summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/file.c
blob: 9f455c96c9744b5f9ed3af1599eb4b375b072907 (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
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/falloc.h>
#include <linux/writeback.h>
#include <linux/compat.h>
#include <linux/slab.h>
#include <linux/btrfs.h>
#include <linux/uio.h>
#include <linux/iversion.h>
#include <linux/fsverity.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"
#include "delalloc-space.h"
#include "reflink.h"
#include "subpage.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;

	/*
	 * The extent size threshold for autodefrag.
	 *
	 * This value is different for compressed/non-compressed extents,
	 * thus needs to be passed from higher layer.
	 * (aka, inode_should_defrag())
	 */
	u32 extent_thresh;
};

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 btrfs_inode *inode,
				    struct inode_defrag *defrag)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct inode_defrag *entry;
	struct rb_node **p;
	struct rb_node *parent = NULL;
	int ret;

	p = &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;
			entry->extent_thresh = min(defrag->extent_thresh,
						   entry->extent_thresh);
			return -EEXIST;
		}
	}
	set_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags);
	rb_link_node(&defrag->rb_node, parent, p);
	rb_insert_color(&defrag->rb_node, &fs_info->defrag_inodes);
	return 0;
}

static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
{
	if (!btrfs_test_opt(fs_info, AUTO_DEFRAG))
		return 0;

	if (btrfs_fs_closing(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 btrfs_inode *inode, u32 extent_thresh)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct inode_defrag *defrag;
	u64 transid;
	int ret;

	if (!__need_auto_defrag(fs_info))
		return 0;

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

	if (trans)
		transid = trans->transid;
	else
		transid = 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;
	defrag->extent_thresh = extent_thresh;

	spin_lock(&fs_info->defrag_inodes_lock);
	if (!test_bit(BTRFS_INODE_IN_DEFRAG, &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(&fs_info->defrag_inodes_lock);
	return 0;
}

/*
 * 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_ioctl_defrag_range_args range;
	int ret = 0;
	u64 cur = 0;

again:
	if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state))
		goto cleanup;
	if (!__need_auto_defrag(fs_info))
		goto cleanup;

	/* get the inode */
	inode_root = btrfs_get_fs_root(fs_info, defrag->root, true);
	if (IS_ERR(inode_root)) {
		ret = PTR_ERR(inode_root);
		goto cleanup;
	}

	inode = btrfs_iget(fs_info->sb, defrag->ino, inode_root);
	btrfs_put_root(inode_root);
	if (IS_ERR(inode)) {
		ret = PTR_ERR(inode);
		goto cleanup;
	}

	if (cur >= i_size_read(inode)) {
		iput(inode);
		goto cleanup;
	}

	/* 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 = cur;
	range.extent_thresh = defrag->extent_thresh;

	sb_start_write(fs_info->sb);
	ret = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
				       BTRFS_DEFRAG_BATCH);
	sb_end_write(fs_info->sb);
	iput(inode);

	if (ret < 0)
		goto cleanup;

	cur = max(cur + fs_info->sectorsize, range.start);
	goto again;

cleanup:
	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))
			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 = offset_in_page(pos);

	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 = copy_page_from_iter_atomic(page, offset, count, i);

		/* 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 (unlikely(copied < count)) {
			if (!PageUptodate(page)) {
				iov_iter_revert(i, copied);
				copied = 0;
			}
			if (!copied)
				break;
		}

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

/*
 * unlocks pages after btrfs_file_write is done with them
 */
static void btrfs_drop_pages(struct btrfs_fs_info *fs_info,
			     struct page **pages, size_t num_pages,
			     u64 pos, u64 copied)
{
	size_t i;
	u64 block_start = round_down(pos, fs_info->sectorsize);
	u64 block_len = round_up(pos + copied, fs_info->sectorsize) - block_start;

	ASSERT(block_len <= U32_MAX);
	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()
		 */
		btrfs_page_clamp_clear_checked(fs_info, pages[i], block_start,
					       block_len);
		unlock_page(pages[i]);
		put_page(pages[i]);
	}
}

/*
 * After btrfs_copy_from_user(), update the following things for delalloc:
 * - Mark newly dirtied pages as DELALLOC in the io tree.
 *   Used to advise which range is to be written back.
 * - Mark modified pages as Uptodate/Dirty and not needing COW fixup
 * - Update inode size for past EOF write
 */
int btrfs_dirty_pages(struct btrfs_inode *inode, struct page **pages,
		      size_t num_pages, loff_t pos, size_t write_bytes,
		      struct extent_state **cached, bool noreserve)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	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->vfs_inode);
	unsigned int extra_bits = 0;

	if (write_bytes == 0)
		return 0;

	if (noreserve)
		extra_bits |= EXTENT_NORESERVE;

	start_pos = round_down(pos, fs_info->sectorsize);
	num_bytes = round_up(write_bytes + pos - start_pos,
			     fs_info->sectorsize);
	ASSERT(num_bytes <= U32_MAX);

	end_of_last_block = start_pos + num_bytes - 1;

	/*
	 * The pages may have already been dirty, clear out old accounting so
	 * we can set things up properly
	 */
	clear_extent_bit(&inode->io_tree, start_pos, end_of_last_block,
			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
			 0, 0, cached);

	err = btrfs_set_extent_delalloc(inode, start_pos, end_of_last_block,
					extra_bits, cached);
	if (err)
		return err;

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

		btrfs_page_clamp_set_uptodate(fs_info, p, start_pos, num_bytes);
		btrfs_page_clamp_clear_checked(fs_info, p, start_pos, num_bytes);
		btrfs_page_clamp_set_dirty(fs_info, p, start_pos, num_bytes);
	}

	/*
	 * 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->vfs_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 btrfs_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 = &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->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->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.
 *
 * Note: the VFS' inode number of bytes is not updated, it's up to the caller
 * to deal with that. We set the field 'bytes_found' of the arguments structure
 * with the number of allocated bytes found in the target range, so that the
 * caller can update the inode's number of bytes in an atomic way when
 * replacing extents in a range to avoid races with stat(2).
 */
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root, struct btrfs_inode *inode,
		       struct btrfs_drop_extents_args *args)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *fi;
	struct btrfs_ref ref = { 0 };
	struct btrfs_key key;
	struct btrfs_key new_key;
	u64 ino = btrfs_ino(inode);
	u64 search_start = args->start;
	u64 disk_bytenr = 0;
	u64 num_bytes = 0;
	u64 extent_offset = 0;
	u64 extent_end = 0;
	u64 last_end = args->start;
	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;
	struct btrfs_path *path = args->path;

	args->bytes_found = 0;
	args->extent_inserted = false;

	/* Must always have a path if ->replace_extent is true */
	ASSERT(!(args->replace_extent && !args->path));

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

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

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

	update_refs = (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID);
	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 == args->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;
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;
			}
			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 >= args->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_ram_bytes(leaf, 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) {
			last_end = extent_end;
			goto delete_extent_item;
		}

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

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

		/*
		 *     | - range to drop - |
		 *  | -------- extent -------- |
		 */
		if (args->start > key.offset && args->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 = args->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,
							args->start - key.offset);

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

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

			if (update_refs && disk_bytenr > 0) {
				btrfs_init_generic_ref(&ref,
						BTRFS_ADD_DELAYED_REF,
						disk_bytenr, num_bytes, 0);
				btrfs_init_data_ref(&ref,
						root->root_key.objectid,
						new_key.objectid,
						args->start - extent_offset,
						0, false);
				ret = btrfs_inc_extent_ref(trans, &ref);
				BUG_ON(ret); /* -ENOMEM */
			}
			key.offset = args->start;
		}
		/*
		 * From here on out we will have actually dropped something, so
		 * last_end can be updated.
		 */
		last_end = extent_end;

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

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

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

		search_start = extent_end;
		/*
		 *       | ---- range to drop ----- |
		 *  | -------- extent -------- |
		 */
		if (args->start > key.offset && args->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,
							args->start - key.offset);
			btrfs_mark_buffer_dirty(leaf);
			if (update_refs && disk_bytenr > 0)
				args->bytes_found += extent_end - args->start;
			if (args->end == extent_end)
				break;

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

		/*
		 *  | ---- range to drop ----- |
		 *    | ------ extent ------ |
		 */
		if (args->start <= key.offset && args->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) {
				args->bytes_found += extent_end - key.offset;
				extent_end = ALIGN(extent_end,
						   fs_info->sectorsize);
			} else if (update_refs && disk_bytenr > 0) {
				btrfs_init_generic_ref(&ref,
						BTRFS_DROP_DELAYED_REF,
						disk_bytenr, num_bytes, 0);
				btrfs_init_data_ref(&ref,
						root->root_key.objectid,
						key.objectid,
						key.offset - extent_offset, 0,
						false);
				ret = btrfs_free_extent(trans, &ref);
				BUG_ON(ret); /* -ENOMEM */
				args->bytes_found += extent_end - key.offset;
			}

			if (args->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();
	}

	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 args->replace_extent).
		 */
		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 && args->replace_extent &&
	    path->locks[0] == BTRFS_WRITE_LOCK &&
	    btrfs_leaf_free_space(leaf) >=
	    sizeof(struct btrfs_item) + args->extent_item_size) {

		key.objectid = ino;
		key.type = BTRFS_EXTENT_DATA_KEY;
		key.offset = args->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]++;
		}
		btrfs_setup_item_for_insert(root, path, &key, args->extent_item_size);
		args->extent_inserted = true;
	}

	if (!args->path)
		btrfs_free_path(path);
	else if (!args->extent_inserted)
		btrfs_release_path(path);
out:
	args->drop_end = found ? min(args->end, last_end) : args->end;

	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 btrfs_inode *inode, u64 start, u64 end)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *root = inode->root;
	struct extent_buffer *leaf;
	struct btrfs_path *path;
	struct btrfs_file_extent_item *fi;
	struct btrfs_ref ref = { 0 };
	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 = 0;
	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]);
	if (key.objectid != ino ||
	    key.type != BTRFS_EXTENT_DATA_KEY) {
		ret = -EINVAL;
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	fi = btrfs_item_ptr(leaf, path->slots[0],
			    struct btrfs_file_extent_item);
	if (btrfs_file_extent_type(leaf, fi) != BTRFS_FILE_EXTENT_PREALLOC) {
		ret = -EINVAL;
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	extent_end = key.offset + btrfs_file_extent_num_bytes(leaf, fi);
	if (key.offset > start || extent_end < end) {
		ret = -EINVAL;
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	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(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(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);

		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, bytenr,
				       num_bytes, 0);
		btrfs_init_data_ref(&ref, root->root_key.objectid, ino,
				    orig_offset, 0, false);
		ret = btrfs_inc_extent_ref(trans, &ref);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}

		if (split == start) {
			key.offset = start;
		} else {
			if (start != key.offset) {
				ret = -EINVAL;
				btrfs_abort_transaction(trans, ret);
				goto out;
			}
			path->slots[0]--;
			extent_end = end;
		}
		recow = 1;
	}

	other_start = end;
	other_end = 0;
	btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
			       num_bytes, 0);
	btrfs_init_data_ref(&ref, root->root_key.objectid, ino, orig_offset,
			    0, false);
	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, &ref);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
	}
	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, &ref);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
	}
	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 ret;
}

/*
 * 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;
		}

		/*
		 * Since btrfs_readpage() will unlock the page before it
		 * returns, there is a window where btrfs_releasepage() can be
		 * called to release the page.  Here we check both inode
		 * mapping and PagePrivate() to make sure the page was not
		 * released.
		 *
		 * The private flag check is essential for subpage as we need
		 * to store extra bitmap using page->private.
		 */
		if (page->mapping != inode->i_mapping || !PagePrivate(page)) {
			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;
		}

		err = set_page_extent_mapped(pages[i]);
		if (err < 0) {
			faili = i;
			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 btrfs_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_fs_info *fs_info = inode->root->fs_info;
	u64 start_pos;
	u64 last_pos;
	int i;
	int ret = 0;

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

	if (start_pos < inode->vfs_inode.i_size) {
		struct btrfs_ordered_extent *ordered;

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

		*lockstart = start_pos;
		*lockend = last_pos;
		ret = 1;
	}

	/*
	 * We should be called after prepare_pages() which should have locked
	 * all pages in the range.
	 */
	for (i = 0; i < num_pages; i++)
		WARN_ON(!PageLocked(pages[i]));

	return ret;
}

static int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
			   size_t *write_bytes, bool nowait)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct btrfs_root *root = inode->root;
	u64 lockstart, lockend;
	u64 num_bytes;
	int ret;

	if (!(inode->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)))
		return 0;

	if (!nowait && !btrfs_drew_try_write_lock(&root->snapshot_lock))
		return -EAGAIN;

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

	if (nowait) {
		struct btrfs_ordered_extent *ordered;

		if (!try_lock_extent(&inode->io_tree, lockstart, lockend))
			return -EAGAIN;

		ordered = btrfs_lookup_ordered_range(inode, lockstart,
						     num_bytes);
		if (ordered) {
			btrfs_put_ordered_extent(ordered);
			ret = -EAGAIN;
			goto out_unlock;
		}
	} else {
		btrfs_lock_and_flush_ordered_range(inode, lockstart,
						   lockend, NULL);
	}

	ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes,
			NULL, NULL, NULL, false);
	if (ret <= 0) {
		ret = 0;
		if (!nowait)
			btrfs_drew_write_unlock(&root->snapshot_lock);
	} else {
		*write_bytes = min_t(size_t, *write_bytes ,
				     num_bytes - pos + lockstart);
	}
out_unlock:
	unlock_extent(&inode->io_tree, lockstart, lockend);

	return ret;
}

static int check_nocow_nolock(struct btrfs_inode *inode, loff_t pos,
			      size_t *write_bytes)
{
	return check_can_nocow(inode, pos, write_bytes, true);
}

/*
 * Check if we can do nocow write into the range [@pos, @pos + @write_bytes)
 *
 * @pos:	 File offset
 * @write_bytes: The length to write, will be updated to the nocow writeable
 *		 range
 *
 * This function will flush ordered extents in the range to ensure proper
 * nocow checks.
 *
 * Return:
 * >0		and update @write_bytes if we can do nocow write
 *  0		if we can't do nocow write
 * -EAGAIN	if we can't get the needed lock or there are ordered extents
 * 		for * (nowait == true) case
 * <0		if other error happened
 *
 * NOTE: Callers need to release the lock by btrfs_check_nocow_unlock().
 */
int btrfs_check_nocow_lock(struct btrfs_inode *inode, loff_t pos,
			   size_t *write_bytes)
{
	return check_can_nocow(inode, pos, write_bytes, false);
}

void btrfs_check_nocow_unlock(struct btrfs_inode *inode)
{
	btrfs_drew_write_unlock(&inode->root->snapshot_lock);
}

static void update_time_for_write(struct inode *inode)
{
	struct timespec64 now;

	if (IS_NOCMTIME(inode))
		return;

	now = current_time(inode);
	if (!timespec64_equal(&inode->i_mtime, &now))
		inode->i_mtime = now;

	if (!timespec64_equal(&inode->i_ctime, &now))
		inode->i_ctime = now;

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

static int btrfs_write_check(struct kiocb *iocb, struct iov_iter *from,
			     size_t count)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	loff_t pos = iocb->ki_pos;
	int ret;
	loff_t oldsize;
	loff_t start_pos;

	if (iocb->ki_flags & IOCB_NOWAIT) {
		size_t nocow_bytes = count;

		/* We will allocate space in case nodatacow is not set, so bail */
		if (check_nocow_nolock(BTRFS_I(inode), pos, &nocow_bytes) <= 0)
			return -EAGAIN;
		/*
		 * There are holes in the range or parts of the range that must
		 * be COWed (shared extents, RO block groups, etc), so just bail
		 * out.
		 */
		if (nocow_bytes < count)
			return -EAGAIN;
	}

	current->backing_dev_info = inode_to_bdi(inode);
	ret = file_remove_privs(file);
	if (ret)
		return ret;

	/*
	 * 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);

	start_pos = round_down(pos, fs_info->sectorsize);
	oldsize = i_size_read(inode);
	if (start_pos > oldsize) {
		/* Expand hole size to cover write data, preventing empty gap */
		loff_t end_pos = round_up(pos + count, fs_info->sectorsize);

		ret = btrfs_cont_expand(BTRFS_I(inode), oldsize, end_pos);
		if (ret) {
			current->backing_dev_info = NULL;
			return ret;
		}
	}

	return 0;
}

static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
					       struct iov_iter *i)
{
	struct file *file = iocb->ki_filp;
	loff_t pos;
	struct inode *inode = file_inode(file);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct page **pages = NULL;
	struct extent_changeset *data_reserved = NULL;
	u64 release_bytes = 0;
	u64 lockstart;
	u64 lockend;
	size_t num_written = 0;
	int nrptrs;
	ssize_t ret;
	bool only_release_metadata = false;
	bool force_page_uptodate = false;
	loff_t old_isize = i_size_read(inode);
	unsigned int ilock_flags = 0;

	if (iocb->ki_flags & IOCB_NOWAIT)
		ilock_flags |= BTRFS_ILOCK_TRY;

	ret = btrfs_inode_lock(inode, ilock_flags);
	if (ret < 0)
		return ret;

	ret = generic_write_checks(iocb, i);
	if (ret <= 0)
		goto out;

	ret = btrfs_write_check(iocb, i, ret);
	if (ret < 0)
		goto out;

	pos = iocb->ki_pos;
	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) {
		ret = -ENOMEM;
		goto out;
	}

	while (iov_iter_count(i) > 0) {
		struct extent_state *cached_state = NULL;
		size_t offset = offset_in_page(pos);
		size_t sector_offset;
		size_t write_bytes = min(iov_iter_count(i),
					 nrptrs * (size_t)PAGE_SIZE -
					 offset);
		size_t num_pages;
		size_t reserve_bytes;
		size_t dirty_pages;
		size_t copied;
		size_t dirty_sectors;
		size_t num_sectors;
		int extents_locked;

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

		only_release_metadata = false;
		sector_offset = pos & (fs_info->sectorsize - 1);

		extent_changeset_release(data_reserved);
		ret = btrfs_check_data_free_space(BTRFS_I(inode),
						  &data_reserved, pos,
						  write_bytes);
		if (ret < 0) {
			/*
			 * If we don't have to COW at the offset, reserve
			 * metadata only. write_bytes may get smaller than
			 * requested here.
			 */
			if (btrfs_check_nocow_lock(BTRFS_I(inode), pos,
						   &write_bytes) > 0)
				only_release_metadata = true;
			else
				break;
		}

		num_pages = DIV_ROUND_UP(write_bytes + offset, PAGE_SIZE);
		WARN_ON(num_pages > nrptrs);
		reserve_bytes = round_up(write_bytes + sector_offset,
					 fs_info->sectorsize);
		WARN_ON(reserve_bytes == 0);
		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
						      reserve_bytes,
						      reserve_bytes);
		if (ret) {
			if (!only_release_metadata)
				btrfs_free_reserved_data_space(BTRFS_I(inode),
						data_reserved, pos,
						write_bytes);
			else
				btrfs_check_nocow_unlock(BTRFS_I(inode));
			break;
		}

		release_bytes = reserve_bytes;
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) {
			btrfs_delalloc_release_extents(BTRFS_I(inode),
						       reserve_bytes);
			break;
		}

		extents_locked = lock_and_cleanup_extent_if_need(
				BTRFS_I(inode), pages,
				num_pages, pos, write_bytes, &lockstart,
				&lockend, &cached_state);
		if (extents_locked < 0) {
			if (extents_locked == -EAGAIN)
				goto again;
			btrfs_delalloc_release_extents(BTRFS_I(inode),
						       reserve_bytes);
			ret = extents_locked;
			break;
		}

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

		num_sectors = BTRFS_BYTES_TO_BLKS(fs_info, reserve_bytes);
		dirty_sectors = round_up(copied + sector_offset,
					fs_info->sectorsize);
		dirty_sectors = BTRFS_BYTES_TO_BLKS(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 (num_sectors > dirty_sectors) {
			/* release everything except the sectors we dirtied */
			release_bytes -= dirty_sectors << fs_info->sectorsize_bits;
			if (only_release_metadata) {
				btrfs_delalloc_release_metadata(BTRFS_I(inode),
							release_bytes, true);
			} else {
				u64 __pos;

				__pos = round_down(pos,
						   fs_info->sectorsize) +
					(dirty_pages << PAGE_SHIFT);
				btrfs_delalloc_release_space(BTRFS_I(inode),
						data_reserved, __pos,
						release_bytes, true);
			}
		}

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

		ret = btrfs_dirty_pages(BTRFS_I(inode), pages,
					dirty_pages, pos, copied,
					&cached_state, only_release_metadata);

		/*
		 * If we have not locked the extent range, because the range's
		 * start offset is >= i_size, we might still have a non-NULL
		 * cached extent state, acquired while marking the extent range
		 * as delalloc through btrfs_dirty_pages(). Therefore free any
		 * possible cached extent state to avoid a memory leak.
		 */
		if (extents_locked)
			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
					     lockstart, lockend, &cached_state);
		else
			free_extent_state(cached_state);

		btrfs_delalloc_release_extents(BTRFS_I(inode), reserve_bytes);
		if (ret) {
			btrfs_drop_pages(fs_info, pages, num_pages, pos, copied);
			break;
		}

		release_bytes = 0;
		if (only_release_metadata)
			btrfs_check_nocow_unlock(BTRFS_I(inode));

		btrfs_drop_pages(fs_info, pages, num_pages, pos, copied);

		cond_resched();

		balance_dirty_pages_ratelimited(inode->i_mapping);

		pos += copied;
		num_written += copied;
	}

	kfree(pages);

	if (release_bytes) {
		if (only_release_metadata) {
			btrfs_check_nocow_unlock(BTRFS_I(inode));
			btrfs_delalloc_release_metadata(BTRFS_I(inode),
					release_bytes, true);
		} else {
			btrfs_delalloc_release_space(BTRFS_I(inode),
					data_reserved,
					round_down(pos, fs_info->sectorsize),
					release_bytes, true);
		}
	}

	extent_changeset_free(data_reserved);
	if (num_written > 0) {
		pagecache_isize_extended(inode, old_isize, iocb->ki_pos);
		iocb->ki_pos += num_written;
	}
out:
	btrfs_inode_unlock(inode, ilock_flags);
	return num_written ? num_written : ret;
}

static ssize_t check_direct_IO(struct btrfs_fs_info *fs_info,
			       const struct iov_iter *iter, loff_t offset)
{
	const u32 blocksize_mask = fs_info->sectorsize - 1;

	if (offset & blocksize_mask)
		return -EINVAL;

	if (iov_iter_alignment(iter) & blocksize_mask)
		return -EINVAL;

	return 0;
}

static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
{
	const bool is_sync_write = (iocb->ki_flags & IOCB_DSYNC);
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	loff_t pos;
	ssize_t written = 0;
	ssize_t written_buffered;
	size_t prev_left = 0;
	loff_t endbyte;
	ssize_t err;
	unsigned int ilock_flags = 0;

	if (iocb->ki_flags & IOCB_NOWAIT)
		ilock_flags |= BTRFS_ILOCK_TRY;

	/* If the write DIO is within EOF, use a shared lock */
	if (iocb->ki_pos + iov_iter_count(from) <= i_size_read(inode))
		ilock_flags |= BTRFS_ILOCK_SHARED;

relock:
	err = btrfs_inode_lock(inode, ilock_flags);
	if (err < 0)
		return err;

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

	err = btrfs_write_check(iocb, from, err);
	if (err < 0) {
		btrfs_inode_unlock(inode, ilock_flags);
		goto out;
	}

	pos = iocb->ki_pos;
	/*
	 * Re-check since file size may have changed just before taking the
	 * lock or pos may have changed because of O_APPEND in generic_write_check()
	 */
	if ((ilock_flags & BTRFS_ILOCK_SHARED) &&
	    pos + iov_iter_count(from) > i_size_read(inode)) {
		btrfs_inode_unlock(inode, ilock_flags);
		ilock_flags &= ~BTRFS_ILOCK_SHARED;
		goto relock;
	}

	if (check_direct_IO(fs_info, from, pos)) {
		btrfs_inode_unlock(inode, ilock_flags);
		goto buffered;
	}

	/*
	 * We remove IOCB_DSYNC so that we don't deadlock when iomap_dio_rw()
	 * calls generic_write_sync() (through iomap_dio_complete()), because
	 * that results in calling fsync (btrfs_sync_file()) which will try to
	 * lock the inode in exclusive/write mode.
	 */
	if (is_sync_write)
		iocb->ki_flags &= ~IOCB_DSYNC;

	/*
	 * The iov_iter can be mapped to the same file range we are writing to.
	 * If that's the case, then we will deadlock in the iomap code, because
	 * it first calls our callback btrfs_dio_iomap_begin(), which will create
	 * an ordered extent, and after that it will fault in the pages that the
	 * iov_iter refers to. During the fault in we end up in the readahead
	 * pages code (starting at btrfs_readahead()), which will lock the range,
	 * find that ordered extent and then wait for it to complete (at
	 * btrfs_lock_and_flush_ordered_range()), resulting in a deadlock since
	 * obviously the ordered extent can never complete as we didn't submit
	 * yet the respective bio(s). This always happens when the buffer is
	 * memory mapped to the same file range, since the iomap DIO code always
	 * invalidates pages in the target file range (after starting and waiting
	 * for any writeback).
	 *
	 * So here we disable page faults in the iov_iter and then retry if we
	 * got -EFAULT, faulting in the pages before the retry.
	 */
again:
	from->nofault = true;
	err = iomap_dio_rw(iocb, from, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
			   IOMAP_DIO_PARTIAL, written);
	from->nofault = false;

	/* No increment (+=) because iomap returns a cumulative value. */
	if (err > 0)
		written = err;

	if (iov_iter_count(from) > 0 && (err == -EFAULT || err > 0)) {
		const size_t left = iov_iter_count(from);
		/*
		 * We have more data left to write. Try to fault in as many as
		 * possible of the remainder pages and retry. We do this without
		 * releasing and locking again the inode, to prevent races with
		 * truncate.
		 *
		 * Also, in case the iov refers to pages in the file range of the
		 * file we want to write to (due to a mmap), we could enter an
		 * infinite loop if we retry after faulting the pages in, since
		 * iomap will invalidate any pages in the range early on, before
		 * it tries to fault in the pages of the iov. So we keep track of
		 * how much was left of iov in the previous EFAULT and fallback
		 * to buffered IO in case we haven't made any progress.
		 */
		if (left == prev_left) {
			err = -ENOTBLK;
		} else {
			fault_in_iov_iter_readable(from, left);
			prev_left = left;
			goto again;
		}
	}

	btrfs_inode_unlock(inode, ilock_flags);

	/*
	 * Add back IOCB_DSYNC. Our caller, btrfs_file_write_iter(), will do
	 * the fsync (call generic_write_sync()).
	 */
	if (is_sync_write)
		iocb->ki_flags |= IOCB_DSYNC;

	/* If 'err' is -ENOTBLK then it means we must fallback to buffered IO. */
	if ((err < 0 && err != -ENOTBLK) || !iov_iter_count(from))
		goto out;

buffered:
	pos = iocb->ki_pos;
	written_buffered = btrfs_buffered_write(iocb, from);
	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 err < 0 ? err : written;
}

static ssize_t btrfs_encoded_write(struct kiocb *iocb, struct iov_iter *from,
			const struct btrfs_ioctl_encoded_io_args *encoded)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	loff_t count;
	ssize_t ret;

	btrfs_inode_lock(inode, 0);
	count = encoded->len;
	ret = generic_write_checks_count(iocb, &count);
	if (ret == 0 && count != encoded->len) {
		/*
		 * The write got truncated by generic_write_checks_count(). We
		 * can't do a partial encoded write.
		 */
		ret = -EFBIG;
	}
	if (ret || encoded->len == 0)
		goto out;

	ret = btrfs_write_check(iocb, from, encoded->len);
	if (ret < 0)
		goto out;

	ret = btrfs_do_encoded_write(iocb, from, encoded);
out:
	btrfs_inode_unlock(inode, 0);
	return ret;
}

ssize_t btrfs_do_write_iter(struct kiocb *iocb, struct iov_iter *from,
			    const struct btrfs_ioctl_encoded_io_args *encoded)
{
	struct file *file = iocb->ki_filp;
	struct btrfs_inode *inode = BTRFS_I(file_inode(file));
	ssize_t num_written, num_sync;
	const bool sync = iocb->ki_flags & IOCB_DSYNC;

	/*
	 * If the fs flips readonly due to some impossible error, although we
	 * have opened a file as writable, we have to stop this write operation
	 * to ensure consistency.
	 */
	if (BTRFS_FS_ERROR(inode->root->fs_info))
		return -EROFS;

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

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

	if (encoded) {
		num_written = btrfs_encoded_write(iocb, from, encoded);
		num_sync = encoded->len;
	} else if (iocb->ki_flags & IOCB_DIRECT) {
		num_written = num_sync = btrfs_direct_write(iocb, from);
	} else {
		num_written = num_sync = btrfs_buffered_write(iocb, from);
	}

	btrfs_set_inode_last_sub_trans(inode);

	if (num_sync > 0) {
		num_sync = generic_write_sync(iocb, num_sync);
		if (num_sync < 0)
			num_written = num_sync;
	}

	if (sync)
		atomic_dec(&inode->sync_writers);

	current->backing_dev_info = NULL;
	return num_written;
}

static ssize_t btrfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	return btrfs_do_write_iter(iocb, from, NULL);
}

int btrfs_release_file(struct inode *inode, struct file *filp)
{
	struct btrfs_file_private *private = filp->private_data;

	if (private && private->filldir_buf)
		kfree(private->filldir_buf);
	kfree(private);
	filp->private_data = NULL;

	/*
	 * Set by setattr 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_FLUSH_ON_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;
	struct blk_plug plug;

	/*
	 * This is only called in fsync, which would do synchronous writes, so
	 * a plug can merge adjacent IOs as much as possible.  Esp. in case of
	 * multiple disks using raid profile, a large IO can be split to
	 * several segments of stripe length (currently 64K).
	 */
	blk_start_plug(&plug);
	atomic_inc(&BTRFS_I(inode)->sync_writers);
	ret = btrfs_fdatawrite_range(inode, start, end);
	atomic_dec(&BTRFS_I(inode)->sync_writers);
	blk_finish_plug(&plug);

	return ret;
}

static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
{
	struct btrfs_inode *inode = BTRFS_I(ctx->inode);
	struct btrfs_fs_info *fs_info = inode->root->fs_info;

	if (btrfs_inode_in_log(inode, fs_info->generation) &&
	    list_empty(&ctx->ordered_extents))
		return true;

	/*
	 * If we are doing a fast fsync we can not bail out if the inode's
	 * last_trans is <= then the last committed transaction, because we only
	 * update the last_trans of the inode during ordered extent completion,
	 * and for a fast fsync we don't wait for that, we only wait for the
	 * writeback to complete.
	 */
	if (inode->last_trans <= fs_info->last_trans_committed &&
	    (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags) ||
	     list_empty(&ctx->ordered_extents)))
		return true;

	return false;
}

/*
 * 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_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
	struct btrfs_log_ctx ctx;
	int ret = 0, err;
	u64 len;
	bool full_sync;

	trace_btrfs_sync_file(file, datasync);

	btrfs_init_log_ctx(&ctx, inode);

	/*
	 * Always set the range to a full range, otherwise we can get into
	 * several problems, from missing file extent items to represent holes
	 * when not using the NO_HOLES feature, to log tree corruption due to
	 * races between hole detection during logging and completion of ordered
	 * extents outside the range, to missing checksums due to ordered extents
	 * for which we flushed only a subset of their pages.
	 */
	start = 0;
	end = LLONG_MAX;
	len = (u64)LLONG_MAX + 1;

	/*
	 * 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)
		goto out;

	btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);

	atomic_inc(&root->log_batch);

	/*
	 * Always check for the full sync flag while holding the inode's lock,
	 * to avoid races with other tasks. The flag must be either set all the
	 * time during logging or always off all the time while logging.
	 */
	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
			     &BTRFS_I(inode)->runtime_flags);

	/*
	 * Before we acquired the inode's lock and the mmap lock, someone may
	 * have dirtied more pages in the target range. We need to make sure
	 * that writeback for any such pages does not start while we are logging
	 * the inode, because if it does, any of the following might happen when
	 * we are not doing a full inode sync:
	 *
	 * 1) We log an extent after its writeback finishes but before its
	 *    checksums are added to the csum tree, leading to -EIO errors
	 *    when attempting to read the extent after a log replay.
	 *
	 * 2) We can end up logging an extent before its writeback finishes.
	 *    Therefore after the log replay we will have a file extent item
	 *    pointing to an unwritten extent (and no data checksums as well).
	 *
	 * So trigger writeback for any eventual new dirty pages and then we
	 * wait for all ordered extents to complete below.
	 */
	ret = start_ordered_ops(inode, start, end);
	if (ret) {
		btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
		goto out;
	}

	/*
	 * We have to do this here to avoid the priority inversion of waiting on
	 * IO of a lower priority task while holding a transaction open.
	 *
	 * For a full fsync we wait for the ordered extents to complete while
	 * for a fast fsync we wait just for writeback to complete, and then
	 * attach the ordered extents to the transaction so that a transaction
	 * commit waits for their completion, to avoid data loss if we fsync,
	 * the current transaction commits before the ordered extents complete
	 * and a power failure happens right after that.
	 *
	 * For zoned filesystem, if a write IO uses a ZONE_APPEND command, the
	 * logical address recorded in the ordered extent may change. We need
	 * to wait for the IO to stabilize the logical address.
	 */
	if (full_sync || btrfs_is_zoned(fs_info)) {
		ret = btrfs_wait_ordered_range(inode, start, len);
	} else {
		/*
		 * Get our ordered extents as soon as possible to avoid doing
		 * checksum lookups in the csum tree, and use instead the
		 * checksums attached to the ordered extents.
		 */
		btrfs_get_ordered_extents_for_logging(BTRFS_I(inode),
						      &ctx.ordered_extents);
		ret = filemap_fdatawait_range(inode->i_mapping, start, end);
	}

	if (ret)
		goto out_release_extents;

	atomic_inc(&root->log_batch);

	smp_mb();
	if (skip_inode_logging(&ctx)) {
		/*
		 * 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
		 * for any errors that might have happened since we last
		 * checked called fsync.
		 */
		ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err);
		goto out_release_extents;
	}

	/*
	 * 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 joiners.  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);
		goto out_release_extents;
	}
	trans->in_fsync = true;

	ret = btrfs_log_dentry_safe(trans, dentry, &ctx);
	btrfs_release_log_ctx_extents(&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.
	 */
	btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);

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

out_release_extents:
	btrfs_release_log_ctx_extents(&ctx);
	btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
	goto out;
}

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 btrfs_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 btrfs_inode *inode,
		struct btrfs_path *path, u64 offset, u64 end)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *root = inode->root;
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *fi;
	struct extent_map *hole_em;
	struct extent_map_tree *em_tree = &inode->extent_tree;
	struct btrfs_key key;
	int ret;

	if (btrfs_fs_incompat(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) {
		/*
		 * We should have dropped this offset, so if we find it then
		 * something has gone horribly wrong.
		 */
		if (ret == 0)
			ret = -EINVAL;
		return 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(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);
		btrfs_set_inode_full_sync(inode);
	} 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->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)
			btrfs_set_inode_full_sync(inode);
	}

	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 btrfs_inode *inode, u64 *start, u64 *len)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct extent_map *em;
	int ret = 0;

	em = btrfs_get_extent(inode, NULL, 0,
			      round_down(*start, fs_info->sectorsize),
			      round_up(*len, fs_info->sectorsize));
	if (IS_ERR(em))
		return PTR_ERR(em);

	/* 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_lock_range(struct inode *inode,
				       const u64 lockstart,
				       const u64 lockend,
				       struct extent_state **cached_state)
{
	/*
	 * For subpage case, if the range is not at page boundary, we could
	 * have pages at the leading/tailing part of the range.
	 * This could lead to dead loop since filemap_range_has_page()
	 * will always return true.
	 * So here we need to do extra page alignment for
	 * filemap_range_has_page().
	 */
	const u64 page_lockstart = round_up(lockstart, PAGE_SIZE);
	const u64 page_lockend = round_down(lockend + 1, PAGE_SIZE) - 1;

	while (1) {
		struct btrfs_ordered_extent *ordered;
		int ret;

		truncate_pagecache_range(inode, lockstart, lockend);

		lock_extent_bits(&BTRFS_I(inode)->io_tree, lockstart, lockend,
				 cached_state);
		ordered = btrfs_lookup_first_ordered_extent(BTRFS_I(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->num_bytes <= lockstart ||
		     ordered->file_offset > lockend)) &&
		     !filemap_range_has_page(inode->i_mapping,
					     page_lockstart, page_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);
		ret = btrfs_wait_ordered_range(inode, lockstart,
					       lockend - lockstart + 1);
		if (ret)
			return ret;
	}
	return 0;
}

static int btrfs_insert_replace_extent(struct btrfs_trans_handle *trans,
				     struct btrfs_inode *inode,
				     struct btrfs_path *path,
				     struct btrfs_replace_extent_info *extent_info,
				     const u64 replace_len,
				     const u64 bytes_to_drop)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *root = inode->root;
	struct btrfs_file_extent_item *extent;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	int slot;
	struct btrfs_ref ref = { 0 };
	int ret;

	if (replace_len == 0)
		return 0;

	if (extent_info->disk_offset == 0 &&
	    btrfs_fs_incompat(fs_info, NO_HOLES)) {
		btrfs_update_inode_bytes(inode, 0, bytes_to_drop);
		return 0;
	}

	key.objectid = btrfs_ino(inode);
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = extent_info->file_offset;
	ret = btrfs_insert_empty_item(trans, root, path, &key,
				      sizeof(struct btrfs_file_extent_item));
	if (ret)
		return ret;
	leaf = path->nodes[0];
	slot = path->slots[0];
	write_extent_buffer(leaf, extent_info->extent_buf,
			    btrfs_item_ptr_offset(leaf, slot),
			    sizeof(struct btrfs_file_extent_item));
	extent = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
	ASSERT(btrfs_file_extent_type(leaf, extent) != BTRFS_FILE_EXTENT_INLINE);
	btrfs_set_file_extent_offset(leaf, extent, extent_info->data_offset);
	btrfs_set_file_extent_num_bytes(leaf, extent, replace_len);
	if (extent_info->is_new_extent)
		btrfs_set_file_extent_generation(leaf, extent, trans->transid);
	btrfs_mark_buffer_dirty(leaf);
	btrfs_release_path(path);

	ret = btrfs_inode_set_file_extent_range(inode, extent_info->file_offset,
						replace_len);
	if (ret)
		return ret;

	/* If it's a hole, nothing more needs to be done. */
	if (extent_info->disk_offset == 0) {
		btrfs_update_inode_bytes(inode, 0, bytes_to_drop);
		return 0;
	}

	btrfs_update_inode_bytes(inode, replace_len, bytes_to_drop);

	if (extent_info->is_new_extent && extent_info->insertions == 0) {
		key.objectid = extent_info->disk_offset;
		key.type = BTRFS_EXTENT_ITEM_KEY;
		key.offset = extent_info->disk_len;
		ret = btrfs_alloc_reserved_file_extent(trans, root,
						       btrfs_ino(inode),
						       extent_info->file_offset,
						       extent_info->qgroup_reserved,
						       &key);
	} else {
		u64 ref_offset;

		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF,
				       extent_info->disk_offset,
				       extent_info->disk_len, 0);
		ref_offset = extent_info->file_offset - extent_info->data_offset;
		btrfs_init_data_ref(&ref, root->root_key.objectid,
				    btrfs_ino(inode), ref_offset, 0, false);
		ret = btrfs_inc_extent_ref(trans, &ref);
	}

	extent_info->insertions++;

	return ret;
}

/*
 * The respective range must have been previously locked, as well as the inode.
 * The end offset is inclusive (last byte of the range).
 * @extent_info is NULL for fallocate's hole punching and non-NULL when replacing
 * the file range with an extent.
 * When not punching a hole, we don't want to end up in a state where we dropped
 * extents without inserting a new one, so we must abort the transaction to avoid
 * a corruption.
 */
int btrfs_replace_file_extents(struct btrfs_inode *inode,
			       struct btrfs_path *path, const u64 start,
			       const u64 end,
			       struct btrfs_replace_extent_info *extent_info,
			       struct btrfs_trans_handle **trans_out)
{
	struct btrfs_drop_extents_args drop_args = { 0 };
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 min_size = btrfs_calc_insert_metadata_size(fs_info, 1);
	u64 ino_size = round_up(inode->vfs_inode.i_size, fs_info->sectorsize);
	struct btrfs_trans_handle *trans = NULL;
	struct btrfs_block_rsv *rsv;
	unsigned int rsv_count;
	u64 cur_offset;
	u64 len = end - start;
	int ret = 0;

	if (end <= start)
		return -EINVAL;

	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
	if (!rsv) {
		ret = -ENOMEM;
		goto out;
	}
	rsv->size = btrfs_calc_insert_metadata_size(fs_info, 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 or if we are
	 *     replacing the range with a new extent
	 */
	if (!btrfs_fs_incompat(fs_info, NO_HOLES) || extent_info)
		rsv_count = 3;
	else
		rsv_count = 2;

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

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

	cur_offset = start;
	drop_args.path = path;
	drop_args.end = end + 1;
	drop_args.drop_cache = true;
	while (cur_offset < end) {
		drop_args.start = cur_offset;
		ret = btrfs_drop_extents(trans, root, inode, &drop_args);
		/* If we are punching a hole decrement the inode's byte count */
		if (!extent_info)
			btrfs_update_inode_bytes(inode, 0,
						 drop_args.bytes_found);
		if (ret != -ENOSPC) {
			/*
			 * The only time we don't want to abort is if we are
			 * attempting to clone a partial inline extent, in which
			 * case we'll get EOPNOTSUPP.  However if we aren't
			 * clone we need to abort no matter what, because if we
			 * got EOPNOTSUPP via prealloc then we messed up and
			 * need to abort.
			 */
			if (ret &&
			    (ret != -EOPNOTSUPP ||
			     (extent_info && extent_info->is_new_extent)))
				btrfs_abort_transaction(trans, ret);
			break;
		}

		trans->block_rsv = &fs_info->trans_block_rsv;

		if (!extent_info && cur_offset < drop_args.drop_end &&
		    cur_offset < ino_size) {
			ret = fill_holes(trans, inode, path, cur_offset,
					 drop_args.drop_end);
			if (ret) {
				/*
				 * If we failed then we didn't insert our hole
				 * entries for the area we dropped, so now the
				 * fs is corrupted, so we must abort the
				 * transaction.
				 */
				btrfs_abort_transaction(trans, ret);
				break;
			}
		} else if (!extent_info && cur_offset < drop_args.drop_end) {
			/*
			 * We are past the i_size here, but since we didn't
			 * insert holes we need to clear the mapped area so we
			 * know to not set disk_i_size in this area until a new
			 * file extent is inserted here.
			 */
			ret = btrfs_inode_clear_file_extent_range(inode,
					cur_offset,
					drop_args.drop_end - cur_offset);
			if (ret) {
				/*
				 * We couldn't clear our area, so we could
				 * presumably adjust up and corrupt the fs, so
				 * we need to abort.
				 */
				btrfs_abort_transaction(trans, ret);
				break;
			}
		}

		if (extent_info &&
		    drop_args.drop_end > extent_info->file_offset) {
			u64 replace_len = drop_args.drop_end -
					  extent_info->file_offset;

			ret = btrfs_insert_replace_extent(trans, inode,	path,
					extent_info, replace_len,
					drop_args.bytes_found);
			if (ret) {
				btrfs_abort_transaction(trans, ret);
				break;
			}
			extent_info->data_len -= replace_len;
			extent_info->data_offset += replace_len;
			extent_info->file_offset += replace_len;
		}

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

		btrfs_end_transaction(trans);
		btrfs_btree_balance_dirty(fs_info);

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

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

		cur_offset = drop_args.drop_end;
		len = end - cur_offset;
		if (!extent_info && len) {
			ret = find_first_non_hole(inode, &cur_offset, &len);
			if (unlikely(ret < 0))
				break;
			if (ret && !len) {
				ret = 0;
				break;
			}
		}
	}

	/*
	 * If we were cloning, force the next fsync to be a full one since we
	 * we replaced (or just dropped in the case of cloning holes when
	 * NO_HOLES is enabled) file extent items and did not setup new extent
	 * maps for the replacement extents (or holes).
	 */
	if (extent_info && !extent_info->is_new_extent)
		btrfs_set_inode_full_sync(inode);

	if (ret)
		goto out_trans;

	trans->block_rsv = &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_args.drop_end <= end)
		drop_args.drop_end = end + 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 (!extent_info && cur_offset < ino_size &&
	    cur_offset < drop_args.drop_end) {
		ret = fill_holes(trans, inode, path, cur_offset,
				 drop_args.drop_end);
		if (ret) {
			/* Same comment as above. */
			btrfs_abort_transaction(trans, ret);
			goto out_trans;
		}
	} else if (!extent_info && cur_offset < drop_args.drop_end) {
		/* See the comment in the loop above for the reasoning here. */
		ret = btrfs_inode_clear_file_extent_range(inode, cur_offset,
					drop_args.drop_end - cur_offset);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out_trans;
		}

	}
	if (extent_info) {
		ret = btrfs_insert_replace_extent(trans, inode, path,
				extent_info, extent_info->data_len,
				drop_args.bytes_found);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out_trans;
		}
	}

out_trans:
	if (!trans)
		goto out_free;

	trans->block_rsv = &fs_info->trans_block_rsv;
	if (ret)
		btrfs_end_transaction(trans);
	else
		*trans_out = trans;
out_free:
	btrfs_free_block_rsv(fs_info, rsv);
out:
	return ret;
}

static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_state *cached_state = NULL;
	struct btrfs_path *path;
	struct btrfs_trans_handle *trans = NULL;
	u64 lockstart;
	u64 lockend;
	u64 tail_start;
	u64 tail_len;
	u64 orig_start = offset;
	int ret = 0;
	bool same_block;
	u64 ino_size;
	bool truncated_block = false;
	bool updated_inode = false;

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

	btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);
	ino_size = round_up(inode->i_size, fs_info->sectorsize);
	ret = find_first_non_hole(BTRFS_I(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_inode_sectorsize(BTRFS_I(inode)));
	lockend = round_down(offset + len,
			     btrfs_inode_sectorsize(BTRFS_I(inode))) - 1;
	same_block = (BTRFS_BYTES_TO_BLKS(fs_info, offset))
		== (BTRFS_BYTES_TO_BLKS(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 < fs_info->sectorsize) {
		if (offset < ino_size) {
			truncated_block = true;
			ret = btrfs_truncate_block(BTRFS_I(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(BTRFS_I(inode), offset, 0, 0);
		if (ret) {
			btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
			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(BTRFS_I(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(BTRFS_I(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(BTRFS_I(inode),
							tail_start + tail_len,
							0, 1);
				if (ret)
					goto out_only_mutex;
			}
		}
	}

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

	ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend,
					  &cached_state);
	if (ret)
		goto out_only_mutex;

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

	ret = btrfs_replace_file_extents(BTRFS_I(inode), path, lockstart,
					 lockend, NULL, &trans);
	btrfs_free_path(path);
	if (ret)
		goto out;

	ASSERT(trans != NULL);
	inode_inc_iversion(inode);
	inode->i_mtime = inode->i_ctime = current_time(inode);
	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
	updated_inode = true;
	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(fs_info);
out:
	unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart, lockend,
			     &cached_state);
out_only_mutex:
	if (!updated_inode && truncated_block && !ret) {
		/*
		 * 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.
		 */
		struct timespec64 now = current_time(inode);

		inode_inc_iversion(inode);
		inode->i_mtime = now;
		inode->i_ctime = now;
		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
		} else {
			int ret2;

			ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
			ret2 = btrfs_end_transaction(trans);
			if (!ret)
				ret = ret2;
		}
	}
	btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
	return ret;
}

/* 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 *range = NULL;

	if (!list_empty(head)) {
		/*
		 * As fallocate iterates by bytenr order, we only need to check
		 * the last range.
		 */
		range = list_last_entry(head, struct falloc_range, list);
		if (range->start + range->len == start) {
			range->len += len;
			return 0;
		}
	}

	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 int btrfs_fallocate_update_isize(struct inode *inode,
					const u64 end,
					const int mode)
{
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	int ret;
	int ret2;

	if (mode & FALLOC_FL_KEEP_SIZE || end <= i_size_read(inode))
		return 0;

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

	inode->i_ctime = current_time(inode);
	i_size_write(inode, end);
	btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
	ret = btrfs_update_inode(trans, root, BTRFS_I(inode));
	ret2 = btrfs_end_transaction(trans);

	return ret ? ret : ret2;
}

enum {
	RANGE_BOUNDARY_WRITTEN_EXTENT,
	RANGE_BOUNDARY_PREALLOC_EXTENT,
	RANGE_BOUNDARY_HOLE,
};

static int btrfs_zero_range_check_range_boundary(struct btrfs_inode *inode,
						 u64 offset)
{
	const u64 sectorsize = btrfs_inode_sectorsize(inode);
	struct extent_map *em;
	int ret;

	offset = round_down(offset, sectorsize);
	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize);
	if (IS_ERR(em))
		return PTR_ERR(em);

	if (em->block_start == EXTENT_MAP_HOLE)
		ret = RANGE_BOUNDARY_HOLE;
	else if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
		ret = RANGE_BOUNDARY_PREALLOC_EXTENT;
	else
		ret = RANGE_BOUNDARY_WRITTEN_EXTENT;

	free_extent_map(em);
	return ret;
}

static int btrfs_zero_range(struct inode *inode,
			    loff_t offset,
			    loff_t len,
			    const int mode)
{
	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
	struct extent_map *em;
	struct extent_changeset *data_reserved = NULL;
	int ret;
	u64 alloc_hint = 0;
	const u64 sectorsize = btrfs_inode_sectorsize(BTRFS_I(inode));
	u64 alloc_start = round_down(offset, sectorsize);
	u64 alloc_end = round_up(offset + len, sectorsize);
	u64 bytes_to_reserve = 0;
	bool space_reserved = false;

	inode_dio_wait(inode);

	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
			      alloc_end - alloc_start);
	if (IS_ERR(em)) {
		ret = PTR_ERR(em);
		goto out;
	}

	/*
	 * Avoid hole punching and extent allocation for some cases. More cases
	 * could be considered, but these are unlikely common and we keep things
	 * as simple as possible for now. Also, intentionally, if the target
	 * range contains one or more prealloc extents together with regular
	 * extents and holes, we drop all the existing extents and allocate a
	 * new prealloc extent, so that we get a larger contiguous disk extent.
	 */
	if (em->start <= alloc_start &&
	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
		const u64 em_end = em->start + em->len;

		if (em_end >= offset + len) {
			/*
			 * The whole range is already a prealloc extent,
			 * do nothing except updating the inode's i_size if
			 * needed.
			 */
			free_extent_map(em);
			ret = btrfs_fallocate_update_isize(inode, offset + len,
							   mode);
			goto out;
		}
		/*
		 * Part of the range is already a prealloc extent, so operate
		 * only on the remaining part of the range.
		 */
		alloc_start = em_end;
		ASSERT(IS_ALIGNED(alloc_start, sectorsize));
		len = offset + len - alloc_start;
		offset = alloc_start;
		alloc_hint = em->block_start + em->len;
	}
	free_extent_map(em);

	if (BTRFS_BYTES_TO_BLKS(fs_info, offset) ==
	    BTRFS_BYTES_TO_BLKS(fs_info, offset + len - 1)) {
		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, alloc_start,
				      sectorsize);
		if (IS_ERR(em)) {
			ret = PTR_ERR(em);
			goto out;
		}

		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
			free_extent_map(em);
			ret = btrfs_fallocate_update_isize(inode, offset + len,
							   mode);
			goto out;
		}
		if (len < sectorsize && em->block_start != EXTENT_MAP_HOLE) {
			free_extent_map(em);
			ret = btrfs_truncate_block(BTRFS_I(inode), offset, len,
						   0);
			if (!ret)
				ret = btrfs_fallocate_update_isize(inode,
								   offset + len,
								   mode);
			return ret;
		}
		free_extent_map(em);
		alloc_start = round_down(offset, sectorsize);
		alloc_end = alloc_start + sectorsize;
		goto reserve_space;
	}

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

	/*
	 * For unaligned ranges, check the pages at the boundaries, they might
	 * map to an extent, in which case we need to partially zero them, or
	 * they might map to a hole, in which case we need our allocation range
	 * to cover them.
	 */
	if (!IS_ALIGNED(offset, sectorsize)) {
		ret = btrfs_zero_range_check_range_boundary(BTRFS_I(inode),
							    offset);
		if (ret < 0)
			goto out;
		if (ret == RANGE_BOUNDARY_HOLE) {
			alloc_start = round_down(offset, sectorsize);
			ret = 0;
		} else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) {
			ret = btrfs_truncate_block(BTRFS_I(inode), offset, 0, 0);
			if (ret)
				goto out;
		} else {
			ret = 0;
		}
	}

	if (!IS_ALIGNED(offset + len, sectorsize)) {
		ret = btrfs_zero_range_check_range_boundary(BTRFS_I(inode),
							    offset + len);
		if (ret < 0)
			goto out;
		if (ret == RANGE_BOUNDARY_HOLE) {
			alloc_end = round_up(offset + len, sectorsize);
			ret = 0;
		} else if (ret == RANGE_BOUNDARY_WRITTEN_EXTENT) {
			ret = btrfs_truncate_block(BTRFS_I(inode), offset + len,
						   0, 1);
			if (ret)
				goto out;
		} else {
			ret = 0;
		}
	}

reserve_space:
	if (alloc_start < alloc_end) {
		struct extent_state *cached_state = NULL;
		const u64 lockstart = alloc_start;
		const u64 lockend = alloc_end - 1;

		bytes_to_reserve = alloc_end - alloc_start;
		ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode),
						      bytes_to_reserve);
		if (ret < 0)
			goto out;
		space_reserved = true;
		ret = btrfs_punch_hole_lock_range(inode, lockstart, lockend,
						  &cached_state);
		if (ret)
			goto out;
		ret = btrfs_qgroup_reserve_data(BTRFS_I(inode), &data_reserved,
						alloc_start, bytes_to_reserve);
		if (ret) {
			unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
					     lockend, &cached_state);
			goto out;
		}
		ret = btrfs_prealloc_file_range(inode, mode, alloc_start,
						alloc_end - alloc_start,
						i_blocksize(inode),
						offset + len, &alloc_hint);
		unlock_extent_cached(&BTRFS_I(inode)->io_tree, lockstart,
				     lockend, &cached_state);
		/* btrfs_prealloc_file_range releases reserved space on error */
		if (ret) {
			space_reserved = false;
			goto out;
		}
	}
	ret = btrfs_fallocate_update_isize(inode, offset + len, mode);
 out:
	if (ret && space_reserved)
		btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved,
					       alloc_start, bytes_to_reserve);
	extent_changeset_free(data_reserved);

	return ret;
}

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 extent_changeset *data_reserved = 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_inode_sectorsize(BTRFS_I(inode));
	int ret;

	/* Do not allow fallocate in ZONED mode */
	if (btrfs_is_zoned(btrfs_sb(inode->i_sb)))
		return -EOPNOTSUPP;

	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 |
		     FALLOC_FL_ZERO_RANGE))
		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.
	 */
	if (!(mode & FALLOC_FL_ZERO_RANGE)) {
		ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode),
						      alloc_end - alloc_start);
		if (ret < 0)
			return ret;
	}

	btrfs_inode_lock(inode, BTRFS_ILOCK_MMAP);

	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(BTRFS_I(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(BTRFS_I(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;

	if (mode & FALLOC_FL_ZERO_RANGE) {
		ret = btrfs_zero_range(inode, offset, len, mode);
		btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
		return ret;
	}

	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(BTRFS_I(inode),
							    locked_end);

		if (ordered &&
		    ordered->file_offset + ordered->num_bytes > 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);
			/*
			 * 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 (cur_offset < alloc_end) {
		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
				      alloc_end - cur_offset);
		if (IS_ERR(em)) {
			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(BTRFS_I(inode),
					&data_reserved, cur_offset,
					last_byte - cur_offset);
			if (ret < 0) {
				cur_offset = last_byte;
				free_extent_map(em);
				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(BTRFS_I(inode),
				data_reserved, cur_offset,
				last_byte - cur_offset);
		}
		free_extent_map(em);
		cur_offset = last_byte;
	}

	/*
	 * 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, i_blocksize(inode),
					offset + len, &alloc_hint);
		else
			btrfs_free_reserved_data_space(BTRFS_I(inode),
					data_reserved, range->start,
					range->len);
		list_del(&range->list);
		kfree(range);
	}
	if (ret < 0)
		goto out_unlock;

	/*
	 * 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.
	 */
	ret = btrfs_fallocate_update_isize(inode, actual_end, mode);
out_unlock:
	unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
			     &cached_state);
out:
	btrfs_inode_unlock(inode, BTRFS_ILOCK_MMAP);
	/* Let go of our reservation. */
	if (ret != 0 && !(mode & FALLOC_FL_ZERO_RANGE))
		btrfs_free_reserved_data_space(BTRFS_I(inode), data_reserved,
				cur_offset, alloc_end - cur_offset);
	extent_changeset_free(data_reserved);
	return ret;
}

static loff_t find_desired_extent(struct btrfs_inode *inode, loff_t offset,
				  int whence)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct extent_map *em = NULL;
	struct extent_state *cached_state = NULL;
	loff_t i_size = inode->vfs_inode.i_size;
	u64 lockstart;
	u64 lockend;
	u64 start;
	u64 len;
	int ret = 0;

	if (i_size == 0 || offset >= i_size)
		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, fs_info->sectorsize);
	lockend = round_up(i_size, fs_info->sectorsize);
	if (lockend <= lockstart)
		lockend = lockstart + fs_info->sectorsize;
	lockend--;
	len = lockend - lockstart + 1;

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

	while (start < i_size) {
		em = btrfs_get_extent_fiemap(inode, start, len);
		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);
	unlock_extent_cached(&inode->io_tree, lockstart, lockend,
			     &cached_state);
	if (ret) {
		offset = ret;
	} else {
		if (whence == SEEK_DATA && start >= i_size)
			offset = -ENXIO;
		else
			offset = min_t(loff_t, start, i_size);
	}

	return offset;
}

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

	switch (whence) {
	default:
		return generic_file_llseek(file, offset, whence);
	case SEEK_DATA:
	case SEEK_HOLE:
		btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
		offset = find_desired_extent(BTRFS_I(inode), offset, whence);
		btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
		break;
	}

	if (offset < 0)
		return offset;

	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
}

static int btrfs_file_open(struct inode *inode, struct file *filp)
{
	int ret;

	filp->f_mode |= FMODE_NOWAIT | FMODE_BUF_RASYNC;

	ret = fsverity_file_open(inode, filp);
	if (ret)
		return ret;
	return generic_file_open(inode, filp);
}

static int check_direct_read(struct btrfs_fs_info *fs_info,
			     const struct iov_iter *iter, loff_t offset)
{
	int ret;
	int i, seg;

	ret = check_direct_IO(fs_info, iter, offset);
	if (ret < 0)
		return ret;

	if (!iter_is_iovec(iter))
		return 0;

	for (seg = 0; seg < iter->nr_segs; seg++)
		for (i = seg + 1; i < iter->nr_segs; i++)
			if (iter->iov[seg].iov_base == iter->iov[i].iov_base)
				return -EINVAL;
	return 0;
}

static ssize_t btrfs_direct_read(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	size_t prev_left = 0;
	ssize_t read = 0;
	ssize_t ret;

	if (fsverity_active(inode))
		return 0;

	if (check_direct_read(btrfs_sb(inode->i_sb), to, iocb->ki_pos))
		return 0;

	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);
again:
	/*
	 * This is similar to what we do for direct IO writes, see the comment
	 * at btrfs_direct_write(), but we also disable page faults in addition
	 * to disabling them only at the iov_iter level. This is because when
	 * reading from a hole or prealloc extent, iomap calls iov_iter_zero(),
	 * which can still trigger page fault ins despite having set ->nofault
	 * to true of our 'to' iov_iter.
	 *
	 * The difference to direct IO writes is that we deadlock when trying
	 * to lock the extent range in the inode's tree during he page reads
	 * triggered by the fault in (while for writes it is due to waiting for
	 * our own ordered extent). This is because for direct IO reads,
	 * btrfs_dio_iomap_begin() returns with the extent range locked, which
	 * is only unlocked in the endio callback (end_bio_extent_readpage()).
	 */
	pagefault_disable();
	to->nofault = true;
	ret = iomap_dio_rw(iocb, to, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
			   IOMAP_DIO_PARTIAL, read);
	to->nofault = false;
	pagefault_enable();

	/* No increment (+=) because iomap returns a cumulative value. */
	if (ret > 0)
		read = ret;

	if (iov_iter_count(to) > 0 && (ret == -EFAULT || ret > 0)) {
		const size_t left = iov_iter_count(to);

		if (left == prev_left) {
			/*
			 * We didn't make any progress since the last attempt,
			 * fallback to a buffered read for the remainder of the
			 * range. This is just to avoid any possibility of looping
			 * for too long.
			 */
			ret = read;
		} else {
			/*
			 * We made some progress since the last retry or this is
			 * the first time we are retrying. Fault in as many pages
			 * as possible and retry.
			 */
			fault_in_iov_iter_writeable(to, left);
			prev_left = left;
			goto again;
		}
	}
	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
	return ret < 0 ? ret : read;
}

static ssize_t btrfs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	ssize_t ret = 0;

	if (iocb->ki_flags & IOCB_DIRECT) {
		ret = btrfs_direct_read(iocb, to);
		if (ret < 0 || !iov_iter_count(to) ||
		    iocb->ki_pos >= i_size_read(file_inode(iocb->ki_filp)))
			return ret;
	}

	return filemap_read(iocb, to, ret);
}

const struct file_operations btrfs_file_operations = {
	.llseek		= btrfs_file_llseek,
	.read_iter      = btrfs_file_read_iter,
	.splice_read	= generic_file_splice_read,
	.write_iter	= btrfs_file_write_iter,
	.splice_write	= iter_file_splice_write,
	.mmap		= btrfs_file_mmap,
	.open		= btrfs_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
	.remap_file_range = btrfs_remap_file_range,
};

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

int __init 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;
}