aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs/file.c
blob: 3391f2adf0c869466d47124461e62c2ee3bf3989 (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
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
/*
 * 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/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
#include <linux/falloc.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/slab.h>
#include <linux/btrfs.h>
#include <linux/uio.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "tree-log.h"
#include "locking.h"
#include "volumes.h"
#include "qgroup.h"
#include "compression.h"

static struct kmem_cache *btrfs_inode_defrag_cachep;
/*
 * when auto defrag is enabled we
 * queue up these defrag structs to remember which
 * inodes need defragging passes
 */
struct inode_defrag {
	struct rb_node rb_node;
	/* objectid */
	u64 ino;
	/*
	 * transid where the defrag was added, we search for
	 * extents newer than this
	 */
	u64 transid;

	/* root objectid */
	u64 root;

	/* last offset we were able to defrag */
	u64 last_offset;

	/* if we've wrapped around back to zero once already */
	int cycled;
};

static int __compare_inode_defrag(struct inode_defrag *defrag1,
				  struct inode_defrag *defrag2)
{
	if (defrag1->root > defrag2->root)
		return 1;
	else if (defrag1->root < defrag2->root)
		return -1;
	else if (defrag1->ino > defrag2->ino)
		return 1;
	else if (defrag1->ino < defrag2->ino)
		return -1;
	else
		return 0;
}

/* pop a record for an inode into the defrag tree.  The lock
 * must be held already
 *
 * If you're inserting a record for an older transid than an
 * existing record, the transid already in the tree is lowered
 *
 * If an existing record is found the defrag item you
 * pass in is freed
 */
static int __btrfs_add_inode_defrag(struct inode *inode,
				    struct inode_defrag *defrag)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct inode_defrag *entry;
	struct rb_node **p;
	struct rb_node *parent = NULL;
	int ret;

	p = &root->fs_info->defrag_inodes.rb_node;
	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct inode_defrag, rb_node);

		ret = __compare_inode_defrag(defrag, entry);
		if (ret < 0)
			p = &parent->rb_left;
		else if (ret > 0)
			p = &parent->rb_right;
		else {
			/* if we're reinserting an entry for
			 * an old defrag run, make sure to
			 * lower the transid of our existing record
			 */
			if (defrag->transid < entry->transid)
				entry->transid = defrag->transid;
			if (defrag->last_offset > entry->last_offset)
				entry->last_offset = defrag->last_offset;
			return -EEXIST;
		}
	}
	set_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
	rb_link_node(&defrag->rb_node, parent, p);
	rb_insert_color(&defrag->rb_node, &root->fs_info->defrag_inodes);
	return 0;
}

static inline int __need_auto_defrag(struct btrfs_root *root)
{
	if (!btrfs_test_opt(root->fs_info, AUTO_DEFRAG))
		return 0;

	if (btrfs_fs_closing(root->fs_info))
		return 0;

	return 1;
}

/*
 * insert a defrag record for this inode if auto defrag is
 * enabled
 */
int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
			   struct inode *inode)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct inode_defrag *defrag;
	u64 transid;
	int ret;

	if (!__need_auto_defrag(root))
		return 0;

	if (test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags))
		return 0;

	if (trans)
		transid = trans->transid;
	else
		transid = BTRFS_I(inode)->root->last_trans;

	defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS);
	if (!defrag)
		return -ENOMEM;

	defrag->ino = btrfs_ino(inode);
	defrag->transid = transid;
	defrag->root = root->root_key.objectid;

	spin_lock(&root->fs_info->defrag_inodes_lock);
	if (!test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags)) {
		/*
		 * If we set IN_DEFRAG flag and evict the inode from memory,
		 * and then re-read this inode, this new inode doesn't have
		 * IN_DEFRAG flag. At the case, we may find the existed defrag.
		 */
		ret = __btrfs_add_inode_defrag(inode, defrag);
		if (ret)
			kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
	} else {
		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
	}
	spin_unlock(&root->fs_info->defrag_inodes_lock);
	return 0;
}

/*
 * Requeue the defrag object. If there is a defrag object that points to
 * the same inode in the tree, we will merge them together (by
 * __btrfs_add_inode_defrag()) and free the one that we want to requeue.
 */
static void btrfs_requeue_inode_defrag(struct inode *inode,
				       struct inode_defrag *defrag)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	int ret;

	if (!__need_auto_defrag(root))
		goto out;

	/*
	 * Here we don't check the IN_DEFRAG flag, because we need merge
	 * them together.
	 */
	spin_lock(&root->fs_info->defrag_inodes_lock);
	ret = __btrfs_add_inode_defrag(inode, defrag);
	spin_unlock(&root->fs_info->defrag_inodes_lock);
	if (ret)
		goto out;
	return;
out:
	kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
}

/*
 * pick the defragable inode that we want, if it doesn't exist, we will get
 * the next one.
 */
static struct inode_defrag *
btrfs_pick_defrag_inode(struct btrfs_fs_info *fs_info, u64 root, u64 ino)
{
	struct inode_defrag *entry = NULL;
	struct inode_defrag tmp;
	struct rb_node *p;
	struct rb_node *parent = NULL;
	int ret;

	tmp.ino = ino;
	tmp.root = root;

	spin_lock(&fs_info->defrag_inodes_lock);
	p = fs_info->defrag_inodes.rb_node;
	while (p) {
		parent = p;
		entry = rb_entry(parent, struct inode_defrag, rb_node);

		ret = __compare_inode_defrag(&tmp, entry);
		if (ret < 0)
			p = parent->rb_left;
		else if (ret > 0)
			p = parent->rb_right;
		else
			goto out;
	}

	if (parent && __compare_inode_defrag(&tmp, entry) > 0) {
		parent = rb_next(parent);
		if (parent)
			entry = rb_entry(parent, struct inode_defrag, rb_node);
		else
			entry = NULL;
	}
out:
	if (entry)
		rb_erase(parent, &fs_info->defrag_inodes);
	spin_unlock(&fs_info->defrag_inodes_lock);
	return entry;
}

void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info)
{
	struct inode_defrag *defrag;
	struct rb_node *node;

	spin_lock(&fs_info->defrag_inodes_lock);
	node = rb_first(&fs_info->defrag_inodes);
	while (node) {
		rb_erase(node, &fs_info->defrag_inodes);
		defrag = rb_entry(node, struct inode_defrag, rb_node);
		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);

		cond_resched_lock(&fs_info->defrag_inodes_lock);

		node = rb_first(&fs_info->defrag_inodes);
	}
	spin_unlock(&fs_info->defrag_inodes_lock);
}

#define BTRFS_DEFRAG_BATCH	1024

static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
				    struct inode_defrag *defrag)
{
	struct btrfs_root *inode_root;
	struct inode *inode;
	struct btrfs_key key;
	struct btrfs_ioctl_defrag_range_args range;
	int num_defrag;
	int index;
	int ret;

	/* get the inode */
	key.objectid = defrag->root;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;

	index = srcu_read_lock(&fs_info->subvol_srcu);

	inode_root = btrfs_read_fs_root_no_name(fs_info, &key);
	if (IS_ERR(inode_root)) {
		ret = PTR_ERR(inode_root);
		goto cleanup;
	}

	key.objectid = defrag->ino;
	key.type = BTRFS_INODE_ITEM_KEY;
	key.offset = 0;
	inode = btrfs_iget(fs_info->sb, &key, inode_root, NULL);
	if (IS_ERR(inode)) {
		ret = PTR_ERR(inode);
		goto cleanup;
	}
	srcu_read_unlock(&fs_info->subvol_srcu, index);

	/* do a chunk of defrag */
	clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
	memset(&range, 0, sizeof(range));
	range.len = (u64)-1;
	range.start = defrag->last_offset;

	sb_start_write(fs_info->sb);
	num_defrag = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
				       BTRFS_DEFRAG_BATCH);
	sb_end_write(fs_info->sb);
	/*
	 * if we filled the whole defrag batch, there
	 * must be more work to do.  Queue this defrag
	 * again
	 */
	if (num_defrag == BTRFS_DEFRAG_BATCH) {
		defrag->last_offset = range.start;
		btrfs_requeue_inode_defrag(inode, defrag);
	} else if (defrag->last_offset && !defrag->cycled) {
		/*
		 * we didn't fill our defrag batch, but
		 * we didn't start at zero.  Make sure we loop
		 * around to the start of the file.
		 */
		defrag->last_offset = 0;
		defrag->cycled = 1;
		btrfs_requeue_inode_defrag(inode, defrag);
	} else {
		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
	}

	iput(inode);
	return 0;
cleanup:
	srcu_read_unlock(&fs_info->subvol_srcu, index);
	kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
	return ret;
}

/*
 * run through the list of inodes in the FS that need
 * defragging
 */
int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
{
	struct inode_defrag *defrag;
	u64 first_ino = 0;
	u64 root_objectid = 0;

	atomic_inc(&fs_info->defrag_running);
	while (1) {
		/* Pause the auto defragger. */
		if (test_bit(BTRFS_FS_STATE_REMOUNTING,
			     &fs_info->fs_state))
			break;

		if (!__need_auto_defrag(fs_info->tree_root))
			break;

		/* find an inode to defrag */
		defrag = btrfs_pick_defrag_inode(fs_info, root_objectid,
						 first_ino);
		if (!defrag) {
			if (root_objectid || first_ino) {
				root_objectid = 0;
				first_ino = 0;
				continue;
			} else {
				break;
			}
		}

		first_ino = defrag->ino + 1;
		root_objectid = defrag->root;

		__btrfs_run_defrag_inode(fs_info, defrag);
	}
	atomic_dec(&fs_info->defrag_running);

	/*
	 * during unmount, we use the transaction_wait queue to
	 * wait for the defragger to stop
	 */
	wake_up(&fs_info->transaction_wait);
	return 0;
}

/* simple helper to fault in pages and copy.  This should go away
 * and be replaced with calls into generic code.
 */
static noinline int btrfs_copy_from_user(loff_t pos, size_t write_bytes,
					 struct page **prepared_pages,
					 struct iov_iter *i)
{
	size_t copied = 0;
	size_t total_copied = 0;
	int pg = 0;
	int offset = pos & (PAGE_SIZE - 1);

	while (write_bytes > 0) {
		size_t count = min_t(size_t,
				     PAGE_SIZE - offset, write_bytes);
		struct page *page = prepared_pages[pg];
		/*
		 * Copy data from userspace to the current page
		 */
		copied = iov_iter_copy_from_user_atomic(page, i, offset, count);

		/* Flush processor's dcache for this page */
		flush_dcache_page(page);

		/*
		 * if we get a partial write, we can end up with
		 * partially up to date pages.  These add
		 * a lot of complexity, so make sure they don't
		 * happen by forcing this copy to be retried.
		 *
		 * The rest of the btrfs_file_write code will fall
		 * back to page at a time copies after we return 0.
		 */
		if (!PageUptodate(page) && copied < count)
			copied = 0;

		iov_iter_advance(i, copied);
		write_bytes -= copied;
		total_copied += copied;

		/* Return to btrfs_file_write_iter to fault page */
		if (unlikely(copied == 0))
			break;

		if (copied < PAGE_SIZE - offset) {
			offset += copied;
		} else {
			pg++;
			offset = 0;
		}
	}
	return total_copied;
}

/*
 * unlocks pages after btrfs_file_write is done with them
 */
static void btrfs_drop_pages(struct page **pages, size_t num_pages)
{
	size_t i;
	for (i = 0; i < num_pages; i++) {
		/* page checked is some magic around finding pages that
		 * have been modified without going through btrfs_set_page_dirty
		 * clear it here. There should be no need to mark the pages
		 * accessed as prepare_pages should have marked them accessed
		 * in prepare_pages via find_or_create_page()
		 */
		ClearPageChecked(pages[i]);
		unlock_page(pages[i]);
		put_page(pages[i]);
	}
}

/*
 * after copy_from_user, pages need to be dirtied and we need to make
 * sure holes are created between the current EOF and the start of
 * any next extents (if required).
 *
 * this also makes the decision about creating an inline extent vs
 * doing real data extents, marking pages dirty and delalloc as required.
 */
int btrfs_dirty_pages(struct btrfs_root *root, struct inode *inode,
			     struct page **pages, size_t num_pages,
			     loff_t pos, size_t write_bytes,
			     struct extent_state **cached)
{
	int err = 0;
	int i;
	u64 num_bytes;
	u64 start_pos;
	u64 end_of_last_block;
	u64 end_pos = pos + write_bytes;
	loff_t isize = i_size_read(inode);

	start_pos = pos & ~((u64)root->sectorsize - 1);
	num_bytes = round_up(write_bytes + pos - start_pos, root->sectorsize);

	end_of_last_block = start_pos + num_bytes - 1;
	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
					cached);
	if (err)
		return err;

	for (i = 0; i < num_pages; i++) {
		struct page *p = pages[i];
		SetPageUptodate(p);
		ClearPageChecked(p);
		set_page_dirty(p);
	}

	/*
	 * we've only changed i_size in ram, and we haven't updated
	 * the disk i_size.  There is no need to log the inode
	 * at this time.
	 */
	if (end_pos > isize)
		i_size_write(inode, end_pos);
	return 0;
}

/*
 * this drops all the extents in the cache that intersect the range
 * [start, end].  Existing extents are split as required.
 */
void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
			     int skip_pinned)
{
	struct extent_map *em;
	struct extent_map *split = NULL;
	struct extent_map *split2 = NULL;
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	u64 len = end - start + 1;
	u64 gen;
	int ret;
	int testend = 1;
	unsigned long flags;
	int compressed = 0;
	bool modified;

	WARN_ON(end < start);
	if (end == (u64)-1) {
		len = (u64)-1;
		testend = 0;
	}
	while (1) {
		int no_splits = 0;

		modified = false;
		if (!split)
			split = alloc_extent_map();
		if (!split2)
			split2 = alloc_extent_map();
		if (!split || !split2)
			no_splits = 1;

		write_lock(&em_tree->lock);
		em = lookup_extent_mapping(em_tree, start, len);
		if (!em) {
			write_unlock(&em_tree->lock);
			break;
		}
		flags = em->flags;
		gen = em->generation;
		if (skip_pinned && test_bit(EXTENT_FLAG_PINNED, &em->flags)) {
			if (testend && em->start + em->len >= start + len) {
				free_extent_map(em);
				write_unlock(&em_tree->lock);
				break;
			}
			start = em->start + em->len;
			if (testend)
				len = start + len - (em->start + em->len);
			free_extent_map(em);
			write_unlock(&em_tree->lock);
			continue;
		}
		compressed = test_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
		clear_bit(EXTENT_FLAG_PINNED, &em->flags);
		clear_bit(EXTENT_FLAG_LOGGING, &flags);
		modified = !list_empty(&em->list);
		if (no_splits)
			goto next;

		if (em->start < start) {
			split->start = em->start;
			split->len = start - em->start;

			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
				split->orig_start = em->orig_start;
				split->block_start = em->block_start;

				if (compressed)
					split->block_len = em->block_len;
				else
					split->block_len = split->len;
				split->orig_block_len = max(split->block_len,
						em->orig_block_len);
				split->ram_bytes = em->ram_bytes;
			} else {
				split->orig_start = split->start;
				split->block_len = 0;
				split->block_start = em->block_start;
				split->orig_block_len = 0;
				split->ram_bytes = split->len;
			}

			split->generation = gen;
			split->bdev = em->bdev;
			split->flags = flags;
			split->compress_type = em->compress_type;
			replace_extent_mapping(em_tree, em, split, modified);
			free_extent_map(split);
			split = split2;
			split2 = NULL;
		}
		if (testend && em->start + em->len > start + len) {
			u64 diff = start + len - em->start;

			split->start = start + len;
			split->len = em->start + em->len - (start + len);
			split->bdev = em->bdev;
			split->flags = flags;
			split->compress_type = em->compress_type;
			split->generation = gen;

			if (em->block_start < EXTENT_MAP_LAST_BYTE) {
				split->orig_block_len = max(em->block_len,
						    em->orig_block_len);

				split->ram_bytes = em->ram_bytes;
				if (compressed) {
					split->block_len = em->block_len;
					split->block_start = em->block_start;
					split->orig_start = em->orig_start;
				} else {
					split->block_len = split->len;
					split->block_start = em->block_start
						+ diff;
					split->orig_start = em->orig_start;
				}
			} else {
				split->ram_bytes = split->len;
				split->orig_start = split->start;
				split->block_len = 0;
				split->block_start = em->block_start;
				split->orig_block_len = 0;
			}

			if (extent_map_in_tree(em)) {
				replace_extent_mapping(em_tree, em, split,
						       modified);
			} else {
				ret = add_extent_mapping(em_tree, split,
							 modified);
				ASSERT(ret == 0); /* Logic error */
			}
			free_extent_map(split);
			split = NULL;
		}
next:
		if (extent_map_in_tree(em))
			remove_extent_mapping(em_tree, em);
		write_unlock(&em_tree->lock);

		/* once for us */
		free_extent_map(em);
		/* once for the tree*/
		free_extent_map(em);
	}
	if (split)
		free_extent_map(split);
	if (split2)
		free_extent_map(split2);
}

/*
 * this is very complex, but the basic idea is to drop all extents
 * in the range start - end.  hint_block is filled in with a block number
 * that would be a good hint to the block allocator for this file.
 *
 * If an extent intersects the range but is not entirely inside the range
 * it is either truncated or split.  Anything entirely inside the range
 * is deleted from the tree.
 */
int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
			 struct btrfs_root *root, struct inode *inode,
			 struct btrfs_path *path, u64 start, u64 end,
			 u64 *drop_end, int drop_cache,
			 int replace_extent,
			 u32 extent_item_size,
			 int *key_inserted)
{
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;
	struct btrfs_key new_key;
	u64 ino = btrfs_ino(inode);
	u64 search_start = start;
	u64 disk_bytenr = 0;
	u64 num_bytes = 0;
	u64 extent_offset = 0;
	u64 extent_end = 0;
	int del_nr = 0;
	int del_slot = 0;
	int extent_type;
	int recow;
	int ret;
	int modify_tree = -1;
	int update_refs;
	int found = 0;
	int leafs_visited = 0;

	if (drop_cache)
		btrfs_drop_extent_cache(inode, start, end - 1, 0);

	if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
		modify_tree = 0;

	update_refs = (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
		       root == root->fs_info->tree_root);
	while (1) {
		recow = 0;
		ret = btrfs_lookup_file_extent(trans, root, path, ino,
					       search_start, modify_tree);
		if (ret < 0)
			break;
		if (ret > 0 && path->slots[0] > 0 && search_start == start) {
			leaf = path->nodes[0];
			btrfs_item_key_to_cpu(leaf, &key, path->slots[0] - 1);
			if (key.objectid == ino &&
			    key.type == BTRFS_EXTENT_DATA_KEY)
				path->slots[0]--;
		}
		ret = 0;
		leafs_visited++;
next_slot:
		leaf = path->nodes[0];
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			BUG_ON(del_nr > 0);
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				break;
			if (ret > 0) {
				ret = 0;
				break;
			}
			leafs_visited++;
			leaf = path->nodes[0];
			recow = 1;
		}

		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);

		if (key.objectid > ino)
			break;
		if (WARN_ON_ONCE(key.objectid < ino) ||
		    key.type < BTRFS_EXTENT_DATA_KEY) {
			ASSERT(del_nr == 0);
			path->slots[0]++;
			goto next_slot;
		}
		if (key.type > BTRFS_EXTENT_DATA_KEY || key.offset >= end)
			break;

		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);
		extent_type = btrfs_file_extent_type(leaf, fi);

		if (extent_type == BTRFS_FILE_EXTENT_REG ||
		    extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
			disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
			num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
			extent_offset = btrfs_file_extent_offset(leaf, fi);
			extent_end = key.offset +
				btrfs_file_extent_num_bytes(leaf, fi);
		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
			extent_end = key.offset +
				btrfs_file_extent_inline_len(leaf,
						     path->slots[0], fi);
		} else {
			/* can't happen */
			BUG();
		}

		/*
		 * Don't skip extent items representing 0 byte lengths. They
		 * used to be created (bug) if while punching holes we hit
		 * -ENOSPC condition. So if we find one here, just ensure we
		 * delete it, otherwise we would insert a new file extent item
		 * with the same key (offset) as that 0 bytes length file
		 * extent item in the call to setup_items_for_insert() later
		 * in this function.
		 */
		if (extent_end == key.offset && extent_end >= search_start)
			goto delete_extent_item;

		if (extent_end <= search_start) {
			path->slots[0]++;
			goto next_slot;
		}

		found = 1;
		search_start = max(key.offset, start);
		if (recow || !modify_tree) {
			modify_tree = -1;
			btrfs_release_path(path);
			continue;
		}

		/*
		 *     | - range to drop - |
		 *  | -------- extent -------- |
		 */
		if (start > key.offset && end < extent_end) {
			BUG_ON(del_nr > 0);
			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
				ret = -EOPNOTSUPP;
				break;
			}

			memcpy(&new_key, &key, sizeof(new_key));
			new_key.offset = start;
			ret = btrfs_duplicate_item(trans, root, path,
						   &new_key);
			if (ret == -EAGAIN) {
				btrfs_release_path(path);
				continue;
			}
			if (ret < 0)
				break;

			leaf = path->nodes[0];
			fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							start - key.offset);

			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);

			extent_offset += start - key.offset;
			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							extent_end - start);
			btrfs_mark_buffer_dirty(leaf);

			if (update_refs && disk_bytenr > 0) {
				ret = btrfs_inc_extent_ref(trans, root,
						disk_bytenr, num_bytes, 0,
						root->root_key.objectid,
						new_key.objectid,
						start - extent_offset);
				BUG_ON(ret); /* -ENOMEM */
			}
			key.offset = start;
		}
		/*
		 *  | ---- range to drop ----- |
		 *      | -------- extent -------- |
		 */
		if (start <= key.offset && end < extent_end) {
			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
				ret = -EOPNOTSUPP;
				break;
			}

			memcpy(&new_key, &key, sizeof(new_key));
			new_key.offset = end;
			btrfs_set_item_key_safe(root->fs_info, path, &new_key);

			extent_offset += end - key.offset;
			btrfs_set_file_extent_offset(leaf, fi, extent_offset);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							extent_end - end);
			btrfs_mark_buffer_dirty(leaf);
			if (update_refs && disk_bytenr > 0)
				inode_sub_bytes(inode, end - key.offset);
			break;
		}

		search_start = extent_end;
		/*
		 *       | ---- range to drop ----- |
		 *  | -------- extent -------- |
		 */
		if (start > key.offset && end >= extent_end) {
			BUG_ON(del_nr > 0);
			if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
				ret = -EOPNOTSUPP;
				break;
			}

			btrfs_set_file_extent_num_bytes(leaf, fi,
							start - key.offset);
			btrfs_mark_buffer_dirty(leaf);
			if (update_refs && disk_bytenr > 0)
				inode_sub_bytes(inode, extent_end - start);
			if (end == extent_end)
				break;

			path->slots[0]++;
			goto next_slot;
		}

		/*
		 *  | ---- range to drop ----- |
		 *    | ------ extent ------ |
		 */
		if (start <= key.offset && end >= extent_end) {
delete_extent_item:
			if (del_nr == 0) {
				del_slot = path->slots[0];
				del_nr = 1;
			} else {
				BUG_ON(del_slot + del_nr != path->slots[0]);
				del_nr++;
			}

			if (update_refs &&
			    extent_type == BTRFS_FILE_EXTENT_INLINE) {
				inode_sub_bytes(inode,
						extent_end - key.offset);
				extent_end = ALIGN(extent_end,
						   root->sectorsize);
			} else if (update_refs && disk_bytenr > 0) {
				ret = btrfs_free_extent(trans, root,
						disk_bytenr, num_bytes, 0,
						root->root_key.objectid,
						key.objectid, key.offset -
						extent_offset);
				BUG_ON(ret); /* -ENOMEM */
				inode_sub_bytes(inode,
						extent_end - key.offset);
			}

			if (end == extent_end)
				break;

			if (path->slots[0] + 1 < btrfs_header_nritems(leaf)) {
				path->slots[0]++;
				goto next_slot;
			}

			ret = btrfs_del_items(trans, root, path, del_slot,
					      del_nr);
			if (ret) {
				btrfs_abort_transaction(trans, ret);
				break;
			}

			del_nr = 0;
			del_slot = 0;

			btrfs_release_path(path);
			continue;
		}

		BUG_ON(1);
	}

	if (!ret && del_nr > 0) {
		/*
		 * Set path->slots[0] to first slot, so that after the delete
		 * if items are move off from our leaf to its immediate left or
		 * right neighbor leafs, we end up with a correct and adjusted
		 * path->slots[0] for our insertion (if replace_extent != 0).
		 */
		path->slots[0] = del_slot;
		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
		if (ret)
			btrfs_abort_transaction(trans, ret);
	}

	leaf = path->nodes[0];
	/*
	 * If btrfs_del_items() was called, it might have deleted a leaf, in
	 * which case it unlocked our path, so check path->locks[0] matches a
	 * write lock.
	 */
	if (!ret && replace_extent && leafs_visited == 1 &&
	    (path->locks[0] == BTRFS_WRITE_LOCK_BLOCKING ||
	     path->locks[0] == BTRFS_WRITE_LOCK) &&
	    btrfs_leaf_free_space(root, leaf) >=
	    sizeof(struct btrfs_item) + extent_item_size) {

		key.objectid = ino;
		key.type = BTRFS_EXTENT_DATA_KEY;
		key.offset = start;
		if (!del_nr && path->slots[0] < btrfs_header_nritems(leaf)) {
			struct btrfs_key slot_key;

			btrfs_item_key_to_cpu(leaf, &slot_key, path->slots[0]);
			if (btrfs_comp_cpu_keys(&key, &slot_key) > 0)
				path->slots[0]++;
		}
		setup_items_for_insert(root, path, &key,
				       &extent_item_size,
				       extent_item_size,
				       sizeof(struct btrfs_item) +
				       extent_item_size, 1);
		*key_inserted = 1;
	}

	if (!replace_extent || !(*key_inserted))
		btrfs_release_path(path);
	if (drop_end)
		*drop_end = found ? min(end, extent_end) : end;
	return ret;
}

int btrfs_drop_extents(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root, struct inode *inode, u64 start,
		       u64 end, int drop_cache)
{
	struct btrfs_path *path;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	ret = __btrfs_drop_extents(trans, root, inode, path, start, end, NULL,
				   drop_cache, 0, 0, NULL);
	btrfs_free_path(path);
	return ret;
}

static int extent_mergeable(struct extent_buffer *leaf, int slot,
			    u64 objectid, u64 bytenr, u64 orig_offset,
			    u64 *start, u64 *end)
{
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;
	u64 extent_end;

	if (slot < 0 || slot >= btrfs_header_nritems(leaf))
		return 0;

	btrfs_item_key_to_cpu(leaf, &key, slot);
	if (key.objectid != objectid || key.type != BTRFS_EXTENT_DATA_KEY)
		return 0;

	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
	if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG ||
	    btrfs_file_extent_disk_bytenr(leaf, fi) != bytenr ||
	    btrfs_file_extent_offset(leaf, fi) != key.offset - orig_offset ||
	    btrfs_file_extent_compression(leaf, fi) ||
	    btrfs_file_extent_encryption(leaf, fi) ||
	    btrfs_file_extent_other_encoding(leaf, fi))
		return 0;

	extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
	if ((*start && *start != key.offset) || (*end && *end != extent_end))
		return 0;

	*start = key.offset;
	*end = extent_end;
	return 1;
}

/*
 * Mark extent in the range start - end as written.
 *
 * This changes extent type from 'pre-allocated' to 'regular'. If only
 * part of extent is marked as written, the extent will be split into
 * two or three.
 */
int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
			      struct inode *inode, u64 start, u64 end)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_buffer *leaf;
	struct btrfs_path *path;
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;
	struct btrfs_key new_key;
	u64 bytenr;
	u64 num_bytes;
	u64 extent_end;
	u64 orig_offset;
	u64 other_start;
	u64 other_end;
	u64 split;
	int del_nr = 0;
	int del_slot = 0;
	int recow;
	int ret;
	u64 ino = btrfs_ino(inode);

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
again:
	recow = 0;
	split = start;
	key.objectid = ino;
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = split;

	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
	if (ret < 0)
		goto out;
	if (ret > 0 && path->slots[0] > 0)
		path->slots[0]--;

	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
	BUG_ON(key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY);
	fi = btrfs_item_ptr(leaf, path->slots[0],
			    struct btrfs_file_extent_item);
	BUG_ON(btrfs_file_extent_type(leaf, fi) !=
	       BTRFS_FILE_EXTENT_PREALLOC);
	extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
	BUG_ON(key.offset > start || extent_end < end);

	bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
	num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
	orig_offset = key.offset - btrfs_file_extent_offset(leaf, fi);
	memcpy(&new_key, &key, sizeof(new_key));

	if (start == key.offset && end < extent_end) {
		other_start = 0;
		other_end = start;
		if (extent_mergeable(leaf, path->slots[0] - 1,
				     ino, bytenr, orig_offset,
				     &other_start, &other_end)) {
			new_key.offset = end;
			btrfs_set_item_key_safe(root->fs_info, path, &new_key);
			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_generation(leaf, fi,
							 trans->transid);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							extent_end - end);
			btrfs_set_file_extent_offset(leaf, fi,
						     end - orig_offset);
			fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_generation(leaf, fi,
							 trans->transid);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							end - other_start);
			btrfs_mark_buffer_dirty(leaf);
			goto out;
		}
	}

	if (start > key.offset && end == extent_end) {
		other_start = end;
		other_end = 0;
		if (extent_mergeable(leaf, path->slots[0] + 1,
				     ino, bytenr, orig_offset,
				     &other_start, &other_end)) {
			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							start - key.offset);
			btrfs_set_file_extent_generation(leaf, fi,
							 trans->transid);
			path->slots[0]++;
			new_key.offset = start;
			btrfs_set_item_key_safe(root->fs_info, path, &new_key);

			fi = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_file_extent_item);
			btrfs_set_file_extent_generation(leaf, fi,
							 trans->transid);
			btrfs_set_file_extent_num_bytes(leaf, fi,
							other_end - start);
			btrfs_set_file_extent_offset(leaf, fi,
						     start - orig_offset);
			btrfs_mark_buffer_dirty(leaf);
			goto out;
		}
	}

	while (start > key.offset || end < extent_end) {
		if (key.offset == start)
			split = end;

		new_key.offset = split;
		ret = btrfs_duplicate_item(trans, root, path, &new_key);
		if (ret == -EAGAIN) {
			btrfs_release_path(path);
			goto again;
		}
		if (ret < 0) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}

		leaf = path->nodes[0];
		fi = btrfs_item_ptr(leaf, path->slots[0] - 1,
				    struct btrfs_file_extent_item);
		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
		btrfs_set_file_extent_num_bytes(leaf, fi,
						split - key.offset);

		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);

		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
		btrfs_set_file_extent_offset(leaf, fi, split - orig_offset);
		btrfs_set_file_extent_num_bytes(leaf, fi,
						extent_end - split);
		btrfs_mark_buffer_dirty(leaf);

		ret = btrfs_inc_extent_ref(trans, root, bytenr, num_bytes, 0,
					   root->root_key.objectid,
					   ino, orig_offset);
		BUG_ON(ret); /* -ENOMEM */

		if (split == start) {
			key.offset = start;
		} else {
			BUG_ON(start != key.offset);
			path->slots[0]--;
			extent_end = end;
		}
		recow = 1;
	}

	other_start = end;
	other_end = 0;
	if (extent_mergeable(leaf, path->slots[0] + 1,
			     ino, bytenr, orig_offset,
			     &other_start, &other_end)) {
		if (recow) {
			btrfs_release_path(path);
			goto again;
		}
		extent_end = other_end;
		del_slot = path->slots[0] + 1;
		del_nr++;
		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
					0, root->root_key.objectid,
					ino, orig_offset);
		BUG_ON(ret); /* -ENOMEM */
	}
	other_start = 0;
	other_end = start;
	if (extent_mergeable(leaf, path->slots[0] - 1,
			     ino, bytenr, orig_offset,
			     &other_start, &other_end)) {
		if (recow) {
			btrfs_release_path(path);
			goto again;
		}
		key.offset = other_start;
		del_slot = path->slots[0];
		del_nr++;
		ret = btrfs_free_extent(trans, root, bytenr, num_bytes,
					0, root->root_key.objectid,
					ino, orig_offset);
		BUG_ON(ret); /* -ENOMEM */
	}
	if (del_nr == 0) {
		fi = btrfs_item_ptr(leaf, path->slots[0],
			   struct btrfs_file_extent_item);
		btrfs_set_file_extent_type(leaf, fi,
					   BTRFS_FILE_EXTENT_REG);
		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
		btrfs_mark_buffer_dirty(leaf);
	} else {
		fi = btrfs_item_ptr(leaf, del_slot - 1,
			   struct btrfs_file_extent_item);
		btrfs_set_file_extent_type(leaf, fi,
					   BTRFS_FILE_EXTENT_REG);
		btrfs_set_file_extent_generation(leaf, fi, trans->transid);
		btrfs_set_file_extent_num_bytes(leaf, fi,
						extent_end - key.offset);
		btrfs_mark_buffer_dirty(leaf);

		ret = btrfs_del_items(trans, root, path, del_slot, del_nr);
		if (ret < 0) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
	}
out:
	btrfs_free_path(path);
	return 0;
}

/*
 * on error we return an unlocked page and the error value
 * on success we return a locked page and 0
 */
static int prepare_uptodate_page(struct inode *inode,
				 struct page *page, u64 pos,
				 bool force_uptodate)
{
	int ret = 0;

	if (((pos & (PAGE_SIZE - 1)) || force_uptodate) &&
	    !PageUptodate(page)) {
		ret = btrfs_readpage(NULL, page);
		if (ret)
			return ret;
		lock_page(page);
		if (!PageUptodate(page)) {
			unlock_page(page);
			return -EIO;
		}
		if (page->mapping != inode->i_mapping) {
			unlock_page(page);
			return -EAGAIN;
		}
	}
	return 0;
}

/*
 * this just gets pages into the page cache and locks them down.
 */
static noinline int prepare_pages(struct inode *inode, struct page **pages,
				  size_t num_pages, loff_t pos,
				  size_t write_bytes, bool force_uptodate)
{
	int i;
	unsigned long index = pos >> PAGE_SHIFT;
	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
	int err = 0;
	int faili;

	for (i = 0; i < num_pages; i++) {
again:
		pages[i] = find_or_create_page(inode->i_mapping, index + i,
					       mask | __GFP_WRITE);
		if (!pages[i]) {
			faili = i - 1;
			err = -ENOMEM;
			goto fail;
		}

		if (i == 0)
			err = prepare_uptodate_page(inode, pages[i], pos,
						    force_uptodate);
		if (!err && i == num_pages - 1)
			err = prepare_uptodate_page(inode, pages[i],
						    pos + write_bytes, false);
		if (err) {
			put_page(pages[i]);
			if (err == -EAGAIN) {
				err = 0;
				goto again;
			}
			faili = i - 1;
			goto fail;
		}
		wait_on_page_writeback(pages[i]);
	}

	return 0;
fail:
	while (faili >= 0) {
		unlock_page(pages[faili]);
		put_page(pages[faili]);
		faili--;
	}
	return err;

}

/*
 * This function locks the extent and properly waits for data=ordered extents
 * to finish before allowing the pages to be modified if need.
 *
 * The return value:
 * 1 - the extent is locked
 * 0 - the extent is not locked, and everything is OK
 * -EAGAIN - need re-prepare the pages
 * the other < 0 number - Something wrong happens
 */
static noinline int
lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
				size_t num_pages, loff_t pos,
				size_t write_bytes,
				u64 *lockstart, u64 *lockend,
				struct extent_state **cached_state)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	u64 start_pos;
	u64 last_pos;
	int i;
	int ret = 0;

	start_pos = round_down(pos, root->sectorsize);
	last_pos = start_pos
		+ round_up(pos + write_bytes - start_pos, root->sectorsize) - 1;

	if (start_pos < inode->i_size) {
		struct btrfs_ordered_extent *ordered;
		lock_extent_bits(&BTRFS_I(inode)->io_tree,
				 start_pos, last_pos, cached_state);
		ordered = btrfs_lookup_ordered_range(inode, start_pos,
						     last_pos - start_pos + 1);
		if (ordered &&
		    ordered->file_offset + ordered->len > start_pos &&
		    ordered->file_offset <= last_pos) {
			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
					     start_pos, last_pos,
					     cached_state, GFP_NOFS);
			for (i = 0; i < num_pages; i++) {
				unlock_page(pages[i]);
				put_page(pages[i]);
			}
			btrfs_start_ordered_extent(inode, ordered, 1);
			btrfs_put_ordered_extent(ordered);
			return -EAGAIN;
		}
		if (ordered)
			btrfs_put_ordered_extent(ordered);

		clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos,
				  last_pos, EXTENT_DIRTY | EXTENT_DELALLOC |
				  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
				  0, 0, cached_state, GFP_NOFS);
		*lockstart = start_pos;
		*lockend = last_pos;
		ret = 1;
	}

	for (i = 0; i < num_pages; i++) {
		if (clear_page_dirty_for_io(pages[i]))
			account_page_redirty(pages[i]);
		set_page_extent_mapped(pages[i]);
		WARN_ON(!PageLocked(pages[i]));
	}

	return ret;
}

static noinline int check_can_nocow(struct inode *inode, loff_t pos,
				    size_t *write_bytes)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_ordered_extent *ordered;
	u64 lockstart, lockend;
	u64 num_bytes;
	int ret;

	ret = btrfs_start_write_no_snapshoting(root);
	if (!ret)
		return -ENOSPC;

	lockstart = round_down(pos, root->sectorsize);
	lockend = round_up(pos + *write_bytes, root->sectorsize) - 1;

	while (1) {
		lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
		ordered = btrfs_lookup_ordered_range(inode, lockstart,
						     lockend - lockstart + 1);
		if (!ordered) {
			break;
		}
		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
		btrfs_start_ordered_extent(inode, ordered, 1);
		btrfs_put_ordered_extent(ordered);
	}

	num_bytes = lockend - lockstart + 1;
	ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
	if (ret <= 0) {
		ret = 0;
		btrfs_end_write_no_snapshoting(root);
	} else {
		*write_bytes = min_t(size_t, *write_bytes ,
				     num_bytes - pos + lockstart);
	}

	unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);

	return ret;
}

static noinline ssize_t __btrfs_buffered_write(struct file *file,
					       struct iov_iter *i,
					       loff_t pos)
{
	struct inode *inode = file_inode(file);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct page **pages = NULL;
	struct extent_state *cached_state = NULL;
	u64 release_bytes = 0;
	u64 lockstart;
	u64 lockend;
	size_t num_written = 0;
	int nrptrs;
	int ret = 0;
	bool only_release_metadata = false;
	bool force_page_uptodate = false;
	bool need_unlock;

	nrptrs = min(DIV_ROUND_UP(iov_iter_count(i), PAGE_SIZE),
			PAGE_SIZE / (sizeof(struct page *)));
	nrptrs = min(nrptrs, current->nr_dirtied_pause - current->nr_dirtied);
	nrptrs = max(nrptrs, 8);
	pages = kmalloc_array(nrptrs, sizeof(struct page *), GFP_KERNEL);
	if (!pages)
		return -ENOMEM;

	while (iov_iter_count(i) > 0) {
		size_t offset = pos & (PAGE_SIZE - 1);
		size_t sector_offset;
		size_t write_bytes = min(iov_iter_count(i),
					 nrptrs * (size_t)PAGE_SIZE -
					 offset);
		size_t num_pages = DIV_ROUND_UP(write_bytes + offset,
						PAGE_SIZE);
		size_t reserve_bytes;
		size_t dirty_pages;
		size_t copied;
		size_t dirty_sectors;
		size_t num_sectors;

		WARN_ON(num_pages > nrptrs);

		/*
		 * Fault pages before locking them in prepare_pages
		 * to avoid recursive lock
		 */
		if (unlikely(iov_iter_fault_in_readable(i, write_bytes))) {
			ret = -EFAULT;
			break;
		}

		sector_offset = pos & (root->sectorsize - 1);
		reserve_bytes = round_up(write_bytes + sector_offset,
				root->sectorsize);

		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
		if (ret < 0) {
			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
						      BTRFS_INODE_PREALLOC)) &&
			    check_can_nocow(inode, pos, &write_bytes) > 0) {
				/*
				 * For nodata cow case, no need to reserve
				 * data space.
				 */
				only_release_metadata = true;
				/*
				 * our prealloc extent may be smaller than
				 * write_bytes, so scale down.
				 */
				num_pages = DIV_ROUND_UP(write_bytes + offset,
							 PAGE_SIZE);
				reserve_bytes = round_up(write_bytes +
							 sector_offset,
							 root->sectorsize);
			} else {
				break;
			}
		}

		ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
		if (ret) {
			if (!only_release_metadata)
				btrfs_free_reserved_data_space(inode, pos,
							       write_bytes);
			else
				btrfs_end_write_no_snapshoting(root);
			break;
		}

		release_bytes = reserve_bytes;
		need_unlock = false;
again:
		/*
		 * This is going to setup the pages array with the number of
		 * pages we want, so we don't really need to worry about the
		 * contents of pages from loop to loop
		 */
		ret = prepare_pages(inode, pages, num_pages,
				    pos, write_bytes,
				    force_page_uptodate);
		if (ret)
			break;

		ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
						pos, write_bytes, &lockstart,
						&lockend, &cached_state);
		if (ret < 0) {
			if (ret == -EAGAIN)
				goto again;
			break;
		} else if (ret > 0) {
			need_unlock = true;
			ret = 0;
		}

		copied = btrfs_copy_from_user(pos, write_bytes, pages, i);

		num_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
						reserve_bytes);
		dirty_sectors = round_up(copied + sector_offset,
					root->sectorsize);
		dirty_sectors = BTRFS_BYTES_TO_BLKS(root->fs_info,
						dirty_sectors);

		/*
		 * if we have trouble faulting in the pages, fall
		 * back to one page at a time
		 */
		if (copied < write_bytes)
			nrptrs = 1;

		if (copied == 0) {
			force_page_uptodate = true;
			dirty_sectors = 0;
			dirty_pages = 0;
		} else {
			force_page_uptodate = false;
			dirty_pages = DIV_ROUND_UP(copied + offset,
						   PAGE_SIZE);
		}

		/*
		 * If we had a short copy we need to release the excess delaloc
		 * bytes we reserved.  We need to increment outstanding_extents
		 * because btrfs_delalloc_release_space and
		 * btrfs_delalloc_release_metadata will decrement it, but
		 * we still have an outstanding extent for the chunk we actually
		 * managed to copy.
		 */
		if (num_sectors > dirty_sectors) {

			/* release everything except the sectors we dirtied */
			release_bytes -= dirty_sectors <<
				root->fs_info->sb->s_blocksize_bits;

			if (copied > 0) {
				spin_lock(&BTRFS_I(inode)->lock);
				BTRFS_I(inode)->outstanding_extents++;
				spin_unlock(&BTRFS_I(inode)->lock);
			}
			if (only_release_metadata) {
				btrfs_delalloc_release_metadata(inode,
								release_bytes);
			} else {
				u64 __pos;

				__pos = round_down(pos, root->sectorsize) +
					(dirty_pages << PAGE_SHIFT);
				btrfs_delalloc_release_space(inode, __pos,
							     release_bytes);
			}
		}

		release_bytes = round_up(copied + sector_offset,
					root->sectorsize);

		if (copied > 0)
			ret = btrfs_dirty_pages(root, inode, pages,
						dirty_pages, pos, copied,
						NULL);
		if (need_unlock)
			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
					     lockstart, lockend, &cached_state,
					     GFP_NOFS);
		if (ret) {
			btrfs_drop_pages(pages, num_pages);
			break;
		}

		release_bytes = 0;
		if (only_release_metadata)
			btrfs_end_write_no_snapshoting(root);

		if (only_release_metadata && copied > 0) {
			lockstart = round_down(pos, root->sectorsize);
			lockend = round_up(pos + copied, root->sectorsize) - 1;

			set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart,
				       lockend, EXTENT_NORESERVE, NULL,
				       NULL, GFP_NOFS);
			only_release_metadata = false;
		}

		btrfs_drop_pages(pages, num_pages);

		cond_resched();

		balance_dirty_pages_ratelimited(inode->i_mapping);
		if (dirty_pages < (root->nodesize >> PAGE_SHIFT) + 1)
			btrfs_btree_balance_dirty(root);

		pos += copied;
		num_written += copied;
	}

	kfree(pages);

	if (release_bytes) {
		if (only_release_metadata) {
			btrfs_end_write_no_snapshoting(root);
			btrfs_delalloc_release_metadata(inode, release_bytes);
		} else {
			btrfs_delalloc_release_space(inode,
						round_down(pos, root->sectorsize),
						release_bytes);
		}
	}

	return num_written ? num_written : ret;
}

static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	loff_t pos = iocb->ki_pos;
	ssize_t written;
	ssize_t written_buffered;
	loff_t endbyte;
	int err;

	written = generic_file_direct_write(iocb, from);

	if (written < 0 || !iov_iter_count(from))
		return written;

	pos += written;
	written_buffered = __btrfs_buffered_write(file, from, pos);
	if (written_buffered < 0) {
		err = written_buffered;
		goto out;
	}
	/*
	 * Ensure all data is persisted. We want the next direct IO read to be
	 * able to read what was just written.
	 */
	endbyte = pos + written_buffered - 1;
	err = btrfs_fdatawrite_range(inode, pos, endbyte);
	if (err)
		goto out;
	err = filemap_fdatawait_range(inode->i_mapping, pos, endbyte);
	if (err)
		goto out;
	written += written_buffered;
	iocb->ki_pos = pos + written_buffered;
	invalidate_mapping_pages(file->f_mapping, pos >> PAGE_SHIFT,
				 endbyte >> PAGE_SHIFT);
out:
	return written ? written : err;
}

static void update_time_for_write(struct inode *inode)
{
	struct timespec now;

	if (IS_NOCMTIME(inode))
		return;

	now = current_fs_time(inode->i_sb);
	if (!timespec_equal(&inode->i_mtime, &now))
		inode->i_mtime = now;

	if (!timespec_equal(&inode->i_ctime, &now))
		inode->i_ctime = now;

	if (IS_I_VERSION(inode))
		inode_inc_iversion(inode);
}

static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
				    struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	u64 start_pos;
	u64 end_pos;
	ssize_t num_written = 0;
	bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
	ssize_t err;
	loff_t pos;
	size_t count;
	loff_t oldsize;
	int clean_page = 0;

	inode_lock(inode);
	err = generic_write_checks(iocb, from);
	if (err <= 0) {
		inode_unlock(inode);
		return err;
	}

	current->backing_dev_info = inode_to_bdi(inode);
	err = file_remove_privs(file);
	if (err) {
		inode_unlock(inode);
		goto out;
	}

	/*
	 * If BTRFS flips readonly due to some impossible error
	 * (fs_info->fs_state now has BTRFS_SUPER_FLAG_ERROR),
	 * although we have opened a file as writable, we have
	 * to stop this write operation to ensure FS consistency.
	 */
	if (test_bit(BTRFS_FS_STATE_ERROR, &root->fs_info->fs_state)) {
		inode_unlock(inode);
		err = -EROFS;
		goto out;
	}

	/*
	 * We reserve space for updating the inode when we reserve space for the
	 * extent we are going to write, so we will enospc out there.  We don't
	 * need to start yet another transaction to update the inode as we will
	 * update the inode when we finish writing whatever data we write.
	 */
	update_time_for_write(inode);

	pos = iocb->ki_pos;
	count = iov_iter_count(from);
	start_pos = round_down(pos, root->sectorsize);
	oldsize = i_size_read(inode);
	if (start_pos > oldsize) {
		/* Expand hole size to cover write data, preventing empty gap */
		end_pos = round_up(pos + count, root->sectorsize);
		err = btrfs_cont_expand(inode, oldsize, end_pos);
		if (err) {
			inode_unlock(inode);
			goto out;
		}
		if (start_pos > round_up(oldsize, root->sectorsize))
			clean_page = 1;
	}

	if (sync)
		atomic_inc(&BTRFS_I(inode)->sync_writers);

	if (iocb->ki_flags & IOCB_DIRECT) {
		num_written = __btrfs_direct_write(iocb, from);
	} else {
		num_written = __btrfs_buffered_write(file, from, pos);
		if (num_written > 0)
			iocb->ki_pos = pos + num_written;
		if (clean_page)
			pagecache_isize_extended(inode, oldsize,
						i_size_read(inode));
	}

	inode_unlock(inode);

	/*
	 * We also have to set last_sub_trans to the current log transid,
	 * otherwise subsequent syncs to a file that's been synced in this
	 * transaction will appear to have already occurred.
	 */
	spin_lock(&BTRFS_I(inode)->lock);
	BTRFS_I(inode)->last_sub_trans = root->log_transid;
	spin_unlock(&BTRFS_I(inode)->lock);
	if (num_written > 0)
		num_written = generic_write_sync(iocb, num_written);

	if (sync)
		atomic_dec(&BTRFS_I(inode)->sync_writers);
out:
	current->backing_dev_info = NULL;
	return num_written ? num_written : err;
}

int btrfs_release_file(struct inode *inode, struct file *filp)
{
	if (filp->private_data)
		btrfs_ioctl_trans_end(filp);
	/*
	 * ordered_data_close is set by settattr when we are about to truncate
	 * a file from a non-zero size to a zero size.  This tries to
	 * flush down new bytes that may have been written if the
	 * application were using truncate to replace a file in place.
	 */
	if (test_and_clear_bit(BTRFS_INODE_ORDERED_DATA_CLOSE,
			       &BTRFS_I(inode)->runtime_flags))
			filemap_flush(inode->i_mapping);
	return 0;
}

static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
{
	int ret;

	atomic_inc(&BTRFS_I(inode)->sync_writers);
	ret = btrfs_fdatawrite_range(inode, start, end);
	atomic_dec(&BTRFS_I(inode)->sync_writers);

	return ret;
}

/*
 * fsync call for both files and directories.  This logs the inode into
 * the tree log instead of forcing full commits whenever possible.
 *
 * It needs to call filemap_fdatawait so that all ordered extent updates are
 * in the metadata btree are up to date for copying to the log.
 *
 * It drops the inode mutex before doing the tree log commit.  This is an
 * important optimization for directories because holding the mutex prevents
 * new operations on the dir while we write to disk.
 */
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
	struct dentry *dentry = file_dentry(file);
	struct inode *inode = d_inode(dentry);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
	struct btrfs_log_ctx ctx;
	int ret = 0;
	bool full_sync = 0;
	u64 len;

	/*
	 * The range length can be represented by u64, we have to do the typecasts
	 * to avoid signed overflow if it's [0, LLONG_MAX] eg. from fsync()
	 */
	len = (u64)end - (u64)start + 1;
	trace_btrfs_sync_file(file, datasync);

	/*
	 * We write the dirty pages in the range and wait until they complete
	 * out of the ->i_mutex. If so, we can flush the dirty pages by
	 * multi-task, and make the performance up.  See
	 * btrfs_wait_ordered_range for an explanation of the ASYNC check.
	 */
	ret = start_ordered_ops(inode, start, end);
	if (ret)
		return ret;

	inode_lock(inode);
	atomic_inc(&root->log_batch);
	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
			     &BTRFS_I(inode)->runtime_flags);
	/*
	 * We might have have had more pages made dirty after calling
	 * start_ordered_ops and before acquiring the inode's i_mutex.
	 */
	if (full_sync) {
		/*
		 * For a full sync, we need to make sure any ordered operations
		 * start and finish before we start logging the inode, so that
		 * all extents are persisted and the respective file extent
		 * items are in the fs/subvol btree.
		 */
		ret = btrfs_wait_ordered_range(inode, start, len);
	} else {
		/*
		 * Start any new ordered operations before starting to log the
		 * inode. We will wait for them to finish in btrfs_sync_log().
		 *
		 * Right before acquiring the inode's mutex, we might have new
		 * writes dirtying pages, which won't immediately start the
		 * respective ordered operations - that is done through the
		 * fill_delalloc callbacks invoked from the writepage and
		 * writepages address space operations. So make sure we start
		 * all ordered operations before starting to log our inode. Not
		 * doing this means that while logging the inode, writeback
		 * could start and invoke writepage/writepages, which would call
		 * the fill_delalloc callbacks (cow_file_range,
		 * submit_compressed_extents). These callbacks add first an
		 * extent map to the modified list of extents and then create
		 * the respective ordered operation, which means in
		 * tree-log.c:btrfs_log_inode() we might capture all existing
		 * ordered operations (with btrfs_get_logged_extents()) before
		 * the fill_delalloc callback adds its ordered operation, and by
		 * the time we visit the modified list of extent maps (with
		 * btrfs_log_changed_extents()), we see and process the extent
		 * map they created. We then use the extent map to construct a
		 * file extent item for logging without waiting for the
		 * respective ordered operation to finish - this file extent
		 * item points to a disk location that might not have yet been
		 * written to, containing random data - so after a crash a log
		 * replay will make our inode have file extent items that point
		 * to disk locations containing invalid data, as we returned
		 * success to userspace without waiting for the respective
		 * ordered operation to finish, because it wasn't captured by
		 * btrfs_get_logged_extents().
		 */
		ret = start_ordered_ops(inode, start, end);
	}
	if (ret) {
		inode_unlock(inode);
		goto out;
	}
	atomic_inc(&root->log_batch);

	/*
	 * If the last transaction that changed this file was before the current
	 * transaction and we have the full sync flag set in our inode, we can
	 * bail out now without any syncing.
	 *
	 * Note that we can't bail out if the full sync flag isn't set. This is
	 * because when the full sync flag is set we start all ordered extents
	 * and wait for them to fully complete - when they complete they update
	 * the inode's last_trans field through:
	 *
	 *     btrfs_finish_ordered_io() ->
	 *         btrfs_update_inode_fallback() ->
	 *             btrfs_update_inode() ->
	 *                 btrfs_set_inode_last_trans()
	 *
	 * So we are sure that last_trans is up to date and can do this check to
	 * bail out safely. For the fast path, when the full sync flag is not
	 * set in our inode, we can not do it because we start only our ordered
	 * extents and don't wait for them to complete (that is when
	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
	 * value might be less than or equals to fs_info->last_trans_committed,
	 * and setting a speculative last_trans for an inode when a buffered
	 * write is made (such as fs_info->generation + 1 for example) would not
	 * be reliable since after setting the value and before fsync is called
	 * any number of transactions can start and commit (transaction kthread
	 * commits the current transaction periodically), and a transaction
	 * commit does not start nor waits for ordered extents to complete.
	 */
	smp_mb();
	if (btrfs_inode_in_log(inode, root->fs_info->generation) ||
	    (full_sync && BTRFS_I(inode)->last_trans <=
	     root->fs_info->last_trans_committed) ||
	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
	     BTRFS_I(inode)->last_trans
	     <= root->fs_info->last_trans_committed)) {
		/*
		 * We've had everything committed since the last time we were
		 * modified so clear this flag in case it was set for whatever
		 * reason, it's no longer relevant.
		 */
		clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
			  &BTRFS_I(inode)->runtime_flags);
		/*
		 * An ordered extent might have started before and completed
		 * already with io errors, in which case the inode was not
		 * updated and we end up here. So check the inode's mapping
		 * flags for any errors that might have happened while doing
		 * writeback of file data.
		 */
		ret = btrfs_inode_check_errors(inode);
		inode_unlock(inode);
		goto out;
	}

	/*
	 * ok we haven't committed the transaction yet, lets do a commit
	 */
	if (file->private_data)
		btrfs_ioctl_trans_end(file);

	/*
	 * We use start here because we will need to wait on the IO to complete
	 * in btrfs_sync_log, which could require joining a transaction (for
	 * example checking cross references in the nocow path).  If we use join
	 * here we could get into a situation where we're waiting on IO to
	 * happen that is blocked on a transaction trying to commit.  With start
	 * we inc the extwriter counter, so we wait for all extwriters to exit
	 * before we start blocking join'ers.  This comment is to keep somebody
	 * from thinking they are super smart and changing this to
	 * btrfs_join_transaction *cough*Josef*cough*.
	 */
	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		inode_unlock(inode);
		goto out;
	}
	trans->sync = true;

	btrfs_init_log_ctx(&ctx);

	ret = btrfs_log_dentry_safe(trans, root, dentry, start, end, &ctx);
	if (ret < 0) {
		/* Fallthrough and commit/free transaction. */
		ret = 1;
	}

	/* we've logged all the items and now have a consistent
	 * version of the file in the log.  It is possible that
	 * someone will come in and modify the file, but that's
	 * fine because the log is consistent on disk, and we
	 * have references to all of the file's extents
	 *
	 * It is possible that someone will come in and log the
	 * file again, but that will end up using the synchronization
	 * inside btrfs_sync_log to keep things safe.
	 */
	inode_unlock(inode);

	/*
	 * If any of the ordered extents had an error, just return it to user
	 * space, so that the application knows some writes didn't succeed and
	 * can take proper action (retry for e.g.). Blindly committing the
	 * transaction in this case, would fool userspace that everything was
	 * successful. And we also want to make sure our log doesn't contain
	 * file extent items pointing to extents that weren't fully written to -
	 * just like in the non fast fsync path, where we check for the ordered
	 * operation's error flag before writing to the log tree and return -EIO
	 * if any of them had this flag set (btrfs_wait_ordered_range) -
	 * therefore we need to check for errors in the ordered operations,
	 * which are indicated by ctx.io_err.
	 */
	if (ctx.io_err) {
		btrfs_end_transaction(trans, root);
		ret = ctx.io_err;
		goto out;
	}

	if (ret != BTRFS_NO_LOG_SYNC) {
		if (!ret) {
			ret = btrfs_sync_log(trans, root, &ctx);
			if (!ret) {
				ret = btrfs_end_transaction(trans, root);
				goto out;
			}
		}
		if (!full_sync) {
			ret = btrfs_wait_ordered_range(inode, start, len);
			if (ret) {
				btrfs_end_transaction(trans, root);
				goto out;
			}
		}
		ret = btrfs_commit_transaction(trans, root);
	} else {
		ret = btrfs_end_transaction(trans, root);
	}
out:
	return ret > 0 ? -EIO : ret;
}

static const struct vm_operations_struct btrfs_file_vm_ops = {
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= btrfs_page_mkwrite,
};

static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
{
	struct address_space *mapping = filp->f_mapping;

	if (!mapping->a_ops->readpage)
		return -ENOEXEC;

	file_accessed(filp);
	vma->vm_ops = &btrfs_file_vm_ops;

	return 0;
}

static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf,
			  int slot, u64 start, u64 end)
{
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;

	if (slot < 0 || slot >= btrfs_header_nritems(leaf))
		return 0;

	btrfs_item_key_to_cpu(leaf, &key, slot);
	if (key.objectid != btrfs_ino(inode) ||
	    key.type != BTRFS_EXTENT_DATA_KEY)
		return 0;

	fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);

	if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_REG)
		return 0;

	if (btrfs_file_extent_disk_bytenr(leaf, fi))
		return 0;

	if (key.offset == end)
		return 1;
	if (key.offset + btrfs_file_extent_num_bytes(leaf, fi) == start)
		return 1;
	return 0;
}

static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
		      struct btrfs_path *path, u64 offset, u64 end)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *fi;
	struct extent_map *hole_em;
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	struct btrfs_key key;
	int ret;

	if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
		goto out;

	key.objectid = btrfs_ino(inode);
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = offset;

	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
	if (ret < 0)
		return ret;
	BUG_ON(!ret);

	leaf = path->nodes[0];
	if (hole_mergeable(inode, leaf, path->slots[0]-1, offset, end)) {
		u64 num_bytes;

		path->slots[0]--;
		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);
		num_bytes = btrfs_file_extent_num_bytes(leaf, fi) +
			end - offset;
		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
		btrfs_set_file_extent_offset(leaf, fi, 0);
		btrfs_mark_buffer_dirty(leaf);
		goto out;
	}

	if (hole_mergeable(inode, leaf, path->slots[0], offset, end)) {
		u64 num_bytes;

		key.offset = offset;
		btrfs_set_item_key_safe(root->fs_info, path, &key);
		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);
		num_bytes = btrfs_file_extent_num_bytes(leaf, fi) + end -
			offset;
		btrfs_set_file_extent_num_bytes(leaf, fi, num_bytes);
		btrfs_set_file_extent_ram_bytes(leaf, fi, num_bytes);
		btrfs_set_file_extent_offset(leaf, fi, 0);
		btrfs_mark_buffer_dirty(leaf);
		goto out;
	}
	btrfs_release_path(path);

	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset,
				       0, 0, end - offset, 0, end - offset,
				       0, 0, 0);
	if (ret)
		return ret;

out:
	btrfs_release_path(path);

	hole_em = alloc_extent_map();
	if (!hole_em) {
		btrfs_drop_extent_cache(inode, offset, end - 1, 0);
		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
			&BTRFS_I(inode)->runtime_flags);
	} else {
		hole_em->start = offset;
		hole_em->len = end - offset;
		hole_em->ram_bytes = hole_em->len;
		hole_em->orig_start = offset;

		hole_em->block_start = EXTENT_MAP_HOLE;
		hole_em->block_len = 0;
		hole_em->orig_block_len = 0;
		hole_em->bdev = root->fs_info->fs_devices->latest_bdev;
		hole_em->compress_type = BTRFS_COMPRESS_NONE;
		hole_em->generation = trans->transid;

		do {
			btrfs_drop_extent_cache(inode, offset, end - 1, 0);
			write_lock(&em_tree->lock);
			ret = add_extent_mapping(em_tree, hole_em, 1);
			write_unlock(&em_tree->lock);
		} while (ret == -EEXIST);
		free_extent_map(hole_em);
		if (ret)
			set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
				&BTRFS_I(inode)->runtime_flags);
	}

	return 0;
}

/*
 * Find a hole extent on given inode and change start/len to the end of hole
 * extent.(hole/vacuum extent whose em->start <= start &&
 *	   em->start + em->len > start)
 * When a hole extent is found, return 1 and modify start/len.
 */
static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
{
	struct extent_map *em;
	int ret = 0;

	em = btrfs_get_extent(inode, NULL, 0, *start, *len, 0);
	if (IS_ERR_OR_NULL(em)) {
		if (!em)
			ret = -ENOMEM;
		else
			ret = PTR_ERR(em);
		return ret;
	}

	/* Hole or vacuum extent(only exists in no-hole mode) */
	if (em->block_start == EXTENT_MAP_HOLE) {
		ret = 1;
		*len = em->start + em->len > *start + *len ?
		       0 : *start + *len - em->start - em->len;
		*start = em->start + em->len;
	}
	free_extent_map(em);
	return ret;
}

static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_state *cached_state = NULL;
	struct btrfs_path *path;
	struct btrfs_block_rsv *rsv;
	struct btrfs_trans_handle *trans;
	u64 lockstart;
	u64 lockend;
	u64 tail_start;
	u64 tail_len;
	u64 orig_start = offset;
	u64 cur_offset;
	u64 min_size = btrfs_calc_trunc_metadata_size(root, 1);
	u64 drop_end;
	int ret = 0;
	int err = 0;
	unsigned int rsv_count;
	bool same_block;
	bool no_holes = btrfs_fs_incompat(root->fs_info, NO_HOLES);
	u64 ino_size;
	bool truncated_block = false;
	bool updated_inode = false;

	ret = btrfs_wait_ordered_range(inode, offset, len);
	if (ret)
		return ret;

	inode_lock(inode);
	ino_size = round_up(inode->i_size, root->sectorsize);
	ret = find_first_non_hole(inode, &offset, &len);
	if (ret < 0)
		goto out_only_mutex;
	if (ret && !len) {
		/* Already in a large hole */
		ret = 0;
		goto out_only_mutex;
	}

	lockstart = round_up(offset, BTRFS_I(inode)->root->sectorsize);
	lockend = round_down(offset + len,
			     BTRFS_I(inode)->root->sectorsize) - 1;
	same_block = (BTRFS_BYTES_TO_BLKS(root->fs_info, offset))
		== (BTRFS_BYTES_TO_BLKS(root->fs_info, offset + len - 1));
	/*
	 * We needn't truncate any block which is beyond the end of the file
	 * because we are sure there is no data there.
	 */
	/*
	 * Only do this if we are in the same block and we aren't doing the
	 * entire block.
	 */
	if (same_block && len < root->sectorsize) {
		if (offset < ino_size) {
			truncated_block = true;
			ret = btrfs_truncate_block(inode, offset, len, 0);
		} else {
			ret = 0;
		}
		goto out_only_mutex;
	}

	/* zero back part of the first block */
	if (offset < ino_size) {
		truncated_block = true;
		ret = btrfs_truncate_block(inode, offset, 0, 0);
		if (ret) {
			inode_unlock(inode);
			return ret;
		}
	}

	/* Check the aligned pages after the first unaligned page,
	 * if offset != orig_start, which means the first unaligned page
	 * including several following pages are already in holes,
	 * the extra check can be skipped */
	if (offset == orig_start) {
		/* after truncate page, check hole again */
		len = offset + len - lockstart;
		offset = lockstart;
		ret = find_first_non_hole(inode, &offset, &len);
		if (ret < 0)
			goto out_only_mutex;
		if (ret && !len) {
			ret = 0;
			goto out_only_mutex;
		}
		lockstart = offset;
	}

	/* Check the tail unaligned part is in a hole */
	tail_start = lockend + 1;
	tail_len = offset + len - tail_start;
	if (tail_len) {
		ret = find_first_non_hole(inode, &tail_start, &tail_len);
		if (unlikely(ret < 0))
			goto out_only_mutex;
		if (!ret) {
			/* zero the front end of the last page */
			if (tail_start + tail_len < ino_size) {
				truncated_block = true;
				ret = btrfs_truncate_block(inode,
							tail_start + tail_len,
							0, 1);
				if (ret)
					goto out_only_mutex;
			}
		}
	}

	if (lockend < lockstart) {
		ret = 0;
		goto out_only_mutex;
	}

	while (1) {
		struct btrfs_ordered_extent *ordered;

		truncate_pagecache_range(inode, lockstart, lockend);

		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
				 &cached_state);
		ordered = btrfs_lookup_first_ordered_extent(inode, lockend);

		/*
		 * We need to make sure we have no ordered extents in this range
		 * and nobody raced in and read a page in this range, if we did
		 * we need to try again.
		 */
		if ((!ordered ||
		    (ordered->file_offset + ordered->len <= lockstart ||
		     ordered->file_offset > lockend)) &&
		     !btrfs_page_exists_in_range(inode, lockstart, lockend)) {
			if (ordered)
				btrfs_put_ordered_extent(ordered);
			break;
		}
		if (ordered)
			btrfs_put_ordered_extent(ordered);
		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
				     lockend, &cached_state, GFP_NOFS);
		ret = btrfs_wait_ordered_range(inode, lockstart,
					       lockend - lockstart + 1);
		if (ret) {
			inode_unlock(inode);
			return ret;
		}
	}

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	rsv = btrfs_alloc_block_rsv(root, BTRFS_BLOCK_RSV_TEMP);
	if (!rsv) {
		ret = -ENOMEM;
		goto out_free;
	}
	rsv->size = btrfs_calc_trunc_metadata_size(root, 1);
	rsv->failfast = 1;

	/*
	 * 1 - update the inode
	 * 1 - removing the extents in the range
	 * 1 - adding the hole extent if no_holes isn't set
	 */
	rsv_count = no_holes ? 2 : 3;
	trans = btrfs_start_transaction(root, rsv_count);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_free;
	}

	ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv, rsv,
				      min_size, 0);
	BUG_ON(ret);
	trans->block_rsv = rsv;

	cur_offset = lockstart;
	len = lockend - cur_offset;
	while (cur_offset < lockend) {
		ret = __btrfs_drop_extents(trans, root, inode, path,
					   cur_offset, lockend + 1,
					   &drop_end, 1, 0, 0, NULL);
		if (ret != -ENOSPC)
			break;

		trans->block_rsv = &root->fs_info->trans_block_rsv;

		if (cur_offset < ino_size) {
			ret = fill_holes(trans, inode, path, cur_offset,
					 drop_end);
			if (ret) {
				err = ret;
				break;
			}
		}

		cur_offset = drop_end;

		ret = btrfs_update_inode(trans, root, inode);
		if (ret) {
			err = ret;
			break;
		}

		btrfs_end_transaction(trans, root);
		btrfs_btree_balance_dirty(root);

		trans = btrfs_start_transaction(root, rsv_count);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			trans = NULL;
			break;
		}

		ret = btrfs_block_rsv_migrate(&root->fs_info->trans_block_rsv,
					      rsv, min_size, 0);
		BUG_ON(ret);	/* shouldn't happen */
		trans->block_rsv = rsv;

		ret = find_first_non_hole(inode, &cur_offset, &len);
		if (unlikely(ret < 0))
			break;
		if (ret && !len) {
			ret = 0;
			break;
		}
	}

	if (ret) {
		err = ret;
		goto out_trans;
	}

	trans->block_rsv = &root->fs_info->trans_block_rsv;
	/*
	 * If we are using the NO_HOLES feature we might have had already an
	 * hole that overlaps a part of the region [lockstart, lockend] and
	 * ends at (or beyond) lockend. Since we have no file extent items to
	 * represent holes, drop_end can be less than lockend and so we must
	 * make sure we have an extent map representing the existing hole (the
	 * call to __btrfs_drop_extents() might have dropped the existing extent
	 * map representing the existing hole), otherwise the fast fsync path
	 * will not record the existence of the hole region
	 * [existing_hole_start, lockend].
	 */
	if (drop_end <= lockend)
		drop_end = lockend + 1;
	/*
	 * Don't insert file hole extent item if it's for a range beyond eof
	 * (because it's useless) or if it represents a 0 bytes range (when
	 * cur_offset == drop_end).
	 */
	if (cur_offset < ino_size && cur_offset < drop_end) {
		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
		if (ret) {
			err = ret;
			goto out_trans;
		}
	}

out_trans:
	if (!trans)
		goto out_free;

	inode_inc_iversion(inode);
	inode->i_mtime = inode->i_ctime = current_fs_time(inode->i_sb);

	trans->block_rsv = &root->fs_info->trans_block_rsv;
	ret = btrfs_update_inode(trans, root, inode);
	updated_inode = true;
	btrfs_end_transaction(trans, root);
	btrfs_btree_balance_dirty(root);
out_free:
	btrfs_free_path(path);
	btrfs_free_block_rsv(root, rsv);
out:
	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
			     &cached_state, GFP_NOFS);
out_only_mutex:
	if (!updated_inode && truncated_block && !ret && !err) {
		/*
		 * If we only end up zeroing part of a page, we still need to
		 * update the inode item, so that all the time fields are
		 * updated as well as the necessary btrfs inode in memory fields
		 * for detecting, at fsync time, if the inode isn't yet in the
		 * log tree or it's there but not up to date.
		 */
		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans)) {
			err = PTR_ERR(trans);
		} else {
			err = btrfs_update_inode(trans, root, inode);
			ret = btrfs_end_transaction(trans, root);
		}
	}
	inode_unlock(inode);
	if (ret && !err)
		err = ret;
	return err;
}

/* Helper structure to record which range is already reserved */
struct falloc_range {
	struct list_head list;
	u64 start;
	u64 len;
};

/*
 * Helper function to add falloc range
 *
 * Caller should have locked the larger range of extent containing
 * [start, len)
 */
static int add_falloc_range(struct list_head *head, u64 start, u64 len)
{
	struct falloc_range *prev = NULL;
	struct falloc_range *range = NULL;

	if (list_empty(head))
		goto insert;

	/*
	 * As fallocate iterate by bytenr order, we only need to check
	 * the last range.
	 */
	prev = list_entry(head->prev, struct falloc_range, list);
	if (prev->start + prev->len == start) {
		prev->len += len;
		return 0;
	}
insert:
	range = kmalloc(sizeof(*range), GFP_KERNEL);
	if (!range)
		return -ENOMEM;
	range->start = start;
	range->len = len;
	list_add_tail(&range->list, head);
	return 0;
}

static long btrfs_fallocate(struct file *file, int mode,
			    loff_t offset, loff_t len)
{
	struct inode *inode = file_inode(file);
	struct extent_state *cached_state = NULL;
	struct falloc_range *range;
	struct falloc_range *tmp;
	struct list_head reserve_list;
	u64 cur_offset;
	u64 last_byte;
	u64 alloc_start;
	u64 alloc_end;
	u64 alloc_hint = 0;
	u64 locked_end;
	u64 actual_end = 0;
	struct extent_map *em;
	int blocksize = BTRFS_I(inode)->root->sectorsize;
	int ret;

	alloc_start = round_down(offset, blocksize);
	alloc_end = round_up(offset + len, blocksize);
	cur_offset = alloc_start;

	/* Make sure we aren't being give some crap mode */
	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	if (mode & FALLOC_FL_PUNCH_HOLE)
		return btrfs_punch_hole(inode, offset, len);

	/*
	 * Only trigger disk allocation, don't trigger qgroup reserve
	 *
	 * For qgroup space, it will be checked later.
	 */
	ret = btrfs_alloc_data_chunk_ondemand(inode, alloc_end - alloc_start);
	if (ret < 0)
		return ret;

	inode_lock(inode);

	if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) {
		ret = inode_newsize_ok(inode, offset + len);
		if (ret)
			goto out;
	}

	/*
	 * TODO: Move these two operations after we have checked
	 * accurate reserved space, or fallocate can still fail but
	 * with page truncated or size expanded.
	 *
	 * But that's a minor problem and won't do much harm BTW.
	 */
	if (alloc_start > inode->i_size) {
		ret = btrfs_cont_expand(inode, i_size_read(inode),
					alloc_start);
		if (ret)
			goto out;
	} else if (offset + len > inode->i_size) {
		/*
		 * If we are fallocating from the end of the file onward we
		 * need to zero out the end of the block if i_size lands in the
		 * middle of a block.
		 */
		ret = btrfs_truncate_block(inode, inode->i_size, 0, 0);
		if (ret)
			goto out;
	}

	/*
	 * wait for ordered IO before we have any locks.  We'll loop again
	 * below with the locks held.
	 */
	ret = btrfs_wait_ordered_range(inode, alloc_start,
				       alloc_end - alloc_start);
	if (ret)
		goto out;

	locked_end = alloc_end - 1;
	while (1) {
		struct btrfs_ordered_extent *ordered;

		/* the extent lock is ordered inside the running
		 * transaction
		 */
		lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
				 locked_end, &cached_state);
		ordered = btrfs_lookup_first_ordered_extent(inode,
							    alloc_end - 1);
		if (ordered &&
		    ordered->file_offset + ordered->len > alloc_start &&
		    ordered->file_offset < alloc_end) {
			btrfs_put_ordered_extent(ordered);
			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
					     alloc_start, locked_end,
					     &cached_state, GFP_KERNEL);
			/*
			 * we can't wait on the range with the transaction
			 * running or with the extent lock held
			 */
			ret = btrfs_wait_ordered_range(inode, alloc_start,
						       alloc_end - alloc_start);
			if (ret)
				goto out;
		} else {
			if (ordered)
				btrfs_put_ordered_extent(ordered);
			break;
		}
	}

	/* First, check if we exceed the qgroup limit */
	INIT_LIST_HEAD(&reserve_list);
	while (1) {
		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
				      alloc_end - cur_offset, 0);
		if (IS_ERR_OR_NULL(em)) {
			if (!em)
				ret = -ENOMEM;
			else
				ret = PTR_ERR(em);
			break;
		}
		last_byte = min(extent_map_end(em), alloc_end);
		actual_end = min_t(u64, extent_map_end(em), offset + len);
		last_byte = ALIGN(last_byte, blocksize);
		if (em->block_start == EXTENT_MAP_HOLE ||
		    (cur_offset >= inode->i_size &&
		     !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
			ret = add_falloc_range(&reserve_list, cur_offset,
					       last_byte - cur_offset);
			if (ret < 0) {
				free_extent_map(em);
				break;
			}
			ret = btrfs_qgroup_reserve_data(inode, cur_offset,
					last_byte - cur_offset);
			if (ret < 0)
				break;
		} else {
			/*
			 * Do not need to reserve unwritten extent for this
			 * range, free reserved data space first, otherwise
			 * it'll result in false ENOSPC error.
			 */
			btrfs_free_reserved_data_space(inode, cur_offset,
				last_byte - cur_offset);
		}
		free_extent_map(em);
		cur_offset = last_byte;
		if (cur_offset >= alloc_end)
			break;
	}

	/*
	 * If ret is still 0, means we're OK to fallocate.
	 * Or just cleanup the list and exit.
	 */
	list_for_each_entry_safe(range, tmp, &reserve_list, list) {
		if (!ret)
			ret = btrfs_prealloc_file_range(inode, mode,
					range->start,
					range->len, 1 << inode->i_blkbits,
					offset + len, &alloc_hint);
		else
			btrfs_free_reserved_data_space(inode, range->start,
						       range->len);
		list_del(&range->list);
		kfree(range);
	}
	if (ret < 0)
		goto out_unlock;

	if (actual_end > inode->i_size &&
	    !(mode & FALLOC_FL_KEEP_SIZE)) {
		struct btrfs_trans_handle *trans;
		struct btrfs_root *root = BTRFS_I(inode)->root;

		/*
		 * We didn't need to allocate any more space, but we
		 * still extended the size of the file so we need to
		 * update i_size and the inode item.
		 */
		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
		} else {
			inode->i_ctime = current_fs_time(inode->i_sb);
			i_size_write(inode, actual_end);
			btrfs_ordered_update_i_size(inode, actual_end, NULL);
			ret = btrfs_update_inode(trans, root, inode);
			if (ret)
				btrfs_end_transaction(trans, root);
			else
				ret = btrfs_end_transaction(trans, root);
		}
	}
out_unlock:
	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
			     &cached_state, GFP_KERNEL);
out:
	inode_unlock(inode);
	/* Let go of our reservation. */
	if (ret != 0)
		btrfs_free_reserved_data_space(inode, alloc_start,
				       alloc_end - cur_offset);
	return ret;
}

static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_map *em = NULL;
	struct extent_state *cached_state = NULL;
	u64 lockstart;
	u64 lockend;
	u64 start;
	u64 len;
	int ret = 0;

	if (inode->i_size == 0)
		return -ENXIO;

	/*
	 * *offset can be negative, in this case we start finding DATA/HOLE from
	 * the very start of the file.
	 */
	start = max_t(loff_t, 0, *offset);

	lockstart = round_down(start, root->sectorsize);
	lockend = round_up(i_size_read(inode), root->sectorsize);
	if (lockend <= lockstart)
		lockend = lockstart + root->sectorsize;
	lockend--;
	len = lockend - lockstart + 1;

	lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
			 &cached_state);

	while (start < inode->i_size) {
		em = btrfs_get_extent_fiemap(inode, NULL, 0, start, len, 0);
		if (IS_ERR(em)) {
			ret = PTR_ERR(em);
			em = NULL;
			break;
		}

		if (whence == SEEK_HOLE &&
		    (em->block_start == EXTENT_MAP_HOLE ||
		     test_bit(EXTENT_FLAG_PREALLOC, &em->flags)))
			break;
		else if (whence == SEEK_DATA &&
			   (em->block_start != EXTENT_MAP_HOLE &&
			    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags)))
			break;

		start = em->start + em->len;
		free_extent_map(em);
		em = NULL;
		cond_resched();
	}
	free_extent_map(em);
	if (!ret) {
		if (whence == SEEK_DATA && start >= inode->i_size)
			ret = -ENXIO;
		else
			*offset = min_t(loff_t, start, inode->i_size);
	}
	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
			     &cached_state, GFP_NOFS);
	return ret;
}

static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	int ret;

	inode_lock(inode);
	switch (whence) {
	case SEEK_END:
	case SEEK_CUR:
		offset = generic_file_llseek(file, offset, whence);
		goto out;
	case SEEK_DATA:
	case SEEK_HOLE:
		if (offset >= i_size_read(inode)) {
			inode_unlock(inode);
			return -ENXIO;
		}

		ret = find_desired_extent(inode, &offset, whence);
		if (ret) {
			inode_unlock(inode);
			return ret;
		}
	}

	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
out:
	inode_unlock(inode);
	return offset;
}

const struct file_operations btrfs_file_operations = {
	.llseek		= btrfs_file_llseek,
	.read_iter      = generic_file_read_iter,
	.splice_read	= generic_file_splice_read,
	.write_iter	= btrfs_file_write_iter,
	.mmap		= btrfs_file_mmap,
	.open		= generic_file_open,
	.release	= btrfs_release_file,
	.fsync		= btrfs_sync_file,
	.fallocate	= btrfs_fallocate,
	.unlocked_ioctl	= btrfs_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= btrfs_compat_ioctl,
#endif
	.copy_file_range = btrfs_copy_file_range,
	.clone_file_range = btrfs_clone_file_range,
	.dedupe_file_range = btrfs_dedupe_file_range,
};

void btrfs_auto_defrag_exit(void)
{
	kmem_cache_destroy(btrfs_inode_defrag_cachep);
}

int btrfs_auto_defrag_init(void)
{
	btrfs_inode_defrag_cachep = kmem_cache_create("btrfs_inode_defrag",
					sizeof(struct inode_defrag), 0,
					SLAB_MEM_SPREAD,
					NULL);
	if (!btrfs_inode_defrag_cachep)
		return -ENOMEM;

	return 0;
}

int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end)
{
	int ret;

	/*
	 * So with compression we will find and lock a dirty page and clear the
	 * first one as dirty, setup an async extent, and immediately return
	 * with the entire range locked but with nobody actually marked with
	 * writeback.  So we can't just filemap_write_and_wait_range() and
	 * expect it to work since it will just kick off a thread to do the
	 * actual work.  So we need to call filemap_fdatawrite_range _again_
	 * since it will wait on the page lock, which won't be unlocked until
	 * after the pages have been marked as writeback and so we're good to go
	 * from there.  We have to do this otherwise we'll miss the ordered
	 * extents and that results in badness.  Please Josef, do not think you
	 * know better and pull this out at some point in the future, it is
	 * right and you are wrong.
	 */
	ret = filemap_fdatawrite_range(inode->i_mapping, start, end);
	if (!ret && test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
			     &BTRFS_I(inode)->runtime_flags))
		ret = filemap_fdatawrite_range(inode->i_mapping, start, end);

	return ret;
}