summaryrefslogtreecommitdiff
path: root/drivers/block/loop.c
blob: d6b6f434fd4bb7652faf597ef9ab6c7b6dd7c362 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
/*
 *  linux/drivers/block/loop.c
 *
 *  Written by Theodore Ts'o, 3/29/93
 *
 * Copyright 1993 by Theodore Ts'o.  Redistribution of this file is
 * permitted under the GNU General Public License.
 *
 * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993
 * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996
 *
 * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994
 * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996
 *
 * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997
 *
 * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998
 *
 * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998
 *
 * Loadable modules and other fixes by AK, 1998
 *
 * Make real block number available to downstream transfer functions, enables
 * CBC (and relatives) mode encryption requiring unique IVs per data block.
 * Reed H. Petty, rhp@draper.net
 *
 * Maximum number of loop devices now dynamic via max_loop module parameter.
 * Russell Kroll <rkroll@exploits.org> 19990701
 *
 * Maximum number of loop devices when compiled-in now selectable by passing
 * max_loop=<1-255> to the kernel on boot.
 * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999
 *
 * Completely rewrite request handling to be make_request_fn style and
 * non blocking, pushing work to a helper thread. Lots of fixes from
 * Al Viro too.
 * Jens Axboe <axboe@suse.de>, Nov 2000
 *
 * Support up to 256 loop devices
 * Heinz Mauelshagen <mge@sistina.com>, Feb 2002
 *
 * Support for falling back on the write file operation when the address space
 * operations write_begin is not available on the backing filesystem.
 * Anton Altaparmakov, 16 Feb 2005
 *
 * Still To Fix:
 * - Advisory locking is ignored here.
 * - Should use an own CAP_* category instead of CAP_SYS_ADMIN
 *
 */

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/major.h>
#include <linux/wait.h>
#include <linux/blkdev.h>
#include <linux/blkpg.h>
#include <linux/init.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/compat.h>
#include <linux/suspend.h>
#include <linux/freezer.h>
#include <linux/mutex.h>
#include <linux/writeback.h>
#include <linux/completion.h>
#include <linux/highmem.h>
#include <linux/kthread.h>
#include <linux/splice.h>
#include <linux/sysfs.h>
#include <linux/miscdevice.h>
#include <linux/falloc.h>
#include <linux/uio.h>
#include <linux/ioprio.h>

#include "loop.h"

#include <linux/uaccess.h>

static DEFINE_IDR(loop_index_idr);
static DEFINE_MUTEX(loop_index_mutex);

static int max_part;
static int part_shift;

static int transfer_xor(struct loop_device *lo, int cmd,
			struct page *raw_page, unsigned raw_off,
			struct page *loop_page, unsigned loop_off,
			int size, sector_t real_block)
{
	char *raw_buf = kmap_atomic(raw_page) + raw_off;
	char *loop_buf = kmap_atomic(loop_page) + loop_off;
	char *in, *out, *key;
	int i, keysize;

	if (cmd == READ) {
		in = raw_buf;
		out = loop_buf;
	} else {
		in = loop_buf;
		out = raw_buf;
	}

	key = lo->lo_encrypt_key;
	keysize = lo->lo_encrypt_key_size;
	for (i = 0; i < size; i++)
		*out++ = *in++ ^ key[(i & 511) % keysize];

	kunmap_atomic(loop_buf);
	kunmap_atomic(raw_buf);
	cond_resched();
	return 0;
}

static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
{
	if (unlikely(info->lo_encrypt_key_size <= 0))
		return -EINVAL;
	return 0;
}

static struct loop_func_table none_funcs = {
	.number = LO_CRYPT_NONE,
}; 

static struct loop_func_table xor_funcs = {
	.number = LO_CRYPT_XOR,
	.transfer = transfer_xor,
	.init = xor_init
}; 

/* xfer_funcs[0] is special - its release function is never called */
static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
	&none_funcs,
	&xor_funcs
};

static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
{
	loff_t loopsize;

	/* Compute loopsize in bytes */
	loopsize = i_size_read(file->f_mapping->host);
	if (offset > 0)
		loopsize -= offset;
	/* offset is beyond i_size, weird but possible */
	if (loopsize < 0)
		return 0;

	if (sizelimit > 0 && sizelimit < loopsize)
		loopsize = sizelimit;
	/*
	 * Unfortunately, if we want to do I/O on the device,
	 * the number of 512-byte sectors has to fit into a sector_t.
	 */
	return loopsize >> 9;
}

static loff_t get_loop_size(struct loop_device *lo, struct file *file)
{
	return get_size(lo->lo_offset, lo->lo_sizelimit, file);
}

static void __loop_update_dio(struct loop_device *lo, bool dio)
{
	struct file *file = lo->lo_backing_file;
	struct address_space *mapping = file->f_mapping;
	struct inode *inode = mapping->host;
	unsigned short sb_bsize = 0;
	unsigned dio_align = 0;
	bool use_dio;

	if (inode->i_sb->s_bdev) {
		sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
		dio_align = sb_bsize - 1;
	}

	/*
	 * We support direct I/O only if lo_offset is aligned with the
	 * logical I/O size of backing device, and the logical block
	 * size of loop is bigger than the backing device's and the loop
	 * needn't transform transfer.
	 *
	 * TODO: the above condition may be loosed in the future, and
	 * direct I/O may be switched runtime at that time because most
	 * of requests in sane applications should be PAGE_SIZE aligned
	 */
	if (dio) {
		if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
				!(lo->lo_offset & dio_align) &&
				mapping->a_ops->direct_IO &&
				!lo->transfer)
			use_dio = true;
		else
			use_dio = false;
	} else {
		use_dio = false;
	}

	if (lo->use_dio == use_dio)
		return;

	/* flush dirty pages before changing direct IO */
	vfs_fsync(file, 0);

	/*
	 * The flag of LO_FLAGS_DIRECT_IO is handled similarly with
	 * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
	 * will get updated by ioctl(LOOP_GET_STATUS)
	 */
	blk_mq_freeze_queue(lo->lo_queue);
	lo->use_dio = use_dio;
	if (use_dio) {
		blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, lo->lo_queue);
		lo->lo_flags |= LO_FLAGS_DIRECT_IO;
	} else {
		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);
		lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
	}
	blk_mq_unfreeze_queue(lo->lo_queue);
}

static int
figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
{
	loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
	sector_t x = (sector_t)size;
	struct block_device *bdev = lo->lo_device;

	if (unlikely((loff_t)x != size))
		return -EFBIG;
	if (lo->lo_offset != offset)
		lo->lo_offset = offset;
	if (lo->lo_sizelimit != sizelimit)
		lo->lo_sizelimit = sizelimit;
	set_capacity(lo->lo_disk, x);
	bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
	/* let user-space know about the new size */
	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
	return 0;
}

static inline int
lo_do_transfer(struct loop_device *lo, int cmd,
	       struct page *rpage, unsigned roffs,
	       struct page *lpage, unsigned loffs,
	       int size, sector_t rblock)
{
	int ret;

	ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
	if (likely(!ret))
		return 0;

	printk_ratelimited(KERN_ERR
		"loop: Transfer error at byte offset %llu, length %i.\n",
		(unsigned long long)rblock << 9, size);
	return ret;
}

static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
{
	struct iov_iter i;
	ssize_t bw;

	iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len);

	file_start_write(file);
	bw = vfs_iter_write(file, &i, ppos, 0);
	file_end_write(file);

	if (likely(bw ==  bvec->bv_len))
		return 0;

	printk_ratelimited(KERN_ERR
		"loop: Write error at byte offset %llu, length %i.\n",
		(unsigned long long)*ppos, bvec->bv_len);
	if (bw >= 0)
		bw = -EIO;
	return bw;
}

static int lo_write_simple(struct loop_device *lo, struct request *rq,
		loff_t pos)
{
	struct bio_vec bvec;
	struct req_iterator iter;
	int ret = 0;

	rq_for_each_segment(bvec, rq, iter) {
		ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos);
		if (ret < 0)
			break;
		cond_resched();
	}

	return ret;
}

/*
 * This is the slow, transforming version that needs to double buffer the
 * data as it cannot do the transformations in place without having direct
 * access to the destination pages of the backing file.
 */
static int lo_write_transfer(struct loop_device *lo, struct request *rq,
		loff_t pos)
{
	struct bio_vec bvec, b;
	struct req_iterator iter;
	struct page *page;
	int ret = 0;

	page = alloc_page(GFP_NOIO);
	if (unlikely(!page))
		return -ENOMEM;

	rq_for_each_segment(bvec, rq, iter) {
		ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page,
			bvec.bv_offset, bvec.bv_len, pos >> 9);
		if (unlikely(ret))
			break;

		b.bv_page = page;
		b.bv_offset = 0;
		b.bv_len = bvec.bv_len;
		ret = lo_write_bvec(lo->lo_backing_file, &b, &pos);
		if (ret < 0)
			break;
	}

	__free_page(page);
	return ret;
}

static int lo_read_simple(struct loop_device *lo, struct request *rq,
		loff_t pos)
{
	struct bio_vec bvec;
	struct req_iterator iter;
	struct iov_iter i;
	ssize_t len;

	rq_for_each_segment(bvec, rq, iter) {
		iov_iter_bvec(&i, ITER_BVEC, &bvec, 1, bvec.bv_len);
		len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
		if (len < 0)
			return len;

		flush_dcache_page(bvec.bv_page);

		if (len != bvec.bv_len) {
			struct bio *bio;

			__rq_for_each_bio(bio, rq)
				zero_fill_bio(bio);
			break;
		}
		cond_resched();
	}

	return 0;
}

static int lo_read_transfer(struct loop_device *lo, struct request *rq,
		loff_t pos)
{
	struct bio_vec bvec, b;
	struct req_iterator iter;
	struct iov_iter i;
	struct page *page;
	ssize_t len;
	int ret = 0;

	page = alloc_page(GFP_NOIO);
	if (unlikely(!page))
		return -ENOMEM;

	rq_for_each_segment(bvec, rq, iter) {
		loff_t offset = pos;

		b.bv_page = page;
		b.bv_offset = 0;
		b.bv_len = bvec.bv_len;

		iov_iter_bvec(&i, ITER_BVEC, &b, 1, b.bv_len);
		len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
		if (len < 0) {
			ret = len;
			goto out_free_page;
		}

		ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page,
			bvec.bv_offset, len, offset >> 9);
		if (ret)
			goto out_free_page;

		flush_dcache_page(bvec.bv_page);

		if (len != bvec.bv_len) {
			struct bio *bio;

			__rq_for_each_bio(bio, rq)
				zero_fill_bio(bio);
			break;
		}
	}

	ret = 0;
out_free_page:
	__free_page(page);
	return ret;
}

static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
{
	/*
	 * We use punch hole to reclaim the free space used by the
	 * image a.k.a. discard. However we do not support discard if
	 * encryption is enabled, because it may give an attacker
	 * useful information.
	 */
	struct file *file = lo->lo_backing_file;
	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
	int ret;

	if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
		ret = -EOPNOTSUPP;
		goto out;
	}

	ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
	if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
		ret = -EIO;
 out:
	return ret;
}

static int lo_req_flush(struct loop_device *lo, struct request *rq)
{
	struct file *file = lo->lo_backing_file;
	int ret = vfs_fsync(file, 0);
	if (unlikely(ret && ret != -EINVAL))
		ret = -EIO;

	return ret;
}

static void lo_complete_rq(struct request *rq)
{
	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
	blk_status_t ret = BLK_STS_OK;

	if (!cmd->use_aio || cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) ||
	    req_op(rq) != REQ_OP_READ) {
		if (cmd->ret < 0)
			ret = BLK_STS_IOERR;
		goto end_io;
	}

	/*
	 * Short READ - if we got some data, advance our request and
	 * retry it. If we got no data, end the rest with EIO.
	 */
	if (cmd->ret) {
		blk_update_request(rq, BLK_STS_OK, cmd->ret);
		cmd->ret = 0;
		blk_mq_requeue_request(rq, true);
	} else {
		if (cmd->use_aio) {
			struct bio *bio = rq->bio;

			while (bio) {
				zero_fill_bio(bio);
				bio = bio->bi_next;
			}
		}
		ret = BLK_STS_IOERR;
end_io:
		blk_mq_end_request(rq, ret);
	}
}

static void lo_rw_aio_do_completion(struct loop_cmd *cmd)
{
	struct request *rq = blk_mq_rq_from_pdu(cmd);

	if (!atomic_dec_and_test(&cmd->ref))
		return;
	kfree(cmd->bvec);
	cmd->bvec = NULL;
	blk_mq_complete_request(rq);
}

static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
{
	struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);

	if (cmd->css)
		css_put(cmd->css);
	cmd->ret = ret;
	lo_rw_aio_do_completion(cmd);
}

static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
		     loff_t pos, bool rw)
{
	struct iov_iter iter;
	struct bio_vec *bvec;
	struct request *rq = blk_mq_rq_from_pdu(cmd);
	struct bio *bio = rq->bio;
	struct file *file = lo->lo_backing_file;
	unsigned int offset;
	int segments = 0;
	int ret;

	if (rq->bio != rq->biotail) {
		struct req_iterator iter;
		struct bio_vec tmp;

		__rq_for_each_bio(bio, rq)
			segments += bio_segments(bio);
		bvec = kmalloc_array(segments, sizeof(struct bio_vec),
				     GFP_NOIO);
		if (!bvec)
			return -EIO;
		cmd->bvec = bvec;

		/*
		 * The bios of the request may be started from the middle of
		 * the 'bvec' because of bio splitting, so we can't directly
		 * copy bio->bi_iov_vec to new bvec. The rq_for_each_segment
		 * API will take care of all details for us.
		 */
		rq_for_each_segment(tmp, rq, iter) {
			*bvec = tmp;
			bvec++;
		}
		bvec = cmd->bvec;
		offset = 0;
	} else {
		/*
		 * Same here, this bio may be started from the middle of the
		 * 'bvec' because of bio splitting, so offset from the bvec
		 * must be passed to iov iterator
		 */
		offset = bio->bi_iter.bi_bvec_done;
		bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
		segments = bio_segments(bio);
	}
	atomic_set(&cmd->ref, 2);

	iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
		      segments, blk_rq_bytes(rq));
	iter.iov_offset = offset;

	cmd->iocb.ki_pos = pos;
	cmd->iocb.ki_filp = file;
	cmd->iocb.ki_complete = lo_rw_aio_complete;
	cmd->iocb.ki_flags = IOCB_DIRECT;
	cmd->iocb.ki_ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_NONE, 0);
	if (cmd->css)
		kthread_associate_blkcg(cmd->css);

	if (rw == WRITE)
		ret = call_write_iter(file, &cmd->iocb, &iter);
	else
		ret = call_read_iter(file, &cmd->iocb, &iter);

	lo_rw_aio_do_completion(cmd);
	kthread_associate_blkcg(NULL);

	if (ret != -EIOCBQUEUED)
		cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
	return 0;
}

static int do_req_filebacked(struct loop_device *lo, struct request *rq)
{
	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
	loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset;

	/*
	 * lo_write_simple and lo_read_simple should have been covered
	 * by io submit style function like lo_rw_aio(), one blocker
	 * is that lo_read_simple() need to call flush_dcache_page after
	 * the page is written from kernel, and it isn't easy to handle
	 * this in io submit style function which submits all segments
	 * of the req at one time. And direct read IO doesn't need to
	 * run flush_dcache_page().
	 */
	switch (req_op(rq)) {
	case REQ_OP_FLUSH:
		return lo_req_flush(lo, rq);
	case REQ_OP_DISCARD:
	case REQ_OP_WRITE_ZEROES:
		return lo_discard(lo, rq, pos);
	case REQ_OP_WRITE:
		if (lo->transfer)
			return lo_write_transfer(lo, rq, pos);
		else if (cmd->use_aio)
			return lo_rw_aio(lo, cmd, pos, WRITE);
		else
			return lo_write_simple(lo, rq, pos);
	case REQ_OP_READ:
		if (lo->transfer)
			return lo_read_transfer(lo, rq, pos);
		else if (cmd->use_aio)
			return lo_rw_aio(lo, cmd, pos, READ);
		else
			return lo_read_simple(lo, rq, pos);
	default:
		WARN_ON_ONCE(1);
		return -EIO;
		break;
	}
}

static inline void loop_update_dio(struct loop_device *lo)
{
	__loop_update_dio(lo, io_is_direct(lo->lo_backing_file) |
			lo->use_dio);
}

static void loop_reread_partitions(struct loop_device *lo,
				   struct block_device *bdev)
{
	int rc;

	/*
	 * bd_mutex has been held already in release path, so don't
	 * acquire it if this function is called in such case.
	 *
	 * If the reread partition isn't from release path, lo_refcnt
	 * must be at least one and it can only become zero when the
	 * current holder is released.
	 */
	if (!atomic_read(&lo->lo_refcnt))
		rc = __blkdev_reread_part(bdev);
	else
		rc = blkdev_reread_part(bdev);
	if (rc)
		pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
			__func__, lo->lo_number, lo->lo_file_name, rc);
}

static inline int is_loop_device(struct file *file)
{
	struct inode *i = file->f_mapping->host;

	return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
}

static int loop_validate_file(struct file *file, struct block_device *bdev)
{
	struct inode	*inode = file->f_mapping->host;
	struct file	*f = file;

	/* Avoid recursion */
	while (is_loop_device(f)) {
		struct loop_device *l;

		if (f->f_mapping->host->i_bdev == bdev)
			return -EBADF;

		l = f->f_mapping->host->i_bdev->bd_disk->private_data;
		if (l->lo_state == Lo_unbound) {
			return -EINVAL;
		}
		f = l->lo_backing_file;
	}
	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
		return -EINVAL;
	return 0;
}

/*
 * loop_change_fd switched the backing store of a loopback device to
 * a new file. This is useful for operating system installers to free up
 * the original file and in High Availability environments to switch to
 * an alternative location for the content in case of server meltdown.
 * This can only work if the loop device is used read-only, and if the
 * new backing store is the same size and type as the old backing store.
 */
static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
			  unsigned int arg)
{
	struct file	*file, *old_file;
	struct inode	*inode;
	int		error;

	error = -ENXIO;
	if (lo->lo_state != Lo_bound)
		goto out;

	/* the loop device has to be read-only */
	error = -EINVAL;
	if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
		goto out;

	error = -EBADF;
	file = fget(arg);
	if (!file)
		goto out;

	error = loop_validate_file(file, bdev);
	if (error)
		goto out_putf;

	inode = file->f_mapping->host;
	old_file = lo->lo_backing_file;

	error = -EINVAL;

	/* size of the new backing store needs to be the same */
	if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
		goto out_putf;

	/* and ... switch */
	blk_mq_freeze_queue(lo->lo_queue);
	mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
	lo->lo_backing_file = file;
	lo->old_gfp_mask = mapping_gfp_mask(file->f_mapping);
	mapping_set_gfp_mask(file->f_mapping,
			     lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
	loop_update_dio(lo);
	blk_mq_unfreeze_queue(lo->lo_queue);

	fput(old_file);
	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
		loop_reread_partitions(lo, bdev);
	return 0;

 out_putf:
	fput(file);
 out:
	return error;
}

/* loop sysfs attributes */

static ssize_t loop_attr_show(struct device *dev, char *page,
			      ssize_t (*callback)(struct loop_device *, char *))
{
	struct gendisk *disk = dev_to_disk(dev);
	struct loop_device *lo = disk->private_data;

	return callback(lo, page);
}

#define LOOP_ATTR_RO(_name)						\
static ssize_t loop_attr_##_name##_show(struct loop_device *, char *);	\
static ssize_t loop_attr_do_show_##_name(struct device *d,		\
				struct device_attribute *attr, char *b)	\
{									\
	return loop_attr_show(d, b, loop_attr_##_name##_show);		\
}									\
static struct device_attribute loop_attr_##_name =			\
	__ATTR(_name, 0444, loop_attr_do_show_##_name, NULL);

static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
{
	ssize_t ret;
	char *p = NULL;

	spin_lock_irq(&lo->lo_lock);
	if (lo->lo_backing_file)
		p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1);
	spin_unlock_irq(&lo->lo_lock);

	if (IS_ERR_OR_NULL(p))
		ret = PTR_ERR(p);
	else {
		ret = strlen(p);
		memmove(buf, p, ret);
		buf[ret++] = '\n';
		buf[ret] = 0;
	}

	return ret;
}

static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf)
{
	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset);
}

static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf)
{
	return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
}

static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf)
{
	int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR);

	return sprintf(buf, "%s\n", autoclear ? "1" : "0");
}

static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
{
	int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN);

	return sprintf(buf, "%s\n", partscan ? "1" : "0");
}

static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
{
	int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);

	return sprintf(buf, "%s\n", dio ? "1" : "0");
}

LOOP_ATTR_RO(backing_file);
LOOP_ATTR_RO(offset);
LOOP_ATTR_RO(sizelimit);
LOOP_ATTR_RO(autoclear);
LOOP_ATTR_RO(partscan);
LOOP_ATTR_RO(dio);

static struct attribute *loop_attrs[] = {
	&loop_attr_backing_file.attr,
	&loop_attr_offset.attr,
	&loop_attr_sizelimit.attr,
	&loop_attr_autoclear.attr,
	&loop_attr_partscan.attr,
	&loop_attr_dio.attr,
	NULL,
};

static struct attribute_group loop_attribute_group = {
	.name = "loop",
	.attrs= loop_attrs,
};

static void loop_sysfs_init(struct loop_device *lo)
{
	lo->sysfs_inited = !sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
						&loop_attribute_group);
}

static void loop_sysfs_exit(struct loop_device *lo)
{
	if (lo->sysfs_inited)
		sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
				   &loop_attribute_group);
}

static void loop_config_discard(struct loop_device *lo)
{
	struct file *file = lo->lo_backing_file;
	struct inode *inode = file->f_mapping->host;
	struct request_queue *q = lo->lo_queue;

	/*
	 * We use punch hole to reclaim the free space used by the
	 * image a.k.a. discard. However we do not support discard if
	 * encryption is enabled, because it may give an attacker
	 * useful information.
	 */
	if ((!file->f_op->fallocate) ||
	    lo->lo_encrypt_key_size) {
		q->limits.discard_granularity = 0;
		q->limits.discard_alignment = 0;
		blk_queue_max_discard_sectors(q, 0);
		blk_queue_max_write_zeroes_sectors(q, 0);
		blk_queue_flag_clear(QUEUE_FLAG_DISCARD, q);
		return;
	}

	q->limits.discard_granularity = inode->i_sb->s_blocksize;
	q->limits.discard_alignment = 0;

	blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
	blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
	blk_queue_flag_set(QUEUE_FLAG_DISCARD, q);
}

static void loop_unprepare_queue(struct loop_device *lo)
{
	kthread_flush_worker(&lo->worker);
	kthread_stop(lo->worker_task);
}

static int loop_kthread_worker_fn(void *worker_ptr)
{
	current->flags |= PF_LESS_THROTTLE;
	return kthread_worker_fn(worker_ptr);
}

static int loop_prepare_queue(struct loop_device *lo)
{
	kthread_init_worker(&lo->worker);
	lo->worker_task = kthread_run(loop_kthread_worker_fn,
			&lo->worker, "loop%d", lo->lo_number);
	if (IS_ERR(lo->worker_task))
		return -ENOMEM;
	set_user_nice(lo->worker_task, MIN_NICE);
	return 0;
}

static int loop_set_fd(struct loop_device *lo, fmode_t mode,
		       struct block_device *bdev, unsigned int arg)
{
	struct file	*file;
	struct inode	*inode;
	struct address_space *mapping;
	int		lo_flags = 0;
	int		error;
	loff_t		size;

	/* This is safe, since we have a reference from open(). */
	__module_get(THIS_MODULE);

	error = -EBADF;
	file = fget(arg);
	if (!file)
		goto out;

	error = -EBUSY;
	if (lo->lo_state != Lo_unbound)
		goto out_putf;

	error = loop_validate_file(file, bdev);
	if (error)
		goto out_putf;

	mapping = file->f_mapping;
	inode = mapping->host;

	if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
	    !file->f_op->write_iter)
		lo_flags |= LO_FLAGS_READ_ONLY;

	error = -EFBIG;
	size = get_loop_size(lo, file);
	if ((loff_t)(sector_t)size != size)
		goto out_putf;
	error = loop_prepare_queue(lo);
	if (error)
		goto out_putf;

	error = 0;

	set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);

	lo->use_dio = false;
	lo->lo_device = bdev;
	lo->lo_flags = lo_flags;
	lo->lo_backing_file = file;
	lo->transfer = NULL;
	lo->ioctl = NULL;
	lo->lo_sizelimit = 0;
	lo->old_gfp_mask = mapping_gfp_mask(mapping);
	mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));

	if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
		blk_queue_write_cache(lo->lo_queue, true, false);

	loop_update_dio(lo);
	set_capacity(lo->lo_disk, size);
	bd_set_size(bdev, size << 9);
	loop_sysfs_init(lo);
	/* let user-space know about the new size */
	kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);

	set_blocksize(bdev, S_ISBLK(inode->i_mode) ?
		      block_size(inode->i_bdev) : PAGE_SIZE);

	lo->lo_state = Lo_bound;
	if (part_shift)
		lo->lo_flags |= LO_FLAGS_PARTSCAN;
	if (lo->lo_flags & LO_FLAGS_PARTSCAN)
		loop_reread_partitions(lo, bdev);

	/* Grab the block_device to prevent its destruction after we
	 * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
	 */
	bdgrab(bdev);
	return 0;

 out_putf:
	fput(file);
 out:
	/* This is safe: open() is still holding a reference. */
	module_put(THIS_MODULE);
	return error;
}

static int
loop_release_xfer(struct loop_device *lo)
{
	int err = 0;
	struct loop_func_table *xfer = lo->lo_encryption;

	if (xfer) {
		if (xfer->release)
			err = xfer->release(lo);
		lo->transfer = NULL;
		lo->lo_encryption = NULL;
		module_put(xfer->owner);
	}
	return err;
}

static int
loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
	       const struct loop_info64 *i)
{
	int err = 0;

	if (xfer) {
		struct module *owner = xfer->owner;

		if (!try_module_get(owner))
			return -EINVAL;
		if (xfer->init)
			err = xfer->init(lo, i);
		if (err)
			module_put(owner);
		else
			lo->lo_encryption = xfer;
	}
	return err;
}

static int loop_clr_fd(struct loop_device *lo)
{
	struct file *filp = lo->lo_backing_file;
	gfp_t gfp = lo->old_gfp_mask;
	struct block_device *bdev = lo->lo_device;

	if (lo->lo_state != Lo_bound)
		return -ENXIO;

	/*
	 * If we've explicitly asked to tear down the loop device,
	 * and it has an elevated reference count, set it for auto-teardown when
	 * the last reference goes away. This stops $!~#$@ udev from
	 * preventing teardown because it decided that it needs to run blkid on
	 * the loopback device whenever they appear. xfstests is notorious for
	 * failing tests because blkid via udev races with a losetup
	 * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
	 * command to fail with EBUSY.
	 */
	if (atomic_read(&lo->lo_refcnt) > 1) {
		lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
		mutex_unlock(&lo->lo_ctl_mutex);
		return 0;
	}

	if (filp == NULL)
		return -EINVAL;

	/* freeze request queue during the transition */
	blk_mq_freeze_queue(lo->lo_queue);

	spin_lock_irq(&lo->lo_lock);
	lo->lo_state = Lo_rundown;
	lo->lo_backing_file = NULL;
	spin_unlock_irq(&lo->lo_lock);

	loop_release_xfer(lo);
	lo->transfer = NULL;
	lo->ioctl = NULL;
	lo->lo_device = NULL;
	lo->lo_encryption = NULL;
	lo->lo_offset = 0;
	lo->lo_sizelimit = 0;
	lo->lo_encrypt_key_size = 0;
	memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
	memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
	memset(lo->lo_file_name, 0, LO_NAME_SIZE);
	blk_queue_logical_block_size(lo->lo_queue, 512);
	blk_queue_physical_block_size(lo->lo_queue, 512);
	blk_queue_io_min(lo->lo_queue, 512);
	if (bdev) {
		bdput(bdev);
		invalidate_bdev(bdev);
		bdev->bd_inode->i_mapping->wb_err = 0;
	}
	set_capacity(lo->lo_disk, 0);
	loop_sysfs_exit(lo);
	if (bdev) {
		bd_set_size(bdev, 0);
		/* let user-space know about this change */
		kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
	}
	mapping_set_gfp_mask(filp->f_mapping, gfp);
	lo->lo_state = Lo_unbound;
	/* This is safe: open() is still holding a reference. */
	module_put(THIS_MODULE);
	blk_mq_unfreeze_queue(lo->lo_queue);

	if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
		loop_reread_partitions(lo, bdev);
	lo->lo_flags = 0;
	if (!part_shift)
		lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
	loop_unprepare_queue(lo);
	mutex_unlock(&lo->lo_ctl_mutex);
	/*
	 * Need not hold lo_ctl_mutex to fput backing file.
	 * Calling fput holding lo_ctl_mutex triggers a circular
	 * lock dependency possibility warning as fput can take
	 * bd_mutex which is usually taken before lo_ctl_mutex.
	 */
	fput(filp);
	return 0;
}

static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
	int err;
	struct loop_func_table *xfer;
	kuid_t uid = current_uid();

	if (lo->lo_encrypt_key_size &&
	    !uid_eq(lo->lo_key_owner, uid) &&
	    !capable(CAP_SYS_ADMIN))
		return -EPERM;
	if (lo->lo_state != Lo_bound)
		return -ENXIO;
	if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
		return -EINVAL;

	/* I/O need to be drained during transfer transition */
	blk_mq_freeze_queue(lo->lo_queue);

	err = loop_release_xfer(lo);
	if (err)
		goto exit;

	if (info->lo_encrypt_type) {
		unsigned int type = info->lo_encrypt_type;

		if (type >= MAX_LO_CRYPT) {
			err = -EINVAL;
			goto exit;
		}
		xfer = xfer_funcs[type];
		if (xfer == NULL) {
			err = -EINVAL;
			goto exit;
		}
	} else
		xfer = NULL;

	err = loop_init_xfer(lo, xfer, info);
	if (err)
		goto exit;

	if (lo->lo_offset != info->lo_offset ||
	    lo->lo_sizelimit != info->lo_sizelimit) {
		if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
			err = -EFBIG;
			goto exit;
		}
	}

	loop_config_discard(lo);

	memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
	memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
	lo->lo_file_name[LO_NAME_SIZE-1] = 0;
	lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;

	if (!xfer)
		xfer = &none_funcs;
	lo->transfer = xfer->transfer;
	lo->ioctl = xfer->ioctl;

	if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) !=
	     (info->lo_flags & LO_FLAGS_AUTOCLEAR))
		lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;

	lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
	lo->lo_init[0] = info->lo_init[0];
	lo->lo_init[1] = info->lo_init[1];
	if (info->lo_encrypt_key_size) {
		memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
		       info->lo_encrypt_key_size);
		lo->lo_key_owner = uid;
	}

	/* update dio if lo_offset or transfer is changed */
	__loop_update_dio(lo, lo->use_dio);

 exit:
	blk_mq_unfreeze_queue(lo->lo_queue);

	if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
	     !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
		lo->lo_flags |= LO_FLAGS_PARTSCAN;
		lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
		loop_reread_partitions(lo, lo->lo_device);
	}

	return err;
}

static int
loop_get_status(struct loop_device *lo, struct loop_info64 *info)
{
	struct file *file;
	struct kstat stat;
	int ret;

	if (lo->lo_state != Lo_bound) {
		mutex_unlock(&lo->lo_ctl_mutex);
		return -ENXIO;
	}

	memset(info, 0, sizeof(*info));
	info->lo_number = lo->lo_number;
	info->lo_offset = lo->lo_offset;
	info->lo_sizelimit = lo->lo_sizelimit;
	info->lo_flags = lo->lo_flags;
	memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE);
	memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);
	info->lo_encrypt_type =
		lo->lo_encryption ? lo->lo_encryption->number : 0;
	if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) {
		info->lo_encrypt_key_size = lo->lo_encrypt_key_size;
		memcpy(info->lo_encrypt_key, lo->lo_encrypt_key,
		       lo->lo_encrypt_key_size);
	}

	/* Drop lo_ctl_mutex while we call into the filesystem. */
	file = get_file(lo->lo_backing_file);
	mutex_unlock(&lo->lo_ctl_mutex);
	ret = vfs_getattr(&file->f_path, &stat, STATX_INO,
			  AT_STATX_SYNC_AS_STAT);
	if (!ret) {
		info->lo_device = huge_encode_dev(stat.dev);
		info->lo_inode = stat.ino;
		info->lo_rdevice = huge_encode_dev(stat.rdev);
	}
	fput(file);
	return ret;
}

static void
loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64)
{
	memset(info64, 0, sizeof(*info64));
	info64->lo_number = info->lo_number;
	info64->lo_device = info->lo_device;
	info64->lo_inode = info->lo_inode;
	info64->lo_rdevice = info->lo_rdevice;
	info64->lo_offset = info->lo_offset;
	info64->lo_sizelimit = 0;
	info64->lo_encrypt_type = info->lo_encrypt_type;
	info64->lo_encrypt_key_size = info->lo_encrypt_key_size;
	info64->lo_flags = info->lo_flags;
	info64->lo_init[0] = info->lo_init[0];
	info64->lo_init[1] = info->lo_init[1];
	if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
		memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE);
	else
		memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
	memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE);
}

static int
loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info)
{
	memset(info, 0, sizeof(*info));
	info->lo_number = info64->lo_number;
	info->lo_device = info64->lo_device;
	info->lo_inode = info64->lo_inode;
	info->lo_rdevice = info64->lo_rdevice;
	info->lo_offset = info64->lo_offset;
	info->lo_encrypt_type = info64->lo_encrypt_type;
	info->lo_encrypt_key_size = info64->lo_encrypt_key_size;
	info->lo_flags = info64->lo_flags;
	info->lo_init[0] = info64->lo_init[0];
	info->lo_init[1] = info64->lo_init[1];
	if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
		memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
	else
		memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
	memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);

	/* error in case values were truncated */
	if (info->lo_device != info64->lo_device ||
	    info->lo_rdevice != info64->lo_rdevice ||
	    info->lo_inode != info64->lo_inode ||
	    info->lo_offset != info64->lo_offset)
		return -EOVERFLOW;

	return 0;
}

static int
loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg)
{
	struct loop_info info;
	struct loop_info64 info64;

	if (copy_from_user(&info, arg, sizeof (struct loop_info)))
		return -EFAULT;
	loop_info64_from_old(&info, &info64);
	return loop_set_status(lo, &info64);
}

static int
loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg)
{
	struct loop_info64 info64;

	if (copy_from_user(&info64, arg, sizeof (struct loop_info64)))
		return -EFAULT;
	return loop_set_status(lo, &info64);
}

static int
loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) {
	struct loop_info info;
	struct loop_info64 info64;
	int err;

	if (!arg) {
		mutex_unlock(&lo->lo_ctl_mutex);
		return -EINVAL;
	}
	err = loop_get_status(lo, &info64);
	if (!err)
		err = loop_info64_to_old(&info64, &info);
	if (!err && copy_to_user(arg, &info, sizeof(info)))
		err = -EFAULT;

	return err;
}

static int
loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
	struct loop_info64 info64;
	int err;

	if (!arg) {
		mutex_unlock(&lo->lo_ctl_mutex);
		return -EINVAL;
	}
	err = loop_get_status(lo, &info64);
	if (!err && copy_to_user(arg, &info64, sizeof(info64)))
		err = -EFAULT;

	return err;
}

static int loop_set_capacity(struct loop_device *lo)
{
	if (unlikely(lo->lo_state != Lo_bound))
		return -ENXIO;

	return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
}

static int loop_set_dio(struct loop_device *lo, unsigned long arg)
{
	int error = -ENXIO;
	if (lo->lo_state != Lo_bound)
		goto out;

	__loop_update_dio(lo, !!arg);
	if (lo->use_dio == !!arg)
		return 0;
	error = -EINVAL;
 out:
	return error;
}

static int loop_set_block_size(struct loop_device *lo, unsigned long arg)
{
	if (lo->lo_state != Lo_bound)
		return -ENXIO;

	if (arg < 512 || arg > PAGE_SIZE || !is_power_of_2(arg))
		return -EINVAL;

	blk_mq_freeze_queue(lo->lo_queue);

	blk_queue_logical_block_size(lo->lo_queue, arg);
	blk_queue_physical_block_size(lo->lo_queue, arg);
	blk_queue_io_min(lo->lo_queue, arg);
	loop_update_dio(lo);

	blk_mq_unfreeze_queue(lo->lo_queue);

	return 0;
}

static int lo_ioctl(struct block_device *bdev, fmode_t mode,
	unsigned int cmd, unsigned long arg)
{
	struct loop_device *lo = bdev->bd_disk->private_data;
	int err;

	err = mutex_lock_killable_nested(&lo->lo_ctl_mutex, 1);
	if (err)
		goto out_unlocked;

	switch (cmd) {
	case LOOP_SET_FD:
		err = loop_set_fd(lo, mode, bdev, arg);
		break;
	case LOOP_CHANGE_FD:
		err = loop_change_fd(lo, bdev, arg);
		break;
	case LOOP_CLR_FD:
		/* loop_clr_fd would have unlocked lo_ctl_mutex on success */
		err = loop_clr_fd(lo);
		if (!err)
			goto out_unlocked;
		break;
	case LOOP_SET_STATUS:
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_status_old(lo,
					(struct loop_info __user *)arg);
		break;
	case LOOP_GET_STATUS:
		err = loop_get_status_old(lo, (struct loop_info __user *) arg);
		/* loop_get_status() unlocks lo_ctl_mutex */
		goto out_unlocked;
	case LOOP_SET_STATUS64:
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_status64(lo,
					(struct loop_info64 __user *) arg);
		break;
	case LOOP_GET_STATUS64:
		err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
		/* loop_get_status() unlocks lo_ctl_mutex */
		goto out_unlocked;
	case LOOP_SET_CAPACITY:
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_capacity(lo);
		break;
	case LOOP_SET_DIRECT_IO:
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_dio(lo, arg);
		break;
	case LOOP_SET_BLOCK_SIZE:
		err = -EPERM;
		if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
			err = loop_set_block_size(lo, arg);
		break;
	default:
		err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
	}
	mutex_unlock(&lo->lo_ctl_mutex);

out_unlocked:
	return err;
}

#ifdef CONFIG_COMPAT
struct compat_loop_info {
	compat_int_t	lo_number;      /* ioctl r/o */
	compat_dev_t	lo_device;      /* ioctl r/o */
	compat_ulong_t	lo_inode;       /* ioctl r/o */
	compat_dev_t	lo_rdevice;     /* ioctl r/o */
	compat_int_t	lo_offset;
	compat_int_t	lo_encrypt_type;
	compat_int_t	lo_encrypt_key_size;    /* ioctl w/o */
	compat_int_t	lo_flags;       /* ioctl r/o */
	char		lo_name[LO_NAME_SIZE];
	unsigned char	lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
	compat_ulong_t	lo_init[2];
	char		reserved[4];
};

/*
 * Transfer 32-bit compatibility structure in userspace to 64-bit loop info
 * - noinlined to reduce stack space usage in main part of driver
 */
static noinline int
loop_info64_from_compat(const struct compat_loop_info __user *arg,
			struct loop_info64 *info64)
{
	struct compat_loop_info info;

	if (copy_from_user(&info, arg, sizeof(info)))
		return -EFAULT;

	memset(info64, 0, sizeof(*info64));
	info64->lo_number = info.lo_number;
	info64->lo_device = info.lo_device;
	info64->lo_inode = info.lo_inode;
	info64->lo_rdevice = info.lo_rdevice;
	info64->lo_offset = info.lo_offset;
	info64->lo_sizelimit = 0;
	info64->lo_encrypt_type = info.lo_encrypt_type;
	info64->lo_encrypt_key_size = info.lo_encrypt_key_size;
	info64->lo_flags = info.lo_flags;
	info64->lo_init[0] = info.lo_init[0];
	info64->lo_init[1] = info.lo_init[1];
	if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
		memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE);
	else
		memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
	memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE);
	return 0;
}

/*
 * Transfer 64-bit loop info to 32-bit compatibility structure in userspace
 * - noinlined to reduce stack space usage in main part of driver
 */
static noinline int
loop_info64_to_compat(const struct loop_info64 *info64,
		      struct compat_loop_info __user *arg)
{
	struct compat_loop_info info;

	memset(&info, 0, sizeof(info));
	info.lo_number = info64->lo_number;
	info.lo_device = info64->lo_device;
	info.lo_inode = info64->lo_inode;
	info.lo_rdevice = info64->lo_rdevice;
	info.lo_offset = info64->lo_offset;
	info.lo_encrypt_type = info64->lo_encrypt_type;
	info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
	info.lo_flags = info64->lo_flags;
	info.lo_init[0] = info64->lo_init[0];
	info.lo_init[1] = info64->lo_init[1];
	if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
		memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
	else
		memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
	memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);

	/* error in case values were truncated */
	if (info.lo_device != info64->lo_device ||
	    info.lo_rdevice != info64->lo_rdevice ||
	    info.lo_inode != info64->lo_inode ||
	    info.lo_offset != info64->lo_offset ||
	    info.lo_init[0] != info64->lo_init[0] ||
	    info.lo_init[1] != info64->lo_init[1])
		return -EOVERFLOW;

	if (copy_to_user(arg, &info, sizeof(info)))
		return -EFAULT;
	return 0;
}

static int
loop_set_status_compat(struct loop_device *lo,
		       const struct compat_loop_info __user *arg)
{
	struct loop_info64 info64;
	int ret;

	ret = loop_info64_from_compat(arg, &info64);
	if (ret < 0)
		return ret;
	return loop_set_status(lo, &info64);
}

static int
loop_get_status_compat(struct loop_device *lo,
		       struct compat_loop_info __user *arg)
{
	struct loop_info64 info64;
	int err;

	if (!arg) {
		mutex_unlock(&lo->lo_ctl_mutex);
		return -EINVAL;
	}
	err = loop_get_status(lo, &info64);
	if (!err)
		err = loop_info64_to_compat(&info64, arg);
	return err;
}

static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
			   unsigned int cmd, unsigned long arg)
{
	struct loop_device *lo = bdev->bd_disk->private_data;
	int err;

	switch(cmd) {
	case LOOP_SET_STATUS:
		err = mutex_lock_killable(&lo->lo_ctl_mutex);
		if (!err) {
			err = loop_set_status_compat(lo,
						     (const struct compat_loop_info __user *)arg);
			mutex_unlock(&lo->lo_ctl_mutex);
		}
		break;
	case LOOP_GET_STATUS:
		err = mutex_lock_killable(&lo->lo_ctl_mutex);
		if (!err) {
			err = loop_get_status_compat(lo,
						     (struct compat_loop_info __user *)arg);
			/* loop_get_status() unlocks lo_ctl_mutex */
		}
		break;
	case LOOP_SET_CAPACITY:
	case LOOP_CLR_FD:
	case LOOP_GET_STATUS64:
	case LOOP_SET_STATUS64:
		arg = (unsigned long) compat_ptr(arg);
	case LOOP_SET_FD:
	case LOOP_CHANGE_FD:
		err = lo_ioctl(bdev, mode, cmd, arg);
		break;
	default:
		err = -ENOIOCTLCMD;
		break;
	}
	return err;
}
#endif

static int lo_open(struct block_device *bdev, fmode_t mode)
{
	struct loop_device *lo;
	int err = 0;

	mutex_lock(&loop_index_mutex);
	lo = bdev->bd_disk->private_data;
	if (!lo) {
		err = -ENXIO;
		goto out;
	}

	atomic_inc(&lo->lo_refcnt);
out:
	mutex_unlock(&loop_index_mutex);
	return err;
}

static void __lo_release(struct loop_device *lo)
{
	int err;

	if (atomic_dec_return(&lo->lo_refcnt))
		return;

	mutex_lock(&lo->lo_ctl_mutex);
	if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) {
		/*
		 * In autoclear mode, stop the loop thread
		 * and remove configuration after last close.
		 */
		err = loop_clr_fd(lo);
		if (!err)
			return;
	} else if (lo->lo_state == Lo_bound) {
		/*
		 * Otherwise keep thread (if running) and config,
		 * but flush possible ongoing bios in thread.
		 */
		blk_mq_freeze_queue(lo->lo_queue);
		blk_mq_unfreeze_queue(lo->lo_queue);
	}

	mutex_unlock(&lo->lo_ctl_mutex);
}

static void lo_release(struct gendisk *disk, fmode_t mode)
{
	mutex_lock(&loop_index_mutex);
	__lo_release(disk->private_data);
	mutex_unlock(&loop_index_mutex);
}

static const struct block_device_operations lo_fops = {
	.owner =	THIS_MODULE,
	.open =		lo_open,
	.release =	lo_release,
	.ioctl =	lo_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl =	lo_compat_ioctl,
#endif
};

/*
 * And now the modules code and kernel interface.
 */
static int max_loop;
module_param(max_loop, int, 0444);
MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
module_param(max_part, int, 0444);
MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);

int loop_register_transfer(struct loop_func_table *funcs)
{
	unsigned int n = funcs->number;

	if (n >= MAX_LO_CRYPT || xfer_funcs[n])
		return -EINVAL;
	xfer_funcs[n] = funcs;
	return 0;
}

static int unregister_transfer_cb(int id, void *ptr, void *data)
{
	struct loop_device *lo = ptr;
	struct loop_func_table *xfer = data;

	mutex_lock(&lo->lo_ctl_mutex);
	if (lo->lo_encryption == xfer)
		loop_release_xfer(lo);
	mutex_unlock(&lo->lo_ctl_mutex);
	return 0;
}

int loop_unregister_transfer(int number)
{
	unsigned int n = number;
	struct loop_func_table *xfer;

	if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
		return -EINVAL;

	xfer_funcs[n] = NULL;
	idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer);
	return 0;
}

EXPORT_SYMBOL(loop_register_transfer);
EXPORT_SYMBOL(loop_unregister_transfer);

static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
		const struct blk_mq_queue_data *bd)
{
	struct request *rq = bd->rq;
	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);
	struct loop_device *lo = rq->q->queuedata;

	blk_mq_start_request(rq);

	if (lo->lo_state != Lo_bound)
		return BLK_STS_IOERR;

	switch (req_op(rq)) {
	case REQ_OP_FLUSH:
	case REQ_OP_DISCARD:
	case REQ_OP_WRITE_ZEROES:
		cmd->use_aio = false;
		break;
	default:
		cmd->use_aio = lo->use_dio;
		break;
	}

	/* always use the first bio's css */
#ifdef CONFIG_BLK_CGROUP
	if (cmd->use_aio && rq->bio && rq->bio->bi_css) {
		cmd->css = rq->bio->bi_css;
		css_get(cmd->css);
	} else
#endif
		cmd->css = NULL;
	kthread_queue_work(&lo->worker, &cmd->work);

	return BLK_STS_OK;
}

static void loop_handle_cmd(struct loop_cmd *cmd)
{
	struct request *rq = blk_mq_rq_from_pdu(cmd);
	const bool write = op_is_write(req_op(rq));
	struct loop_device *lo = rq->q->queuedata;
	int ret = 0;

	if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
		ret = -EIO;
		goto failed;
	}

	ret = do_req_filebacked(lo, rq);
 failed:
	/* complete non-aio request */
	if (!cmd->use_aio || ret) {
		cmd->ret = ret ? -EIO : 0;
		blk_mq_complete_request(rq);
	}
}

static void loop_queue_work(struct kthread_work *work)
{
	struct loop_cmd *cmd =
		container_of(work, struct loop_cmd, work);

	loop_handle_cmd(cmd);
}

static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq,
		unsigned int hctx_idx, unsigned int numa_node)
{
	struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);

	kthread_init_work(&cmd->work, loop_queue_work);
	return 0;
}

static const struct blk_mq_ops loop_mq_ops = {
	.queue_rq       = loop_queue_rq,
	.init_request	= loop_init_request,
	.complete	= lo_complete_rq,
};

static int loop_add(struct loop_device **l, int i)
{
	struct loop_device *lo;
	struct gendisk *disk;
	int err;

	err = -ENOMEM;
	lo = kzalloc(sizeof(*lo), GFP_KERNEL);
	if (!lo)
		goto out;

	lo->lo_state = Lo_unbound;

	/* allocate id, if @id >= 0, we're requesting that specific id */
	if (i >= 0) {
		err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
		if (err == -ENOSPC)
			err = -EEXIST;
	} else {
		err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL);
	}
	if (err < 0)
		goto out_free_dev;
	i = err;

	err = -ENOMEM;
	lo->tag_set.ops = &loop_mq_ops;
	lo->tag_set.nr_hw_queues = 1;
	lo->tag_set.queue_depth = 128;
	lo->tag_set.numa_node = NUMA_NO_NODE;
	lo->tag_set.cmd_size = sizeof(struct loop_cmd);
	lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
	lo->tag_set.driver_data = lo;

	err = blk_mq_alloc_tag_set(&lo->tag_set);
	if (err)
		goto out_free_idr;

	lo->lo_queue = blk_mq_init_queue(&lo->tag_set);
	if (IS_ERR_OR_NULL(lo->lo_queue)) {
		err = PTR_ERR(lo->lo_queue);
		goto out_cleanup_tags;
	}
	lo->lo_queue->queuedata = lo;

	blk_queue_max_hw_sectors(lo->lo_queue, BLK_DEF_MAX_SECTORS);

	/*
	 * By default, we do buffer IO, so it doesn't make sense to enable
	 * merge because the I/O submitted to backing file is handled page by
	 * page. For directio mode, merge does help to dispatch bigger request
	 * to underlayer disk. We will enable merge once directio is enabled.
	 */
	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, lo->lo_queue);

	err = -ENOMEM;
	disk = lo->lo_disk = alloc_disk(1 << part_shift);
	if (!disk)
		goto out_free_queue;

	/*
	 * Disable partition scanning by default. The in-kernel partition
	 * scanning can be requested individually per-device during its
	 * setup. Userspace can always add and remove partitions from all
	 * devices. The needed partition minors are allocated from the
	 * extended minor space, the main loop device numbers will continue
	 * to match the loop minors, regardless of the number of partitions
	 * used.
	 *
	 * If max_part is given, partition scanning is globally enabled for
	 * all loop devices. The minors for the main loop devices will be
	 * multiples of max_part.
	 *
	 * Note: Global-for-all-devices, set-only-at-init, read-only module
	 * parameteters like 'max_loop' and 'max_part' make things needlessly
	 * complicated, are too static, inflexible and may surprise
	 * userspace tools. Parameters like this in general should be avoided.
	 */
	if (!part_shift)
		disk->flags |= GENHD_FL_NO_PART_SCAN;
	disk->flags |= GENHD_FL_EXT_DEVT;
	mutex_init(&lo->lo_ctl_mutex);
	atomic_set(&lo->lo_refcnt, 0);
	lo->lo_number		= i;
	spin_lock_init(&lo->lo_lock);
	disk->major		= LOOP_MAJOR;
	disk->first_minor	= i << part_shift;
	disk->fops		= &lo_fops;
	disk->private_data	= lo;
	disk->queue		= lo->lo_queue;
	sprintf(disk->disk_name, "loop%d", i);
	add_disk(disk);
	*l = lo;
	return lo->lo_number;

out_free_queue:
	blk_cleanup_queue(lo->lo_queue);
out_cleanup_tags:
	blk_mq_free_tag_set(&lo->tag_set);
out_free_idr:
	idr_remove(&loop_index_idr, i);
out_free_dev:
	kfree(lo);
out:
	return err;
}

static void loop_remove(struct loop_device *lo)
{
	del_gendisk(lo->lo_disk);
	blk_cleanup_queue(lo->lo_queue);
	blk_mq_free_tag_set(&lo->tag_set);
	put_disk(lo->lo_disk);
	kfree(lo);
}

static int find_free_cb(int id, void *ptr, void *data)
{
	struct loop_device *lo = ptr;
	struct loop_device **l = data;

	if (lo->lo_state == Lo_unbound) {
		*l = lo;
		return 1;
	}
	return 0;
}

static int loop_lookup(struct loop_device **l, int i)
{
	struct loop_device *lo;
	int ret = -ENODEV;

	if (i < 0) {
		int err;

		err = idr_for_each(&loop_index_idr, &find_free_cb, &lo);
		if (err == 1) {
			*l = lo;
			ret = lo->lo_number;
		}
		goto out;
	}

	/* lookup and return a specific i */
	lo = idr_find(&loop_index_idr, i);
	if (lo) {
		*l = lo;
		ret = lo->lo_number;
	}
out:
	return ret;
}

static struct kobject *loop_probe(dev_t dev, int *part, void *data)
{
	struct loop_device *lo;
	struct kobject *kobj;
	int err;

	mutex_lock(&loop_index_mutex);
	err = loop_lookup(&lo, MINOR(dev) >> part_shift);
	if (err < 0)
		err = loop_add(&lo, MINOR(dev) >> part_shift);
	if (err < 0)
		kobj = NULL;
	else
		kobj = get_disk_and_module(lo->lo_disk);
	mutex_unlock(&loop_index_mutex);

	*part = 0;
	return kobj;
}

static long loop_control_ioctl(struct file *file, unsigned int cmd,
			       unsigned long parm)
{
	struct loop_device *lo;
	int ret = -ENOSYS;

	mutex_lock(&loop_index_mutex);
	switch (cmd) {
	case LOOP_CTL_ADD:
		ret = loop_lookup(&lo, parm);
		if (ret >= 0) {
			ret = -EEXIST;
			break;
		}
		ret = loop_add(&lo, parm);
		break;
	case LOOP_CTL_REMOVE:
		ret = loop_lookup(&lo, parm);
		if (ret < 0)
			break;
		ret = mutex_lock_killable(&lo->lo_ctl_mutex);
		if (ret)
			break;
		if (lo->lo_state != Lo_unbound) {
			ret = -EBUSY;
			mutex_unlock(&lo->lo_ctl_mutex);
			break;
		}
		if (atomic_read(&lo->lo_refcnt) > 0) {
			ret = -EBUSY;
			mutex_unlock(&lo->lo_ctl_mutex);
			break;
		}
		lo->lo_disk->private_data = NULL;
		mutex_unlock(&lo->lo_ctl_mutex);
		idr_remove(&loop_index_idr, lo->lo_number);
		loop_remove(lo);
		break;
	case LOOP_CTL_GET_FREE:
		ret = loop_lookup(&lo, -1);
		if (ret >= 0)
			break;
		ret = loop_add(&lo, -1);
	}
	mutex_unlock(&loop_index_mutex);

	return ret;
}

static const struct file_operations loop_ctl_fops = {
	.open		= nonseekable_open,
	.unlocked_ioctl	= loop_control_ioctl,
	.compat_ioctl	= loop_control_ioctl,
	.owner		= THIS_MODULE,
	.llseek		= noop_llseek,
};

static struct miscdevice loop_misc = {
	.minor		= LOOP_CTRL_MINOR,
	.name		= "loop-control",
	.fops		= &loop_ctl_fops,
};

MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR);
MODULE_ALIAS("devname:loop-control");

static int __init loop_init(void)
{
	int i, nr;
	unsigned long range;
	struct loop_device *lo;
	int err;

	part_shift = 0;
	if (max_part > 0) {
		part_shift = fls(max_part);

		/*
		 * Adjust max_part according to part_shift as it is exported
		 * to user space so that user can decide correct minor number
		 * if [s]he want to create more devices.
		 *
		 * Note that -1 is required because partition 0 is reserved
		 * for the whole disk.
		 */
		max_part = (1UL << part_shift) - 1;
	}

	if ((1UL << part_shift) > DISK_MAX_PARTS) {
		err = -EINVAL;
		goto err_out;
	}

	if (max_loop > 1UL << (MINORBITS - part_shift)) {
		err = -EINVAL;
		goto err_out;
	}

	/*
	 * If max_loop is specified, create that many devices upfront.
	 * This also becomes a hard limit. If max_loop is not specified,
	 * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module
	 * init time. Loop devices can be requested on-demand with the
	 * /dev/loop-control interface, or be instantiated by accessing
	 * a 'dead' device node.
	 */
	if (max_loop) {
		nr = max_loop;
		range = max_loop << part_shift;
	} else {
		nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
		range = 1UL << MINORBITS;
	}

	err = misc_register(&loop_misc);
	if (err < 0)
		goto err_out;


	if (register_blkdev(LOOP_MAJOR, "loop")) {
		err = -EIO;
		goto misc_out;
	}

	blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
				  THIS_MODULE, loop_probe, NULL, NULL);

	/* pre-create number of devices given by config or max_loop */
	mutex_lock(&loop_index_mutex);
	for (i = 0; i < nr; i++)
		loop_add(&lo, i);
	mutex_unlock(&loop_index_mutex);

	printk(KERN_INFO "loop: module loaded\n");
	return 0;

misc_out:
	misc_deregister(&loop_misc);
err_out:
	return err;
}

static int loop_exit_cb(int id, void *ptr, void *data)
{
	struct loop_device *lo = ptr;

	loop_remove(lo);
	return 0;
}

static void __exit loop_exit(void)
{
	unsigned long range;

	range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;

	idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
	idr_destroy(&loop_index_idr);

	blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
	unregister_blkdev(LOOP_MAJOR, "loop");

	misc_deregister(&loop_misc);
}

module_init(loop_init);
module_exit(loop_exit);

#ifndef MODULE
static int __init max_loop_setup(char *str)
{
	max_loop = simple_strtol(str, NULL, 0);
	return 1;
}

__setup("max_loop=", max_loop_setup);
#endif