fs/block_dev.c



1da177e4c3f


1da177e4c3f


1da177e4c3f
7db9cfd3802
1da177e4c3f


585d3bc06f4
811d736f9e8
1da177e4c3f


1368c4f2482
2e1483c995b
1da177e4c3f
07f3f05c1e3
1da177e4c3f


4c54ac62dce

1da177e4c3f


f9a14399aea
1da177e4c3f

f9a14399aea


1da177e4c3f


1368c4f2482
1da177e4c3f


e1defc4ff0c
1da177e4c3f


1da177e4c3f


38885bd4c2a
1da177e4c3f


e1defc4ff0c
1da177e4c3f


b2e895dbd80


5cee5815d15


585d3bc06f4


5cee5815d15
585d3bc06f4


60b0680fa23
585d3bc06f4


47e4491b40d
585d3bc06f4


585d3bc06f4


4504230a715


585d3bc06f4
4504230a715


4b06e5b9ad8

585d3bc06f4


4504230a715


585d3bc06f4

4504230a715
585d3bc06f4
4504230a715
585d3bc06f4

4fadd7bb20a
585d3bc06f4


4504230a715
585d3bc06f4

4504230a715


4b06e5b9ad8
4504230a715


585d3bc06f4
585d3bc06f4

4b06e5b9ad8
4504230a715


4504230a715


585d3bc06f4


1da177e4c3f


6272b5a5868


1da177e4c3f
6272b5a5868


1da177e4c3f

6272b5a5868


1da177e4c3f
6272b5a5868


1da177e4c3f


0f7fc9e4d03
1da177e4c3f


1b1dcc1b57a
1da177e4c3f


1b1dcc1b57a
1da177e4c3f


ab0a9735e06


1da177e4c3f


e18b890bb08
1da177e4c3f


e94b1766097
1da177e4c3f


1da177e4c3f


51cc50685a4
1da177e4c3f


a35afb830f8

a35afb830f8

641dc636b04
a35afb830f8
641dc636b04
a35afb830f8
fcccf502540

1da177e4c3f


ee9b6d61a2a
1da177e4c3f


454e2398be9

1da177e4c3f
454e2398be9
1da177e4c3f


c2acf7b9082
1da177e4c3f


c2acf7b9082

1da177e4c3f
fffb60f93ce

20c2df83d25
1da177e4c3f


1da177e4c3f

2e1483c995b


1da177e4c3f


c2acf7b9082
1da177e4c3f


dddac6a7b44


1da177e4c3f

203a2935c73
1da177e4c3f

203a2935c73
1da177e4c3f


09d967c6f32
1da177e4c3f

09d967c6f32

1da177e4c3f


09d967c6f32
1da177e4c3f


09d967c6f32


1da177e4c3f


09d967c6f32

1da177e4c3f
09d967c6f32
c2acf7b9082
09d967c6f32
1da177e4c3f
09d967c6f32
1da177e4c3f
09d967c6f32


1da177e4c3f


641dc636b04


4d7dd8fd955
641dc636b04

4d7dd8fd955

641dc636b04


0762b8bde97
641dc636b04


4c46501d165
641dc636b04


df6c0cd9a87


36a561d6a95

df6c0cd9a87


641dc636b04


df6c0cd9a87
641dc636b04
df6c0cd9a87

641dc636b04


4e91672c763
641dc636b04

4d7dd8fd955
641dc636b04
641dc636b04
4d7dd8fd955
641dc636b04
4e91672c763


4d7dd8fd955
4e91672c763


641dc636b04


4e91672c763
df6c0cd9a87
641dc636b04


2e7b651df11
df6c0cd9a87
4e91672c763

4210df283cc
4e91672c763


4210df283cc
4e91672c763


4210df283cc


b4cf1b72eec
4210df283cc
4e91672c763
641dc636b04


641dc636b04


2e7b651df11
641dc636b04
4210df283cc
b4cf1b72eec
641dc636b04


1da177e4c3f


aeb5d727062
1da177e4c3f


1da177e4c3f
572c4892157
1da177e4c3f


0c002c2f74e
56ade44b467


57d1b5366f4
c3279d1454c


608aeef17a9
c3279d1454c


57d1b5366f4
0c002c2f74e


c3279d1454c
0c002c2f74e


c3279d1454c


0c002c2f74e


1da177e4c3f


83d5cde47de
1da177e4c3f


56ade44b467
1da177e4c3f

1da177e4c3f


e1defc4ff0c
1da177e4c3f


9a1c3542768
37be41241f4
6d740cd5b18


572c4892157
1da177e4c3f
1da177e4c3f
7db9cfd3802
cf771cb5a7b
fe6e9c1f25a

572c4892157
fe6e9c1f25a
572c4892157
fe6e9c1f25a


8266602033d

7db9cfd3802
8266602033d
7db9cfd3802
1da177e4c3f
d3374825ce5
0762b8bde97
89f97496e81
cf771cb5a7b
0762b8bde97

1da177e4c3f
6796bf54a64
1da177e4c3f


cf771cb5a7b
1da177e4c3f
89f97496e81


1da177e4c3f
572c4892157
d3374825ce5


1da177e4c3f
0762b8bde97
1da177e4c3f


1da177e4c3f


0762b8bde97
37be41241f4
572c4892157
1da177e4c3f
0762b8bde97
1da177e4c3f
1da177e4c3f

89f97496e81
e71bf0d0ee8
89f97496e81
1da177e4c3f
0762b8bde97
1da177e4c3f
89f97496e81
1da177e4c3f

0762b8bde97
960cc0f4fef
0762b8bde97
1da177e4c3f

572c4892157
1da177e4c3f
0762b8bde97
1da177e4c3f


1da177e4c3f


37be41241f4

c039e3134ae
1da177e4c3f


0762b8bde97
89f97496e81
1da177e4c3f
0762b8bde97
1da177e4c3f

572c4892157
1da177e4c3f
0762b8bde97
c039e3134ae
0762b8bde97
1da177e4c3f
0762b8bde97
0762b8bde97


1da177e4c3f


572c4892157
1da177e4c3f
572c4892157
37be41241f4
1da177e4c3f


572c4892157


1da177e4c3f
6a2aae06cc1

1da177e4c3f
572c4892157


1da177e4c3f


ebbefc011e5


1da177e4c3f
ebbefc011e5
1da177e4c3f
ebbefc011e5
9a1c3542768
1da177e4c3f


9a1c3542768
2e7b651df11

2e7b651df11
37be41241f4
2e7b651df11
6796bf54a64
2e7b651df11
37be41241f4


2e7b651df11


9a1c3542768
2e7b651df11


0762b8bde97

2e7b651df11

37be41241f4

2e7b651df11


37be41241f4
9a1c3542768
2e7b651df11


9a1c3542768
37be41241f4
9a1c3542768
37be41241f4
2e7b651df11

1da177e4c3f


9a1c3542768
1da177e4c3f

bb93e3a52f8
1da177e4c3f
56b26add02b

fd4ce1acd0f


56b26add02b
fd4ce1acd0f


56b26add02b
1da177e4c3f

87d8fe1ee6b
eef99380679


87d8fe1ee6b


4c54ac62dce
1da177e4c3f


6272b5a5868

1da177e4c3f
87d8fe1ee6b
1da177e4c3f


4b6f5d20b04
1da177e4c3f


543ade1fc90

1da177e4c3f
eef99380679
1da177e4c3f

bb93e3a52f8
1da177e4c3f


7f9c51f0d97

1da177e4c3f


56b26add02b
1da177e4c3f


94e2959e7a6
1da177e4c3f
57d1b5366f4
1da177e4c3f


421748ecde8
1da177e4c3f


421748ecde8
1da177e4c3f

421748ecde8
1da177e4c3f

421748ecde8
1da177e4c3f


421748ecde8
1da177e4c3f


421748ecde8
1da177e4c3f


421748ecde8
1da177e4c3f


d5686b444ff
1da177e4c3f

30c40d2c01f
1da177e4c3f

30c40d2c01f
1da177e4c3f


30c40d2c01f
1da177e4c3f

1da177e4c3f


572c4892157
1da177e4c3f


30c40d2c01f
1da177e4c3f


9a1c3542768
1da177e4c3f


30c40d2c01f
1da177e4c3f

30c40d2c01f
1da177e4c3f

30c40d2c01f
1da177e4c3f
30c40d2c01f
1da177e4c3f
30c40d2c01f
1da177e4c3f

30c40d2c01f
1da177e4c3f

30c40d2c01f
b71e8a4ce03


f98393a64ca
b71e8a4ce03


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


/*
 *  linux/fs/block_dev.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *  Copyright (C) 2001  Andrea Arcangeli <andrea@suse.de> SuSE
 */

#include <linux/init.h>
#include <linux/mm.h>
#include <linux/fcntl.h>
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/major.h>
#include <linux/smp_lock.h>
#include <linux/device_cgroup.h>
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/buffer_head.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/mpage.h>
#include <linux/mount.h>
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/log2.h>
#include <linux/kmemleak.h>
#include <asm/uaccess.h>
#include "internal.h"

struct bdev_inode {
	struct block_device bdev;
	struct inode vfs_inode;
};

static const struct address_space_operations def_blk_aops;

static inline struct bdev_inode *BDEV_I(struct inode *inode)
{
	return container_of(inode, struct bdev_inode, vfs_inode);
}

inline struct block_device *I_BDEV(struct inode *inode)
{
	return &BDEV_I(inode)->bdev;
}

EXPORT_SYMBOL(I_BDEV);

static sector_t max_block(struct block_device *bdev)
{
	sector_t retval = ~((sector_t)0);
	loff_t sz = i_size_read(bdev->bd_inode);

	if (sz) {
		unsigned int size = block_size(bdev);
		unsigned int sizebits = blksize_bits(size);
		retval = (sz >> sizebits);
	}
	return retval;
}

/* Kill _all_ buffers and pagecache , dirty or not.. */
static void kill_bdev(struct block_device *bdev)
{
	if (bdev->bd_inode->i_mapping->nrpages == 0)
		return;
	invalidate_bh_lrus();
	truncate_inode_pages(bdev->bd_inode->i_mapping, 0);
}	

int set_blocksize(struct block_device *bdev, int size)
{
	/* Size must be a power of two, and between 512 and PAGE_SIZE */
	if (size > PAGE_SIZE || size < 512 || !is_power_of_2(size))
		return -EINVAL;

	/* Size cannot be smaller than the size supported by the device */
	if (size < bdev_logical_block_size(bdev))
		return -EINVAL;

	/* Don't change the size if it is same as current */
	if (bdev->bd_block_size != size) {
		sync_blockdev(bdev);
		bdev->bd_block_size = size;
		bdev->bd_inode->i_blkbits = blksize_bits(size);
		kill_bdev(bdev);
	}
	return 0;
}

EXPORT_SYMBOL(set_blocksize);

int sb_set_blocksize(struct super_block *sb, int size)
{
	if (set_blocksize(sb->s_bdev, size))
		return 0;
	/* If we get here, we know size is power of two
	 * and it's value is between 512 and PAGE_SIZE */
	sb->s_blocksize = size;
	sb->s_blocksize_bits = blksize_bits(size);
	return sb->s_blocksize;
}

EXPORT_SYMBOL(sb_set_blocksize);

int sb_min_blocksize(struct super_block *sb, int size)
{
	int minsize = bdev_logical_block_size(sb->s_bdev);
	if (size < minsize)
		size = minsize;
	return sb_set_blocksize(sb, size);
}

EXPORT_SYMBOL(sb_min_blocksize);

static int
blkdev_get_block(struct inode *inode, sector_t iblock,
		struct buffer_head *bh, int create)
{
	if (iblock >= max_block(I_BDEV(inode))) {
		if (create)
			return -EIO;

		/*
		 * for reads, we're just trying to fill a partial page.
		 * return a hole, they will have to call get_block again
		 * before they can fill it, and they will get -EIO at that
		 * time
		 */
		return 0;
	}
	bh->b_bdev = I_BDEV(inode);
	bh->b_blocknr = iblock;
	set_buffer_mapped(bh);
	return 0;
}

static int
blkdev_get_blocks(struct inode *inode, sector_t iblock,
		struct buffer_head *bh, int create)
{
	sector_t end_block = max_block(I_BDEV(inode));
	unsigned long max_blocks = bh->b_size >> inode->i_blkbits;

	if ((iblock + max_blocks) > end_block) {
		max_blocks = end_block - iblock;
		if ((long)max_blocks <= 0) {
			if (create)
				return -EIO;	/* write fully beyond EOF */
			/*
			 * It is a read which is fully beyond EOF.  We return
			 * a !buffer_mapped buffer
			 */
			max_blocks = 0;
		}
	}

	bh->b_bdev = I_BDEV(inode);
	bh->b_blocknr = iblock;
	bh->b_size = max_blocks << inode->i_blkbits;
	if (max_blocks)
		set_buffer_mapped(bh);
	return 0;
}

static ssize_t
blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov,
			loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;

	return blockdev_direct_IO_no_locking(rw, iocb, inode, I_BDEV(inode),
				iov, offset, nr_segs, blkdev_get_blocks, NULL);
}

int __sync_blockdev(struct block_device *bdev, int wait)
{
	if (!bdev)
		return 0;
	if (!wait)
		return filemap_flush(bdev->bd_inode->i_mapping);
	return filemap_write_and_wait(bdev->bd_inode->i_mapping);
}

/*
 * Write out and wait upon all the dirty data associated with a block
 * device via its mapping.  Does not take the superblock lock.
 */
int sync_blockdev(struct block_device *bdev)
{
	return __sync_blockdev(bdev, 1);
}
EXPORT_SYMBOL(sync_blockdev);

/*
 * Write out and wait upon all dirty data associated with this
 * device.   Filesystem data as well as the underlying block
 * device.  Takes the superblock lock.
 */
int fsync_bdev(struct block_device *bdev)
{
	struct super_block *sb = get_super(bdev);
	if (sb) {
		int res = sync_filesystem(sb);
		drop_super(sb);
		return res;
	}
	return sync_blockdev(bdev);
}
EXPORT_SYMBOL(fsync_bdev);

/**
 * freeze_bdev  --  lock a filesystem and force it into a consistent state
 * @bdev:	blockdevice to lock
 *
 * If a superblock is found on this device, we take the s_umount semaphore
 * on it to make sure nobody unmounts until the snapshot creation is done.
 * The reference counter (bd_fsfreeze_count) guarantees that only the last
 * unfreeze process can unfreeze the frozen filesystem actually when multiple
 * freeze requests arrive simultaneously. It counts up in freeze_bdev() and
 * count down in thaw_bdev(). When it becomes 0, thaw_bdev() will unfreeze
 * actually.
 */
struct super_block *freeze_bdev(struct block_device *bdev)
{
	struct super_block *sb;
	int error = 0;

	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (++bdev->bd_fsfreeze_count > 1) {
		/*
		 * We don't even need to grab a reference - the first call
		 * to freeze_bdev grab an active reference and only the last
		 * thaw_bdev drops it.
		 */
		sb = get_super(bdev);
		drop_super(sb);
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return sb;
	}

	sb = get_active_super(bdev);
	if (!sb)
		goto out;
	if (sb->s_flags & MS_RDONLY) {
		sb->s_frozen = SB_FREEZE_TRANS;
		up_write(&sb->s_umount);
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return sb;
	}

	sb->s_frozen = SB_FREEZE_WRITE;
	smp_wmb();

	sync_filesystem(sb);

	sb->s_frozen = SB_FREEZE_TRANS;
	smp_wmb();

	sync_blockdev(sb->s_bdev);

	if (sb->s_op->freeze_fs) {
		error = sb->s_op->freeze_fs(sb);
		if (error) {
			printk(KERN_ERR
				"VFS:Filesystem freeze failed\n");
			sb->s_frozen = SB_UNFROZEN;
			deactivate_locked_super(sb);
			bdev->bd_fsfreeze_count--;
			mutex_unlock(&bdev->bd_fsfreeze_mutex);
			return ERR_PTR(error);
		}
	}
	up_write(&sb->s_umount);

 out:
	sync_blockdev(bdev);
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return sb;	/* thaw_bdev releases s->s_umount */
}
EXPORT_SYMBOL(freeze_bdev);

/**
 * thaw_bdev  -- unlock filesystem
 * @bdev:	blockdevice to unlock
 * @sb:		associated superblock
 *
 * Unlocks the filesystem and marks it writeable again after freeze_bdev().
 */
int thaw_bdev(struct block_device *bdev, struct super_block *sb)
{
	int error = -EINVAL;

	mutex_lock(&bdev->bd_fsfreeze_mutex);
	if (!bdev->bd_fsfreeze_count)
		goto out_unlock;

	error = 0;
	if (--bdev->bd_fsfreeze_count > 0)
		goto out_unlock;

	if (!sb)
		goto out_unlock;

	BUG_ON(sb->s_bdev != bdev);
	down_write(&sb->s_umount);
	if (sb->s_flags & MS_RDONLY)
		goto out_unfrozen;

	if (sb->s_op->unfreeze_fs) {
		error = sb->s_op->unfreeze_fs(sb);
		if (error) {
			printk(KERN_ERR
				"VFS:Filesystem thaw failed\n");
			sb->s_frozen = SB_FREEZE_TRANS;
			bdev->bd_fsfreeze_count++;
			mutex_unlock(&bdev->bd_fsfreeze_mutex);
			return error;
		}
	}

out_unfrozen:
	sb->s_frozen = SB_UNFROZEN;
	smp_wmb();
	wake_up(&sb->s_wait_unfrozen);

	if (sb)
		deactivate_locked_super(sb);
out_unlock:
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return 0;
}
EXPORT_SYMBOL(thaw_bdev);

static int blkdev_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page, blkdev_get_block, wbc);
}

static int blkdev_readpage(struct file * file, struct page * page)
{
	return block_read_full_page(page, blkdev_get_block);
}

static int blkdev_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	*pagep = NULL;
	return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
				blkdev_get_block);
}

static int blkdev_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	int ret;
	ret = block_write_end(file, mapping, pos, len, copied, page, fsdata);

	unlock_page(page);
	page_cache_release(page);

	return ret;
}

/*
 * private llseek:
 * for a block special file file->f_path.dentry->d_inode->i_size is zero
 * so we compute the size by hand (just as in block_read/write above)
 */
static loff_t block_llseek(struct file *file, loff_t offset, int origin)
{
	struct inode *bd_inode = file->f_mapping->host;
	loff_t size;
	loff_t retval;

	mutex_lock(&bd_inode->i_mutex);
	size = i_size_read(bd_inode);

	switch (origin) {
		case 2:
			offset += size;
			break;
		case 1:
			offset += file->f_pos;
	}
	retval = -EINVAL;
	if (offset >= 0 && offset <= size) {
		if (offset != file->f_pos) {
			file->f_pos = offset;
		}
		retval = offset;
	}
	mutex_unlock(&bd_inode->i_mutex);
	return retval;
}
	
/*
 *	Filp is never NULL; the only case when ->fsync() is called with
 *	NULL first argument is nfsd_sync_dir() and that's not a directory.
 */
 
static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
{
	struct block_device *bdev = I_BDEV(filp->f_mapping->host);
	int error;

	error = sync_blockdev(bdev);
	if (error)
		return error;
	
	error = blkdev_issue_flush(bdev, NULL);
	if (error == -EOPNOTSUPP)
		error = 0;
	return error;
}

/*
 * pseudo-fs
 */

static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
static struct kmem_cache * bdev_cachep __read_mostly;

static struct inode *bdev_alloc_inode(struct super_block *sb)
{
	struct bdev_inode *ei = kmem_cache_alloc(bdev_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void bdev_destroy_inode(struct inode *inode)
{
	struct bdev_inode *bdi = BDEV_I(inode);

	kmem_cache_free(bdev_cachep, bdi);
}

static void init_once(void *foo)
{
	struct bdev_inode *ei = (struct bdev_inode *) foo;
	struct block_device *bdev = &ei->bdev;

	memset(bdev, 0, sizeof(*bdev));
	mutex_init(&bdev->bd_mutex);
	INIT_LIST_HEAD(&bdev->bd_inodes);
	INIT_LIST_HEAD(&bdev->bd_list);
#ifdef CONFIG_SYSFS
	INIT_LIST_HEAD(&bdev->bd_holder_list);
#endif
	inode_init_once(&ei->vfs_inode);
	/* Initialize mutex for freeze. */
	mutex_init(&bdev->bd_fsfreeze_mutex);
}

static inline void __bd_forget(struct inode *inode)
{
	list_del_init(&inode->i_devices);
	inode->i_bdev = NULL;
	inode->i_mapping = &inode->i_data;
}

static void bdev_clear_inode(struct inode *inode)
{
	struct block_device *bdev = &BDEV_I(inode)->bdev;
	struct list_head *p;
	spin_lock(&bdev_lock);
	while ( (p = bdev->bd_inodes.next) != &bdev->bd_inodes ) {
		__bd_forget(list_entry(p, struct inode, i_devices));
	}
	list_del_init(&bdev->bd_list);
	spin_unlock(&bdev_lock);
}

static const struct super_operations bdev_sops = {
	.statfs = simple_statfs,
	.alloc_inode = bdev_alloc_inode,
	.destroy_inode = bdev_destroy_inode,
	.drop_inode = generic_delete_inode,
	.clear_inode = bdev_clear_inode,
};

static int bd_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	return get_sb_pseudo(fs_type, "bdev:", &bdev_sops, 0x62646576, mnt);
}

static struct file_system_type bd_type = {
	.name		= "bdev",
	.get_sb		= bd_get_sb,
	.kill_sb	= kill_anon_super,
};

struct super_block *blockdev_superblock __read_mostly;

void __init bdev_cache_init(void)
{
	int err;
	struct vfsmount *bd_mnt;

	bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
			0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
				SLAB_MEM_SPREAD|SLAB_PANIC),
			init_once);
	err = register_filesystem(&bd_type);
	if (err)
		panic("Cannot register bdev pseudo-fs");
	bd_mnt = kern_mount(&bd_type);
	if (IS_ERR(bd_mnt))
		panic("Cannot create bdev pseudo-fs");
	/*
	 * This vfsmount structure is only used to obtain the
	 * blockdev_superblock, so tell kmemleak not to report it.
	 */
	kmemleak_not_leak(bd_mnt);
	blockdev_superblock = bd_mnt->mnt_sb;	/* For writeback */
}

/*
 * Most likely _very_ bad one - but then it's hardly critical for small
 * /dev and can be fixed when somebody will need really large one.
 * Keep in mind that it will be fed through icache hash function too.
 */
static inline unsigned long hash(dev_t dev)
{
	return MAJOR(dev)+MINOR(dev);
}

static int bdev_test(struct inode *inode, void *data)
{
	return BDEV_I(inode)->bdev.bd_dev == *(dev_t *)data;
}

static int bdev_set(struct inode *inode, void *data)
{
	BDEV_I(inode)->bdev.bd_dev = *(dev_t *)data;
	return 0;
}

static LIST_HEAD(all_bdevs);

struct block_device *bdget(dev_t dev)
{
	struct block_device *bdev;
	struct inode *inode;

	inode = iget5_locked(blockdev_superblock, hash(dev),
			bdev_test, bdev_set, &dev);

	if (!inode)
		return NULL;

	bdev = &BDEV_I(inode)->bdev;

	if (inode->i_state & I_NEW) {
		bdev->bd_contains = NULL;
		bdev->bd_inode = inode;
		bdev->bd_block_size = (1 << inode->i_blkbits);
		bdev->bd_part_count = 0;
		bdev->bd_invalidated = 0;
		inode->i_mode = S_IFBLK;
		inode->i_rdev = dev;
		inode->i_bdev = bdev;
		inode->i_data.a_ops = &def_blk_aops;
		mapping_set_gfp_mask(&inode->i_data, GFP_USER);
		inode->i_data.backing_dev_info = &default_backing_dev_info;
		spin_lock(&bdev_lock);
		list_add(&bdev->bd_list, &all_bdevs);
		spin_unlock(&bdev_lock);
		unlock_new_inode(inode);
	}
	return bdev;
}

EXPORT_SYMBOL(bdget);

/**
 * bdgrab -- Grab a reference to an already referenced block device
 * @bdev:	Block device to grab a reference to.
 */
struct block_device *bdgrab(struct block_device *bdev)
{
	atomic_inc(&bdev->bd_inode->i_count);
	return bdev;
}

long nr_blockdev_pages(void)
{
	struct block_device *bdev;
	long ret = 0;
	spin_lock(&bdev_lock);
	list_for_each_entry(bdev, &all_bdevs, bd_list) {
		ret += bdev->bd_inode->i_mapping->nrpages;
	}
	spin_unlock(&bdev_lock);
	return ret;
}

void bdput(struct block_device *bdev)
{
	iput(bdev->bd_inode);
}

EXPORT_SYMBOL(bdput);
 
static struct block_device *bd_acquire(struct inode *inode)
{
	struct block_device *bdev;

	spin_lock(&bdev_lock);
	bdev = inode->i_bdev;
	if (bdev) {
		atomic_inc(&bdev->bd_inode->i_count);
		spin_unlock(&bdev_lock);
		return bdev;
	}
	spin_unlock(&bdev_lock);

	bdev = bdget(inode->i_rdev);
	if (bdev) {
		spin_lock(&bdev_lock);
		if (!inode->i_bdev) {
			/*
			 * We take an additional bd_inode->i_count for inode,
			 * and it's released in clear_inode() of inode.
			 * So, we can access it via ->i_mapping always
			 * without igrab().
			 */
			atomic_inc(&bdev->bd_inode->i_count);
			inode->i_bdev = bdev;
			inode->i_mapping = bdev->bd_inode->i_mapping;
			list_add(&inode->i_devices, &bdev->bd_inodes);
		}
		spin_unlock(&bdev_lock);
	}
	return bdev;
}

/* Call when you free inode */

void bd_forget(struct inode *inode)
{
	struct block_device *bdev = NULL;

	spin_lock(&bdev_lock);
	if (inode->i_bdev) {
		if (!sb_is_blkdev_sb(inode->i_sb))
			bdev = inode->i_bdev;
		__bd_forget(inode);
	}
	spin_unlock(&bdev_lock);

	if (bdev)
		iput(bdev->bd_inode);
}

int bd_claim(struct block_device *bdev, void *holder)
{
	int res;
	spin_lock(&bdev_lock);

	/* first decide result */
	if (bdev->bd_holder == holder)
		res = 0;	 /* already a holder */
	else if (bdev->bd_holder != NULL)
		res = -EBUSY; 	 /* held by someone else */
	else if (bdev->bd_contains == bdev)
		res = 0;  	 /* is a whole device which isn't held */

	else if (bdev->bd_contains->bd_holder == bd_claim)
		res = 0; 	 /* is a partition of a device that is being partitioned */
	else if (bdev->bd_contains->bd_holder != NULL)
		res = -EBUSY;	 /* is a partition of a held device */
	else
		res = 0;	 /* is a partition of an un-held device */

	/* now impose change */
	if (res==0) {
		/* note that for a whole device bd_holders
		 * will be incremented twice, and bd_holder will
		 * be set to bd_claim before being set to holder
		 */
		bdev->bd_contains->bd_holders ++;
		bdev->bd_contains->bd_holder = bd_claim;
		bdev->bd_holders++;
		bdev->bd_holder = holder;
	}
	spin_unlock(&bdev_lock);
	return res;
}

EXPORT_SYMBOL(bd_claim);

void bd_release(struct block_device *bdev)
{
	spin_lock(&bdev_lock);
	if (!--bdev->bd_contains->bd_holders)