summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/super.c
blob: a958f625793bc18466b8110513a77689d4604ce5 (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
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/seq_file.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/mpage.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/parser.h>
#include <linux/ctype.h>
#include <linux/namei.h>
#include <linux/miscdevice.h>
#include <linux/magic.h>
#include <linux/slab.h>
#include <linux/cleancache.h>
#include <linux/ratelimit.h>
#include <linux/btrfs.h>
#include "delayed-inode.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "hash.h"
#include "props.h"
#include "xattr.h"
#include "volumes.h"
#include "export.h"
#include "compression.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "free-space-cache.h"
#include "backref.h"
#include "tests/btrfs-tests.h"

#include "qgroup.h"
#define CREATE_TRACE_POINTS
#include <trace/events/btrfs.h>

static const struct super_operations btrfs_super_ops;
static struct file_system_type btrfs_fs_type;

static int btrfs_remount(struct super_block *sb, int *flags, char *data);

const char *btrfs_decode_error(int errno)
{
	char *errstr = "unknown";

	switch (errno) {
	case -EIO:
		errstr = "IO failure";
		break;
	case -ENOMEM:
		errstr = "Out of memory";
		break;
	case -EROFS:
		errstr = "Readonly filesystem";
		break;
	case -EEXIST:
		errstr = "Object already exists";
		break;
	case -ENOSPC:
		errstr = "No space left";
		break;
	case -ENOENT:
		errstr = "No such entry";
		break;
	}

	return errstr;
}

static void save_error_info(struct btrfs_fs_info *fs_info)
{
	/*
	 * today we only save the error info into ram.  Long term we'll
	 * also send it down to the disk
	 */
	set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
}

/* btrfs handle error by forcing the filesystem readonly */
static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
{
	struct super_block *sb = fs_info->sb;

	if (sb->s_flags & MS_RDONLY)
		return;

	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
		sb->s_flags |= MS_RDONLY;
		btrfs_info(fs_info, "forced readonly");
		/*
		 * Note that a running device replace operation is not
		 * canceled here although there is no way to update
		 * the progress. It would add the risk of a deadlock,
		 * therefore the canceling is ommited. The only penalty
		 * is that some I/O remains active until the procedure
		 * completes. The next time when the filesystem is
		 * mounted writeable again, the device replace
		 * operation continues.
		 */
	}
}

/*
 * __btrfs_std_error decodes expected errors from the caller and
 * invokes the approciate error response.
 */
__cold
void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
		       unsigned int line, int errno, const char *fmt, ...)
{
	struct super_block *sb = fs_info->sb;
#ifdef CONFIG_PRINTK
	const char *errstr;
#endif

	/*
	 * Special case: if the error is EROFS, and we're already
	 * under MS_RDONLY, then it is safe here.
	 */
	if (errno == -EROFS && (sb->s_flags & MS_RDONLY))
  		return;

#ifdef CONFIG_PRINTK
	errstr = btrfs_decode_error(errno);
	if (fmt) {
		struct va_format vaf;
		va_list args;

		va_start(args, fmt);
		vaf.fmt = fmt;
		vaf.va = &args;

		printk(KERN_CRIT
			"BTRFS: error (device %s) in %s:%d: errno=%d %s (%pV)\n",
			sb->s_id, function, line, errno, errstr, &vaf);
		va_end(args);
	} else {
		printk(KERN_CRIT "BTRFS: error (device %s) in %s:%d: errno=%d %s\n",
			sb->s_id, function, line, errno, errstr);
	}
#endif

	/* Don't go through full error handling during mount */
	save_error_info(fs_info);
	if (sb->s_flags & MS_BORN)
		btrfs_handle_error(fs_info);
}

#ifdef CONFIG_PRINTK
static const char * const logtypes[] = {
	"emergency",
	"alert",
	"critical",
	"error",
	"warning",
	"notice",
	"info",
	"debug",
};

void btrfs_printk(const struct btrfs_fs_info *fs_info, const char *fmt, ...)
{
	struct super_block *sb = fs_info->sb;
	char lvl[4];
	struct va_format vaf;
	va_list args;
	const char *type = logtypes[4];
	int kern_level;

	va_start(args, fmt);

	kern_level = printk_get_level(fmt);
	if (kern_level) {
		size_t size = printk_skip_level(fmt) - fmt;
		memcpy(lvl, fmt,  size);
		lvl[size] = '\0';
		fmt += size;
		type = logtypes[kern_level - '0'];
	} else
		*lvl = '\0';

	vaf.fmt = fmt;
	vaf.va = &args;

	printk("%sBTRFS %s (device %s): %pV\n", lvl, type, sb->s_id, &vaf);

	va_end(args);
}
#endif

/*
 * We only mark the transaction aborted and then set the file system read-only.
 * This will prevent new transactions from starting or trying to join this
 * one.
 *
 * This means that error recovery at the call site is limited to freeing
 * any local memory allocations and passing the error code up without
 * further cleanup. The transaction should complete as it normally would
 * in the call path but will return -EIO.
 *
 * We'll complete the cleanup in btrfs_end_transaction and
 * btrfs_commit_transaction.
 */
__cold
void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root, const char *function,
			       unsigned int line, int errno)
{
	trans->aborted = errno;
	/* Nothing used. The other threads that have joined this
	 * transaction may be able to continue. */
	if (!trans->blocks_used && list_empty(&trans->new_bgs)) {
		const char *errstr;

		errstr = btrfs_decode_error(errno);
		btrfs_warn(root->fs_info,
		           "%s:%d: Aborting unused transaction(%s).",
		           function, line, errstr);
		return;
	}
	ACCESS_ONCE(trans->transaction->aborted) = errno;
	/* Wake up anybody who may be waiting on this transaction */
	wake_up(&root->fs_info->transaction_wait);
	wake_up(&root->fs_info->transaction_blocked_wait);
	__btrfs_std_error(root->fs_info, function, line, errno, NULL);
}
/*
 * __btrfs_panic decodes unexpected, fatal errors from the caller,
 * issues an alert, and either panics or BUGs, depending on mount options.
 */
__cold
void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
		   unsigned int line, int errno, const char *fmt, ...)
{
	char *s_id = "<unknown>";
	const char *errstr;
	struct va_format vaf = { .fmt = fmt };
	va_list args;

	if (fs_info)
		s_id = fs_info->sb->s_id;

	va_start(args, fmt);
	vaf.va = &args;

	errstr = btrfs_decode_error(errno);
	if (fs_info && (fs_info->mount_opt & BTRFS_MOUNT_PANIC_ON_FATAL_ERROR))
		panic(KERN_CRIT "BTRFS panic (device %s) in %s:%d: %pV (errno=%d %s)\n",
			s_id, function, line, &vaf, errno, errstr);

	btrfs_crit(fs_info, "panic in %s:%d: %pV (errno=%d %s)",
		   function, line, &vaf, errno, errstr);
	va_end(args);
	/* Caller calls BUG() */
}

static void btrfs_put_super(struct super_block *sb)
{
	close_ctree(btrfs_sb(sb)->tree_root);
}

enum {
	Opt_degraded, Opt_subvol, Opt_subvolid, Opt_device, Opt_nodatasum,
	Opt_nodatacow, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd,
	Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, Opt_compress,
	Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
	Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
	Opt_space_cache, Opt_space_cache_version, Opt_clear_cache,
	Opt_user_subvol_rm_allowed, Opt_enospc_debug, Opt_subvolrootid,
	Opt_defrag, Opt_inode_cache, Opt_no_space_cache, Opt_recovery,
	Opt_skip_balance, Opt_check_integrity,
	Opt_check_integrity_including_extent_data,
	Opt_check_integrity_print_mask, Opt_fatal_errors, Opt_rescan_uuid_tree,
	Opt_commit_interval, Opt_barrier, Opt_nodefrag, Opt_nodiscard,
	Opt_noenospc_debug, Opt_noflushoncommit, Opt_acl, Opt_datacow,
	Opt_datasum, Opt_treelog, Opt_noinode_cache, Opt_usebackuproot,
	Opt_nologreplay, Opt_norecovery,
#ifdef CONFIG_BTRFS_DEBUG
	Opt_fragment_data, Opt_fragment_metadata, Opt_fragment_all,
#endif
	Opt_err,
};

static const match_table_t tokens = {
	{Opt_degraded, "degraded"},
	{Opt_subvol, "subvol=%s"},
	{Opt_subvolid, "subvolid=%s"},
	{Opt_device, "device=%s"},
	{Opt_nodatasum, "nodatasum"},
	{Opt_datasum, "datasum"},
	{Opt_nodatacow, "nodatacow"},
	{Opt_datacow, "datacow"},
	{Opt_nobarrier, "nobarrier"},
	{Opt_barrier, "barrier"},
	{Opt_max_inline, "max_inline=%s"},
	{Opt_alloc_start, "alloc_start=%s"},
	{Opt_thread_pool, "thread_pool=%d"},
	{Opt_compress, "compress"},
	{Opt_compress_type, "compress=%s"},
	{Opt_compress_force, "compress-force"},
	{Opt_compress_force_type, "compress-force=%s"},
	{Opt_ssd, "ssd"},
	{Opt_ssd_spread, "ssd_spread"},
	{Opt_nossd, "nossd"},
	{Opt_acl, "acl"},
	{Opt_noacl, "noacl"},
	{Opt_notreelog, "notreelog"},
	{Opt_treelog, "treelog"},
	{Opt_nologreplay, "nologreplay"},
	{Opt_norecovery, "norecovery"},
	{Opt_flushoncommit, "flushoncommit"},
	{Opt_noflushoncommit, "noflushoncommit"},
	{Opt_ratio, "metadata_ratio=%d"},
	{Opt_discard, "discard"},
	{Opt_nodiscard, "nodiscard"},
	{Opt_space_cache, "space_cache"},
	{Opt_space_cache_version, "space_cache=%s"},
	{Opt_clear_cache, "clear_cache"},
	{Opt_user_subvol_rm_allowed, "user_subvol_rm_allowed"},
	{Opt_enospc_debug, "enospc_debug"},
	{Opt_noenospc_debug, "noenospc_debug"},
	{Opt_subvolrootid, "subvolrootid=%d"},
	{Opt_defrag, "autodefrag"},
	{Opt_nodefrag, "noautodefrag"},
	{Opt_inode_cache, "inode_cache"},
	{Opt_noinode_cache, "noinode_cache"},
	{Opt_no_space_cache, "nospace_cache"},
	{Opt_recovery, "recovery"}, /* deprecated */
	{Opt_usebackuproot, "usebackuproot"},
	{Opt_skip_balance, "skip_balance"},
	{Opt_check_integrity, "check_int"},
	{Opt_check_integrity_including_extent_data, "check_int_data"},
	{Opt_check_integrity_print_mask, "check_int_print_mask=%d"},
	{Opt_rescan_uuid_tree, "rescan_uuid_tree"},
	{Opt_fatal_errors, "fatal_errors=%s"},
	{Opt_commit_interval, "commit=%d"},
#ifdef CONFIG_BTRFS_DEBUG
	{Opt_fragment_data, "fragment=data"},
	{Opt_fragment_metadata, "fragment=metadata"},
	{Opt_fragment_all, "fragment=all"},
#endif
	{Opt_err, NULL},
};

/*
 * Regular mount options parser.  Everything that is needed only when
 * reading in a new superblock is parsed here.
 * XXX JDM: This needs to be cleaned up for remount.
 */
int btrfs_parse_options(struct btrfs_root *root, char *options,
			unsigned long new_flags)
{
	struct btrfs_fs_info *info = root->fs_info;
	substring_t args[MAX_OPT_ARGS];
	char *p, *num, *orig = NULL;
	u64 cache_gen;
	int intarg;
	int ret = 0;
	char *compress_type;
	bool compress_force = false;
	enum btrfs_compression_type saved_compress_type;
	bool saved_compress_force;
	int no_compress = 0;

	cache_gen = btrfs_super_cache_generation(root->fs_info->super_copy);
	if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE))
		btrfs_set_opt(info->mount_opt, FREE_SPACE_TREE);
	else if (cache_gen)
		btrfs_set_opt(info->mount_opt, SPACE_CACHE);

	/*
	 * Even the options are empty, we still need to do extra check
	 * against new flags
	 */
	if (!options)
		goto check;

	/*
	 * strsep changes the string, duplicate it because parse_options
	 * gets called twice
	 */
	options = kstrdup(options, GFP_NOFS);
	if (!options)
		return -ENOMEM;

	orig = options;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_degraded:
			btrfs_info(root->fs_info, "allowing degraded mounts");
			btrfs_set_opt(info->mount_opt, DEGRADED);
			break;
		case Opt_subvol:
		case Opt_subvolid:
		case Opt_subvolrootid:
		case Opt_device:
			/*
			 * These are parsed by btrfs_parse_early_options
			 * and can be happily ignored here.
			 */
			break;
		case Opt_nodatasum:
			btrfs_set_and_info(root, NODATASUM,
					   "setting nodatasum");
			break;
		case Opt_datasum:
			if (btrfs_test_opt(root, NODATASUM)) {
				if (btrfs_test_opt(root, NODATACOW))
					btrfs_info(root->fs_info, "setting datasum, datacow enabled");
				else
					btrfs_info(root->fs_info, "setting datasum");
			}
			btrfs_clear_opt(info->mount_opt, NODATACOW);
			btrfs_clear_opt(info->mount_opt, NODATASUM);
			break;
		case Opt_nodatacow:
			if (!btrfs_test_opt(root, NODATACOW)) {
				if (!btrfs_test_opt(root, COMPRESS) ||
				    !btrfs_test_opt(root, FORCE_COMPRESS)) {
					btrfs_info(root->fs_info,
						   "setting nodatacow, compression disabled");
				} else {
					btrfs_info(root->fs_info, "setting nodatacow");
				}
			}
			btrfs_clear_opt(info->mount_opt, COMPRESS);
			btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
			btrfs_set_opt(info->mount_opt, NODATACOW);
			btrfs_set_opt(info->mount_opt, NODATASUM);
			break;
		case Opt_datacow:
			btrfs_clear_and_info(root, NODATACOW,
					     "setting datacow");
			break;
		case Opt_compress_force:
		case Opt_compress_force_type:
			compress_force = true;
			/* Fallthrough */
		case Opt_compress:
		case Opt_compress_type:
			saved_compress_type = btrfs_test_opt(root, COMPRESS) ?
				info->compress_type : BTRFS_COMPRESS_NONE;
			saved_compress_force =
				btrfs_test_opt(root, FORCE_COMPRESS);
			if (token == Opt_compress ||
			    token == Opt_compress_force ||
			    strcmp(args[0].from, "zlib") == 0) {
				compress_type = "zlib";
				info->compress_type = BTRFS_COMPRESS_ZLIB;
				btrfs_set_opt(info->mount_opt, COMPRESS);
				btrfs_clear_opt(info->mount_opt, NODATACOW);
				btrfs_clear_opt(info->mount_opt, NODATASUM);
				no_compress = 0;
			} else if (strcmp(args[0].from, "lzo") == 0) {
				compress_type = "lzo";
				info->compress_type = BTRFS_COMPRESS_LZO;
				btrfs_set_opt(info->mount_opt, COMPRESS);
				btrfs_clear_opt(info->mount_opt, NODATACOW);
				btrfs_clear_opt(info->mount_opt, NODATASUM);
				btrfs_set_fs_incompat(info, COMPRESS_LZO);
				no_compress = 0;
			} else if (strncmp(args[0].from, "no", 2) == 0) {
				compress_type = "no";
				btrfs_clear_opt(info->mount_opt, COMPRESS);
				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
				compress_force = false;
				no_compress++;
			} else {
				ret = -EINVAL;
				goto out;
			}

			if (compress_force) {
				btrfs_set_opt(info->mount_opt, FORCE_COMPRESS);
			} else {
				/*
				 * If we remount from compress-force=xxx to
				 * compress=xxx, we need clear FORCE_COMPRESS
				 * flag, otherwise, there is no way for users
				 * to disable forcible compression separately.
				 */
				btrfs_clear_opt(info->mount_opt, FORCE_COMPRESS);
			}
			if ((btrfs_test_opt(root, COMPRESS) &&
			     (info->compress_type != saved_compress_type ||
			      compress_force != saved_compress_force)) ||
			    (!btrfs_test_opt(root, COMPRESS) &&
			     no_compress == 1)) {
				btrfs_info(root->fs_info,
					   "%s %s compression",
					   (compress_force) ? "force" : "use",
					   compress_type);
			}
			compress_force = false;
			break;
		case Opt_ssd:
			btrfs_set_and_info(root, SSD,
					   "use ssd allocation scheme");
			break;
		case Opt_ssd_spread:
			btrfs_set_and_info(root, SSD_SPREAD,
					   "use spread ssd allocation scheme");
			btrfs_set_opt(info->mount_opt, SSD);
			break;
		case Opt_nossd:
			btrfs_set_and_info(root, NOSSD,
					     "not using ssd allocation scheme");
			btrfs_clear_opt(info->mount_opt, SSD);
			break;
		case Opt_barrier:
			btrfs_clear_and_info(root, NOBARRIER,
					     "turning on barriers");
			break;
		case Opt_nobarrier:
			btrfs_set_and_info(root, NOBARRIER,
					   "turning off barriers");
			break;
		case Opt_thread_pool:
			ret = match_int(&args[0], &intarg);
			if (ret) {
				goto out;
			} else if (intarg > 0) {
				info->thread_pool_size = intarg;
			} else {
				ret = -EINVAL;
				goto out;
			}
			break;
		case Opt_max_inline:
			num = match_strdup(&args[0]);
			if (num) {
				info->max_inline = memparse(num, NULL);
				kfree(num);

				if (info->max_inline) {
					info->max_inline = min_t(u64,
						info->max_inline,
						root->sectorsize);
				}
				btrfs_info(root->fs_info, "max_inline at %llu",
					info->max_inline);
			} else {
				ret = -ENOMEM;
				goto out;
			}
			break;
		case Opt_alloc_start:
			num = match_strdup(&args[0]);
			if (num) {
				mutex_lock(&info->chunk_mutex);
				info->alloc_start = memparse(num, NULL);
				mutex_unlock(&info->chunk_mutex);
				kfree(num);
				btrfs_info(root->fs_info, "allocations start at %llu",
					info->alloc_start);
			} else {
				ret = -ENOMEM;
				goto out;
			}
			break;
		case Opt_acl:
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
			root->fs_info->sb->s_flags |= MS_POSIXACL;
			break;
#else
			btrfs_err(root->fs_info,
				"support for ACL not compiled in!");
			ret = -EINVAL;
			goto out;
#endif
		case Opt_noacl:
			root->fs_info->sb->s_flags &= ~MS_POSIXACL;
			break;
		case Opt_notreelog:
			btrfs_set_and_info(root, NOTREELOG,
					   "disabling tree log");
			break;
		case Opt_treelog:
			btrfs_clear_and_info(root, NOTREELOG,
					     "enabling tree log");
			break;
		case Opt_norecovery:
		case Opt_nologreplay:
			btrfs_set_and_info(root, NOLOGREPLAY,
					   "disabling log replay at mount time");
			break;
		case Opt_flushoncommit:
			btrfs_set_and_info(root, FLUSHONCOMMIT,
					   "turning on flush-on-commit");
			break;
		case Opt_noflushoncommit:
			btrfs_clear_and_info(root, FLUSHONCOMMIT,
					     "turning off flush-on-commit");
			break;
		case Opt_ratio:
			ret = match_int(&args[0], &intarg);
			if (ret) {
				goto out;
			} else if (intarg >= 0) {
				info->metadata_ratio = intarg;
				btrfs_info(root->fs_info, "metadata ratio %d",
				       info->metadata_ratio);
			} else {
				ret = -EINVAL;
				goto out;
			}
			break;
		case Opt_discard:
			btrfs_set_and_info(root, DISCARD,
					   "turning on discard");
			break;
		case Opt_nodiscard:
			btrfs_clear_and_info(root, DISCARD,
					     "turning off discard");
			break;
		case Opt_space_cache:
		case Opt_space_cache_version:
			if (token == Opt_space_cache ||
			    strcmp(args[0].from, "v1") == 0) {
				btrfs_clear_opt(root->fs_info->mount_opt,
						FREE_SPACE_TREE);
				btrfs_set_and_info(root, SPACE_CACHE,
						   "enabling disk space caching");
			} else if (strcmp(args[0].from, "v2") == 0) {
				btrfs_clear_opt(root->fs_info->mount_opt,
						SPACE_CACHE);
				btrfs_set_and_info(root, FREE_SPACE_TREE,
						   "enabling free space tree");
			} else {
				ret = -EINVAL;
				goto out;
			}
			break;
		case Opt_rescan_uuid_tree:
			btrfs_set_opt(info->mount_opt, RESCAN_UUID_TREE);
			break;
		case Opt_no_space_cache:
			if (btrfs_test_opt(root, SPACE_CACHE)) {
				btrfs_clear_and_info(root, SPACE_CACHE,
						     "disabling disk space caching");
			}
			if (btrfs_test_opt(root, FREE_SPACE_TREE)) {
				btrfs_clear_and_info(root, FREE_SPACE_TREE,
						     "disabling free space tree");
			}
			break;
		case Opt_inode_cache:
			btrfs_set_pending_and_info(info, INODE_MAP_CACHE,
					   "enabling inode map caching");
			break;
		case Opt_noinode_cache:
			btrfs_clear_pending_and_info(info, INODE_MAP_CACHE,
					     "disabling inode map caching");
			break;
		case Opt_clear_cache:
			btrfs_set_and_info(root, CLEAR_CACHE,
					   "force clearing of disk cache");
			break;
		case Opt_user_subvol_rm_allowed:
			btrfs_set_opt(info->mount_opt, USER_SUBVOL_RM_ALLOWED);
			break;
		case Opt_enospc_debug:
			btrfs_set_opt(info->mount_opt, ENOSPC_DEBUG);
			break;
		case Opt_noenospc_debug:
			btrfs_clear_opt(info->mount_opt, ENOSPC_DEBUG);
			break;
		case Opt_defrag:
			btrfs_set_and_info(root, AUTO_DEFRAG,
					   "enabling auto defrag");
			break;
		case Opt_nodefrag:
			btrfs_clear_and_info(root, AUTO_DEFRAG,
					     "disabling auto defrag");
			break;
		case Opt_recovery:
			btrfs_warn(root->fs_info,
				   "'recovery' is deprecated, use 'usebackuproot' instead");
		case Opt_usebackuproot:
			btrfs_info(root->fs_info,
				   "trying to use backup root at mount time");
			btrfs_set_opt(info->mount_opt, USEBACKUPROOT);
			break;
		case Opt_skip_balance:
			btrfs_set_opt(info->mount_opt, SKIP_BALANCE);
			break;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
		case Opt_check_integrity_including_extent_data:
			btrfs_info(root->fs_info,
				   "enabling check integrity including extent data");
			btrfs_set_opt(info->mount_opt,
				      CHECK_INTEGRITY_INCLUDING_EXTENT_DATA);
			btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
			break;
		case Opt_check_integrity:
			btrfs_info(root->fs_info, "enabling check integrity");
			btrfs_set_opt(info->mount_opt, CHECK_INTEGRITY);
			break;
		case Opt_check_integrity_print_mask:
			ret = match_int(&args[0], &intarg);
			if (ret) {
				goto out;
			} else if (intarg >= 0) {
				info->check_integrity_print_mask = intarg;
				btrfs_info(root->fs_info, "check_integrity_print_mask 0x%x",
				       info->check_integrity_print_mask);
			} else {
				ret = -EINVAL;
				goto out;
			}
			break;
#else
		case Opt_check_integrity_including_extent_data:
		case Opt_check_integrity:
		case Opt_check_integrity_print_mask:
			btrfs_err(root->fs_info,
				"support for check_integrity* not compiled in!");
			ret = -EINVAL;
			goto out;
#endif
		case Opt_fatal_errors:
			if (strcmp(args[0].from, "panic") == 0)
				btrfs_set_opt(info->mount_opt,
					      PANIC_ON_FATAL_ERROR);
			else if (strcmp(args[0].from, "bug") == 0)
				btrfs_clear_opt(info->mount_opt,
					      PANIC_ON_FATAL_ERROR);
			else {
				ret = -EINVAL;
				goto out;
			}
			break;
		case Opt_commit_interval:
			intarg = 0;
			ret = match_int(&args[0], &intarg);
			if (ret < 0) {
				btrfs_err(root->fs_info, "invalid commit interval");
				ret = -EINVAL;
				goto out;
			}
			if (intarg > 0) {
				if (intarg > 300) {
					btrfs_warn(root->fs_info, "excessive commit interval %d",
							intarg);
				}
				info->commit_interval = intarg;
			} else {
				btrfs_info(root->fs_info, "using default commit interval %ds",
				    BTRFS_DEFAULT_COMMIT_INTERVAL);
				info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
			}
			break;
#ifdef CONFIG_BTRFS_DEBUG
		case Opt_fragment_all:
			btrfs_info(root->fs_info, "fragmenting all space");
			btrfs_set_opt(info->mount_opt, FRAGMENT_DATA);
			btrfs_set_opt(info->mount_opt, FRAGMENT_METADATA);
			break;
		case Opt_fragment_metadata:
			btrfs_info(root->fs_info, "fragmenting metadata");
			btrfs_set_opt(info->mount_opt,
				      FRAGMENT_METADATA);
			break;
		case Opt_fragment_data:
			btrfs_info(root->fs_info, "fragmenting data");
			btrfs_set_opt(info->mount_opt, FRAGMENT_DATA);
			break;
#endif
		case Opt_err:
			btrfs_info(root->fs_info, "unrecognized mount option '%s'", p);
			ret = -EINVAL;
			goto out;
		default:
			break;
		}
	}
check:
	/*
	 * Extra check for current option against current flag
	 */
	if (btrfs_test_opt(root, NOLOGREPLAY) && !(new_flags & MS_RDONLY)) {
		btrfs_err(root->fs_info,
			  "nologreplay must be used with ro mount option");
		ret = -EINVAL;
	}
out:
	if (btrfs_fs_compat_ro(root->fs_info, FREE_SPACE_TREE) &&
	    !btrfs_test_opt(root, FREE_SPACE_TREE) &&
	    !btrfs_test_opt(root, CLEAR_CACHE)) {
		btrfs_err(root->fs_info, "cannot disable free space tree");
		ret = -EINVAL;

	}
	if (!ret && btrfs_test_opt(root, SPACE_CACHE))
		btrfs_info(root->fs_info, "disk space caching is enabled");
	if (!ret && btrfs_test_opt(root, FREE_SPACE_TREE))
		btrfs_info(root->fs_info, "using free space tree");
	kfree(orig);
	return ret;
}

/*
 * Parse mount options that are required early in the mount process.
 *
 * All other options will be parsed on much later in the mount process and
 * only when we need to allocate a new super block.
 */
static int btrfs_parse_early_options(const char *options, fmode_t flags,
		void *holder, char **subvol_name, u64 *subvol_objectid,
		struct btrfs_fs_devices **fs_devices)
{
	substring_t args[MAX_OPT_ARGS];
	char *device_name, *opts, *orig, *p;
	char *num = NULL;
	int error = 0;

	if (!options)
		return 0;

	/*
	 * strsep changes the string, duplicate it because parse_options
	 * gets called twice
	 */
	opts = kstrdup(options, GFP_KERNEL);
	if (!opts)
		return -ENOMEM;
	orig = opts;

	while ((p = strsep(&opts, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_subvol:
			kfree(*subvol_name);
			*subvol_name = match_strdup(&args[0]);
			if (!*subvol_name) {
				error = -ENOMEM;
				goto out;
			}
			break;
		case Opt_subvolid:
			num = match_strdup(&args[0]);
			if (num) {
				*subvol_objectid = memparse(num, NULL);
				kfree(num);
				/* we want the original fs_tree */
				if (!*subvol_objectid)
					*subvol_objectid =
						BTRFS_FS_TREE_OBJECTID;
			} else {
				error = -EINVAL;
				goto out;
			}
			break;
		case Opt_subvolrootid:
			printk(KERN_WARNING
				"BTRFS: 'subvolrootid' mount option is deprecated and has "
				"no effect\n");
			break;
		case Opt_device:
			device_name = match_strdup(&args[0]);
			if (!device_name) {
				error = -ENOMEM;
				goto out;
			}
			error = btrfs_scan_one_device(device_name,
					flags, holder, fs_devices);
			kfree(device_name);
			if (error)
				goto out;
			break;
		default:
			break;
		}
	}

out:
	kfree(orig);
	return error;
}

static char *get_subvol_name_from_objectid(struct btrfs_fs_info *fs_info,
					   u64 subvol_objectid)
{
	struct btrfs_root *root = fs_info->tree_root;
	struct btrfs_root *fs_root;
	struct btrfs_root_ref *root_ref;
	struct btrfs_inode_ref *inode_ref;
	struct btrfs_key key;
	struct btrfs_path *path = NULL;
	char *name = NULL, *ptr;
	u64 dirid;
	int len;
	int ret;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto err;
	}
	path->leave_spinning = 1;

	name = kmalloc(PATH_MAX, GFP_NOFS);
	if (!name) {
		ret = -ENOMEM;
		goto err;
	}
	ptr = name + PATH_MAX - 1;
	ptr[0] = '\0';

	/*
	 * Walk up the subvolume trees in the tree of tree roots by root
	 * backrefs until we hit the top-level subvolume.
	 */
	while (subvol_objectid != BTRFS_FS_TREE_OBJECTID) {
		key.objectid = subvol_objectid;
		key.type = BTRFS_ROOT_BACKREF_KEY;
		key.offset = (u64)-1;

		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
		if (ret < 0) {
			goto err;
		} else if (ret > 0) {
			ret = btrfs_previous_item(root, path, subvol_objectid,
						  BTRFS_ROOT_BACKREF_KEY);
			if (ret < 0) {
				goto err;
			} else if (ret > 0) {
				ret = -ENOENT;
				goto err;
			}
		}

		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		subvol_objectid = key.offset;

		root_ref = btrfs_item_ptr(path->nodes[0], path->slots[0],
					  struct btrfs_root_ref);
		len = btrfs_root_ref_name_len(path->nodes[0], root_ref);
		ptr -= len + 1;
		if (ptr < name) {
			ret = -ENAMETOOLONG;
			goto err;
		}
		read_extent_buffer(path->nodes[0], ptr + 1,
				   (unsigned long)(root_ref + 1), len);
		ptr[0] = '/';
		dirid = btrfs_root_ref_dirid(path->nodes[0], root_ref);
		btrfs_release_path(path);

		key.objectid = subvol_objectid;
		key.type = BTRFS_ROOT_ITEM_KEY;
		key.offset = (u64)-1;
		fs_root = btrfs_read_fs_root_no_name(fs_info, &key);
		if (IS_ERR(fs_root)) {
			ret = PTR_ERR(fs_root);
			goto err;
		}

		/*
		 * Walk up the filesystem tree by inode refs until we hit the
		 * root directory.
		 */
		while (dirid != BTRFS_FIRST_FREE_OBJECTID) {
			key.objectid = dirid;
			key.type = BTRFS_INODE_REF_KEY;
			key.offset = (u64)-1;

			ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0);
			if (ret < 0) {
				goto err;
			} else if (ret > 0) {
				ret = btrfs_previous_item(fs_root, path, dirid,
							  BTRFS_INODE_REF_KEY);
				if (ret < 0) {
					goto err;
				} else if (ret > 0) {
					ret = -ENOENT;
					goto err;
				}
			}

			btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
			dirid = key.offset;

			inode_ref = btrfs_item_ptr(path->nodes[0],
						   path->slots[0],
						   struct btrfs_inode_ref);
			len = btrfs_inode_ref_name_len(path->nodes[0],
						       inode_ref);
			ptr -= len + 1;
			if (ptr < name) {
				ret = -ENAMETOOLONG;
				goto err;
			}
			read_extent_buffer(path->nodes[0], ptr + 1,
					   (unsigned long)(inode_ref + 1), len);
			ptr[0] = '/';
			btrfs_release_path(path);
		}
	}

	btrfs_free_path(path);
	if (ptr == name + PATH_MAX - 1) {
		name[0] = '/';
		name[1] = '\0';
	} else {
		memmove(name, ptr, name + PATH_MAX - ptr);
	}
	return name;

err:
	btrfs_free_path(path);
	kfree(name);
	return ERR_PTR(ret);
}

static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objectid)
{
	struct btrfs_root *root = fs_info->tree_root;
	struct btrfs_dir_item *di;
	struct btrfs_path *path;
	struct btrfs_key location;
	u64 dir_id;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	path->leave_spinning = 1;

	/*
	 * Find the "default" dir item which points to the root item that we
	 * will mount by default if we haven't been given a specific subvolume
	 * to mount.
	 */
	dir_id = btrfs_super_root_dir(fs_info->super_copy);
	di = btrfs_lookup_dir_item(NULL, root, path, dir_id, "default", 7, 0);
	if (IS_ERR(di)) {
		btrfs_free_path(path);
		return PTR_ERR(di);
	}
	if (!di) {
		/*
		 * Ok the default dir item isn't there.  This is weird since
		 * it's always been there, but don't freak out, just try and
		 * mount the top-level subvolume.
		 */
		btrfs_free_path(path);
		*objectid = BTRFS_FS_TREE_OBJECTID;
		return 0;
	}

	btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
	btrfs_free_path(path);
	*objectid = location.objectid;
	return 0;
}

static int btrfs_fill_super(struct super_block *sb,
			    struct btrfs_fs_devices *fs_devices,
			    void *data, int silent)
{
	struct inode *inode;
	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
	struct btrfs_key key;
	int err;

	sb->s_maxbytes = MAX_LFS_FILESIZE;
	sb->s_magic = BTRFS_SUPER_MAGIC;
	sb->s_op = &btrfs_super_ops;
	sb->s_d_op = &btrfs_dentry_operations;
	sb->s_export_op = &btrfs_export_ops;
	sb->s_xattr = btrfs_xattr_handlers;
	sb->s_time_gran = 1;
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
	sb->s_flags |= MS_POSIXACL;
#endif
	sb->s_flags |= MS_I_VERSION;
	sb->s_iflags |= SB_I_CGROUPWB;
	err = open_ctree(sb, fs_devices, (char *)data);
	if (err) {
		printk(KERN_ERR "BTRFS: open_ctree failed\n");
		return err;
	}

	key.objectid = BTRFS_FIRST_FREE_OBJECTID;
	key.type = BTRFS_INODE_ITEM_KEY;
	key.offset = 0;
	inode = btrfs_iget(sb, &key, fs_info->fs_root, NULL);
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		goto fail_close;
	}

	sb->s_root = d_make_root(inode);
	if (!sb->s_root) {
		err = -ENOMEM;
		goto fail_close;
	}

	save_mount_options(sb, data);
	cleancache_init_fs(sb);
	sb->s_flags |= MS_ACTIVE;
	return 0;

fail_close:
	close_ctree(fs_info->tree_root);
	return err;
}

int btrfs_sync_fs(struct super_block *sb, int wait)
{
	struct btrfs_trans_handle *trans;
	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
	struct btrfs_root *root = fs_info->tree_root;

	trace_btrfs_sync_fs(wait);

	if (!wait) {
		filemap_flush(fs_info->btree_inode->i_mapping);
		return 0;
	}

	btrfs_wait_ordered_roots(fs_info, -1);

	trans = btrfs_attach_transaction_barrier(root);
	if (IS_ERR(trans)) {
		/* no transaction, don't bother */
		if (PTR_ERR(trans) == -ENOENT) {
			/*
			 * Exit unless we have some pending changes
			 * that need to go through commit
			 */
			if (fs_info->pending_changes == 0)
				return 0;
			/*
			 * A non-blocking test if the fs is frozen. We must not
			 * start a new transaction here otherwise a deadlock
			 * happens. The pending operations are delayed to the
			 * next commit after thawing.
			 */
			if (__sb_start_write(sb, SB_FREEZE_WRITE, false))
				__sb_end_write(sb, SB_FREEZE_WRITE);
			else
				return 0;
			trans = btrfs_start_transaction(root, 0);
		}
		if (IS_ERR(trans))
			return PTR_ERR(trans);
	}
	return btrfs_commit_transaction(trans, root);
}

static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
{
	struct btrfs_fs_info *info = btrfs_sb(dentry->d_sb);
	struct btrfs_root *root = info->tree_root;
	char *compress_type;

	if (btrfs_test_opt(root, DEGRADED))
		seq_puts(seq, ",degraded");
	if (btrfs_test_opt(root, NODATASUM))
		seq_puts(seq, ",nodatasum");
	if (btrfs_test_opt(root, NODATACOW))
		seq_puts(seq, ",nodatacow");
	if (btrfs_test_opt(root, NOBARRIER))
		seq_puts(seq, ",nobarrier");
	if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE)
		seq_printf(seq, ",max_inline=%llu", info->max_inline);
	if (info->alloc_start != 0)
		seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
	if (info->thread_pool_size !=  min_t(unsigned long,
					     num_online_cpus() + 2, 8))
		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
	if (btrfs_test_opt(root, COMPRESS)) {
		if (info->compress_type == BTRFS_COMPRESS_ZLIB)
			compress_type = "zlib";
		else
			compress_type = "lzo";
		if (btrfs_test_opt(root, FORCE_COMPRESS))
			seq_printf(seq, ",compress-force=%s", compress_type);
		else
			seq_printf(seq, ",compress=%s", compress_type);
	}
	if (btrfs_test_opt(root, NOSSD))
		seq_puts(seq, ",nossd");
	if (btrfs_test_opt(root, SSD_SPREAD))
		seq_puts(seq, ",ssd_spread");
	else if (btrfs_test_opt(root, SSD))
		seq_puts(seq, ",ssd");
	if (btrfs_test_opt(root, NOTREELOG))
		seq_puts(seq, ",notreelog");
	if (btrfs_test_opt(root, NOLOGREPLAY))
		seq_puts(seq, ",nologreplay");
	if (btrfs_test_opt(root, FLUSHONCOMMIT))
		seq_puts(seq, ",flushoncommit");
	if (btrfs_test_opt(root, DISCARD))
		seq_puts(seq, ",discard");
	if (!(root->fs_info->sb->s_flags & MS_POSIXACL))
		seq_puts(seq, ",noacl");
	if (btrfs_test_opt(root, SPACE_CACHE))
		seq_puts(seq, ",space_cache");
	else if (btrfs_test_opt(root, FREE_SPACE_TREE))
		seq_puts(seq, ",space_cache=v2");
	else
		seq_puts(seq, ",nospace_cache");
	if (btrfs_test_opt(root, RESCAN_UUID_TREE))
		seq_puts(seq, ",rescan_uuid_tree");
	if (btrfs_test_opt(root, CLEAR_CACHE))
		seq_puts(seq, ",clear_cache");
	if (btrfs_test_opt(root, USER_SUBVOL_RM_ALLOWED))
		seq_puts(seq, ",user_subvol_rm_allowed");
	if (btrfs_test_opt(root, ENOSPC_DEBUG))
		seq_puts(seq, ",enospc_debug");
	if (btrfs_test_opt(root, AUTO_DEFRAG))
		seq_puts(seq, ",autodefrag");
	if (btrfs_test_opt(root, INODE_MAP_CACHE))
		seq_puts(seq, ",inode_cache");
	if (btrfs_test_opt(root, SKIP_BALANCE))
		seq_puts(seq, ",skip_balance");
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	if (btrfs_test_opt(root, CHECK_INTEGRITY_INCLUDING_EXTENT_DATA))
		seq_puts(seq, ",check_int_data");
	else if (btrfs_test_opt(root, CHECK_INTEGRITY))
		seq_puts(seq, ",check_int");
	if (info->check_integrity_print_mask)
		seq_printf(seq, ",check_int_print_mask=%d",
				info->check_integrity_print_mask);
#endif
	if (info->metadata_ratio)
		seq_printf(seq, ",metadata_ratio=%d",
				info->metadata_ratio);
	if (btrfs_test_opt(root, PANIC_ON_FATAL_ERROR))
		seq_puts(seq, ",fatal_errors=panic");
	if (info->commit_interval != BTRFS_DEFAULT_COMMIT_INTERVAL)
		seq_printf(seq, ",commit=%d", info->commit_interval);
#ifdef CONFIG_BTRFS_DEBUG
	if (btrfs_test_opt(root, FRAGMENT_DATA))
		seq_puts(seq, ",fragment=data");
	if (btrfs_test_opt(root, FRAGMENT_METADATA))
		seq_puts(seq, ",fragment=metadata");
#endif
	seq_printf(seq, ",subvolid=%llu",
		  BTRFS_I(d_inode(dentry))->root->root_key.objectid);
	seq_puts(seq, ",subvol=");
	seq_dentry(seq, dentry, " \t\n\\");
	return 0;
}

static int btrfs_test_super(struct super_block *s, void *data)
{
	struct btrfs_fs_info *p = data;
	struct btrfs_fs_info *fs_info = btrfs_sb(s);

	return fs_info->fs_devices == p->fs_devices;
}

static int btrfs_set_super(struct super_block *s, void *data)
{
	int err = set_anon_super(s, data);
	if (!err)
		s->s_fs_info = data;
	return err;
}

/*
 * subvolumes are identified by ino 256
 */
static inline int is_subvolume_inode(struct inode *inode)
{
	if (inode && inode->i_ino == BTRFS_FIRST_FREE_OBJECTID)
		return 1;
	return 0;
}

/*
 * This will add subvolid=0 to the argument string while removing any subvol=
 * and subvolid= arguments to make sure we get the top-level root for path
 * walking to the subvol we want.
 */
static char *setup_root_args(char *args)
{
	char *buf, *dst, *sep;

	if (!args)
		return kstrdup("subvolid=0", GFP_NOFS);

	/* The worst case is that we add ",subvolid=0" to the end. */
	buf = dst = kmalloc(strlen(args) + strlen(",subvolid=0") + 1, GFP_NOFS);
	if (!buf)
		return NULL;

	while (1) {
		sep = strchrnul(args, ',');
		if (!strstarts(args, "subvol=") &&
		    !strstarts(args, "subvolid=")) {
			memcpy(dst, args, sep - args);
			dst += sep - args;
			*dst++ = ',';
		}
		if (*sep)
			args = sep + 1;
		else
			break;
	}
	strcpy(dst, "subvolid=0");

	return buf;
}

static struct dentry *mount_subvol(const char *subvol_name, u64 subvol_objectid,
				   int flags, const char *device_name,
				   char *data)
{
	struct dentry *root;
	struct vfsmount *mnt = NULL;
	char *newargs;
	int ret;

	newargs = setup_root_args(data);
	if (!newargs) {
		root = ERR_PTR(-ENOMEM);
		goto out;
	}

	mnt = vfs_kern_mount(&btrfs_fs_type, flags, device_name, newargs);
	if (PTR_ERR_OR_ZERO(mnt) == -EBUSY) {
		if (flags & MS_RDONLY) {
			mnt = vfs_kern_mount(&btrfs_fs_type, flags & ~MS_RDONLY,
					     device_name, newargs);
		} else {
			mnt = vfs_kern_mount(&btrfs_fs_type, flags | MS_RDONLY,
					     device_name, newargs);
			if (IS_ERR(mnt)) {
				root = ERR_CAST(mnt);
				mnt = NULL;
				goto out;
			}

			down_write(&mnt->mnt_sb->s_umount);
			ret = btrfs_remount(mnt->mnt_sb, &flags, NULL);
			up_write(&mnt->mnt_sb->s_umount);
			if (ret < 0) {
				root = ERR_PTR(ret);
				goto out;
			}
		}
	}
	if (IS_ERR(mnt)) {
		root = ERR_CAST(mnt);
		mnt = NULL;
		goto out;
	}

	if (!subvol_name) {
		if (!subvol_objectid) {
			ret = get_default_subvol_objectid(btrfs_sb(mnt->mnt_sb),
							  &subvol_objectid);
			if (ret) {
				root = ERR_PTR(ret);
				goto out;
			}
		}
		subvol_name = get_subvol_name_from_objectid(btrfs_sb(mnt->mnt_sb),
							    subvol_objectid);
		if (IS_ERR(subvol_name)) {
			root = ERR_CAST(subvol_name);
			subvol_name = NULL;
			goto out;
		}

	}

	root = mount_subtree(mnt, subvol_name);
	/* mount_subtree() drops our reference on the vfsmount. */
	mnt = NULL;

	if (!IS_ERR(root)) {
		struct super_block *s = root->d_sb;
		struct inode *root_inode = d_inode(root);
		u64 root_objectid = BTRFS_I(root_inode)->root->root_key.objectid;

		ret = 0;
		if (!is_subvolume_inode(root_inode)) {
			pr_err("BTRFS: '%s' is not a valid subvolume\n",
			       subvol_name);
			ret = -EINVAL;
		}
		if (subvol_objectid && root_objectid != subvol_objectid) {
			/*
			 * This will also catch a race condition where a
			 * subvolume which was passed by ID is renamed and
			 * another subvolume is renamed over the old location.
			 */
			pr_err("BTRFS: subvol '%s' does not match subvolid %llu\n",
			       subvol_name, subvol_objectid);
			ret = -EINVAL;
		}
		if (ret) {
			dput(root);
			root = ERR_PTR(ret);
			deactivate_locked_super(s);
		}
	}

out:
	mntput(mnt);
	kfree(newargs);
	kfree(subvol_name);
	return root;
}

static int parse_security_options(char *orig_opts,
				  struct security_mnt_opts *sec_opts)
{
	char *secdata = NULL;
	int ret = 0;

	secdata = alloc_secdata();
	if (!secdata)
		return -ENOMEM;
	ret = security_sb_copy_data(orig_opts, secdata);
	if (ret) {
		free_secdata(secdata);
		return ret;
	}
	ret = security_sb_parse_opts_str(secdata, sec_opts);
	free_secdata(secdata);
	return ret;
}

static int setup_security_options(struct btrfs_fs_info *fs_info,
				  struct super_block *sb,
				  struct security_mnt_opts *sec_opts)
{
	int ret = 0;

	/*
	 * Call security_sb_set_mnt_opts() to check whether new sec_opts
	 * is valid.
	 */
	ret = security_sb_set_mnt_opts(sb, sec_opts, 0, NULL);
	if (ret)
		return ret;

#ifdef CONFIG_SECURITY
	if (!fs_info->security_opts.num_mnt_opts) {
		/* first time security setup, copy sec_opts to fs_info */
		memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts));
	} else {
		/*
		 * Since SELinux(the only one supports security_mnt_opts) does
		 * NOT support changing context during remount/mount same sb,
		 * This must be the same or part of the same security options,
		 * just free it.
		 */
		security_free_mnt_opts(sec_opts);
	}
#endif
	return ret;
}

/*
 * Find a superblock for the given device / mount point.
 *
 * Note:  This is based on get_sb_bdev from fs/super.c with a few additions
 *	  for multiple device setup.  Make sure to keep it in sync.
 */
static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
		const char *device_name, void *data)
{
	struct block_device *bdev = NULL;
	struct super_block *s;
	struct btrfs_fs_devices *fs_devices = NULL;
	struct btrfs_fs_info *fs_info = NULL;
	struct security_mnt_opts new_sec_opts;
	fmode_t mode = FMODE_READ;
	char *subvol_name = NULL;
	u64 subvol_objectid = 0;
	int error = 0;

	if (!(flags & MS_RDONLY))
		mode |= FMODE_WRITE;

	error = btrfs_parse_early_options(data, mode, fs_type,
					  &subvol_name, &subvol_objectid,
					  &fs_devices);
	if (error) {
		kfree(subvol_name);
		return ERR_PTR(error);
	}

	if (subvol_name || subvol_objectid != BTRFS_FS_TREE_OBJECTID) {
		/* mount_subvol() will free subvol_name. */
		return mount_subvol(subvol_name, subvol_objectid, flags,
				    device_name, data);
	}

	security_init_mnt_opts(&new_sec_opts);
	if (data) {
		error = parse_security_options(data, &new_sec_opts);
		if (error)
			return ERR_PTR(error);
	}

	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
	if (error)
		goto error_sec_opts;

	/*
	 * Setup a dummy root and fs_info for test/set super.  This is because
	 * we don't actually fill this stuff out until open_ctree, but we need
	 * it for searching for existing supers, so this lets us do that and
	 * then open_ctree will properly initialize everything later.
	 */
	fs_info = kzalloc(sizeof(struct btrfs_fs_info), GFP_NOFS);
	if (!fs_info) {
		error = -ENOMEM;
		goto error_sec_opts;
	}

	fs_info->fs_devices = fs_devices;

	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_NOFS);
	security_init_mnt_opts(&fs_info->security_opts);
	if (!fs_info->super_copy || !fs_info->super_for_commit) {
		error = -ENOMEM;
		goto error_fs_info;
	}

	error = btrfs_open_devices(fs_devices, mode, fs_type);
	if (error)
		goto error_fs_info;

	if (!(flags & MS_RDONLY) && fs_devices->rw_devices == 0) {
		error = -EACCES;
		goto error_close_devices;
	}

	bdev = fs_devices->latest_bdev;
	s = sget(fs_type, btrfs_test_super, btrfs_set_super, flags | MS_NOSEC,
		 fs_info);
	if (IS_ERR(s)) {
		error = PTR_ERR(s);
		goto error_close_devices;
	}

	if (s->s_root) {
		btrfs_close_devices(fs_devices);
		free_fs_info(fs_info);
		if ((flags ^ s->s_flags) & MS_RDONLY)
			error = -EBUSY;
	} else {
		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
		btrfs_sb(s)->bdev_holder = fs_type;
		error = btrfs_fill_super(s, fs_devices, data,
					 flags & MS_SILENT ? 1 : 0);
	}
	if (error) {
		deactivate_locked_super(s);
		goto error_sec_opts;
	}

	fs_info = btrfs_sb(s);
	error = setup_security_options(fs_info, s, &new_sec_opts);
	if (error) {
		deactivate_locked_super(s);
		goto error_sec_opts;
	}

	return dget(s->s_root);

error_close_devices:
	btrfs_close_devices(fs_devices);
error_fs_info:
	free_fs_info(fs_info);
error_sec_opts:
	security_free_mnt_opts(&new_sec_opts);
	return ERR_PTR(error);
}

static void btrfs_resize_thread_pool(struct btrfs_fs_info *fs_info,
				     int new_pool_size, int old_pool_size)
{
	if (new_pool_size == old_pool_size)
		return;

	fs_info->thread_pool_size = new_pool_size;

	btrfs_info(fs_info, "resize thread pool %d -> %d",
	       old_pool_size, new_pool_size);

	btrfs_workqueue_set_max(fs_info->workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->delalloc_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->submit_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->caching_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->endio_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->endio_meta_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->endio_meta_write_workers,
				new_pool_size);
	btrfs_workqueue_set_max(fs_info->endio_write_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->endio_freespace_worker, new_pool_size);
	btrfs_workqueue_set_max(fs_info->delayed_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->readahead_workers, new_pool_size);
	btrfs_workqueue_set_max(fs_info->scrub_wr_completion_workers,
				new_pool_size);
}

static inline void btrfs_remount_prepare(struct btrfs_fs_info *fs_info)
{
	set_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
}

static inline void btrfs_remount_begin(struct btrfs_fs_info *fs_info,
				       unsigned long old_opts, int flags)
{
	if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
	    (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
	     (flags & MS_RDONLY))) {
		/* wait for any defraggers to finish */
		wait_event(fs_info->transaction_wait,
			   (atomic_read(&fs_info->defrag_running) == 0));
		if (flags & MS_RDONLY)
			sync_filesystem(fs_info->sb);
	}
}

static inline void btrfs_remount_cleanup(struct btrfs_fs_info *fs_info,
					 unsigned long old_opts)
{
	/*
	 * We need cleanup all defragable inodes if the autodefragment is
	 * close or the fs is R/O.
	 */
	if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
	    (!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
	     (fs_info->sb->s_flags & MS_RDONLY))) {
		btrfs_cleanup_defrag_inodes(fs_info);
	}

	clear_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state);
}

static int btrfs_remount(struct super_block *sb, int *flags, char *data)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
	struct btrfs_root *root = fs_info->tree_root;
	unsigned old_flags = sb->s_flags;
	unsigned long old_opts = fs_info->mount_opt;
	unsigned long old_compress_type = fs_info->compress_type;
	u64 old_max_inline = fs_info->max_inline;
	u64 old_alloc_start = fs_info->alloc_start;
	int old_thread_pool_size = fs_info->thread_pool_size;
	unsigned int old_metadata_ratio = fs_info->metadata_ratio;
	int ret;

	sync_filesystem(sb);
	btrfs_remount_prepare(fs_info);

	if (data) {
		struct security_mnt_opts new_sec_opts;

		security_init_mnt_opts(&new_sec_opts);
		ret = parse_security_options(data, &new_sec_opts);
		if (ret)
			goto restore;
		ret = setup_security_options(fs_info, sb,
					     &new_sec_opts);
		if (ret) {
			security_free_mnt_opts(&new_sec_opts);
			goto restore;
		}
	}

	ret = btrfs_parse_options(root, data, *flags);
	if (ret) {
		ret = -EINVAL;
		goto restore;
	}

	btrfs_remount_begin(fs_info, old_opts, *flags);
	btrfs_resize_thread_pool(fs_info,
		fs_info->thread_pool_size, old_thread_pool_size);

	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
		goto out;

	if (*flags & MS_RDONLY) {
		/*
		 * this also happens on 'umount -rf' or on shutdown, when
		 * the filesystem is busy.
		 */
		cancel_work_sync(&fs_info->async_reclaim_work);

		/* wait for the uuid_scan task to finish */
		down(&fs_info->uuid_tree_rescan_sem);
		/* avoid complains from lockdep et al. */
		up(&fs_info->uuid_tree_rescan_sem);

		sb->s_flags |= MS_RDONLY;

		/*
		 * Setting MS_RDONLY will put the cleaner thread to
		 * sleep at the next loop if it's already active.
		 * If it's already asleep, we'll leave unused block
		 * groups on disk until we're mounted read-write again
		 * unless we clean them up here.
		 */
		btrfs_delete_unused_bgs(fs_info);

		btrfs_dev_replace_suspend_for_unmount(fs_info);
		btrfs_scrub_cancel(fs_info);
		btrfs_pause_balance(fs_info);

		ret = btrfs_commit_super(root);
		if (ret)
			goto restore;
	} else {
		if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
			btrfs_err(fs_info,
				"Remounting read-write after error is not allowed");
			ret = -EINVAL;
			goto restore;
		}
		if (fs_info->fs_devices->rw_devices == 0) {
			ret = -EACCES;
			goto restore;
		}

		if (fs_info->fs_devices->missing_devices >
		     fs_info->num_tolerated_disk_barrier_failures &&
		    !(*flags & MS_RDONLY)) {
			btrfs_warn(fs_info,
				"too many missing devices, writeable remount is not allowed");
			ret = -EACCES;
			goto restore;
		}

		if (btrfs_super_log_root(fs_info->super_copy) != 0) {
			ret = -EINVAL;
			goto restore;
		}

		ret = btrfs_cleanup_fs_roots(fs_info);
		if (ret)
			goto restore;

		/* recover relocation */
		mutex_lock(&fs_info->cleaner_mutex);
		ret = btrfs_recover_relocation(root);
		mutex_unlock(&fs_info->cleaner_mutex);
		if (ret)
			goto restore;

		ret = btrfs_resume_balance_async(fs_info);
		if (ret)
			goto restore;

		ret = btrfs_resume_dev_replace_async(fs_info);
		if (ret) {
			btrfs_warn(fs_info, "failed to resume dev_replace");
			goto restore;
		}

		if (!fs_info->uuid_root) {
			btrfs_info(fs_info, "creating UUID tree");
			ret = btrfs_create_uuid_tree(fs_info);
			if (ret) {
				btrfs_warn(fs_info, "failed to create the UUID tree %d", ret);
				goto restore;
			}
		}
		sb->s_flags &= ~MS_RDONLY;
	}
out:
	wake_up_process(fs_info->transaction_kthread);
	btrfs_remount_cleanup(fs_info, old_opts);
	return 0;

restore:
	/* We've hit an error - don't reset MS_RDONLY */
	if (sb->s_flags & MS_RDONLY)
		old_flags |= MS_RDONLY;
	sb->s_flags = old_flags;
	fs_info->mount_opt = old_opts;
	fs_info->compress_type = old_compress_type;
	fs_info->max_inline = old_max_inline;
	mutex_lock(&fs_info->chunk_mutex);
	fs_info->alloc_start = old_alloc_start;
	mutex_unlock(&fs_info->chunk_mutex);
	btrfs_resize_thread_pool(fs_info,
		old_thread_pool_size, fs_info->thread_pool_size);
	fs_info->metadata_ratio = old_metadata_ratio;
	btrfs_remount_cleanup(fs_info, old_opts);
	return ret;
}

/* Used to sort the devices by max_avail(descending sort) */
static int btrfs_cmp_device_free_bytes(const void *dev_info1,
				       const void *dev_info2)
{
	if (((struct btrfs_device_info *)dev_info1)->max_avail >
	    ((struct btrfs_device_info *)dev_info2)->max_avail)
		return -1;
	else if (((struct btrfs_device_info *)dev_info1)->max_avail <
		 ((struct btrfs_device_info *)dev_info2)->max_avail)
		return 1;
	else
	return 0;
}

/*
 * sort the devices by max_avail, in which max free extent size of each device
 * is stored.(Descending Sort)
 */
static inline void btrfs_descending_sort_devices(
					struct btrfs_device_info *devices,
					size_t nr_devices)
{
	sort(devices, nr_devices, sizeof(struct btrfs_device_info),
	     btrfs_cmp_device_free_bytes, NULL);
}

/*
 * The helper to calc the free space on the devices that can be used to store
 * file data.
 */
static int btrfs_calc_avail_data_space(struct btrfs_root *root, u64 *free_bytes)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_device_info *devices_info;
	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
	struct btrfs_device *device;
	u64 skip_space;
	u64 type;
	u64 avail_space;
	u64 used_space;
	u64 min_stripe_size;
	int min_stripes = 1, num_stripes = 1;
	int i = 0, nr_devices;
	int ret;

	/*
	 * We aren't under the device list lock, so this is racey-ish, but good
	 * enough for our purposes.
	 */
	nr_devices = fs_info->fs_devices->open_devices;
	if (!nr_devices) {
		smp_mb();
		nr_devices = fs_info->fs_devices->open_devices;
		ASSERT(nr_devices);
		if (!nr_devices) {
			*free_bytes = 0;
			return 0;
		}
	}

	devices_info = kmalloc_array(nr_devices, sizeof(*devices_info),
			       GFP_NOFS);
	if (!devices_info)
		return -ENOMEM;

	/* calc min stripe number for data space alloction */
	type = btrfs_get_alloc_profile(root, 1);
	if (type & BTRFS_BLOCK_GROUP_RAID0) {
		min_stripes = 2;
		num_stripes = nr_devices;
	} else if (type & BTRFS_BLOCK_GROUP_RAID1) {
		min_stripes = 2;
		num_stripes = 2;
	} else if (type & BTRFS_BLOCK_GROUP_RAID10) {
		min_stripes = 4;
		num_stripes = 4;
	}

	if (type & BTRFS_BLOCK_GROUP_DUP)
		min_stripe_size = 2 * BTRFS_STRIPE_LEN;
	else
		min_stripe_size = BTRFS_STRIPE_LEN;

	if (fs_info->alloc_start)
		mutex_lock(&fs_devices->device_list_mutex);
	rcu_read_lock();
	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
		if (!device->in_fs_metadata || !device->bdev ||
		    device->is_tgtdev_for_dev_replace)
			continue;

		if (i >= nr_devices)
			break;

		avail_space = device->total_bytes - device->bytes_used;

		/* align with stripe_len */
		avail_space = div_u64(avail_space, BTRFS_STRIPE_LEN);
		avail_space *= BTRFS_STRIPE_LEN;

		/*
		 * In order to avoid overwritting the superblock on the drive,
		 * btrfs starts at an offset of at least 1MB when doing chunk
		 * allocation.
		 */
		skip_space = SZ_1M;

		/* user can set the offset in fs_info->alloc_start. */
		if (fs_info->alloc_start &&
		    fs_info->alloc_start + BTRFS_STRIPE_LEN <=
		    device->total_bytes) {
			rcu_read_unlock();
			skip_space = max(fs_info->alloc_start, skip_space);

			/*
			 * btrfs can not use the free space in
			 * [0, skip_space - 1], we must subtract it from the
			 * total. In order to implement it, we account the used
			 * space in this range first.
			 */
			ret = btrfs_account_dev_extents_size(device, 0,
							     skip_space - 1,
							     &used_space);
			if (ret) {
				kfree(devices_info);
				mutex_unlock(&fs_devices->device_list_mutex);
				return ret;
			}

			rcu_read_lock();

			/* calc the free space in [0, skip_space - 1] */
			skip_space -= used_space;
		}

		/*
		 * we can use the free space in [0, skip_space - 1], subtract
		 * it from the total.
		 */
		if (avail_space && avail_space >= skip_space)
			avail_space -= skip_space;
		else
			avail_space = 0;

		if (avail_space < min_stripe_size)
			continue;

		devices_info[i].dev = device;
		devices_info[i].max_avail = avail_space;

		i++;
	}
	rcu_read_unlock();
	if (fs_info->alloc_start)
		mutex_unlock(&fs_devices->device_list_mutex);

	nr_devices = i;

	btrfs_descending_sort_devices(devices_info, nr_devices);

	i = nr_devices - 1;
	avail_space = 0;
	while (nr_devices >= min_stripes) {
		if (num_stripes > nr_devices)
			num_stripes = nr_devices;

		if (devices_info[i].max_avail >= min_stripe_size) {
			int j;
			u64 alloc_size;

			avail_space += devices_info[i].max_avail * num_stripes;
			alloc_size = devices_info[i].max_avail;
			for (j = i + 1 - num_stripes; j <= i; j++)
				devices_info[j].max_avail -= alloc_size;
		}
		i--;
		nr_devices--;
	}

	kfree(devices_info);
	*free_bytes = avail_space;
	return 0;
}

/*
 * Calculate numbers for 'df', pessimistic in case of mixed raid profiles.
 *
 * If there's a redundant raid level at DATA block groups, use the respective
 * multiplier to scale the sizes.
 *
 * Unused device space usage is based on simulating the chunk allocator
 * algorithm that respects the device sizes, order of allocations and the
 * 'alloc_start' value, this is a close approximation of the actual use but
 * there are other factors that may change the result (like a new metadata
 * chunk).
 *
 * If metadata is exhausted, f_bavail will be 0.
 *
 * FIXME: not accurate for mixed block groups, total and free/used are ok,
 * available appears slightly larger.
 */
static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
	struct btrfs_super_block *disk_super = fs_info->super_copy;
	struct list_head *head = &fs_info->space_info;
	struct btrfs_space_info *found;
	u64 total_used = 0;
	u64 total_free_data = 0;
	u64 total_free_meta = 0;
	int bits = dentry->d_sb->s_blocksize_bits;
	__be32 *fsid = (__be32 *)fs_info->fsid;
	unsigned factor = 1;
	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
	int ret;
	u64 thresh = 0;

	/*
	 * holding chunk_muext to avoid allocating new chunks, holding
	 * device_list_mutex to avoid the device being removed
	 */
	rcu_read_lock();
	list_for_each_entry_rcu(found, head, list) {
		if (found->flags & BTRFS_BLOCK_GROUP_DATA) {
			int i;

			total_free_data += found->disk_total - found->disk_used;
			total_free_data -=
				btrfs_account_ro_block_groups_free_space(found);

			for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
				if (!list_empty(&found->block_groups[i])) {
					switch (i) {
					case BTRFS_RAID_DUP:
					case BTRFS_RAID_RAID1:
					case BTRFS_RAID_RAID10:
						factor = 2;
					}
				}
			}
		}
		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
			total_free_meta += found->disk_total - found->disk_used;

		total_used += found->disk_used;
	}

	rcu_read_unlock();

	buf->f_blocks = div_u64(btrfs_super_total_bytes(disk_super), factor);
	buf->f_blocks >>= bits;
	buf->f_bfree = buf->f_blocks - (div_u64(total_used, factor) >> bits);

	/* Account global block reserve as used, it's in logical size already */
	spin_lock(&block_rsv->lock);
	buf->f_bfree -= block_rsv->size >> bits;
	spin_unlock(&block_rsv->lock);

	buf->f_bavail = div_u64(total_free_data, factor);
	ret = btrfs_calc_avail_data_space(fs_info->tree_root, &total_free_data);
	if (ret)
		return ret;
	buf->f_bavail += div_u64(total_free_data, factor);
	buf->f_bavail = buf->f_bavail >> bits;

	/*
	 * We calculate the remaining metadata space minus global reserve. If
	 * this is (supposedly) smaller than zero, there's no space. But this
	 * does not hold in practice, the exhausted state happens where's still
	 * some positive delta. So we apply some guesswork and compare the
	 * delta to a 4M threshold.  (Practically observed delta was ~2M.)
	 *
	 * We probably cannot calculate the exact threshold value because this
	 * depends on the internal reservations requested by various
	 * operations, so some operations that consume a few metadata will
	 * succeed even if the Avail is zero. But this is better than the other
	 * way around.
	 */
	thresh = 4 * 1024 * 1024;

	if (total_free_meta - thresh < block_rsv->size)
		buf->f_bavail = 0;

	buf->f_type = BTRFS_SUPER_MAGIC;
	buf->f_bsize = dentry->d_sb->s_blocksize;
	buf->f_namelen = BTRFS_NAME_LEN;

	/* We treat it as constant endianness (it doesn't matter _which_)
	   because we want the fsid to come out the same whether mounted
	   on a big-endian or little-endian host */
	buf->f_fsid.val[0] = be32_to_cpu(fsid[0]) ^ be32_to_cpu(fsid[2]);
	buf->f_fsid.val[1] = be32_to_cpu(fsid[1]) ^ be32_to_cpu(fsid[3]);
	/* Mask in the root object ID too, to disambiguate subvols */
	buf->f_fsid.val[0] ^= BTRFS_I(d_inode(dentry))->root->objectid >> 32;
	buf->f_fsid.val[1] ^= BTRFS_I(d_inode(dentry))->root->objectid;

	return 0;
}

static void btrfs_kill_super(struct super_block *sb)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
	kill_anon_super(sb);
	free_fs_info(fs_info);
}

static struct file_system_type btrfs_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "btrfs",
	.mount		= btrfs_mount,
	.kill_sb	= btrfs_kill_super,
	.fs_flags	= FS_REQUIRES_DEV | FS_BINARY_MOUNTDATA,
};
MODULE_ALIAS_FS("btrfs");

static int btrfs_control_open(struct inode *inode, struct file *file)
{
	/*
	 * The control file's private_data is used to hold the
	 * transaction when it is started and is used to keep
	 * track of whether a transaction is already in progress.
	 */
	file->private_data = NULL;
	return 0;
}

/*
 * used by btrfsctl to scan devices when no FS is mounted
 */
static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
				unsigned long arg)
{
	struct btrfs_ioctl_vol_args *vol;
	struct btrfs_fs_devices *fs_devices;
	int ret = -ENOTTY;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	vol = memdup_user((void __user *)arg, sizeof(*vol));
	if (IS_ERR(vol))
		return PTR_ERR(vol);

	switch (cmd) {
	case BTRFS_IOC_SCAN_DEV:
		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
					    &btrfs_fs_type, &fs_devices);
		break;
	case BTRFS_IOC_DEVICES_READY:
		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
					    &btrfs_fs_type, &fs_devices);
		if (ret)
			break;
		ret = !(fs_devices->num_devices == fs_devices->total_devices);
		break;
	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
		ret = btrfs_ioctl_get_supported_features((void __user*)arg);
		break;
	}

	kfree(vol);
	return ret;
}

static int btrfs_freeze(struct super_block *sb)
{
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = btrfs_sb(sb)->tree_root;

	trans = btrfs_attach_transaction_barrier(root);
	if (IS_ERR(trans)) {
		/* no transaction, don't bother */
		if (PTR_ERR(trans) == -ENOENT)
			return 0;
		return PTR_ERR(trans);
	}
	return btrfs_commit_transaction(trans, root);
}

static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(root->d_sb);
	struct btrfs_fs_devices *cur_devices;
	struct btrfs_device *dev, *first_dev = NULL;
	struct list_head *head;
	struct rcu_string *name;

	mutex_lock(&fs_info->fs_devices->device_list_mutex);
	cur_devices = fs_info->fs_devices;
	while (cur_devices) {
		head = &cur_devices->devices;
		list_for_each_entry(dev, head, dev_list) {
			if (dev->missing)
				continue;
			if (!dev->name)
				continue;
			if (!first_dev || dev->devid < first_dev->devid)
				first_dev = dev;
		}
		cur_devices = cur_devices->seed;
	}

	if (first_dev) {
		rcu_read_lock();
		name = rcu_dereference(first_dev->name);
		seq_escape(m, name->str, " \t\n\\");
		rcu_read_unlock();
	} else {
		WARN_ON(1);
	}
	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
	return 0;
}

static const struct super_operations btrfs_super_ops = {
	.drop_inode	= btrfs_drop_inode,
	.evict_inode	= btrfs_evict_inode,
	.put_super	= btrfs_put_super,
	.sync_fs	= btrfs_sync_fs,
	.show_options	= btrfs_show_options,
	.show_devname	= btrfs_show_devname,
	.write_inode	= btrfs_write_inode,
	.alloc_inode	= btrfs_alloc_inode,
	.destroy_inode	= btrfs_destroy_inode,
	.statfs		= btrfs_statfs,
	.remount_fs	= btrfs_remount,
	.freeze_fs	= btrfs_freeze,
};

static const struct file_operations btrfs_ctl_fops = {
	.open = btrfs_control_open,
	.unlocked_ioctl	 = btrfs_control_ioctl,
	.compat_ioctl = btrfs_control_ioctl,
	.owner	 = THIS_MODULE,
	.llseek = noop_llseek,
};

static struct miscdevice btrfs_misc = {
	.minor		= BTRFS_MINOR,
	.name		= "btrfs-control",
	.fops		= &btrfs_ctl_fops
};

MODULE_ALIAS_MISCDEV(BTRFS_MINOR);
MODULE_ALIAS("devname:btrfs-control");

static int btrfs_interface_init(void)
{
	return misc_register(&btrfs_misc);
}

static void btrfs_interface_exit(void)
{
	misc_deregister(&btrfs_misc);
}

static void btrfs_print_info(void)
{
	printk(KERN_INFO "Btrfs loaded"
#ifdef CONFIG_BTRFS_DEBUG
			", debug=on"
#endif
#ifdef CONFIG_BTRFS_ASSERT
			", assert=on"
#endif
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
			", integrity-checker=on"
#endif
			"\n");
}

static int btrfs_run_sanity_tests(void)
{
	int ret;

	ret = btrfs_init_test_fs();
	if (ret)
		return ret;

	ret = btrfs_test_free_space_cache();
	if (ret)
		goto out;
	ret = btrfs_test_extent_buffer_operations();
	if (ret)
		goto out;
	ret = btrfs_test_extent_io();
	if (ret)
		goto out;
	ret = btrfs_test_inodes();
	if (ret)
		goto out;
	ret = btrfs_test_qgroups();
	if (ret)
		goto out;
	ret = btrfs_test_free_space_tree();
out:
	btrfs_destroy_test_fs();
	return ret;
}

static int __init init_btrfs_fs(void)
{
	int err;

	err = btrfs_hash_init();
	if (err)
		return err;

	btrfs_props_init();

	err = btrfs_init_sysfs();
	if (err)
		goto free_hash;

	btrfs_init_compress();

	err = btrfs_init_cachep();
	if (err)
		goto free_compress;

	err = extent_io_init();
	if (err)
		goto free_cachep;

	err = extent_map_init();
	if (err)
		goto free_extent_io;

	err = ordered_data_init();
	if (err)
		goto free_extent_map;

	err = btrfs_delayed_inode_init();
	if (err)
		goto free_ordered_data;

	err = btrfs_auto_defrag_init();
	if (err)
		goto free_delayed_inode;

	err = btrfs_delayed_ref_init();
	if (err)
		goto free_auto_defrag;

	err = btrfs_prelim_ref_init();
	if (err)
		goto free_delayed_ref;

	err = btrfs_end_io_wq_init();
	if (err)
		goto free_prelim_ref;

	err = btrfs_interface_init();
	if (err)
		goto free_end_io_wq;

	btrfs_init_lockdep();

	btrfs_print_info();

	err = btrfs_run_sanity_tests();
	if (err)
		goto unregister_ioctl;

	err = register_filesystem(&btrfs_fs_type);
	if (err)
		goto unregister_ioctl;

	return 0;

unregister_ioctl:
	btrfs_interface_exit();
free_end_io_wq:
	btrfs_end_io_wq_exit();
free_prelim_ref:
	btrfs_prelim_ref_exit();
free_delayed_ref:
	btrfs_delayed_ref_exit();
free_auto_defrag:
	btrfs_auto_defrag_exit();
free_delayed_inode:
	btrfs_delayed_inode_exit();
free_ordered_data:
	ordered_data_exit();
free_extent_map:
	extent_map_exit();
free_extent_io:
	extent_io_exit();
free_cachep:
	btrfs_destroy_cachep();
free_compress:
	btrfs_exit_compress();
	btrfs_exit_sysfs();
free_hash:
	btrfs_hash_exit();
	return err;
}

static void __exit exit_btrfs_fs(void)
{
	btrfs_destroy_cachep();
	btrfs_delayed_ref_exit();
	btrfs_auto_defrag_exit();
	btrfs_delayed_inode_exit();
	btrfs_prelim_ref_exit();
	ordered_data_exit();
	extent_map_exit();
	extent_io_exit();
	btrfs_interface_exit();
	btrfs_end_io_wq_exit();
	unregister_filesystem(&btrfs_fs_type);
	btrfs_exit_sysfs();
	btrfs_cleanup_fs_uuids();
	btrfs_exit_compress();
	btrfs_hash_exit();
}

late_initcall(init_btrfs_fs);
module_exit(exit_btrfs_fs)

MODULE_LICENSE("GPL");
OpenPOWER on IntegriCloud