summaryrefslogtreecommitdiff
path: root/fs/block_dev.c
blob: 4afa4d5ff969e962bd16cc454904af0de20d5467 (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
/*
 *  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/device_cgroup.h>
#include <linux/highmem.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/blkpg.h>
#include <linux/magic.h>
#include <linux/dax.h>
#include <linux/buffer_head.h>
#include <linux/swap.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/cleancache.h>
#include <linux/dax.h>
#include <linux/badblocks.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/falloc.h>
#include <linux/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);
}

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

static void bdev_write_inode(struct block_device *bdev)
{
	struct inode *inode = bdev->bd_inode;
	int ret;

	spin_lock(&inode->i_lock);
	while (inode->i_state & I_DIRTY) {
		spin_unlock(&inode->i_lock);
		ret = write_inode_now(inode, true);
		if (ret) {
			char name[BDEVNAME_SIZE];
			pr_warn_ratelimited("VFS: Dirty inode writeback failed "
					    "for block device %s (err=%d).\n",
					    bdevname(bdev, name), ret);
		}
		spin_lock(&inode->i_lock);
	}
	spin_unlock(&inode->i_lock);
}

/* Kill _all_ buffers and pagecache , dirty or not.. */
void kill_bdev(struct block_device *bdev)
{
	struct address_space *mapping = bdev->bd_inode->i_mapping;

	if (mapping->nrpages == 0 && mapping->nrexceptional == 0)
		return;

	invalidate_bh_lrus();
	truncate_inode_pages(mapping, 0);
}	
EXPORT_SYMBOL(kill_bdev);

/* Invalidate clean unused buffers and pagecache. */
void invalidate_bdev(struct block_device *bdev)
{
	struct address_space *mapping = bdev->bd_inode->i_mapping;

	if (mapping->nrpages) {
		invalidate_bh_lrus();
		lru_add_drain_all();	/* make sure all lru add caches are flushed */
		invalidate_mapping_pages(mapping, 0, -1);
	}
	/* 99% of the time, we don't need to flush the cleancache on the bdev.
	 * But, for the strange corners, lets be cautious
	 */
	cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(invalidate_bdev);

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)
{
	bh->b_bdev = I_BDEV(inode);
	bh->b_blocknr = iblock;
	set_buffer_mapped(bh);
	return 0;
}

static struct inode *bdev_file_inode(struct file *file)
{
	return file->f_mapping->host;
}

static unsigned int dio_bio_write_op(struct kiocb *iocb)
{
	unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE;

	/* avoid the need for a I/O completion work item */
	if (iocb->ki_flags & IOCB_DSYNC)
		op |= REQ_FUA;
	return op;
}

#define DIO_INLINE_BIO_VECS 4

static void blkdev_bio_end_io_simple(struct bio *bio)
{
	struct task_struct *waiter = bio->bi_private;

	WRITE_ONCE(bio->bi_private, NULL);
	wake_up_process(waiter);
}

static ssize_t
__blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
		int nr_pages)
{
	struct file *file = iocb->ki_filp;
	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
	struct bio_vec inline_vecs[DIO_INLINE_BIO_VECS], *vecs, *bvec;
	loff_t pos = iocb->ki_pos;
	bool should_dirty = false;
	struct bio bio;
	ssize_t ret;
	blk_qc_t qc;
	int i;

	if ((pos | iov_iter_alignment(iter)) &
	    (bdev_logical_block_size(bdev) - 1))
		return -EINVAL;

	if (nr_pages <= DIO_INLINE_BIO_VECS)
		vecs = inline_vecs;
	else {
		vecs = kmalloc(nr_pages * sizeof(struct bio_vec), GFP_KERNEL);
		if (!vecs)
			return -ENOMEM;
	}

	bio_init(&bio, vecs, nr_pages);
	bio_set_dev(&bio, bdev);
	bio.bi_iter.bi_sector = pos >> 9;
	bio.bi_write_hint = iocb->ki_hint;
	bio.bi_private = current;
	bio.bi_end_io = blkdev_bio_end_io_simple;

	ret = bio_iov_iter_get_pages(&bio, iter);
	if (unlikely(ret))
		return ret;
	ret = bio.bi_iter.bi_size;

	if (iov_iter_rw(iter) == READ) {
		bio.bi_opf = REQ_OP_READ;
		if (iter_is_iovec(iter))
			should_dirty = true;
	} else {
		bio.bi_opf = dio_bio_write_op(iocb);
		task_io_account_write(ret);
	}

	qc = submit_bio(&bio);
	for (;;) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		if (!READ_ONCE(bio.bi_private))
			break;
		if (!(iocb->ki_flags & IOCB_HIPRI) ||
		    !blk_poll(bdev_get_queue(bdev), qc))
			io_schedule();
	}
	__set_current_state(TASK_RUNNING);

	bio_for_each_segment_all(bvec, &bio, i) {
		if (should_dirty && !PageCompound(bvec->bv_page))
			set_page_dirty_lock(bvec->bv_page);
		put_page(bvec->bv_page);
	}

	if (vecs != inline_vecs)
		kfree(vecs);

	if (unlikely(bio.bi_status))
		ret = blk_status_to_errno(bio.bi_status);

	bio_uninit(&bio);

	return ret;
}

struct blkdev_dio {
	union {
		struct kiocb		*iocb;
		struct task_struct	*waiter;
	};
	size_t			size;
	atomic_t		ref;
	bool			multi_bio : 1;
	bool			should_dirty : 1;
	bool			is_sync : 1;
	struct bio		bio;
};

static struct bio_set *blkdev_dio_pool __read_mostly;

static void blkdev_bio_end_io(struct bio *bio)
{
	struct blkdev_dio *dio = bio->bi_private;
	bool should_dirty = dio->should_dirty;

	if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) {
		if (bio->bi_status && !dio->bio.bi_status)
			dio->bio.bi_status = bio->bi_status;
	} else {
		if (!dio->is_sync) {
			struct kiocb *iocb = dio->iocb;
			ssize_t ret;

			if (likely(!dio->bio.bi_status)) {
				ret = dio->size;
				iocb->ki_pos += ret;
			} else {
				ret = blk_status_to_errno(dio->bio.bi_status);
			}

			dio->iocb->ki_complete(iocb, ret, 0);
			bio_put(&dio->bio);
		} else {
			struct task_struct *waiter = dio->waiter;

			WRITE_ONCE(dio->waiter, NULL);
			wake_up_process(waiter);
		}
	}

	if (should_dirty) {
		bio_check_pages_dirty(bio);
	} else {
		struct bio_vec *bvec;
		int i;

		bio_for_each_segment_all(bvec, bio, i)
			put_page(bvec->bv_page);
		bio_put(bio);
	}
}

static ssize_t
__blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = bdev_file_inode(file);
	struct block_device *bdev = I_BDEV(inode);
	struct blk_plug plug;
	struct blkdev_dio *dio;
	struct bio *bio;
	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
	loff_t pos = iocb->ki_pos;
	blk_qc_t qc = BLK_QC_T_NONE;
	int ret = 0;

	if ((pos | iov_iter_alignment(iter)) &
	    (bdev_logical_block_size(bdev) - 1))
		return -EINVAL;

	bio = bio_alloc_bioset(GFP_KERNEL, nr_pages, blkdev_dio_pool);
	bio_get(bio); /* extra ref for the completion handler */

	dio = container_of(bio, struct blkdev_dio, bio);
	dio->is_sync = is_sync = is_sync_kiocb(iocb);
	if (dio->is_sync)
		dio->waiter = current;
	else
		dio->iocb = iocb;

	dio->size = 0;
	dio->multi_bio = false;
	dio->should_dirty = is_read && (iter->type == ITER_IOVEC);

	blk_start_plug(&plug);
	for (;;) {
		bio_set_dev(bio, bdev);
		bio->bi_iter.bi_sector = pos >> 9;
		bio->bi_write_hint = iocb->ki_hint;
		bio->bi_private = dio;
		bio->bi_end_io = blkdev_bio_end_io;

		ret = bio_iov_iter_get_pages(bio, iter);
		if (unlikely(ret)) {
			bio->bi_status = BLK_STS_IOERR;
			bio_endio(bio);
			break;
		}

		if (is_read) {
			bio->bi_opf = REQ_OP_READ;
			if (dio->should_dirty)
				bio_set_pages_dirty(bio);
		} else {
			bio->bi_opf = dio_bio_write_op(iocb);
			task_io_account_write(bio->bi_iter.bi_size);
		}

		dio->size += bio->bi_iter.bi_size;
		pos += bio->bi_iter.bi_size;

		nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES);
		if (!nr_pages) {
			qc = submit_bio(bio);
			break;
		}

		if (!dio->multi_bio) {
			dio->multi_bio = true;
			atomic_set(&dio->ref, 2);
		} else {
			atomic_inc(&dio->ref);
		}

		submit_bio(bio);
		bio = bio_alloc(GFP_KERNEL, nr_pages);
	}
	blk_finish_plug(&plug);

	if (!is_sync)
		return -EIOCBQUEUED;

	for (;;) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		if (!READ_ONCE(dio->waiter))
			break;

		if (!(iocb->ki_flags & IOCB_HIPRI) ||
		    !blk_poll(bdev_get_queue(bdev), qc))
			io_schedule();
	}
	__set_current_state(TASK_RUNNING);

	if (!ret)
		ret = blk_status_to_errno(dio->bio.bi_status);
	if (likely(!ret))
		ret = dio->size;

	bio_put(&dio->bio);
	return ret;
}

static ssize_t
blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
	int nr_pages;

	nr_pages = iov_iter_npages(iter, BIO_MAX_PAGES + 1);
	if (!nr_pages)
		return 0;
	if (is_sync_kiocb(iocb) && nr_pages <= BIO_MAX_PAGES)
		return __blkdev_direct_IO_simple(iocb, iter, nr_pages);

	return __blkdev_direct_IO(iocb, iter, min(nr_pages, BIO_MAX_PAGES));
}

static __init int blkdev_init(void)
{
	blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
	if (!blkdev_dio_pool)
		return -ENOMEM;
	return 0;
}
module_init(blkdev_init);

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);
		if (sb)
			drop_super(sb);
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return sb;
	}

	sb = get_active_super(bdev);
	if (!sb)
		goto out;
	if (sb->s_op->freeze_super)
		error = sb->s_op->freeze_super(sb);
	else
		error = freeze_super(sb);
	if (error) {
		deactivate_super(sb);
		bdev->bd_fsfreeze_count--;
		mutex_unlock(&bdev->bd_fsfreeze_mutex);
		return ERR_PTR(error);
	}
	deactivate_super(sb);
 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;

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

	if (!sb)
		goto out;

	if (sb->s_op->thaw_super)
		error = sb->s_op->thaw_super(sb);
	else
		error = thaw_super(sb);
	if (error)
		bdev->bd_fsfreeze_count++;
out:
	mutex_unlock(&bdev->bd_fsfreeze_mutex);
	return error;
}
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_readpages(struct file *file, struct address_space *mapping,
			struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, 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)
{
	return block_write_begin(mapping, pos, len, flags, pagep,
				 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);
	put_page(page);

	return ret;
}

/*
 * private llseek:
 * for a block special file file_inode(file)->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 whence)
{
	struct inode *bd_inode = bdev_file_inode(file);
	loff_t retval;

	inode_lock(bd_inode);
	retval = fixed_size_llseek(file, offset, whence, i_size_read(bd_inode));
	inode_unlock(bd_inode);
	return retval;
}
	
int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
{
	struct inode *bd_inode = bdev_file_inode(filp);
	struct block_device *bdev = I_BDEV(bd_inode);
	int error;
	
	error = file_write_and_wait_range(filp, start, end);
	if (error)
		return error;

	/*
	 * There is no need to serialise calls to blkdev_issue_flush with
	 * i_mutex and doing so causes performance issues with concurrent
	 * O_SYNC writers to a block device.
	 */
	error = blkdev_issue_flush(bdev, GFP_KERNEL, NULL);
	if (error == -EOPNOTSUPP)
		error = 0;

	return error;
}
EXPORT_SYMBOL(blkdev_fsync);

/**
 * bdev_read_page() - Start reading a page from a block device
 * @bdev: The device to read the page from
 * @sector: The offset on the device to read the page to (need not be aligned)
 * @page: The page to read
 *
 * On entry, the page should be locked.  It will be unlocked when the page
 * has been read.  If the block driver implements rw_page synchronously,
 * that will be true on exit from this function, but it need not be.
 *
 * Errors returned by this function are usually "soft", eg out of memory, or
 * queue full; callers should try a different route to read this page rather
 * than propagate an error back up the stack.
 *
 * Return: negative errno if an error occurs, 0 if submission was successful.
 */
int bdev_read_page(struct block_device *bdev, sector_t sector,
			struct page *page)
{
	const struct block_device_operations *ops = bdev->bd_disk->fops;
	int result = -EOPNOTSUPP;

	if (!ops->rw_page || bdev_get_integrity(bdev))
		return result;

	result = blk_queue_enter(bdev->bd_queue, false);
	if (result)
		return result;
	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
	blk_queue_exit(bdev->bd_queue);
	return result;
}
EXPORT_SYMBOL_GPL(bdev_read_page);

/**
 * bdev_write_page() - Start writing a page to a block device
 * @bdev: The device to write the page to
 * @sector: The offset on the device to write the page to (need not be aligned)
 * @page: The page to write
 * @wbc: The writeback_control for the write
 *
 * On entry, the page should be locked and not currently under writeback.
 * On exit, if the write started successfully, the page will be unlocked and
 * under writeback.  If the write failed already (eg the driver failed to
 * queue the page to the device), the page will still be locked.  If the
 * caller is a ->writepage implementation, it will need to unlock the page.
 *
 * Errors returned by this function are usually "soft", eg out of memory, or
 * queue full; callers should try a different route to write this page rather
 * than propagate an error back up the stack.
 *
 * Return: negative errno if an error occurs, 0 if submission was successful.
 */
int bdev_write_page(struct block_device *bdev, sector_t sector,
			struct page *page, struct writeback_control *wbc)
{
	int result;
	const struct block_device_operations *ops = bdev->bd_disk->fops;

	if (!ops->rw_page || bdev_get_integrity(bdev))
		return -EOPNOTSUPP;
	result = blk_queue_enter(bdev->bd_queue, false);
	if (result)
		return result;

	set_page_writeback(page);
	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
	if (result)
		end_page_writeback(page);
	else
		unlock_page(page);
	blk_queue_exit(bdev->bd_queue);
	return result;
}
EXPORT_SYMBOL_GPL(bdev_write_page);

/*
 * 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_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	struct bdev_inode *bdi = BDEV_I(inode);

	kmem_cache_free(bdev_cachep, bdi);
}

static void bdev_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, bdev_i_callback);
}

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_list);
#ifdef CONFIG_SYSFS
	INIT_LIST_HEAD(&bdev->bd_holder_disks);
#endif
	bdev->bd_bdi = &noop_backing_dev_info;
	inode_init_once(&ei->vfs_inode);
	/* Initialize mutex for freeze. */
	mutex_init(&bdev->bd_fsfreeze_mutex);
}

static void bdev_evict_inode(struct inode *inode)
{
	struct block_device *bdev = &BDEV_I(inode)->bdev;
	truncate_inode_pages_final(&inode->i_data);
	invalidate_inode_buffers(inode); /* is it needed here? */
	clear_inode(inode);
	spin_lock(&bdev_lock);
	list_del_init(&bdev->bd_list);
	spin_unlock(&bdev_lock);
	/* Detach inode from wb early as bdi_put() may free bdi->wb */
	inode_detach_wb(inode);
	if (bdev->bd_bdi != &noop_backing_dev_info) {
		bdi_put(bdev->bd_bdi);
		bdev->bd_bdi = &noop_backing_dev_info;
	}
}

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,
	.evict_inode = bdev_evict_inode,
};

static struct dentry *bd_mount(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data)
{
	struct dentry *dent;
	dent = mount_pseudo(fs_type, "bdev:", &bdev_sops, NULL, BDEVFS_MAGIC);
	if (!IS_ERR(dent))
		dent->d_sb->s_iflags |= SB_I_CGROUPWB;
	return dent;
}

static struct file_system_type bd_type = {
	.name		= "bdev",
	.mount		= bd_mount,
	.kill_sb	= kill_anon_super,
};

struct super_block *blockdev_superblock __read_mostly;
EXPORT_SYMBOL_GPL(blockdev_superblock);

void __init bdev_cache_init(void)
{
	int err;
	static 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_ACCOUNT|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");
	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);

/*
 * If there is a bdev inode for this device, unhash it so that it gets evicted
 * as soon as last inode reference is dropped.
 */
void bdev_unhash_inode(dev_t dev)
{
	struct inode *inode;

	inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev);
	if (inode) {
		remove_inode_hash(inode);
		iput(inode);
	}
}

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_super = NULL;
		bdev->bd_inode = inode;
		bdev->bd_block_size = i_blocksize(inode);
		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);
		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)
{
	ihold(bdev->bd_inode);
	return bdev;
}
EXPORT_SYMBOL(bdgrab);

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 && !inode_unhashed(bdev->bd_inode)) {
		bdgrab(bdev);
		spin_unlock(&bdev_lock);
		return bdev;
	}
	spin_unlock(&bdev_lock);

	/*
	 * i_bdev references block device inode that was already shut down
	 * (corresponding device got removed).  Remove the reference and look
	 * up block device inode again just in case new device got
	 * reestablished under the same device number.
	 */
	if (bdev)
		bd_forget(inode);

	bdev = bdget(inode->i_rdev);
	if (bdev) {
		spin_lock(&bdev_lock);
		if (!inode->i_bdev) {
			/*
			 * We take an additional reference to bd_inode,
			 * and it's released in clear_inode() of inode.
			 * So, we can access it via ->i_mapping always
			 * without igrab().
			 */
			bdgrab(bdev);
			inode->i_bdev = bdev;
			inode->i_mapping = bdev->bd_inode->i_mapping;
		}
		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 (!sb_is_blkdev_sb(inode->i_sb))
		bdev = inode->i_bdev;
	inode->i_bdev = NULL;
	inode->i_mapping = &inode->i_data;
	spin_unlock(&bdev_lock);

	if (bdev)
		bdput(bdev);
}

/**
 * bd_may_claim - test whether a block device can be claimed
 * @bdev: block device of interest
 * @whole: whole block device containing @bdev, may equal @bdev
 * @holder: holder trying to claim @bdev
 *
 * Test whether @bdev can be claimed by @holder.
 *
 * CONTEXT:
 * spin_lock(&bdev_lock).
 *
 * RETURNS:
 * %true if @bdev can be claimed, %false otherwise.
 */
static bool bd_may_claim(struct block_device *bdev, struct block_device *whole,
			 void *holder)
{
	if (bdev->bd_holder == holder)
		return true;	 /* already a holder */
	else if (bdev->bd_holder != NULL)
		return false; 	 /* held by someone else */
	else if (whole == bdev)
		return true;  	 /* is a whole device which isn't held */

	else if (whole->bd_holder == bd_may_claim)
		return true; 	 /* is a partition of a device that is being partitioned */
	else if (whole->bd_holder != NULL)
		return false;	 /* is a partition of a held device */
	else
		return true;	 /* is a partition of an un-held device */
}

/**
 * bd_prepare_to_claim - prepare to claim a block device
 * @bdev: block device of interest
 * @whole: the whole device containing @bdev, may equal @bdev
 * @holder: holder trying to claim @bdev
 *
 * Prepare to claim @bdev.  This function fails if @bdev is already
 * claimed by another holder and waits if another claiming is in
 * progress.  This function doesn't actually claim.  On successful
 * return, the caller has ownership of bd_claiming and bd_holder[s].
 *
 * CONTEXT:
 * spin_lock(&bdev_lock).  Might release bdev_lock, sleep and regrab
 * it multiple times.
 *
 * RETURNS:
 * 0 if @bdev can be claimed, -EBUSY otherwise.
 */
static int bd_prepare_to_claim(struct block_device *bdev,
			       struct block_device *whole, void *holder)
{
retry:
	/* if someone else claimed, fail */
	if (!bd_may_claim(bdev, whole, holder))
		return -EBUSY;

	/* if claiming is already in progress, wait for it to finish */
	if (whole->bd_claiming) {
		wait_queue_head_t *wq = bit_waitqueue(&whole->bd_claiming, 0);
		DEFINE_WAIT(wait);

		prepare_to_wait(wq, &wait, TASK_UNINTERRUPTIBLE);
		spin_unlock(&bdev_lock);
		schedule();
		finish_wait(wq, &wait);
		spin_lock(&bdev_lock);
		goto retry;
	}

	/* yay, all mine */
	return 0;
}

/**
 * bd_start_claiming - start claiming a block device
 * @bdev: block device of interest
 * @holder: holder trying to claim @bdev
 *
 * @bdev is about to be opened exclusively.  Check @bdev can be opened
 * exclusively and mark that an exclusive open is in progress.  Each
 * successful call to this function must be matched with a call to
 * either bd_finish_claiming() or bd_abort_claiming() (which do not
 * fail).
 *
 * This function is used to gain exclusive access to the block device
 * without actually causing other exclusive open attempts to fail. It
 * should be used when the open sequence itself requires exclusive
 * access but may subsequently fail.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Pointer to the block device containing @bdev on success, ERR_PTR()
 * value on failure.
 */
static struct block_device *bd_start_claiming(struct block_device *bdev,
					      void *holder)
{
	struct gendisk *disk;
	struct block_device *whole;
	int partno, err;

	might_sleep();

	/*
	 * @bdev might not have been initialized properly yet, look up
	 * and grab the outer block device the hard way.
	 */
	disk = get_gendisk(bdev->bd_dev, &partno);
	if (!disk)
		return ERR_PTR(-ENXIO);

	/*
	 * Normally, @bdev should equal what's returned from bdget_disk()
	 * if partno is 0; however, some drivers (floppy) use multiple
	 * bdev's for the same physical device and @bdev may be one of the
	 * aliases.  Keep @bdev if partno is 0.  This means claimer
	 * tracking is broken for those devices but it has always been that
	 * way.
	 */
	if (partno)
		whole = bdget_disk(disk, 0);
	else
		whole = bdgrab(bdev);

	module_put(disk->fops->owner);
	put_disk(disk);
	if (!whole)
		return ERR_PTR(-ENOMEM);

	/* prepare to claim, if successful, mark claiming in progress */
	spin_lock(&bdev_lock);

	err = bd_prepare_to_claim(bdev, whole, holder);
	if (err == 0) {
		whole->bd_claiming = holder;
		spin_unlock(&bdev_lock);
		return whole;
	} else {
		spin_unlock(&bdev_lock);
		bdput(whole);
		return ERR_PTR(err);
	}
}

#ifdef CONFIG_SYSFS
struct bd_holder_disk {
	struct list_head	list;
	struct gendisk		*disk;
	int			refcnt;
};

static struct bd_holder_disk *bd_find_holder_disk(struct block_device *bdev,
						  struct gendisk *disk)
{
	struct bd_holder_disk *holder;

	list_for_each_entry(holder, &bdev->bd_holder_disks, list)
		if (holder->disk == disk)
			return holder;
	return NULL;
}

static int add_symlink(struct kobject *from, struct kobject *to)
{
	return sysfs_create_link(from, to, kobject_name(to));
}

static void del_symlink(struct kobject *from, struct kobject *to)
{
	sysfs_remove_link(from, kobject_name(to));
}

/**
 * bd_link_disk_holder - create symlinks between holding disk and slave bdev
 * @bdev: the claimed slave bdev
 * @disk: the holding disk
 *
 * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
 *
 * This functions creates the following sysfs symlinks.
 *
 * - from "slaves" directory of the holder @disk to the claimed @bdev
 * - from "holders" directory of the @bdev to the holder @disk
 *
 * For example, if /dev/dm-0 maps to /dev/sda and disk for dm-0 is
 * passed to bd_link_disk_holder(), then:
 *
 *   /sys/block/dm-0/slaves/sda --> /sys/block/sda
 *   /sys/block/sda/holders/dm-0 --> /sys/block/dm-0
 *
 * The caller must have claimed @bdev before calling this function and
 * ensure that both @bdev and @disk are valid during the creation and
 * lifetime of these symlinks.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk)
{
	struct bd_holder_disk *holder;
	int ret = 0;

	mutex_lock(&bdev->bd_mutex);

	WARN_ON_ONCE(!bdev->bd_holder);

	/* FIXME: remove the following once add_disk() handles errors */
	if (WARN_ON(!disk->slave_dir || !bdev->bd_part->holder_dir))
		goto out_unlock;

	holder = bd_find_holder_disk(bdev, disk);
	if (holder) {
		holder->refcnt++;
		goto out_unlock;
	}

	holder = kzalloc(sizeof(*holder), GFP_KERNEL);
	if (!holder) {
		ret = -ENOMEM;
		goto out_unlock;
	}

	INIT_LIST_HEAD(&holder->list);
	holder->disk = disk;
	holder->refcnt = 1;

	ret = add_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
	if (ret)
		goto out_free;

	ret = add_symlink(bdev->bd_part->holder_dir, &disk_to_dev(disk)->kobj);
	if (ret)
		goto out_del;
	/*
	 * bdev could be deleted beneath us which would implicitly destroy
	 * the holder directory.  Hold on to it.
	 */
	kobject_get(bdev->bd_part->holder_dir);

	list_add(&holder->list, &bdev->bd_holder_disks);
	goto out_unlock;

out_del:
	del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
out_free:
	kfree(holder);
out_unlock:
	mutex_unlock(&bdev->bd_mutex);
	return ret;
}
EXPORT_SYMBOL_GPL(bd_link_disk_holder);

/**
 * bd_unlink_disk_holder - destroy symlinks created by bd_link_disk_holder()
 * @bdev: the calimed slave bdev
 * @disk: the holding disk
 *
 * DON'T USE THIS UNLESS YOU'RE ALREADY USING IT.
 *
 * CONTEXT:
 * Might sleep.
 */
void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk)
{
	struct bd_holder_disk *holder;

	mutex_lock(&bdev->bd_mutex);

	holder = bd_find_holder_disk(bdev, disk);

	if (!WARN_ON_ONCE(holder == NULL) && !--holder->refcnt) {
		del_symlink(disk->slave_dir, &part_to_dev(bdev->bd_part)->kobj);
		del_symlink(bdev->bd_part->holder_dir,
			    &disk_to_dev(disk)->kobj);
		kobject_put(bdev->bd_part->holder_dir);
		list_del_init(&holder->list);
		kfree(holder);
	}

	mutex_unlock(&bdev->bd_mutex);
}
EXPORT_SYMBOL_GPL(bd_unlink_disk_holder);
#endif

/**
 * flush_disk - invalidates all buffer-cache entries on a disk
 *
 * @bdev:      struct block device to be flushed
 * @kill_dirty: flag to guide handling of dirty inodes
 *
 * Invalidates all buffer-cache entries on a disk. It should be called
 * when a disk has been changed -- either by a media change or online
 * resize.
 */
static void flush_disk(struct block_device *bdev, bool kill_dirty)
{
	if (__invalidate_device(bdev, kill_dirty)) {
		printk(KERN_WARNING "VFS: busy inodes on changed media or "
		       "resized disk %s\n",
		       bdev->bd_disk ? bdev->bd_disk->disk_name : "");
	}

	if (!bdev->bd_disk)
		return;
	if (disk_part_scan_enabled(bdev->bd_disk))
		bdev->bd_invalidated = 1;
}

/**
 * check_disk_size_change - checks for disk size change and adjusts bdev size.
 * @disk: struct gendisk to check
 * @bdev: struct bdev to adjust.
 *
 * This routine checks to see if the bdev size does not match the disk size
 * and adjusts it if it differs.
 */
void check_disk_size_change(struct gendisk *disk, struct block_device *bdev)
{
	loff_t disk_size, bdev_size;

	disk_size = (loff_t)get_capacity(disk) << 9;
	bdev_size = i_size_read(bdev->bd_inode);
	if (disk_size != bdev_size) {
		printk(KERN_INFO
		       "%s: detected capacity change from %lld to %lld\n",
		       disk->disk_name, bdev_size, disk_size);
		i_size_write(bdev->bd_inode, disk_size);
		flush_disk(bdev, false);
	}
}
EXPORT_SYMBOL(check_disk_size_change);

/**
 * revalidate_disk - wrapper for lower-level driver's revalidate_disk call-back
 * @disk: struct gendisk to be revalidated
 *
 * This routine is a wrapper for lower-level driver's revalidate_disk
 * call-backs.  It is used to do common pre and post operations needed
 * for all revalidate_disk operations.
 */
int revalidate_disk(struct gendisk *disk)
{
	struct block_device *bdev;
	int ret = 0;

	if (disk->fops->revalidate_disk)
		ret = disk->fops->revalidate_disk(disk);
	bdev = bdget_disk(disk, 0);
	if (!bdev)
		return ret;

	mutex_lock(&bdev->bd_mutex);
	check_disk_size_change(disk, bdev);
	bdev->bd_invalidated = 0;
	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
	return ret;
}
EXPORT_SYMBOL(revalidate_disk);

/*
 * This routine checks whether a removable media has been changed,
 * and invalidates all buffer-cache-entries in that case. This
 * is a relatively slow routine, so we have to try to minimize using
 * it. Thus it is called only upon a 'mount' or 'open'. This
 * is the best way of combining speed and utility, I think.
 * People changing diskettes in the middle of an operation deserve
 * to lose :-)
 */
int check_disk_change(struct block_device *bdev)
{
	struct gendisk *disk = bdev->bd_disk;
	const struct block_device_operations *bdops = disk->fops;
	unsigned int events;

	events = disk_clear_events(disk, DISK_EVENT_MEDIA_CHANGE |
				   DISK_EVENT_EJECT_REQUEST);
	if (!(events & DISK_EVENT_MEDIA_CHANGE))
		return 0;

	flush_disk(bdev, true);
	if (bdops->revalidate_disk)
		bdops->revalidate_disk(bdev->bd_disk);
	return 1;
}

EXPORT_SYMBOL(check_disk_change);

void bd_set_size(struct block_device *bdev, loff_t size)
{
	unsigned bsize = bdev_logical_block_size(bdev);

	inode_lock(bdev->bd_inode);
	i_size_write(bdev->bd_inode, size);
	inode_unlock(bdev->bd_inode);
	while (bsize < PAGE_SIZE) {
		if (size & bsize)
			break;
		bsize <<= 1;
	}
	bdev->bd_block_size = bsize;
	bdev->bd_inode->i_blkbits = blksize_bits(bsize);
}
EXPORT_SYMBOL(bd_set_size);

static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part);

/*
 * bd_mutex locking:
 *
 *  mutex_lock(part->bd_mutex)
 *    mutex_lock_nested(whole->bd_mutex, 1)
 */

static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
{
	struct gendisk *disk;
	struct module *owner;
	int ret;
	int partno;
	int perm = 0;

	if (mode & FMODE_READ)
		perm |= MAY_READ;
	if (mode & FMODE_WRITE)
		perm |= MAY_WRITE;
	/*
	 * hooks: /n/, see "layering violations".
	 */
	if (!for_part) {
		ret = devcgroup_inode_permission(bdev->bd_inode, perm);
		if (ret != 0) {
			bdput(bdev);
			return ret;
		}
	}

 restart:

	ret = -ENXIO;
	disk = get_gendisk(bdev->bd_dev, &partno);
	if (!disk)
		goto out;
	owner = disk->fops->owner;

	disk_block_events(disk);
	mutex_lock_nested(&bdev->bd_mutex, for_part);
	if (!bdev->bd_openers) {
		bdev->bd_disk = disk;
		bdev->bd_queue = disk->queue;
		bdev->bd_contains = bdev;
		bdev->bd_partno = partno;

		if (!partno) {
			ret = -ENXIO;
			bdev->bd_part = disk_get_part(disk, partno);
			if (!bdev->bd_part)
				goto out_clear;

			ret = 0;
			if (disk->fops->open) {
				ret = disk->fops->open(bdev, mode);
				if (ret == -ERESTARTSYS) {
					/* Lost a race with 'disk' being
					 * deleted, try again.
					 * See md.c
					 */
					disk_put_part(bdev->bd_part);
					bdev->bd_part = NULL;
					bdev->bd_disk = NULL;
					bdev->bd_queue = NULL;
					mutex_unlock(&bdev->bd_mutex);
					disk_unblock_events(disk);
					put_disk(disk);
					module_put(owner);
					goto restart;
				}
			}

			if (!ret)
				bd_set_size(bdev,(loff_t)get_capacity(disk)<<9);

			/*
			 * If the device is invalidated, rescan partition
			 * if open succeeded or failed with -ENOMEDIUM.
			 * The latter is necessary to prevent ghost
			 * partitions on a removed medium.
			 */
			if (bdev->bd_invalidated) {
				if (!ret)
					rescan_partitions(disk, bdev);
				else if (ret == -ENOMEDIUM)
					invalidate_partitions(disk, bdev);
			}

			if (ret)
				goto out_clear;
		} else {
			struct block_device *whole;
			whole = bdget_disk(disk, 0);
			ret = -ENOMEM;
			if (!whole)
				goto out_clear;
			BUG_ON(for_part);
			ret = __blkdev_get(whole, mode, 1);
			if (ret)
				goto out_clear;
			bdev->bd_contains = whole;
			bdev->bd_part = disk_get_part(disk, partno);
			if (!(disk->flags & GENHD_FL_UP) ||
			    !bdev->bd_part || !bdev->bd_part->nr_sects) {
				ret = -ENXIO;
				goto out_clear;
			}
			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
		}

		if (bdev->bd_bdi == &noop_backing_dev_info)
			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
	} else {
		if (bdev->bd_contains == bdev) {
			ret = 0;
			if (bdev->bd_disk->fops->open)
				ret = bdev->bd_disk->fops->open(bdev, mode);
			/* the same as first opener case, read comment there */
			if (bdev->bd_invalidated) {
				if (!ret)
					rescan_partitions(bdev->bd_disk, bdev);
				else if (ret == -ENOMEDIUM)
					invalidate_partitions(bdev->bd_disk, bdev);
			}
			if (ret)
				goto out_unlock_bdev;
		}
		/* only one opener holds refs to the module and disk */
		put_disk(disk);
		module_put(owner);
	}
	bdev->bd_openers++;
	if (for_part)
		bdev->bd_part_count++;
	mutex_unlock(&bdev->bd_mutex);
	disk_unblock_events(disk);
	return 0;

 out_clear:
	disk_put_part(bdev->bd_part);
	bdev->bd_disk = NULL;
	bdev->bd_part = NULL;
	bdev->bd_queue = NULL;
	if (bdev != bdev->bd_contains)
		__blkdev_put(bdev->bd_contains, mode, 1);
	bdev->bd_contains = NULL;
 out_unlock_bdev:
	mutex_unlock(&bdev->bd_mutex);
	disk_unblock_events(disk);
	put_disk(disk);
	module_put(owner);
 out:
	bdput(bdev);

	return ret;
}

/**
 * blkdev_get - open a block device
 * @bdev: block_device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open @bdev with @mode.  If @mode includes %FMODE_EXCL, @bdev is
 * open with exclusive access.  Specifying %FMODE_EXCL with %NULL
 * @holder is invalid.  Exclusive opens may nest for the same @holder.
 *
 * On success, the reference count of @bdev is unchanged.  On failure,
 * @bdev is put.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
{
	struct block_device *whole = NULL;
	int res;

	WARN_ON_ONCE((mode & FMODE_EXCL) && !holder);

	if ((mode & FMODE_EXCL) && holder) {
		whole = bd_start_claiming(bdev, holder);
		if (IS_ERR(whole)) {
			bdput(bdev);
			return PTR_ERR(whole);
		}
	}

	res = __blkdev_get(bdev, mode, 0);

	if (whole) {
		struct gendisk *disk = whole->bd_disk;

		/* finish claiming */
		mutex_lock(&bdev->bd_mutex);
		spin_lock(&bdev_lock);

		if (!res) {
			BUG_ON(!bd_may_claim(bdev, whole, holder));
			/*
			 * Note that for a whole device bd_holders
			 * will be incremented twice, and bd_holder
			 * will be set to bd_may_claim before being
			 * set to holder
			 */
			whole->bd_holders++;
			whole->bd_holder = bd_may_claim;
			bdev->bd_holders++;
			bdev->bd_holder = holder;
		}

		/* tell others that we're done */
		BUG_ON(whole->bd_claiming != holder);
		whole->bd_claiming = NULL;
		wake_up_bit(&whole->bd_claiming, 0);

		spin_unlock(&bdev_lock);

		/*
		 * Block event polling for write claims if requested.  Any
		 * write holder makes the write_holder state stick until
		 * all are released.  This is good enough and tracking
		 * individual writeable reference is too fragile given the
		 * way @mode is used in blkdev_get/put().
		 */
		if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
		    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
			bdev->bd_write_holder = true;
			disk_block_events(disk);
		}

		mutex_unlock(&bdev->bd_mutex);
		bdput(whole);
	}

	return res;
}
EXPORT_SYMBOL(blkdev_get);

/**
 * blkdev_get_by_path - open a block device by name
 * @path: path to the block device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open the blockdevice described by the device file at @path.  @mode
 * and @holder are identical to blkdev_get().
 *
 * On success, the returned block_device has reference count of one.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Pointer to block_device on success, ERR_PTR(-errno) on failure.
 */
struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
					void *holder)
{
	struct block_device *bdev;
	int err;

	bdev = lookup_bdev(path);
	if (IS_ERR(bdev))
		return bdev;

	err = blkdev_get(bdev, mode, holder);
	if (err)
		return ERR_PTR(err);

	if ((mode & FMODE_WRITE) && bdev_read_only(bdev)) {
		blkdev_put(bdev, mode);
		return ERR_PTR(-EACCES);
	}

	return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_path);

/**
 * blkdev_get_by_dev - open a block device by device number
 * @dev: device number of block device to open
 * @mode: FMODE_* mask
 * @holder: exclusive holder identifier
 *
 * Open the blockdevice described by device number @dev.  @mode and
 * @holder are identical to blkdev_get().
 *
 * Use it ONLY if you really do not have anything better - i.e. when
 * you are behind a truly sucky interface and all you are given is a
 * device number.  _Never_ to be used for internal purposes.  If you
 * ever need it - reconsider your API.
 *
 * On success, the returned block_device has reference count of one.
 *
 * CONTEXT:
 * Might sleep.
 *
 * RETURNS:
 * Pointer to block_device on success, ERR_PTR(-errno) on failure.
 */
struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder)
{
	struct block_device *bdev;
	int err;

	bdev = bdget(dev);
	if (!bdev)
		return ERR_PTR(-ENOMEM);

	err = blkdev_get(bdev, mode, holder);
	if (err)
		return ERR_PTR(err);

	return bdev;
}
EXPORT_SYMBOL(blkdev_get_by_dev);

static int blkdev_open(struct inode * inode, struct file * filp)
{
	struct block_device *bdev;

	/*
	 * Preserve backwards compatibility and allow large file access
	 * even if userspace doesn't ask for it explicitly. Some mkfs
	 * binary needs it. We might want to drop this workaround
	 * during an unstable branch.
	 */
	filp->f_flags |= O_LARGEFILE;

	filp->f_mode |= FMODE_NOWAIT;

	if (filp->f_flags & O_NDELAY)
		filp->f_mode |= FMODE_NDELAY;
	if (filp->f_flags & O_EXCL)
		filp->f_mode |= FMODE_EXCL;
	if ((filp->f_flags & O_ACCMODE) == 3)
		filp->f_mode |= FMODE_WRITE_IOCTL;

	bdev = bd_acquire(inode);
	if (bdev == NULL)
		return -ENOMEM;

	filp->f_mapping = bdev->bd_inode->i_mapping;
	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);

	return blkdev_get(bdev, filp->f_mode, filp);
}

static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
{
	struct gendisk *disk = bdev->bd_disk;
	struct block_device *victim = NULL;

	mutex_lock_nested(&bdev->bd_mutex, for_part);
	if (for_part)
		bdev->bd_part_count--;

	if (!--bdev->bd_openers) {
		WARN_ON_ONCE(bdev->bd_holders);
		sync_blockdev(bdev);
		kill_bdev(bdev);

		bdev_write_inode(bdev);
	}
	if (bdev->bd_contains == bdev) {
		if (disk->fops->release)
			disk->fops->release(disk, mode);
	}
	if (!bdev->bd_openers) {
		struct module *owner = disk->fops->owner;

		disk_put_part(bdev->bd_part);
		bdev->bd_part = NULL;
		bdev->bd_disk = NULL;
		if (bdev != bdev->bd_contains)
			victim = bdev->bd_contains;
		bdev->bd_contains = NULL;

		put_disk(disk);
		module_put(owner);
	}
	mutex_unlock(&bdev->bd_mutex);
	bdput(bdev);
	if (victim)
		__blkdev_put(victim, mode, 1);
}

void blkdev_put(struct block_device *bdev, fmode_t mode)
{
	mutex_lock(&bdev->bd_mutex);

	if (mode & FMODE_EXCL) {
		bool bdev_free;

		/*
		 * Release a claim on the device.  The holder fields
		 * are protected with bdev_lock.  bd_mutex is to
		 * synchronize disk_holder unlinking.
		 */
		spin_lock(&bdev_lock);

		WARN_ON_ONCE(--bdev->bd_holders < 0);
		WARN_ON_ONCE(--bdev->bd_contains->bd_holders < 0);

		/* bd_contains might point to self, check in a separate step */
		if ((bdev_free = !bdev->bd_holders))
			bdev->bd_holder = NULL;
		if (!bdev->bd_contains->bd_holders)
			bdev->bd_contains->bd_holder = NULL;

		spin_unlock(&bdev_lock);

		/*
		 * If this was the last claim, remove holder link and
		 * unblock evpoll if it was a write holder.
		 */
		if (bdev_free && bdev->bd_write_holder) {
			disk_unblock_events(bdev->bd_disk);
			bdev->bd_write_holder = false;
		}
	}

	/*
	 * Trigger event checking and tell drivers to flush MEDIA_CHANGE
	 * event.  This is to ensure detection of media removal commanded
	 * from userland - e.g. eject(1).
	 */
	disk_flush_events(bdev->bd_disk, DISK_EVENT_MEDIA_CHANGE);

	mutex_unlock(&bdev->bd_mutex);

	__blkdev_put(bdev, mode, 0);
}
EXPORT_SYMBOL(blkdev_put);

static int blkdev_close(struct inode * inode, struct file * filp)
{
	struct block_device *bdev = I_BDEV(bdev_file_inode(filp));
	blkdev_put(bdev, filp->f_mode);
	return 0;
}

static long block_ioctl(struct file *file, unsigned cmd, unsigned long arg)
{
	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
	fmode_t mode = file->f_mode;

	/*
	 * O_NDELAY can be altered using fcntl(.., F_SETFL, ..), so we have
	 * to updated it before every ioctl.
	 */
	if (file->f_flags & O_NDELAY)
		mode |= FMODE_NDELAY;
	else
		mode &= ~FMODE_NDELAY;

	return blkdev_ioctl(bdev, mode, cmd, arg);
}

/*
 * Write data to the block device.  Only intended for the block device itself
 * and the raw driver which basically is a fake block device.
 *
 * Does not take i_mutex for the write and thus is not for general purpose
 * use.
 */
ssize_t blkdev_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *bd_inode = bdev_file_inode(file);
	loff_t size = i_size_read(bd_inode);
	struct blk_plug plug;
	ssize_t ret;

	if (bdev_read_only(I_BDEV(bd_inode)))
		return -EPERM;

	if (!iov_iter_count(from))
		return 0;

	if (iocb->ki_pos >= size)
		return -ENOSPC;

	if ((iocb->ki_flags & (IOCB_NOWAIT | IOCB_DIRECT)) == IOCB_NOWAIT)
		return -EOPNOTSUPP;

	iov_iter_truncate(from, size - iocb->ki_pos);

	blk_start_plug(&plug);
	ret = __generic_file_write_iter(iocb, from);
	if (ret > 0)
		ret = generic_write_sync(iocb, ret);
	blk_finish_plug(&plug);
	return ret;
}
EXPORT_SYMBOL_GPL(blkdev_write_iter);

ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *file = iocb->ki_filp;
	struct inode *bd_inode = bdev_file_inode(file);
	loff_t size = i_size_read(bd_inode);
	loff_t pos = iocb->ki_pos;

	if (pos >= size)
		return 0;

	size -= pos;
	iov_iter_truncate(to, size);
	return generic_file_read_iter(iocb, to);
}
EXPORT_SYMBOL_GPL(blkdev_read_iter);

/*
 * Try to release a page associated with block device when the system
 * is under memory pressure.
 */
static int blkdev_releasepage(struct page *page, gfp_t wait)
{
	struct super_block *super = BDEV_I(page->mapping->host)->bdev.bd_super;

	if (super && super->s_op->bdev_try_to_free_page)
		return super->s_op->bdev_try_to_free_page(super, page, wait);

	return try_to_free_buffers(page);
}

static int blkdev_writepages(struct address_space *mapping,
			     struct writeback_control *wbc)
{
	if (dax_mapping(mapping)) {
		struct block_device *bdev = I_BDEV(mapping->host);

		return dax_writeback_mapping_range(mapping, bdev, wbc);
	}
	return generic_writepages(mapping, wbc);
}

static const struct address_space_operations def_blk_aops = {
	.readpage	= blkdev_readpage,
	.readpages	= blkdev_readpages,
	.writepage	= blkdev_writepage,
	.write_begin	= blkdev_write_begin,
	.write_end	= blkdev_write_end,
	.writepages	= blkdev_writepages,
	.releasepage	= blkdev_releasepage,
	.direct_IO	= blkdev_direct_IO,
	.is_dirty_writeback = buffer_check_dirty_writeback,
};

#define	BLKDEV_FALLOC_FL_SUPPORTED					\
		(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |		\
		 FALLOC_FL_ZERO_RANGE | FALLOC_FL_NO_HIDE_STALE)

static long blkdev_fallocate(struct file *file, int mode, loff_t start,
			     loff_t len)
{
	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
	struct address_space *mapping;
	loff_t end = start + len - 1;
	loff_t isize;
	int error;

	/* Fail if we don't recognize the flags. */
	if (mode & ~BLKDEV_FALLOC_FL_SUPPORTED)
		return -EOPNOTSUPP;

	/* Don't go off the end of the device. */
	isize = i_size_read(bdev->bd_inode);
	if (start >= isize)
		return -EINVAL;
	if (end >= isize) {
		if (mode & FALLOC_FL_KEEP_SIZE) {
			len = isize - start;
			end = start + len - 1;
		} else
			return -EINVAL;
	}

	/*
	 * Don't allow IO that isn't aligned to logical block size.
	 */
	if ((start | len) & (bdev_logical_block_size(bdev) - 1))
		return -EINVAL;

	/* Invalidate the page cache, including dirty pages. */
	mapping = bdev->bd_inode->i_mapping;
	truncate_inode_pages_range(mapping, start, end);

	switch (mode) {
	case FALLOC_FL_ZERO_RANGE:
	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
					    GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
		break;
	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
					     GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
		break;
	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
					     GFP_KERNEL, 0);
		break;
	default:
		return -EOPNOTSUPP;
	}
	if (error)
		return error;

	/*
	 * Invalidate again; if someone wandered in and dirtied a page,
	 * the caller will be given -EBUSY.  The third argument is
	 * inclusive, so the rounding here is safe.
	 */
	return invalidate_inode_pages2_range(mapping,
					     start >> PAGE_SHIFT,
					     end >> PAGE_SHIFT);
}

const struct file_operations def_blk_fops = {
	.open		= blkdev_open,
	.release	= blkdev_close,
	.llseek		= block_llseek,
	.read_iter	= blkdev_read_iter,
	.write_iter	= blkdev_write_iter,
	.mmap		= generic_file_mmap,
	.fsync		= blkdev_fsync,
	.unlocked_ioctl	= block_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= compat_blkdev_ioctl,
#endif
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.fallocate	= blkdev_fallocate,
};

int ioctl_by_bdev(struct block_device *bdev, unsigned cmd, unsigned long arg)
{
	int res;
	mm_segment_t old_fs = get_fs();
	set_fs(KERNEL_DS);
	res = blkdev_ioctl(bdev, 0, cmd, arg);
	set_fs(old_fs);
	return res;
}

EXPORT_SYMBOL(ioctl_by_bdev);

/**
 * lookup_bdev  - lookup a struct block_device by name
 * @pathname:	special file representing the block device
 *
 * Get a reference to the blockdevice at @pathname in the current
 * namespace if possible and return it.  Return ERR_PTR(error)
 * otherwise.
 */
struct block_device *lookup_bdev(const char *pathname)
{
	struct block_device *bdev;
	struct inode *inode;
	struct path path;
	int error;

	if (!pathname || !*pathname)
		return ERR_PTR(-EINVAL);

	error = kern_path(pathname, LOOKUP_FOLLOW, &path);
	if (error)
		return ERR_PTR(error);

	inode = d_backing_inode(path.dentry);
	error = -ENOTBLK;
	if (!S_ISBLK(inode->i_mode))
		goto fail;
	error = -EACCES;
	if (!may_open_dev(&path))
		goto fail;
	error = -ENOMEM;
	bdev = bd_acquire(inode);
	if (!bdev)
		goto fail;
out:
	path_put(&path);
	return bdev;
fail:
	bdev = ERR_PTR(error);
	goto out;
}
EXPORT_SYMBOL(lookup_bdev);

int __invalidate_device(struct block_device *bdev, bool kill_dirty)
{
	struct super_block *sb = get_super(bdev);
	int res = 0;

	if (sb) {
		/*
		 * no need to lock the super, get_super holds the
		 * read mutex so the filesystem cannot go away
		 * under us (->put_super runs with the write lock
		 * hold).
		 */
		shrink_dcache_sb(sb);
		res = invalidate_inodes(sb, kill_dirty);
		drop_super(sb);
	}
	invalidate_bdev(bdev);
	return res;
}
EXPORT_SYMBOL(__invalidate_device);

void iterate_bdevs(void (*func)(struct block_device *, void *), void *arg)
{
	struct inode *inode, *old_inode = NULL;

	spin_lock(&blockdev_superblock->s_inode_list_lock);
	list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) {
		struct address_space *mapping = inode->i_mapping;
		struct block_device *bdev;

		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW) ||
		    mapping->nrpages == 0) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&blockdev_superblock->s_inode_list_lock);
		/*
		 * We hold a reference to 'inode' so it couldn't have been
		 * removed from s_inodes list while we dropped the
		 * s_inode_list_lock  We cannot iput the inode now as we can
		 * be holding the last reference and we cannot iput it under
		 * s_inode_list_lock. So we keep the reference and iput it
		 * later.
		 */
		iput(old_inode);
		old_inode = inode;
		bdev = I_BDEV(inode);

		mutex_lock(&bdev->bd_mutex);
		if (bdev->bd_openers)
			func(bdev, arg);
		mutex_unlock(&bdev->bd_mutex);

		spin_lock(&blockdev_superblock->s_inode_list_lock);
	}
	spin_unlock(&blockdev_superblock->s_inode_list_lock);
	iput(old_inode);
}