summaryrefslogtreecommitdiff
path: root/drivers/mtd/ubi/wl.c
blob: 40f39e5d6dfcc068519598452bd8787c7b143c39 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * Copyright (c) International Business Machines Corp., 2006
 *
 * Authors: Artem Bityutskiy (Битюцкий Артём), Thomas Gleixner
 */

/*
 * UBI wear-leveling sub-system.
 *
 * This sub-system is responsible for wear-leveling. It works in terms of
 * physical eraseblocks and erase counters and knows nothing about logical
 * eraseblocks, volumes, etc. From this sub-system's perspective all physical
 * eraseblocks are of two types - used and free. Used physical eraseblocks are
 * those that were "get" by the 'ubi_wl_get_peb()' function, and free physical
 * eraseblocks are those that were put by the 'ubi_wl_put_peb()' function.
 *
 * Physical eraseblocks returned by 'ubi_wl_get_peb()' have only erase counter
 * header. The rest of the physical eraseblock contains only %0xFF bytes.
 *
 * When physical eraseblocks are returned to the WL sub-system by means of the
 * 'ubi_wl_put_peb()' function, they are scheduled for erasure. The erasure is
 * done asynchronously in context of the per-UBI device background thread,
 * which is also managed by the WL sub-system.
 *
 * The wear-leveling is ensured by means of moving the contents of used
 * physical eraseblocks with low erase counter to free physical eraseblocks
 * with high erase counter.
 *
 * If the WL sub-system fails to erase a physical eraseblock, it marks it as
 * bad.
 *
 * This sub-system is also responsible for scrubbing. If a bit-flip is detected
 * in a physical eraseblock, it has to be moved. Technically this is the same
 * as moving it for wear-leveling reasons.
 *
 * As it was said, for the UBI sub-system all physical eraseblocks are either
 * "free" or "used". Free eraseblock are kept in the @wl->free RB-tree, while
 * used eraseblocks are kept in @wl->used, @wl->erroneous, or @wl->scrub
 * RB-trees, as well as (temporarily) in the @wl->pq queue.
 *
 * When the WL sub-system returns a physical eraseblock, the physical
 * eraseblock is protected from being moved for some "time". For this reason,
 * the physical eraseblock is not directly moved from the @wl->free tree to the
 * @wl->used tree. There is a protection queue in between where this
 * physical eraseblock is temporarily stored (@wl->pq).
 *
 * All this protection stuff is needed because:
 *  o we don't want to move physical eraseblocks just after we have given them
 *    to the user; instead, we first want to let users fill them up with data;
 *
 *  o there is a chance that the user will put the physical eraseblock very
 *    soon, so it makes sense not to move it for some time, but wait.
 *
 * Physical eraseblocks stay protected only for limited time. But the "time" is
 * measured in erase cycles in this case. This is implemented with help of the
 * protection queue. Eraseblocks are put to the tail of this queue when they
 * are returned by the 'ubi_wl_get_peb()', and eraseblocks are removed from the
 * head of the queue on each erase operation (for any eraseblock). So the
 * length of the queue defines how may (global) erase cycles PEBs are protected.
 *
 * To put it differently, each physical eraseblock has 2 main states: free and
 * used. The former state corresponds to the @wl->free tree. The latter state
 * is split up on several sub-states:
 * o the WL movement is allowed (@wl->used tree);
 * o the WL movement is disallowed (@wl->erroneous) because the PEB is
 *   erroneous - e.g., there was a read error;
 * o the WL movement is temporarily prohibited (@wl->pq queue);
 * o scrubbing is needed (@wl->scrub tree).
 *
 * Depending on the sub-state, wear-leveling entries of the used physical
 * eraseblocks may be kept in one of those structures.
 *
 * Note, in this implementation, we keep a small in-RAM object for each physical
 * eraseblock. This is surely not a scalable solution. But it appears to be good
 * enough for moderately large flashes and it is simple. In future, one may
 * re-work this sub-system and make it more scalable.
 *
 * At the moment this sub-system does not utilize the sequence number, which
 * was introduced relatively recently. But it would be wise to do this because
 * the sequence number of a logical eraseblock characterizes how old is it. For
 * example, when we move a PEB with low erase counter, and we need to pick the
 * target PEB, we pick a PEB with the highest EC if our PEB is "old" and we
 * pick target PEB with an average EC if our PEB is not very "old". This is a
 * room for future re-works of the WL sub-system.
 */

#include <linux/slab.h>
#include <linux/crc32.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include "ubi.h"
#include "wl.h"

/* Number of physical eraseblocks reserved for wear-leveling purposes */
#define WL_RESERVED_PEBS 1

/*
 * Maximum difference between two erase counters. If this threshold is
 * exceeded, the WL sub-system starts moving data from used physical
 * eraseblocks with low erase counter to free physical eraseblocks with high
 * erase counter.
 */
#define UBI_WL_THRESHOLD CONFIG_MTD_UBI_WL_THRESHOLD

/*
 * When a physical eraseblock is moved, the WL sub-system has to pick the target
 * physical eraseblock to move to. The simplest way would be just to pick the
 * one with the highest erase counter. But in certain workloads this could lead
 * to an unlimited wear of one or few physical eraseblock. Indeed, imagine a
 * situation when the picked physical eraseblock is constantly erased after the
 * data is written to it. So, we have a constant which limits the highest erase
 * counter of the free physical eraseblock to pick. Namely, the WL sub-system
 * does not pick eraseblocks with erase counter greater than the lowest erase
 * counter plus %WL_FREE_MAX_DIFF.
 */
#define WL_FREE_MAX_DIFF (2*UBI_WL_THRESHOLD)

/*
 * Maximum number of consecutive background thread failures which is enough to
 * switch to read-only mode.
 */
#define WL_MAX_FAILURES 32

static int self_check_ec(struct ubi_device *ubi, int pnum, int ec);
static int self_check_in_wl_tree(const struct ubi_device *ubi,
				 struct ubi_wl_entry *e, struct rb_root *root);
static int self_check_in_pq(const struct ubi_device *ubi,
			    struct ubi_wl_entry *e);

/**
 * wl_tree_add - add a wear-leveling entry to a WL RB-tree.
 * @e: the wear-leveling entry to add
 * @root: the root of the tree
 *
 * Note, we use (erase counter, physical eraseblock number) pairs as keys in
 * the @ubi->used and @ubi->free RB-trees.
 */
static void wl_tree_add(struct ubi_wl_entry *e, struct rb_root *root)
{
	struct rb_node **p, *parent = NULL;

	p = &root->rb_node;
	while (*p) {
		struct ubi_wl_entry *e1;

		parent = *p;
		e1 = rb_entry(parent, struct ubi_wl_entry, u.rb);

		if (e->ec < e1->ec)
			p = &(*p)->rb_left;
		else if (e->ec > e1->ec)
			p = &(*p)->rb_right;
		else {
			ubi_assert(e->pnum != e1->pnum);
			if (e->pnum < e1->pnum)
				p = &(*p)->rb_left;
			else
				p = &(*p)->rb_right;
		}
	}

	rb_link_node(&e->u.rb, parent, p);
	rb_insert_color(&e->u.rb, root);
}

/**
 * wl_entry_destroy - destroy a wear-leveling entry.
 * @ubi: UBI device description object
 * @e: the wear-leveling entry to add
 *
 * This function destroys a wear leveling entry and removes
 * the reference from the lookup table.
 */
static void wl_entry_destroy(struct ubi_device *ubi, struct ubi_wl_entry *e)
{
	ubi->lookuptbl[e->pnum] = NULL;
	kmem_cache_free(ubi_wl_entry_slab, e);
}

/**
 * do_work - do one pending work.
 * @ubi: UBI device description object
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
static int do_work(struct ubi_device *ubi)
{
	int err;
	struct ubi_work *wrk;

	cond_resched();

	/*
	 * @ubi->work_sem is used to synchronize with the workers. Workers take
	 * it in read mode, so many of them may be doing works at a time. But
	 * the queue flush code has to be sure the whole queue of works is
	 * done, and it takes the mutex in write mode.
	 */
	down_read(&ubi->work_sem);
	spin_lock(&ubi->wl_lock);
	if (list_empty(&ubi->works)) {
		spin_unlock(&ubi->wl_lock);
		up_read(&ubi->work_sem);
		return 0;
	}

	wrk = list_entry(ubi->works.next, struct ubi_work, list);
	list_del(&wrk->list);
	ubi->works_count -= 1;
	ubi_assert(ubi->works_count >= 0);
	spin_unlock(&ubi->wl_lock);

	/*
	 * Call the worker function. Do not touch the work structure
	 * after this call as it will have been freed or reused by that
	 * time by the worker function.
	 */
	err = wrk->func(ubi, wrk, 0);
	if (err)
		ubi_err(ubi, "work failed with error code %d", err);
	up_read(&ubi->work_sem);

	return err;
}

/**
 * in_wl_tree - check if wear-leveling entry is present in a WL RB-tree.
 * @e: the wear-leveling entry to check
 * @root: the root of the tree
 *
 * This function returns non-zero if @e is in the @root RB-tree and zero if it
 * is not.
 */
static int in_wl_tree(struct ubi_wl_entry *e, struct rb_root *root)
{
	struct rb_node *p;

	p = root->rb_node;
	while (p) {
		struct ubi_wl_entry *e1;

		e1 = rb_entry(p, struct ubi_wl_entry, u.rb);

		if (e->pnum == e1->pnum) {
			ubi_assert(e == e1);
			return 1;
		}

		if (e->ec < e1->ec)
			p = p->rb_left;
		else if (e->ec > e1->ec)
			p = p->rb_right;
		else {
			ubi_assert(e->pnum != e1->pnum);
			if (e->pnum < e1->pnum)
				p = p->rb_left;
			else
				p = p->rb_right;
		}
	}

	return 0;
}

/**
 * in_pq - check if a wear-leveling entry is present in the protection queue.
 * @ubi: UBI device description object
 * @e: the wear-leveling entry to check
 *
 * This function returns non-zero if @e is in the protection queue and zero
 * if it is not.
 */
static inline int in_pq(const struct ubi_device *ubi, struct ubi_wl_entry *e)
{
	struct ubi_wl_entry *p;
	int i;

	for (i = 0; i < UBI_PROT_QUEUE_LEN; ++i)
		list_for_each_entry(p, &ubi->pq[i], u.list)
			if (p == e)
				return 1;

	return 0;
}

/**
 * prot_queue_add - add physical eraseblock to the protection queue.
 * @ubi: UBI device description object
 * @e: the physical eraseblock to add
 *
 * This function adds @e to the tail of the protection queue @ubi->pq, where
 * @e will stay for %UBI_PROT_QUEUE_LEN erase operations and will be
 * temporarily protected from the wear-leveling worker. Note, @wl->lock has to
 * be locked.
 */
static void prot_queue_add(struct ubi_device *ubi, struct ubi_wl_entry *e)
{
	int pq_tail = ubi->pq_head - 1;

	if (pq_tail < 0)
		pq_tail = UBI_PROT_QUEUE_LEN - 1;
	ubi_assert(pq_tail >= 0 && pq_tail < UBI_PROT_QUEUE_LEN);
	list_add_tail(&e->u.list, &ubi->pq[pq_tail]);
	dbg_wl("added PEB %d EC %d to the protection queue", e->pnum, e->ec);
}

/**
 * find_wl_entry - find wear-leveling entry closest to certain erase counter.
 * @ubi: UBI device description object
 * @root: the RB-tree where to look for
 * @diff: maximum possible difference from the smallest erase counter
 *
 * This function looks for a wear leveling entry with erase counter closest to
 * min + @diff, where min is the smallest erase counter.
 */
static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi,
					  struct rb_root *root, int diff)
{
	struct rb_node *p;
	struct ubi_wl_entry *e;
	int max;

	e = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb);
	max = e->ec + diff;

	p = root->rb_node;
	while (p) {
		struct ubi_wl_entry *e1;

		e1 = rb_entry(p, struct ubi_wl_entry, u.rb);
		if (e1->ec >= max)
			p = p->rb_left;
		else {
			p = p->rb_right;
			e = e1;
		}
	}

	return e;
}

/**
 * find_mean_wl_entry - find wear-leveling entry with medium erase counter.
 * @ubi: UBI device description object
 * @root: the RB-tree where to look for
 *
 * This function looks for a wear leveling entry with medium erase counter,
 * but not greater or equivalent than the lowest erase counter plus
 * %WL_FREE_MAX_DIFF/2.
 */
static struct ubi_wl_entry *find_mean_wl_entry(struct ubi_device *ubi,
					       struct rb_root *root)
{
	struct ubi_wl_entry *e, *first, *last;

	first = rb_entry(rb_first(root), struct ubi_wl_entry, u.rb);
	last = rb_entry(rb_last(root), struct ubi_wl_entry, u.rb);

	if (last->ec - first->ec < WL_FREE_MAX_DIFF) {
		e = rb_entry(root->rb_node, struct ubi_wl_entry, u.rb);

		/* If no fastmap has been written and this WL entry can be used
		 * as anchor PEB, hold it back and return the second best
		 * WL entry such that fastmap can use the anchor PEB later. */
		e = may_reserve_for_fm(ubi, e, root);
	} else
		e = find_wl_entry(ubi, root, WL_FREE_MAX_DIFF/2);

	return e;
}

/**
 * wl_get_wle - get a mean wl entry to be used by ubi_wl_get_peb() or
 * refill_wl_user_pool().
 * @ubi: UBI device description object
 *
 * This function returns a wear leveling entry in case of success and
 * NULL in case of failure.
 */
static struct ubi_wl_entry *wl_get_wle(struct ubi_device *ubi)
{
	struct ubi_wl_entry *e;

	e = find_mean_wl_entry(ubi, &ubi->free);
	if (!e) {
		ubi_err(ubi, "no free eraseblocks");
		return NULL;
	}

	self_check_in_wl_tree(ubi, e, &ubi->free);

	/*
	 * Move the physical eraseblock to the protection queue where it will
	 * be protected from being moved for some time.
	 */
	rb_erase(&e->u.rb, &ubi->free);
	ubi->free_count--;
	dbg_wl("PEB %d EC %d", e->pnum, e->ec);

	return e;
}

/**
 * prot_queue_del - remove a physical eraseblock from the protection queue.
 * @ubi: UBI device description object
 * @pnum: the physical eraseblock to remove
 *
 * This function deletes PEB @pnum from the protection queue and returns zero
 * in case of success and %-ENODEV if the PEB was not found.
 */
static int prot_queue_del(struct ubi_device *ubi, int pnum)
{
	struct ubi_wl_entry *e;

	e = ubi->lookuptbl[pnum];
	if (!e)
		return -ENODEV;

	if (self_check_in_pq(ubi, e))
		return -ENODEV;

	list_del(&e->u.list);
	dbg_wl("deleted PEB %d from the protection queue", e->pnum);
	return 0;
}

/**
 * sync_erase - synchronously erase a physical eraseblock.
 * @ubi: UBI device description object
 * @e: the physical eraseblock to erase
 * @torture: if the physical eraseblock has to be tortured
 *
 * This function returns zero in case of success and a negative error code in
 * case of failure.
 */
static int sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e,
		      int torture)
{
	int err;
	struct ubi_ec_hdr *ec_hdr;
	unsigned long long ec = e->ec;

	dbg_wl("erase PEB %d, old EC %llu", e->pnum, ec);

	err = self_check_ec(ubi, e->pnum, e->ec);
	if (err)
		return -EINVAL;

	ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_NOFS);
	if (!ec_hdr)
		return -ENOMEM;

	err = ubi_io_sync_erase(ubi, e->pnum, torture);
	if (err < 0)
		goto out_free;

	ec += err;
	if (ec > UBI_MAX_ERASECOUNTER) {
		/*
		 * Erase counter overflow. Upgrade UBI and use 64-bit
		 * erase counters internally.
		 */
		ubi_err(ubi, "erase counter overflow at PEB %d, EC %llu",
			e->pnum, ec);
		err = -EINVAL;
		goto out_free;
	}

	dbg_wl("erased PEB %d, new EC %llu", e->pnum, ec);

	ec_hdr->ec = cpu_to_be64(ec);

	err = ubi_io_write_ec_hdr(ubi, e->pnum, ec_hdr);
	if (err)
		goto out_free;

	e->ec = ec;
	spin_lock(&ubi->wl_lock);
	if (e->ec > ubi->max_ec)
		ubi->max_ec = e->ec;
	spin_unlock(&ubi->wl_lock);

out_free:
	kfree(ec_hdr);
	return err;
}

/**
 * serve_prot_queue - check if it is time to stop protecting PEBs.
 * @ubi: UBI device description object
 *
 * This function is called after each erase operation and removes PEBs from the
 * tail of the protection queue. These PEBs have been protected for long enough
 * and should be moved to the used tree.
 */
static void serve_prot_queue(struct ubi_device *ubi)
{
	struct ubi_wl_entry *e, *tmp;
	int count;

	/*
	 * There may be several protected physical eraseblock to remove,
	 * process them all.
	 */
repeat:
	count = 0;
	spin_lock(&ubi->wl_lock);
	list_for_each_entry_safe(e, tmp, &ubi->pq[ubi->pq_head], u.list) {
		dbg_wl("PEB %d EC %d protection over, move to used tree",
			e->pnum, e->ec);

		list_del(&e->u.list);
		wl_tree_add(e, &ubi->used);
		if (count++ > 32) {
			/*
			 * Let's be nice and avoid holding the spinlock for
			 * too long.
			 */
			spin_unlock(&ubi->wl_lock);
			cond_resched();
			goto repeat;
		}
	}

	ubi->pq_head += 1;
	if (ubi->pq_head == UBI_PROT_QUEUE_LEN)
		ubi->pq_head = 0;
	ubi_assert(ubi->pq_head >= 0 && ubi->pq_head < UBI_PROT_QUEUE_LEN);
	spin_unlock(&ubi->wl_lock);
}

/**
 * __schedule_ubi_work - schedule a work.
 * @ubi: UBI device description object
 * @wrk: the work to schedule
 *
 * This function adds a work defined by @wrk to the tail of the pending works
 * list. Can only be used if ubi->work_sem is already held in read mode!
 */
static void __schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk)
{
	spin_lock(&ubi->wl_lock);
	list_add_tail(&wrk->list, &ubi->works);
	ubi_assert(ubi->works_count >= 0);
	ubi->works_count += 1;
	if (ubi->thread_enabled && !ubi_dbg_is_bgt_disabled(ubi))
		wake_up_process(ubi->bgt_thread);
	spin_unlock(&ubi->wl_lock);
}

/**
 * schedule_ubi_work - schedule a work.
 * @ubi: UBI device description object
 * @wrk: the work to schedule
 *
 * This function adds a work defined by @wrk to the tail of the pending works
 * list.
 */
static void schedule_ubi_work(struct ubi_device *ubi, struct ubi_work *wrk)
{
	down_read(&ubi->work_sem);
	__schedule_ubi_work(ubi, wrk);
	up_read(&ubi->work_sem);
}

static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
			int shutdown);

/**
 * schedule_erase - schedule an erase work.
 * @ubi: UBI device description object
 * @e: the WL entry of the physical eraseblock to erase
 * @vol_id: the volume ID that last used this PEB
 * @lnum: the last used logical eraseblock number for the PEB
 * @torture: if the physical eraseblock has to be tortured
 * @nested: denotes whether the work_sem is already held in read mode
 *
 * This function returns zero in case of success and a %-ENOMEM in case of
 * failure.
 */
static int schedule_erase(struct ubi_device *ubi, struct ubi_wl_entry *e,
			  int vol_id, int lnum, int torture, bool nested)
{
	struct ubi_work *wl_wrk;

	ubi_assert(e);

	dbg_wl("schedule erasure of PEB %d, EC %d, torture %d",
	       e->pnum, e->ec, torture);

	wl_wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS);
	if (!wl_wrk)
		return -ENOMEM;

	wl_wrk->func = &erase_worker;
	wl_wrk->e = e;
	wl_wrk->vol_id = vol_id;
	wl_wrk->lnum = lnum;
	wl_wrk->torture = torture;

	if (nested)
		__schedule_ubi_work(ubi, wl_wrk);
	else
		schedule_ubi_work(ubi, wl_wrk);
	return 0;
}

static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk);
/**
 * do_sync_erase - run the erase worker synchronously.
 * @ubi: UBI device description object
 * @e: the WL entry of the physical eraseblock to erase
 * @vol_id: the volume ID that last used this PEB
 * @lnum: the last used logical eraseblock number for the PEB
 * @torture: if the physical eraseblock has to be tortured
 *
 */
static int do_sync_erase(struct ubi_device *ubi, struct ubi_wl_entry *e,
			 int vol_id, int lnum, int torture)
{
	struct ubi_work wl_wrk;

	dbg_wl("sync erase of PEB %i", e->pnum);

	wl_wrk.e = e;
	wl_wrk.vol_id = vol_id;
	wl_wrk.lnum = lnum;
	wl_wrk.torture = torture;

	return __erase_worker(ubi, &wl_wrk);
}

static int ensure_wear_leveling(struct ubi_device *ubi, int nested);
/**
 * wear_leveling_worker - wear-leveling worker function.
 * @ubi: UBI device description object
 * @wrk: the work object
 * @shutdown: non-zero if the worker has to free memory and exit
 * because the WL-subsystem is shutting down
 *
 * This function copies a more worn out physical eraseblock to a less worn out
 * one. Returns zero in case of success and a negative error code in case of
 * failure.
 */
static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk,
				int shutdown)
{
	int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0;
	int erase = 0, keep = 0, vol_id = -1, lnum = -1;
	struct ubi_wl_entry *e1, *e2;
	struct ubi_vid_io_buf *vidb;
	struct ubi_vid_hdr *vid_hdr;
	int dst_leb_clean = 0;

	kfree(wrk);
	if (shutdown)
		return 0;

	vidb = ubi_alloc_vid_buf(ubi, GFP_NOFS);
	if (!vidb)
		return -ENOMEM;

	vid_hdr = ubi_get_vid_hdr(vidb);

	down_read(&ubi->fm_eba_sem);
	mutex_lock(&ubi->move_mutex);
	spin_lock(&ubi->wl_lock);
	ubi_assert(!ubi->move_from && !ubi->move_to);
	ubi_assert(!ubi->move_to_put);

#ifdef CONFIG_MTD_UBI_FASTMAP
	if (!next_peb_for_wl(ubi) ||
#else
	if (!ubi->free.rb_node ||
#endif
	    (!ubi->used.rb_node && !ubi->scrub.rb_node)) {
		/*
		 * No free physical eraseblocks? Well, they must be waiting in
		 * the queue to be erased. Cancel movement - it will be
		 * triggered again when a free physical eraseblock appears.
		 *
		 * No used physical eraseblocks? They must be temporarily
		 * protected from being moved. They will be moved to the
		 * @ubi->used tree later and the wear-leveling will be
		 * triggered again.
		 */
		dbg_wl("cancel WL, a list is empty: free %d, used %d",
		       !ubi->free.rb_node, !ubi->used.rb_node);
		goto out_cancel;
	}

#ifdef CONFIG_MTD_UBI_FASTMAP
	e1 = find_anchor_wl_entry(&ubi->used);
	if (e1 && ubi->fm_anchor &&
	    (ubi->fm_anchor->ec - e1->ec >= UBI_WL_THRESHOLD)) {
		ubi->fm_do_produce_anchor = 1;
		/*
		 * fm_anchor is no longer considered a good anchor.
		 * NULL assignment also prevents multiple wear level checks
		 * of this PEB.
		 */
		wl_tree_add(ubi->fm_anchor, &ubi->free);
		ubi->fm_anchor = NULL;
		ubi->free_count++;
	}

	if (ubi->fm_do_produce_anchor) {
		if (!e1)
			goto out_cancel;
		e2 = get_peb_for_wl(ubi);
		if (!e2)
			goto out_cancel;

		self_check_in_wl_tree(ubi, e1, &ubi->used);
		rb_erase(&e1->u.rb, &ubi->used);
		dbg_wl("anchor-move PEB %d to PEB %d", e1->pnum, e2->pnum);
		ubi->fm_do_produce_anchor = 0;
	} else if (!ubi->scrub.rb_node) {
#else
	if (!ubi->scrub.rb_node) {
#endif
		/*
		 * Now pick the least worn-out used physical eraseblock and a
		 * highly worn-out free physical eraseblock. If the erase
		 * counters differ much enough, start wear-leveling.
		 */
		e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb);
		e2 = get_peb_for_wl(ubi);
		if (!e2)
			goto out_cancel;

		if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD)) {
			dbg_wl("no WL needed: min used EC %d, max free EC %d",
			       e1->ec, e2->ec);

			/* Give the unused PEB back */
			wl_tree_add(e2, &ubi->free);
			ubi->free_count++;
			goto out_cancel;
		}
		self_check_in_wl_tree(ubi, e1, &ubi->used);
		rb_erase(&e1->u.rb, &ubi->used);
		dbg_wl("move PEB %d EC %d to PEB %d EC %d",
		       e1->pnum, e1->ec, e2->pnum, e2->ec);
	} else {
		/* Perform scrubbing */
		scrubbing = 1;
		e1 = rb_entry(rb_first(&ubi->scrub), struct ubi_wl_entry, u.rb);
		e2 = get_peb_for_wl(ubi);
		if (!e2)
			goto out_cancel;

		self_check_in_wl_tree(ubi, e1, &ubi->scrub);
		rb_erase(&e1->u.rb, &ubi->scrub);
		dbg_wl("scrub PEB %d to PEB %d", e1->pnum, e2->pnum);
	}

	ubi->move_from = e1;
	ubi->move_to = e2;
	spin_unlock(&ubi->wl_lock);

	/*
	 * Now we are going to copy physical eraseblock @e1->pnum to @e2->pnum.
	 * We so far do not know which logical eraseblock our physical
	 * eraseblock (@e1) belongs to. We have to read the volume identifier
	 * header first.
	 *
	 * Note, we are protected from this PEB being unmapped and erased. The
	 * 'ubi_wl_put_peb()' would wait for moving to be finished if the PEB
	 * which is being moved was unmapped.
	 */

	err = ubi_io_read_vid_hdr(ubi, e1->pnum, vidb, 0);
	if (err && err != UBI_IO_BITFLIPS) {
		dst_leb_clean = 1;
		if (err == UBI_IO_FF) {
			/*
			 * We are trying to move PEB without a VID header. UBI
			 * always write VID headers shortly after the PEB was
			 * given, so we have a situation when it has not yet
			 * had a chance to write it, because it was preempted.
			 * So add this PEB to the protection queue so far,
			 * because presumably more data will be written there
			 * (including the missing VID header), and then we'll
			 * move it.
			 */
			dbg_wl("PEB %d has no VID header", e1->pnum);
			protect = 1;
			goto out_not_moved;
		} else if (err == UBI_IO_FF_BITFLIPS) {
			/*
			 * The same situation as %UBI_IO_FF, but bit-flips were
			 * detected. It is better to schedule this PEB for
			 * scrubbing.
			 */
			dbg_wl("PEB %d has no VID header but has bit-flips",
			       e1->pnum);
			scrubbing = 1;
			goto out_not_moved;
		} else if (ubi->fast_attach && err == UBI_IO_BAD_HDR_EBADMSG) {
			/*
			 * While a full scan would detect interrupted erasures
			 * at attach time we can face them here when attached from
			 * Fastmap.
			 */
			dbg_wl("PEB %d has ECC errors, maybe from an interrupted erasure",
			       e1->pnum);
			erase = 1;
			goto out_not_moved;
		}

		ubi_err(ubi, "error %d while reading VID header from PEB %d",
			err, e1->pnum);
		goto out_error;
	}

	vol_id = be32_to_cpu(vid_hdr->vol_id);
	lnum = be32_to_cpu(vid_hdr->lnum);

	err = ubi_eba_copy_leb(ubi, e1->pnum, e2->pnum, vidb);
	if (err) {
		if (err == MOVE_CANCEL_RACE) {
			/*
			 * The LEB has not been moved because the volume is
			 * being deleted or the PEB has been put meanwhile. We
			 * should prevent this PEB from being selected for
			 * wear-leveling movement again, so put it to the
			 * protection queue.
			 */
			protect = 1;
			dst_leb_clean = 1;
			goto out_not_moved;
		}
		if (err == MOVE_RETRY) {
			scrubbing = 1;
			dst_leb_clean = 1;
			goto out_not_moved;
		}
		if (err == MOVE_TARGET_BITFLIPS || err == MOVE_TARGET_WR_ERR ||
		    err == MOVE_TARGET_RD_ERR) {
			/*
			 * Target PEB had bit-flips or write error - torture it.
			 */
			torture = 1;
			keep = 1;
			goto out_not_moved;
		}

		if (err == MOVE_SOURCE_RD_ERR) {
			/*
			 * An error happened while reading the source PEB. Do
			 * not switch to R/O mode in this case, and give the
			 * upper layers a possibility to recover from this,
			 * e.g. by unmapping corresponding LEB. Instead, just
			 * put this PEB to the @ubi->erroneous list to prevent
			 * UBI from trying to move it over and over again.
			 */
			if (ubi->erroneous_peb_count > ubi->max_erroneous) {
				ubi_err(ubi, "too many erroneous eraseblocks (%d)",
					ubi->erroneous_peb_count);
				goto out_error;
			}
			dst_leb_clean = 1;
			erroneous = 1;
			goto out_not_moved;
		}

		if (err < 0)
			goto out_error;

		ubi_assert(0);
	}

	/* The PEB has been successfully moved */
	if (scrubbing)
		ubi_msg(ubi, "scrubbed PEB %d (LEB %d:%d), data moved to PEB %d",
			e1->pnum, vol_id, lnum, e2->pnum);
	ubi_free_vid_buf(vidb);

	spin_lock(&ubi->wl_lock);
	if (!ubi->move_to_put) {
		wl_tree_add(e2, &ubi->used);
		e2 = NULL;
	}
	ubi->move_from = ubi->move_to = NULL;
	ubi->move_to_put = ubi->wl_scheduled = 0;
	spin_unlock(&ubi->wl_lock);

	err = do_sync_erase(ubi, e1, vol_id, lnum, 0);
	if (err) {
		if (e2) {
			spin_lock(&ubi->wl_lock);
			wl_entry_destroy(ubi, e2);
			spin_unlock(&ubi->wl_lock);
		}
		goto out_ro;
	}

	if (e2) {
		/*
		 * Well, the target PEB was put meanwhile, schedule it for
		 * erasure.
		 */
		dbg_wl("PEB %d (LEB %d:%d) was put meanwhile, erase",
		       e2->pnum, vol_id, lnum);
		err = do_sync_erase(ubi, e2, vol_id, lnum, 0);
		if (err)
			goto out_ro;
	}

	dbg_wl("done");
	mutex_unlock(&ubi->move_mutex);
	up_read(&ubi->fm_eba_sem);
	return 0;

	/*
	 * For some reasons the LEB was not moved, might be an error, might be
	 * something else. @e1 was not changed, so return it back. @e2 might
	 * have been changed, schedule it for erasure.
	 */
out_not_moved:
	if (vol_id != -1)
		dbg_wl("cancel moving PEB %d (LEB %d:%d) to PEB %d (%d)",
		       e1->pnum, vol_id, lnum, e2->pnum, err);
	else
		dbg_wl("cancel moving PEB %d to PEB %d (%d)",
		       e1->pnum, e2->pnum, err);
	spin_lock(&ubi->wl_lock);
	if (protect)
		prot_queue_add(ubi, e1);
	else if (erroneous) {
		wl_tree_add(e1, &ubi->erroneous);
		ubi->erroneous_peb_count += 1;
	} else if (scrubbing)
		wl_tree_add(e1, &ubi->scrub);
	else if (keep)
		wl_tree_add(e1, &ubi->used);
	if (dst_leb_clean) {
		wl_tree_add(e2, &ubi->free);
		ubi->free_count++;
	}

	ubi_assert(!ubi->move_to_put);
	ubi->move_from = ubi->move_to = NULL;
	ubi->wl_scheduled = 0;
	spin_unlock(&ubi->wl_lock);

	ubi_free_vid_buf(vidb);
	if (dst_leb_clean) {
		ensure_wear_leveling(ubi, 1);
	} else {
		err = do_sync_erase(ubi, e2, vol_id, lnum, torture);
		if (err)
			goto out_ro;
	}

	if (erase) {
		err = do_sync_erase(ubi, e1, vol_id, lnum, 1);
		if (err)
			goto out_ro;
	}

	mutex_unlock(&ubi->move_mutex);
	up_read(&ubi->fm_eba_sem);
	return 0;

out_error:
	if (vol_id != -1)
		ubi_err(ubi, "error %d while moving PEB %d to PEB %d",
			err, e1->pnum, e2->pnum);
	else
		ubi_err(ubi, "error %d while moving PEB %d (LEB %d:%d) to PEB %d",
			err, e1->pnum, vol_id, lnum, e2->pnum);
	spin_lock(&ubi->wl_lock);
	ubi->move_from = ubi->move_to = NULL;
	ubi->move_to_put = ubi->wl_scheduled = 0;
	wl_entry_destroy(ubi, e1);
	wl_entry_destroy(ubi, e2);
	spin_unlock(&ubi->wl_lock);

	ubi_free_vid_buf(vidb);

out_ro:
	ubi_ro_mode(ubi);
	mutex_unlock(&ubi->move_mutex);
	up_read(&ubi->fm_eba_sem);
	ubi_assert(err != 0);
	return err < 0 ? err : -EIO;

out_cancel:
	ubi->wl_scheduled = 0;
	spin_unlock(&ubi->wl_lock);
	mutex_unlock(&ubi->move_mutex);
	up_read(&ubi->fm_eba_sem);
	ubi_free_vid_buf(vidb);
	return 0;
}

/**
 * ensure_wear_leveling - schedule wear-leveling if it is needed.
 * @ubi: UBI device description object
 * @nested: set to non-zero if this function is called from UBI worker
 *
 * This function checks if it is time to start wear-leveling and schedules it
 * if yes. This function returns zero in case of success and a negative error
 * code in case of failure.
 */
static int ensure_wear_leveling(struct ubi_device *ubi, int nested)
{
	int err = 0;
	struct ubi_work *wrk;

	spin_lock(&ubi->wl_lock);
	if (ubi->wl_scheduled)
		/* Wear-leveling is already in the work queue */
		goto out_unlock;

	/*
	 * If the ubi->scrub tree is not empty, scrubbing is needed, and the
	 * WL worker has to be scheduled anyway.
	 */
	if (!ubi->scrub.rb_node) {
#ifdef CONFIG_MTD_UBI_FASTMAP
		if (!need_wear_leveling(ubi))
			goto out_unlock;
#else
		struct ubi_wl_entry *e1;
		struct ubi_wl_entry *e2;

		if (!ubi->used.rb_node || !ubi->free.rb_node)
			/* No physical eraseblocks - no deal */
			goto out_unlock;

		/*
		 * We schedule wear-leveling only if the difference between the
		 * lowest erase counter of used physical eraseblocks and a high
		 * erase counter of free physical eraseblocks is greater than
		 * %UBI_WL_THRESHOLD.
		 */
		e1 = rb_entry(rb_first(&ubi->used), struct ubi_wl_entry, u.rb);
		e2 = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF);

		if (!(e2->ec - e1->ec >= UBI_WL_THRESHOLD))
			goto out_unlock;
#endif
		dbg_wl("schedule wear-leveling");
	} else
		dbg_wl("schedule scrubbing");

	ubi->wl_scheduled = 1;
	spin_unlock(&ubi->wl_lock);

	wrk = kmalloc(sizeof(struct ubi_work), GFP_NOFS);
	if (!wrk) {
		err = -ENOMEM;
		goto out_cancel;
	}

	wrk->func = &wear_leveling_worker;
	if (nested)
		__schedule_ubi_work(ubi, wrk);
	else
		schedule_ubi_work(ubi, wrk);
	return err;

out_cancel:
	spin_lock(&ubi->wl_lock);
	ubi->wl_scheduled = 0;
out_unlock:
	spin_unlock(&ubi->wl_lock);
	return err;
}

/**
 * __erase_worker - physical eraseblock erase worker function.
 * @ubi: UBI device description object
 * @wl_wrk: the work object
 *
 * This function erases a physical eraseblock and perform torture testing if
 * needed. It also takes care about marking the physical eraseblock bad if
 * needed. Returns zero in case of success and a negative error code in case of
 * failure.
 */
static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk)
{
	struct ubi_wl_entry *e = wl_wrk->e;
	int pnum = e->pnum;
	int vol_id = wl_wrk->vol_id;
	int lnum = wl_wrk->lnum;
	int err, available_consumed = 0;

	dbg_wl("erase PEB %d EC %d LEB %d:%d",
	       pnum, e->ec, wl_wrk->vol_id, wl_wrk->lnum);

	err = sync_erase(ubi, e, wl_wrk->torture);
	if (!err) {
		spin_lock(&ubi->wl_lock);

		if (!ubi->fm_disabled && !ubi->fm_anchor &&
		    e->pnum < UBI_FM_MAX_START) {
			/*
			 * Abort anchor production, if needed it will be
			 * enabled again in the wear leveling started below.
			 */
			ubi->fm_anchor = e;
			ubi->fm_do_produce_anchor = 0;
		} else {
			wl_tree_add(e, &ubi->free);
			ubi->free_count++;
		}

		spin_unlock(&ubi->wl_lock);

		/*
		 * One more erase operation has happened, take care about
		 * protected physical eraseblocks.
		 */
		serve_prot_queue(ubi);

		/* And take care about wear-leveling */
		err = ensure_wear_leveling(ubi, 1);
		return err;
	}

	ubi_err(ubi, "failed to erase PEB %d, error %d", pnum, err);

	if (err == -EINTR || err == -ENOMEM || err == -EAGAIN ||
	    err == -EBUSY) {
		int err1;

		/* Re-schedule the LEB for erasure */
		err1 = schedule_erase(ubi, e, vol_id, lnum, 0, false);
		if (err1) {
			spin_lock(&ubi->wl_lock);
			wl_entry_destroy(ubi, e);
			spin_unlock(&ubi->wl_lock);
			err = err1;
			goto out_ro;
		}
		return err;
	}

	spin_lock(&ubi->wl_lock);
	wl_entry_destroy(ubi, e);
	spin_unlock(&ubi->wl_lock);
	if (err != -EIO)
		/*
		 * If this is not %-EIO, we have no idea what to do. Scheduling
		 * this physical eraseblock for erasure again would cause
		 * errors again and again. Well, lets switch to R/O mode.
		 */
		goto out_ro;

	/* It is %-EIO, the PEB went bad */

	if (!ubi->bad_allowed) {
		ubi_err(ubi, "bad physical eraseblock %d detected", pnum);
		goto out_ro;
	}

	spin_lock(&ubi->volumes_lock);
	if (ubi->beb_rsvd_pebs == 0) {
		if (ubi->avail_pebs == 0) {
			spin_unlock(&ubi->volumes_lock);
			ubi_err(ubi, "no reserved/available physical eraseblocks");
			goto out_ro;
		}
		ubi->avail_pebs -= 1;
		available_consumed = 1;
	}
	spin_unlock(&ubi->volumes_lock);

	ubi_msg(ubi, "mark PEB %d as bad", pnum);
	err = ubi_io_mark_bad(ubi, pnum);
	if (err)
		goto out_ro;

	spin_lock(&ubi->volumes_lock);
	if (ubi->beb_rsvd_pebs > 0) {
		if (available_consumed) {
			/*
			 * The amount of reserved PEBs increased since we last
			 * checked.
			 */
			ubi->avail_pebs += 1;
			available_consumed = 0;
		}
		ubi->beb_rsvd_pebs -= 1;
	}
	ubi->bad_peb_count += 1;
	ubi->good_peb_count -= 1;
	ubi_calculate_reserved(ubi);
	if (available_consumed)
		ubi_warn(ubi, "no PEBs in the reserved pool, used an available PEB");
	else if (ubi->beb_rsvd_pebs)
		ubi_msg(ubi, "%d PEBs left in the reserve",
			ubi->beb_rsvd_pebs);
	else
		ubi_warn(ubi, "last PEB from the reserve was used");
	spin_unlock(&ubi->volumes_lock);

	return err;

out_ro:
	if (available_consumed) {
		spin_lock(&ubi->volumes_lock);
		ubi->avail_pebs += 1;
		spin_unlock(&ubi->volumes_lock);
	}
	ubi_ro_mode(ubi);
	return err;
}

static int erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk,
			  int shutdown)
{
	int ret;

	if (shutdown) {
		struct ubi_wl_entry *e = wl_wrk->e;

		dbg_wl("cancel erasure of PEB %d EC %d", e->pnum, e->ec);
		kfree(wl_wrk);
		wl_entry_destroy(ubi, e);
		return 0;
	}

	ret = __erase_worker(ubi, wl_wrk);
	kfree(wl_wrk);
	return ret;
}

/**
 * ubi_wl_put_peb - return a PEB to the wear-leveling sub-system.
 * @ubi: UBI device description object
 * @vol_id: the volume ID that last used this PEB
 * @lnum: the last used logical eraseblock number for the PEB
 * @pnum: physical eraseblock to return
 * @torture: if this physical eraseblock has to be tortured
 *
 * This function is called to return physical eraseblock @pnum to the pool of
 * free physical eraseblocks. The @torture flag has to be set if an I/O error
 * occurred to this @pnum and it has to be tested. This function returns zero
 * in case of success, and a negative error code in case of failure.
 */
int ubi_wl_put_peb(struct ubi_device *ubi, int vol_id, int lnum,
		   int pnum, int torture)
{
	int err;
	struct ubi_wl_entry *e;

	dbg_wl("PEB %d", pnum);
	ubi_assert(pnum >= 0);
	ubi_assert(pnum < ubi->peb_count);

	down_read(&ubi->fm_protect);

retry:
	spin_lock(&ubi->wl_lock);
	e = ubi->lookuptbl[pnum];
	if (!e) {
		/*
		 * This wl entry has been removed for some errors by other
		 * process (eg. wear leveling worker), corresponding process
		 * (except __erase_worker, which cannot concurrent with
		 * ubi_wl_put_peb) will set ubi ro_mode at the same time,
		 * just ignore this wl entry.
		 */
		spin_unlock(&ubi->wl_lock);
		up_read(&ubi->fm_protect);
		return 0;
	}
	if (e == ubi->move_from) {
		/*
		 * User is putting the physical eraseblock which was selected to
		 * be moved. It will be scheduled for erasure in the
		 * wear-leveling worker.
		 */
		dbg_wl("PEB %d is being moved, wait", pnum);
		spin_unlock(&ubi->wl_lock);

		/* Wait for the WL worker by taking the @ubi->move_mutex */
		mutex_lock(&ubi->move_mutex);
		mutex_unlock(&ubi->move_mutex);
		goto retry;
	} else if (e == ubi->move_to) {
		/*
		 * User is putting the physical eraseblock which was selected
		 * as the target the data is moved to. It may happen if the EBA
		 * sub-system already re-mapped the LEB in 'ubi_eba_copy_leb()'
		 * but the WL sub-system has not put the PEB to the "used" tree
		 * yet, but it is about to do this. So we just set a flag which
		 * will tell the WL worker that the PEB is not needed anymore
		 * and should be scheduled for erasure.
		 */
		dbg_wl("PEB %d is the target of data moving", pnum);
		ubi_assert(!ubi->move_to_put);
		ubi->move_to_put = 1;
		spin_unlock(&ubi->wl_lock);
		up_read(&ubi->fm_protect);
		return 0;
	} else {
		if (in_wl_tree(e, &ubi->used)) {
			self_check_in_wl_tree(ubi, e, &ubi->used);
			rb_erase(&e->u.rb, &ubi->used);
		} else if (in_wl_tree(e, &ubi->scrub)) {
			self_check_in_wl_tree(ubi, e, &ubi->scrub);
			rb_erase(&e->u.rb, &ubi->scrub);
		} else if (in_wl_tree(e, &ubi->erroneous)) {
			self_check_in_wl_tree(ubi, e, &ubi->erroneous);
			rb_erase(&e->u.rb, &ubi->erroneous);
			ubi->erroneous_peb_count -= 1;
			ubi_assert(ubi->erroneous_peb_count >= 0);
			/* Erroneous PEBs should be tortured */
			torture = 1;
		} else {
			err = prot_queue_del(ubi, e->pnum);
			if (err) {
				ubi_err(ubi, "PEB %d not found", pnum);
				ubi_ro_mode(ubi);
				spin_unlock(&ubi->wl_lock);
				up_read(&ubi->fm_protect);
				return err;
			}
		}
	}
	spin_unlock(&ubi->wl_lock);

	err = schedule_erase(ubi, e, vol_id, lnum, torture, false);
	if (err) {
		spin_lock(&ubi->wl_lock);
		wl_tree_add(e, &ubi->used);
		spin_unlock(&ubi->wl_lock);
	}

	up_read(&ubi->fm_protect);
	return err;
}

/**
 * ubi_wl_scrub_peb - schedule a physical eraseblock for scrubbing.
 * @ubi: UBI device description object
 * @pnum: the physical eraseblock to schedule
 *
 * If a bit-flip in a physical eraseblock is detected, this physical eraseblock
 * needs scrubbing. This function schedules a physical eraseblock for
 * scrubbing which is done in background. This function returns zero in case of
 * success and a negative error code in case of failure.
 */
int ubi_wl_scrub_peb(struct ubi_device *ubi, int pnum)
{
	struct ubi_wl_entry *e;

	ubi_msg(ubi, "schedule PEB %d for scrubbing", pnum);

retry:
	spin_lock(&ubi->wl_lock);
	e = ubi->lookuptbl[pnum];
	if (e == ubi->move_from || in_wl_tree(e, &ubi->scrub) ||
				   in_wl_tree(e, &ubi->erroneous)) {
		spin_unlock(&ubi->wl_lock);
		return 0;
	}

	if (e == ubi->move_to) {
		/*
		 * This physical eraseblock was used to move data to. The data
		 * was moved but the PEB was not yet inserted to the proper
		 * tree. We should just wait a little and let the WL worker
		 * proceed.
		 */
		spin_unlock(&ubi->wl_lock);
		dbg_wl("the PEB %d is not in proper tree, retry", pnum);
		yield();
		goto retry;
	}

	if (in_wl_tree(e, &ubi->used)) {
		self_check_in_wl_tree(ubi, e, &ubi->used);
		rb_erase(&e->u.rb, &ubi->used);
	} else {
		int err;

		err = prot_queue_del(ubi, e->pnum);
		if (err) {
			ubi_err(ubi, "PEB %d not found", pnum);
			ubi_ro_mode(ubi);
			spin_unlock(&ubi->wl_lock);
			return err;
		}
	}

	wl_tree_add(e, &ubi->scrub);
	spin_unlock(&ubi->wl_lock);

	/*
	 * Technically scrubbing is the same as wear-leveling, so it is done
	 * by the WL worker.
	 */
	return ensure_wear_leveling(ubi, 0);
}

/**
 * ubi_wl_flush - flush all pending works.
 * @ubi: UBI device description object
 * @vol_id: the volume id to flush for
 * @lnum: the logical eraseblock number to flush for
 *
 * This function executes all pending works for a particular volume id /
 * logical eraseblock number pair. If either value is set to %UBI_ALL, then it
 * acts as a wildcard for all of the corresponding volume numbers or logical
 * eraseblock numbers. It returns zero in case of success and a negative error
 * code in case of failure.
 */
int ubi_wl_flush(struct ubi_device *ubi, int vol_id, int lnum)
{
	int err = 0;
	int found = 1;

	/*
	 * Erase while the pending works queue is not empty, but not more than
	 * the number of currently pending works.
	 */
	dbg_wl("flush pending work for LEB %d:%d (%d pending works)",
	       vol_id, lnum, ubi->works_count);

	while (found) {
		struct ubi_work *wrk, *tmp;
		found = 0;

		down_read(&ubi->work_sem);
		spin_lock(&ubi->wl_lock);
		list_for_each_entry_safe(wrk, tmp, &ubi->works, list) {
			if ((vol_id == UBI_ALL || wrk->vol_id == vol_id) &&
			    (lnum == UBI_ALL || wrk->lnum == lnum)) {
				list_del(&wrk->list);
				ubi->works_count -= 1;
				ubi_assert(ubi->works_count >= 0);
				spin_unlock(&ubi->wl_lock);

				err = wrk->func(ubi, wrk, 0);
				if (err) {
					up_read(&ubi->work_sem);
					return err;
				}

				spin_lock(&ubi->wl_lock);
				found = 1;
				break;
			}
		}
		spin_unlock(&ubi->wl_lock);
		up_read(&ubi->work_sem);
	}

	/*
	 * Make sure all the works which have been done in parallel are
	 * finished.
	 */
	down_write(&ubi->work_sem);
	up_write(&ubi->work_sem);

	return err;
}

static bool scrub_possible(struct ubi_device *ubi, struct ubi_wl_entry *e)
{
	if (in_wl_tree(e, &ubi->scrub))
		return false;
	else if (in_wl_tree(e, &ubi->erroneous))
		return false;
	else if (ubi->move_from == e)
		return false;
	else if (ubi->move_to == e)
		return false;

	return true;
}

/**
 * ubi_bitflip_check - Check an eraseblock for bitflips and scrub it if needed.
 * @ubi: UBI device description object
 * @pnum: the physical eraseblock to schedule
 * @force: don't read the block, assume bitflips happened and take action.
 *
 * This function reads the given eraseblock and checks if bitflips occured.
 * In case of bitflips, the eraseblock is scheduled for scrubbing.
 * If scrubbing is forced with @force, the eraseblock is not read,
 * but scheduled for scrubbing right away.
 *
 * Returns:
 * %EINVAL, PEB is out of range
 * %ENOENT, PEB is no longer used by UBI
 * %EBUSY, PEB cannot be checked now or a check is currently running on it
 * %EAGAIN, bit flips happened but scrubbing is currently not possible
 * %EUCLEAN, bit flips happened and PEB is scheduled for scrubbing
 * %0, no bit flips detected
 */
int ubi_bitflip_check(struct ubi_device *ubi, int pnum, int force)
{
	int err = 0;
	struct ubi_wl_entry *e;

	if (pnum < 0 || pnum >= ubi->peb_count) {
		err = -EINVAL;
		goto out;
	}

	/*
	 * Pause all parallel work, otherwise it can happen that the
	 * erase worker frees a wl entry under us.
	 */
	down_write(&ubi->work_sem);

	/*
	 * Make sure that the wl entry does not change state while
	 * inspecting it.
	 */
	spin_lock(&ubi->wl_lock);
	e = ubi->lookuptbl[pnum];
	if (!e) {
		spin_unlock(&ubi->wl_lock);
		err = -ENOENT;
		goto out_resume;
	}

	/*
	 * Does it make sense to check this PEB?
	 */
	if (!scrub_possible(ubi, e)) {
		spin_unlock(&ubi->wl_lock);
		err = -EBUSY;
		goto out_resume;
	}
	spin_unlock(&ubi->wl_lock);

	if (!force) {
		mutex_lock(&ubi->buf_mutex);
		err = ubi_io_read(ubi, ubi->peb_buf, pnum, 0, ubi->peb_size);
		mutex_unlock(&ubi->buf_mutex);
	}

	if (force || err == UBI_IO_BITFLIPS) {
		/*
		 * Okay, bit flip happened, let's figure out what we can do.
		 */
		spin_lock(&ubi->wl_lock);

		/*
		 * Recheck. We released wl_lock, UBI might have killed the
		 * wl entry under us.
		 */
		e = ubi->lookuptbl[pnum];
		if (!e) {
			spin_unlock(&ubi->wl_lock);
			err = -ENOENT;
			goto out_resume;
		}

		/*
		 * Need to re-check state
		 */
		if (!scrub_possible(ubi, e)) {
			spin_unlock(&ubi->wl_lock);
			err = -EBUSY;
			goto out_resume;
		}

		if (in_pq(ubi, e)) {
			prot_queue_del(ubi, e->pnum);
			wl_tree_add(e, &ubi->scrub);
			spin_unlock(&ubi->wl_lock);

			err = ensure_wear_leveling(ubi, 1);
		} else if (in_wl_tree(e, &ubi->used)) {
			rb_erase(&e->u.rb, &ubi->used);
			wl_tree_add(e, &ubi->scrub);
			spin_unlock(&ubi->wl_lock);

			err = ensure_wear_leveling(ubi, 1);
		} else if (in_wl_tree(e, &ubi->free)) {
			rb_erase(&e->u.rb, &ubi->free);
			ubi->free_count--;
			spin_unlock(&ubi->wl_lock);

			/*
			 * This PEB is empty we can schedule it for
			 * erasure right away. No wear leveling needed.
			 */
			err = schedule_erase(ubi, e, UBI_UNKNOWN, UBI_UNKNOWN,
					     force ? 0 : 1, true);
		} else {
			spin_unlock(&ubi->wl_lock);
			err = -EAGAIN;
		}

		if (!err && !force)
			err = -EUCLEAN;
	} else {
		err = 0;
	}

out_resume:
	up_write(&ubi->work_sem);
out:

	return err;
}

/**
 * tree_destroy - destroy an RB-tree.
 * @ubi: UBI device description object
 * @root: the root of the tree to destroy
 */
static void tree_destroy(struct ubi_device *ubi, struct rb_root *root)
{
	struct rb_node *rb;
	struct ubi_wl_entry *e;

	rb = root->rb_node;
	while (rb) {
		if (rb->rb_left)
			rb = rb->rb_left;
		else if (rb->rb_right)
			rb = rb->rb_right;
		else {
			e = rb_entry(rb, struct ubi_wl_entry, u.rb);

			rb = rb_parent(rb);
			if (rb) {
				if (rb->rb_left == &e->u.rb)
					rb->rb_left = NULL;
				else
					rb->rb_right = NULL;
			}

			wl_entry_destroy(ubi, e);
		}
	}
}

/**
 * ubi_thread - UBI background thread.
 * @u: the UBI device description object pointer
 */
int ubi_thread(void *u)
{
	int failures = 0;
	struct ubi_device *ubi = u;

	ubi_msg(ubi, "background thread \"%s\" started, PID %d",
		ubi->bgt_name, task_pid_nr(current));

	set_freezable();
	for (;;) {
		int err;

		if (kthread_should_stop())
			break;

		if (try_to_freeze())
			continue;

		spin_lock(&ubi->wl_lock);
		if (list_empty(&ubi->works) || ubi->ro_mode ||
		    !ubi->thread_enabled || ubi_dbg_is_bgt_disabled(ubi)) {
			set_current_state(TASK_INTERRUPTIBLE);
			spin_unlock(&ubi->wl_lock);

			/*
			 * Check kthread_should_stop() after we set the task
			 * state to guarantee that we either see the stop bit
			 * and exit or the task state is reset to runnable such
			 * that it's not scheduled out indefinitely and detects
			 * the stop bit at kthread_should_stop().
			 */
			if (kthread_should_stop()) {
				set_current_state(TASK_RUNNING);
				break;
			}

			schedule();
			continue;
		}
		spin_unlock(&ubi->wl_lock);

		err = do_work(ubi);
		if (err) {
			ubi_err(ubi, "%s: work failed with error code %d",
				ubi->bgt_name, err);
			if (failures++ > WL_MAX_FAILURES) {
				/*
				 * Too many failures, disable the thread and
				 * switch to read-only mode.
				 */
				ubi_msg(ubi, "%s: %d consecutive failures",
					ubi->bgt_name, WL_MAX_FAILURES);
				ubi_ro_mode(ubi);
				ubi->thread_enabled = 0;
				continue;
			}
		} else
			failures = 0;

		cond_resched();
	}

	dbg_wl("background thread \"%s\" is killed", ubi->bgt_name);
	ubi->thread_enabled = 0;
	return 0;
}

/**
 * shutdown_work - shutdown all pending works.
 * @ubi: UBI device description object
 */
static void shutdown_work(struct ubi_device *ubi)
{
	while (!list_empty(&ubi->works)) {
		struct ubi_work *wrk;

		wrk = list_entry(ubi->works.next, struct ubi_work, list);
		list_del(&wrk->list);
		wrk->func(ubi, wrk, 1);
		ubi->works_count -= 1;
		ubi_assert(ubi->works_count >= 0);
	}
}

/**
 * erase_aeb - erase a PEB given in UBI attach info PEB
 * @ubi: UBI device description object
 * @aeb: UBI attach info PEB
 * @sync: If true, erase synchronously. Otherwise schedule for erasure
 */
static int erase_aeb(struct ubi_device *ubi, struct ubi_ainf_peb *aeb, bool sync)
{
	struct ubi_wl_entry *e;
	int err;

	e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
	if (!e)
		return -ENOMEM;

	e->pnum = aeb->pnum;
	e->ec = aeb->ec;
	ubi->lookuptbl[e->pnum] = e;

	if (sync) {
		err = sync_erase(ubi, e, false);
		if (err)
			goto out_free;

		wl_tree_add(e, &ubi->free);
		ubi->free_count++;
	} else {
		err = schedule_erase(ubi, e, aeb->vol_id, aeb->lnum, 0, false);
		if (err)
			goto out_free;
	}

	return 0;

out_free:
	wl_entry_destroy(ubi, e);

	return err;
}

/**
 * ubi_wl_init - initialize the WL sub-system using attaching information.
 * @ubi: UBI device description object
 * @ai: attaching information
 *
 * This function returns zero in case of success, and a negative error code in
 * case of failure.
 */
int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
{
	int err, i, reserved_pebs, found_pebs = 0;
	struct rb_node *rb1, *rb2;
	struct ubi_ainf_volume *av;
	struct ubi_ainf_peb *aeb, *tmp;
	struct ubi_wl_entry *e;

	ubi->used = ubi->erroneous = ubi->free = ubi->scrub = RB_ROOT;
	spin_lock_init(&ubi->wl_lock);
	mutex_init(&ubi->move_mutex);
	init_rwsem(&ubi->work_sem);
	ubi->max_ec = ai->max_ec;
	INIT_LIST_HEAD(&ubi->works);

	sprintf(ubi->bgt_name, UBI_BGT_NAME_PATTERN, ubi->ubi_num);

	err = -ENOMEM;
	ubi->lookuptbl = kcalloc(ubi->peb_count, sizeof(void *), GFP_KERNEL);
	if (!ubi->lookuptbl)
		return err;

	for (i = 0; i < UBI_PROT_QUEUE_LEN; i++)
		INIT_LIST_HEAD(&ubi->pq[i]);
	ubi->pq_head = 0;

	ubi->free_count = 0;
	list_for_each_entry_safe(aeb, tmp, &ai->erase, u.list) {
		cond_resched();

		err = erase_aeb(ubi, aeb, false);
		if (err)
			goto out_free;

		found_pebs++;
	}

	list_for_each_entry(aeb, &ai->free, u.list) {
		cond_resched();

		e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
		if (!e) {
			err = -ENOMEM;
			goto out_free;
		}

		e->pnum = aeb->pnum;
		e->ec = aeb->ec;
		ubi_assert(e->ec >= 0);

		wl_tree_add(e, &ubi->free);
		ubi->free_count++;

		ubi->lookuptbl[e->pnum] = e;

		found_pebs++;
	}

	ubi_rb_for_each_entry(rb1, av, &ai->volumes, rb) {
		ubi_rb_for_each_entry(rb2, aeb, &av->root, u.rb) {
			cond_resched();

			e = kmem_cache_alloc(ubi_wl_entry_slab, GFP_KERNEL);
			if (!e) {
				err = -ENOMEM;
				goto out_free;
			}

			e->pnum = aeb->pnum;
			e->ec = aeb->ec;
			ubi->lookuptbl[e->pnum] = e;

			if (!aeb->scrub) {
				dbg_wl("add PEB %d EC %d to the used tree",
				       e->pnum, e->ec);
				wl_tree_add(e, &ubi->used);
			} else {
				dbg_wl("add PEB %d EC %d to the scrub tree",
				       e->pnum, e->ec);
				wl_tree_add(e, &ubi->scrub);
			}

			found_pebs++;
		}
	}

	list_for_each_entry(aeb, &ai->fastmap, u.list) {
		cond_resched();

		e = ubi_find_fm_block(ubi, aeb->pnum);

		if (e) {
			ubi_assert(!ubi->lookuptbl[e->pnum]);
			ubi->lookuptbl[e->pnum] = e;
		} else {
			bool sync = false;

			/*
			 * Usually old Fastmap PEBs are scheduled for erasure
			 * and we don't have to care about them but if we face
			 * an power cut before scheduling them we need to
			 * take care of them here.
			 */
			if (ubi->lookuptbl[aeb->pnum])
				continue;

			/*
			 * The fastmap update code might not find a free PEB for
			 * writing the fastmap anchor to and then reuses the
			 * current fastmap anchor PEB. When this PEB gets erased
			 * and a power cut happens before it is written again we
			 * must make sure that the fastmap attach code doesn't
			 * find any outdated fastmap anchors, hence we erase the
			 * outdated fastmap anchor PEBs synchronously here.
			 */
			if (aeb->vol_id == UBI_FM_SB_VOLUME_ID)
				sync = true;

			err = erase_aeb(ubi, aeb, sync);
			if (err)
				goto out_free;
		}

		found_pebs++;
	}

	dbg_wl("found %i PEBs", found_pebs);

	ubi_assert(ubi->good_peb_count == found_pebs);

	reserved_pebs = WL_RESERVED_PEBS;
	ubi_fastmap_init(ubi, &reserved_pebs);

	if (ubi->avail_pebs < reserved_pebs) {
		ubi_err(ubi, "no enough physical eraseblocks (%d, need %d)",
			ubi->avail_pebs, reserved_pebs);
		if (ubi->corr_peb_count)
			ubi_err(ubi, "%d PEBs are corrupted and not used",
				ubi->corr_peb_count);
		err = -ENOSPC;
		goto out_free;
	}
	ubi->avail_pebs -= reserved_pebs;
	ubi->rsvd_pebs += reserved_pebs;

	/* Schedule wear-leveling if needed */
	err = ensure_wear_leveling(ubi, 0);
	if (err)
		goto out_free;

#ifdef CONFIG_MTD_UBI_FASTMAP
	if (!ubi->ro_mode && !ubi->fm_disabled)
		ubi_ensure_anchor_pebs(ubi);
#endif
	return 0;

out_free:
	shutdown_work(ubi);
	tree_destroy(ubi, &ubi->used);
	tree_destroy(ubi, &ubi->free);
	tree_destroy(ubi, &ubi->scrub);
	kfree(ubi->lookuptbl);
	return err;
}

/**
 * protection_queue_destroy - destroy the protection queue.
 * @ubi: UBI device description object
 */
static void protection_queue_destroy(struct ubi_device *ubi)
{
	int i;
	struct ubi_wl_entry *e, *tmp;

	for (i = 0; i < UBI_PROT_QUEUE_LEN; ++i) {
		list_for_each_entry_safe(e, tmp, &ubi->pq[i], u.list) {
			list_del(&e->u.list);
			wl_entry_destroy(ubi, e);
		}
	}
}

/**
 * ubi_wl_close - close the wear-leveling sub-system.
 * @ubi: UBI device description object
 */
void ubi_wl_close(struct ubi_device *ubi)
{
	dbg_wl("close the WL sub-system");
	ubi_fastmap_close(ubi);
	shutdown_work(ubi);
	protection_queue_destroy(ubi);
	tree_destroy(ubi, &ubi->used);
	tree_destroy(ubi, &ubi->erroneous);
	tree_destroy(ubi, &ubi->free);
	tree_destroy(ubi, &ubi->scrub);
	kfree(ubi->lookuptbl);
}

/**
 * self_check_ec - make sure that the erase counter of a PEB is correct.
 * @ubi: UBI device description object
 * @pnum: the physical eraseblock number to check
 * @ec: the erase counter to check
 *
 * This function returns zero if the erase counter of physical eraseblock @pnum
 * is equivalent to @ec, and a negative error code if not or if an error
 * occurred.
 */
static int self_check_ec(struct ubi_device *ubi, int pnum, int ec)
{
	int err;
	long long read_ec;
	struct ubi_ec_hdr *ec_hdr;

	if (!ubi_dbg_chk_gen(ubi))
		return 0;

	ec_hdr = kzalloc(ubi->ec_hdr_alsize, GFP_NOFS);
	if (!ec_hdr)
		return -ENOMEM;

	err = ubi_io_read_ec_hdr(ubi, pnum, ec_hdr, 0);
	if (err && err != UBI_IO_BITFLIPS) {
		/* The header does not have to exist */
		err = 0;
		goto out_free;
	}

	read_ec = be64_to_cpu(ec_hdr->ec);
	if (ec != read_ec && read_ec - ec > 1) {
		ubi_err(ubi, "self-check failed for PEB %d", pnum);
		ubi_err(ubi, "read EC is %lld, should be %d", read_ec, ec);
		dump_stack();
		err = 1;
	} else
		err = 0;

out_free:
	kfree(ec_hdr);
	return err;
}

/**
 * self_check_in_wl_tree - check that wear-leveling entry is in WL RB-tree.
 * @ubi: UBI device description object
 * @e: the wear-leveling entry to check
 * @root: the root of the tree
 *
 * This function returns zero if @e is in the @root RB-tree and %-EINVAL if it
 * is not.
 */
static int self_check_in_wl_tree(const struct ubi_device *ubi,
				 struct ubi_wl_entry *e, struct rb_root *root)
{
	if (!ubi_dbg_chk_gen(ubi))
		return 0;

	if (in_wl_tree(e, root))
		return 0;

	ubi_err(ubi, "self-check failed for PEB %d, EC %d, RB-tree %p ",
		e->pnum, e->ec, root);
	dump_stack();
	return -EINVAL;
}

/**
 * self_check_in_pq - check if wear-leveling entry is in the protection
 *                        queue.
 * @ubi: UBI device description object
 * @e: the wear-leveling entry to check
 *
 * This function returns zero if @e is in @ubi->pq and %-EINVAL if it is not.
 */
static int self_check_in_pq(const struct ubi_device *ubi,
			    struct ubi_wl_entry *e)
{
	if (!ubi_dbg_chk_gen(ubi))
		return 0;

	if (in_pq(ubi, e))
		return 0;

	ubi_err(ubi, "self-check failed for PEB %d, EC %d, Protect queue",
		e->pnum, e->ec);
	dump_stack();
	return -EINVAL;
}
#ifndef CONFIG_MTD_UBI_FASTMAP
static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi)
{
	struct ubi_wl_entry *e;

	e = find_wl_entry(ubi, &ubi->free, WL_FREE_MAX_DIFF);
	self_check_in_wl_tree(ubi, e, &ubi->free);
	ubi->free_count--;
	ubi_assert(ubi->free_count >= 0);
	rb_erase(&e->u.rb, &ubi->free);

	return e;
}

/**
 * produce_free_peb - produce a free physical eraseblock.
 * @ubi: UBI device description object
 *
 * This function tries to make a free PEB by means of synchronous execution of
 * pending works. This may be needed if, for example the background thread is
 * disabled. Returns zero in case of success and a negative error code in case
 * of failure.
 */
static int produce_free_peb(struct ubi_device *ubi)
{
	int err;

	while (!ubi->free.rb_node && ubi->works_count) {
		spin_unlock(&ubi->wl_lock);

		dbg_wl("do one work synchronously");
		err = do_work(ubi);

		spin_lock(&ubi->wl_lock);
		if (err)
			return err;
	}

	return 0;
}

/**
 * ubi_wl_get_peb - get a physical eraseblock.
 * @ubi: UBI device description object
 *
 * This function returns a physical eraseblock in case of success and a
 * negative error code in case of failure.
 * Returns with ubi->fm_eba_sem held in read mode!
 */
int ubi_wl_get_peb(struct ubi_device *ubi)
{
	int err;
	struct ubi_wl_entry *e;

retry:
	down_read(&ubi->fm_eba_sem);
	spin_lock(&ubi->wl_lock);
	if (!ubi->free.rb_node) {
		if (ubi->works_count == 0) {
			ubi_err(ubi, "no free eraseblocks");
			ubi_assert(list_empty(&ubi->works));
			spin_unlock(&ubi->wl_lock);
			return -ENOSPC;
		}

		err = produce_free_peb(ubi);
		if (err < 0) {
			spin_unlock(&ubi->wl_lock);
			return err;
		}
		spin_unlock(&ubi->wl_lock);
		up_read(&ubi->fm_eba_sem);
		goto retry;

	}
	e = wl_get_wle(ubi);
	prot_queue_add(ubi, e);
	spin_unlock(&ubi->wl_lock);

	err = ubi_self_check_all_ff(ubi, e->pnum, ubi->vid_hdr_aloffset,
				    ubi->peb_size - ubi->vid_hdr_aloffset);
	if (err) {
		ubi_err(ubi, "new PEB %d does not contain all 0xFF bytes", e->pnum);
		return err;
	}

	return e->pnum;
}
#else
#include "fastmap-wl.c"
#endif