summaryrefslogtreecommitdiff
path: root/fs/btrfs/transaction.c
blob: cfc08ef9b87648e4ec63156e32ef84e0424c76e3 (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
2459
2460
2461
2462
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
#include <linux/blkdev.h>
#include <linux/uuid.h>
#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "locking.h"
#include "tree-log.h"
#include "inode-map.h"
#include "volumes.h"
#include "dev-replace.h"
#include "qgroup.h"
#include "block-group.h"

#define BTRFS_ROOT_TRANS_TAG 0

/*
 * Transaction states and transitions
 *
 * No running transaction (fs tree blocks are not modified)
 * |
 * | To next stage:
 * |  Call start_transaction() variants. Except btrfs_join_transaction_nostart().
 * V
 * Transaction N [[TRANS_STATE_RUNNING]]
 * |
 * | New trans handles can be attached to transaction N by calling all
 * | start_transaction() variants.
 * |
 * | To next stage:
 * |  Call btrfs_commit_transaction() on any trans handle attached to
 * |  transaction N
 * V
 * Transaction N [[TRANS_STATE_COMMIT_START]]
 * |
 * | Will wait for previous running transaction to completely finish if there
 * | is one
 * |
 * | Then one of the following happes:
 * | - Wait for all other trans handle holders to release.
 * |   The btrfs_commit_transaction() caller will do the commit work.
 * | - Wait for current transaction to be committed by others.
 * |   Other btrfs_commit_transaction() caller will do the commit work.
 * |
 * | At this stage, only btrfs_join_transaction*() variants can attach
 * | to this running transaction.
 * | All other variants will wait for current one to finish and attach to
 * | transaction N+1.
 * |
 * | To next stage:
 * |  Caller is chosen to commit transaction N, and all other trans handle
 * |  haven been released.
 * V
 * Transaction N [[TRANS_STATE_COMMIT_DOING]]
 * |
 * | The heavy lifting transaction work is started.
 * | From running delayed refs (modifying extent tree) to creating pending
 * | snapshots, running qgroups.
 * | In short, modify supporting trees to reflect modifications of subvolume
 * | trees.
 * |
 * | At this stage, all start_transaction() calls will wait for this
 * | transaction to finish and attach to transaction N+1.
 * |
 * | To next stage:
 * |  Until all supporting trees are updated.
 * V
 * Transaction N [[TRANS_STATE_UNBLOCKED]]
 * |						    Transaction N+1
 * | All needed trees are modified, thus we only    [[TRANS_STATE_RUNNING]]
 * | need to write them back to disk and update	    |
 * | super blocks.				    |
 * |						    |
 * | At this stage, new transaction is allowed to   |
 * | start.					    |
 * | All new start_transaction() calls will be	    |
 * | attached to transid N+1.			    |
 * |						    |
 * | To next stage:				    |
 * |  Until all tree blocks are super blocks are    |
 * |  written to block devices			    |
 * V						    |
 * Transaction N [[TRANS_STATE_COMPLETED]]	    V
 *   All tree blocks and super blocks are written.  Transaction N+1
 *   This transaction is finished and all its	    [[TRANS_STATE_COMMIT_START]]
 *   data structures will be cleaned up.	    | Life goes on
 */
static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
	[TRANS_STATE_RUNNING]		= 0U,
	[TRANS_STATE_COMMIT_START]	= (__TRANS_START | __TRANS_ATTACH),
	[TRANS_STATE_COMMIT_DOING]	= (__TRANS_START |
					   __TRANS_ATTACH |
					   __TRANS_JOIN |
					   __TRANS_JOIN_NOSTART),
	[TRANS_STATE_UNBLOCKED]		= (__TRANS_START |
					   __TRANS_ATTACH |
					   __TRANS_JOIN |
					   __TRANS_JOIN_NOLOCK |
					   __TRANS_JOIN_NOSTART),
	[TRANS_STATE_COMPLETED]		= (__TRANS_START |
					   __TRANS_ATTACH |
					   __TRANS_JOIN |
					   __TRANS_JOIN_NOLOCK |
					   __TRANS_JOIN_NOSTART),
};

void btrfs_put_transaction(struct btrfs_transaction *transaction)
{
	WARN_ON(refcount_read(&transaction->use_count) == 0);
	if (refcount_dec_and_test(&transaction->use_count)) {
		BUG_ON(!list_empty(&transaction->list));
		WARN_ON(!RB_EMPTY_ROOT(
				&transaction->delayed_refs.href_root.rb_root));
		if (transaction->delayed_refs.pending_csums)
			btrfs_err(transaction->fs_info,
				  "pending csums is %llu",
				  transaction->delayed_refs.pending_csums);
		/*
		 * If any block groups are found in ->deleted_bgs then it's
		 * because the transaction was aborted and a commit did not
		 * happen (things failed before writing the new superblock
		 * and calling btrfs_finish_extent_commit()), so we can not
		 * discard the physical locations of the block groups.
		 */
		while (!list_empty(&transaction->deleted_bgs)) {
			struct btrfs_block_group *cache;

			cache = list_first_entry(&transaction->deleted_bgs,
						 struct btrfs_block_group,
						 bg_list);
			list_del_init(&cache->bg_list);
			btrfs_put_block_group_trimming(cache);
			btrfs_put_block_group(cache);
		}
		WARN_ON(!list_empty(&transaction->dev_update_list));
		kfree(transaction);
	}
}

static noinline void switch_commit_roots(struct btrfs_transaction *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *root, *tmp;

	down_write(&fs_info->commit_root_sem);
	list_for_each_entry_safe(root, tmp, &trans->switch_commits,
				 dirty_list) {
		list_del_init(&root->dirty_list);
		free_extent_buffer(root->commit_root);
		root->commit_root = btrfs_root_node(root);
		if (is_fstree(root->root_key.objectid))
			btrfs_unpin_free_ino(root);
		extent_io_tree_release(&root->dirty_log_pages);
		btrfs_qgroup_clean_swapped_blocks(root);
	}

	/* We can free old roots now. */
	spin_lock(&trans->dropped_roots_lock);
	while (!list_empty(&trans->dropped_roots)) {
		root = list_first_entry(&trans->dropped_roots,
					struct btrfs_root, root_list);
		list_del_init(&root->root_list);
		spin_unlock(&trans->dropped_roots_lock);
		btrfs_drop_and_free_fs_root(fs_info, root);
		spin_lock(&trans->dropped_roots_lock);
	}
	spin_unlock(&trans->dropped_roots_lock);
	up_write(&fs_info->commit_root_sem);
}

static inline void extwriter_counter_inc(struct btrfs_transaction *trans,
					 unsigned int type)
{
	if (type & TRANS_EXTWRITERS)
		atomic_inc(&trans->num_extwriters);
}

static inline void extwriter_counter_dec(struct btrfs_transaction *trans,
					 unsigned int type)
{
	if (type & TRANS_EXTWRITERS)
		atomic_dec(&trans->num_extwriters);
}

static inline void extwriter_counter_init(struct btrfs_transaction *trans,
					  unsigned int type)
{
	atomic_set(&trans->num_extwriters, ((type & TRANS_EXTWRITERS) ? 1 : 0));
}

static inline int extwriter_counter_read(struct btrfs_transaction *trans)
{
	return atomic_read(&trans->num_extwriters);
}

/*
 * To be called after all the new block groups attached to the transaction
 * handle have been created (btrfs_create_pending_block_groups()).
 */
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;

	if (!trans->chunk_bytes_reserved)
		return;

	WARN_ON_ONCE(!list_empty(&trans->new_bgs));

	btrfs_block_rsv_release(fs_info, &fs_info->chunk_block_rsv,
				trans->chunk_bytes_reserved);
	trans->chunk_bytes_reserved = 0;
}

/*
 * either allocate a new transaction or hop into the existing one
 */
static noinline int join_transaction(struct btrfs_fs_info *fs_info,
				     unsigned int type)
{
	struct btrfs_transaction *cur_trans;

	spin_lock(&fs_info->trans_lock);
loop:
	/* The file system has been taken offline. No new transactions. */
	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
		spin_unlock(&fs_info->trans_lock);
		return -EROFS;
	}

	cur_trans = fs_info->running_transaction;
	if (cur_trans) {
		if (cur_trans->aborted) {
			spin_unlock(&fs_info->trans_lock);
			return cur_trans->aborted;
		}
		if (btrfs_blocked_trans_types[cur_trans->state] & type) {
			spin_unlock(&fs_info->trans_lock);
			return -EBUSY;
		}
		refcount_inc(&cur_trans->use_count);
		atomic_inc(&cur_trans->num_writers);
		extwriter_counter_inc(cur_trans, type);
		spin_unlock(&fs_info->trans_lock);
		return 0;
	}
	spin_unlock(&fs_info->trans_lock);

	/*
	 * If we are ATTACH, we just want to catch the current transaction,
	 * and commit it. If there is no transaction, just return ENOENT.
	 */
	if (type == TRANS_ATTACH)
		return -ENOENT;

	/*
	 * JOIN_NOLOCK only happens during the transaction commit, so
	 * it is impossible that ->running_transaction is NULL
	 */
	BUG_ON(type == TRANS_JOIN_NOLOCK);

	cur_trans = kmalloc(sizeof(*cur_trans), GFP_NOFS);
	if (!cur_trans)
		return -ENOMEM;

	spin_lock(&fs_info->trans_lock);
	if (fs_info->running_transaction) {
		/*
		 * someone started a transaction after we unlocked.  Make sure
		 * to redo the checks above
		 */
		kfree(cur_trans);
		goto loop;
	} else if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
		spin_unlock(&fs_info->trans_lock);
		kfree(cur_trans);
		return -EROFS;
	}

	cur_trans->fs_info = fs_info;
	atomic_set(&cur_trans->num_writers, 1);
	extwriter_counter_init(cur_trans, type);
	init_waitqueue_head(&cur_trans->writer_wait);
	init_waitqueue_head(&cur_trans->commit_wait);
	cur_trans->state = TRANS_STATE_RUNNING;
	/*
	 * One for this trans handle, one so it will live on until we
	 * commit the transaction.
	 */
	refcount_set(&cur_trans->use_count, 2);
	cur_trans->flags = 0;
	cur_trans->start_time = ktime_get_seconds();

	memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs));

	cur_trans->delayed_refs.href_root = RB_ROOT_CACHED;
	cur_trans->delayed_refs.dirty_extent_root = RB_ROOT;
	atomic_set(&cur_trans->delayed_refs.num_entries, 0);

	/*
	 * although the tree mod log is per file system and not per transaction,
	 * the log must never go across transaction boundaries.
	 */
	smp_mb();
	if (!list_empty(&fs_info->tree_mod_seq_list))
		WARN(1, KERN_ERR "BTRFS: tree_mod_seq_list not empty when creating a fresh transaction\n");
	if (!RB_EMPTY_ROOT(&fs_info->tree_mod_log))
		WARN(1, KERN_ERR "BTRFS: tree_mod_log rb tree not empty when creating a fresh transaction\n");
	atomic64_set(&fs_info->tree_mod_seq, 0);

	spin_lock_init(&cur_trans->delayed_refs.lock);

	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
	INIT_LIST_HEAD(&cur_trans->dev_update_list);
	INIT_LIST_HEAD(&cur_trans->switch_commits);
	INIT_LIST_HEAD(&cur_trans->dirty_bgs);
	INIT_LIST_HEAD(&cur_trans->io_bgs);
	INIT_LIST_HEAD(&cur_trans->dropped_roots);
	mutex_init(&cur_trans->cache_write_mutex);
	spin_lock_init(&cur_trans->dirty_bgs_lock);
	INIT_LIST_HEAD(&cur_trans->deleted_bgs);
	spin_lock_init(&cur_trans->dropped_roots_lock);
	list_add_tail(&cur_trans->list, &fs_info->trans_list);
	extent_io_tree_init(fs_info, &cur_trans->dirty_pages,
			IO_TREE_TRANS_DIRTY_PAGES, fs_info->btree_inode);
	fs_info->generation++;
	cur_trans->transid = fs_info->generation;
	fs_info->running_transaction = cur_trans;
	cur_trans->aborted = 0;
	spin_unlock(&fs_info->trans_lock);

	return 0;
}

/*
 * this does all the record keeping required to make sure that a reference
 * counted root is properly recorded in a given transaction.  This is required
 * to make sure the old root from before we joined the transaction is deleted
 * when the transaction commits
 */
static int record_root_in_trans(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root,
			       int force)
{
	struct btrfs_fs_info *fs_info = root->fs_info;

	if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
	    root->last_trans < trans->transid) || force) {
		WARN_ON(root == fs_info->extent_root);
		WARN_ON(!force && root->commit_root != root->node);

		/*
		 * see below for IN_TRANS_SETUP usage rules
		 * we have the reloc mutex held now, so there
		 * is only one writer in this function
		 */
		set_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state);

		/* make sure readers find IN_TRANS_SETUP before
		 * they find our root->last_trans update
		 */
		smp_wmb();

		spin_lock(&fs_info->fs_roots_radix_lock);
		if (root->last_trans == trans->transid && !force) {
			spin_unlock(&fs_info->fs_roots_radix_lock);
			return 0;
		}
		radix_tree_tag_set(&fs_info->fs_roots_radix,
				   (unsigned long)root->root_key.objectid,
				   BTRFS_ROOT_TRANS_TAG);
		spin_unlock(&fs_info->fs_roots_radix_lock);
		root->last_trans = trans->transid;

		/* this is pretty tricky.  We don't want to
		 * take the relocation lock in btrfs_record_root_in_trans
		 * unless we're really doing the first setup for this root in
		 * this transaction.
		 *
		 * Normally we'd use root->last_trans as a flag to decide
		 * if we want to take the expensive mutex.
		 *
		 * But, we have to set root->last_trans before we
		 * init the relocation root, otherwise, we trip over warnings
		 * in ctree.c.  The solution used here is to flag ourselves
		 * with root IN_TRANS_SETUP.  When this is 1, we're still
		 * fixing up the reloc trees and everyone must wait.
		 *
		 * When this is zero, they can trust root->last_trans and fly
		 * through btrfs_record_root_in_trans without having to take the
		 * lock.  smp_wmb() makes sure that all the writes above are
		 * done before we pop in the zero below
		 */
		btrfs_init_reloc_root(trans, root);
		smp_mb__before_atomic();
		clear_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state);
	}
	return 0;
}


void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_transaction *cur_trans = trans->transaction;

	/* Add ourselves to the transaction dropped list */
	spin_lock(&cur_trans->dropped_roots_lock);
	list_add_tail(&root->root_list, &cur_trans->dropped_roots);
	spin_unlock(&cur_trans->dropped_roots_lock);

	/* Make sure we don't try to update the root at commit time */
	spin_lock(&fs_info->fs_roots_radix_lock);
	radix_tree_tag_clear(&fs_info->fs_roots_radix,
			     (unsigned long)root->root_key.objectid,
			     BTRFS_ROOT_TRANS_TAG);
	spin_unlock(&fs_info->fs_roots_radix_lock);
}

int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;

	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
		return 0;

	/*
	 * see record_root_in_trans for comments about IN_TRANS_SETUP usage
	 * and barriers
	 */
	smp_rmb();
	if (root->last_trans == trans->transid &&
	    !test_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state))
		return 0;

	mutex_lock(&fs_info->reloc_mutex);
	record_root_in_trans(trans, root, 0);
	mutex_unlock(&fs_info->reloc_mutex);

	return 0;
}

static inline int is_transaction_blocked(struct btrfs_transaction *trans)
{
	return (trans->state >= TRANS_STATE_COMMIT_START &&
		trans->state < TRANS_STATE_UNBLOCKED &&
		!trans->aborted);
}

/* wait for commit against the current transaction to become unblocked
 * when this is done, it is safe to start a new transaction, but the current
 * transaction might not be fully on disk.
 */
static void wait_current_trans(struct btrfs_fs_info *fs_info)
{
	struct btrfs_transaction *cur_trans;

	spin_lock(&fs_info->trans_lock);
	cur_trans = fs_info->running_transaction;
	if (cur_trans && is_transaction_blocked(cur_trans)) {
		refcount_inc(&cur_trans->use_count);
		spin_unlock(&fs_info->trans_lock);

		wait_event(fs_info->transaction_wait,
			   cur_trans->state >= TRANS_STATE_UNBLOCKED ||
			   cur_trans->aborted);
		btrfs_put_transaction(cur_trans);
	} else {
		spin_unlock(&fs_info->trans_lock);
	}
}

static int may_wait_transaction(struct btrfs_fs_info *fs_info, int type)
{
	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
		return 0;

	if (type == TRANS_START)
		return 1;

	return 0;
}

static inline bool need_reserve_reloc_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;

	if (!fs_info->reloc_ctl ||
	    !test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
	    root->reloc_root)
		return false;

	return true;
}

static struct btrfs_trans_handle *
start_transaction(struct btrfs_root *root, unsigned int num_items,
		  unsigned int type, enum btrfs_reserve_flush_enum flush,
		  bool enforce_qgroups)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
	struct btrfs_trans_handle *h;
	struct btrfs_transaction *cur_trans;
	u64 num_bytes = 0;
	u64 qgroup_reserved = 0;
	bool reloc_reserved = false;
	int ret;

	/* Send isn't supposed to start transactions. */
	ASSERT(current->journal_info != BTRFS_SEND_TRANS_STUB);

	if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state))
		return ERR_PTR(-EROFS);

	if (current->journal_info) {
		WARN_ON(type & TRANS_EXTWRITERS);
		h = current->journal_info;
		refcount_inc(&h->use_count);
		WARN_ON(refcount_read(&h->use_count) > 2);
		h->orig_rsv = h->block_rsv;
		h->block_rsv = NULL;
		goto got_it;
	}

	/*
	 * Do the reservation before we join the transaction so we can do all
	 * the appropriate flushing if need be.
	 */
	if (num_items && root != fs_info->chunk_root) {
		struct btrfs_block_rsv *rsv = &fs_info->trans_block_rsv;
		u64 delayed_refs_bytes = 0;

		qgroup_reserved = num_items * fs_info->nodesize;
		ret = btrfs_qgroup_reserve_meta_pertrans(root, qgroup_reserved,
				enforce_qgroups);
		if (ret)
			return ERR_PTR(ret);

		/*
		 * We want to reserve all the bytes we may need all at once, so
		 * we only do 1 enospc flushing cycle per transaction start.  We
		 * accomplish this by simply assuming we'll do 2 x num_items
		 * worth of delayed refs updates in this trans handle, and
		 * refill that amount for whatever is missing in the reserve.
		 */
		num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_items);
		if (delayed_refs_rsv->full == 0) {
			delayed_refs_bytes = num_bytes;
			num_bytes <<= 1;
		}

		/*
		 * Do the reservation for the relocation root creation
		 */
		if (need_reserve_reloc_root(root)) {
			num_bytes += fs_info->nodesize;
			reloc_reserved = true;
		}

		ret = btrfs_block_rsv_add(root, rsv, num_bytes, flush);
		if (ret)
			goto reserve_fail;
		if (delayed_refs_bytes) {
			btrfs_migrate_to_delayed_refs_rsv(fs_info, rsv,
							  delayed_refs_bytes);
			num_bytes -= delayed_refs_bytes;
		}
	} else if (num_items == 0 && flush == BTRFS_RESERVE_FLUSH_ALL &&
		   !delayed_refs_rsv->full) {
		/*
		 * Some people call with btrfs_start_transaction(root, 0)
		 * because they can be throttled, but have some other mechanism
		 * for reserving space.  We still want these guys to refill the
		 * delayed block_rsv so just add 1 items worth of reservation
		 * here.
		 */
		ret = btrfs_delayed_refs_rsv_refill(fs_info, flush);
		if (ret)
			goto reserve_fail;
	}
again:
	h = kmem_cache_zalloc(btrfs_trans_handle_cachep, GFP_NOFS);
	if (!h) {
		ret = -ENOMEM;
		goto alloc_fail;
	}

	/*
	 * If we are JOIN_NOLOCK we're already committing a transaction and
	 * waiting on this guy, so we don't need to do the sb_start_intwrite
	 * because we're already holding a ref.  We need this because we could
	 * have raced in and did an fsync() on a file which can kick a commit
	 * and then we deadlock with somebody doing a freeze.
	 *
	 * If we are ATTACH, it means we just want to catch the current
	 * transaction and commit it, so we needn't do sb_start_intwrite(). 
	 */
	if (type & __TRANS_FREEZABLE)
		sb_start_intwrite(fs_info->sb);

	if (may_wait_transaction(fs_info, type))
		wait_current_trans(fs_info);

	do {
		ret = join_transaction(fs_info, type);
		if (ret == -EBUSY) {
			wait_current_trans(fs_info);
			if (unlikely(type == TRANS_ATTACH ||
				     type == TRANS_JOIN_NOSTART))
				ret = -ENOENT;
		}
	} while (ret == -EBUSY);

	if (ret < 0)
		goto join_fail;

	cur_trans = fs_info->running_transaction;

	h->transid = cur_trans->transid;
	h->transaction = cur_trans;
	h->root = root;
	refcount_set(&h->use_count, 1);
	h->fs_info = root->fs_info;

	h->type = type;
	h->can_flush_pending_bgs = true;
	INIT_LIST_HEAD(&h->new_bgs);

	smp_mb();
	if (cur_trans->state >= TRANS_STATE_COMMIT_START &&
	    may_wait_transaction(fs_info, type)) {
		current->journal_info = h;
		btrfs_commit_transaction(h);
		goto again;
	}

	if (num_bytes) {
		trace_btrfs_space_reservation(fs_info, "transaction",
					      h->transid, num_bytes, 1);
		h->block_rsv = &fs_info->trans_block_rsv;
		h->bytes_reserved = num_bytes;
		h->reloc_reserved = reloc_reserved;
	}

got_it:
	btrfs_record_root_in_trans(h, root);

	if (!current->journal_info)
		current->journal_info = h;
	return h;

join_fail:
	if (type & __TRANS_FREEZABLE)
		sb_end_intwrite(fs_info->sb);
	kmem_cache_free(btrfs_trans_handle_cachep, h);
alloc_fail:
	if (num_bytes)
		btrfs_block_rsv_release(fs_info, &fs_info->trans_block_rsv,
					num_bytes);
reserve_fail:
	btrfs_qgroup_free_meta_pertrans(root, qgroup_reserved);
	return ERR_PTR(ret);
}

struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
						   unsigned int num_items)
{
	return start_transaction(root, num_items, TRANS_START,
				 BTRFS_RESERVE_FLUSH_ALL, true);
}

struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
					struct btrfs_root *root,
					unsigned int num_items,
					int min_factor)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	u64 num_bytes;
	int ret;

	/*
	 * We have two callers: unlink and block group removal.  The
	 * former should succeed even if we will temporarily exceed
	 * quota and the latter operates on the extent root so
	 * qgroup enforcement is ignored anyway.
	 */
	trans = start_transaction(root, num_items, TRANS_START,
				  BTRFS_RESERVE_FLUSH_ALL, false);
	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
		return trans;

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans))
		return trans;

	num_bytes = btrfs_calc_insert_metadata_size(fs_info, num_items);
	ret = btrfs_cond_migrate_bytes(fs_info, &fs_info->trans_block_rsv,
				       num_bytes, min_factor);
	if (ret) {
		btrfs_end_transaction(trans);
		return ERR_PTR(ret);
	}

	trans->block_rsv = &fs_info->trans_block_rsv;
	trans->bytes_reserved = num_bytes;
	trace_btrfs_space_reservation(fs_info, "transaction",
				      trans->transid, num_bytes, 1);

	return trans;
}

struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
{
	return start_transaction(root, 0, TRANS_JOIN, BTRFS_RESERVE_NO_FLUSH,
				 true);
}

struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root)
{
	return start_transaction(root, 0, TRANS_JOIN_NOLOCK,
				 BTRFS_RESERVE_NO_FLUSH, true);
}

/*
 * Similar to regular join but it never starts a transaction when none is
 * running or after waiting for the current one to finish.
 */
struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root)
{
	return start_transaction(root, 0, TRANS_JOIN_NOSTART,
				 BTRFS_RESERVE_NO_FLUSH, true);
}

/*
 * btrfs_attach_transaction() - catch the running transaction
 *
 * It is used when we want to commit the current the transaction, but
 * don't want to start a new one.
 *
 * Note: If this function return -ENOENT, it just means there is no
 * running transaction. But it is possible that the inactive transaction
 * is still in the memory, not fully on disk. If you hope there is no
 * inactive transaction in the fs when -ENOENT is returned, you should
 * invoke
 *     btrfs_attach_transaction_barrier()
 */
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root)
{
	return start_transaction(root, 0, TRANS_ATTACH,
				 BTRFS_RESERVE_NO_FLUSH, true);
}

/*
 * btrfs_attach_transaction_barrier() - catch the running transaction
 *
 * It is similar to the above function, the difference is this one
 * will wait for all the inactive transactions until they fully
 * complete.
 */
struct btrfs_trans_handle *
btrfs_attach_transaction_barrier(struct btrfs_root *root)
{
	struct btrfs_trans_handle *trans;

	trans = start_transaction(root, 0, TRANS_ATTACH,
				  BTRFS_RESERVE_NO_FLUSH, true);
	if (trans == ERR_PTR(-ENOENT))
		btrfs_wait_for_commit(root->fs_info, 0);

	return trans;
}

/* wait for a transaction commit to be fully complete */
static noinline void wait_for_commit(struct btrfs_transaction *commit)
{
	wait_event(commit->commit_wait, commit->state == TRANS_STATE_COMPLETED);
}

int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid)
{
	struct btrfs_transaction *cur_trans = NULL, *t;
	int ret = 0;

	if (transid) {
		if (transid <= fs_info->last_trans_committed)
			goto out;

		/* find specified transaction */
		spin_lock(&fs_info->trans_lock);
		list_for_each_entry(t, &fs_info->trans_list, list) {
			if (t->transid == transid) {
				cur_trans = t;
				refcount_inc(&cur_trans->use_count);
				ret = 0;
				break;
			}
			if (t->transid > transid) {
				ret = 0;
				break;
			}
		}
		spin_unlock(&fs_info->trans_lock);

		/*
		 * The specified transaction doesn't exist, or we
		 * raced with btrfs_commit_transaction
		 */
		if (!cur_trans) {
			if (transid > fs_info->last_trans_committed)
				ret = -EINVAL;
			goto out;
		}
	} else {
		/* find newest transaction that is committing | committed */
		spin_lock(&fs_info->trans_lock);
		list_for_each_entry_reverse(t, &fs_info->trans_list,
					    list) {
			if (t->state >= TRANS_STATE_COMMIT_START) {
				if (t->state == TRANS_STATE_COMPLETED)
					break;
				cur_trans = t;
				refcount_inc(&cur_trans->use_count);
				break;
			}
		}
		spin_unlock(&fs_info->trans_lock);
		if (!cur_trans)
			goto out;  /* nothing committing|committed */
	}

	wait_for_commit(cur_trans);
	btrfs_put_transaction(cur_trans);
out:
	return ret;
}

void btrfs_throttle(struct btrfs_fs_info *fs_info)
{
	wait_current_trans(fs_info);
}

static int should_end_transaction(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;

	if (btrfs_check_space_for_delayed_refs(fs_info))
		return 1;

	return !!btrfs_block_rsv_check(&fs_info->global_block_rsv, 5);
}

int btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
{
	struct btrfs_transaction *cur_trans = trans->transaction;

	smp_mb();
	if (cur_trans->state >= TRANS_STATE_COMMIT_START ||
	    cur_trans->delayed_refs.flushing)
		return 1;

	return should_end_transaction(trans);
}

static void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans)

{
	struct btrfs_fs_info *fs_info = trans->fs_info;

	if (!trans->block_rsv) {
		ASSERT(!trans->bytes_reserved);
		return;
	}

	if (!trans->bytes_reserved)
		return;

	ASSERT(trans->block_rsv == &fs_info->trans_block_rsv);
	trace_btrfs_space_reservation(fs_info, "transaction",
				      trans->transid, trans->bytes_reserved, 0);
	btrfs_block_rsv_release(fs_info, trans->block_rsv,
				trans->bytes_reserved);
	trans->bytes_reserved = 0;
}

static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
				   int throttle)
{
	struct btrfs_fs_info *info = trans->fs_info;
	struct btrfs_transaction *cur_trans = trans->transaction;
	int err = 0;

	if (refcount_read(&trans->use_count) > 1) {
		refcount_dec(&trans->use_count);
		trans->block_rsv = trans->orig_rsv;
		return 0;
	}

	btrfs_trans_release_metadata(trans);
	trans->block_rsv = NULL;

	btrfs_create_pending_block_groups(trans);

	btrfs_trans_release_chunk_metadata(trans);

	if (trans->type & __TRANS_FREEZABLE)
		sb_end_intwrite(info->sb);

	WARN_ON(cur_trans != info->running_transaction);
	WARN_ON(atomic_read(&cur_trans->num_writers) < 1);
	atomic_dec(&cur_trans->num_writers);
	extwriter_counter_dec(cur_trans, trans->type);

	cond_wake_up(&cur_trans->writer_wait);
	btrfs_put_transaction(cur_trans);

	if (current->journal_info == trans)
		current->journal_info = NULL;

	if (throttle)
		btrfs_run_delayed_iputs(info);

	if (trans->aborted ||
	    test_bit(BTRFS_FS_STATE_ERROR, &info->fs_state)) {
		wake_up_process(info->transaction_kthread);
		err = -EIO;
	}

	kmem_cache_free(btrfs_trans_handle_cachep, trans);
	return err;
}

int btrfs_end_transaction(struct btrfs_trans_handle *trans)
{
	return __btrfs_end_transaction(trans, 0);
}

int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans)
{
	return __btrfs_end_transaction(trans, 1);
}

/*
 * when btree blocks are allocated, they have some corresponding bits set for
 * them in one of two extent_io trees.  This is used to make sure all of
 * those extents are sent to disk but does not wait on them
 */
int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
			       struct extent_io_tree *dirty_pages, int mark)
{
	int err = 0;
	int werr = 0;
	struct address_space *mapping = fs_info->btree_inode->i_mapping;
	struct extent_state *cached_state = NULL;
	u64 start = 0;
	u64 end;

	atomic_inc(&BTRFS_I(fs_info->btree_inode)->sync_writers);
	while (!find_first_extent_bit(dirty_pages, start, &start, &end,
				      mark, &cached_state)) {
		bool wait_writeback = false;

		err = convert_extent_bit(dirty_pages, start, end,
					 EXTENT_NEED_WAIT,
					 mark, &cached_state);
		/*
		 * convert_extent_bit can return -ENOMEM, which is most of the
		 * time a temporary error. So when it happens, ignore the error
		 * and wait for writeback of this range to finish - because we
		 * failed to set the bit EXTENT_NEED_WAIT for the range, a call
		 * to __btrfs_wait_marked_extents() would not know that
		 * writeback for this range started and therefore wouldn't
		 * wait for it to finish - we don't want to commit a
		 * superblock that points to btree nodes/leafs for which
		 * writeback hasn't finished yet (and without errors).
		 * We cleanup any entries left in the io tree when committing
		 * the transaction (through extent_io_tree_release()).
		 */
		if (err == -ENOMEM) {
			err = 0;
			wait_writeback = true;
		}
		if (!err)
			err = filemap_fdatawrite_range(mapping, start, end);
		if (err)
			werr = err;
		else if (wait_writeback)
			werr = filemap_fdatawait_range(mapping, start, end);
		free_extent_state(cached_state);
		cached_state = NULL;
		cond_resched();
		start = end + 1;
	}
	atomic_dec(&BTRFS_I(fs_info->btree_inode)->sync_writers);
	return werr;
}

/*
 * when btree blocks are allocated, they have some corresponding bits set for
 * them in one of two extent_io trees.  This is used to make sure all of
 * those extents are on disk for transaction or log commit.  We wait
 * on all the pages and clear them from the dirty pages state tree
 */
static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
				       struct extent_io_tree *dirty_pages)
{
	int err = 0;
	int werr = 0;
	struct address_space *mapping = fs_info->btree_inode->i_mapping;
	struct extent_state *cached_state = NULL;
	u64 start = 0;
	u64 end;

	while (!find_first_extent_bit(dirty_pages, start, &start, &end,
				      EXTENT_NEED_WAIT, &cached_state)) {
		/*
		 * Ignore -ENOMEM errors returned by clear_extent_bit().
		 * When committing the transaction, we'll remove any entries
		 * left in the io tree. For a log commit, we don't remove them
		 * after committing the log because the tree can be accessed
		 * concurrently - we do it only at transaction commit time when
		 * it's safe to do it (through extent_io_tree_release()).
		 */
		err = clear_extent_bit(dirty_pages, start, end,
				       EXTENT_NEED_WAIT, 0, 0, &cached_state);
		if (err == -ENOMEM)
			err = 0;
		if (!err)
			err = filemap_fdatawait_range(mapping, start, end);
		if (err)
			werr = err;
		free_extent_state(cached_state);
		cached_state = NULL;
		cond_resched();
		start = end + 1;
	}
	if (err)
		werr = err;
	return werr;
}

static int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
		       struct extent_io_tree *dirty_pages)
{
	bool errors = false;
	int err;

	err = __btrfs_wait_marked_extents(fs_info, dirty_pages);
	if (test_and_clear_bit(BTRFS_FS_BTREE_ERR, &fs_info->flags))
		errors = true;

	if (errors && !err)
		err = -EIO;
	return err;
}

int btrfs_wait_tree_log_extents(struct btrfs_root *log_root, int mark)
{
	struct btrfs_fs_info *fs_info = log_root->fs_info;
	struct extent_io_tree *dirty_pages = &log_root->dirty_log_pages;
	bool errors = false;
	int err;

	ASSERT(log_root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);

	err = __btrfs_wait_marked_extents(fs_info, dirty_pages);
	if ((mark & EXTENT_DIRTY) &&
	    test_and_clear_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags))
		errors = true;

	if ((mark & EXTENT_NEW) &&
	    test_and_clear_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags))
		errors = true;

	if (errors && !err)
		err = -EIO;
	return err;
}

/*
 * When btree blocks are allocated the corresponding extents are marked dirty.
 * This function ensures such extents are persisted on disk for transaction or
 * log commit.
 *
 * @trans: transaction whose dirty pages we'd like to write
 */
static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans)
{
	int ret;
	int ret2;
	struct extent_io_tree *dirty_pages = &trans->transaction->dirty_pages;
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct blk_plug plug;

	blk_start_plug(&plug);
	ret = btrfs_write_marked_extents(fs_info, dirty_pages, EXTENT_DIRTY);
	blk_finish_plug(&plug);
	ret2 = btrfs_wait_extents(fs_info, dirty_pages);

	extent_io_tree_release(&trans->transaction->dirty_pages);

	if (ret)
		return ret;
	else if (ret2)
		return ret2;
	else
		return 0;
}

/*
 * this is used to update the root pointer in the tree of tree roots.
 *
 * But, in the case of the extent allocation tree, updating the root
 * pointer may allocate blocks which may change the root of the extent
 * allocation tree.
 *
 * So, this loops and repeats and makes sure the cowonly root didn't
 * change while the root pointer was being updated in the metadata.
 */
static int update_cowonly_root(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root)
{
	int ret;
	u64 old_root_bytenr;
	u64 old_root_used;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_root *tree_root = fs_info->tree_root;

	old_root_used = btrfs_root_used(&root->root_item);

	while (1) {
		old_root_bytenr = btrfs_root_bytenr(&root->root_item);
		if (old_root_bytenr == root->node->start &&
		    old_root_used == btrfs_root_used(&root->root_item))
			break;

		btrfs_set_root_node(&root->root_item, root->node);
		ret = btrfs_update_root(trans, tree_root,
					&root->root_key,
					&root->root_item);
		if (ret)
			return ret;

		old_root_used = btrfs_root_used(&root->root_item);
	}

	return 0;
}

/*
 * update all the cowonly tree roots on disk
 *
 * The error handling in this function may not be obvious. Any of the
 * failures will cause the file system to go offline. We still need
 * to clean up the delayed refs.
 */
static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct list_head *dirty_bgs = &trans->transaction->dirty_bgs;
	struct list_head *io_bgs = &trans->transaction->io_bgs;
	struct list_head *next;
	struct extent_buffer *eb;
	int ret;

	eb = btrfs_lock_root_node(fs_info->tree_root);
	ret = btrfs_cow_block(trans, fs_info->tree_root, eb, NULL,
			      0, &eb);
	btrfs_tree_unlock(eb);
	free_extent_buffer(eb);

	if (ret)
		return ret;

	ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
	if (ret)
		return ret;

	ret = btrfs_run_dev_stats(trans);
	if (ret)
		return ret;
	ret = btrfs_run_dev_replace(trans);
	if (ret)
		return ret;
	ret = btrfs_run_qgroups(trans);
	if (ret)
		return ret;

	ret = btrfs_setup_space_cache(trans);
	if (ret)
		return ret;

	/* run_qgroups might have added some more refs */
	ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
	if (ret)
		return ret;
again:
	while (!list_empty(&fs_info->dirty_cowonly_roots)) {
		struct btrfs_root *root;
		next = fs_info->dirty_cowonly_roots.next;
		list_del_init(next);
		root = list_entry(next, struct btrfs_root, dirty_list);
		clear_bit(BTRFS_ROOT_DIRTY, &root->state);

		if (root != fs_info->extent_root)
			list_add_tail(&root->dirty_list,
				      &trans->transaction->switch_commits);
		ret = update_cowonly_root(trans, root);
		if (ret)
			return ret;
		ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
		if (ret)
			return ret;
	}

	while (!list_empty(dirty_bgs) || !list_empty(io_bgs)) {
		ret = btrfs_write_dirty_block_groups(trans);
		if (ret)
			return ret;
		ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
		if (ret)
			return ret;
	}

	if (!list_empty(&fs_info->dirty_cowonly_roots))
		goto again;

	list_add_tail(&fs_info->extent_root->dirty_list,
		      &trans->transaction->switch_commits);

	/* Update dev-replace pointer once everything is committed */
	fs_info->dev_replace.committed_cursor_left =
		fs_info->dev_replace.cursor_left_last_write_of_item;

	return 0;
}

/*
 * dead roots are old snapshots that need to be deleted.  This allocates
 * a dirty root struct and adds it into the list of dead roots that need to
 * be deleted
 */
void btrfs_add_dead_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;

	spin_lock(&fs_info->trans_lock);
	if (list_empty(&root->root_list))
		list_add_tail(&root->root_list, &fs_info->dead_roots);
	spin_unlock(&fs_info->trans_lock);
}

/*
 * update all the cowonly tree roots on disk
 */
static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *gang[8];
	int i;
	int ret;
	int err = 0;

	spin_lock(&fs_info->fs_roots_radix_lock);
	while (1) {
		ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
						 (void **)gang, 0,
						 ARRAY_SIZE(gang),
						 BTRFS_ROOT_TRANS_TAG);
		if (ret == 0)
			break;
		for (i = 0; i < ret; i++) {
			struct btrfs_root *root = gang[i];
			radix_tree_tag_clear(&fs_info->fs_roots_radix,
					(unsigned long)root->root_key.objectid,
					BTRFS_ROOT_TRANS_TAG);
			spin_unlock(&fs_info->fs_roots_radix_lock);

			btrfs_free_log(trans, root);
			btrfs_update_reloc_root(trans, root);

			btrfs_save_ino_cache(root, trans);

			/* see comments in should_cow_block() */
			clear_bit(BTRFS_ROOT_FORCE_COW, &root->state);
			smp_mb__after_atomic();

			if (root->commit_root != root->node) {
				list_add_tail(&root->dirty_list,
					&trans->transaction->switch_commits);
				btrfs_set_root_node(&root->root_item,
						    root->node);
			}

			err = btrfs_update_root(trans, fs_info->tree_root,
						&root->root_key,
						&root->root_item);
			spin_lock(&fs_info->fs_roots_radix_lock);
			if (err)
				break;
			btrfs_qgroup_free_meta_all_pertrans(root);
		}
	}
	spin_unlock(&fs_info->fs_roots_radix_lock);
	return err;
}

/*
 * defrag a given btree.
 * Every leaf in the btree is read and defragged.
 */
int btrfs_defrag_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *info = root->fs_info;
	struct btrfs_trans_handle *trans;
	int ret;

	if (test_and_set_bit(BTRFS_ROOT_DEFRAG_RUNNING, &root->state))
		return 0;

	while (1) {
		trans = btrfs_start_transaction(root, 0);
		if (IS_ERR(trans))
			return PTR_ERR(trans);

		ret = btrfs_defrag_leaves(trans, root);

		btrfs_end_transaction(trans);
		btrfs_btree_balance_dirty(info);
		cond_resched();

		if (btrfs_fs_closing(info) || ret != -EAGAIN)
			break;

		if (btrfs_defrag_cancelled(info)) {
			btrfs_debug(info, "defrag_root cancelled");
			ret = -EAGAIN;
			break;
		}
	}
	clear_bit(BTRFS_ROOT_DEFRAG_RUNNING, &root->state);
	return ret;
}

/*
 * Do all special snapshot related qgroup dirty hack.
 *
 * Will do all needed qgroup inherit and dirty hack like switch commit
 * roots inside one transaction and write all btree into disk, to make
 * qgroup works.
 */
static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
				   struct btrfs_root *src,
				   struct btrfs_root *parent,
				   struct btrfs_qgroup_inherit *inherit,
				   u64 dst_objectid)
{
	struct btrfs_fs_info *fs_info = src->fs_info;
	int ret;

	/*
	 * Save some performance in the case that qgroups are not
	 * enabled. If this check races with the ioctl, rescan will
	 * kick in anyway.
	 */
	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
		return 0;

	/*
	 * Ensure dirty @src will be committed.  Or, after coming
	 * commit_fs_roots() and switch_commit_roots(), any dirty but not
	 * recorded root will never be updated again, causing an outdated root
	 * item.
	 */
	record_root_in_trans(trans, src, 1);

	/*
	 * We are going to commit transaction, see btrfs_commit_transaction()
	 * comment for reason locking tree_log_mutex
	 */
	mutex_lock(&fs_info->tree_log_mutex);

	ret = commit_fs_roots(trans);
	if (ret)
		goto out;
	ret = btrfs_qgroup_account_extents(trans);
	if (ret < 0)
		goto out;

	/* Now qgroup are all updated, we can inherit it to new qgroups */
	ret = btrfs_qgroup_inherit(trans, src->root_key.objectid, dst_objectid,
				   inherit);
	if (ret < 0)
		goto out;

	/*
	 * Now we do a simplified commit transaction, which will:
	 * 1) commit all subvolume and extent tree
	 *    To ensure all subvolume and extent tree have a valid
	 *    commit_root to accounting later insert_dir_item()
	 * 2) write all btree blocks onto disk
	 *    This is to make sure later btree modification will be cowed
	 *    Or commit_root can be populated and cause wrong qgroup numbers
	 * In this simplified commit, we don't really care about other trees
	 * like chunk and root tree, as they won't affect qgroup.
	 * And we don't write super to avoid half committed status.
	 */
	ret = commit_cowonly_roots(trans);
	if (ret)
		goto out;
	switch_commit_roots(trans->transaction);
	ret = btrfs_write_and_wait_transaction(trans);
	if (ret)
		btrfs_handle_fs_error(fs_info, ret,
			"Error while writing out transaction for qgroup");

out:
	mutex_unlock(&fs_info->tree_log_mutex);

	/*
	 * Force parent root to be updated, as we recorded it before so its
	 * last_trans == cur_transid.
	 * Or it won't be committed again onto disk after later
	 * insert_dir_item()
	 */
	if (!ret)
		record_root_in_trans(trans, parent, 1);
	return ret;
}

/*
 * new snapshots need to be created at a very specific time in the
 * transaction commit.  This does the actual creation.
 *
 * Note:
 * If the error which may affect the commitment of the current transaction
 * happens, we should return the error number. If the error which just affect
 * the creation of the pending snapshots, just return 0.
 */
static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
				   struct btrfs_pending_snapshot *pending)
{

	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_key key;
	struct btrfs_root_item *new_root_item;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root *root = pending->root;
	struct btrfs_root *parent_root;
	struct btrfs_block_rsv *rsv;
	struct inode *parent_inode;
	struct btrfs_path *path;
	struct btrfs_dir_item *dir_item;
	struct dentry *dentry;
	struct extent_buffer *tmp;
	struct extent_buffer *old;
	struct timespec64 cur_time;
	int ret = 0;
	u64 to_reserve = 0;
	u64 index = 0;
	u64 objectid;
	u64 root_flags;
	uuid_le new_uuid;

	ASSERT(pending->path);
	path = pending->path;

	ASSERT(pending->root_item);
	new_root_item = pending->root_item;

	pending->error = btrfs_find_free_objectid(tree_root, &objectid);
	if (pending->error)
		goto no_free_objectid;

	/*
	 * Make qgroup to skip current new snapshot's qgroupid, as it is
	 * accounted by later btrfs_qgroup_inherit().
	 */
	btrfs_set_skip_qgroup(trans, objectid);

	btrfs_reloc_pre_snapshot(pending, &to_reserve);

	if (to_reserve > 0) {
		pending->error = btrfs_block_rsv_add(root,
						     &pending->block_rsv,
						     to_reserve,
						     BTRFS_RESERVE_NO_FLUSH);
		if (pending->error)
			goto clear_skip_qgroup;
	}

	key.objectid = objectid;
	key.offset = (u64)-1;
	key.type = BTRFS_ROOT_ITEM_KEY;

	rsv = trans->block_rsv;
	trans->block_rsv = &pending->block_rsv;
	trans->bytes_reserved = trans->block_rsv->reserved;
	trace_btrfs_space_reservation(fs_info, "transaction",
				      trans->transid,
				      trans->bytes_reserved, 1);
	dentry = pending->dentry;
	parent_inode = pending->dir;
	parent_root = BTRFS_I(parent_inode)->root;
	record_root_in_trans(trans, parent_root, 0);

	cur_time = current_time(parent_inode);

	/*
	 * insert the directory item
	 */
	ret = btrfs_set_inode_index(BTRFS_I(parent_inode), &index);
	BUG_ON(ret); /* -ENOMEM */

	/* check if there is a file/dir which has the same name. */
	dir_item = btrfs_lookup_dir_item(NULL, parent_root, path,
					 btrfs_ino(BTRFS_I(parent_inode)),
					 dentry->d_name.name,
					 dentry->d_name.len, 0);
	if (dir_item != NULL && !IS_ERR(dir_item)) {
		pending->error = -EEXIST;
		goto dir_item_existed;
	} else if (IS_ERR(dir_item)) {
		ret = PTR_ERR(dir_item);
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}
	btrfs_release_path(path);

	/*
	 * pull in the delayed directory update
	 * and the delayed inode item
	 * otherwise we corrupt the FS during
	 * snapshot
	 */
	ret = btrfs_run_delayed_items(trans);
	if (ret) {	/* Transaction aborted */
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	record_root_in_trans(trans, root, 0);
	btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
	memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
	btrfs_check_and_init_root_item(new_root_item);

	root_flags = btrfs_root_flags(new_root_item);
	if (pending->readonly)
		root_flags |= BTRFS_ROOT_SUBVOL_RDONLY;
	else
		root_flags &= ~BTRFS_ROOT_SUBVOL_RDONLY;
	btrfs_set_root_flags(new_root_item, root_flags);

	btrfs_set_root_generation_v2(new_root_item,
			trans->transid);
	uuid_le_gen(&new_uuid);
	memcpy(new_root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE);
	memcpy(new_root_item->parent_uuid, root->root_item.uuid,
			BTRFS_UUID_SIZE);
	if (!(root_flags & BTRFS_ROOT_SUBVOL_RDONLY)) {
		memset(new_root_item->received_uuid, 0,
		       sizeof(new_root_item->received_uuid));
		memset(&new_root_item->stime, 0, sizeof(new_root_item->stime));
		memset(&new_root_item->rtime, 0, sizeof(new_root_item->rtime));
		btrfs_set_root_stransid(new_root_item, 0);
		btrfs_set_root_rtransid(new_root_item, 0);
	}
	btrfs_set_stack_timespec_sec(&new_root_item->otime, cur_time.tv_sec);
	btrfs_set_stack_timespec_nsec(&new_root_item->otime, cur_time.tv_nsec);
	btrfs_set_root_otransid(new_root_item, trans->transid);

	old = btrfs_lock_root_node(root);
	ret = btrfs_cow_block(trans, root, old, NULL, 0, &old);
	if (ret) {
		btrfs_tree_unlock(old);
		free_extent_buffer(old);
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	btrfs_set_lock_blocking_write(old);

	ret = btrfs_copy_root(trans, root, old, &tmp, objectid);
	/* clean up in any case */
	btrfs_tree_unlock(old);
	free_extent_buffer(old);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}
	/* see comments in should_cow_block() */
	set_bit(BTRFS_ROOT_FORCE_COW, &root->state);
	smp_wmb();

	btrfs_set_root_node(new_root_item, tmp);
	/* record when the snapshot was created in key.offset */
	key.offset = trans->transid;
	ret = btrfs_insert_root(trans, tree_root, &key, new_root_item);
	btrfs_tree_unlock(tmp);
	free_extent_buffer(tmp);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	/*
	 * insert root back/forward references
	 */
	ret = btrfs_add_root_ref(trans, objectid,
				 parent_root->root_key.objectid,
				 btrfs_ino(BTRFS_I(parent_inode)), index,
				 dentry->d_name.name, dentry->d_name.len);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	key.offset = (u64)-1;
	pending->snap = btrfs_read_fs_root_no_name(fs_info, &key);
	if (IS_ERR(pending->snap)) {
		ret = PTR_ERR(pending->snap);
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	ret = btrfs_reloc_post_snapshot(trans, pending);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	/*
	 * Do special qgroup accounting for snapshot, as we do some qgroup
	 * snapshot hack to do fast snapshot.
	 * To co-operate with that hack, we do hack again.
	 * Or snapshot will be greatly slowed down by a subtree qgroup rescan
	 */
	ret = qgroup_account_snapshot(trans, root, parent_root,
				      pending->inherit, objectid);
	if (ret < 0)
		goto fail;

	ret = btrfs_insert_dir_item(trans, dentry->d_name.name,
				    dentry->d_name.len, BTRFS_I(parent_inode),
				    &key, BTRFS_FT_DIR, index);
	/* We have check then name at the beginning, so it is impossible. */
	BUG_ON(ret == -EEXIST || ret == -EOVERFLOW);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

	btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size +
					 dentry->d_name.len * 2);
	parent_inode->i_mtime = parent_inode->i_ctime =
		current_time(parent_inode);
	ret = btrfs_update_inode_fallback(trans, parent_root, parent_inode);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}
	ret = btrfs_uuid_tree_add(trans, new_uuid.b, BTRFS_UUID_KEY_SUBVOL,
				  objectid);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}
	if (!btrfs_is_empty_uuid(new_root_item->received_uuid)) {
		ret = btrfs_uuid_tree_add(trans, new_root_item->received_uuid,
					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
					  objectid);
		if (ret && ret != -EEXIST) {
			btrfs_abort_transaction(trans, ret);
			goto fail;
		}
	}

	ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto fail;
	}

fail:
	pending->error = ret;
dir_item_existed:
	trans->block_rsv = rsv;
	trans->bytes_reserved = 0;
clear_skip_qgroup:
	btrfs_clear_skip_qgroup(trans);
no_free_objectid:
	kfree(new_root_item);
	pending->root_item = NULL;
	btrfs_free_path(path);
	pending->path = NULL;

	return ret;
}

/*
 * create all the snapshots we've scheduled for creation
 */
static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans)
{
	struct btrfs_pending_snapshot *pending, *next;
	struct list_head *head = &trans->transaction->pending_snapshots;
	int ret = 0;

	list_for_each_entry_safe(pending, next, head, list) {
		list_del(&pending->list);
		ret = create_pending_snapshot(trans, pending);
		if (ret)
			break;
	}
	return ret;
}

static void update_super_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root_item *root_item;
	struct btrfs_super_block *super;

	super = fs_info->super_copy;

	root_item = &fs_info->chunk_root->root_item;
	super->chunk_root = root_item->bytenr;
	super->chunk_root_generation = root_item->generation;
	super->chunk_root_level = root_item->level;

	root_item = &fs_info->tree_root->root_item;
	super->root = root_item->bytenr;
	super->generation = root_item->generation;
	super->root_level = root_item->level;
	if (btrfs_test_opt(fs_info, SPACE_CACHE))
		super->cache_generation = root_item->generation;
	if (test_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags))
		super->uuid_tree_generation = root_item->generation;
}

int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
{
	struct btrfs_transaction *trans;
	int ret = 0;

	spin_lock(&info->trans_lock);
	trans = info->running_transaction;
	if (trans)
		ret = (trans->state >= TRANS_STATE_COMMIT_START);
	spin_unlock(&info->trans_lock);
	return ret;
}

int btrfs_transaction_blocked(struct btrfs_fs_info *info)
{
	struct btrfs_transaction *trans;
	int ret = 0;

	spin_lock(&info->trans_lock);
	trans = info->running_transaction;
	if (trans)
		ret = is_transaction_blocked(trans);
	spin_unlock(&info->trans_lock);
	return ret;
}

/*
 * wait for the current transaction commit to start and block subsequent
 * transaction joins
 */
static void wait_current_trans_commit_start(struct btrfs_fs_info *fs_info,
					    struct btrfs_transaction *trans)
{
	wait_event(fs_info->transaction_blocked_wait,
		   trans->state >= TRANS_STATE_COMMIT_START || trans->aborted);
}

/*
 * wait for the current transaction to start and then become unblocked.
 * caller holds ref.
 */
static void wait_current_trans_commit_start_and_unblock(
					struct btrfs_fs_info *fs_info,
					struct btrfs_transaction *trans)
{
	wait_event(fs_info->transaction_wait,
		   trans->state >= TRANS_STATE_UNBLOCKED || trans->aborted);
}

/*
 * commit transactions asynchronously. once btrfs_commit_transaction_async
 * returns, any subsequent transaction will not be allowed to join.
 */
struct btrfs_async_commit {
	struct btrfs_trans_handle *newtrans;
	struct work_struct work;
};

static void do_async_commit(struct work_struct *work)
{
	struct btrfs_async_commit *ac =
		container_of(work, struct btrfs_async_commit, work);

	/*
	 * We've got freeze protection passed with the transaction.
	 * Tell lockdep about it.
	 */
	if (ac->newtrans->type & __TRANS_FREEZABLE)
		__sb_writers_acquired(ac->newtrans->fs_info->sb, SB_FREEZE_FS);

	current->journal_info = ac->newtrans;

	btrfs_commit_transaction(ac->newtrans);
	kfree(ac);
}

int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
				   int wait_for_unblock)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_async_commit *ac;
	struct btrfs_transaction *cur_trans;

	ac = kmalloc(sizeof(*ac), GFP_NOFS);
	if (!ac)
		return -ENOMEM;

	INIT_WORK(&ac->work, do_async_commit);
	ac->newtrans = btrfs_join_transaction(trans->root);
	if (IS_ERR(ac->newtrans)) {
		int err = PTR_ERR(ac->newtrans);
		kfree(ac);
		return err;
	}

	/* take transaction reference */
	cur_trans = trans->transaction;
	refcount_inc(&cur_trans->use_count);

	btrfs_end_transaction(trans);

	/*
	 * Tell lockdep we've released the freeze rwsem, since the
	 * async commit thread will be the one to unlock it.
	 */
	if (ac->newtrans->type & __TRANS_FREEZABLE)
		__sb_writers_release(fs_info->sb, SB_FREEZE_FS);

	schedule_work(&ac->work);

	/* wait for transaction to start and unblock */
	if (wait_for_unblock)
		wait_current_trans_commit_start_and_unblock(fs_info, cur_trans);
	else
		wait_current_trans_commit_start(fs_info, cur_trans);

	if (current->journal_info == trans)
		current->journal_info = NULL;

	btrfs_put_transaction(cur_trans);
	return 0;
}


static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_transaction *cur_trans = trans->transaction;

	WARN_ON(refcount_read(&trans->use_count) > 1);

	btrfs_abort_transaction(trans, err);

	spin_lock(&fs_info->trans_lock);

	/*
	 * If the transaction is removed from the list, it means this
	 * transaction has been committed successfully, so it is impossible
	 * to call the cleanup function.
	 */
	BUG_ON(list_empty(&cur_trans->list));

	list_del_init(&cur_trans->list);
	if (cur_trans == fs_info->running_transaction) {
		cur_trans->state = TRANS_STATE_COMMIT_DOING;
		spin_unlock(&fs_info->trans_lock);
		wait_event(cur_trans->writer_wait,
			   atomic_read(&cur_trans->num_writers) == 1);

		spin_lock(&fs_info->trans_lock);
	}
	spin_unlock(&fs_info->trans_lock);

	btrfs_cleanup_one_transaction(trans->transaction, fs_info);

	spin_lock(&fs_info->trans_lock);
	if (cur_trans == fs_info->running_transaction)
		fs_info->running_transaction = NULL;
	spin_unlock(&fs_info->trans_lock);

	if (trans->type & __TRANS_FREEZABLE)
		sb_end_intwrite(fs_info->sb);
	btrfs_put_transaction(cur_trans);
	btrfs_put_transaction(cur_trans);

	trace_btrfs_transaction_commit(trans->root);

	if (current->journal_info == trans)
		current->journal_info = NULL;
	btrfs_scrub_cancel(fs_info);

	kmem_cache_free(btrfs_trans_handle_cachep, trans);
}

/*
 * Release reserved delayed ref space of all pending block groups of the
 * transaction and remove them from the list
 */
static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
{
       struct btrfs_fs_info *fs_info = trans->fs_info;
       struct btrfs_block_group *block_group, *tmp;

       list_for_each_entry_safe(block_group, tmp, &trans->new_bgs, bg_list) {
               btrfs_delayed_refs_rsv_release(fs_info, 1);
               list_del_init(&block_group->bg_list);
       }
}

static inline int btrfs_start_delalloc_flush(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;

	/*
	 * We use writeback_inodes_sb here because if we used
	 * btrfs_start_delalloc_roots we would deadlock with fs freeze.
	 * Currently are holding the fs freeze lock, if we do an async flush
	 * we'll do btrfs_join_transaction() and deadlock because we need to
	 * wait for the fs freeze lock.  Using the direct flushing we benefit
	 * from already being in a transaction and our join_transaction doesn't
	 * have to re-take the fs freeze lock.
	 */
	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
		writeback_inodes_sb(fs_info->sb, WB_REASON_SYNC);
	} else {
		struct btrfs_pending_snapshot *pending;
		struct list_head *head = &trans->transaction->pending_snapshots;

		/*
		 * Flush dellaloc for any root that is going to be snapshotted.
		 * This is done to avoid a corrupted version of files, in the
		 * snapshots, that had both buffered and direct IO writes (even
		 * if they were done sequentially) due to an unordered update of
		 * the inode's size on disk.
		 */
		list_for_each_entry(pending, head, list) {
			int ret;

			ret = btrfs_start_delalloc_snapshot(pending->root);
			if (ret)
				return ret;
		}
	}
	return 0;
}

static inline void btrfs_wait_delalloc_flush(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;

	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT)) {
		btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
	} else {
		struct btrfs_pending_snapshot *pending;
		struct list_head *head = &trans->transaction->pending_snapshots;

		/*
		 * Wait for any dellaloc that we started previously for the roots
		 * that are going to be snapshotted. This is to avoid a corrupted
		 * version of files in the snapshots that had both buffered and
		 * direct IO writes (even if they were done sequentially).
		 */
		list_for_each_entry(pending, head, list)
			btrfs_wait_ordered_extents(pending->root,
						   U64_MAX, 0, U64_MAX);
	}
}

int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_transaction *cur_trans = trans->transaction;
	struct btrfs_transaction *prev_trans = NULL;
	int ret;

	ASSERT(refcount_read(&trans->use_count) == 1);

	/* Stop the commit early if ->aborted is set */
	if (unlikely(READ_ONCE(cur_trans->aborted))) {
		ret = cur_trans->aborted;
		btrfs_end_transaction(trans);
		return ret;
	}

	btrfs_trans_release_metadata(trans);
	trans->block_rsv = NULL;

	/* make a pass through all the delayed refs we have so far
	 * any runnings procs may add more while we are here
	 */
	ret = btrfs_run_delayed_refs(trans, 0);
	if (ret) {
		btrfs_end_transaction(trans);
		return ret;
	}

	cur_trans = trans->transaction;

	/*
	 * set the flushing flag so procs in this transaction have to
	 * start sending their work down.
	 */
	cur_trans->delayed_refs.flushing = 1;
	smp_wmb();

	btrfs_create_pending_block_groups(trans);

	ret = btrfs_run_delayed_refs(trans, 0);
	if (ret) {
		btrfs_end_transaction(trans);
		return ret;
	}

	if (!test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &cur_trans->flags)) {
		int run_it = 0;

		/* this mutex is also taken before trying to set
		 * block groups readonly.  We need to make sure
		 * that nobody has set a block group readonly
		 * after a extents from that block group have been
		 * allocated for cache files.  btrfs_set_block_group_ro
		 * will wait for the transaction to commit if it
		 * finds BTRFS_TRANS_DIRTY_BG_RUN set.
		 *
		 * The BTRFS_TRANS_DIRTY_BG_RUN flag is also used to make sure
		 * only one process starts all the block group IO.  It wouldn't
		 * hurt to have more than one go through, but there's no
		 * real advantage to it either.
		 */
		mutex_lock(&fs_info->ro_block_group_mutex);
		if (!test_and_set_bit(BTRFS_TRANS_DIRTY_BG_RUN,
				      &cur_trans->flags))
			run_it = 1;
		mutex_unlock(&fs_info->ro_block_group_mutex);

		if (run_it) {
			ret = btrfs_start_dirty_block_groups(trans);
			if (ret) {
				btrfs_end_transaction(trans);
				return ret;
			}
		}
	}

	spin_lock(&fs_info->trans_lock);
	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
		spin_unlock(&fs_info->trans_lock);
		refcount_inc(&cur_trans->use_count);
		ret = btrfs_end_transaction(trans);

		wait_for_commit(cur_trans);

		if (unlikely(cur_trans->aborted))
			ret = cur_trans->aborted;

		btrfs_put_transaction(cur_trans);

		return ret;
	}

	cur_trans->state = TRANS_STATE_COMMIT_START;
	wake_up(&fs_info->transaction_blocked_wait);

	if (cur_trans->list.prev != &fs_info->trans_list) {
		prev_trans = list_entry(cur_trans->list.prev,
					struct btrfs_transaction, list);
		if (prev_trans->state != TRANS_STATE_COMPLETED) {
			refcount_inc(&prev_trans->use_count);
			spin_unlock(&fs_info->trans_lock);

			wait_for_commit(prev_trans);
			ret = prev_trans->aborted;

			btrfs_put_transaction(prev_trans);
			if (ret)
				goto cleanup_transaction;
		} else {
			spin_unlock(&fs_info->trans_lock);
		}
	} else {
		spin_unlock(&fs_info->trans_lock);
		/*
		 * The previous transaction was aborted and was already removed
		 * from the list of transactions at fs_info->trans_list. So we
		 * abort to prevent writing a new superblock that reflects a
		 * corrupt state (pointing to trees with unwritten nodes/leafs).
		 */
		if (test_bit(BTRFS_FS_STATE_TRANS_ABORTED, &fs_info->fs_state)) {
			ret = -EROFS;
			goto cleanup_transaction;
		}
	}

	extwriter_counter_dec(cur_trans, trans->type);

	ret = btrfs_start_delalloc_flush(trans);
	if (ret)
		goto cleanup_transaction;

	ret = btrfs_run_delayed_items(trans);
	if (ret)
		goto cleanup_transaction;

	wait_event(cur_trans->writer_wait,
		   extwriter_counter_read(cur_trans) == 0);

	/* some pending stuffs might be added after the previous flush. */
	ret = btrfs_run_delayed_items(trans);
	if (ret)
		goto cleanup_transaction;

	btrfs_wait_delalloc_flush(trans);

	btrfs_scrub_pause(fs_info);
	/*
	 * Ok now we need to make sure to block out any other joins while we
	 * commit the transaction.  We could have started a join before setting
	 * COMMIT_DOING so make sure to wait for num_writers to == 1 again.
	 */
	spin_lock(&fs_info->trans_lock);
	cur_trans->state = TRANS_STATE_COMMIT_DOING;
	spin_unlock(&fs_info->trans_lock);
	wait_event(cur_trans->writer_wait,
		   atomic_read(&cur_trans->num_writers) == 1);

	/* ->aborted might be set after the previous check, so check it */
	if (unlikely(READ_ONCE(cur_trans->aborted))) {
		ret = cur_trans->aborted;
		goto scrub_continue;
	}
	/*
	 * the reloc mutex makes sure that we stop
	 * the balancing code from coming in and moving
	 * extents around in the middle of the commit
	 */
	mutex_lock(&fs_info->reloc_mutex);

	/*
	 * We needn't worry about the delayed items because we will
	 * deal with them in create_pending_snapshot(), which is the
	 * core function of the snapshot creation.
	 */
	ret = create_pending_snapshots(trans);
	if (ret) {
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	/*
	 * We insert the dir indexes of the snapshots and update the inode
	 * of the snapshots' parents after the snapshot creation, so there
	 * are some delayed items which are not dealt with. Now deal with
	 * them.
	 *
	 * We needn't worry that this operation will corrupt the snapshots,
	 * because all the tree which are snapshoted will be forced to COW
	 * the nodes and leaves.
	 */
	ret = btrfs_run_delayed_items(trans);
	if (ret) {
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
	if (ret) {
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	/*
	 * make sure none of the code above managed to slip in a
	 * delayed item
	 */
	btrfs_assert_delayed_root_empty(fs_info);

	WARN_ON(cur_trans != trans->transaction);

	/* btrfs_commit_tree_roots is responsible for getting the
	 * various roots consistent with each other.  Every pointer
	 * in the tree of tree roots has to point to the most up to date
	 * root for every subvolume and other tree.  So, we have to keep
	 * the tree logging code from jumping in and changing any
	 * of the trees.
	 *
	 * At this point in the commit, there can't be any tree-log
	 * writers, but a little lower down we drop the trans mutex
	 * and let new people in.  By holding the tree_log_mutex
	 * from now until after the super is written, we avoid races
	 * with the tree-log code.
	 */
	mutex_lock(&fs_info->tree_log_mutex);

	ret = commit_fs_roots(trans);
	if (ret) {
		mutex_unlock(&fs_info->tree_log_mutex);
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	/*
	 * Since the transaction is done, we can apply the pending changes
	 * before the next transaction.
	 */
	btrfs_apply_pending_changes(fs_info);

	/* commit_fs_roots gets rid of all the tree log roots, it is now
	 * safe to free the root of tree log roots
	 */
	btrfs_free_log_root_tree(trans, fs_info);

	/*
	 * commit_fs_roots() can call btrfs_save_ino_cache(), which generates
	 * new delayed refs. Must handle them or qgroup can be wrong.
	 */
	ret = btrfs_run_delayed_refs(trans, (unsigned long)-1);
	if (ret) {
		mutex_unlock(&fs_info->tree_log_mutex);
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	/*
	 * Since fs roots are all committed, we can get a quite accurate
	 * new_roots. So let's do quota accounting.
	 */
	ret = btrfs_qgroup_account_extents(trans);
	if (ret < 0) {
		mutex_unlock(&fs_info->tree_log_mutex);
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	ret = commit_cowonly_roots(trans);
	if (ret) {
		mutex_unlock(&fs_info->tree_log_mutex);
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	/*
	 * The tasks which save the space cache and inode cache may also
	 * update ->aborted, check it.
	 */
	if (unlikely(READ_ONCE(cur_trans->aborted))) {
		ret = cur_trans->aborted;
		mutex_unlock(&fs_info->tree_log_mutex);
		mutex_unlock(&fs_info->reloc_mutex);
		goto scrub_continue;
	}

	btrfs_prepare_extent_commit(fs_info);

	cur_trans = fs_info->running_transaction;

	btrfs_set_root_node(&fs_info->tree_root->root_item,
			    fs_info->tree_root->node);
	list_add_tail(&fs_info->tree_root->dirty_list,
		      &cur_trans->switch_commits);

	btrfs_set_root_node(&fs_info->chunk_root->root_item,
			    fs_info->chunk_root->node);
	list_add_tail(&fs_info->chunk_root->dirty_list,
		      &cur_trans->switch_commits);

	switch_commit_roots(cur_trans);

	ASSERT(list_empty(&cur_trans->dirty_bgs));
	ASSERT(list_empty(&cur_trans->io_bgs));
	update_super_roots(fs_info);

	btrfs_set_super_log_root(fs_info->super_copy, 0);
	btrfs_set_super_log_root_level(fs_info->super_copy, 0);
	memcpy(fs_info->super_for_commit, fs_info->super_copy,
	       sizeof(*fs_info->super_copy));

	btrfs_commit_device_sizes(cur_trans);

	clear_bit(BTRFS_FS_LOG1_ERR, &fs_info->flags);
	clear_bit(BTRFS_FS_LOG2_ERR, &fs_info->flags);

	btrfs_trans_release_chunk_metadata(trans);

	spin_lock(&fs_info->trans_lock);
	cur_trans->state = TRANS_STATE_UNBLOCKED;
	fs_info->running_transaction = NULL;
	spin_unlock(&fs_info->trans_lock);
	mutex_unlock(&fs_info->reloc_mutex);

	wake_up(&fs_info->transaction_wait);

	ret = btrfs_write_and_wait_transaction(trans);
	if (ret) {
		btrfs_handle_fs_error(fs_info, ret,
				      "Error while writing out transaction");
		mutex_unlock(&fs_info->tree_log_mutex);
		goto scrub_continue;
	}

	ret = write_all_supers(fs_info, 0);
	/*
	 * the super is written, we can safely allow the tree-loggers
	 * to go about their business
	 */
	mutex_unlock(&fs_info->tree_log_mutex);
	if (ret)
		goto scrub_continue;

	btrfs_finish_extent_commit(trans);

	if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &cur_trans->flags))
		btrfs_clear_space_info_full(fs_info);

	fs_info->last_trans_committed = cur_trans->transid;
	/*
	 * We needn't acquire the lock here because there is no other task
	 * which can change it.
	 */
	cur_trans->state = TRANS_STATE_COMPLETED;
	wake_up(&cur_trans->commit_wait);
	clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);

	spin_lock(&fs_info->trans_lock);
	list_del_init(&cur_trans->list);
	spin_unlock(&fs_info->trans_lock);

	btrfs_put_transaction(cur_trans);
	btrfs_put_transaction(cur_trans);

	if (trans->type & __TRANS_FREEZABLE)
		sb_end_intwrite(fs_info->sb);

	trace_btrfs_transaction_commit(trans->root);

	btrfs_scrub_continue(fs_info);

	if (current->journal_info == trans)
		current->journal_info = NULL;

	kmem_cache_free(btrfs_trans_handle_cachep, trans);

	return ret;

scrub_continue:
	btrfs_scrub_continue(fs_info);
cleanup_transaction:
	btrfs_trans_release_metadata(trans);
	btrfs_cleanup_pending_block_groups(trans);
	btrfs_trans_release_chunk_metadata(trans);
	trans->block_rsv = NULL;
	btrfs_warn(fs_info, "Skipping commit of aborted transaction.");
	if (current->journal_info == trans)
		current->journal_info = NULL;
	cleanup_transaction(trans, ret);

	return ret;
}

/*
 * return < 0 if error
 * 0 if there are no more dead_roots at the time of call
 * 1 there are more to be processed, call me again
 *
 * The return value indicates there are certainly more snapshots to delete, but
 * if there comes a new one during processing, it may return 0. We don't mind,
 * because btrfs_commit_super will poke cleaner thread and it will process it a
 * few seconds later.
 */
int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root)
{
	int ret;
	struct btrfs_fs_info *fs_info = root->fs_info;

	spin_lock(&fs_info->trans_lock);
	if (list_empty(&fs_info->dead_roots)) {
		spin_unlock(&fs_info->trans_lock);
		return 0;
	}
	root = list_first_entry(&fs_info->dead_roots,
			struct btrfs_root, root_list);
	list_del_init(&root->root_list);
	spin_unlock(&fs_info->trans_lock);

	btrfs_debug(fs_info, "cleaner removing %llu", root->root_key.objectid);

	btrfs_kill_all_delayed_nodes(root);

	if (btrfs_header_backref_rev(root->node) <
			BTRFS_MIXED_BACKREF_REV)
		ret = btrfs_drop_snapshot(root, NULL, 0, 0);
	else
		ret = btrfs_drop_snapshot(root, NULL, 1, 0);

	return (ret < 0) ? 0 : 1;
}

void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info)
{
	unsigned long prev;
	unsigned long bit;

	prev = xchg(&fs_info->pending_changes, 0);
	if (!prev)
		return;

	bit = 1 << BTRFS_PENDING_SET_INODE_MAP_CACHE;
	if (prev & bit)
		btrfs_set_opt(fs_info->mount_opt, INODE_MAP_CACHE);
	prev &= ~bit;

	bit = 1 << BTRFS_PENDING_CLEAR_INODE_MAP_CACHE;
	if (prev & bit)
		btrfs_clear_opt(fs_info->mount_opt, INODE_MAP_CACHE);
	prev &= ~bit;

	bit = 1 << BTRFS_PENDING_COMMIT;
	if (prev & bit)
		btrfs_debug(fs_info, "pending commit done");
	prev &= ~bit;

	if (prev)
		btrfs_warn(fs_info,
			"unknown pending changes left 0x%lx, ignoring", prev);
}