S                           |
 *        +-------------------------------------------------------+
 *        |<----- BB_MAX_LEN ----->|
 *                                 +-----+     +-----+   +-----+
 *                                 | E1  |     | E2  |   | E3  |
 *                                 +-----+     +-----+   +-----+
 *     In the above example, when the bad blocks table is full, inserting the
 *     first part of setting range S will fail because no more available slot
 *     can be allocated from bad blocks table. In this situation a proper
 *     setting method should be go though all the setting bad blocks range and
 *     look for chance to merge already set ranges into less ones. When there
 *     is available slot from bad blocks table, re-try again to handle more
 *     setting bad blocks ranges as many as possible.
 *        +------------------------+
 *        |          S3            |
 *        +------------------------+
 *        |<----- BB_MAX_LEN ----->|
 *                                 +-----+-----+-----+---+-----+--+
 *                                 |       S1        |     S2     |
 *                                 +-----+-----+-----+---+-----+--+
 *     The above chart shows although the first part (S3) cannot be inserted due
 *     to no-space in bad blocks table, but the following E1, E2 and E3 ranges
 *     can be merged with rest part of S into less range S1 and S2. Now there is
 *     1 free slot in bad blocks table.
 *        +------------------------+-----+-----+-----+---+-----+--+
 *        |           S3           |       S1        |     S2     |
 *        +------------------------+-----+-----+-----+---+-----+--+
 *     Since the bad blocks table is not full anymore, re-try again for the
 *     origin setting range S. Now the setting range S3 can be inserted into the
 *     bad blocks table with previous freed slot from multiple ranges merge.
 * 6.2) Front merge after overwrite
 *    In the following example, in bad blocks table, E1 is an acked bad blocks
 *    range and E2 is an unacked bad blocks range, therefore they are not able
 *    to merge into a larger range. The setting bad blocks range S is acked,
 *    therefore part of E2 can be overwritten by S.
 *                      +--------+
 *                      |    S   |                             acknowledged
 *                      +--------+                         S:       1
 *              +-------+-------------+                   E1:       1
 *              |   E1  |    E2       |                   E2:       0
 *              +-------+-------------+
 *     With previous simplified routines, after overwriting part of E2 with S,
 *     the bad blocks table should be (E3 is remaining part of E2 which is not
 *     overwritten by S),
 *                                                             acknowledged
 *              +-------+--------+----+                    S:       1
 *              |   E1  |    S   | E3 |                   E1:       1
 *              +-------+--------+----+                   E3:       0
 *     The above result is correct but not perfect. Range E1 and S in the bad
 *     blocks table are all acked, merging them into a larger one range may
 *     occupy less bad blocks table space and make badblocks_check() faster.
 *     Therefore in such situation, after overwriting range S, the previous range
 *     E1 should be checked for possible front combination. Then the ideal
 *     result can be,
 *              +----------------+----+                        acknowledged
 *              |       E1       | E3 |                   E1:       1
 *              +----------------+----+                   E3:       0
 * 6.3) Behind merge: If the already set bad blocks range E is behind the setting
 *    range S and they are adjacent. Normally we don't need to care about this
 *    because front merge handles this while going though range S from head to
 *    tail, except for the tail part of range S. When the setting range S are
 *    fully handled, all the above simplified routine doesn't check whether the
 *    tail LBA of range S is adjacent to the next already set range and not
 *    merge them even it is possible.
 *        +------+
 *        |  S   |
 *        +------+
 *               +-------+
 *               |   E   |
 *               +-------+
 *    For the above special situation, when the setting range S are all handled
 *    and the loop ends, an extra check is necessary for whether next already
 *    set range E is right after S and mergeable.
 * 6.3.1) When total size of range E and S <= BB_MAX_LEN, and their acknowledge
 *    values are same, the setting range S can behind merges into range E. The
 *    result is,
 *        +--------------+
 *        |       S      |
 *        +--------------+
 * 6.3.2) Otherwise these two ranges cannot merge, just insert the setting range
 *     S in front of the already set range E in the bad blocks table. The result
 *     is,
 *        +------+-------+
 *        |  S   |   E   |
 *        +------+-------+
 *
 * All the above 5 simplified situations and 3 special cases may cover 99%+ of
 * the bad block range setting conditions. Maybe there is some rare corner case
 * is not considered and optimized, it won't hurt if badblocks_set() fails due
 * to no space, or some ranges are not merged to save bad blocks table space.
 *
 * Inside badblocks_set() each loop starts by jumping to re_insert label, every
 * time for the new loop prev_badblocks() is called to find an already set range
 * which starts before or at current setting range. Since the setting bad blocks
 * range is handled from head to tail, most of the cases it is unnecessary to do
 * the binary search inside prev_badblocks(), it is possible to provide a hint
 * to prev_badblocks() for a fast path, then the expensive binary search can be
 * avoided. In my test with the hint to prev_badblocks(), except for the first
 * loop, all rested calls to prev_badblocks() can go into the fast path and
 * return correct bad blocks table index immediately.
 *
 *
 * Clearing a bad blocks range from the bad block table has similar idea as
 * setting does, but much more simpler. The only thing needs to be noticed is
 * when the clearing range hits middle of a bad block range, the existing bad
 * block range will split into two, and one more item should be added into the
 * bad block table. The simplified situations to be considered are, (The already
 * set bad blocks ranges in bad block table are naming with prefix E, and the
 * clearing bad blocks range is naming with prefix C)
 *
 * 1) A clearing range is not overlapped to any already set ranges in bad block
 *    table.
 *    +-----+         |          +-----+         |          +-----+
 *    |  C  |         |          |  C  |         |          |  C  |
 *    +-----+         or         +-----+         or         +-----+
 *            +---+   |   +----+         +----+  |  +---+
 *            | E |   |   | E1 |         | E2 |  |  | E |
 *            +---+   |   +----+         +----+  |  +---+
 *    For the above situations, no bad block to be cleared and no failure
 *    happens, simply returns 0.
 * 2) The clearing range hits middle of an already setting bad blocks range in
 *    the bad block table.
 *            +---+
 *            | C |
 *            +---+
 *     +-----------------+
 *     |         E       |
 *     +-----------------+
 *    In this situation if the bad block table is not full, the range E will be
 *    split into two ranges E1 and E2. The result is,
 *     +------+   +------+
 *     |  E1  |   |  E2  |
 *     +------+   +------+
 * 3) The clearing range starts exactly at same LBA as an already set bad block range
 *    from the bad block table.
 * 3.1) Partially covered at head part
 *         +------------+
 *         |     C      |
 *         +------------+
 *         +-----------------+
 *         |         E       |
 *         +-----------------+
 *    For this situation, the overlapped already set range will update the
 *    start LBA to end of C and shrink the range to BB_LEN(E) - BB_LEN(C). No
 *    item deleted from bad block table. The result is,
 *                      +----+
 *                      | E1 |
 *                      +----+
 * 3.2) Exact fully covered
 *         +-----------------+
 *         |         C       |
 *         +-----------------+
 *         +-----------------+
 *         |         E       |
 *         +-----------------+
 *    For this situation the whole bad blocks range E will be cleared and its
 *    corresponded item is deleted from the bad block table.
 * 4) The clearing range exactly ends at same LBA as an already set bad block
 *    range.
 *                   +-------+
 *                   |   C   |
 *                   +-------+
 *         +-----------------+
 *         |         E       |
 *         +-----------------+
 *    For the above situation, the already set range E is updated to shrink its
 *    end to the start of C, and reduce its length to BB_LEN(E) - BB_LEN(C).
 *    The result is,
 *         +---------+
 *         |    E    |
 *         +---------+
 * 5) The clearing range is partially overlapped with an already set bad block
 *    range from the bad block table.
 * 5.1) The already set bad block range is front overlapped with the clearing
 *    range.
 *         +----------+
 *         |     C    |
 *         +----------+
 *              +------------+
 *              |      E     |
 *              +------------+
 *   For such situation, the clearing range C can be treated as two parts. The
 *   first part ends at the start LBA of range E, and the second part starts at
 *   same LBA of range E.
 *         +----+-----+               +----+   +-----+
 *         | C1 | C2  |               | C1 |   | C2  |
 *         +----+-----+         ===>  +----+   +-----+
 *              +------------+                 +------------+
 *              |      E     |                 |      E     |
 *              +------------+                 +------------+
 *   Now the first part C1 can be handled as condition 1), and the second part C2 can be
 *   handled as condition 3.1) in next loop.
 * 5.2) The already set bad block range is behind overlaopped with the clearing
 *   range.
 *                 +----------+
 *                 |     C    |
 *                 +----------+
 *         +------------+
 *         |      E     |
 *         +------------+
 *   For such situation, the clearing range C can be treated as two parts. The
 *   first part C1 ends at same end LBA of range E, and the second part starts
 *   at end LBA of range E.
 *                 +----+-----+                 +----+    +-----+
 *                 | C1 | C2  |                 | C1 |    | C2  |
 *                 +----+-----+  ===>           +----+    +-----+
 *         +------------+               +------------+
 *         |      E     |               |      E     |
 *         +------------+               +------------+
 *   Now the first part clearing range C1 can be handled as condition 4), and
 *   the second part clearing range C2 can be handled as condition 1) in next
 *   loop.
 *
 *   All bad blocks range clearing can be simplified into the above 5 situations
 *   by only handling the head part of the clearing range in each run of the
 *   while-loop. The idea is similar to bad blocks range setting but much
 *   simpler.
 */

/*
 * Find the range starts at-or-before 's' from bad table. The search
 * starts from index 'hint' and stops at index 'hint_end' from the bad
 * table.
 */
static int prev_by_hint(struct badblocks *bb, sector_t s, int hint)
{
	int hint_end = hint + 2;
	u64 *p = bb->page;
	int ret = -1;

	while ((hint < hint_end) && ((hint + 1) <= bb->count) &&
	       (BB_OFFSET(p[hint]) <= s)) {
		if ((hint + 1) == bb->count || BB_OFFSET(p[hint + 1]) > s) {
			ret = hint;
			break;
		}
		hint++;
	}

	return ret;
}

/*
 * Find the range starts at-or-before bad->start. If 'hint' is provided
 * (hint >= 0) then search in the bad table from hint firstly. It is
 * very probably the wanted bad range can be found from the hint index,
 * then the unnecessary while-loop iteration can be avoided.
 */
static int prev_badblocks(struct badblocks *bb, struct badblocks_context *bad,
			  int hint)
{
	sector_t s = bad->start;
	int ret = -1;
	int lo, hi;
	u64 *p;

	if (!bb->count)
		goto out;

	if (hint >= 0) {
		ret = prev_by_hint(bb, s, hint);
		if (ret >= 0)
			goto out;
	}

	lo = 0;
	hi = bb->count;
	p = bb->page;

	/* The following bisect search might be unnecessary */
	if (BB_OFFSET(p[lo]) > s)
		return -1;
	if (BB_OFFSET(p[hi - 1]) <= s)
		return hi - 1;

	/* Do bisect search in bad table */
	while (hi - lo > 1) {
		int mid = (lo + hi)/2;
		sector_t a = BB_OFFSET(p[mid]);

		if (a == s) {
			ret = mid;
			goto out;
		}

		if (a < s)
			lo = mid;
		else
			hi = mid;
	}

	if (BB_OFFSET(p[lo]) <= s)
		ret = lo;
out:
	return ret;
}

/*
 * Return 'true' if the range indicated by 'bad' can be backward merged
 * with the bad range (from the bad table) index by 'behind'.
 */
static bool can_merge_behind(struct badblocks *bb,
			     struct badblocks_context *bad, int behind)
{
	sector_t sectors = bad->len;
	sector_t s = bad->start;
	u64 *p = bb->page;

	if ((s < BB_OFFSET(p[behind])) &&
	    ((s + sectors) >= BB_OFFSET(p[behind])) &&
	    ((BB_END(p[behind]) - s) <= BB_MAX_LEN) &&
	    BB_ACK(p[behind]) == bad->ack)
		return true;
	return false;
}

/*
 * Do backward merge for range indicated by 'bad' and the bad range
 * (from the bad table) indexed by 'behind'. The return value is merged
 * sectors from bad->len.
 */
static int behind_merge(struct badblocks *bb, struct badblocks_context *bad,
			int behind)
{
	sector_t sectors = bad->len;
	sector_t s = bad->start;
	u64 *p = bb->page;
	int merged = 0;

	WARN_ON(s >= BB_OFFSET(p[behind]));
	WARN_ON((s + sectors) < BB_OFFSET(p[behind]));

	if (s < BB_OFFSET(p[behind])) {
		merged = BB_OFFSET(p[behind]) - s;
		p[behind] =  BB_MAKE(s, BB_LEN(p[behind]) + merged, bad->ack);

		WARN_ON((BB_LEN(p[behind]) + merged) >= BB_MAX_LEN);
	}

	return merged;
}

/*
 * Return 'true' if the range indicated by 'bad' can be forward
 * merged with the bad range (from the bad table) indexed by 'prev'.
 */
static bool can_merge_front(struct badblocks *bb, int prev,
			    struct badblocks_context *bad)
{
	sector_t s = bad->start;
	u64 *p = bb->page;

	if (BB_ACK(p[prev]) == bad->ack &&
	    (s < BB_END(p[prev]) ||
	     (s == BB_END(p[prev]) && (BB_LEN(p[prev]) < BB_MAX_LEN))))
		return true;
	return false;
}

/*
 * Do forward merge for range indicated by 'bad' and the bad range
 * (from bad table) indexed by 'prev'. The return value is sectors
 * merged from bad->len.
 */
static int front_merge(struct badblocks *bb, int prev, struct badblocks_context *bad)
{
	sector_t sectors = bad->len;
	sector_t s = bad->start;
	u64 *p = bb->page;
	int merged = 0;

	WARN_ON(s > BB_END(p[prev]));

	if (s < BB_END(p[prev])) {
		merged = min_t(sector_t, sectors, BB_END(p[prev]) - s);
	} else {
		merged = min_t(sector_t, sectors, BB_MAX_LEN - BB_LEN(p[prev]));
		if ((prev + 1) < bb->count &&
		    merged > (BB_OFFSET(p[prev + 1]) - BB_END(p[prev]))) {
			merged = BB_OFFSET(p[prev + 1]) - BB_END(p[prev]);
		}

		p[prev] = BB_MAKE(BB_OFFSET(p[prev]),
				  BB_LEN(p[prev]) + merged, bad->ack);
	}

	return merged;
}

/*
 * 'Combine' is a special case which can_merge_front() is not able to
 * handle: If a bad range (indexed by 'prev' from bad table) exactly
 * starts as bad->start, and the bad range ahead of 'prev' (indexed by
 * 'prev - 1' from bad table) exactly ends at where 'prev' starts, and
 * the sum of their lengths does not exceed BB_MAX_LEN limitation, then
 * these two bad range (from bad table) can be combined.
 *
 * Return 'true' if bad ranges indexed by 'prev' and 'prev - 1' from bad
 * table can be combined.
 */
static bool can_combine_front(struct badblocks *bb, int prev,
			      struct badblocks_context *bad)
{
	u64 *p = bb->page;

	if ((prev > 0) &&
	    (BB_OFFSET(p[prev]) == bad->start) &&
	    (BB_END(p[prev - 1]) == BB_OFFSET(p[prev])) &&
	    (BB_LEN(p[prev - 1]) + BB_LEN(p[prev]) <= BB_MAX_LEN) &&
	    (BB_ACK(p[prev - 1]) == BB_ACK(p[prev])))
		return true;
	return false;
}

/*
 * Combine the bad ranges indexed by 'prev' and 'prev - 1' (from bad
 * table) into one larger bad range, and the new range is indexed by
 * 'prev - 1'.
 * The caller of front_combine() will decrease bb->count, therefore
 * it is unnecessary to clear p[perv] after front merge.
 */
static void front_combine(struct badblocks *bb, int prev)
{
	u64 *p = bb->page;

	p[prev - 1] = BB_MAKE(BB_OFFSET(p[prev - 1]),
			      BB_LEN(p[prev - 1]) + BB_LEN(p[prev]),
			      BB_ACK(p[prev]));
	if ((prev + 1) < bb->count)
		memmove(p + prev, p + prev + 1, (bb->count - prev - 1) * 8);
}

/*
 * Return 'true' if the range indicated by 'bad' is exactly forward
 * overlapped with the bad range (from bad table) indexed by 'front'.
 * Exactly forward overlap means the bad range (from bad table) indexed
 * by 'prev' does not cover the whole range indicated by 'bad'.
 */
static bool overlap_front(struct badblocks *bb, int front,
			  struct badblocks_context *bad)
{
	u64 *p = bb->page;

	if (bad->start >= BB_OFFSET(p[front]) &&
	    bad->start < BB_END(p[front]))
		return true;
	return false;
}

/*
 * Return 'true' if the range indicated by 'bad' is exactly backward
 * overlapped with the bad range (from bad table) indexed by 'behind'.
 */
static bool overlap_behind(struct badblocks *bb, struct badblocks_context *bad,
			   int behind)
{
	u64 *p = bb->page;

	if (bad->start < BB_OFFSET(p[behind]) &&
	    (bad->start + bad->len) > BB_OFFSET(p[behind]))
		return true;
	return false;
}

/*
 * Return 'true' if the range indicated by 'bad' can overwrite the bad
 * range (from bad table) indexed by 'prev'.
 *
 * The range indicated by 'bad' can overwrite the bad range indexed by
 * 'prev' when,
 * 1) The whole range indicated by 'bad' can cover partial or whole bad
 *    range (from bad table) indexed by 'prev'.
 * 2) The ack value of 'bad' is larger or equal to the ack value of bad
 *    range 'prev'.
 *
 * If the overwriting doesn't cover the whole bad range (from bad table)
 * indexed by 'prev', new range might be split from existing bad range,
 * 1) The overwrite covers head or tail part of existing bad range, 1
 *    extra bad range will be split and added into the bad table.
 * 2) The overwrite covers middle of existing bad range, 2 extra bad
 *    ranges will be split (ahead and after the overwritten range) and
 *    added into the bad table.
 * The number of extra split ranges of the overwriting is stored in
 * 'extra' and returned for the caller.
 */
static bool can_front_overwrite(struct badblocks *bb, int prev,
				struct badblocks_context *bad, int *extra)
{
	u64 *p = bb->page;
	int len;

	WARN_ON(!overlap_front(bb, prev, bad));

	if (BB_ACK(p[prev]) >= bad->ack)
		return false;

	if (BB_END(p[prev]) <= (bad->start + bad->len)) {
		len = BB_END(p[prev]) - bad->start;
		if (BB_OFFSET(p[prev]) == bad->start)
			*extra = 0;
		else
			*extra = 1;

		bad->len = len;
	} else {
		if (BB_OFFSET(p[prev]) == bad->start)
			*extra = 1;
		else
		/*
		 * prev range will be split into two, beside the overwritten
		 * one, an extra slot needed from bad table.
		 */
			*extra = 2;
	}

	if ((bb->count + (*extra)) >= MAX_BADBLOCKS)
		return false;

	return true;
}

/*
 * Do the overwrite from the range indicated by 'bad' to the bad range
 * (from bad table) indexed by 'prev'.
 * The previously called can_front_overwrite() will provide how many
 * extra bad range(s) might be split and added into the bad table. All
 * the splitting cases in the bad table will be handled here.
 */
static int front_overwrite(struct badblocks *bb, int prev,
			   struct badblocks_context *bad, int extra)
{
	u64 *p = bb->page;
	sector_t orig_end = BB_END(p[prev]);
	int orig_ack = BB_ACK(p[prev]);

	switch (extra) {
	case 0:
		p[prev] = BB_MAKE(BB_OFFSET(p[prev]), BB_LEN(p[prev]),
				  bad->ack);
		break;
	case 1:
		if (BB_OFFSET(p[prev]) == bad->start) {
			p[prev] = BB_MAKE(BB_OFFSET(p[prev]),
					  bad->len, bad->ack);
			memmove(p + prev + 2, p + prev + 1,
				(bb->count - prev - 1) * 8);
			p[prev + 1] = BB_MAKE(bad->start + bad->len,
					      orig_end - BB_END(p[prev]),
					      orig_ack);
		} else {
			p[prev] = BB_MAKE(BB_OFFSET(p[prev]),
					  bad->start - BB_OFFSET(p[prev]),
					  orig_ack);
			/*
			 * prev +2 -> prev + 1 + 1, which is for,
			 * 1) prev + 1: the slot index of the previous one
			 * 2) + 1: one more slot for extra being 1.
			 */
			memmove(p + prev + 2, p + prev + 1,
				(bb->count - prev - 1) * 8);
			p[prev + 1] = BB_MAKE(bad->start, bad->len, bad->ack);
		}
		break;
	case 2:
		p[prev] = BB_MAKE(BB_OFFSET(p[prev]),
				  bad->start - BB_OFFSET(p[prev]),
				  orig_ack);
		/*
		 * prev + 3 -> prev + 1 + 2, which is for,
		 * 1) prev + 1: the slot index of the previous one
		 * 2) + 2: two more slots for extra being 2.
		 */
		memmove(p + prev + 3, p + prev + 1,
			(bb->count - prev - 1) * 8);
		p[prev + 1] = BB_MAKE(bad->start, bad->len, bad->ack);
		p[prev + 2] = BB_MAKE(BB_END(p[prev + 1]),
				      orig_end - BB_END(p[prev + 1]),
				      orig_ack);
		break;
	default:
		break;
	}

	return bad->len;
}

/*
 * Explicitly insert a range indicated by 'bad' to the bad table, where
 * the location is indexed by 'at'.
 */
static int insert_at(struct badblocks *bb, int at, struct badblocks_context *bad)
{
	u64 *p = bb->page;
	int len;

	WARN_ON(badblocks_full(bb));

	len = min_t(sector_t, bad->len, BB_MAX_LEN);
	if (at < bb->count)
		memmove(p + at + 1, p + at, (bb->count - at) * 8);
	p[at] = BB_MAKE(bad->start, len, bad->ack);

	return len;
}

static void badblocks_update_acked(struct badblocks *bb)
{
	bool unacked = false;
	u64 *p = bb->page;
	int i;

	if (!bb->unacked_exist)
		return;

	for (i = 0; i < bb->count ; i++) {
		if (!BB_ACK(p[i])) {
			unacked = true;
			break;
		}
	}

	if (!unacked)
		bb->unacked_exist = 0;
}

/* Do exact work to set bad block range into the bad block table */
static int _badblocks_set(struct badblocks *bb, sector_t s, int sectors,
			  int acknowledged)
{
	int retried = 0, space_desired = 0;
	int orig_len, len = 0, added = 0;
	struct badblocks_context bad;
	int prev = -1, hint = -1;
	sector_t orig_start;
	unsigned long flags;
	int rv = 0;
	u64 *p;

	if (bb->shift < 0)
		/* badblocks are disabled */
		return 1;

	if (sectors == 0)
		/* Invalid sectors number */
		return 1;

	if (bb->shift) {
		/* round the start down, and the end up */
		sector_t next = s + sectors;

		rounddown(s, bb->shift);
		roundup(next, bb->shift);
		sectors = next - s;
	}

	write_seqlock_irqsave(&bb->lock, flags);

	orig_start = s;
	orig_len = sectors;
	bad.ack = acknowledged;
	p = bb->page;

re_insert:
	bad.start = s;
	bad.len = sectors;
	len = 0;

	if (badblocks_empty(bb)) {
		len = insert_at(bb, 0, &bad);
		bb->count++;
		added++;
		goto update_sectors;
	}

	prev = prev_badblocks(bb, &bad, hint);

	/* start before all badblocks */
	if (prev < 0) {
		if (!badblocks_full(bb)) {
			/* insert on the first */
			if (bad.len > (BB_OFFSET(p[0]) - bad.start))
				bad.len = BB_OFFSET(p[0]) - bad.start;
			len = insert_at(bb, 0, &bad);
			bb->count++;
			added++;
			hint = 0;
			goto update_sectors;
		}

		/* No sapce, try to merge */
		if (overlap_behind(bb, &bad, 0)) {
			if (can_merge_behind(bb, &bad, 0)) {
				len = behind_merge(bb, &bad, 0);
				added++;
			} else {
				len = BB_OFFSET(p[0]) - s;
				space_desired = 1;
			}
			hint = 0;
			goto update_sectors;
		}

		/* no table space and give up */
		goto out;
	}

	/* in case p[prev-1] can be merged with p[prev] */
	if (can_combine_front(bb, prev, &bad)) {
		front_combine(bb, prev);
		bb->count--;
		added++;
		hint = prev;
		goto update_sectors;
	}

	if (overlap_front(bb, prev, &bad)) {
		if (can_merge_front(bb, prev, &bad)) {
			len = front_merge(bb, prev, &bad);
			added++;
		} else {
			int extra = 0;

			if (!can_front_overwrite(bb, prev, &bad, &extra)) {
				len = min_t(sector_t,
					    BB_END(p[prev]) - s, sectors);
				hint = prev;
				goto update_sectors;
			}

			len = front_overwrite(bb, prev, &bad, extra);
			added++;
			bb->count += extra;

			if (can_combine_front(bb, prev, &bad)) {
				front_combine(bb, prev);
				bb->count--;
			}
		}
		hint = prev;
		goto update_sectors;
	}

	if (can_merge_front(bb, prev, &bad)) {
		len = front_merge(bb, prev, &bad);
		added++;
		hint = prev;
		goto update_sectors;
	}

	/* if no space in table, still try to merge in the covered range */
	if (badblocks_full(bb)) {
		/* skip the cannot-merge range */
		if (((prev + 1) < bb->count) &&
		    overlap_behind(bb, &bad, prev + 1) &&
		    ((s + sectors) >= BB_END(p[prev + 1]))) {
			len = BB_END(p[prev + 1]) - s;
			hint = prev + 1;
			goto update_sectors;
		}

		/* no retry any more */
		len = sectors;
		space_desired = 1;
		hint = -1;
		goto update_sectors;
	}

	/* cannot merge and there is space in bad table */
	if ((prev + 1) < bb->count &&
	    overlap_behind(bb, &bad, prev + 1))
		bad.len = min_t(sector_t,
				bad.len, BB_OFFSET(p[prev + 1]) - bad.start);

	len = insert_at(bb, prev + 1, &bad);
	bb->count++;
	added++;
	hint = prev + 1;

update_sectors:
	s += len;
	sectors -= len;

	if (sectors > 0)
		goto re_insert;

	WARN_ON(sectors < 0);

	/*
	 * Check whether the following already set range can be
	 * merged. (prev < 0) condition is not handled here,
	 * because it's already complicated enough.
	 */
	if (prev >= 0 &&
	    (prev + 1) < bb->count &&
	    BB_END(p[prev]) == BB_OFFSET(p[prev + 1]) &&
	    (BB_LEN(p[prev]) + BB_LEN(p[prev + 1])) <= BB_MAX_LEN &&
	    BB_ACK(p[prev]) == BB_ACK(p[prev + 1])) {
		p[prev] = BB_MAKE(BB_OFFSET(p[prev]),
				  BB_LEN(p[prev]) + BB_LEN(p[prev + 1]),
				  BB_ACK(p[prev]));

		if ((prev + 2) < bb->count)
			memmove(p + prev + 1, p + prev + 2,
				(bb->count -  (prev + 2)) * 8);
		bb->count--;
	}

	if (space_desired && !badblocks_full(bb)) {
		s = orig_start;
		sectors = orig_len;
		space_desired = 0;
		if (retried++ < 3)
			goto re_insert;
	}

out:
	if (added) {
		set_changed(bb);

		if (!acknowledged)
			bb->unacked_exist = 1;
		else
			badblocks_update_acked(bb);
	}

	write_sequnlock_irqrestore(&bb->lock, flags);

	if (!added)
		rv = 1;

	return rv;
}

/*
 * Clear the bad block range from bad block table which is front overlapped
 * with the clearing range. The return value is how many sectors from an
 * already set bad block range are cleared. If the whole bad block range is
 * covered by the clearing range and fully cleared, 'delete' is set as 1 for
 * the caller to reduce bb->count.
 */
static int front_clear(struct badblocks *bb, int prev,
		       struct badblocks_context *bad, int *deleted)
{
	sector_t sectors = bad->len;
	sector_t s = bad->start;
	u64 *p = bb->page;
	int cleared = 0;

	*deleted = 0;
	if (s == BB_OFFSET(p[prev])) {
		if (BB_LEN(p[prev]) > sectors) {
			p[prev] = BB_MAKE(BB_OFFSET(p[prev]) + sectors,
					  BB_LEN(p[prev]) - sectors,
					  BB_ACK(p[prev]));
			cleared = sectors;
		} else {
			/* BB_LEN(p[prev]) <= sectors */
			cleared = BB_LEN(p[prev]);
			if ((prev + 1) < bb->count)
				memmove(p + prev, p + prev + 1,
				       (bb->count - prev - 1) * 8);
			*deleted = 1;
		}
	} else if (s > BB_OFFSET(p[prev])) {
		if (BB_END(p[prev]) <= (s + sectors)) {
			cleared = BB_END(p[prev]) - s;
			p[prev] = BB_MAKE(BB_OFFSET(p[prev]),
					  s - BB_OFFSET(p[prev]),
					  BB_ACK(p[prev]));
		} else {
			/* Splitting is handled in front_splitting_clear() */
			BUG();
		}
	}

	return cleared;
}

/*
 * Handle the condition that the clearing range hits middle of an already set
 * bad block range from bad block table. In this condition the existing bad
 * block range is split into two after the middle part is cleared.
 */
static int front_splitting_clear(struct badblocks *bb, int prev,
				  struct badblocks_context *bad)
{
	u64 *p = bb->page;
	u64 end = BB_END(p[prev]);
	int ack = BB_ACK(p[prev]);
	sector_t sectors = bad->len;
	sector_t s = bad->start;

	p[prev] = BB_MAKE(BB_OFFSET(p[prev]),
			  s - BB_OFFSET(p[prev]),
			  ack);
	memmove(p + prev + 2, p + prev + 1, (bb->count - prev - 1) * 8);
	p[prev + 1] = BB_MAKE(s + sectors, end - s - sectors, ack);
	return sectors;
}

/* Do the exact work to clear bad block range from the bad block table */
static int _badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
{
	struct badblocks_context bad;
	int prev = -1, hint = -1;
	int len = 0, cleared = 0;
	int rv = 0;
	u64 *p;

	if (bb->shift < 0)
		/* badblocks are disabled */
		return 1;

	if (sectors == 0)
		/* Invalid sectors number */
		return 1;

	if (bb->shift) {
		sector_t target;

		/* When clearing we round the start up and the end down.
		 * This should not matter as the shift should align with
		 * the block size and no rounding should ever be needed.
		 * However it is better the think a block is bad when it
		 * isn't than to think a block is not bad when it is.
		 */
		target = s + sectors;
		roundup(s, bb->shift);
		rounddown(target, bb->shift);
		sectors = target - s;
	}

	write_seqlock_irq(&bb->lock);

	bad.ack = true;
	p = bb->page;

re_clear:
	bad.start = s;
	bad.len = sectors;

	if (badblocks_empty(bb)) {
		len = sectors;
		cleared++;
		goto update_sectors;
	}


	prev = prev_badblocks(bb, &bad, hint);

	/* Start before all badblocks */
	if (prev < 0) {
		if (overlap_behind(bb, &bad, 0)) {
			len = BB_OFFSET(p[0]) - s;
			hint = 0;
		} else {
			len = sectors;
		}
		/*
		 * Both situations are to clear non-bad range,
		 * should be treated as successful
		 */
		cleared++;
		goto update_sectors;
	}

	/* Start after all badblocks */
	if ((prev + 1) >= bb->count && !overlap_front(bb, prev, &bad)) {
		len = sectors;
		cleared++;
		goto update_sectors;
	}

	/* Clear will split a bad record but the table is full */
	if (badblocks_full(bb) && (BB_OFFSET(p[prev]) < bad.start) &&
	    (BB_END(p[prev]) > (bad.start + sectors))) {
		len = sectors;
		goto update_sectors;
	}

	if (overlap_front(bb, prev, &bad)) {
		if ((BB_OFFSET(p[prev]) < bad.start) &&
		    (BB_END(p[prev]) > (bad.start + bad.len))) {
			/* Splitting */
			if ((bb->count + 1) < MAX_BADBLOCKS) {
				len = front_splitting_clear(bb, prev, &bad);
				bb->count += 1;
				cleared++;
			} else {
				/* No space to split, give up */
				len = sectors;
			}
		} else {
			int deleted = 0;

			len = front_clear(bb, prev, &bad, &deleted);
			bb->count -= deleted;
			cleared++;
			hint = prev;
		}

		goto update_sectors;
	}

	/* Not front overlap, but behind overlap */
	if ((prev + 1) < bb->count && overlap_behind(bb, &bad, prev + 1)) {
		len = BB_OFFSET(p[prev + 1]) - bad.start;
		hint = prev + 1;
		/* Clear non-bad range should be treated as successful */
		cleared++;
		goto update_sectors;
	}

	/* Not cover any badblocks range in the table */
	len = sectors;
	/* Clear non-bad range should be treated as successful */
	cleared++;

update_sectors:
	s += len;
	sectors -= len;

	if (sectors > 0)
		goto re_clear;

	WARN_ON(sectors < 0);

	if (cleared) {
		badblocks_update_acked(bb);
		set_changed(bb);
	}

	write_sequnlock_irq(&bb->lock);

	if (!cleared)
		rv = 1;

	return rv;
}

/* Do the exact work to check bad blocks range from the bad block table */
static int _badblocks_check(struct badblocks *bb, sector_t s, int sectors,
			    sector_t *first_bad, int *bad_sectors)
{
	int unacked_badblocks, acked_badblocks;
	int prev = -1, hint = -1, set = 0;
	struct badblocks_context bad;
	unsigned int seq;
	int len, rv;
	u64 *p;

	WARN_ON(bb->shift < 0 || sectors == 0);

	if (bb->shift > 0) {
		sector_t target;

		/* round the start down, and the end up */
		target = s + sectors;
		rounddown(s, bb->shift);
		roundup(target, bb->shift);
		sectors = target - s;
	}

retry:
	seq = read_seqbegin(&bb->lock);

	p = bb->page;
	unacked_badblocks = 0;
	acked_badblocks = 0;

re_check:
	bad.start = s;
	bad.len = sectors;

	if (badblocks_empty(bb)) {
		len = sectors;
		goto update_sectors;
	}

	prev = prev_badblocks(bb, &bad, hint);

	/* start after all badblocks */
	if ((prev + 1) >= bb->count && !overlap_front(bb, prev, &bad)) {
		len = sectors;
		goto update_sectors;
	}

	if (overlap_front(bb, prev, &bad)) {
		if (BB_ACK(p[prev]))
			acked_badblocks++;
		else
			unacked_badblocks++;

		if (BB_END(p[prev]) >= (s + sectors))
			len = sectors;
		else
			len = BB_END(p[prev]) - s;

		if (set == 0) {
			*first_bad = BB_OFFSET(p[prev]);
			*bad_sectors = BB_LEN(p[prev]);
			set = 1;
		}
		goto update_sectors;
	}

	/* Not front overlap, but behind overlap */
	if ((prev + 1) < bb->count && overlap_behind(bb, &bad, prev + 1)) {
		len = BB_OFFSET(p[prev + 1]) - bad.start;
		hint = prev + 1;
		goto update_sectors;
	}

	/* not cover any badblocks range in the table */
	len = sectors;

update_sectors:
	s += len;
	sectors -= len;

	if (sectors > 0)
		goto re_check;

	WARN_ON(sectors < 0);

	if (unacked_badblocks > 0)
		rv = -1;
	else if (acked_badblocks > 0)
		rv = 1;
	else
		rv = 0;

	if (read_seqretry(&bb->lock, seq))
		goto retry;

	return rv;
}

/**
 * badblocks_check() - check a given range for bad sectors
 * @bb:		the badblocks structure that holds all badblock information
 * @s:		sector (start) at which to check for badblocks
 * @sectors:	number of sectors to check for badblocks
 * @first_bad:	pointer to store location of the first badblock
 * @bad_sectors: pointer to store number of badblocks after @first_bad
 *
 * We can record which blocks on each device are 'bad' and so just
 * fail those blocks, or that stripe, rather than the whole device.
 * Entries in the bad-block table are 64bits wide.  This comprises:
 * Length of bad-range, in sectors: 0-511 for lengths 1-512
 * Start of bad-range, sector offset, 54 bits (allows 8 exbibytes)
 *  A 'shift' can be set so that larger blocks are tracked and
 *  consequently larger devices can be covered.
 * 'Acknowledged' flag - 1 bit. - the most significant bit.
 *
 * Locking of the bad-block table uses a seqlock so badblocks_check
 * might need to retry if it is very unlucky.
 * We will sometimes want to check for bad blocks in a bi_end_io function,
 * so we use the write_seqlock_irq variant.
 *
 * When looking for a bad block we specify a range and want to
 * know if any block in the range is bad.  So we binary-search
 * to the last range that starts at-or-before the given endpoint,
 * (or "before the sector after the target range")
 * then see if it ends after the given start.
 *
 * Return:
 *  0: there are no known bad blocks in the range
 *  1: there are known bad block which are all acknowledged
 * -1: there are bad blocks which have not yet been acknowledged in metadata.
 * plus the start/length of the first bad section we overlap.
 */
int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
			sector_t *first_bad, int *bad_sectors)
{
	return _badblocks_check(bb, s, sectors, first_bad, bad_sectors);
}
EXPORT_SYMBOL_GPL(badblocks_check);

/**
 * badblocks_set() - Add a range of bad blocks to the table.
 * @bb:		the badblocks structure that holds all badblock information
 * @s:		first sector to mark as bad
 * @sectors:	number of sectors to mark as bad
 * @acknowledged: weather to mark the bad sectors as acknowledged
 *
 * This might extend the table, or might contract it if two adjacent ranges
 * can be merged. We binary-search to find the 'insertion' point, then
 * decide how best to handle it.
 *
 * Return:
 *  0: success
 *  1: failed to set badblocks (out of space)
 */
int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
			int acknowledged)
{
	return _badblocks_set(bb, s, sectors, acknowledged);
}
EXPORT_SYMBOL_GPL(badblocks_set);

/**
 * badblocks_clear() - Remove a range of bad blocks to the table.
 * @bb:		the badblocks structure that holds all badblock information
 * @s:		first sector to mark as bad
 * @sectors:	number of sectors to mark as bad
 *
 * This may involve extending the table if we spilt a region,
 * but it must not fail.  So if the table becomes full, we just
 * drop the remove request.
 *
 * Return:
 *  0: success
 *  1: failed to clear badblocks
 */
int badblocks_clear(struct badblocks *bb, sector_t s, int sectors)
{
	return _badblocks_clear(bb, s, sectors);
}
EXPORT_SYMBOL_GPL(badblocks_clear);

/**
 * ack_all_badblocks() - Acknowledge all bad blocks in a list.
 * @bb:		the badblocks structure that holds all badblock information
 *
 * This only succeeds if ->changed is clear.  It is used by
 * in-kernel metadata updates
 */
void ack_all_badblocks(struct badblocks *bb)
{
	if (bb->page == NULL || bb->changed)
		/* no point even trying */
		return;
	write_seqlock_irq(&bb->lock);

	if (bb->changed == 0 && bb->unacked_exist) {
		u64 *p = bb->page;
		int i;

		for (i = 0; i < bb->count ; i++) {
			if (!BB_ACK(p[i])) {
				sector_t start = BB_OFFSET(p[i]);
				int len = BB_LEN(p[i]);

				p[i] = BB_MAKE(start, len, 1);
			}
		}
		bb->unacked_exist = 0;
	}
	write_sequnlock_irq(&bb->lock);
}
EXPORT_SYMBOL_GPL(ack_all_badblocks);

/**
 * badblocks_show() - sysfs access to bad-blocks list
 * @bb:		the badblocks structure that holds all badblock information
 * @page:	buffer received from sysfs
 * @unack:	weather to show unacknowledged badblocks
 *
 * Return:
 *  Length of returned data
 */
ssize_t badblocks_show(struct badblocks *bb, char *page, int unack)
{
	size_t len;
	int i;
	u64 *p = bb->page;
	unsigned seq;

	if (bb->shift < 0)
		return 0;

retry:
	seq = read_seqbegin(&bb->lock);

	len = 0;
	i = 0;

	while (len < PAGE_SIZE && i < bb->count) {
		sector_t s = BB_OFFSET(p[i]);
		unsigned int length = BB_LEN(p[i]);
		int ack = BB_ACK(p[i]);

		i++;

		if (unack && ack)
			continue;

		len += snprintf(page+len, PAGE_SIZE-len, "%llu %u\n",
				(unsigned long long)s << bb->shift,
				length << bb->shift);
	}
	if (unack && len == 0)
		bb->unacked_exist = 0;

	if (read_seqretry(&bb->lock, seq))
		goto retry;

	return len;
}
EXPORT_SYMBOL_GPL(badblocks_show);

/**
 * badblocks_store() - sysfs access to bad-blocks list
 * @bb:		the badblocks structure that holds all badblock information
 * @page:	buffer received from sysfs
 * @len:	length of data received from sysfs
 * @unack:	weather to show unacknowledged badblocks
 *
 * Return:
 *  Length of the buffer processed or -ve error.
 */
ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
			int unack)
{
	unsigned long long sector;
	int length;
	char newline;

	switch (sscanf(page, "%llu %d%c", &sector, &length, &newline)) {
	case 3:
		if (newline != '\n')
			return -EINVAL;
		fallthrough;
	case 2:
		if (length <= 0)
			return -EINVAL;
		break;
	default:
		return -EINVAL;
	}

	if (badblocks_set(bb, sector, length, !unack))
		return -ENOSPC;
	else
		return len;
}
EXPORT_SYMBOL_GPL(badblocks_store);

static int __badblocks_init(struct device *dev, struct badblocks *bb,
		int enable)
{
	bb->dev = dev;
	bb->count = 0;
	if (enable)
		bb->shift = 0;
	else
		bb->shift = -1;
	if (dev)
		bb->page = devm_kzalloc(dev, PAGE_SIZE, GFP_KERNEL);
	else
		bb->page = kzalloc(PAGE_SIZE, GFP_KERNEL);
	if (!bb->page) {
		bb->shift = -1;
		return -ENOMEM;
	}
	seqlock_init(&bb->lock);

	return 0;
}

/**
 * badblocks_init() - initialize the badblocks structure
 * @bb:		the badblocks structure that holds all badblock information
 * @enable:	weather to enable badblocks accounting
 *
 * Return:
 *  0: success
 *  -ve errno: on error
 */
int badblocks_init(struct badblocks *bb, int enable)
{
	return __badblocks_init(NULL, bb, enable);
}
EXPORT_SYMBOL_GPL(badblocks_init);

int devm_init_badblocks(struct device *dev, struct badblocks *bb)
{
	if (!bb)
		return -EINVAL;
	return __badblocks_init(dev, bb, 1);
}
EXPORT_SYMBOL_GPL(devm_init_badblocks);

/**
 * badblocks_exit() - free the badblocks structure
 * @bb:		the badblocks structure that holds all badblock information
 */
void badblocks_exit(struct badblocks *bb)
{
	if (!bb)
		return;
	if (bb->dev)
		devm_kfree(bb->dev, bb->page);
	else
		kfree(bb->page);
	bb->page = NULL;
}
EXPORT_SYMBOL_GPL(badblocks_exit);