summaryrefslogtreecommitdiffstats
path: root/drivers/md/bitmap.c
blob: 06b0ded1ce23071d12c89dd3d379f9925f968c92 (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
/*
 * bitmap.c two-level bitmap (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003
 *
 * bitmap_create  - sets up the bitmap structure
 * bitmap_destroy - destroys the bitmap structure
 *
 * additions, Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.:
 * - added disk storage for bitmap
 * - changes to allow various bitmap chunk sizes
 */

/*
 * Still to do:
 *
 * flush after percent set rather than just time based. (maybe both).
 * wait if count gets too high, wake when it drops to half.
 */

#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/timer.h>
#include <linux/sched.h>
#include <linux/list.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/buffer_head.h>
#include "md.h"
#include "bitmap.h"

/* debug macros */

#define DEBUG 0

#if DEBUG
/* these are for debugging purposes only! */

/* define one and only one of these */
#define INJECT_FAULTS_1 0 /* cause bitmap_alloc_page to fail always */
#define INJECT_FAULTS_2 0 /* cause bitmap file to be kicked when first bit set*/
#define INJECT_FAULTS_3 0 /* treat bitmap file as kicked at init time */
#define INJECT_FAULTS_4 0 /* undef */
#define INJECT_FAULTS_5 0 /* undef */
#define INJECT_FAULTS_6 0

/* if these are defined, the driver will fail! debug only */
#define INJECT_FATAL_FAULT_1 0 /* fail kmalloc, causing bitmap_create to fail */
#define INJECT_FATAL_FAULT_2 0 /* undef */
#define INJECT_FATAL_FAULT_3 0 /* undef */
#endif

//#define DPRINTK PRINTK /* set this NULL to avoid verbose debug output */
#define DPRINTK(x...) do { } while(0)

#ifndef PRINTK
#  if DEBUG > 0
#    define PRINTK(x...) printk(KERN_DEBUG x)
#  else
#    define PRINTK(x...)
#  endif
#endif

static inline char * bmname(struct bitmap *bitmap)
{
	return bitmap->mddev ? mdname(bitmap->mddev) : "mdX";
}


/*
 * just a placeholder - calls kmalloc for bitmap pages
 */
static unsigned char *bitmap_alloc_page(struct bitmap *bitmap)
{
	unsigned char *page;

#ifdef INJECT_FAULTS_1
	page = NULL;
#else
	page = kmalloc(PAGE_SIZE, GFP_NOIO);
#endif
	if (!page)
		printk("%s: bitmap_alloc_page FAILED\n", bmname(bitmap));
	else
		PRINTK("%s: bitmap_alloc_page: allocated page at %p\n",
			bmname(bitmap), page);
	return page;
}

/*
 * for now just a placeholder -- just calls kfree for bitmap pages
 */
static void bitmap_free_page(struct bitmap *bitmap, unsigned char *page)
{
	PRINTK("%s: bitmap_free_page: free page %p\n", bmname(bitmap), page);
	kfree(page);
}

/*
 * check a page and, if necessary, allocate it (or hijack it if the alloc fails)
 *
 * 1) check to see if this page is allocated, if it's not then try to alloc
 * 2) if the alloc fails, set the page's hijacked flag so we'll use the
 *    page pointer directly as a counter
 *
 * if we find our page, we increment the page's refcount so that it stays
 * allocated while we're using it
 */
static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int create)
{
	unsigned char *mappage;

	if (page >= bitmap->pages) {
		/* This can happen if bitmap_start_sync goes beyond
		 * End-of-device while looking for a whole page.
		 * It is harmless.
		 */
		return -EINVAL;
	}


	if (bitmap->bp[page].hijacked) /* it's hijacked, don't try to alloc */
		return 0;

	if (bitmap->bp[page].map) /* page is already allocated, just return */
		return 0;

	if (!create)
		return -ENOENT;

	spin_unlock_irq(&bitmap->lock);

	/* this page has not been allocated yet */

	if ((mappage = bitmap_alloc_page(bitmap)) == NULL) {
		PRINTK("%s: bitmap map page allocation failed, hijacking\n",
			bmname(bitmap));
		/* failed - set the hijacked flag so that we can use the
		 * pointer as a counter */
		spin_lock_irq(&bitmap->lock);
		if (!bitmap->bp[page].map)
			bitmap->bp[page].hijacked = 1;
		goto out;
	}

	/* got a page */

	spin_lock_irq(&bitmap->lock);

	/* recheck the page */

	if (bitmap->bp[page].map || bitmap->bp[page].hijacked) {
		/* somebody beat us to getting the page */
		bitmap_free_page(bitmap, mappage);
		return 0;
	}

	/* no page was in place and we have one, so install it */

	memset(mappage, 0, PAGE_SIZE);
	bitmap->bp[page].map = mappage;
	bitmap->missing_pages--;
out:
	return 0;
}


/* if page is completely empty, put it back on the free list, or dealloc it */
/* if page was hijacked, unmark the flag so it might get alloced next time */
/* Note: lock should be held when calling this */
static void bitmap_checkfree(struct bitmap *bitmap, unsigned long page)
{
	char *ptr;

	if (bitmap->bp[page].count) /* page is still busy */
		return;

	/* page is no longer in use, it can be released */

	if (bitmap->bp[page].hijacked) { /* page was hijacked, undo this now */
		bitmap->bp[page].hijacked = 0;
		bitmap->bp[page].map = NULL;
		return;
	}

	/* normal case, free the page */

#if 0
/* actually ... let's not.  We will probably need the page again exactly when
 * memory is tight and we are flusing to disk
 */
	return;
#else
	ptr = bitmap->bp[page].map;
	bitmap->bp[page].map = NULL;
	bitmap->missing_pages++;
	bitmap_free_page(bitmap, ptr);
	return;
#endif
}


/*
 * bitmap file handling - read and write the bitmap file and its superblock
 */

/*
 * basic page I/O operations
 */

/* IO operations when bitmap is stored near all superblocks */
static struct page *read_sb_page(mddev_t *mddev, long offset,
				 struct page *page,
				 unsigned long index, int size)
{
	/* choose a good rdev and read the page from there */

	mdk_rdev_t *rdev;
	sector_t target;

	if (!page)
		page = alloc_page(GFP_KERNEL);
	if (!page)
		return ERR_PTR(-ENOMEM);

	list_for_each_entry(rdev, &mddev->disks, same_set) {
		if (! test_bit(In_sync, &rdev->flags)
		    || test_bit(Faulty, &rdev->flags))
			continue;

		target = rdev->sb_start + offset + index * (PAGE_SIZE/512);

		if (sync_page_io(rdev->bdev, target,
				 roundup(size, bdev_logical_block_size(rdev->bdev)),
				 page, READ)) {
			page->index = index;
			attach_page_buffers(page, NULL); /* so that free_buffer will
							  * quietly no-op */
			return page;
		}
	}
	return ERR_PTR(-EIO);

}

static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
{
	/* Iterate the disks of an mddev, using rcu to protect access to the
	 * linked list, and raising the refcount of devices we return to ensure
	 * they don't disappear while in use.
	 * As devices are only added or removed when raid_disk is < 0 and
	 * nr_pending is 0 and In_sync is clear, the entries we return will
	 * still be in the same position on the list when we re-enter
	 * list_for_each_continue_rcu.
	 */
	struct list_head *pos;
	rcu_read_lock();
	if (rdev == NULL)
		/* start at the beginning */
		pos = &mddev->disks;
	else {
		/* release the previous rdev and start from there. */
		rdev_dec_pending(rdev, mddev);
		pos = &rdev->same_set;
	}
	list_for_each_continue_rcu(pos, &mddev->disks) {
		rdev = list_entry(pos, mdk_rdev_t, same_set);
		if (rdev->raid_disk >= 0 &&
		    !test_bit(Faulty, &rdev->flags)) {
			/* this is a usable devices */
			atomic_inc(&rdev->nr_pending);
			rcu_read_unlock();
			return rdev;
		}
	}
	rcu_read_unlock();
	return NULL;
}

static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
{
	mdk_rdev_t *rdev = NULL;
	mddev_t *mddev = bitmap->mddev;

	while ((rdev = next_active_rdev(rdev, mddev)) != NULL) {
			int size = PAGE_SIZE;
			if (page->index == bitmap->file_pages-1)
				size = roundup(bitmap->last_page_size,
					       bdev_logical_block_size(rdev->bdev));
			/* Just make sure we aren't corrupting data or
			 * metadata
			 */
			if (bitmap->offset < 0) {
				/* DATA  BITMAP METADATA  */
				if (bitmap->offset
				    + (long)(page->index * (PAGE_SIZE/512))
				    + size/512 > 0)
					/* bitmap runs in to metadata */
					goto bad_alignment;
				if (rdev->data_offset + mddev->dev_sectors
				    > rdev->sb_start + bitmap->offset)
					/* data runs in to bitmap */
					goto bad_alignment;
			} else if (rdev->sb_start < rdev->data_offset) {
				/* METADATA BITMAP DATA */
				if (rdev->sb_start
				    + bitmap->offset
				    + page->index*(PAGE_SIZE/512) + size/512
				    > rdev->data_offset)
					/* bitmap runs in to data */
					goto bad_alignment;
			} else {
				/* DATA METADATA BITMAP - no problems */
			}
			md_super_write(mddev, rdev,
				       rdev->sb_start + bitmap->offset
				       + page->index * (PAGE_SIZE/512),
				       size,
				       page);
	}

	if (wait)
		md_super_wait(mddev);
	return 0;

 bad_alignment:
	rcu_read_unlock();
	return -EINVAL;
}

static void bitmap_file_kick(struct bitmap *bitmap);
/*
 * write out a page to a file
 */
static void write_page(struct bitmap *bitmap, struct page *page, int wait)
{
	struct buffer_head *bh;

	if (bitmap->file == NULL) {
		switch (write_sb_page(bitmap, page, wait)) {
		case -EINVAL:
			bitmap->flags |= BITMAP_WRITE_ERROR;
		}
	} else {

		bh = page_buffers(page);

		while (bh && bh->b_blocknr) {
			atomic_inc(&bitmap->pending_writes);
			set_buffer_locked(bh);
			set_buffer_mapped(bh);
			submit_bh(WRITE, bh);
			bh = bh->b_this_page;
		}

		if (wait) {
			wait_event(bitmap->write_wait,
				   atomic_read(&bitmap->pending_writes)==0);
		}
	}
	if (bitmap->flags & BITMAP_WRITE_ERROR)
		bitmap_file_kick(bitmap);
}

static void end_bitmap_write(struct buffer_head *bh, int uptodate)
{
	struct bitmap *bitmap = bh->b_private;
	unsigned long flags;

	if (!uptodate) {
		spin_lock_irqsave(&bitmap->lock, flags);
		bitmap->flags |= BITMAP_WRITE_ERROR;
		spin_unlock_irqrestore(&bitmap->lock, flags);
	}
	if (atomic_dec_and_test(&bitmap->pending_writes))
		wake_up(&bitmap->write_wait);
}

/* copied from buffer.c */
static void
__clear_page_buffers(struct page *page)
{
	ClearPagePrivate(page);
	set_page_private(page, 0);
	page_cache_release(page);
}
static void free_buffers(struct page *page)
{
	struct buffer_head *bh = page_buffers(page);

	while (bh) {
		struct buffer_head *next = bh->b_this_page;
		free_buffer_head(bh);
		bh = next;
	}
	__clear_page_buffers(page);
	put_page(page);
}

/* read a page from a file.
 * We both read the page, and attach buffers to the page to record the
 * address of each block (using bmap).  These addresses will be used
 * to write the block later, completely bypassing the filesystem.
 * This usage is similar to how swap files are handled, and allows us
 * to write to a file with no concerns of memory allocation failing.
 */
static struct page *read_page(struct file *file, unsigned long index,
			      struct bitmap *bitmap,
			      unsigned long count)
{
	struct page *page = NULL;
	struct inode *inode = file->f_path.dentry->d_inode;
	struct buffer_head *bh;
	sector_t block;

	PRINTK("read bitmap file (%dB @ %Lu)\n", (int)PAGE_SIZE,
			(unsigned long long)index << PAGE_SHIFT);

	page = alloc_page(GFP_KERNEL);
	if (!page)
		page = ERR_PTR(-ENOMEM);
	if (IS_ERR(page))
		goto out;

	bh = alloc_page_buffers(page, 1<<inode->i_blkbits, 0);
	if (!bh) {
		put_page(page);
		page = ERR_PTR(-ENOMEM);
		goto out;
	}
	attach_page_buffers(page, bh);
	block = index << (PAGE_SHIFT - inode->i_blkbits);
	while (bh) {
		if (count == 0)
			bh->b_blocknr = 0;
		else {
			bh->b_blocknr = bmap(inode, block);
			if (bh->b_blocknr == 0) {
				/* Cannot use this file! */
				free_buffers(page);
				page = ERR_PTR(-EINVAL);
				goto out;
			}
			bh->b_bdev = inode->i_sb->s_bdev;
			if (count < (1<<inode->i_blkbits))
				count = 0;
			else
				count -= (1<<inode->i_blkbits);

			bh->b_end_io = end_bitmap_write;
			bh->b_private = bitmap;
			atomic_inc(&bitmap->pending_writes);
			set_buffer_locked(bh);
			set_buffer_mapped(bh);
			submit_bh(READ, bh);
		}
		block++;
		bh = bh->b_this_page;
	}
	page->index = index;

	wait_event(bitmap->write_wait,
		   atomic_read(&bitmap->pending_writes)==0);
	if (bitmap->flags & BITMAP_WRITE_ERROR) {
		free_buffers(page);
		page = ERR_PTR(-EIO);
	}
out:
	if (IS_ERR(page))
		printk(KERN_ALERT "md: bitmap read error: (%dB @ %Lu): %ld\n",
			(int)PAGE_SIZE,
			(unsigned long long)index << PAGE_SHIFT,
			PTR_ERR(page));
	return page;
}

/*
 * bitmap file superblock operations
 */

/* update the event counter and sync the superblock to disk */
void bitmap_update_sb(struct bitmap *bitmap)
{
	bitmap_super_t *sb;
	unsigned long flags;

	if (!bitmap || !bitmap->mddev) /* no bitmap for this array */
		return;
	spin_lock_irqsave(&bitmap->lock, flags);
	if (!bitmap->sb_page) { /* no superblock */
		spin_unlock_irqrestore(&bitmap->lock, flags);
		return;
	}
	spin_unlock_irqrestore(&bitmap->lock, flags);
	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
	sb->events = cpu_to_le64(bitmap->mddev->events);
	if (bitmap->mddev->events < bitmap->events_cleared) {
		/* rocking back to read-only */
		bitmap->events_cleared = bitmap->mddev->events;
		sb->events_cleared = cpu_to_le64(bitmap->events_cleared);
	}
	kunmap_atomic(sb, KM_USER0);
	write_page(bitmap, bitmap->sb_page, 1);
}

/* print out the bitmap file superblock */
void bitmap_print_sb(struct bitmap *bitmap)
{
	bitmap_super_t *sb;

	if (!bitmap || !bitmap->sb_page)
		return;
	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
	printk(KERN_DEBUG "%s: bitmap file superblock:\n", bmname(bitmap));
	printk(KERN_DEBUG "         magic: %08x\n", le32_to_cpu(sb->magic));
	printk(KERN_DEBUG "       version: %d\n", le32_to_cpu(sb->version));
	printk(KERN_DEBUG "          uuid: %08x.%08x.%08x.%08x\n",
					*(__u32 *)(sb->uuid+0),
					*(__u32 *)(sb->uuid+4),
					*(__u32 *)(sb->uuid+8),
					*(__u32 *)(sb->uuid+12));
	printk(KERN_DEBUG "        events: %llu\n",
			(unsigned long long) le64_to_cpu(sb->events));
	printk(KERN_DEBUG "events cleared: %llu\n",
			(unsigned long long) le64_to_cpu(sb->events_cleared));
	printk(KERN_DEBUG "         state: %08x\n", le32_to_cpu(sb->state));
	printk(KERN_DEBUG "     chunksize: %d B\n", le32_to_cpu(sb->chunksize));
	printk(KERN_DEBUG "  daemon sleep: %ds\n", le32_to_cpu(sb->daemon_sleep));
	printk(KERN_DEBUG "     sync size: %llu KB\n",
			(unsigned long long)le64_to_cpu(sb->sync_size)/2);
	printk(KERN_DEBUG "max write behind: %d\n", le32_to_cpu(sb->write_behind));
	kunmap_atomic(sb, KM_USER0);
}

/* read the superblock from the bitmap file and initialize some bitmap fields */
static int bitmap_read_sb(struct bitmap *bitmap)
{
	char *reason = NULL;
	bitmap_super_t *sb;
	unsigned long chunksize, daemon_sleep, write_behind;
	unsigned long long events;
	int err = -EINVAL;

	/* page 0 is the superblock, read it... */
	if (bitmap->file) {
		loff_t isize = i_size_read(bitmap->file->f_mapping->host);
		int bytes = isize > PAGE_SIZE ? PAGE_SIZE : isize;

		bitmap->sb_page = read_page(bitmap->file, 0, bitmap, bytes);
	} else {
		bitmap->sb_page = read_sb_page(bitmap->mddev, bitmap->offset,
					       NULL,
					       0, sizeof(bitmap_super_t));
	}
	if (IS_ERR(bitmap->sb_page)) {
		err = PTR_ERR(bitmap->sb_page);
		bitmap->sb_page = NULL;
		return err;
	}

	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);

	chunksize = le32_to_cpu(sb->chunksize);
	daemon_sleep = le32_to_cpu(sb->daemon_sleep);
	write_behind = le32_to_cpu(sb->write_behind);

	/* verify that the bitmap-specific fields are valid */
	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
		reason = "bad magic";
	else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
		 le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
		reason = "unrecognized superblock version";
	else if (chunksize < 512)
		reason = "bitmap chunksize too small";
	else if ((1 << ffz(~chunksize)) != chunksize)
		reason = "bitmap chunksize not a power of 2";
	else if (daemon_sleep < 1 || daemon_sleep > MAX_SCHEDULE_TIMEOUT / HZ)
		reason = "daemon sleep period out of range";
	else if (write_behind > COUNTER_MAX)
		reason = "write-behind limit out of range (0 - 16383)";
	if (reason) {
		printk(KERN_INFO "%s: invalid bitmap file superblock: %s\n",
			bmname(bitmap), reason);
		goto out;
	}

	/* keep the array size field of the bitmap superblock up to date */
	sb->sync_size = cpu_to_le64(bitmap->mddev->resync_max_sectors);

	if (!bitmap->mddev->persistent)
		goto success;

	/*
	 * if we have a persistent array superblock, compare the
	 * bitmap's UUID and event counter to the mddev's
	 */
	if (memcmp(sb->uuid, bitmap->mddev->uuid, 16)) {
		printk(KERN_INFO "%s: bitmap superblock UUID mismatch\n",
			bmname(bitmap));
		goto out;
	}
	events = le64_to_cpu(sb->events);
	if (events < bitmap->mddev->events) {
		printk(KERN_INFO "%s: bitmap file is out of date (%llu < %llu) "
			"-- forcing full recovery\n", bmname(bitmap), events,
			(unsigned long long) bitmap->mddev->events);
		sb->state |= cpu_to_le32(BITMAP_STALE);
	}
success:
	/* assign fields using values from superblock */
	bitmap->chunksize = chunksize;
	bitmap->daemon_sleep = daemon_sleep;
	bitmap->daemon_lastrun = jiffies;
	bitmap->max_write_behind = write_behind;
	bitmap->flags |= le32_to_cpu(sb->state);
	if (le32_to_cpu(sb->version) == BITMAP_MAJOR_HOSTENDIAN)
		bitmap->flags |= BITMAP_HOSTENDIAN;
	bitmap->events_cleared = le64_to_cpu(sb->events_cleared);
	if (sb->state & cpu_to_le32(BITMAP_STALE))
		bitmap->events_cleared = bitmap->mddev->events;
	err = 0;
out:
	kunmap_atomic(sb, KM_USER0);
	if (err)
		bitmap_print_sb(bitmap);
	return err;
}

enum bitmap_mask_op {
	MASK_SET,
	MASK_UNSET
};

/* record the state of the bitmap in the superblock.  Return the old value */
static int bitmap_mask_state(struct bitmap *bitmap, enum bitmap_state bits,
			     enum bitmap_mask_op op)
{
	bitmap_super_t *sb;
	unsigned long flags;
	int old;

	spin_lock_irqsave(&bitmap->lock, flags);
	if (!bitmap->sb_page) { /* can't set the state */
		spin_unlock_irqrestore(&bitmap->lock, flags);
		return 0;
	}
	spin_unlock_irqrestore(&bitmap->lock, flags);
	sb = (bitmap_super_t *)kmap_atomic(bitmap->sb_page, KM_USER0);
	old = le32_to_cpu(sb->state) & bits;
	switch (op) {
		case MASK_SET: sb->state |= cpu_to_le32(bits);
				break;
		case MASK_UNSET: sb->state &= cpu_to_le32(~bits);
				break;
		default: BUG();
	}
	kunmap_atomic(sb, KM_USER0);
	return old;
}

/*
 * general bitmap file operations
 */

/* calculate the index of the page that contains this bit */
static inline unsigned long file_page_index(unsigned long chunk)
{
	return CHUNK_BIT_OFFSET(chunk) >> PAGE_BIT_SHIFT;
}

/* calculate the (bit) offset of this bit within a page */
static inline unsigned long file_page_offset(unsigned long chunk)
{
	return CHUNK_BIT_OFFSET(chunk) & (PAGE_BITS - 1);
}

/*
 * return a pointer to the page in the filemap that contains the given bit
 *
 * this lookup is complicated by the fact that the bitmap sb might be exactly
 * 1 page (e.g., x86) or less than 1 page -- so the bitmap might start on page
 * 0 or page 1
 */
static inline struct page *filemap_get_page(struct bitmap *bitmap,
					unsigned long chunk)
{
	if (file_page_index(chunk) >= bitmap->file_pages) return NULL;
	return bitmap->filemap[file_page_index(chunk) - file_page_index(0)];
}


static void bitmap_file_unmap(struct bitmap *bitmap)
{
	struct page **map, *sb_page;
	unsigned long *attr;
	int pages;
	unsigned long flags;

	spin_lock_irqsave(&bitmap->lock, flags);
	map = bitmap->filemap;
	bitmap->filemap = NULL;
	attr = bitmap->filemap_attr;
	bitmap->filemap_attr = NULL;
	pages = bitmap->file_pages;
	bitmap->file_pages = 0;
	sb_page = bitmap->sb_page;
	bitmap->sb_page = NULL;
	spin_unlock_irqrestore(&bitmap->lock, flags);

	while (pages--)
		if (map[pages]->index != 0) /* 0 is sb_page, release it below */
			free_buffers(map[pages]);
	kfree(map);
	kfree(attr);

	if (sb_page)
		free_buffers(sb_page);
}

static void bitmap_file_put(struct bitmap *bitmap)
{
	struct file *file;
	unsigned long flags;

	spin_lock_irqsave(&bitmap->lock, flags);
	file = bitmap->file;
	bitmap->file = NULL;
	spin_unlock_irqrestore(&bitmap->lock, flags);

	if (file)
		wait_event(bitmap->write_wait,
			   atomic_read(&bitmap->pending_writes)==0);
	bitmap_file_unmap(bitmap);

	if (file) {
		struct inode *inode = file->f_path.dentry->d_inode;
		invalidate_mapping_pages(inode->i_mapping, 0, -1);
		fput(file);
	}
}


/*
 * bitmap_file_kick - if an error occurs while manipulating the bitmap file
 * then it is no longer reliable, so we stop using it and we mark the file
 * as failed in the superblock
 */
static void bitmap_file_kick(struct bitmap *bitmap)
{
	char *path, *ptr = NULL;

	if (bitmap_mask_state(bitmap, BITMAP_STALE, MASK_SET) == 0) {
		bitmap_update_sb(bitmap);

		if (bitmap->file) {
			path = kmalloc(PAGE_SIZE, GFP_KERNEL);
			if (path)
				ptr = d_path(&bitmap->file->f_path, path,
					     PAGE_SIZE);


			printk(KERN_ALERT
			      "%s: kicking failed bitmap file %s from array!\n",
			      bmname(bitmap), IS_ERR(ptr) ? "" : ptr);

			kfree(path);
		} else
			printk(KERN_ALERT
			       "%s: disabling internal bitmap due to errors\n",
			       bmname(bitmap));
	}

	bitmap_file_put(bitmap);

	return;
}

enum bitmap_page_attr {
	BITMAP_PAGE_DIRTY = 0, // there are set bits that need to be synced
	BITMAP_PAGE_CLEAN = 1, // there are bits that might need to be cleared
	BITMAP_PAGE_NEEDWRITE=2, // there are cleared bits that need to be synced
};

static inline void set_page_attr(struct bitmap *bitmap, struct page *page,
				enum bitmap_page_attr attr)
{
	__set_bit((page->index<<2) + attr, bitmap->filemap_attr);
}

static inline void clear_page_attr(struct bitmap *bitmap, struct page *page,
				enum bitmap_page_attr attr)
{
	__clear_bit((page->index<<2) + attr, bitmap->filemap_attr);
}

static inline unsigned long test_page_attr(struct bitmap *bitmap, struct page *page,
					   enum bitmap_page_attr attr)
{
	return test_bit((page->index<<2) + attr, bitmap->filemap_attr);
}

/*
 * bitmap_file_set_bit -- called before performing a write to the md device
 * to set (and eventually sync) a particular bit in the bitmap file
 *
 * we set the bit immediately, then we record the page number so that
 * when an unplug occurs, we can flush the dirty pages out to disk
 */
static void bitmap_file_set_bit(struct bitmap *bitmap, sector_t block)
{
	unsigned long bit;
	struct page *page;
	void *kaddr;
	unsigned long chunk = block >> CHUNK_BLOCK_SHIFT(bitmap);

	if (!bitmap->filemap) {
		return;
	}

	page = filemap_get_page(bitmap, chunk);
	if (!page) return;
	bit = file_page_offset(chunk);

 	/* set the bit */
	kaddr = kmap_atomic(page, KM_USER0);
	if (bitmap->flags & BITMAP_HOSTENDIAN)
		set_bit(bit, kaddr);
	else
		ext2_set_bit(bit, kaddr);
	kunmap_atomic(kaddr, KM_USER0);
	PRINTK("set file bit %lu page %lu\n", bit, page->index);

	/* record page number so it gets flushed to disk when unplug occurs */
	set_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);

}

/* this gets called when the md device is ready to unplug its underlying
 * (slave) device queues -- before we let any writes go down, we need to
 * sync the dirty pages of the bitmap file to disk */
void bitmap_unplug(struct bitmap *bitmap)
{
	unsigned long i, flags;
	int dirty, need_write;
	struct page *page;
	int wait = 0;

	if (!bitmap)
		return;

	/* look at each page to see if there are any set bits that need to be
	 * flushed out to disk */
	for (i = 0; i < bitmap->file_pages; i++) {
		spin_lock_irqsave(&bitmap->lock, flags);
		if (!bitmap->filemap) {
			spin_unlock_irqrestore(&bitmap->lock, flags);
			return;
		}
		page = bitmap->filemap[i];
		dirty = test_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
		need_write = test_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
		clear_page_attr(bitmap, page, BITMAP_PAGE_DIRTY);
		clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);
		if (dirty)
			wait = 1;
		spin_unlock_irqrestore(&bitmap->lock, flags);

		if (dirty | need_write)
			write_page(bitmap, page, 0);
	}
	if (wait) { /* if any writes were performed, we need to wait on them */
		if (bitmap->file)
			wait_event(bitmap->write_wait,
				   atomic_read(&bitmap->pending_writes)==0);
		else
			md_super_wait(bitmap->mddev);
	}
	if (bitmap->flags & BITMAP_WRITE_ERROR)
		bitmap_file_kick(bitmap);
}

static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed);
/* * bitmap_init_from_disk -- called at bitmap_create time to initialize
 * the in-memory bitmap from the on-disk bitmap -- also, sets up the
 * memory mapping of the bitmap file
 * Special cases:
 *   if there's no bitmap file, or if the bitmap file had been
 *   previously kicked from the array, we mark all the bits as
 *   1's in order to cause a full resync.
 *
 * We ignore all bits for sectors that end earlier than 'start'.
 * This is used when reading an out-of-date bitmap...
 */
static int bitmap_init_from_disk(struct bitmap *bitmap, sector_t start)
{
	unsigned long i, chunks, index, oldindex, bit;
	struct page *page = NULL, *oldpage = NULL;
	unsigned long num_pages, bit_cnt = 0;
	struct file *file;
	unsigned long bytes, offset;
	int outofdate;
	int ret = -ENOSPC;
	void *paddr;

	chunks = bitmap->chunks;
	file = bitmap->file;

	BUG_ON(!file && !bitmap->offset);

#ifdef INJECT_FAULTS_3
	outofdate = 1;
#else
	outofdate = bitmap->flags & BITMAP_STALE;
#endif
	if (outofdate)
		printk(KERN_INFO "%s: bitmap file is out of date, doing full "
			"recovery\n", bmname(bitmap));

	bytes = (chunks + 7) / 8;

	num_pages = (bytes + sizeof(bitmap_super_t) + PAGE_SIZE - 1) / PAGE_SIZE;

	if (file && i_size_read(file->f_mapping->host) < bytes + sizeof(bitmap_super_t)) {
		printk(KERN_INFO "%s: bitmap file too short %lu < %lu\n",
			bmname(bitmap),
			(unsigned long) i_size_read(file->f_mapping->host),
			bytes + sizeof(bitmap_super_t));
		goto err;
	}

	ret = -ENOMEM;

	bitmap->filemap = kmalloc(sizeof(struct page *) * num_pages, GFP_KERNEL);
	if (!bitmap->filemap)
		goto err;

	/* We need 4 bits per page, rounded up to a multiple of sizeof(unsigned long) */
	bitmap->filemap_attr = kzalloc(
		roundup( DIV_ROUND_UP(num_pages*4, 8), sizeof(unsigned long)),
		GFP_KERNEL);
	if (!bitmap->filemap_attr)
		goto err;

	oldindex = ~0L;

	for (i = 0; i < chunks; i++) {
		int b;
		index = file_page_index(i);
		bit = file_page_offset(i);
		if (index != oldindex) { /* this is a new page, read it in */
			int count;
			/* unmap the old page, we're done with it */
			if (index == num_pages-1)
				count = bytes + sizeof(bitmap_super_t)
					- index * PAGE_SIZE;
			else
				count = PAGE_SIZE;
			if (index == 0) {
				/*
				 * if we're here then the superblock page
				 * contains some bits (PAGE_SIZE != sizeof sb)
				 * we've already read it in, so just use it
				 */
				page = bitmap->sb_page;
				offset = sizeof(bitmap_super_t);
				if (!file)
					read_sb_page(bitmap->mddev,
						     bitmap->offset,
						     page,
						     index, count);
			} else if (file) {
				page = read_page(file, index, bitmap, count);
				offset = 0;
			} else {
				page = read_sb_page(bitmap->mddev, bitmap->offset,
						    NULL,
						    index, count);
				offset = 0;
			}
			if (IS_ERR(page)) { /* read error */
				ret = PTR_ERR(page);
				goto err;
			}

			oldindex = index;
			oldpage = page;

			bitmap->filemap[bitmap->file_pages++] = page;
			bitmap->last_page_size = count;

			if (outofdate) {
				/*
				 * if bitmap is out of date, dirty the
			 	 * whole page and write it out
				 */
				paddr = kmap_atomic(page, KM_USER0);
				memset(paddr + offset, 0xff,
				       PAGE_SIZE - offset);
				kunmap_atomic(paddr, KM_USER0);
				write_page(bitmap, page, 1);

				ret = -EIO;
				if (bitmap->flags & BITMAP_WRITE_ERROR)
					goto err;
			}
		}
		paddr = kmap_atomic(page, KM_USER0);
		if (bitmap->flags & BITMAP_HOSTENDIAN)
			b = test_bit(bit, paddr);
		else
			b = ext2_test_bit(bit, paddr);
		kunmap_atomic(paddr, KM_USER0);
		if (b) {
			/* if the disk bit is set, set the memory bit */
			int needed = ((sector_t)(i+1) << (CHUNK_BLOCK_SHIFT(bitmap))
				      >= start);
			bitmap_set_memory_bits(bitmap,
					       (sector_t)i << CHUNK_BLOCK_SHIFT(bitmap),
					       needed);
			bit_cnt++;
			set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
		}
	}

 	/* everything went OK */
	ret = 0;
	bitmap_mask_state(bitmap, BITMAP_STALE, MASK_UNSET);

	if (bit_cnt) { /* Kick recovery if any bits were set */
		set_bit(MD_RECOVERY_NEEDED, &bitmap->mddev->recovery);
		md_wakeup_thread(bitmap->mddev->thread);
	}

	printk(KERN_INFO "%s: bitmap initialized from disk: "
		"read %lu/%lu pages, set %lu bits\n",
		bmname(bitmap), bitmap->file_pages, num_pages, bit_cnt);

	return 0;

 err:
	printk(KERN_INFO "%s: bitmap initialisation failed: %d\n",
	       bmname(bitmap), ret);
	return ret;
}

void bitmap_write_all(struct bitmap *bitmap)
{
	/* We don't actually write all bitmap blocks here,
	 * just flag them as needing to be written
	 */
	int i;

	for (i=0; i < bitmap->file_pages; i++)
		set_page_attr(bitmap, bitmap->filemap[i],
			      BITMAP_PAGE_NEEDWRITE);
}


static void bitmap_count_page(struct bitmap *bitmap, sector_t offset, int inc)
{
	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
	bitmap->bp[page].count += inc;
/*
	if (page == 0) printk("count page 0, offset %llu: %d gives %d\n",
			      (unsigned long long)offset, inc, bitmap->bp[page].count);
*/
	bitmap_checkfree(bitmap, page);
}
static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
					    sector_t offset, int *blocks,
					    int create);

/*
 * bitmap daemon -- periodically wakes up to clean bits and flush pages
 *			out to disk
 */

void bitmap_daemon_work(struct bitmap *bitmap)
{
	unsigned long j;
	unsigned long flags;
	struct page *page = NULL, *lastpage = NULL;
	int blocks;
	void *paddr;

	if (bitmap == NULL)
		return;
	if (time_before(jiffies, bitmap->daemon_lastrun + bitmap->daemon_sleep*HZ))
		goto done;

	bitmap->daemon_lastrun = jiffies;
	if (bitmap->allclean) {
		bitmap->mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;
		return;
	}
	bitmap->allclean = 1;

	for (j = 0; j < bitmap->chunks; j++) {
		bitmap_counter_t *bmc;
		spin_lock_irqsave(&bitmap->lock, flags);
		if (!bitmap->filemap) {
			/* error or shutdown */
			spin_unlock_irqrestore(&bitmap->lock, flags);
			break;
		}

		page = filemap_get_page(bitmap, j);

		if (page != lastpage) {
			/* skip this page unless it's marked as needing cleaning */
			if (!test_page_attr(bitmap, page, BITMAP_PAGE_CLEAN)) {
				int need_write = test_page_attr(bitmap, page,
								BITMAP_PAGE_NEEDWRITE);
				if (need_write)
					clear_page_attr(bitmap, page, BITMAP_PAGE_NEEDWRITE);

				spin_unlock_irqrestore(&bitmap->lock, flags);
				if (need_write) {
					write_page(bitmap, page, 0);
					bitmap->allclean = 0;
				}
				continue;
			}

			/* grab the new page, sync and release the old */
			if (lastpage != NULL) {
				if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
					clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
					spin_unlock_irqrestore(&bitmap->lock, flags);
					write_page(bitmap, lastpage, 0);
				} else {
					set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
					spin_unlock_irqrestore(&bitmap->lock, flags);
				}
			} else
				spin_unlock_irqrestore(&bitmap->lock, flags);
			lastpage = page;

			/* We are possibly going to clear some bits, so make
			 * sure that events_cleared is up-to-date.
			 */
			if (bitmap->need_sync) {
				bitmap_super_t *sb;
				bitmap->need_sync = 0;
				sb = kmap_atomic(bitmap->sb_page, KM_USER0);
				sb->events_cleared =
					cpu_to_le64(bitmap->events_cleared);
				kunmap_atomic(sb, KM_USER0);
				write_page(bitmap, bitmap->sb_page, 1);
			}
			spin_lock_irqsave(&bitmap->lock, flags);
			clear_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
		}
		bmc = bitmap_get_counter(bitmap,
					 (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
					 &blocks, 0);
		if (bmc) {
/*
  if (j < 100) printk("bitmap: j=%lu, *bmc = 0x%x\n", j, *bmc);
*/
			if (*bmc)
				bitmap->allclean = 0;

			if (*bmc == 2) {
				*bmc=1; /* maybe clear the bit next time */
				set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
			} else if (*bmc == 1) {
				/* we can clear the bit */
				*bmc = 0;
				bitmap_count_page(bitmap,
						  (sector_t)j << CHUNK_BLOCK_SHIFT(bitmap),
						  -1);

				/* clear the bit */
				paddr = kmap_atomic(page, KM_USER0);
				if (bitmap->flags & BITMAP_HOSTENDIAN)
					clear_bit(file_page_offset(j), paddr);
				else
					ext2_clear_bit(file_page_offset(j), paddr);
				kunmap_atomic(paddr, KM_USER0);
			}
		}
		spin_unlock_irqrestore(&bitmap->lock, flags);
	}

	/* now sync the final page */
	if (lastpage != NULL) {
		spin_lock_irqsave(&bitmap->lock, flags);
		if (test_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE)) {
			clear_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
			spin_unlock_irqrestore(&bitmap->lock, flags);
			write_page(bitmap, lastpage, 0);
		} else {
			set_page_attr(bitmap, lastpage, BITMAP_PAGE_NEEDWRITE);
			spin_unlock_irqrestore(&bitmap->lock, flags);
		}
	}

 done:
	if (bitmap->allclean == 0)
		bitmap->mddev->thread->timeout = bitmap->daemon_sleep * HZ;
}

static bitmap_counter_t *bitmap_get_counter(struct bitmap *bitmap,
					    sector_t offset, int *blocks,
					    int create)
{
	/* If 'create', we might release the lock and reclaim it.
	 * The lock must have been taken with interrupts enabled.
	 * If !create, we don't release the lock.
	 */
	sector_t chunk = offset >> CHUNK_BLOCK_SHIFT(bitmap);
	unsigned long page = chunk >> PAGE_COUNTER_SHIFT;
	unsigned long pageoff = (chunk & PAGE_COUNTER_MASK) << COUNTER_BYTE_SHIFT;
	sector_t csize;

	if (bitmap_checkpage(bitmap, page, create) < 0) {
		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
		*blocks = csize - (offset & (csize- 1));
		return NULL;
	}
	/* now locked ... */

	if (bitmap->bp[page].hijacked) { /* hijacked pointer */
		/* should we use the first or second counter field
		 * of the hijacked pointer? */
		int hi = (pageoff > PAGE_COUNTER_MASK);
		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap) +
					  PAGE_COUNTER_SHIFT - 1);
		*blocks = csize - (offset & (csize- 1));
		return  &((bitmap_counter_t *)
			  &bitmap->bp[page].map)[hi];
	} else { /* page is allocated */
		csize = ((sector_t)1) << (CHUNK_BLOCK_SHIFT(bitmap));
		*blocks = csize - (offset & (csize- 1));
		return (bitmap_counter_t *)
			&(bitmap->bp[page].map[pageoff]);
	}
}

int bitmap_startwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors, int behind)
{
	if (!bitmap) return 0;

	if (behind) {
		atomic_inc(&bitmap->behind_writes);
		PRINTK(KERN_DEBUG "inc write-behind count %d/%d\n",
		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
	}

	while (sectors) {
		int blocks;
		bitmap_counter_t *bmc;

		spin_lock_irq(&bitmap->lock);
		bmc = bitmap_get_counter(bitmap, offset, &blocks, 1);
		if (!bmc) {
			spin_unlock_irq(&bitmap->lock);
			return 0;
		}

		if (unlikely((*bmc & COUNTER_MAX) == COUNTER_MAX)) {
			DEFINE_WAIT(__wait);
			/* note that it is safe to do the prepare_to_wait
			 * after the test as long as we do it before dropping
			 * the spinlock.
			 */
			prepare_to_wait(&bitmap->overflow_wait, &__wait,
					TASK_UNINTERRUPTIBLE);
			spin_unlock_irq(&bitmap->lock);
			blk_unplug(bitmap->mddev->queue);
			schedule();
			finish_wait(&bitmap->overflow_wait, &__wait);
			continue;
		}

		switch(*bmc) {
		case 0:
			bitmap_file_set_bit(bitmap, offset);
			bitmap_count_page(bitmap,offset, 1);
			blk_plug_device_unlocked(bitmap->mddev->queue);
			/* fall through */
		case 1:
			*bmc = 2;
		}

		(*bmc)++;

		spin_unlock_irq(&bitmap->lock);

		offset += blocks;
		if (sectors > blocks)
			sectors -= blocks;
		else sectors = 0;
	}
	bitmap->allclean = 0;
	return 0;
}

void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long sectors,
		     int success, int behind)
{
	if (!bitmap) return;
	if (behind) {
		atomic_dec(&bitmap->behind_writes);
		PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
	}
	if (bitmap->mddev->degraded)
		/* Never clear bits or update events_cleared when degraded */
		success = 0;

	while (sectors) {
		int blocks;
		unsigned long flags;
		bitmap_counter_t *bmc;

		spin_lock_irqsave(&bitmap->lock, flags);
		bmc = bitmap_get_counter(bitmap, offset, &blocks, 0);
		if (!bmc) {
			spin_unlock_irqrestore(&bitmap->lock, flags);
			return;
		}

		if (success &&
		    bitmap->events_cleared < bitmap->mddev->events) {
			bitmap->events_cleared = bitmap->mddev->events;
			bitmap->need_sync = 1;
		}

		if (!success && ! (*bmc & NEEDED_MASK))
			*bmc |= NEEDED_MASK;

		if ((*bmc & COUNTER_MAX) == COUNTER_MAX)
			wake_up(&bitmap->overflow_wait);

		(*bmc)--;
		if (*bmc <= 2) {
			set_page_attr(bitmap,
				      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
				      BITMAP_PAGE_CLEAN);
		}
		spin_unlock_irqrestore(&bitmap->lock, flags);
		offset += blocks;
		if (sectors > blocks)
			sectors -= blocks;
		else sectors = 0;
	}
}

static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
			       int degraded)
{
	bitmap_counter_t *bmc;
	int rv;
	if (bitmap == NULL) {/* FIXME or bitmap set as 'failed' */
		*blocks = 1024;
		return 1; /* always resync if no bitmap */
	}
	spin_lock_irq(&bitmap->lock);
	bmc = bitmap_get_counter(bitmap, offset, blocks, 0);
	rv = 0;
	if (bmc) {
		/* locked */
		if (RESYNC(*bmc))
			rv = 1;
		else if (NEEDED(*bmc)) {
			rv = 1;
			if (!degraded) { /* don't set/clear bits if degraded */
				*bmc |= RESYNC_MASK;
				*bmc &= ~NEEDED_MASK;
			}
		}
	}
	spin_unlock_irq(&bitmap->lock);
	bitmap->allclean = 0;
	return rv;
}

int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
		      int degraded)
{
	/* bitmap_start_sync must always report on multiples of whole
	 * pages, otherwise resync (which is very PAGE_SIZE based) will
	 * get confused.
	 * So call __bitmap_start_sync repeatedly (if needed) until
	 * At least PAGE_SIZE>>9 blocks are covered.
	 * Return the 'or' of the result.
	 */
	int rv = 0;
	int blocks1;

	*blocks = 0;
	while (*blocks < (PAGE_SIZE>>9)) {
		rv |= __bitmap_start_sync(bitmap, offset,
					  &blocks1, degraded);
		offset += blocks1;
		*blocks += blocks1;
	}
	return rv;
}

void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
{
	bitmap_counter_t *bmc;
	unsigned long flags;
/*
	if (offset == 0) printk("bitmap_end_sync 0 (%d)\n", aborted);
*/	if (bitmap == NULL) {
		*blocks = 1024;
		return;
	}
	spin_lock_irqsave(&bitmap->lock, flags);
	bmc = bitmap_get_counter(bitmap, offset, blocks, 0);
	if (bmc == NULL)
		goto unlock;
	/* locked */
/*
	if (offset == 0) printk("bitmap_end sync found 0x%x, blocks %d\n", *bmc, *blocks);
*/
	if (RESYNC(*bmc)) {
		*bmc &= ~RESYNC_MASK;

		if (!NEEDED(*bmc) && aborted)
			*bmc |= NEEDED_MASK;
		else {
			if (*bmc <= 2) {
				set_page_attr(bitmap,
					      filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap)),
					      BITMAP_PAGE_CLEAN);
			}
		}
	}
 unlock:
	spin_unlock_irqrestore(&bitmap->lock, flags);
	bitmap->allclean = 0;
}

void bitmap_close_sync(struct bitmap *bitmap)
{
	/* Sync has finished, and any bitmap chunks that weren't synced
	 * properly have been aborted.  It remains to us to clear the
	 * RESYNC bit wherever it is still on
	 */
	sector_t sector = 0;
	int blocks;
	if (!bitmap)
		return;
	while (sector < bitmap->mddev->resync_max_sectors) {
		bitmap_end_sync(bitmap, sector, &blocks, 0);
		sector += blocks;
	}
}

void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
{
	sector_t s = 0;
	int blocks;

	if (!bitmap)
		return;
	if (sector == 0) {
		bitmap->last_end_sync = jiffies;
		return;
	}
	if (time_before(jiffies, (bitmap->last_end_sync
				  + bitmap->daemon_sleep * HZ)))
		return;
	wait_event(bitmap->mddev->recovery_wait,
		   atomic_read(&bitmap->mddev->recovery_active) == 0);

	bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
	sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
	s = 0;
	while (s < sector && s < bitmap->mddev->resync_max_sectors) {
		bitmap_end_sync(bitmap, s, &blocks, 0);
		s += blocks;
	}
	bitmap->last_end_sync = jiffies;
	sysfs_notify(&bitmap->mddev->kobj, NULL, "sync_completed");
}

static void bitmap_set_memory_bits(struct bitmap *bitmap, sector_t offset, int needed)
{
	/* For each chunk covered by any of these sectors, set the
	 * counter to 1 and set resync_needed.  They should all
	 * be 0 at this point
	 */

	int secs;
	bitmap_counter_t *bmc;
	spin_lock_irq(&bitmap->lock);
	bmc = bitmap_get_counter(bitmap, offset, &secs, 1);
	if (!bmc) {
		spin_unlock_irq(&bitmap->lock);
		return;
	}
	if (! *bmc) {
		struct page *page;
		*bmc = 1 | (needed?NEEDED_MASK:0);
		bitmap_count_page(bitmap, offset, 1);
		page = filemap_get_page(bitmap, offset >> CHUNK_BLOCK_SHIFT(bitmap));
		set_page_attr(bitmap, page, BITMAP_PAGE_CLEAN);
	}
	spin_unlock_irq(&bitmap->lock);
	bitmap->allclean = 0;
}

/* dirty the memory and file bits for bitmap chunks "s" to "e" */
void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e)
{
	unsigned long chunk;

	for (chunk = s; chunk <= e; chunk++) {
		sector_t sec = (sector_t)chunk << CHUNK_BLOCK_SHIFT(bitmap);
		bitmap_set_memory_bits(bitmap, sec, 1);
		bitmap_file_set_bit(bitmap, sec);
	}
}

/*
 * flush out any pending updates
 */
void bitmap_flush(mddev_t *mddev)
{
	struct bitmap *bitmap = mddev->bitmap;
	int sleep;

	if (!bitmap) /* there was no bitmap */
		return;

	/* run the daemon_work three time to ensure everything is flushed
	 * that can be
	 */
	sleep = bitmap->daemon_sleep;
	bitmap->daemon_sleep = 0;
	bitmap_daemon_work(bitmap);
	bitmap_daemon_work(bitmap);
	bitmap_daemon_work(bitmap);
	bitmap->daemon_sleep = sleep;
	bitmap_update_sb(bitmap);
}

/*
 * free memory that was allocated
 */
static void bitmap_free(struct bitmap *bitmap)
{
	unsigned long k, pages;
	struct bitmap_page *bp;

	if (!bitmap) /* there was no bitmap */
		return;

	/* release the bitmap file and kill the daemon */
	bitmap_file_put(bitmap);

	bp = bitmap->bp;
	pages = bitmap->pages;

	/* free all allocated memory */

	if (bp) /* deallocate the page memory */
		for (k = 0; k < pages; k++)
			if (bp[k].map && !bp[k].hijacked)
				kfree(bp[k].map);
	kfree(bp);
	kfree(bitmap);
}
void bitmap_destroy(mddev_t *mddev)
{
	struct bitmap *bitmap = mddev->bitmap;

	if (!bitmap) /* there was no bitmap */
		return;

	mddev->bitmap = NULL; /* disconnect from the md device */
	if (mddev->thread)
		mddev->thread->timeout = MAX_SCHEDULE_TIMEOUT;

	bitmap_free(bitmap);
}

/*
 * initialize the bitmap structure
 * if this returns an error, bitmap_destroy must be called to do clean up
 */
int bitmap_create(mddev_t *mddev)
{
	struct bitmap *bitmap;
	sector_t blocks = mddev->resync_max_sectors;
	unsigned long chunks;
	unsigned long pages;
	struct file *file = mddev->bitmap_file;
	int err;
	sector_t start;

	BUILD_BUG_ON(sizeof(bitmap_super_t) != 256);

	if (!file && !mddev->bitmap_offset) /* bitmap disabled, nothing to do */
		return 0;

	BUG_ON(file && mddev->bitmap_offset);

	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
	if (!bitmap)
		return -ENOMEM;

	spin_lock_init(&bitmap->lock);
	atomic_set(&bitmap->pending_writes, 0);
	init_waitqueue_head(&bitmap->write_wait);
	init_waitqueue_head(&bitmap->overflow_wait);

	bitmap->mddev = mddev;

	bitmap->file = file;
	bitmap->offset = mddev->bitmap_offset;
	if (file) {
		get_file(file);
		do_sync_mapping_range(file->f_mapping, 0, LLONG_MAX,
				      SYNC_FILE_RANGE_WAIT_BEFORE |
				      SYNC_FILE_RANGE_WRITE |
				      SYNC_FILE_RANGE_WAIT_AFTER);
	}
	/* read superblock from bitmap file (this sets bitmap->chunksize) */
	err = bitmap_read_sb(bitmap);
	if (err)
		goto error;

	bitmap->chunkshift = ffz(~bitmap->chunksize);

	/* now that chunksize and chunkshift are set, we can use these macros */
 	chunks = (blocks + CHUNK_BLOCK_RATIO(bitmap) - 1) >>
			CHUNK_BLOCK_SHIFT(bitmap);
 	pages = (chunks + PAGE_COUNTER_RATIO - 1) / PAGE_COUNTER_RATIO;

	BUG_ON(!pages);

	bitmap->chunks = chunks;
	bitmap->pages = pages;
	bitmap->missing_pages = pages;
	bitmap->counter_bits = COUNTER_BITS;

	bitmap->syncchunk = ~0UL;

#ifdef INJECT_FATAL_FAULT_1
	bitmap->bp = NULL;
#else
	bitmap->bp = kzalloc(pages * sizeof(*bitmap->bp), GFP_KERNEL);
#endif
	err = -ENOMEM;
	if (!bitmap->bp)
		goto error;

	/* now that we have some pages available, initialize the in-memory
	 * bitmap from the on-disk bitmap */
	start = 0;
	if (mddev->degraded == 0
	    || bitmap->events_cleared == mddev->events)
		/* no need to keep dirty bits to optimise a re-add of a missing device */
		start = mddev->recovery_cp;
	err = bitmap_init_from_disk(bitmap, start);

	if (err)
		goto error;

	printk(KERN_INFO "created bitmap (%lu pages) for device %s\n",
		pages, bmname(bitmap));

	mddev->bitmap = bitmap;

	mddev->thread->timeout = bitmap->daemon_sleep * HZ;

	bitmap_update_sb(bitmap);

	return (bitmap->flags & BITMAP_WRITE_ERROR) ? -EIO : 0;

 error:
	bitmap_free(bitmap);
	return err;
}

/* the bitmap API -- for raid personalities */
EXPORT_SYMBOL(bitmap_startwrite);
EXPORT_SYMBOL(bitmap_endwrite);
EXPORT_SYMBOL(bitmap_start_sync);
EXPORT_SYMBOL(bitmap_end_sync);
EXPORT_SYMBOL(bitmap_unplug);
EXPORT_SYMBOL(bitmap_close_sync);
EXPORT_SYMBOL(bitmap_cond_end_sync);