summaryrefslogtreecommitdiff
path: root/fs/btrfs/inode.c
blob: f88e0ca8331d9b5448e8e07c89e5e66395c782b3 (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
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <crypto/hash.h>
#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/blk-cgroup.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/writeback.h>
#include <linux/compat.h>
#include <linux/xattr.h>
#include <linux/posix_acl.h>
#include <linux/falloc.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/btrfs.h>
#include <linux/blkdev.h>
#include <linux/posix_acl_xattr.h>
#include <linux/uio.h>
#include <linux/magic.h>
#include <linux/iversion.h>
#include <linux/swap.h>
#include <linux/migrate.h>
#include <linux/sched/mm.h>
#include <linux/iomap.h>
#include <asm/unaligned.h>
#include <linux/fsverity.h>
#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "ordered-data.h"
#include "xattr.h"
#include "tree-log.h"
#include "bio.h"
#include "compression.h"
#include "locking.h"
#include "free-space-cache.h"
#include "props.h"
#include "qgroup.h"
#include "delalloc-space.h"
#include "block-group.h"
#include "space-info.h"
#include "zoned.h"
#include "subpage.h"
#include "inode-item.h"
#include "fs.h"
#include "accessors.h"
#include "extent-tree.h"
#include "root-tree.h"
#include "defrag.h"
#include "dir-item.h"
#include "file-item.h"
#include "uuid-tree.h"
#include "ioctl.h"
#include "file.h"
#include "acl.h"
#include "relocation.h"
#include "verity.h"
#include "super.h"
#include "orphan.h"
#include "backref.h"
#include "raid-stripe-tree.h"

struct btrfs_iget_args {
	u64 ino;
	struct btrfs_root *root;
};

struct btrfs_dio_data {
	ssize_t submitted;
	struct extent_changeset *data_reserved;
	struct btrfs_ordered_extent *ordered;
	bool data_space_reserved;
	bool nocow_done;
};

struct btrfs_dio_private {
	/* Range of I/O */
	u64 file_offset;
	u32 bytes;

	/* This must be last */
	struct btrfs_bio bbio;
};

static struct bio_set btrfs_dio_bioset;

struct btrfs_rename_ctx {
	/* Output field. Stores the index number of the old directory entry. */
	u64 index;
};

/*
 * Used by data_reloc_print_warning_inode() to pass needed info for filename
 * resolution and output of error message.
 */
struct data_reloc_warn {
	struct btrfs_path path;
	struct btrfs_fs_info *fs_info;
	u64 extent_item_size;
	u64 logical;
	int mirror_num;
};

/*
 * For the file_extent_tree, we want to hold the inode lock when we lookup and
 * update the disk_i_size, but lockdep will complain because our io_tree we hold
 * the tree lock and get the inode lock when setting delalloc. These two things
 * are unrelated, so make a class for the file_extent_tree so we don't get the
 * two locking patterns mixed up.
 */
static struct lock_class_key file_extent_tree_class;

static const struct inode_operations btrfs_dir_inode_operations;
static const struct inode_operations btrfs_symlink_inode_operations;
static const struct inode_operations btrfs_special_inode_operations;
static const struct inode_operations btrfs_file_inode_operations;
static const struct address_space_operations btrfs_aops;
static const struct file_operations btrfs_dir_file_operations;

static struct kmem_cache *btrfs_inode_cachep;

static int btrfs_setsize(struct inode *inode, struct iattr *attr);
static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback);

static noinline int run_delalloc_cow(struct btrfs_inode *inode,
				     struct page *locked_page, u64 start,
				     u64 end, struct writeback_control *wbc,
				     bool pages_dirty);
static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
				       u64 len, u64 orig_start, u64 block_start,
				       u64 block_len, u64 orig_block_len,
				       u64 ram_bytes, int compress_type,
				       int type);

static int data_reloc_print_warning_inode(u64 inum, u64 offset, u64 num_bytes,
					  u64 root, void *warn_ctx)
{
	struct data_reloc_warn *warn = warn_ctx;
	struct btrfs_fs_info *fs_info = warn->fs_info;
	struct extent_buffer *eb;
	struct btrfs_inode_item *inode_item;
	struct inode_fs_paths *ipath = NULL;
	struct btrfs_root *local_root;
	struct btrfs_key key;
	unsigned int nofs_flag;
	u32 nlink;
	int ret;

	local_root = btrfs_get_fs_root(fs_info, root, true);
	if (IS_ERR(local_root)) {
		ret = PTR_ERR(local_root);
		goto err;
	}

	/* This makes the path point to (inum INODE_ITEM ioff). */
	key.objectid = inum;
	key.type = BTRFS_INODE_ITEM_KEY;
	key.offset = 0;

	ret = btrfs_search_slot(NULL, local_root, &key, &warn->path, 0, 0);
	if (ret) {
		btrfs_put_root(local_root);
		btrfs_release_path(&warn->path);
		goto err;
	}

	eb = warn->path.nodes[0];
	inode_item = btrfs_item_ptr(eb, warn->path.slots[0], struct btrfs_inode_item);
	nlink = btrfs_inode_nlink(eb, inode_item);
	btrfs_release_path(&warn->path);

	nofs_flag = memalloc_nofs_save();
	ipath = init_ipath(4096, local_root, &warn->path);
	memalloc_nofs_restore(nofs_flag);
	if (IS_ERR(ipath)) {
		btrfs_put_root(local_root);
		ret = PTR_ERR(ipath);
		ipath = NULL;
		/*
		 * -ENOMEM, not a critical error, just output an generic error
		 * without filename.
		 */
		btrfs_warn(fs_info,
"checksum error at logical %llu mirror %u root %llu, inode %llu offset %llu",
			   warn->logical, warn->mirror_num, root, inum, offset);
		return ret;
	}
	ret = paths_from_inode(inum, ipath);
	if (ret < 0)
		goto err;

	/*
	 * We deliberately ignore the bit ipath might have been too small to
	 * hold all of the paths here
	 */
	for (int i = 0; i < ipath->fspath->elem_cnt; i++) {
		btrfs_warn(fs_info,
"checksum error at logical %llu mirror %u root %llu inode %llu offset %llu length %u links %u (path: %s)",
			   warn->logical, warn->mirror_num, root, inum, offset,
			   fs_info->sectorsize, nlink,
			   (char *)(unsigned long)ipath->fspath->val[i]);
	}

	btrfs_put_root(local_root);
	free_ipath(ipath);
	return 0;

err:
	btrfs_warn(fs_info,
"checksum error at logical %llu mirror %u root %llu inode %llu offset %llu, path resolving failed with ret=%d",
		   warn->logical, warn->mirror_num, root, inum, offset, ret);

	free_ipath(ipath);
	return ret;
}

/*
 * Do extra user-friendly error output (e.g. lookup all the affected files).
 *
 * Return true if we succeeded doing the backref lookup.
 * Return false if such lookup failed, and has to fallback to the old error message.
 */
static void print_data_reloc_error(const struct btrfs_inode *inode, u64 file_off,
				   const u8 *csum, const u8 *csum_expected,
				   int mirror_num)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct btrfs_path path = { 0 };
	struct btrfs_key found_key = { 0 };
	struct extent_buffer *eb;
	struct btrfs_extent_item *ei;
	const u32 csum_size = fs_info->csum_size;
	u64 logical;
	u64 flags;
	u32 item_size;
	int ret;

	mutex_lock(&fs_info->reloc_mutex);
	logical = btrfs_get_reloc_bg_bytenr(fs_info);
	mutex_unlock(&fs_info->reloc_mutex);

	if (logical == U64_MAX) {
		btrfs_warn_rl(fs_info, "has data reloc tree but no running relocation");
		btrfs_warn_rl(fs_info,
"csum failed root %lld ino %llu off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
			inode->root->root_key.objectid, btrfs_ino(inode), file_off,
			CSUM_FMT_VALUE(csum_size, csum),
			CSUM_FMT_VALUE(csum_size, csum_expected),
			mirror_num);
		return;
	}

	logical += file_off;
	btrfs_warn_rl(fs_info,
"csum failed root %lld ino %llu off %llu logical %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
			inode->root->root_key.objectid,
			btrfs_ino(inode), file_off, logical,
			CSUM_FMT_VALUE(csum_size, csum),
			CSUM_FMT_VALUE(csum_size, csum_expected),
			mirror_num);

	ret = extent_from_logical(fs_info, logical, &path, &found_key, &flags);
	if (ret < 0) {
		btrfs_err_rl(fs_info, "failed to lookup extent item for logical %llu: %d",
			     logical, ret);
		return;
	}
	eb = path.nodes[0];
	ei = btrfs_item_ptr(eb, path.slots[0], struct btrfs_extent_item);
	item_size = btrfs_item_size(eb, path.slots[0]);
	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
		unsigned long ptr = 0;
		u64 ref_root;
		u8 ref_level;

		while (true) {
			ret = tree_backref_for_extent(&ptr, eb, &found_key, ei,
						      item_size, &ref_root,
						      &ref_level);
			if (ret < 0) {
				btrfs_warn_rl(fs_info,
				"failed to resolve tree backref for logical %llu: %d",
					      logical, ret);
				break;
			}
			if (ret > 0)
				break;

			btrfs_warn_rl(fs_info,
"csum error at logical %llu mirror %u: metadata %s (level %d) in tree %llu",
				logical, mirror_num,
				(ref_level ? "node" : "leaf"),
				ref_level, ref_root);
		}
		btrfs_release_path(&path);
	} else {
		struct btrfs_backref_walk_ctx ctx = { 0 };
		struct data_reloc_warn reloc_warn = { 0 };

		btrfs_release_path(&path);

		ctx.bytenr = found_key.objectid;
		ctx.extent_item_pos = logical - found_key.objectid;
		ctx.fs_info = fs_info;

		reloc_warn.logical = logical;
		reloc_warn.extent_item_size = found_key.offset;
		reloc_warn.mirror_num = mirror_num;
		reloc_warn.fs_info = fs_info;

		iterate_extent_inodes(&ctx, true,
				      data_reloc_print_warning_inode, &reloc_warn);
	}
}

static void __cold btrfs_print_data_csum_error(struct btrfs_inode *inode,
		u64 logical_start, u8 *csum, u8 *csum_expected, int mirror_num)
{
	struct btrfs_root *root = inode->root;
	const u32 csum_size = root->fs_info->csum_size;

	/* For data reloc tree, it's better to do a backref lookup instead. */
	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
		return print_data_reloc_error(inode, logical_start, csum,
					      csum_expected, mirror_num);

	/* Output without objectid, which is more meaningful */
	if (root->root_key.objectid >= BTRFS_LAST_FREE_OBJECTID) {
		btrfs_warn_rl(root->fs_info,
"csum failed root %lld ino %lld off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
			root->root_key.objectid, btrfs_ino(inode),
			logical_start,
			CSUM_FMT_VALUE(csum_size, csum),
			CSUM_FMT_VALUE(csum_size, csum_expected),
			mirror_num);
	} else {
		btrfs_warn_rl(root->fs_info,
"csum failed root %llu ino %llu off %llu csum " CSUM_FMT " expected csum " CSUM_FMT " mirror %d",
			root->root_key.objectid, btrfs_ino(inode),
			logical_start,
			CSUM_FMT_VALUE(csum_size, csum),
			CSUM_FMT_VALUE(csum_size, csum_expected),
			mirror_num);
	}
}

/*
 * Lock inode i_rwsem based on arguments passed.
 *
 * ilock_flags can have the following bit set:
 *
 * BTRFS_ILOCK_SHARED - acquire a shared lock on the inode
 * BTRFS_ILOCK_TRY - try to acquire the lock, if fails on first attempt
 *		     return -EAGAIN
 * BTRFS_ILOCK_MMAP - acquire a write lock on the i_mmap_lock
 */
int btrfs_inode_lock(struct btrfs_inode *inode, unsigned int ilock_flags)
{
	if (ilock_flags & BTRFS_ILOCK_SHARED) {
		if (ilock_flags & BTRFS_ILOCK_TRY) {
			if (!inode_trylock_shared(&inode->vfs_inode))
				return -EAGAIN;
			else
				return 0;
		}
		inode_lock_shared(&inode->vfs_inode);
	} else {
		if (ilock_flags & BTRFS_ILOCK_TRY) {
			if (!inode_trylock(&inode->vfs_inode))
				return -EAGAIN;
			else
				return 0;
		}
		inode_lock(&inode->vfs_inode);
	}
	if (ilock_flags & BTRFS_ILOCK_MMAP)
		down_write(&inode->i_mmap_lock);
	return 0;
}

/*
 * Unock inode i_rwsem.
 *
 * ilock_flags should contain the same bits set as passed to btrfs_inode_lock()
 * to decide whether the lock acquired is shared or exclusive.
 */
void btrfs_inode_unlock(struct btrfs_inode *inode, unsigned int ilock_flags)
{
	if (ilock_flags & BTRFS_ILOCK_MMAP)
		up_write(&inode->i_mmap_lock);
	if (ilock_flags & BTRFS_ILOCK_SHARED)
		inode_unlock_shared(&inode->vfs_inode);
	else
		inode_unlock(&inode->vfs_inode);
}

/*
 * Cleanup all submitted ordered extents in specified range to handle errors
 * from the btrfs_run_delalloc_range() callback.
 *
 * NOTE: caller must ensure that when an error happens, it can not call
 * extent_clear_unlock_delalloc() to clear both the bits EXTENT_DO_ACCOUNTING
 * and EXTENT_DELALLOC simultaneously, because that causes the reserved metadata
 * to be released, which we want to happen only when finishing the ordered
 * extent (btrfs_finish_ordered_io()).
 */
static inline void btrfs_cleanup_ordered_extents(struct btrfs_inode *inode,
						 struct page *locked_page,
						 u64 offset, u64 bytes)
{
	unsigned long index = offset >> PAGE_SHIFT;
	unsigned long end_index = (offset + bytes - 1) >> PAGE_SHIFT;
	u64 page_start = 0, page_end = 0;
	struct page *page;

	if (locked_page) {
		page_start = page_offset(locked_page);
		page_end = page_start + PAGE_SIZE - 1;
	}

	while (index <= end_index) {
		/*
		 * For locked page, we will call btrfs_mark_ordered_io_finished
		 * through btrfs_mark_ordered_io_finished() on it
		 * in run_delalloc_range() for the error handling, which will
		 * clear page Ordered and run the ordered extent accounting.
		 *
		 * Here we can't just clear the Ordered bit, or
		 * btrfs_mark_ordered_io_finished() would skip the accounting
		 * for the page range, and the ordered extent will never finish.
		 */
		if (locked_page && index == (page_start >> PAGE_SHIFT)) {
			index++;
			continue;
		}
		page = find_get_page(inode->vfs_inode.i_mapping, index);
		index++;
		if (!page)
			continue;

		/*
		 * Here we just clear all Ordered bits for every page in the
		 * range, then btrfs_mark_ordered_io_finished() will handle
		 * the ordered extent accounting for the range.
		 */
		btrfs_folio_clamp_clear_ordered(inode->root->fs_info,
						page_folio(page), offset, bytes);
		put_page(page);
	}

	if (locked_page) {
		/* The locked page covers the full range, nothing needs to be done */
		if (bytes + offset <= page_start + PAGE_SIZE)
			return;
		/*
		 * In case this page belongs to the delalloc range being
		 * instantiated then skip it, since the first page of a range is
		 * going to be properly cleaned up by the caller of
		 * run_delalloc_range
		 */
		if (page_start >= offset && page_end <= (offset + bytes - 1)) {
			bytes = offset + bytes - page_offset(locked_page) - PAGE_SIZE;
			offset = page_offset(locked_page) + PAGE_SIZE;
		}
	}

	return btrfs_mark_ordered_io_finished(inode, NULL, offset, bytes, false);
}

static int btrfs_dirty_inode(struct btrfs_inode *inode);

static int btrfs_init_inode_security(struct btrfs_trans_handle *trans,
				     struct btrfs_new_inode_args *args)
{
	int err;

	if (args->default_acl) {
		err = __btrfs_set_acl(trans, args->inode, args->default_acl,
				      ACL_TYPE_DEFAULT);
		if (err)
			return err;
	}
	if (args->acl) {
		err = __btrfs_set_acl(trans, args->inode, args->acl, ACL_TYPE_ACCESS);
		if (err)
			return err;
	}
	if (!args->default_acl && !args->acl)
		cache_no_acl(args->inode);
	return btrfs_xattr_security_init(trans, args->inode, args->dir,
					 &args->dentry->d_name);
}

/*
 * this does all the hard work for inserting an inline extent into
 * the btree.  The caller should have done a btrfs_drop_extents so that
 * no overlapping inline items exist in the btree
 */
static int insert_inline_extent(struct btrfs_trans_handle *trans,
				struct btrfs_path *path,
				struct btrfs_inode *inode, bool extent_inserted,
				size_t size, size_t compressed_size,
				int compress_type,
				struct page **compressed_pages,
				bool update_i_size)
{
	struct btrfs_root *root = inode->root;
	struct extent_buffer *leaf;
	struct page *page = NULL;
	char *kaddr;
	unsigned long ptr;
	struct btrfs_file_extent_item *ei;
	int ret;
	size_t cur_size = size;
	u64 i_size;

	ASSERT((compressed_size > 0 && compressed_pages) ||
	       (compressed_size == 0 && !compressed_pages));

	if (compressed_size && compressed_pages)
		cur_size = compressed_size;

	if (!extent_inserted) {
		struct btrfs_key key;
		size_t datasize;

		key.objectid = btrfs_ino(inode);
		key.offset = 0;
		key.type = BTRFS_EXTENT_DATA_KEY;

		datasize = btrfs_file_extent_calc_inline_size(cur_size);
		ret = btrfs_insert_empty_item(trans, root, path, &key,
					      datasize);
		if (ret)
			goto fail;
	}
	leaf = path->nodes[0];
	ei = btrfs_item_ptr(leaf, path->slots[0],
			    struct btrfs_file_extent_item);
	btrfs_set_file_extent_generation(leaf, ei, trans->transid);
	btrfs_set_file_extent_type(leaf, ei, BTRFS_FILE_EXTENT_INLINE);
	btrfs_set_file_extent_encryption(leaf, ei, 0);
	btrfs_set_file_extent_other_encoding(leaf, ei, 0);
	btrfs_set_file_extent_ram_bytes(leaf, ei, size);
	ptr = btrfs_file_extent_inline_start(ei);

	if (compress_type != BTRFS_COMPRESS_NONE) {
		struct page *cpage;
		int i = 0;
		while (compressed_size > 0) {
			cpage = compressed_pages[i];
			cur_size = min_t(unsigned long, compressed_size,
				       PAGE_SIZE);

			kaddr = kmap_local_page(cpage);
			write_extent_buffer(leaf, kaddr, ptr, cur_size);
			kunmap_local(kaddr);

			i++;
			ptr += cur_size;
			compressed_size -= cur_size;
		}
		btrfs_set_file_extent_compression(leaf, ei,
						  compress_type);
	} else {
		page = find_get_page(inode->vfs_inode.i_mapping, 0);
		btrfs_set_file_extent_compression(leaf, ei, 0);
		kaddr = kmap_local_page(page);
		write_extent_buffer(leaf, kaddr, ptr, size);
		kunmap_local(kaddr);
		put_page(page);
	}
	btrfs_mark_buffer_dirty(trans, leaf);
	btrfs_release_path(path);

	/*
	 * We align size to sectorsize for inline extents just for simplicity
	 * sake.
	 */
	ret = btrfs_inode_set_file_extent_range(inode, 0,
					ALIGN(size, root->fs_info->sectorsize));
	if (ret)
		goto fail;

	/*
	 * We're an inline extent, so nobody can extend the file past i_size
	 * without locking a page we already have locked.
	 *
	 * We must do any i_size and inode updates before we unlock the pages.
	 * Otherwise we could end up racing with unlink.
	 */
	i_size = i_size_read(&inode->vfs_inode);
	if (update_i_size && size > i_size) {
		i_size_write(&inode->vfs_inode, size);
		i_size = size;
	}
	inode->disk_i_size = i_size;

fail:
	return ret;
}


/*
 * conditionally insert an inline extent into the file.  This
 * does the checks required to make sure the data is small enough
 * to fit as an inline extent.
 */
static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 size,
					  size_t compressed_size,
					  int compress_type,
					  struct page **compressed_pages,
					  bool update_i_size)
{
	struct btrfs_drop_extents_args drop_args = { 0 };
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	u64 data_len = (compressed_size ?: size);
	int ret;
	struct btrfs_path *path;

	/*
	 * We can create an inline extent if it ends at or beyond the current
	 * i_size, is no larger than a sector (decompressed), and the (possibly
	 * compressed) data fits in a leaf and the configured maximum inline
	 * size.
	 */
	if (size < i_size_read(&inode->vfs_inode) ||
	    size > fs_info->sectorsize ||
	    data_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info) ||
	    data_len > fs_info->max_inline)
		return 1;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	trans = btrfs_join_transaction(root);
	if (IS_ERR(trans)) {
		btrfs_free_path(path);
		return PTR_ERR(trans);
	}
	trans->block_rsv = &inode->block_rsv;

	drop_args.path = path;
	drop_args.start = 0;
	drop_args.end = fs_info->sectorsize;
	drop_args.drop_cache = true;
	drop_args.replace_extent = true;
	drop_args.extent_item_size = btrfs_file_extent_calc_inline_size(data_len);
	ret = btrfs_drop_extents(trans, root, inode, &drop_args);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	ret = insert_inline_extent(trans, path, inode, drop_args.extent_inserted,
				   size, compressed_size, compress_type,
				   compressed_pages, update_i_size);
	if (ret && ret != -ENOSPC) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	} else if (ret == -ENOSPC) {
		ret = 1;
		goto out;
	}

	btrfs_update_inode_bytes(inode, size, drop_args.bytes_found);
	ret = btrfs_update_inode(trans, inode);
	if (ret && ret != -ENOSPC) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	} else if (ret == -ENOSPC) {
		ret = 1;
		goto out;
	}

	btrfs_set_inode_full_sync(inode);
out:
	/*
	 * Don't forget to free the reserved space, as for inlined extent
	 * it won't count as data extent, free them directly here.
	 * And at reserve time, it's always aligned to page size, so
	 * just free one page here.
	 */
	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE, NULL);
	btrfs_free_path(path);
	btrfs_end_transaction(trans);
	return ret;
}

struct async_extent {
	u64 start;
	u64 ram_size;
	u64 compressed_size;
	struct page **pages;
	unsigned long nr_pages;
	int compress_type;
	struct list_head list;
};

struct async_chunk {
	struct btrfs_inode *inode;
	struct page *locked_page;
	u64 start;
	u64 end;
	blk_opf_t write_flags;
	struct list_head extents;
	struct cgroup_subsys_state *blkcg_css;
	struct btrfs_work work;
	struct async_cow *async_cow;
};

struct async_cow {
	atomic_t num_chunks;
	struct async_chunk chunks[];
};

static noinline int add_async_extent(struct async_chunk *cow,
				     u64 start, u64 ram_size,
				     u64 compressed_size,
				     struct page **pages,
				     unsigned long nr_pages,
				     int compress_type)
{
	struct async_extent *async_extent;

	async_extent = kmalloc(sizeof(*async_extent), GFP_NOFS);
	BUG_ON(!async_extent); /* -ENOMEM */
	async_extent->start = start;
	async_extent->ram_size = ram_size;
	async_extent->compressed_size = compressed_size;
	async_extent->pages = pages;
	async_extent->nr_pages = nr_pages;
	async_extent->compress_type = compress_type;
	list_add_tail(&async_extent->list, &cow->extents);
	return 0;
}

/*
 * Check if the inode needs to be submitted to compression, based on mount
 * options, defragmentation, properties or heuristics.
 */
static inline int inode_need_compress(struct btrfs_inode *inode, u64 start,
				      u64 end)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;

	if (!btrfs_inode_can_compress(inode)) {
		WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
			KERN_ERR "BTRFS: unexpected compression for ino %llu\n",
			btrfs_ino(inode));
		return 0;
	}
	/*
	 * Special check for subpage.
	 *
	 * We lock the full page then run each delalloc range in the page, thus
	 * for the following case, we will hit some subpage specific corner case:
	 *
	 * 0		32K		64K
	 * |	|///////|	|///////|
	 *		\- A		\- B
	 *
	 * In above case, both range A and range B will try to unlock the full
	 * page [0, 64K), causing the one finished later will have page
	 * unlocked already, triggering various page lock requirement BUG_ON()s.
	 *
	 * So here we add an artificial limit that subpage compression can only
	 * if the range is fully page aligned.
	 *
	 * In theory we only need to ensure the first page is fully covered, but
	 * the tailing partial page will be locked until the full compression
	 * finishes, delaying the write of other range.
	 *
	 * TODO: Make btrfs_run_delalloc_range() to lock all delalloc range
	 * first to prevent any submitted async extent to unlock the full page.
	 * By this, we can ensure for subpage case that only the last async_cow
	 * will unlock the full page.
	 */
	if (fs_info->sectorsize < PAGE_SIZE) {
		if (!PAGE_ALIGNED(start) ||
		    !PAGE_ALIGNED(end + 1))
			return 0;
	}

	/* force compress */
	if (btrfs_test_opt(fs_info, FORCE_COMPRESS))
		return 1;
	/* defrag ioctl */
	if (inode->defrag_compress)
		return 1;
	/* bad compression ratios */
	if (inode->flags & BTRFS_INODE_NOCOMPRESS)
		return 0;
	if (btrfs_test_opt(fs_info, COMPRESS) ||
	    inode->flags & BTRFS_INODE_COMPRESS ||
	    inode->prop_compress)
		return btrfs_compress_heuristic(&inode->vfs_inode, start, end);
	return 0;
}

static inline void inode_should_defrag(struct btrfs_inode *inode,
		u64 start, u64 end, u64 num_bytes, u32 small_write)
{
	/* If this is a small write inside eof, kick off a defrag */
	if (num_bytes < small_write &&
	    (start > 0 || end + 1 < inode->disk_i_size))
		btrfs_add_inode_defrag(NULL, inode, small_write);
}

/*
 * Work queue call back to started compression on a file and pages.
 *
 * This is done inside an ordered work queue, and the compression is spread
 * across many cpus.  The actual IO submission is step two, and the ordered work
 * queue takes care of making sure that happens in the same order things were
 * put onto the queue by writepages and friends.
 *
 * If this code finds it can't get good compression, it puts an entry onto the
 * work queue to write the uncompressed bytes.  This makes sure that both
 * compressed inodes and uncompressed inodes are written in the same order that
 * the flusher thread sent them down.
 */
static void compress_file_range(struct btrfs_work *work)
{
	struct async_chunk *async_chunk =
		container_of(work, struct async_chunk, work);
	struct btrfs_inode *inode = async_chunk->inode;
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct address_space *mapping = inode->vfs_inode.i_mapping;
	u64 blocksize = fs_info->sectorsize;
	u64 start = async_chunk->start;
	u64 end = async_chunk->end;
	u64 actual_end;
	u64 i_size;
	int ret = 0;
	struct page **pages;
	unsigned long nr_pages;
	unsigned long total_compressed = 0;
	unsigned long total_in = 0;
	unsigned int poff;
	int i;
	int compress_type = fs_info->compress_type;

	inode_should_defrag(inode, start, end, end - start + 1, SZ_16K);

	/*
	 * We need to call clear_page_dirty_for_io on each page in the range.
	 * Otherwise applications with the file mmap'd can wander in and change
	 * the page contents while we are compressing them.
	 */
	extent_range_clear_dirty_for_io(&inode->vfs_inode, start, end);

	/*
	 * We need to save i_size before now because it could change in between
	 * us evaluating the size and assigning it.  This is because we lock and
	 * unlock the page in truncate and fallocate, and then modify the i_size
	 * later on.
	 *
	 * The barriers are to emulate READ_ONCE, remove that once i_size_read
	 * does that for us.
	 */
	barrier();
	i_size = i_size_read(&inode->vfs_inode);
	barrier();
	actual_end = min_t(u64, i_size, end + 1);
again:
	pages = NULL;
	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
	nr_pages = min_t(unsigned long, nr_pages, BTRFS_MAX_COMPRESSED_PAGES);

	/*
	 * we don't want to send crud past the end of i_size through
	 * compression, that's just a waste of CPU time.  So, if the
	 * end of the file is before the start of our current
	 * requested range of bytes, we bail out to the uncompressed
	 * cleanup code that can deal with all of this.
	 *
	 * It isn't really the fastest way to fix things, but this is a
	 * very uncommon corner.
	 */
	if (actual_end <= start)
		goto cleanup_and_bail_uncompressed;

	total_compressed = actual_end - start;

	/*
	 * Skip compression for a small file range(<=blocksize) that
	 * isn't an inline extent, since it doesn't save disk space at all.
	 */
	if (total_compressed <= blocksize &&
	   (start > 0 || end + 1 < inode->disk_i_size))
		goto cleanup_and_bail_uncompressed;

	/*
	 * For subpage case, we require full page alignment for the sector
	 * aligned range.
	 * Thus we must also check against @actual_end, not just @end.
	 */
	if (blocksize < PAGE_SIZE) {
		if (!PAGE_ALIGNED(start) ||
		    !PAGE_ALIGNED(round_up(actual_end, blocksize)))
			goto cleanup_and_bail_uncompressed;
	}

	total_compressed = min_t(unsigned long, total_compressed,
			BTRFS_MAX_UNCOMPRESSED);
	total_in = 0;
	ret = 0;

	/*
	 * We do compression for mount -o compress and when the inode has not
	 * been flagged as NOCOMPRESS.  This flag can change at any time if we
	 * discover bad compression ratios.
	 */
	if (!inode_need_compress(inode, start, end))
		goto cleanup_and_bail_uncompressed;

	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
	if (!pages) {
		/*
		 * Memory allocation failure is not a fatal error, we can fall
		 * back to uncompressed code.
		 */
		goto cleanup_and_bail_uncompressed;
	}

	if (inode->defrag_compress)
		compress_type = inode->defrag_compress;
	else if (inode->prop_compress)
		compress_type = inode->prop_compress;

	/* Compression level is applied here. */
	ret = btrfs_compress_pages(compress_type | (fs_info->compress_level << 4),
				   mapping, start, pages, &nr_pages, &total_in,
				   &total_compressed);
	if (ret)
		goto mark_incompressible;

	/*
	 * Zero the tail end of the last page, as we might be sending it down
	 * to disk.
	 */
	poff = offset_in_page(total_compressed);
	if (poff)
		memzero_page(pages[nr_pages - 1], poff, PAGE_SIZE - poff);

	/*
	 * Try to create an inline extent.
	 *
	 * If we didn't compress the entire range, try to create an uncompressed
	 * inline extent, else a compressed one.
	 *
	 * Check cow_file_range() for why we don't even try to create inline
	 * extent for the subpage case.
	 */
	if (start == 0 && fs_info->sectorsize == PAGE_SIZE) {
		if (total_in < actual_end) {
			ret = cow_file_range_inline(inode, actual_end, 0,
						    BTRFS_COMPRESS_NONE, NULL,
						    false);
		} else {
			ret = cow_file_range_inline(inode, actual_end,
						    total_compressed,
						    compress_type, pages,
						    false);
		}
		if (ret <= 0) {
			unsigned long clear_flags = EXTENT_DELALLOC |
				EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
				EXTENT_DO_ACCOUNTING;

			if (ret < 0)
				mapping_set_error(mapping, -EIO);

			/*
			 * inline extent creation worked or returned error,
			 * we don't need to create any more async work items.
			 * Unlock and free up our temp pages.
			 *
			 * We use DO_ACCOUNTING here because we need the
			 * delalloc_release_metadata to be done _after_ we drop
			 * our outstanding extent for clearing delalloc for this
			 * range.
			 */
			extent_clear_unlock_delalloc(inode, start, end,
						     NULL,
						     clear_flags,
						     PAGE_UNLOCK |
						     PAGE_START_WRITEBACK |
						     PAGE_END_WRITEBACK);
			goto free_pages;
		}
	}

	/*
	 * We aren't doing an inline extent. Round the compressed size up to a
	 * block size boundary so the allocator does sane things.
	 */
	total_compressed = ALIGN(total_compressed, blocksize);

	/*
	 * One last check to make sure the compression is really a win, compare
	 * the page count read with the blocks on disk, compression must free at
	 * least one sector.
	 */
	total_in = round_up(total_in, fs_info->sectorsize);
	if (total_compressed + blocksize > total_in)
		goto mark_incompressible;

	/*
	 * The async work queues will take care of doing actual allocation on
	 * disk for these compressed pages, and will submit the bios.
	 */
	add_async_extent(async_chunk, start, total_in, total_compressed, pages,
			 nr_pages, compress_type);
	if (start + total_in < end) {
		start += total_in;
		cond_resched();
		goto again;
	}
	return;

mark_incompressible:
	if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) && !inode->prop_compress)
		inode->flags |= BTRFS_INODE_NOCOMPRESS;
cleanup_and_bail_uncompressed:
	add_async_extent(async_chunk, start, end - start + 1, 0, NULL, 0,
			 BTRFS_COMPRESS_NONE);
free_pages:
	if (pages) {
		for (i = 0; i < nr_pages; i++) {
			WARN_ON(pages[i]->mapping);
			btrfs_free_compr_page(pages[i]);
		}
		kfree(pages);
	}
}

static void free_async_extent_pages(struct async_extent *async_extent)
{
	int i;

	if (!async_extent->pages)
		return;

	for (i = 0; i < async_extent->nr_pages; i++) {
		WARN_ON(async_extent->pages[i]->mapping);
		btrfs_free_compr_page(async_extent->pages[i]);
	}
	kfree(async_extent->pages);
	async_extent->nr_pages = 0;
	async_extent->pages = NULL;
}

static void submit_uncompressed_range(struct btrfs_inode *inode,
				      struct async_extent *async_extent,
				      struct page *locked_page)
{
	u64 start = async_extent->start;
	u64 end = async_extent->start + async_extent->ram_size - 1;
	int ret;
	struct writeback_control wbc = {
		.sync_mode		= WB_SYNC_ALL,
		.range_start		= start,
		.range_end		= end,
		.no_cgroup_owner	= 1,
	};

	wbc_attach_fdatawrite_inode(&wbc, &inode->vfs_inode);
	ret = run_delalloc_cow(inode, locked_page, start, end, &wbc, false);
	wbc_detach_inode(&wbc);
	if (ret < 0) {
		btrfs_cleanup_ordered_extents(inode, locked_page, start, end - start + 1);
		if (locked_page) {
			const u64 page_start = page_offset(locked_page);

			set_page_writeback(locked_page);
			end_page_writeback(locked_page);
			btrfs_mark_ordered_io_finished(inode, locked_page,
						       page_start, PAGE_SIZE,
						       !ret);
			mapping_set_error(locked_page->mapping, ret);
			unlock_page(locked_page);
		}
	}
}

static void submit_one_async_extent(struct async_chunk *async_chunk,
				    struct async_extent *async_extent,
				    u64 *alloc_hint)
{
	struct btrfs_inode *inode = async_chunk->inode;
	struct extent_io_tree *io_tree = &inode->io_tree;
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_ordered_extent *ordered;
	struct btrfs_key ins;
	struct page *locked_page = NULL;
	struct extent_map *em;
	int ret = 0;
	u64 start = async_extent->start;
	u64 end = async_extent->start + async_extent->ram_size - 1;

	if (async_chunk->blkcg_css)
		kthread_associate_blkcg(async_chunk->blkcg_css);

	/*
	 * If async_chunk->locked_page is in the async_extent range, we need to
	 * handle it.
	 */
	if (async_chunk->locked_page) {
		u64 locked_page_start = page_offset(async_chunk->locked_page);
		u64 locked_page_end = locked_page_start + PAGE_SIZE - 1;

		if (!(start >= locked_page_end || end <= locked_page_start))
			locked_page = async_chunk->locked_page;
	}
	lock_extent(io_tree, start, end, NULL);

	if (async_extent->compress_type == BTRFS_COMPRESS_NONE) {
		submit_uncompressed_range(inode, async_extent, locked_page);
		goto done;
	}

	ret = btrfs_reserve_extent(root, async_extent->ram_size,
				   async_extent->compressed_size,
				   async_extent->compressed_size,
				   0, *alloc_hint, &ins, 1, 1);
	if (ret) {
		/*
		 * Here we used to try again by going back to non-compressed
		 * path for ENOSPC.  But we can't reserve space even for
		 * compressed size, how could it work for uncompressed size
		 * which requires larger size?  So here we directly go error
		 * path.
		 */
		goto out_free;
	}

	/* Here we're doing allocation and writeback of the compressed pages */
	em = create_io_em(inode, start,
			  async_extent->ram_size,	/* len */
			  start,			/* orig_start */
			  ins.objectid,			/* block_start */
			  ins.offset,			/* block_len */
			  ins.offset,			/* orig_block_len */
			  async_extent->ram_size,	/* ram_bytes */
			  async_extent->compress_type,
			  BTRFS_ORDERED_COMPRESSED);
	if (IS_ERR(em)) {
		ret = PTR_ERR(em);
		goto out_free_reserve;
	}
	free_extent_map(em);

	ordered = btrfs_alloc_ordered_extent(inode, start,	/* file_offset */
				       async_extent->ram_size,	/* num_bytes */
				       async_extent->ram_size,	/* ram_bytes */
				       ins.objectid,		/* disk_bytenr */
				       ins.offset,		/* disk_num_bytes */
				       0,			/* offset */
				       1 << BTRFS_ORDERED_COMPRESSED,
				       async_extent->compress_type);
	if (IS_ERR(ordered)) {
		btrfs_drop_extent_map_range(inode, start, end, false);
		ret = PTR_ERR(ordered);
		goto out_free_reserve;
	}
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);

	/* Clear dirty, set writeback and unlock the pages. */
	extent_clear_unlock_delalloc(inode, start, end,
			NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
			PAGE_UNLOCK | PAGE_START_WRITEBACK);
	btrfs_submit_compressed_write(ordered,
			    async_extent->pages,	/* compressed_pages */
			    async_extent->nr_pages,
			    async_chunk->write_flags, true);
	*alloc_hint = ins.objectid + ins.offset;
done:
	if (async_chunk->blkcg_css)
		kthread_associate_blkcg(NULL);
	kfree(async_extent);
	return;

out_free_reserve:
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_free:
	mapping_set_error(inode->vfs_inode.i_mapping, -EIO);
	extent_clear_unlock_delalloc(inode, start, end,
				     NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
				     EXTENT_DELALLOC_NEW |
				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
				     PAGE_UNLOCK | PAGE_START_WRITEBACK |
				     PAGE_END_WRITEBACK);
	free_async_extent_pages(async_extent);
	if (async_chunk->blkcg_css)
		kthread_associate_blkcg(NULL);
	btrfs_debug(fs_info,
"async extent submission failed root=%lld inode=%llu start=%llu len=%llu ret=%d",
		    root->root_key.objectid, btrfs_ino(inode), start,
		    async_extent->ram_size, ret);
	kfree(async_extent);
}

static u64 get_extent_allocation_hint(struct btrfs_inode *inode, u64 start,
				      u64 num_bytes)
{
	struct extent_map_tree *em_tree = &inode->extent_tree;
	struct extent_map *em;
	u64 alloc_hint = 0;

	read_lock(&em_tree->lock);
	em = search_extent_mapping(em_tree, start, num_bytes);
	if (em) {
		/*
		 * if block start isn't an actual block number then find the
		 * first block in this inode and use that as a hint.  If that
		 * block is also bogus then just don't worry about it.
		 */
		if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
			free_extent_map(em);
			em = search_extent_mapping(em_tree, 0, 0);
			if (em && em->block_start < EXTENT_MAP_LAST_BYTE)
				alloc_hint = em->block_start;
			if (em)
				free_extent_map(em);
		} else {
			alloc_hint = em->block_start;
			free_extent_map(em);
		}
	}
	read_unlock(&em_tree->lock);

	return alloc_hint;
}

/*
 * when extent_io.c finds a delayed allocation range in the file,
 * the call backs end up in this code.  The basic idea is to
 * allocate extents on disk for the range, and create ordered data structs
 * in ram to track those extents.
 *
 * locked_page is the page that writepage had locked already.  We use
 * it to make sure we don't do extra locks or unlocks.
 *
 * When this function fails, it unlocks all pages except @locked_page.
 *
 * When this function successfully creates an inline extent, it returns 1 and
 * unlocks all pages including locked_page and starts I/O on them.
 * (In reality inline extents are limited to a single page, so locked_page is
 * the only page handled anyway).
 *
 * When this function succeed and creates a normal extent, the page locking
 * status depends on the passed in flags:
 *
 * - If @keep_locked is set, all pages are kept locked.
 * - Else all pages except for @locked_page are unlocked.
 *
 * When a failure happens in the second or later iteration of the
 * while-loop, the ordered extents created in previous iterations are kept
 * intact. So, the caller must clean them up by calling
 * btrfs_cleanup_ordered_extents(). See btrfs_run_delalloc_range() for
 * example.
 */
static noinline int cow_file_range(struct btrfs_inode *inode,
				   struct page *locked_page, u64 start, u64 end,
				   u64 *done_offset,
				   bool keep_locked, bool no_inline)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 alloc_hint = 0;
	u64 orig_start = start;
	u64 num_bytes;
	unsigned long ram_size;
	u64 cur_alloc_size = 0;
	u64 min_alloc_size;
	u64 blocksize = fs_info->sectorsize;
	struct btrfs_key ins;
	struct extent_map *em;
	unsigned clear_bits;
	unsigned long page_ops;
	bool extent_reserved = false;
	int ret = 0;

	if (btrfs_is_free_space_inode(inode)) {
		ret = -EINVAL;
		goto out_unlock;
	}

	num_bytes = ALIGN(end - start + 1, blocksize);
	num_bytes = max(blocksize,  num_bytes);
	ASSERT(num_bytes <= btrfs_super_total_bytes(fs_info->super_copy));

	inode_should_defrag(inode, start, end, num_bytes, SZ_64K);

	/*
	 * Due to the page size limit, for subpage we can only trigger the
	 * writeback for the dirty sectors of page, that means data writeback
	 * is doing more writeback than what we want.
	 *
	 * This is especially unexpected for some call sites like fallocate,
	 * where we only increase i_size after everything is done.
	 * This means we can trigger inline extent even if we didn't want to.
	 * So here we skip inline extent creation completely.
	 */
	if (start == 0 && fs_info->sectorsize == PAGE_SIZE && !no_inline) {
		u64 actual_end = min_t(u64, i_size_read(&inode->vfs_inode),
				       end + 1);

		/* lets try to make an inline extent */
		ret = cow_file_range_inline(inode, actual_end, 0,
					    BTRFS_COMPRESS_NONE, NULL, false);
		if (ret == 0) {
			/*
			 * We use DO_ACCOUNTING here because we need the
			 * delalloc_release_metadata to be run _after_ we drop
			 * our outstanding extent for clearing delalloc for this
			 * range.
			 */
			extent_clear_unlock_delalloc(inode, start, end,
				     locked_page,
				     EXTENT_LOCKED | EXTENT_DELALLOC |
				     EXTENT_DELALLOC_NEW | EXTENT_DEFRAG |
				     EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
				     PAGE_START_WRITEBACK | PAGE_END_WRITEBACK);
			/*
			 * locked_page is locked by the caller of
			 * writepage_delalloc(), not locked by
			 * __process_pages_contig().
			 *
			 * We can't let __process_pages_contig() to unlock it,
			 * as it doesn't have any subpage::writers recorded.
			 *
			 * Here we manually unlock the page, since the caller
			 * can't determine if it's an inline extent or a
			 * compressed extent.
			 */
			unlock_page(locked_page);
			ret = 1;
			goto done;
		} else if (ret < 0) {
			goto out_unlock;
		}
	}

	alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);

	/*
	 * Relocation relies on the relocated extents to have exactly the same
	 * size as the original extents. Normally writeback for relocation data
	 * extents follows a NOCOW path because relocation preallocates the
	 * extents. However, due to an operation such as scrub turning a block
	 * group to RO mode, it may fallback to COW mode, so we must make sure
	 * an extent allocated during COW has exactly the requested size and can
	 * not be split into smaller extents, otherwise relocation breaks and
	 * fails during the stage where it updates the bytenr of file extent
	 * items.
	 */
	if (btrfs_is_data_reloc_root(root))
		min_alloc_size = num_bytes;
	else
		min_alloc_size = fs_info->sectorsize;

	while (num_bytes > 0) {
		struct btrfs_ordered_extent *ordered;

		cur_alloc_size = num_bytes;
		ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
					   min_alloc_size, 0, alloc_hint,
					   &ins, 1, 1);
		if (ret == -EAGAIN) {
			/*
			 * btrfs_reserve_extent only returns -EAGAIN for zoned
			 * file systems, which is an indication that there are
			 * no active zones to allocate from at the moment.
			 *
			 * If this is the first loop iteration, wait for at
			 * least one zone to finish before retrying the
			 * allocation.  Otherwise ask the caller to write out
			 * the already allocated blocks before coming back to
			 * us, or return -ENOSPC if it can't handle retries.
			 */
			ASSERT(btrfs_is_zoned(fs_info));
			if (start == orig_start) {
				wait_on_bit_io(&inode->root->fs_info->flags,
					       BTRFS_FS_NEED_ZONE_FINISH,
					       TASK_UNINTERRUPTIBLE);
				continue;
			}
			if (done_offset) {
				*done_offset = start - 1;
				return 0;
			}
			ret = -ENOSPC;
		}
		if (ret < 0)
			goto out_unlock;
		cur_alloc_size = ins.offset;
		extent_reserved = true;

		ram_size = ins.offset;
		em = create_io_em(inode, start, ins.offset, /* len */
				  start, /* orig_start */
				  ins.objectid, /* block_start */
				  ins.offset, /* block_len */
				  ins.offset, /* orig_block_len */
				  ram_size, /* ram_bytes */
				  BTRFS_COMPRESS_NONE, /* compress_type */
				  BTRFS_ORDERED_REGULAR /* type */);
		if (IS_ERR(em)) {
			ret = PTR_ERR(em);
			goto out_reserve;
		}
		free_extent_map(em);

		ordered = btrfs_alloc_ordered_extent(inode, start, ram_size,
					ram_size, ins.objectid, cur_alloc_size,
					0, 1 << BTRFS_ORDERED_REGULAR,
					BTRFS_COMPRESS_NONE);
		if (IS_ERR(ordered)) {
			ret = PTR_ERR(ordered);
			goto out_drop_extent_cache;
		}

		if (btrfs_is_data_reloc_root(root)) {
			ret = btrfs_reloc_clone_csums(ordered);

			/*
			 * Only drop cache here, and process as normal.
			 *
			 * We must not allow extent_clear_unlock_delalloc()
			 * at out_unlock label to free meta of this ordered
			 * extent, as its meta should be freed by
			 * btrfs_finish_ordered_io().
			 *
			 * So we must continue until @start is increased to
			 * skip current ordered extent.
			 */
			if (ret)
				btrfs_drop_extent_map_range(inode, start,
							    start + ram_size - 1,
							    false);
		}
		btrfs_put_ordered_extent(ordered);

		btrfs_dec_block_group_reservations(fs_info, ins.objectid);

		/*
		 * We're not doing compressed IO, don't unlock the first page
		 * (which the caller expects to stay locked), don't clear any
		 * dirty bits and don't set any writeback bits
		 *
		 * Do set the Ordered (Private2) bit so we know this page was
		 * properly setup for writepage.
		 */
		page_ops = (keep_locked ? 0 : PAGE_UNLOCK);
		page_ops |= PAGE_SET_ORDERED;

		extent_clear_unlock_delalloc(inode, start, start + ram_size - 1,
					     locked_page,
					     EXTENT_LOCKED | EXTENT_DELALLOC,
					     page_ops);
		if (num_bytes < cur_alloc_size)
			num_bytes = 0;
		else
			num_bytes -= cur_alloc_size;
		alloc_hint = ins.objectid + ins.offset;
		start += cur_alloc_size;
		extent_reserved = false;

		/*
		 * btrfs_reloc_clone_csums() error, since start is increased
		 * extent_clear_unlock_delalloc() at out_unlock label won't
		 * free metadata of current ordered extent, we're OK to exit.
		 */
		if (ret)
			goto out_unlock;
	}
done:
	if (done_offset)
		*done_offset = end;
	return ret;

out_drop_extent_cache:
	btrfs_drop_extent_map_range(inode, start, start + ram_size - 1, false);
out_reserve:
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_unlock:
	/*
	 * Now, we have three regions to clean up:
	 *
	 * |-------(1)----|---(2)---|-------------(3)----------|
	 * `- orig_start  `- start  `- start + cur_alloc_size  `- end
	 *
	 * We process each region below.
	 */

	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
		EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
	page_ops = PAGE_UNLOCK | PAGE_START_WRITEBACK | PAGE_END_WRITEBACK;

	/*
	 * For the range (1). We have already instantiated the ordered extents
	 * for this region. They are cleaned up by
	 * btrfs_cleanup_ordered_extents() in e.g,
	 * btrfs_run_delalloc_range(). EXTENT_LOCKED | EXTENT_DELALLOC are
	 * already cleared in the above loop. And, EXTENT_DELALLOC_NEW |
	 * EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV are handled by the cleanup
	 * function.
	 *
	 * However, in case of @keep_locked, we still need to unlock the pages
	 * (except @locked_page) to ensure all the pages are unlocked.
	 */
	if (keep_locked && orig_start < start) {
		if (!locked_page)
			mapping_set_error(inode->vfs_inode.i_mapping, ret);
		extent_clear_unlock_delalloc(inode, orig_start, start - 1,
					     locked_page, 0, page_ops);
	}

	/*
	 * For the range (2). If we reserved an extent for our delalloc range
	 * (or a subrange) and failed to create the respective ordered extent,
	 * then it means that when we reserved the extent we decremented the
	 * extent's size from the data space_info's bytes_may_use counter and
	 * incremented the space_info's bytes_reserved counter by the same
	 * amount. We must make sure extent_clear_unlock_delalloc() does not try
	 * to decrement again the data space_info's bytes_may_use counter,
	 * therefore we do not pass it the flag EXTENT_CLEAR_DATA_RESV.
	 */
	if (extent_reserved) {
		extent_clear_unlock_delalloc(inode, start,
					     start + cur_alloc_size - 1,
					     locked_page,
					     clear_bits,
					     page_ops);
		start += cur_alloc_size;
	}

	/*
	 * For the range (3). We never touched the region. In addition to the
	 * clear_bits above, we add EXTENT_CLEAR_DATA_RESV to release the data
	 * space_info's bytes_may_use counter, reserved in
	 * btrfs_check_data_free_space().
	 */
	if (start < end) {
		clear_bits |= EXTENT_CLEAR_DATA_RESV;
		extent_clear_unlock_delalloc(inode, start, end, locked_page,
					     clear_bits, page_ops);
	}
	return ret;
}

/*
 * Phase two of compressed writeback.  This is the ordered portion of the code,
 * which only gets called in the order the work was queued.  We walk all the
 * async extents created by compress_file_range and send them down to the disk.
 *
 * If called with @do_free == true then it'll try to finish the work and free
 * the work struct eventually.
 */
static noinline void submit_compressed_extents(struct btrfs_work *work, bool do_free)
{
	struct async_chunk *async_chunk = container_of(work, struct async_chunk,
						     work);
	struct btrfs_fs_info *fs_info = btrfs_work_owner(work);
	struct async_extent *async_extent;
	unsigned long nr_pages;
	u64 alloc_hint = 0;

	if (do_free) {
		struct async_chunk *async_chunk;
		struct async_cow *async_cow;

		async_chunk = container_of(work, struct async_chunk, work);
		btrfs_add_delayed_iput(async_chunk->inode);
		if (async_chunk->blkcg_css)
			css_put(async_chunk->blkcg_css);

		async_cow = async_chunk->async_cow;
		if (atomic_dec_and_test(&async_cow->num_chunks))
			kvfree(async_cow);
		return;
	}

	nr_pages = (async_chunk->end - async_chunk->start + PAGE_SIZE) >>
		PAGE_SHIFT;

	while (!list_empty(&async_chunk->extents)) {
		async_extent = list_entry(async_chunk->extents.next,
					  struct async_extent, list);
		list_del(&async_extent->list);
		submit_one_async_extent(async_chunk, async_extent, &alloc_hint);
	}

	/* atomic_sub_return implies a barrier */
	if (atomic_sub_return(nr_pages, &fs_info->async_delalloc_pages) <
	    5 * SZ_1M)
		cond_wake_up_nomb(&fs_info->async_submit_wait);
}

static bool run_delalloc_compressed(struct btrfs_inode *inode,
				    struct page *locked_page, u64 start,
				    u64 end, struct writeback_control *wbc)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct cgroup_subsys_state *blkcg_css = wbc_blkcg_css(wbc);
	struct async_cow *ctx;
	struct async_chunk *async_chunk;
	unsigned long nr_pages;
	u64 num_chunks = DIV_ROUND_UP(end - start, SZ_512K);
	int i;
	unsigned nofs_flag;
	const blk_opf_t write_flags = wbc_to_write_flags(wbc);

	nofs_flag = memalloc_nofs_save();
	ctx = kvmalloc(struct_size(ctx, chunks, num_chunks), GFP_KERNEL);
	memalloc_nofs_restore(nofs_flag);
	if (!ctx)
		return false;

	unlock_extent(&inode->io_tree, start, end, NULL);
	set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT, &inode->runtime_flags);

	async_chunk = ctx->chunks;
	atomic_set(&ctx->num_chunks, num_chunks);

	for (i = 0; i < num_chunks; i++) {
		u64 cur_end = min(end, start + SZ_512K - 1);

		/*
		 * igrab is called higher up in the call chain, take only the
		 * lightweight reference for the callback lifetime
		 */
		ihold(&inode->vfs_inode);
		async_chunk[i].async_cow = ctx;
		async_chunk[i].inode = inode;
		async_chunk[i].start = start;
		async_chunk[i].end = cur_end;
		async_chunk[i].write_flags = write_flags;
		INIT_LIST_HEAD(&async_chunk[i].extents);

		/*
		 * The locked_page comes all the way from writepage and its
		 * the original page we were actually given.  As we spread
		 * this large delalloc region across multiple async_chunk
		 * structs, only the first struct needs a pointer to locked_page
		 *
		 * This way we don't need racey decisions about who is supposed
		 * to unlock it.
		 */
		if (locked_page) {
			/*
			 * Depending on the compressibility, the pages might or
			 * might not go through async.  We want all of them to
			 * be accounted against wbc once.  Let's do it here
			 * before the paths diverge.  wbc accounting is used
			 * only for foreign writeback detection and doesn't
			 * need full accuracy.  Just account the whole thing
			 * against the first page.
			 */
			wbc_account_cgroup_owner(wbc, locked_page,
						 cur_end - start);
			async_chunk[i].locked_page = locked_page;
			locked_page = NULL;
		} else {
			async_chunk[i].locked_page = NULL;
		}

		if (blkcg_css != blkcg_root_css) {
			css_get(blkcg_css);
			async_chunk[i].blkcg_css = blkcg_css;
			async_chunk[i].write_flags |= REQ_BTRFS_CGROUP_PUNT;
		} else {
			async_chunk[i].blkcg_css = NULL;
		}

		btrfs_init_work(&async_chunk[i].work, compress_file_range,
				submit_compressed_extents);

		nr_pages = DIV_ROUND_UP(cur_end - start, PAGE_SIZE);
		atomic_add(nr_pages, &fs_info->async_delalloc_pages);

		btrfs_queue_work(fs_info->delalloc_workers, &async_chunk[i].work);

		start = cur_end + 1;
	}
	return true;
}

/*
 * Run the delalloc range from start to end, and write back any dirty pages
 * covered by the range.
 */
static noinline int run_delalloc_cow(struct btrfs_inode *inode,
				     struct page *locked_page, u64 start,
				     u64 end, struct writeback_control *wbc,
				     bool pages_dirty)
{
	u64 done_offset = end;
	int ret;

	while (start <= end) {
		ret = cow_file_range(inode, locked_page, start, end, &done_offset,
				     true, false);
		if (ret)
			return ret;
		extent_write_locked_range(&inode->vfs_inode, locked_page, start,
					  done_offset, wbc, pages_dirty);
		start = done_offset + 1;
	}

	return 1;
}

static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info,
					u64 bytenr, u64 num_bytes, bool nowait)
{
	struct btrfs_root *csum_root = btrfs_csum_root(fs_info, bytenr);
	struct btrfs_ordered_sum *sums;
	int ret;
	LIST_HEAD(list);

	ret = btrfs_lookup_csums_list(csum_root, bytenr, bytenr + num_bytes - 1,
				      &list, 0, nowait);
	if (ret == 0 && list_empty(&list))
		return 0;

	while (!list_empty(&list)) {
		sums = list_entry(list.next, struct btrfs_ordered_sum, list);
		list_del(&sums->list);
		kfree(sums);
	}
	if (ret < 0)
		return ret;
	return 1;
}

static int fallback_to_cow(struct btrfs_inode *inode, struct page *locked_page,
			   const u64 start, const u64 end)
{
	const bool is_space_ino = btrfs_is_free_space_inode(inode);
	const bool is_reloc_ino = btrfs_is_data_reloc_root(inode->root);
	const u64 range_bytes = end + 1 - start;
	struct extent_io_tree *io_tree = &inode->io_tree;
	u64 range_start = start;
	u64 count;
	int ret;

	/*
	 * If EXTENT_NORESERVE is set it means that when the buffered write was
	 * made we had not enough available data space and therefore we did not
	 * reserve data space for it, since we though we could do NOCOW for the
	 * respective file range (either there is prealloc extent or the inode
	 * has the NOCOW bit set).
	 *
	 * However when we need to fallback to COW mode (because for example the
	 * block group for the corresponding extent was turned to RO mode by a
	 * scrub or relocation) we need to do the following:
	 *
	 * 1) We increment the bytes_may_use counter of the data space info.
	 *    If COW succeeds, it allocates a new data extent and after doing
	 *    that it decrements the space info's bytes_may_use counter and
	 *    increments its bytes_reserved counter by the same amount (we do
	 *    this at btrfs_add_reserved_bytes()). So we need to increment the
	 *    bytes_may_use counter to compensate (when space is reserved at
	 *    buffered write time, the bytes_may_use counter is incremented);
	 *
	 * 2) We clear the EXTENT_NORESERVE bit from the range. We do this so
	 *    that if the COW path fails for any reason, it decrements (through
	 *    extent_clear_unlock_delalloc()) the bytes_may_use counter of the
	 *    data space info, which we incremented in the step above.
	 *
	 * If we need to fallback to cow and the inode corresponds to a free
	 * space cache inode or an inode of the data relocation tree, we must
	 * also increment bytes_may_use of the data space_info for the same
	 * reason. Space caches and relocated data extents always get a prealloc
	 * extent for them, however scrub or balance may have set the block
	 * group that contains that extent to RO mode and therefore force COW
	 * when starting writeback.
	 */
	count = count_range_bits(io_tree, &range_start, end, range_bytes,
				 EXTENT_NORESERVE, 0, NULL);
	if (count > 0 || is_space_ino || is_reloc_ino) {
		u64 bytes = count;
		struct btrfs_fs_info *fs_info = inode->root->fs_info;
		struct btrfs_space_info *sinfo = fs_info->data_sinfo;

		if (is_space_ino || is_reloc_ino)
			bytes = range_bytes;

		spin_lock(&sinfo->lock);
		btrfs_space_info_update_bytes_may_use(fs_info, sinfo, bytes);
		spin_unlock(&sinfo->lock);

		if (count > 0)
			clear_extent_bit(io_tree, start, end, EXTENT_NORESERVE,
					 NULL);
	}

	/*
	 * Don't try to create inline extents, as a mix of inline extent that
	 * is written out and unlocked directly and a normal NOCOW extent
	 * doesn't work.
	 */
	ret = cow_file_range(inode, locked_page, start, end, NULL, false, true);
	ASSERT(ret != 1);
	return ret;
}

struct can_nocow_file_extent_args {
	/* Input fields. */

	/* Start file offset of the range we want to NOCOW. */
	u64 start;
	/* End file offset (inclusive) of the range we want to NOCOW. */
	u64 end;
	bool writeback_path;
	bool strict;
	/*
	 * Free the path passed to can_nocow_file_extent() once it's not needed
	 * anymore.
	 */
	bool free_path;

	/* Output fields. Only set when can_nocow_file_extent() returns 1. */

	u64 disk_bytenr;
	u64 disk_num_bytes;
	u64 extent_offset;
	/* Number of bytes that can be written to in NOCOW mode. */
	u64 num_bytes;
};

/*
 * Check if we can NOCOW the file extent that the path points to.
 * This function may return with the path released, so the caller should check
 * if path->nodes[0] is NULL or not if it needs to use the path afterwards.
 *
 * Returns: < 0 on error
 *            0 if we can not NOCOW
 *            1 if we can NOCOW
 */
static int can_nocow_file_extent(struct btrfs_path *path,
				 struct btrfs_key *key,
				 struct btrfs_inode *inode,
				 struct can_nocow_file_extent_args *args)
{
	const bool is_freespace_inode = btrfs_is_free_space_inode(inode);
	struct extent_buffer *leaf = path->nodes[0];
	struct btrfs_root *root = inode->root;
	struct btrfs_file_extent_item *fi;
	u64 extent_end;
	u8 extent_type;
	int can_nocow = 0;
	int ret = 0;
	bool nowait = path->nowait;

	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_INLINE)
		goto out;

	/* Can't access these fields unless we know it's not an inline extent. */
	args->disk_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
	args->disk_num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
	args->extent_offset = btrfs_file_extent_offset(leaf, fi);

	if (!(inode->flags & BTRFS_INODE_NODATACOW) &&
	    extent_type == BTRFS_FILE_EXTENT_REG)
		goto out;

	/*
	 * If the extent was created before the generation where the last snapshot
	 * for its subvolume was created, then this implies the extent is shared,
	 * hence we must COW.
	 */
	if (!args->strict &&
	    btrfs_file_extent_generation(leaf, fi) <=
	    btrfs_root_last_snapshot(&root->root_item))
		goto out;

	/* An explicit hole, must COW. */
	if (args->disk_bytenr == 0)
		goto out;

	/* Compressed/encrypted/encoded extents must be COWed. */
	if (btrfs_file_extent_compression(leaf, fi) ||
	    btrfs_file_extent_encryption(leaf, fi) ||
	    btrfs_file_extent_other_encoding(leaf, fi))
		goto out;

	extent_end = btrfs_file_extent_end(path);

	/*
	 * The following checks can be expensive, as they need to take other
	 * locks and do btree or rbtree searches, so release the path to avoid
	 * blocking other tasks for too long.
	 */
	btrfs_release_path(path);

	ret = btrfs_cross_ref_exist(root, btrfs_ino(inode),
				    key->offset - args->extent_offset,
				    args->disk_bytenr, args->strict, path);
	WARN_ON_ONCE(ret > 0 && is_freespace_inode);
	if (ret != 0)
		goto out;

	if (args->free_path) {
		/*
		 * We don't need the path anymore, plus through the
		 * csum_exist_in_range() call below we will end up allocating
		 * another path. So free the path to avoid unnecessary extra
		 * memory usage.
		 */
		btrfs_free_path(path);
		path = NULL;
	}

	/* If there are pending snapshots for this root, we must COW. */
	if (args->writeback_path && !is_freespace_inode &&
	    atomic_read(&root->snapshot_force_cow))
		goto out;

	args->disk_bytenr += args->extent_offset;
	args->disk_bytenr += args->start - key->offset;
	args->num_bytes = min(args->end + 1, extent_end) - args->start;

	/*
	 * Force COW if csums exist in the range. This ensures that csums for a
	 * given extent are either valid or do not exist.
	 */
	ret = csum_exist_in_range(root->fs_info, args->disk_bytenr, args->num_bytes,
				  nowait);
	WARN_ON_ONCE(ret > 0 && is_freespace_inode);
	if (ret != 0)
		goto out;

	can_nocow = 1;
 out:
	if (args->free_path && path)
		btrfs_free_path(path);

	return ret < 0 ? ret : can_nocow;
}

/*
 * when nowcow writeback call back.  This checks for snapshots or COW copies
 * of the extents that exist in the file, and COWs the file as required.
 *
 * If no cow copies or snapshots exist, we write directly to the existing
 * blocks on disk
 */
static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
				       struct page *locked_page,
				       const u64 start, const u64 end)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct btrfs_root *root = inode->root;
	struct btrfs_path *path;
	u64 cow_start = (u64)-1;
	u64 cur_offset = start;
	int ret;
	bool check_prev = true;
	u64 ino = btrfs_ino(inode);
	struct can_nocow_file_extent_args nocow_args = { 0 };

	/*
	 * Normally on a zoned device we're only doing COW writes, but in case
	 * of relocation on a zoned filesystem serializes I/O so that we're only
	 * writing sequentially and can end up here as well.
	 */
	ASSERT(!btrfs_is_zoned(fs_info) || btrfs_is_data_reloc_root(root));

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

	nocow_args.end = end;
	nocow_args.writeback_path = true;

	while (1) {
		struct btrfs_block_group *nocow_bg = NULL;
		struct btrfs_ordered_extent *ordered;
		struct btrfs_key found_key;
		struct btrfs_file_extent_item *fi;
		struct extent_buffer *leaf;
		u64 extent_end;
		u64 ram_bytes;
		u64 nocow_end;
		int extent_type;
		bool is_prealloc;

		ret = btrfs_lookup_file_extent(NULL, root, path, ino,
					       cur_offset, 0);
		if (ret < 0)
			goto error;

		/*
		 * If there is no extent for our range when doing the initial
		 * search, then go back to the previous slot as it will be the
		 * one containing the search offset
		 */
		if (ret > 0 && path->slots[0] > 0 && check_prev) {
			leaf = path->nodes[0];
			btrfs_item_key_to_cpu(leaf, &found_key,
					      path->slots[0] - 1);
			if (found_key.objectid == ino &&
			    found_key.type == BTRFS_EXTENT_DATA_KEY)
				path->slots[0]--;
		}
		check_prev = false;
next_slot:
		/* Go to next leaf if we have exhausted the current one */
		leaf = path->nodes[0];
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				goto error;
			if (ret > 0)
				break;
			leaf = path->nodes[0];
		}

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

		/* Didn't find anything for our INO */
		if (found_key.objectid > ino)
			break;
		/*
		 * Keep searching until we find an EXTENT_ITEM or there are no
		 * more extents for this inode
		 */
		if (WARN_ON_ONCE(found_key.objectid < ino) ||
		    found_key.type < BTRFS_EXTENT_DATA_KEY) {
			path->slots[0]++;
			goto next_slot;
		}

		/* Found key is not EXTENT_DATA_KEY or starts after req range */
		if (found_key.type > BTRFS_EXTENT_DATA_KEY ||
		    found_key.offset > end)
			break;

		/*
		 * If the found extent starts after requested offset, then
		 * adjust extent_end to be right before this extent begins
		 */
		if (found_key.offset > cur_offset) {
			extent_end = found_key.offset;
			extent_type = 0;
			goto must_cow;
		}

		/*
		 * Found extent which begins before our range and potentially
		 * intersect it
		 */
		fi = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_file_extent_item);
		extent_type = btrfs_file_extent_type(leaf, fi);
		/* If this is triggered then we have a memory corruption. */
		ASSERT(extent_type < BTRFS_NR_FILE_EXTENT_TYPES);
		if (WARN_ON(extent_type >= BTRFS_NR_FILE_EXTENT_TYPES)) {
			ret = -EUCLEAN;
			goto error;
		}
		ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);
		extent_end = btrfs_file_extent_end(path);

		/*
		 * If the extent we got ends before our current offset, skip to
		 * the next extent.
		 */
		if (extent_end <= cur_offset) {
			path->slots[0]++;
			goto next_slot;
		}

		nocow_args.start = cur_offset;
		ret = can_nocow_file_extent(path, &found_key, inode, &nocow_args);
		if (ret < 0)
			goto error;
		if (ret == 0)
			goto must_cow;

		ret = 0;
		nocow_bg = btrfs_inc_nocow_writers(fs_info, nocow_args.disk_bytenr);
		if (!nocow_bg) {
must_cow:
			/*
			 * If we can't perform NOCOW writeback for the range,
			 * then record the beginning of the range that needs to
			 * be COWed.  It will be written out before the next
			 * NOCOW range if we find one, or when exiting this
			 * loop.
			 */
			if (cow_start == (u64)-1)
				cow_start = cur_offset;
			cur_offset = extent_end;
			if (cur_offset > end)
				break;
			if (!path->nodes[0])
				continue;
			path->slots[0]++;
			goto next_slot;
		}

		/*
		 * COW range from cow_start to found_key.offset - 1. As the key
		 * will contain the beginning of the first extent that can be
		 * NOCOW, following one which needs to be COW'ed
		 */
		if (cow_start != (u64)-1) {
			ret = fallback_to_cow(inode, locked_page,
					      cow_start, found_key.offset - 1);
			cow_start = (u64)-1;
			if (ret) {
				btrfs_dec_nocow_writers(nocow_bg);
				goto error;
			}
		}

		nocow_end = cur_offset + nocow_args.num_bytes - 1;
		is_prealloc = extent_type == BTRFS_FILE_EXTENT_PREALLOC;
		if (is_prealloc) {
			u64 orig_start = found_key.offset - nocow_args.extent_offset;
			struct extent_map *em;

			em = create_io_em(inode, cur_offset, nocow_args.num_bytes,
					  orig_start,
					  nocow_args.disk_bytenr, /* block_start */
					  nocow_args.num_bytes, /* block_len */
					  nocow_args.disk_num_bytes, /* orig_block_len */
					  ram_bytes, BTRFS_COMPRESS_NONE,
					  BTRFS_ORDERED_PREALLOC);
			if (IS_ERR(em)) {
				btrfs_dec_nocow_writers(nocow_bg);
				ret = PTR_ERR(em);
				goto error;
			}
			free_extent_map(em);
		}

		ordered = btrfs_alloc_ordered_extent(inode, cur_offset,
				nocow_args.num_bytes, nocow_args.num_bytes,
				nocow_args.disk_bytenr, nocow_args.num_bytes, 0,
				is_prealloc
				? (1 << BTRFS_ORDERED_PREALLOC)
				: (1 << BTRFS_ORDERED_NOCOW),
				BTRFS_COMPRESS_NONE);
		btrfs_dec_nocow_writers(nocow_bg);
		if (IS_ERR(ordered)) {
			if (is_prealloc) {
				btrfs_drop_extent_map_range(inode, cur_offset,
							    nocow_end, false);
			}
			ret = PTR_ERR(ordered);
			goto error;
		}

		if (btrfs_is_data_reloc_root(root))
			/*
			 * Error handled later, as we must prevent
			 * extent_clear_unlock_delalloc() in error handler
			 * from freeing metadata of created ordered extent.
			 */
			ret = btrfs_reloc_clone_csums(ordered);
		btrfs_put_ordered_extent(ordered);

		extent_clear_unlock_delalloc(inode, cur_offset, nocow_end,
					     locked_page, EXTENT_LOCKED |
					     EXTENT_DELALLOC |
					     EXTENT_CLEAR_DATA_RESV,
					     PAGE_UNLOCK | PAGE_SET_ORDERED);

		cur_offset = extent_end;

		/*
		 * btrfs_reloc_clone_csums() error, now we're OK to call error
		 * handler, as metadata for created ordered extent will only
		 * be freed by btrfs_finish_ordered_io().
		 */
		if (ret)
			goto error;
		if (cur_offset > end)
			break;
	}
	btrfs_release_path(path);

	if (cur_offset <= end && cow_start == (u64)-1)
		cow_start = cur_offset;

	if (cow_start != (u64)-1) {
		cur_offset = end;
		ret = fallback_to_cow(inode, locked_page, cow_start, end);
		cow_start = (u64)-1;
		if (ret)
			goto error;
	}

	btrfs_free_path(path);
	return 0;

error:
	/*
	 * If an error happened while a COW region is outstanding, cur_offset
	 * needs to be reset to cow_start to ensure the COW region is unlocked
	 * as well.
	 */
	if (cow_start != (u64)-1)
		cur_offset = cow_start;
	if (cur_offset < end)
		extent_clear_unlock_delalloc(inode, cur_offset, end,
					     locked_page, EXTENT_LOCKED |
					     EXTENT_DELALLOC | EXTENT_DEFRAG |
					     EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
					     PAGE_START_WRITEBACK |
					     PAGE_END_WRITEBACK);
	btrfs_free_path(path);
	return ret;
}

static bool should_nocow(struct btrfs_inode *inode, u64 start, u64 end)
{
	if (inode->flags & (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)) {
		if (inode->defrag_bytes &&
		    test_range_bit_exists(&inode->io_tree, start, end, EXTENT_DEFRAG))
			return false;
		return true;
	}
	return false;
}

/*
 * Function to process delayed allocation (create CoW) for ranges which are
 * being touched for the first time.
 */
int btrfs_run_delalloc_range(struct btrfs_inode *inode, struct page *locked_page,
			     u64 start, u64 end, struct writeback_control *wbc)
{
	const bool zoned = btrfs_is_zoned(inode->root->fs_info);
	int ret;

	/*
	 * The range must cover part of the @locked_page, or a return of 1
	 * can confuse the caller.
	 */
	ASSERT(!(end <= page_offset(locked_page) ||
		 start >= page_offset(locked_page) + PAGE_SIZE));

	if (should_nocow(inode, start, end)) {
		ret = run_delalloc_nocow(inode, locked_page, start, end);
		goto out;
	}

	if (btrfs_inode_can_compress(inode) &&
	    inode_need_compress(inode, start, end) &&
	    run_delalloc_compressed(inode, locked_page, start, end, wbc))
		return 1;

	if (zoned)
		ret = run_delalloc_cow(inode, locked_page, start, end, wbc,
				       true);
	else
		ret = cow_file_range(inode, locked_page, start, end, NULL,
				     false, false);

out:
	if (ret < 0)
		btrfs_cleanup_ordered_extents(inode, locked_page, start,
					      end - start + 1);
	return ret;
}

void btrfs_split_delalloc_extent(struct btrfs_inode *inode,
				 struct extent_state *orig, u64 split)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	u64 size;

	/* not delalloc, ignore it */
	if (!(orig->state & EXTENT_DELALLOC))
		return;

	size = orig->end - orig->start + 1;
	if (size > fs_info->max_extent_size) {
		u32 num_extents;
		u64 new_size;

		/*
		 * See the explanation in btrfs_merge_delalloc_extent, the same
		 * applies here, just in reverse.
		 */
		new_size = orig->end - split + 1;
		num_extents = count_max_extents(fs_info, new_size);
		new_size = split - orig->start;
		num_extents += count_max_extents(fs_info, new_size);
		if (count_max_extents(fs_info, size) >= num_extents)
			return;
	}

	spin_lock(&inode->lock);
	btrfs_mod_outstanding_extents(inode, 1);
	spin_unlock(&inode->lock);
}

/*
 * Handle merged delayed allocation extents so we can keep track of new extents
 * that are just merged onto old extents, such as when we are doing sequential
 * writes, so we can properly account for the metadata space we'll need.
 */
void btrfs_merge_delalloc_extent(struct btrfs_inode *inode, struct extent_state *new,
				 struct extent_state *other)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	u64 new_size, old_size;
	u32 num_extents;

	/* not delalloc, ignore it */
	if (!(other->state & EXTENT_DELALLOC))
		return;

	if (new->start > other->start)
		new_size = new->end - other->start + 1;
	else
		new_size = other->end - new->start + 1;

	/* we're not bigger than the max, unreserve the space and go */
	if (new_size <= fs_info->max_extent_size) {
		spin_lock(&inode->lock);
		btrfs_mod_outstanding_extents(inode, -1);
		spin_unlock(&inode->lock);
		return;
	}

	/*
	 * We have to add up either side to figure out how many extents were
	 * accounted for before we merged into one big extent.  If the number of
	 * extents we accounted for is <= the amount we need for the new range
	 * then we can return, otherwise drop.  Think of it like this
	 *
	 * [ 4k][MAX_SIZE]
	 *
	 * So we've grown the extent by a MAX_SIZE extent, this would mean we
	 * need 2 outstanding extents, on one side we have 1 and the other side
	 * we have 1 so they are == and we can return.  But in this case
	 *
	 * [MAX_SIZE+4k][MAX_SIZE+4k]
	 *
	 * Each range on their own accounts for 2 extents, but merged together
	 * they are only 3 extents worth of accounting, so we need to drop in
	 * this case.
	 */
	old_size = other->end - other->start + 1;
	num_extents = count_max_extents(fs_info, old_size);
	old_size = new->end - new->start + 1;
	num_extents += count_max_extents(fs_info, old_size);
	if (count_max_extents(fs_info, new_size) >= num_extents)
		return;

	spin_lock(&inode->lock);
	btrfs_mod_outstanding_extents(inode, -1);
	spin_unlock(&inode->lock);
}

static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
				      struct btrfs_inode *inode)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;

	spin_lock(&root->delalloc_lock);
	if (list_empty(&inode->delalloc_inodes)) {
		list_add_tail(&inode->delalloc_inodes, &root->delalloc_inodes);
		set_bit(BTRFS_INODE_IN_DELALLOC_LIST, &inode->runtime_flags);
		root->nr_delalloc_inodes++;
		if (root->nr_delalloc_inodes == 1) {
			spin_lock(&fs_info->delalloc_root_lock);
			BUG_ON(!list_empty(&root->delalloc_root));
			list_add_tail(&root->delalloc_root,
				      &fs_info->delalloc_roots);
			spin_unlock(&fs_info->delalloc_root_lock);
		}
	}
	spin_unlock(&root->delalloc_lock);
}

void __btrfs_del_delalloc_inode(struct btrfs_root *root,
				struct btrfs_inode *inode)
{
	struct btrfs_fs_info *fs_info = root->fs_info;

	if (!list_empty(&inode->delalloc_inodes)) {
		list_del_init(&inode->delalloc_inodes);
		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
			  &inode->runtime_flags);
		root->nr_delalloc_inodes--;
		if (!root->nr_delalloc_inodes) {
			ASSERT(list_empty(&root->delalloc_inodes));
			spin_lock(&fs_info->delalloc_root_lock);
			BUG_ON(list_empty(&root->delalloc_root));
			list_del_init(&root->delalloc_root);
			spin_unlock(&fs_info->delalloc_root_lock);
		}
	}
}

static void btrfs_del_delalloc_inode(struct btrfs_root *root,
				     struct btrfs_inode *inode)
{
	spin_lock(&root->delalloc_lock);
	__btrfs_del_delalloc_inode(root, inode);
	spin_unlock(&root->delalloc_lock);
}

/*
 * Properly track delayed allocation bytes in the inode and to maintain the
 * list of inodes that have pending delalloc work to be done.
 */
void btrfs_set_delalloc_extent(struct btrfs_inode *inode, struct extent_state *state,
			       u32 bits)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;

	if ((bits & EXTENT_DEFRAG) && !(bits & EXTENT_DELALLOC))
		WARN_ON(1);
	/*
	 * set_bit and clear bit hooks normally require _irqsave/restore
	 * but in this case, we are only testing for the DELALLOC
	 * bit, which is only set or cleared with irqs on
	 */
	if (!(state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
		struct btrfs_root *root = inode->root;
		u64 len = state->end + 1 - state->start;
		u32 num_extents = count_max_extents(fs_info, len);
		bool do_list = !btrfs_is_free_space_inode(inode);

		spin_lock(&inode->lock);
		btrfs_mod_outstanding_extents(inode, num_extents);
		spin_unlock(&inode->lock);

		/* For sanity tests */
		if (btrfs_is_testing(fs_info))
			return;

		percpu_counter_add_batch(&fs_info->delalloc_bytes, len,
					 fs_info->delalloc_batch);
		spin_lock(&inode->lock);
		inode->delalloc_bytes += len;
		if (bits & EXTENT_DEFRAG)
			inode->defrag_bytes += len;
		if (do_list && !test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
					 &inode->runtime_flags))
			btrfs_add_delalloc_inodes(root, inode);
		spin_unlock(&inode->lock);
	}

	if (!(state->state & EXTENT_DELALLOC_NEW) &&
	    (bits & EXTENT_DELALLOC_NEW)) {
		spin_lock(&inode->lock);
		inode->new_delalloc_bytes += state->end + 1 - state->start;
		spin_unlock(&inode->lock);
	}
}

/*
 * Once a range is no longer delalloc this function ensures that proper
 * accounting happens.
 */
void btrfs_clear_delalloc_extent(struct btrfs_inode *inode,
				 struct extent_state *state, u32 bits)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	u64 len = state->end + 1 - state->start;
	u32 num_extents = count_max_extents(fs_info, len);

	if ((state->state & EXTENT_DEFRAG) && (bits & EXTENT_DEFRAG)) {
		spin_lock(&inode->lock);
		inode->defrag_bytes -= len;
		spin_unlock(&inode->lock);
	}

	/*
	 * set_bit and clear bit hooks normally require _irqsave/restore
	 * but in this case, we are only testing for the DELALLOC
	 * bit, which is only set or cleared with irqs on
	 */
	if ((state->state & EXTENT_DELALLOC) && (bits & EXTENT_DELALLOC)) {
		struct btrfs_root *root = inode->root;
		bool do_list = !btrfs_is_free_space_inode(inode);

		spin_lock(&inode->lock);
		btrfs_mod_outstanding_extents(inode, -num_extents);
		spin_unlock(&inode->lock);

		/*
		 * We don't reserve metadata space for space cache inodes so we
		 * don't need to call delalloc_release_metadata if there is an
		 * error.
		 */
		if (bits & EXTENT_CLEAR_META_RESV &&
		    root != fs_info->tree_root)
			btrfs_delalloc_release_metadata(inode, len, false);

		/* For sanity tests. */
		if (btrfs_is_testing(fs_info))
			return;

		if (!btrfs_is_data_reloc_root(root) &&
		    do_list && !(state->state & EXTENT_NORESERVE) &&
		    (bits & EXTENT_CLEAR_DATA_RESV))
			btrfs_free_reserved_data_space_noquota(fs_info, len);

		percpu_counter_add_batch(&fs_info->delalloc_bytes, -len,
					 fs_info->delalloc_batch);
		spin_lock(&inode->lock);
		inode->delalloc_bytes -= len;
		if (do_list && inode->delalloc_bytes == 0 &&
		    test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
					&inode->runtime_flags))
			btrfs_del_delalloc_inode(root, inode);
		spin_unlock(&inode->lock);
	}

	if ((state->state & EXTENT_DELALLOC_NEW) &&
	    (bits & EXTENT_DELALLOC_NEW)) {
		spin_lock(&inode->lock);
		ASSERT(inode->new_delalloc_bytes >= len);
		inode->new_delalloc_bytes -= len;
		if (bits & EXTENT_ADD_INODE_BYTES)
			inode_add_bytes(&inode->vfs_inode, len);
		spin_unlock(&inode->lock);
	}
}

static int btrfs_extract_ordered_extent(struct btrfs_bio *bbio,
					struct btrfs_ordered_extent *ordered)
{
	u64 start = (u64)bbio->bio.bi_iter.bi_sector << SECTOR_SHIFT;
	u64 len = bbio->bio.bi_iter.bi_size;
	struct btrfs_ordered_extent *new;
	int ret;

	/* Must always be called for the beginning of an ordered extent. */
	if (WARN_ON_ONCE(start != ordered->disk_bytenr))
		return -EINVAL;

	/* No need to split if the ordered extent covers the entire bio. */
	if (ordered->disk_num_bytes == len) {
		refcount_inc(&ordered->refs);
		bbio->ordered = ordered;
		return 0;
	}

	/*
	 * Don't split the extent_map for NOCOW extents, as we're writing into
	 * a pre-existing one.
	 */
	if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags)) {
		ret = split_extent_map(bbio->inode, bbio->file_offset,
				       ordered->num_bytes, len,
				       ordered->disk_bytenr);
		if (ret)
			return ret;
	}

	new = btrfs_split_ordered_extent(ordered, len);
	if (IS_ERR(new))
		return PTR_ERR(new);
	bbio->ordered = new;
	return 0;
}

/*
 * given a list of ordered sums record them in the inode.  This happens
 * at IO completion time based on sums calculated at bio submission time.
 */
static int add_pending_csums(struct btrfs_trans_handle *trans,
			     struct list_head *list)
{
	struct btrfs_ordered_sum *sum;
	struct btrfs_root *csum_root = NULL;
	int ret;

	list_for_each_entry(sum, list, list) {
		trans->adding_csums = true;
		if (!csum_root)
			csum_root = btrfs_csum_root(trans->fs_info,
						    sum->logical);
		ret = btrfs_csum_file_blocks(trans, csum_root, sum);
		trans->adding_csums = false;
		if (ret)
			return ret;
	}
	return 0;
}

static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
					 const u64 start,
					 const u64 len,
					 struct extent_state **cached_state)
{
	u64 search_start = start;
	const u64 end = start + len - 1;

	while (search_start < end) {
		const u64 search_len = end - search_start + 1;
		struct extent_map *em;
		u64 em_len;
		int ret = 0;

		em = btrfs_get_extent(inode, NULL, 0, search_start, search_len);
		if (IS_ERR(em))
			return PTR_ERR(em);

		if (em->block_start != EXTENT_MAP_HOLE)
			goto next;

		em_len = em->len;
		if (em->start < search_start)
			em_len -= search_start - em->start;
		if (em_len > search_len)
			em_len = search_len;

		ret = set_extent_bit(&inode->io_tree, search_start,
				     search_start + em_len - 1,
				     EXTENT_DELALLOC_NEW, cached_state);
next:
		search_start = extent_map_end(em);
		free_extent_map(em);
		if (ret)
			return ret;
	}
	return 0;
}

int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end,
			      unsigned int extra_bits,
			      struct extent_state **cached_state)
{
	WARN_ON(PAGE_ALIGNED(end));

	if (start >= i_size_read(&inode->vfs_inode) &&
	    !(inode->flags & BTRFS_INODE_PREALLOC)) {
		/*
		 * There can't be any extents following eof in this case so just
		 * set the delalloc new bit for the range directly.
		 */
		extra_bits |= EXTENT_DELALLOC_NEW;
	} else {
		int ret;

		ret = btrfs_find_new_delalloc_bytes(inode, start,
						    end + 1 - start,
						    cached_state);
		if (ret)
			return ret;
	}

	return set_extent_bit(&inode->io_tree, start, end,
			      EXTENT_DELALLOC | extra_bits, cached_state);
}

/* see btrfs_writepage_start_hook for details on why this is required */
struct btrfs_writepage_fixup {
	struct page *page;
	struct btrfs_inode *inode;
	struct btrfs_work work;
};

static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
{
	struct btrfs_writepage_fixup *fixup =
		container_of(work, struct btrfs_writepage_fixup, work);
	struct btrfs_ordered_extent *ordered;
	struct extent_state *cached_state = NULL;
	struct extent_changeset *data_reserved = NULL;
	struct page *page = fixup->page;
	struct btrfs_inode *inode = fixup->inode;
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	u64 page_start = page_offset(page);
	u64 page_end = page_offset(page) + PAGE_SIZE - 1;
	int ret = 0;
	bool free_delalloc_space = true;

	/*
	 * This is similar to page_mkwrite, we need to reserve the space before
	 * we take the page lock.
	 */
	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
					   PAGE_SIZE);
again:
	lock_page(page);

	/*
	 * Before we queued this fixup, we took a reference on the page.
	 * page->mapping may go NULL, but it shouldn't be moved to a different
	 * address space.
	 */
	if (!page->mapping || !PageDirty(page) || !PageChecked(page)) {
		/*
		 * Unfortunately this is a little tricky, either
		 *
		 * 1) We got here and our page had already been dealt with and
		 *    we reserved our space, thus ret == 0, so we need to just
		 *    drop our space reservation and bail.  This can happen the
		 *    first time we come into the fixup worker, or could happen
		 *    while waiting for the ordered extent.
		 * 2) Our page was already dealt with, but we happened to get an
		 *    ENOSPC above from the btrfs_delalloc_reserve_space.  In
		 *    this case we obviously don't have anything to release, but
		 *    because the page was already dealt with we don't want to
		 *    mark the page with an error, so make sure we're resetting
		 *    ret to 0.  This is why we have this check _before_ the ret
		 *    check, because we do not want to have a surprise ENOSPC
		 *    when the page was already properly dealt with.
		 */
		if (!ret) {
			btrfs_delalloc_release_extents(inode, PAGE_SIZE);
			btrfs_delalloc_release_space(inode, data_reserved,
						     page_start, PAGE_SIZE,
						     true);
		}
		ret = 0;
		goto out_page;
	}

	/*
	 * We can't mess with the page state unless it is locked, so now that
	 * it is locked bail if we failed to make our space reservation.
	 */
	if (ret)
		goto out_page;

	lock_extent(&inode->io_tree, page_start, page_end, &cached_state);

	/* already ordered? We're done */
	if (PageOrdered(page))
		goto out_reserved;

	ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE);
	if (ordered) {
		unlock_extent(&inode->io_tree, page_start, page_end,
			      &cached_state);
		unlock_page(page);
		btrfs_start_ordered_extent(ordered);
		btrfs_put_ordered_extent(ordered);
		goto again;
	}

	ret = btrfs_set_extent_delalloc(inode, page_start, page_end, 0,
					&cached_state);
	if (ret)
		goto out_reserved;

	/*
	 * Everything went as planned, we're now the owner of a dirty page with
	 * delayed allocation bits set and space reserved for our COW
	 * destination.
	 *
	 * The page was dirty when we started, nothing should have cleaned it.
	 */
	BUG_ON(!PageDirty(page));
	free_delalloc_space = false;
out_reserved:
	btrfs_delalloc_release_extents(inode, PAGE_SIZE);
	if (free_delalloc_space)
		btrfs_delalloc_release_space(inode, data_reserved, page_start,
					     PAGE_SIZE, true);
	unlock_extent(&inode->io_tree, page_start, page_end, &cached_state);
out_page:
	if (ret) {
		/*
		 * We hit ENOSPC or other errors.  Update the mapping and page
		 * to reflect the errors and clean the page.
		 */
		mapping_set_error(page->mapping, ret);
		btrfs_mark_ordered_io_finished(inode, page, page_start,
					       PAGE_SIZE, !ret);
		clear_page_dirty_for_io(page);
	}
	btrfs_folio_clear_checked(fs_info, page_folio(page), page_start, PAGE_SIZE);
	unlock_page(page);
	put_page(page);
	kfree(fixup);
	extent_changeset_free(data_reserved);
	/*
	 * As a precaution, do a delayed iput in case it would be the last iput
	 * that could need flushing space. Recursing back to fixup worker would
	 * deadlock.
	 */
	btrfs_add_delayed_iput(inode);
}

/*
 * There are a few paths in the higher layers of the kernel that directly
 * set the page dirty bit without asking the filesystem if it is a
 * good idea.  This causes problems because we want to make sure COW
 * properly happens and the data=ordered rules are followed.
 *
 * In our case any range that doesn't have the ORDERED bit set
 * hasn't been properly setup for IO.  We kick off an async process
 * to fix it up.  The async helper will wait for ordered extents, set
 * the delalloc bit and make it safe to write the page.
 */
int btrfs_writepage_cow_fixup(struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_writepage_fixup *fixup;

	/* This page has ordered extent covering it already */
	if (PageOrdered(page))
		return 0;

	/*
	 * PageChecked is set below when we create a fixup worker for this page,
	 * don't try to create another one if we're already PageChecked()
	 *
	 * The extent_io writepage code will redirty the page if we send back
	 * EAGAIN.
	 */
	if (PageChecked(page))
		return -EAGAIN;

	fixup = kzalloc(sizeof(*fixup), GFP_NOFS);
	if (!fixup)
		return -EAGAIN;

	/*
	 * We are already holding a reference to this inode from
	 * write_cache_pages.  We need to hold it because the space reservation
	 * takes place outside of the page lock, and we can't trust
	 * page->mapping outside of the page lock.
	 */
	ihold(inode);
	btrfs_folio_set_checked(fs_info, page_folio(page), page_offset(page), PAGE_SIZE);
	get_page(page);
	btrfs_init_work(&fixup->work, btrfs_writepage_fixup_worker, NULL);
	fixup->page = page;
	fixup->inode = BTRFS_I(inode);
	btrfs_queue_work(fs_info->fixup_workers, &fixup->work);

	return -EAGAIN;
}

static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
				       struct btrfs_inode *inode, u64 file_pos,
				       struct btrfs_file_extent_item *stack_fi,
				       const bool update_inode_bytes,
				       u64 qgroup_reserved)
{
	struct btrfs_root *root = inode->root;
	const u64 sectorsize = root->fs_info->sectorsize;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_key ins;
	u64 disk_num_bytes = btrfs_stack_file_extent_disk_num_bytes(stack_fi);
	u64 disk_bytenr = btrfs_stack_file_extent_disk_bytenr(stack_fi);
	u64 offset = btrfs_stack_file_extent_offset(stack_fi);
	u64 num_bytes = btrfs_stack_file_extent_num_bytes(stack_fi);
	u64 ram_bytes = btrfs_stack_file_extent_ram_bytes(stack_fi);
	struct btrfs_drop_extents_args drop_args = { 0 };
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/*
	 * we may be replacing one extent in the tree with another.
	 * The new extent is pinned in the extent map, and we don't want
	 * to drop it from the cache until it is completely in the btree.
	 *
	 * So, tell btrfs_drop_extents to leave this extent in the cache.
	 * the caller is expected to unpin it and allow it to be merged
	 * with the others.
	 */
	drop_args.path = path;
	drop_args.start = file_pos;
	drop_args.end = file_pos + num_bytes;
	drop_args.replace_extent = true;
	drop_args.extent_item_size = sizeof(*stack_fi);
	ret = btrfs_drop_extents(trans, root, inode, &drop_args);
	if (ret)
		goto out;

	if (!drop_args.extent_inserted) {
		ins.objectid = btrfs_ino(inode);
		ins.offset = file_pos;
		ins.type = BTRFS_EXTENT_DATA_KEY;

		ret = btrfs_insert_empty_item(trans, root, path, &ins,
					      sizeof(*stack_fi));
		if (ret)
			goto out;
	}
	leaf = path->nodes[0];
	btrfs_set_stack_file_extent_generation(stack_fi, trans->transid);
	write_extent_buffer(leaf, stack_fi,
			btrfs_item_ptr_offset(leaf, path->slots[0]),
			sizeof(struct btrfs_file_extent_item));

	btrfs_mark_buffer_dirty(trans, leaf);
	btrfs_release_path(path);

	/*
	 * If we dropped an inline extent here, we know the range where it is
	 * was not marked with the EXTENT_DELALLOC_NEW bit, so we update the
	 * number of bytes only for that range containing the inline extent.
	 * The remaining of the range will be processed when clearning the
	 * EXTENT_DELALLOC_BIT bit through the ordered extent completion.
	 */
	if (file_pos == 0 && !IS_ALIGNED(drop_args.bytes_found, sectorsize)) {
		u64 inline_size = round_down(drop_args.bytes_found, sectorsize);

		inline_size = drop_args.bytes_found - inline_size;
		btrfs_update_inode_bytes(inode, sectorsize, inline_size);
		drop_args.bytes_found -= inline_size;
		num_bytes -= sectorsize;
	}

	if (update_inode_bytes)
		btrfs_update_inode_bytes(inode, num_bytes, drop_args.bytes_found);

	ins.objectid = disk_bytenr;
	ins.offset = disk_num_bytes;
	ins.type = BTRFS_EXTENT_ITEM_KEY;

	ret = btrfs_inode_set_file_extent_range(inode, file_pos, ram_bytes);
	if (ret)
		goto out;

	ret = btrfs_alloc_reserved_file_extent(trans, root, btrfs_ino(inode),
					       file_pos - offset,
					       qgroup_reserved, &ins);
out:
	btrfs_free_path(path);

	return ret;
}

static void btrfs_release_delalloc_bytes(struct btrfs_fs_info *fs_info,
					 u64 start, u64 len)
{
	struct btrfs_block_group *cache;

	cache = btrfs_lookup_block_group(fs_info, start);
	ASSERT(cache);

	spin_lock(&cache->lock);
	cache->delalloc_bytes -= len;
	spin_unlock(&cache->lock);

	btrfs_put_block_group(cache);
}

static int insert_ordered_extent_file_extent(struct btrfs_trans_handle *trans,
					     struct btrfs_ordered_extent *oe)
{
	struct btrfs_file_extent_item stack_fi;
	bool update_inode_bytes;
	u64 num_bytes = oe->num_bytes;
	u64 ram_bytes = oe->ram_bytes;

	memset(&stack_fi, 0, sizeof(stack_fi));
	btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_REG);
	btrfs_set_stack_file_extent_disk_bytenr(&stack_fi, oe->disk_bytenr);
	btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi,
						   oe->disk_num_bytes);
	btrfs_set_stack_file_extent_offset(&stack_fi, oe->offset);
	if (test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags)) {
		num_bytes = oe->truncated_len;
		ram_bytes = num_bytes;
	}
	btrfs_set_stack_file_extent_num_bytes(&stack_fi, num_bytes);
	btrfs_set_stack_file_extent_ram_bytes(&stack_fi, ram_bytes);
	btrfs_set_stack_file_extent_compression(&stack_fi, oe->compress_type);
	/* Encryption and other encoding is reserved and all 0 */

	/*
	 * For delalloc, when completing an ordered extent we update the inode's
	 * bytes when clearing the range in the inode's io tree, so pass false
	 * as the argument 'update_inode_bytes' to insert_reserved_file_extent(),
	 * except if the ordered extent was truncated.
	 */
	update_inode_bytes = test_bit(BTRFS_ORDERED_DIRECT, &oe->flags) ||
			     test_bit(BTRFS_ORDERED_ENCODED, &oe->flags) ||
			     test_bit(BTRFS_ORDERED_TRUNCATED, &oe->flags);

	return insert_reserved_file_extent(trans, BTRFS_I(oe->inode),
					   oe->file_offset, &stack_fi,
					   update_inode_bytes, oe->qgroup_rsv);
}

/*
 * As ordered data IO finishes, this gets called so we can finish
 * an ordered extent if the range of bytes in the file it covers are
 * fully written.
 */
int btrfs_finish_one_ordered(struct btrfs_ordered_extent *ordered_extent)
{
	struct btrfs_inode *inode = BTRFS_I(ordered_extent->inode);
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans = NULL;
	struct extent_io_tree *io_tree = &inode->io_tree;
	struct extent_state *cached_state = NULL;
	u64 start, end;
	int compress_type = 0;
	int ret = 0;
	u64 logical_len = ordered_extent->num_bytes;
	bool freespace_inode;
	bool truncated = false;
	bool clear_reserved_extent = true;
	unsigned int clear_bits = EXTENT_DEFRAG;

	start = ordered_extent->file_offset;
	end = start + ordered_extent->num_bytes - 1;

	if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
	    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags) &&
	    !test_bit(BTRFS_ORDERED_ENCODED, &ordered_extent->flags))
		clear_bits |= EXTENT_DELALLOC_NEW;

	freespace_inode = btrfs_is_free_space_inode(inode);
	if (!freespace_inode)
		btrfs_lockdep_acquire(fs_info, btrfs_ordered_extent);

	if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
		ret = -EIO;
		goto out;
	}

	if (btrfs_is_zoned(fs_info))
		btrfs_zone_finish_endio(fs_info, ordered_extent->disk_bytenr,
					ordered_extent->disk_num_bytes);

	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
		truncated = true;
		logical_len = ordered_extent->truncated_len;
		/* Truncated the entire extent, don't bother adding */
		if (!logical_len)
			goto out;
	}

	if (test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags)) {
		BUG_ON(!list_empty(&ordered_extent->list)); /* Logic error */

		btrfs_inode_safe_disk_i_size_write(inode, 0);
		if (freespace_inode)
			trans = btrfs_join_transaction_spacecache(root);
		else
			trans = btrfs_join_transaction(root);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			trans = NULL;
			goto out;
		}
		trans->block_rsv = &inode->block_rsv;
		ret = btrfs_update_inode_fallback(trans, inode);
		if (ret) /* -ENOMEM or corruption */
			btrfs_abort_transaction(trans, ret);
		goto out;
	}

	clear_bits |= EXTENT_LOCKED;
	lock_extent(io_tree, start, end, &cached_state);

	if (freespace_inode)
		trans = btrfs_join_transaction_spacecache(root);
	else
		trans = btrfs_join_transaction(root);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		trans = NULL;
		goto out;
	}

	trans->block_rsv = &inode->block_rsv;

	ret = btrfs_insert_raid_extent(trans, ordered_extent);
	if (ret)
		goto out;

	if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
		compress_type = ordered_extent->compress_type;
	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
		BUG_ON(compress_type);
		ret = btrfs_mark_extent_written(trans, inode,
						ordered_extent->file_offset,
						ordered_extent->file_offset +
						logical_len);
		btrfs_zoned_release_data_reloc_bg(fs_info, ordered_extent->disk_bytenr,
						  ordered_extent->disk_num_bytes);
	} else {
		BUG_ON(root == fs_info->tree_root);
		ret = insert_ordered_extent_file_extent(trans, ordered_extent);
		if (!ret) {
			clear_reserved_extent = false;
			btrfs_release_delalloc_bytes(fs_info,
						ordered_extent->disk_bytenr,
						ordered_extent->disk_num_bytes);
		}
	}
	unpin_extent_cache(inode, ordered_extent->file_offset,
			   ordered_extent->num_bytes, trans->transid);
	if (ret < 0) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	ret = add_pending_csums(trans, &ordered_extent->list);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	/*
	 * If this is a new delalloc range, clear its new delalloc flag to
	 * update the inode's number of bytes. This needs to be done first
	 * before updating the inode item.
	 */
	if ((clear_bits & EXTENT_DELALLOC_NEW) &&
	    !test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags))
		clear_extent_bit(&inode->io_tree, start, end,
				 EXTENT_DELALLOC_NEW | EXTENT_ADD_INODE_BYTES,
				 &cached_state);

	btrfs_inode_safe_disk_i_size_write(inode, 0);
	ret = btrfs_update_inode_fallback(trans, inode);
	if (ret) { /* -ENOMEM or corruption */
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	ret = 0;
out:
	clear_extent_bit(&inode->io_tree, start, end, clear_bits,
			 &cached_state);

	if (trans)
		btrfs_end_transaction(trans);

	if (ret || truncated) {
		u64 unwritten_start = start;

		/*
		 * If we failed to finish this ordered extent for any reason we
		 * need to make sure BTRFS_ORDERED_IOERR is set on the ordered
		 * extent, and mark the inode with the error if it wasn't
		 * already set.  Any error during writeback would have already
		 * set the mapping error, so we need to set it if we're the ones
		 * marking this ordered extent as failed.
		 */
		if (ret && !test_and_set_bit(BTRFS_ORDERED_IOERR,
					     &ordered_extent->flags))
			mapping_set_error(ordered_extent->inode->i_mapping, -EIO);

		if (truncated)
			unwritten_start += logical_len;
		clear_extent_uptodate(io_tree, unwritten_start, end, NULL);

		/*
		 * Drop extent maps for the part of the extent we didn't write.
		 *
		 * We have an exception here for the free_space_inode, this is
		 * because when we do btrfs_get_extent() on the free space inode
		 * we will search the commit root.  If this is a new block group
		 * we won't find anything, and we will trip over the assert in
		 * writepage where we do ASSERT(em->block_start !=
		 * EXTENT_MAP_HOLE).
		 *
		 * Theoretically we could also skip this for any NOCOW extent as
		 * we don't mess with the extent map tree in the NOCOW case, but
		 * for now simply skip this if we are the free space inode.
		 */
		if (!btrfs_is_free_space_inode(inode))
			btrfs_drop_extent_map_range(inode, unwritten_start,
						    end, false);

		/*
		 * If the ordered extent had an IOERR or something else went
		 * wrong we need to return the space for this ordered extent
		 * back to the allocator.  We only free the extent in the
		 * truncated case if we didn't write out the extent at all.
		 *
		 * If we made it past insert_reserved_file_extent before we
		 * errored out then we don't need to do this as the accounting
		 * has already been done.
		 */
		if ((ret || !logical_len) &&
		    clear_reserved_extent &&
		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
		    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
			/*
			 * Discard the range before returning it back to the
			 * free space pool
			 */
			if (ret && btrfs_test_opt(fs_info, DISCARD_SYNC))
				btrfs_discard_extent(fs_info,
						ordered_extent->disk_bytenr,
						ordered_extent->disk_num_bytes,
						NULL);
			btrfs_free_reserved_extent(fs_info,
					ordered_extent->disk_bytenr,
					ordered_extent->disk_num_bytes, 1);
			/*
			 * Actually free the qgroup rsv which was released when
			 * the ordered extent was created.
			 */
			btrfs_qgroup_free_refroot(fs_info, inode->root->root_key.objectid,
						  ordered_extent->qgroup_rsv,
						  BTRFS_QGROUP_RSV_DATA);
		}
	}

	/*
	 * This needs to be done to make sure anybody waiting knows we are done
	 * updating everything for this ordered extent.
	 */
	btrfs_remove_ordered_extent(inode, ordered_extent);

	/* once for us */
	btrfs_put_ordered_extent(ordered_extent);
	/* once for the tree */
	btrfs_put_ordered_extent(ordered_extent);

	return ret;
}

int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered)
{
	if (btrfs_is_zoned(btrfs_sb(ordered->inode->i_sb)) &&
	    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
	    list_empty(&ordered->bioc_list))
		btrfs_finish_ordered_zoned(ordered);
	return btrfs_finish_one_ordered(ordered);
}

/*
 * Verify the checksum for a single sector without any extra action that depend
 * on the type of I/O.
 */
int btrfs_check_sector_csum(struct btrfs_fs_info *fs_info, struct page *page,
			    u32 pgoff, u8 *csum, const u8 * const csum_expected)
{
	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
	char *kaddr;

	ASSERT(pgoff + fs_info->sectorsize <= PAGE_SIZE);

	shash->tfm = fs_info->csum_shash;

	kaddr = kmap_local_page(page) + pgoff;
	crypto_shash_digest(shash, kaddr, fs_info->sectorsize, csum);
	kunmap_local(kaddr);

	if (memcmp(csum, csum_expected, fs_info->csum_size))
		return -EIO;
	return 0;
}

/*
 * Verify the checksum of a single data sector.
 *
 * @bbio:	btrfs_io_bio which contains the csum
 * @dev:	device the sector is on
 * @bio_offset:	offset to the beginning of the bio (in bytes)
 * @bv:		bio_vec to check
 *
 * Check if the checksum on a data block is valid.  When a checksum mismatch is
 * detected, report the error and fill the corrupted range with zero.
 *
 * Return %true if the sector is ok or had no checksum to start with, else %false.
 */
bool btrfs_data_csum_ok(struct btrfs_bio *bbio, struct btrfs_device *dev,
			u32 bio_offset, struct bio_vec *bv)
{
	struct btrfs_inode *inode = bbio->inode;
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	u64 file_offset = bbio->file_offset + bio_offset;
	u64 end = file_offset + bv->bv_len - 1;
	u8 *csum_expected;
	u8 csum[BTRFS_CSUM_SIZE];

	ASSERT(bv->bv_len == fs_info->sectorsize);

	if (!bbio->csum)
		return true;

	if (btrfs_is_data_reloc_root(inode->root) &&
	    test_range_bit(&inode->io_tree, file_offset, end, EXTENT_NODATASUM,
			   NULL)) {
		/* Skip the range without csum for data reloc inode */
		clear_extent_bits(&inode->io_tree, file_offset, end,
				  EXTENT_NODATASUM);
		return true;
	}

	csum_expected = bbio->csum + (bio_offset >> fs_info->sectorsize_bits) *
				fs_info->csum_size;
	if (btrfs_check_sector_csum(fs_info, bv->bv_page, bv->bv_offset, csum,
				    csum_expected))
		goto zeroit;
	return true;

zeroit:
	btrfs_print_data_csum_error(inode, file_offset, csum, csum_expected,
				    bbio->mirror_num);
	if (dev)
		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_CORRUPTION_ERRS);
	memzero_bvec(bv);
	return false;
}

/*
 * Perform a delayed iput on @inode.
 *
 * @inode: The inode we want to perform iput on
 *
 * This function uses the generic vfs_inode::i_count to track whether we should
 * just decrement it (in case it's > 1) or if this is the last iput then link
 * the inode to the delayed iput machinery. Delayed iputs are processed at
 * transaction commit time/superblock commit/cleaner kthread.
 */
void btrfs_add_delayed_iput(struct btrfs_inode *inode)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	unsigned long flags;

	if (atomic_add_unless(&inode->vfs_inode.i_count, -1, 1))
		return;

	atomic_inc(&fs_info->nr_delayed_iputs);
	/*
	 * Need to be irq safe here because we can be called from either an irq
	 * context (see bio.c and btrfs_put_ordered_extent()) or a non-irq
	 * context.
	 */
	spin_lock_irqsave(&fs_info->delayed_iput_lock, flags);
	ASSERT(list_empty(&inode->delayed_iput));
	list_add_tail(&inode->delayed_iput, &fs_info->delayed_iputs);
	spin_unlock_irqrestore(&fs_info->delayed_iput_lock, flags);
	if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags))
		wake_up_process(fs_info->cleaner_kthread);
}

static void run_delayed_iput_locked(struct btrfs_fs_info *fs_info,
				    struct btrfs_inode *inode)
{
	list_del_init(&inode->delayed_iput);
	spin_unlock_irq(&fs_info->delayed_iput_lock);
	iput(&inode->vfs_inode);
	if (atomic_dec_and_test(&fs_info->nr_delayed_iputs))
		wake_up(&fs_info->delayed_iputs_wait);
	spin_lock_irq(&fs_info->delayed_iput_lock);
}

static void btrfs_run_delayed_iput(struct btrfs_fs_info *fs_info,
				   struct btrfs_inode *inode)
{
	if (!list_empty(&inode->delayed_iput)) {
		spin_lock_irq(&fs_info->delayed_iput_lock);
		if (!list_empty(&inode->delayed_iput))
			run_delayed_iput_locked(fs_info, inode);
		spin_unlock_irq(&fs_info->delayed_iput_lock);
	}
}

void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info)
{
	/*
	 * btrfs_put_ordered_extent() can run in irq context (see bio.c), which
	 * calls btrfs_add_delayed_iput() and that needs to lock
	 * fs_info->delayed_iput_lock. So we need to disable irqs here to
	 * prevent a deadlock.
	 */
	spin_lock_irq(&fs_info->delayed_iput_lock);
	while (!list_empty(&fs_info->delayed_iputs)) {
		struct btrfs_inode *inode;

		inode = list_first_entry(&fs_info->delayed_iputs,
				struct btrfs_inode, delayed_iput);
		run_delayed_iput_locked(fs_info, inode);
		if (need_resched()) {
			spin_unlock_irq(&fs_info->delayed_iput_lock);
			cond_resched();
			spin_lock_irq(&fs_info->delayed_iput_lock);
		}
	}
	spin_unlock_irq(&fs_info->delayed_iput_lock);
}

/*
 * Wait for flushing all delayed iputs
 *
 * @fs_info:  the filesystem
 *
 * This will wait on any delayed iputs that are currently running with KILLABLE
 * set.  Once they are all done running we will return, unless we are killed in
 * which case we return EINTR. This helps in user operations like fallocate etc
 * that might get blocked on the iputs.
 *
 * Return EINTR if we were killed, 0 if nothing's pending
 */
int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info)
{
	int ret = wait_event_killable(fs_info->delayed_iputs_wait,
			atomic_read(&fs_info->nr_delayed_iputs) == 0);
	if (ret)
		return -EINTR;
	return 0;
}

/*
 * This creates an orphan entry for the given inode in case something goes wrong
 * in the middle of an unlink.
 */
int btrfs_orphan_add(struct btrfs_trans_handle *trans,
		     struct btrfs_inode *inode)
{
	int ret;

	ret = btrfs_insert_orphan_item(trans, inode->root, btrfs_ino(inode));
	if (ret && ret != -EEXIST) {
		btrfs_abort_transaction(trans, ret);
		return ret;
	}

	return 0;
}

/*
 * We have done the delete so we can go ahead and remove the orphan item for
 * this particular inode.
 */
static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
			    struct btrfs_inode *inode)
{
	return btrfs_del_orphan_item(trans, inode->root, btrfs_ino(inode));
}

/*
 * this cleans up any orphans that may be left on the list from the last use
 * of this root.
 */
int btrfs_orphan_cleanup(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_key key, found_key;
	struct btrfs_trans_handle *trans;
	struct inode *inode;
	u64 last_objectid = 0;
	int ret = 0, nr_unlink = 0;

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

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

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

	while (1) {
		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
		if (ret < 0)
			goto out;

		/*
		 * if ret == 0 means we found what we were searching for, which
		 * is weird, but possible, so only screw with path if we didn't
		 * find the key and see if we have stuff that matches
		 */
		if (ret > 0) {
			ret = 0;
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}

		/* pull out the item */
		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);

		/* make sure the item matches what we want */
		if (found_key.objectid != BTRFS_ORPHAN_OBJECTID)
			break;
		if (found_key.type != BTRFS_ORPHAN_ITEM_KEY)
			break;

		/* release the path since we're done with it */
		btrfs_release_path(path);

		/*
		 * this is where we are basically btrfs_lookup, without the
		 * crossing root thing.  we store the inode number in the
		 * offset of the orphan item.
		 */

		if (found_key.offset == last_objectid) {
			/*
			 * We found the same inode as before. This means we were
			 * not able to remove its items via eviction triggered
			 * by an iput(). A transaction abort may have happened,
			 * due to -ENOSPC for example, so try to grab the error
			 * that lead to a transaction abort, if any.
			 */
			btrfs_err(fs_info,
				  "Error removing orphan entry, stopping orphan cleanup");
			ret = BTRFS_FS_ERROR(fs_info) ?: -EINVAL;
			goto out;
		}

		last_objectid = found_key.offset;

		found_key.objectid = found_key.offset;
		found_key.type = BTRFS_INODE_ITEM_KEY;
		found_key.offset = 0;
		inode = btrfs_iget(fs_info->sb, last_objectid, root);
		if (IS_ERR(inode)) {
			ret = PTR_ERR(inode);
			inode = NULL;
			if (ret != -ENOENT)
				goto out;
		}

		if (!inode && root == fs_info->tree_root) {
			struct btrfs_root *dead_root;
			int is_dead_root = 0;

			/*
			 * This is an orphan in the tree root. Currently these
			 * could come from 2 sources:
			 *  a) a root (snapshot/subvolume) deletion in progress
			 *  b) a free space cache inode
			 * We need to distinguish those two, as the orphan item
			 * for a root must not get deleted before the deletion
			 * of the snapshot/subvolume's tree completes.
			 *
			 * btrfs_find_orphan_roots() ran before us, which has
			 * found all deleted roots and loaded them into
			 * fs_info->fs_roots_radix. So here we can find if an
			 * orphan item corresponds to a deleted root by looking
			 * up the root from that radix tree.
			 */

			spin_lock(&fs_info->fs_roots_radix_lock);
			dead_root = radix_tree_lookup(&fs_info->fs_roots_radix,
							 (unsigned long)found_key.objectid);
			if (dead_root && btrfs_root_refs(&dead_root->root_item) == 0)
				is_dead_root = 1;
			spin_unlock(&fs_info->fs_roots_radix_lock);

			if (is_dead_root) {
				/* prevent this orphan from being found again */
				key.offset = found_key.objectid - 1;
				continue;
			}

		}

		/*
		 * If we have an inode with links, there are a couple of
		 * possibilities:
		 *
		 * 1. We were halfway through creating fsverity metadata for the
		 * file. In that case, the orphan item represents incomplete
		 * fsverity metadata which must be cleaned up with
		 * btrfs_drop_verity_items and deleting the orphan item.

		 * 2. Old kernels (before v3.12) used to create an
		 * orphan item for truncate indicating that there were possibly
		 * extent items past i_size that needed to be deleted. In v3.12,
		 * truncate was changed to update i_size in sync with the extent
		 * items, but the (useless) orphan item was still created. Since
		 * v4.18, we don't create the orphan item for truncate at all.
		 *
		 * So, this item could mean that we need to do a truncate, but
		 * only if this filesystem was last used on a pre-v3.12 kernel
		 * and was not cleanly unmounted. The odds of that are quite
		 * slim, and it's a pain to do the truncate now, so just delete
		 * the orphan item.
		 *
		 * It's also possible that this orphan item was supposed to be
		 * deleted but wasn't. The inode number may have been reused,
		 * but either way, we can delete the orphan item.
		 */
		if (!inode || inode->i_nlink) {
			if (inode) {
				ret = btrfs_drop_verity_items(BTRFS_I(inode));
				iput(inode);
				inode = NULL;
				if (ret)
					goto out;
			}
			trans = btrfs_start_transaction(root, 1);
			if (IS_ERR(trans)) {
				ret = PTR_ERR(trans);
				goto out;
			}
			btrfs_debug(fs_info, "auto deleting %Lu",
				    found_key.objectid);
			ret = btrfs_del_orphan_item(trans, root,
						    found_key.objectid);
			btrfs_end_transaction(trans);
			if (ret)
				goto out;
			continue;
		}

		nr_unlink++;

		/* this will do delete_inode and everything for us */
		iput(inode);
	}
	/* release the path since we're done with it */
	btrfs_release_path(path);

	if (test_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state)) {
		trans = btrfs_join_transaction(root);
		if (!IS_ERR(trans))
			btrfs_end_transaction(trans);
	}

	if (nr_unlink)
		btrfs_debug(fs_info, "unlinked %d orphans", nr_unlink);

out:
	if (ret)
		btrfs_err(fs_info, "could not do orphan cleanup %d", ret);
	btrfs_free_path(path);
	return ret;
}

/*
 * very simple check to peek ahead in the leaf looking for xattrs.  If we
 * don't find any xattrs, we know there can't be any acls.
 *
 * slot is the slot the inode is in, objectid is the objectid of the inode
 */
static noinline int acls_after_inode_item(struct extent_buffer *leaf,
					  int slot, u64 objectid,
					  int *first_xattr_slot)
{
	u32 nritems = btrfs_header_nritems(leaf);
	struct btrfs_key found_key;
	static u64 xattr_access = 0;
	static u64 xattr_default = 0;
	int scanned = 0;

	if (!xattr_access) {
		xattr_access = btrfs_name_hash(XATTR_NAME_POSIX_ACL_ACCESS,
					strlen(XATTR_NAME_POSIX_ACL_ACCESS));
		xattr_default = btrfs_name_hash(XATTR_NAME_POSIX_ACL_DEFAULT,
					strlen(XATTR_NAME_POSIX_ACL_DEFAULT));
	}

	slot++;
	*first_xattr_slot = -1;
	while (slot < nritems) {
		btrfs_item_key_to_cpu(leaf, &found_key, slot);

		/* we found a different objectid, there must not be acls */
		if (found_key.objectid != objectid)
			return 0;

		/* we found an xattr, assume we've got an acl */
		if (found_key.type == BTRFS_XATTR_ITEM_KEY) {
			if (*first_xattr_slot == -1)
				*first_xattr_slot = slot;
			if (found_key.offset == xattr_access ||
			    found_key.offset == xattr_default)
				return 1;
		}

		/*
		 * we found a key greater than an xattr key, there can't
		 * be any acls later on
		 */
		if (found_key.type > BTRFS_XATTR_ITEM_KEY)
			return 0;

		slot++;
		scanned++;

		/*
		 * it goes inode, inode backrefs, xattrs, extents,
		 * so if there are a ton of hard links to an inode there can
		 * be a lot of backrefs.  Don't waste time searching too hard,
		 * this is just an optimization
		 */
		if (scanned >= 8)
			break;
	}
	/* we hit the end of the leaf before we found an xattr or
	 * something larger than an xattr.  We have to assume the inode
	 * has acls
	 */
	if (*first_xattr_slot == -1)
		*first_xattr_slot = slot;
	return 1;
}

/*
 * read an inode from the btree into the in-memory inode
 */
static int btrfs_read_locked_inode(struct inode *inode,
				   struct btrfs_path *in_path)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_path *path = in_path;
	struct extent_buffer *leaf;
	struct btrfs_inode_item *inode_item;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_key location;
	unsigned long ptr;
	int maybe_acls;
	u32 rdev;
	int ret;
	bool filled = false;
	int first_xattr_slot;

	ret = btrfs_fill_inode(inode, &rdev);
	if (!ret)
		filled = true;

	if (!path) {
		path = btrfs_alloc_path();
		if (!path)
			return -ENOMEM;
	}

	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));

	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
	if (ret) {
		if (path != in_path)
			btrfs_free_path(path);
		return ret;
	}

	leaf = path->nodes[0];

	if (filled)
		goto cache_index;

	inode_item = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_inode_item);
	inode->i_mode = btrfs_inode_mode(leaf, inode_item);
	set_nlink(inode, btrfs_inode_nlink(leaf, inode_item));
	i_uid_write(inode, btrfs_inode_uid(leaf, inode_item));
	i_gid_write(inode, btrfs_inode_gid(leaf, inode_item));
	btrfs_i_size_write(BTRFS_I(inode), btrfs_inode_size(leaf, inode_item));
	btrfs_inode_set_file_extent_range(BTRFS_I(inode), 0,
			round_up(i_size_read(inode), fs_info->sectorsize));

	inode_set_atime(inode, btrfs_timespec_sec(leaf, &inode_item->atime),
			btrfs_timespec_nsec(leaf, &inode_item->atime));

	inode_set_mtime(inode, btrfs_timespec_sec(leaf, &inode_item->mtime),
			btrfs_timespec_nsec(leaf, &inode_item->mtime));

	inode_set_ctime(inode, btrfs_timespec_sec(leaf, &inode_item->ctime),
			btrfs_timespec_nsec(leaf, &inode_item->ctime));

	BTRFS_I(inode)->i_otime_sec = btrfs_timespec_sec(leaf, &inode_item->otime);
	BTRFS_I(inode)->i_otime_nsec = btrfs_timespec_nsec(leaf, &inode_item->otime);

	inode_set_bytes(inode, btrfs_inode_nbytes(leaf, inode_item));
	BTRFS_I(inode)->generation = btrfs_inode_generation(leaf, inode_item);
	BTRFS_I(inode)->last_trans = btrfs_inode_transid(leaf, inode_item);

	inode_set_iversion_queried(inode,
				   btrfs_inode_sequence(leaf, inode_item));
	inode->i_generation = BTRFS_I(inode)->generation;
	inode->i_rdev = 0;
	rdev = btrfs_inode_rdev(leaf, inode_item);

	BTRFS_I(inode)->index_cnt = (u64)-1;
	btrfs_inode_split_flags(btrfs_inode_flags(leaf, inode_item),
				&BTRFS_I(inode)->flags, &BTRFS_I(inode)->ro_flags);

cache_index:
	/*
	 * If we were modified in the current generation and evicted from memory
	 * and then re-read we need to do a full sync since we don't have any
	 * idea about which extents were modified before we were evicted from
	 * cache.
	 *
	 * This is required for both inode re-read from disk and delayed inode
	 * in the delayed_nodes xarray.
	 */
	if (BTRFS_I(inode)->last_trans == btrfs_get_fs_generation(fs_info))
		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
			&BTRFS_I(inode)->runtime_flags);

	/*
	 * We don't persist the id of the transaction where an unlink operation
	 * against the inode was last made. So here we assume the inode might
	 * have been evicted, and therefore the exact value of last_unlink_trans
	 * lost, and set it to last_trans to avoid metadata inconsistencies
	 * between the inode and its parent if the inode is fsync'ed and the log
	 * replayed. For example, in the scenario:
	 *
	 * touch mydir/foo
	 * ln mydir/foo mydir/bar
	 * sync
	 * unlink mydir/bar
	 * echo 2 > /proc/sys/vm/drop_caches   # evicts inode
	 * xfs_io -c fsync mydir/foo
	 * <power failure>
	 * mount fs, triggers fsync log replay
	 *
	 * We must make sure that when we fsync our inode foo we also log its
	 * parent inode, otherwise after log replay the parent still has the
	 * dentry with the "bar" name but our inode foo has a link count of 1
	 * and doesn't have an inode ref with the name "bar" anymore.
	 *
	 * Setting last_unlink_trans to last_trans is a pessimistic approach,
	 * but it guarantees correctness at the expense of occasional full
	 * transaction commits on fsync if our inode is a directory, or if our
	 * inode is not a directory, logging its parent unnecessarily.
	 */
	BTRFS_I(inode)->last_unlink_trans = BTRFS_I(inode)->last_trans;

	/*
	 * Same logic as for last_unlink_trans. We don't persist the generation
	 * of the last transaction where this inode was used for a reflink
	 * operation, so after eviction and reloading the inode we must be
	 * pessimistic and assume the last transaction that modified the inode.
	 */
	BTRFS_I(inode)->last_reflink_trans = BTRFS_I(inode)->last_trans;

	path->slots[0]++;
	if (inode->i_nlink != 1 ||
	    path->slots[0] >= btrfs_header_nritems(leaf))
		goto cache_acl;

	btrfs_item_key_to_cpu(leaf, &location, path->slots[0]);
	if (location.objectid != btrfs_ino(BTRFS_I(inode)))
		goto cache_acl;

	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
	if (location.type == BTRFS_INODE_REF_KEY) {
		struct btrfs_inode_ref *ref;

		ref = (struct btrfs_inode_ref *)ptr;
		BTRFS_I(inode)->dir_index = btrfs_inode_ref_index(leaf, ref);
	} else if (location.type == BTRFS_INODE_EXTREF_KEY) {
		struct btrfs_inode_extref *extref;

		extref = (struct btrfs_inode_extref *)ptr;
		BTRFS_I(inode)->dir_index = btrfs_inode_extref_index(leaf,
								     extref);
	}
cache_acl:
	/*
	 * try to precache a NULL acl entry for files that don't have
	 * any xattrs or acls
	 */
	maybe_acls = acls_after_inode_item(leaf, path->slots[0],
			btrfs_ino(BTRFS_I(inode)), &first_xattr_slot);
	if (first_xattr_slot != -1) {
		path->slots[0] = first_xattr_slot;
		ret = btrfs_load_inode_props(inode, path);
		if (ret)
			btrfs_err(fs_info,
				  "error loading props for ino %llu (root %llu): %d",
				  btrfs_ino(BTRFS_I(inode)),
				  root->root_key.objectid, ret);
	}
	if (path != in_path)
		btrfs_free_path(path);

	if (!maybe_acls)
		cache_no_acl(inode);

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		inode->i_mapping->a_ops = &btrfs_aops;
		inode->i_fop = &btrfs_file_operations;
		inode->i_op = &btrfs_file_inode_operations;
		break;
	case S_IFDIR:
		inode->i_fop = &btrfs_dir_file_operations;
		inode->i_op = &btrfs_dir_inode_operations;
		break;
	case S_IFLNK:
		inode->i_op = &btrfs_symlink_inode_operations;
		inode_nohighmem(inode);
		inode->i_mapping->a_ops = &btrfs_aops;
		break;
	default:
		inode->i_op = &btrfs_special_inode_operations;
		init_special_inode(inode, inode->i_mode, rdev);
		break;
	}

	btrfs_sync_inode_flags_to_i_flags(inode);
	return 0;
}

/*
 * given a leaf and an inode, copy the inode fields into the leaf
 */
static void fill_inode_item(struct btrfs_trans_handle *trans,
			    struct extent_buffer *leaf,
			    struct btrfs_inode_item *item,
			    struct inode *inode)
{
	struct btrfs_map_token token;
	u64 flags;

	btrfs_init_map_token(&token, leaf);

	btrfs_set_token_inode_uid(&token, item, i_uid_read(inode));
	btrfs_set_token_inode_gid(&token, item, i_gid_read(inode));
	btrfs_set_token_inode_size(&token, item, BTRFS_I(inode)->disk_i_size);
	btrfs_set_token_inode_mode(&token, item, inode->i_mode);
	btrfs_set_token_inode_nlink(&token, item, inode->i_nlink);

	btrfs_set_token_timespec_sec(&token, &item->atime,
				     inode_get_atime_sec(inode));
	btrfs_set_token_timespec_nsec(&token, &item->atime,
				      inode_get_atime_nsec(inode));

	btrfs_set_token_timespec_sec(&token, &item->mtime,
				     inode_get_mtime_sec(inode));
	btrfs_set_token_timespec_nsec(&token, &item->mtime,
				      inode_get_mtime_nsec(inode));

	btrfs_set_token_timespec_sec(&token, &item->ctime,
				     inode_get_ctime_sec(inode));
	btrfs_set_token_timespec_nsec(&token, &item->ctime,
				      inode_get_ctime_nsec(inode));

	btrfs_set_token_timespec_sec(&token, &item->otime, BTRFS_I(inode)->i_otime_sec);
	btrfs_set_token_timespec_nsec(&token, &item->otime, BTRFS_I(inode)->i_otime_nsec);

	btrfs_set_token_inode_nbytes(&token, item, inode_get_bytes(inode));
	btrfs_set_token_inode_generation(&token, item,
					 BTRFS_I(inode)->generation);
	btrfs_set_token_inode_sequence(&token, item, inode_peek_iversion(inode));
	btrfs_set_token_inode_transid(&token, item, trans->transid);
	btrfs_set_token_inode_rdev(&token, item, inode->i_rdev);
	flags = btrfs_inode_combine_flags(BTRFS_I(inode)->flags,
					  BTRFS_I(inode)->ro_flags);
	btrfs_set_token_inode_flags(&token, item, flags);
	btrfs_set_token_inode_block_group(&token, item, 0);
}

/*
 * copy everything in the in-memory inode into the btree.
 */
static noinline int btrfs_update_inode_item(struct btrfs_trans_handle *trans,
					    struct btrfs_inode *inode)
{
	struct btrfs_inode_item *inode_item;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = btrfs_lookup_inode(trans, inode->root, path, &inode->location, 1);
	if (ret) {
		if (ret > 0)
			ret = -ENOENT;
		goto failed;
	}

	leaf = path->nodes[0];
	inode_item = btrfs_item_ptr(leaf, path->slots[0],
				    struct btrfs_inode_item);

	fill_inode_item(trans, leaf, inode_item, &inode->vfs_inode);
	btrfs_mark_buffer_dirty(trans, leaf);
	btrfs_set_inode_last_trans(trans, inode);
	ret = 0;
failed:
	btrfs_free_path(path);
	return ret;
}

/*
 * copy everything in the in-memory inode into the btree.
 */
int btrfs_update_inode(struct btrfs_trans_handle *trans,
		       struct btrfs_inode *inode)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	int ret;

	/*
	 * If the inode is a free space inode, we can deadlock during commit
	 * if we put it into the delayed code.
	 *
	 * The data relocation inode should also be directly updated
	 * without delay
	 */
	if (!btrfs_is_free_space_inode(inode)
	    && !btrfs_is_data_reloc_root(root)
	    && !test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
		btrfs_update_root_times(trans, root);

		ret = btrfs_delayed_update_inode(trans, inode);
		if (!ret)
			btrfs_set_inode_last_trans(trans, inode);
		return ret;
	}

	return btrfs_update_inode_item(trans, inode);
}

int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
				struct btrfs_inode *inode)
{
	int ret;

	ret = btrfs_update_inode(trans, inode);
	if (ret == -ENOSPC)
		return btrfs_update_inode_item(trans, inode);
	return ret;
}

/*
 * unlink helper that gets used here in inode.c and in the tree logging
 * recovery code.  It remove a link in a directory with a given name, and
 * also drops the back refs in the inode to the directory
 */
static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
				struct btrfs_inode *dir,
				struct btrfs_inode *inode,
				const struct fscrypt_str *name,
				struct btrfs_rename_ctx *rename_ctx)
{
	struct btrfs_root *root = dir->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	int ret = 0;
	struct btrfs_dir_item *di;
	u64 index;
	u64 ino = btrfs_ino(inode);
	u64 dir_ino = btrfs_ino(dir);

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

	di = btrfs_lookup_dir_item(trans, root, path, dir_ino, name, -1);
	if (IS_ERR_OR_NULL(di)) {
		ret = di ? PTR_ERR(di) : -ENOENT;
		goto err;
	}
	ret = btrfs_delete_one_dir_name(trans, root, path, di);
	if (ret)
		goto err;
	btrfs_release_path(path);

	/*
	 * If we don't have dir index, we have to get it by looking up
	 * the inode ref, since we get the inode ref, remove it directly,
	 * it is unnecessary to do delayed deletion.
	 *
	 * But if we have dir index, needn't search inode ref to get it.
	 * Since the inode ref is close to the inode item, it is better
	 * that we delay to delete it, and just do this deletion when
	 * we update the inode item.
	 */
	if (inode->dir_index) {
		ret = btrfs_delayed_delete_inode_ref(inode);
		if (!ret) {
			index = inode->dir_index;
			goto skip_backref;
		}
	}

	ret = btrfs_del_inode_ref(trans, root, name, ino, dir_ino, &index);
	if (ret) {
		btrfs_info(fs_info,
			"failed to delete reference to %.*s, inode %llu parent %llu",
			name->len, name->name, ino, dir_ino);
		btrfs_abort_transaction(trans, ret);
		goto err;
	}
skip_backref:
	if (rename_ctx)
		rename_ctx->index = index;

	ret = btrfs_delete_delayed_dir_index(trans, dir, index);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto err;
	}

	/*
	 * If we are in a rename context, we don't need to update anything in the
	 * log. That will be done later during the rename by btrfs_log_new_name().
	 * Besides that, doing it here would only cause extra unnecessary btree
	 * operations on the log tree, increasing latency for applications.
	 */
	if (!rename_ctx) {
		btrfs_del_inode_ref_in_log(trans, root, name, inode, dir_ino);
		btrfs_del_dir_entries_in_log(trans, root, name, dir, index);
	}

	/*
	 * If we have a pending delayed iput we could end up with the final iput
	 * being run in btrfs-cleaner context.  If we have enough of these built
	 * up we can end up burning a lot of time in btrfs-cleaner without any
	 * way to throttle the unlinks.  Since we're currently holding a ref on
	 * the inode we can run the delayed iput here without any issues as the
	 * final iput won't be done until after we drop the ref we're currently
	 * holding.
	 */
	btrfs_run_delayed_iput(fs_info, inode);
err:
	btrfs_free_path(path);
	if (ret)
		goto out;

	btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2);
	inode_inc_iversion(&inode->vfs_inode);
	inode_inc_iversion(&dir->vfs_inode);
 	inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
	ret = btrfs_update_inode(trans, dir);
out:
	return ret;
}

int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
		       struct btrfs_inode *dir, struct btrfs_inode *inode,
		       const struct fscrypt_str *name)
{
	int ret;

	ret = __btrfs_unlink_inode(trans, dir, inode, name, NULL);
	if (!ret) {
		drop_nlink(&inode->vfs_inode);
		ret = btrfs_update_inode(trans, inode);
	}
	return ret;
}

/*
 * helper to start transaction for unlink and rmdir.
 *
 * unlink and rmdir are special in btrfs, they do not always free space, so
 * if we cannot make our reservations the normal way try and see if there is
 * plenty of slack room in the global reserve to migrate, otherwise we cannot
 * allow the unlink to occur.
 */
static struct btrfs_trans_handle *__unlink_start_trans(struct btrfs_inode *dir)
{
	struct btrfs_root *root = dir->root;

	return btrfs_start_transaction_fallback_global_rsv(root,
						   BTRFS_UNLINK_METADATA_UNITS);
}

static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
{
	struct btrfs_trans_handle *trans;
	struct inode *inode = d_inode(dentry);
	int ret;
	struct fscrypt_name fname;

	ret = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname);
	if (ret)
		return ret;

	/* This needs to handle no-key deletions later on */

	trans = __unlink_start_trans(BTRFS_I(dir));
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto fscrypt_free;
	}

	btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
				false);

	ret = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
				 &fname.disk_name);
	if (ret)
		goto end_trans;

	if (inode->i_nlink == 0) {
		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
		if (ret)
			goto end_trans;
	}

end_trans:
	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(BTRFS_I(dir)->root->fs_info);
fscrypt_free:
	fscrypt_free_filename(&fname);
	return ret;
}

static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
			       struct btrfs_inode *dir, struct dentry *dentry)
{
	struct btrfs_root *root = dir->root;
	struct btrfs_inode *inode = BTRFS_I(d_inode(dentry));
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_dir_item *di;
	struct btrfs_key key;
	u64 index;
	int ret;
	u64 objectid;
	u64 dir_ino = btrfs_ino(dir);
	struct fscrypt_name fname;

	ret = fscrypt_setup_filename(&dir->vfs_inode, &dentry->d_name, 1, &fname);
	if (ret)
		return ret;

	/* This needs to handle no-key deletions later on */

	if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID) {
		objectid = inode->root->root_key.objectid;
	} else if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
		objectid = inode->location.objectid;
	} else {
		WARN_ON(1);
		fscrypt_free_filename(&fname);
		return -EINVAL;
	}

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

	di = btrfs_lookup_dir_item(trans, root, path, dir_ino,
				   &fname.disk_name, -1);
	if (IS_ERR_OR_NULL(di)) {
		ret = di ? PTR_ERR(di) : -ENOENT;
		goto out;
	}

	leaf = path->nodes[0];
	btrfs_dir_item_key_to_cpu(leaf, di, &key);
	WARN_ON(key.type != BTRFS_ROOT_ITEM_KEY || key.objectid != objectid);
	ret = btrfs_delete_one_dir_name(trans, root, path, di);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	btrfs_release_path(path);

	/*
	 * This is a placeholder inode for a subvolume we didn't have a
	 * reference to at the time of the snapshot creation.  In the meantime
	 * we could have renamed the real subvol link into our snapshot, so
	 * depending on btrfs_del_root_ref to return -ENOENT here is incorrect.
	 * Instead simply lookup the dir_index_item for this entry so we can
	 * remove it.  Otherwise we know we have a ref to the root and we can
	 * call btrfs_del_root_ref, and it _shouldn't_ fail.
	 */
	if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID) {
		di = btrfs_search_dir_index_item(root, path, dir_ino, &fname.disk_name);
		if (IS_ERR_OR_NULL(di)) {
			if (!di)
				ret = -ENOENT;
			else
				ret = PTR_ERR(di);
			btrfs_abort_transaction(trans, ret);
			goto out;
		}

		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		index = key.offset;
		btrfs_release_path(path);
	} else {
		ret = btrfs_del_root_ref(trans, objectid,
					 root->root_key.objectid, dir_ino,
					 &index, &fname.disk_name);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
	}

	ret = btrfs_delete_delayed_dir_index(trans, dir, index);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	btrfs_i_size_write(dir, dir->vfs_inode.i_size - fname.disk_name.len * 2);
	inode_inc_iversion(&dir->vfs_inode);
	inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
	ret = btrfs_update_inode_fallback(trans, dir);
	if (ret)
		btrfs_abort_transaction(trans, ret);
out:
	btrfs_free_path(path);
	fscrypt_free_filename(&fname);
	return ret;
}

/*
 * Helper to check if the subvolume references other subvolumes or if it's
 * default.
 */
static noinline int may_destroy_subvol(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct btrfs_dir_item *di;
	struct btrfs_key key;
	struct fscrypt_str name = FSTR_INIT("default", 7);
	u64 dir_id;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	/* Make sure this root isn't set as the default subvol */
	dir_id = btrfs_super_root_dir(fs_info->super_copy);
	di = btrfs_lookup_dir_item(NULL, fs_info->tree_root, path,
				   dir_id, &name, 0);
	if (di && !IS_ERR(di)) {
		btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
		if (key.objectid == root->root_key.objectid) {
			ret = -EPERM;
			btrfs_err(fs_info,
				  "deleting default subvolume %llu is not allowed",
				  key.objectid);
			goto out;
		}
		btrfs_release_path(path);
	}

	key.objectid = root->root_key.objectid;
	key.type = BTRFS_ROOT_REF_KEY;
	key.offset = (u64)-1;

	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
	if (ret < 0)
		goto out;
	BUG_ON(ret == 0);

	ret = 0;
	if (path->slots[0] > 0) {
		path->slots[0]--;
		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (key.objectid == root->root_key.objectid &&
		    key.type == BTRFS_ROOT_REF_KEY)
			ret = -ENOTEMPTY;
	}
out:
	btrfs_free_path(path);
	return ret;
}

/* Delete all dentries for inodes belonging to the root */
static void btrfs_prune_dentries(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct rb_node *node;
	struct rb_node *prev;
	struct btrfs_inode *entry;
	struct inode *inode;
	u64 objectid = 0;

	if (!BTRFS_FS_ERROR(fs_info))
		WARN_ON(btrfs_root_refs(&root->root_item) != 0);

	spin_lock(&root->inode_lock);
again:
	node = root->inode_tree.rb_node;
	prev = NULL;
	while (node) {
		prev = node;
		entry = rb_entry(node, struct btrfs_inode, rb_node);

		if (objectid < btrfs_ino(entry))
			node = node->rb_left;
		else if (objectid > btrfs_ino(entry))
			node = node->rb_right;
		else
			break;
	}
	if (!node) {
		while (prev) {
			entry = rb_entry(prev, struct btrfs_inode, rb_node);
			if (objectid <= btrfs_ino(entry)) {
				node = prev;
				break;
			}
			prev = rb_next(prev);
		}
	}
	while (node) {
		entry = rb_entry(node, struct btrfs_inode, rb_node);
		objectid = btrfs_ino(entry) + 1;
		inode = igrab(&entry->vfs_inode);
		if (inode) {
			spin_unlock(&root->inode_lock);
			if (atomic_read(&inode->i_count) > 1)
				d_prune_aliases(inode);
			/*
			 * btrfs_drop_inode will have it removed from the inode
			 * cache when its usage count hits zero.
			 */
			iput(inode);
			cond_resched();
			spin_lock(&root->inode_lock);
			goto again;
		}

		if (cond_resched_lock(&root->inode_lock))
			goto again;

		node = rb_next(node);
	}
	spin_unlock(&root->inode_lock);
}

int btrfs_delete_subvolume(struct btrfs_inode *dir, struct dentry *dentry)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dentry->d_sb);
	struct btrfs_root *root = dir->root;
	struct inode *inode = d_inode(dentry);
	struct btrfs_root *dest = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
	struct btrfs_block_rsv block_rsv;
	u64 root_flags;
	int ret;

	down_write(&fs_info->subvol_sem);

	/*
	 * Don't allow to delete a subvolume with send in progress. This is
	 * inside the inode lock so the error handling that has to drop the bit
	 * again is not run concurrently.
	 */
	spin_lock(&dest->root_item_lock);
	if (dest->send_in_progress) {
		spin_unlock(&dest->root_item_lock);
		btrfs_warn(fs_info,
			   "attempt to delete subvolume %llu during send",
			   dest->root_key.objectid);
		ret = -EPERM;
		goto out_up_write;
	}
	if (atomic_read(&dest->nr_swapfiles)) {
		spin_unlock(&dest->root_item_lock);
		btrfs_warn(fs_info,
			   "attempt to delete subvolume %llu with active swapfile",
			   root->root_key.objectid);
		ret = -EPERM;
		goto out_up_write;
	}
	root_flags = btrfs_root_flags(&dest->root_item);
	btrfs_set_root_flags(&dest->root_item,
			     root_flags | BTRFS_ROOT_SUBVOL_DEAD);
	spin_unlock(&dest->root_item_lock);

	ret = may_destroy_subvol(dest);
	if (ret)
		goto out_undead;

	btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
	/*
	 * One for dir inode,
	 * two for dir entries,
	 * two for root ref/backref.
	 */
	ret = btrfs_subvolume_reserve_metadata(root, &block_rsv, 5, true);
	if (ret)
		goto out_undead;

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out_release;
	}
	trans->block_rsv = &block_rsv;
	trans->bytes_reserved = block_rsv.size;

	btrfs_record_snapshot_destroy(trans, dir);

	ret = btrfs_unlink_subvol(trans, dir, dentry);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_end_trans;
	}

	ret = btrfs_record_root_in_trans(trans, dest);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_end_trans;
	}

	memset(&dest->root_item.drop_progress, 0,
		sizeof(dest->root_item.drop_progress));
	btrfs_set_root_drop_level(&dest->root_item, 0);
	btrfs_set_root_refs(&dest->root_item, 0);

	if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
		ret = btrfs_insert_orphan_item(trans,
					fs_info->tree_root,
					dest->root_key.objectid);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out_end_trans;
		}
	}

	ret = btrfs_uuid_tree_remove(trans, dest->root_item.uuid,
				  BTRFS_UUID_KEY_SUBVOL,
				  dest->root_key.objectid);
	if (ret && ret != -ENOENT) {
		btrfs_abort_transaction(trans, ret);
		goto out_end_trans;
	}
	if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
		ret = btrfs_uuid_tree_remove(trans,
					  dest->root_item.received_uuid,
					  BTRFS_UUID_KEY_RECEIVED_SUBVOL,
					  dest->root_key.objectid);
		if (ret && ret != -ENOENT) {
			btrfs_abort_transaction(trans, ret);
			goto out_end_trans;
		}
	}

	free_anon_bdev(dest->anon_dev);
	dest->anon_dev = 0;
out_end_trans:
	trans->block_rsv = NULL;
	trans->bytes_reserved = 0;
	ret = btrfs_end_transaction(trans);
	inode->i_flags |= S_DEAD;
out_release:
	btrfs_subvolume_release_metadata(root, &block_rsv);
out_undead:
	if (ret) {
		spin_lock(&dest->root_item_lock);
		root_flags = btrfs_root_flags(&dest->root_item);
		btrfs_set_root_flags(&dest->root_item,
				root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
		spin_unlock(&dest->root_item_lock);
	}
out_up_write:
	up_write(&fs_info->subvol_sem);
	if (!ret) {
		d_invalidate(dentry);
		btrfs_prune_dentries(dest);
		ASSERT(dest->send_in_progress == 0);
	}

	return ret;
}

static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
	int err = 0;
	struct btrfs_trans_handle *trans;
	u64 last_unlink_trans;
	struct fscrypt_name fname;

	if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
		return -ENOTEMPTY;
	if (btrfs_ino(BTRFS_I(inode)) == BTRFS_FIRST_FREE_OBJECTID) {
		if (unlikely(btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))) {
			btrfs_err(fs_info,
			"extent tree v2 doesn't support snapshot deletion yet");
			return -EOPNOTSUPP;
		}
		return btrfs_delete_subvolume(BTRFS_I(dir), dentry);
	}

	err = fscrypt_setup_filename(dir, &dentry->d_name, 1, &fname);
	if (err)
		return err;

	/* This needs to handle no-key deletions later on */

	trans = __unlink_start_trans(BTRFS_I(dir));
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_notrans;
	}

	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
		err = btrfs_unlink_subvol(trans, BTRFS_I(dir), dentry);
		goto out;
	}

	err = btrfs_orphan_add(trans, BTRFS_I(inode));
	if (err)
		goto out;

	last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;

	/* now the directory is empty */
	err = btrfs_unlink_inode(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
				 &fname.disk_name);
	if (!err) {
		btrfs_i_size_write(BTRFS_I(inode), 0);
		/*
		 * Propagate the last_unlink_trans value of the deleted dir to
		 * its parent directory. This is to prevent an unrecoverable
		 * log tree in the case we do something like this:
		 * 1) create dir foo
		 * 2) create snapshot under dir foo
		 * 3) delete the snapshot
		 * 4) rmdir foo
		 * 5) mkdir foo
		 * 6) fsync foo or some file inside foo
		 */
		if (last_unlink_trans >= trans->transid)
			BTRFS_I(dir)->last_unlink_trans = last_unlink_trans;
	}
out:
	btrfs_end_transaction(trans);
out_notrans:
	btrfs_btree_balance_dirty(fs_info);
	fscrypt_free_filename(&fname);

	return err;
}

/*
 * Read, zero a chunk and write a block.
 *
 * @inode - inode that we're zeroing
 * @from - the offset to start zeroing
 * @len - the length to zero, 0 to zero the entire range respective to the
 *	offset
 * @front - zero up to the offset instead of from the offset on
 *
 * This will find the block for the "from" offset and cow the block and zero the
 * part we want to zero.  This is used with truncate and hole punching.
 */
int btrfs_truncate_block(struct btrfs_inode *inode, loff_t from, loff_t len,
			 int front)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct address_space *mapping = inode->vfs_inode.i_mapping;
	struct extent_io_tree *io_tree = &inode->io_tree;
	struct btrfs_ordered_extent *ordered;
	struct extent_state *cached_state = NULL;
	struct extent_changeset *data_reserved = NULL;
	bool only_release_metadata = false;
	u32 blocksize = fs_info->sectorsize;
	pgoff_t index = from >> PAGE_SHIFT;
	unsigned offset = from & (blocksize - 1);
	struct page *page;
	gfp_t mask = btrfs_alloc_write_mask(mapping);
	size_t write_bytes = blocksize;
	int ret = 0;
	u64 block_start;
	u64 block_end;

	if (IS_ALIGNED(offset, blocksize) &&
	    (!len || IS_ALIGNED(len, blocksize)))
		goto out;

	block_start = round_down(from, blocksize);
	block_end = block_start + blocksize - 1;

	ret = btrfs_check_data_free_space(inode, &data_reserved, block_start,
					  blocksize, false);
	if (ret < 0) {
		if (btrfs_check_nocow_lock(inode, block_start, &write_bytes, false) > 0) {
			/* For nocow case, no need to reserve data space */
			only_release_metadata = true;
		} else {
			goto out;
		}
	}
	ret = btrfs_delalloc_reserve_metadata(inode, blocksize, blocksize, false);
	if (ret < 0) {
		if (!only_release_metadata)
			btrfs_free_reserved_data_space(inode, data_reserved,
						       block_start, blocksize);
		goto out;
	}
again:
	page = find_or_create_page(mapping, index, mask);
	if (!page) {
		btrfs_delalloc_release_space(inode, data_reserved, block_start,
					     blocksize, true);
		btrfs_delalloc_release_extents(inode, blocksize);
		ret = -ENOMEM;
		goto out;
	}

	if (!PageUptodate(page)) {
		ret = btrfs_read_folio(NULL, page_folio(page));
		lock_page(page);
		if (page->mapping != mapping) {
			unlock_page(page);
			put_page(page);
			goto again;
		}
		if (!PageUptodate(page)) {
			ret = -EIO;
			goto out_unlock;
		}
	}

	/*
	 * We unlock the page after the io is completed and then re-lock it
	 * above.  release_folio() could have come in between that and cleared
	 * folio private, but left the page in the mapping.  Set the page mapped
	 * here to make sure it's properly set for the subpage stuff.
	 */
	ret = set_page_extent_mapped(page);
	if (ret < 0)
		goto out_unlock;

	wait_on_page_writeback(page);

	lock_extent(io_tree, block_start, block_end, &cached_state);

	ordered = btrfs_lookup_ordered_extent(inode, block_start);
	if (ordered) {
		unlock_extent(io_tree, block_start, block_end, &cached_state);
		unlock_page(page);
		put_page(page);
		btrfs_start_ordered_extent(ordered);
		btrfs_put_ordered_extent(ordered);
		goto again;
	}

	clear_extent_bit(&inode->io_tree, block_start, block_end,
			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
			 &cached_state);

	ret = btrfs_set_extent_delalloc(inode, block_start, block_end, 0,
					&cached_state);
	if (ret) {
		unlock_extent(io_tree, block_start, block_end, &cached_state);
		goto out_unlock;
	}

	if (offset != blocksize) {
		if (!len)
			len = blocksize - offset;
		if (front)
			memzero_page(page, (block_start - page_offset(page)),
				     offset);
		else
			memzero_page(page, (block_start - page_offset(page)) + offset,
				     len);
	}
	btrfs_folio_clear_checked(fs_info, page_folio(page), block_start,
				  block_end + 1 - block_start);
	btrfs_folio_set_dirty(fs_info, page_folio(page), block_start,
			      block_end + 1 - block_start);
	unlock_extent(io_tree, block_start, block_end, &cached_state);

	if (only_release_metadata)
		set_extent_bit(&inode->io_tree, block_start, block_end,
			       EXTENT_NORESERVE, NULL);

out_unlock:
	if (ret) {
		if (only_release_metadata)
			btrfs_delalloc_release_metadata(inode, blocksize, true);
		else
			btrfs_delalloc_release_space(inode, data_reserved,
					block_start, blocksize, true);
	}
	btrfs_delalloc_release_extents(inode, blocksize);
	unlock_page(page);
	put_page(page);
out:
	if (only_release_metadata)
		btrfs_check_nocow_unlock(inode);
	extent_changeset_free(data_reserved);
	return ret;
}

static int maybe_insert_hole(struct btrfs_inode *inode, u64 offset, u64 len)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	struct btrfs_drop_extents_args drop_args = { 0 };
	int ret;

	/*
	 * If NO_HOLES is enabled, we don't need to do anything.
	 * Later, up in the call chain, either btrfs_set_inode_last_sub_trans()
	 * or btrfs_update_inode() will be called, which guarantee that the next
	 * fsync will know this inode was changed and needs to be logged.
	 */
	if (btrfs_fs_incompat(fs_info, NO_HOLES))
		return 0;

	/*
	 * 1 - for the one we're dropping
	 * 1 - for the one we're adding
	 * 1 - for updating the inode.
	 */
	trans = btrfs_start_transaction(root, 3);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	drop_args.start = offset;
	drop_args.end = offset + len;
	drop_args.drop_cache = true;

	ret = btrfs_drop_extents(trans, root, inode, &drop_args);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		btrfs_end_transaction(trans);
		return ret;
	}

	ret = btrfs_insert_hole_extent(trans, root, btrfs_ino(inode), offset, len);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
	} else {
		btrfs_update_inode_bytes(inode, 0, drop_args.bytes_found);
		btrfs_update_inode(trans, inode);
	}
	btrfs_end_transaction(trans);
	return ret;
}

/*
 * This function puts in dummy file extents for the area we're creating a hole
 * for.  So if we are truncating this file to a larger size we need to insert
 * these file extents so that btrfs_get_extent will return a EXTENT_MAP_HOLE for
 * the range between oldsize and size
 */
int btrfs_cont_expand(struct btrfs_inode *inode, loff_t oldsize, loff_t size)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct extent_io_tree *io_tree = &inode->io_tree;
	struct extent_map *em = NULL;
	struct extent_state *cached_state = NULL;
	u64 hole_start = ALIGN(oldsize, fs_info->sectorsize);
	u64 block_end = ALIGN(size, fs_info->sectorsize);
	u64 last_byte;
	u64 cur_offset;
	u64 hole_size;
	int err = 0;

	/*
	 * If our size started in the middle of a block we need to zero out the
	 * rest of the block before we expand the i_size, otherwise we could
	 * expose stale data.
	 */
	err = btrfs_truncate_block(inode, oldsize, 0, 0);
	if (err)
		return err;

	if (size <= hole_start)
		return 0;

	btrfs_lock_and_flush_ordered_range(inode, hole_start, block_end - 1,
					   &cached_state);
	cur_offset = hole_start;
	while (1) {
		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
				      block_end - cur_offset);
		if (IS_ERR(em)) {
			err = PTR_ERR(em);
			em = NULL;
			break;
		}
		last_byte = min(extent_map_end(em), block_end);
		last_byte = ALIGN(last_byte, fs_info->sectorsize);
		hole_size = last_byte - cur_offset;

		if (!(em->flags & EXTENT_FLAG_PREALLOC)) {
			struct extent_map *hole_em;

			err = maybe_insert_hole(inode, cur_offset, hole_size);
			if (err)
				break;

			err = btrfs_inode_set_file_extent_range(inode,
							cur_offset, hole_size);
			if (err)
				break;

			hole_em = alloc_extent_map();
			if (!hole_em) {
				btrfs_drop_extent_map_range(inode, cur_offset,
						    cur_offset + hole_size - 1,
						    false);
				btrfs_set_inode_full_sync(inode);
				goto next;
			}
			hole_em->start = cur_offset;
			hole_em->len = hole_size;
			hole_em->orig_start = cur_offset;

			hole_em->block_start = EXTENT_MAP_HOLE;
			hole_em->block_len = 0;
			hole_em->orig_block_len = 0;
			hole_em->ram_bytes = hole_size;
			hole_em->generation = btrfs_get_fs_generation(fs_info);

			err = btrfs_replace_extent_map_range(inode, hole_em, true);
			free_extent_map(hole_em);
		} else {
			err = btrfs_inode_set_file_extent_range(inode,
							cur_offset, hole_size);
			if (err)
				break;
		}
next:
		free_extent_map(em);
		em = NULL;
		cur_offset = last_byte;
		if (cur_offset >= block_end)
			break;
	}
	free_extent_map(em);
	unlock_extent(io_tree, hole_start, block_end - 1, &cached_state);
	return err;
}

static int btrfs_setsize(struct inode *inode, struct iattr *attr)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_trans_handle *trans;
	loff_t oldsize = i_size_read(inode);
	loff_t newsize = attr->ia_size;
	int mask = attr->ia_valid;
	int ret;

	/*
	 * The regular truncate() case without ATTR_CTIME and ATTR_MTIME is a
	 * special case where we need to update the times despite not having
	 * these flags set.  For all other operations the VFS set these flags
	 * explicitly if it wants a timestamp update.
	 */
	if (newsize != oldsize) {
		inode_inc_iversion(inode);
		if (!(mask & (ATTR_CTIME | ATTR_MTIME))) {
			inode_set_mtime_to_ts(inode,
					      inode_set_ctime_current(inode));
		}
	}

	if (newsize > oldsize) {
		/*
		 * Don't do an expanding truncate while snapshotting is ongoing.
		 * This is to ensure the snapshot captures a fully consistent
		 * state of this file - if the snapshot captures this expanding
		 * truncation, it must capture all writes that happened before
		 * this truncation.
		 */
		btrfs_drew_write_lock(&root->snapshot_lock);
		ret = btrfs_cont_expand(BTRFS_I(inode), oldsize, newsize);
		if (ret) {
			btrfs_drew_write_unlock(&root->snapshot_lock);
			return ret;
		}

		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans)) {
			btrfs_drew_write_unlock(&root->snapshot_lock);
			return PTR_ERR(trans);
		}

		i_size_write(inode, newsize);
		btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
		pagecache_isize_extended(inode, oldsize, newsize);
		ret = btrfs_update_inode(trans, BTRFS_I(inode));
		btrfs_drew_write_unlock(&root->snapshot_lock);
		btrfs_end_transaction(trans);
	} else {
		struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);

		if (btrfs_is_zoned(fs_info)) {
			ret = btrfs_wait_ordered_range(inode,
					ALIGN(newsize, fs_info->sectorsize),
					(u64)-1);
			if (ret)
				return ret;
		}

		/*
		 * We're truncating a file that used to have good data down to
		 * zero. Make sure any new writes to the file get on disk
		 * on close.
		 */
		if (newsize == 0)
			set_bit(BTRFS_INODE_FLUSH_ON_CLOSE,
				&BTRFS_I(inode)->runtime_flags);

		truncate_setsize(inode, newsize);

		inode_dio_wait(inode);

		ret = btrfs_truncate(BTRFS_I(inode), newsize == oldsize);
		if (ret && inode->i_nlink) {
			int err;

			/*
			 * Truncate failed, so fix up the in-memory size. We
			 * adjusted disk_i_size down as we removed extents, so
			 * wait for disk_i_size to be stable and then update the
			 * in-memory size to match.
			 */
			err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
			if (err)
				return err;
			i_size_write(inode, BTRFS_I(inode)->disk_i_size);
		}
	}

	return ret;
}

static int btrfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
			 struct iattr *attr)
{
	struct inode *inode = d_inode(dentry);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	int err;

	if (btrfs_root_readonly(root))
		return -EROFS;

	err = setattr_prepare(idmap, dentry, attr);
	if (err)
		return err;

	if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
		err = btrfs_setsize(inode, attr);
		if (err)
			return err;
	}

	if (attr->ia_valid) {
		setattr_copy(idmap, inode, attr);
		inode_inc_iversion(inode);
		err = btrfs_dirty_inode(BTRFS_I(inode));

		if (!err && attr->ia_valid & ATTR_MODE)
			err = posix_acl_chmod(idmap, dentry, inode->i_mode);
	}

	return err;
}

/*
 * While truncating the inode pages during eviction, we get the VFS
 * calling btrfs_invalidate_folio() against each folio of the inode. This
 * is slow because the calls to btrfs_invalidate_folio() result in a
 * huge amount of calls to lock_extent() and clear_extent_bit(),
 * which keep merging and splitting extent_state structures over and over,
 * wasting lots of time.
 *
 * Therefore if the inode is being evicted, let btrfs_invalidate_folio()
 * skip all those expensive operations on a per folio basis and do only
 * the ordered io finishing, while we release here the extent_map and
 * extent_state structures, without the excessive merging and splitting.
 */
static void evict_inode_truncate_pages(struct inode *inode)
{
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct rb_node *node;

	ASSERT(inode->i_state & I_FREEING);
	truncate_inode_pages_final(&inode->i_data);

	btrfs_drop_extent_map_range(BTRFS_I(inode), 0, (u64)-1, false);

	/*
	 * Keep looping until we have no more ranges in the io tree.
	 * We can have ongoing bios started by readahead that have
	 * their endio callback (extent_io.c:end_bio_extent_readpage)
	 * still in progress (unlocked the pages in the bio but did not yet
	 * unlocked the ranges in the io tree). Therefore this means some
	 * ranges can still be locked and eviction started because before
	 * submitting those bios, which are executed by a separate task (work
	 * queue kthread), inode references (inode->i_count) were not taken
	 * (which would be dropped in the end io callback of each bio).
	 * Therefore here we effectively end up waiting for those bios and
	 * anyone else holding locked ranges without having bumped the inode's
	 * reference count - if we don't do it, when they access the inode's
	 * io_tree to unlock a range it may be too late, leading to an
	 * use-after-free issue.
	 */
	spin_lock(&io_tree->lock);
	while (!RB_EMPTY_ROOT(&io_tree->state)) {
		struct extent_state *state;
		struct extent_state *cached_state = NULL;
		u64 start;
		u64 end;
		unsigned state_flags;

		node = rb_first(&io_tree->state);
		state = rb_entry(node, struct extent_state, rb_node);
		start = state->start;
		end = state->end;
		state_flags = state->state;
		spin_unlock(&io_tree->lock);

		lock_extent(io_tree, start, end, &cached_state);

		/*
		 * If still has DELALLOC flag, the extent didn't reach disk,
		 * and its reserved space won't be freed by delayed_ref.
		 * So we need to free its reserved space here.
		 * (Refer to comment in btrfs_invalidate_folio, case 2)
		 *
		 * Note, end is the bytenr of last byte, so we need + 1 here.
		 */
		if (state_flags & EXTENT_DELALLOC)
			btrfs_qgroup_free_data(BTRFS_I(inode), NULL, start,
					       end - start + 1, NULL);

		clear_extent_bit(io_tree, start, end,
				 EXTENT_CLEAR_ALL_BITS | EXTENT_DO_ACCOUNTING,
				 &cached_state);

		cond_resched();
		spin_lock(&io_tree->lock);
	}
	spin_unlock(&io_tree->lock);
}

static struct btrfs_trans_handle *evict_refill_and_join(struct btrfs_root *root,
							struct btrfs_block_rsv *rsv)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	u64 delayed_refs_extra = btrfs_calc_delayed_ref_bytes(fs_info, 1);
	int ret;

	/*
	 * Eviction should be taking place at some place safe because of our
	 * delayed iputs.  However the normal flushing code will run delayed
	 * iputs, so we cannot use FLUSH_ALL otherwise we'll deadlock.
	 *
	 * We reserve the delayed_refs_extra here again because we can't use
	 * btrfs_start_transaction(root, 0) for the same deadlocky reason as
	 * above.  We reserve our extra bit here because we generate a ton of
	 * delayed refs activity by truncating.
	 *
	 * BTRFS_RESERVE_FLUSH_EVICT will steal from the global_rsv if it can,
	 * if we fail to make this reservation we can re-try without the
	 * delayed_refs_extra so we can make some forward progress.
	 */
	ret = btrfs_block_rsv_refill(fs_info, rsv, rsv->size + delayed_refs_extra,
				     BTRFS_RESERVE_FLUSH_EVICT);
	if (ret) {
		ret = btrfs_block_rsv_refill(fs_info, rsv, rsv->size,
					     BTRFS_RESERVE_FLUSH_EVICT);
		if (ret) {
			btrfs_warn(fs_info,
				   "could not allocate space for delete; will truncate on mount");
			return ERR_PTR(-ENOSPC);
		}
		delayed_refs_extra = 0;
	}

	trans = btrfs_join_transaction(root);
	if (IS_ERR(trans))
		return trans;

	if (delayed_refs_extra) {
		trans->block_rsv = &fs_info->trans_block_rsv;
		trans->bytes_reserved = delayed_refs_extra;
		btrfs_block_rsv_migrate(rsv, trans->block_rsv,
					delayed_refs_extra, true);
	}
	return trans;
}

void btrfs_evict_inode(struct inode *inode)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_block_rsv *rsv = NULL;
	int ret;

	trace_btrfs_inode_evict(inode);

	if (!root) {
		fsverity_cleanup_inode(inode);
		clear_inode(inode);
		return;
	}

	evict_inode_truncate_pages(inode);

	if (inode->i_nlink &&
	    ((btrfs_root_refs(&root->root_item) != 0 &&
	      root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) ||
	     btrfs_is_free_space_inode(BTRFS_I(inode))))
		goto out;

	if (is_bad_inode(inode))
		goto out;

	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags))
		goto out;

	if (inode->i_nlink > 0) {
		BUG_ON(btrfs_root_refs(&root->root_item) != 0 &&
		       root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID);
		goto out;
	}

	/*
	 * This makes sure the inode item in tree is uptodate and the space for
	 * the inode update is released.
	 */
	ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode));
	if (ret)
		goto out;

	/*
	 * This drops any pending insert or delete operations we have for this
	 * inode.  We could have a delayed dir index deletion queued up, but
	 * we're removing the inode completely so that'll be taken care of in
	 * the truncate.
	 */
	btrfs_kill_delayed_inode_items(BTRFS_I(inode));

	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
	if (!rsv)
		goto out;
	rsv->size = btrfs_calc_metadata_size(fs_info, 1);
	rsv->failfast = true;

	btrfs_i_size_write(BTRFS_I(inode), 0);

	while (1) {
		struct btrfs_truncate_control control = {
			.inode = BTRFS_I(inode),
			.ino = btrfs_ino(BTRFS_I(inode)),
			.new_size = 0,
			.min_type = 0,
		};

		trans = evict_refill_and_join(root, rsv);
		if (IS_ERR(trans))
			goto out;

		trans->block_rsv = rsv;

		ret = btrfs_truncate_inode_items(trans, root, &control);
		trans->block_rsv = &fs_info->trans_block_rsv;
		btrfs_end_transaction(trans);
		/*
		 * We have not added new delayed items for our inode after we
		 * have flushed its delayed items, so no need to throttle on
		 * delayed items. However we have modified extent buffers.
		 */
		btrfs_btree_balance_dirty_nodelay(fs_info);
		if (ret && ret != -ENOSPC && ret != -EAGAIN)
			goto out;
		else if (!ret)
			break;
	}

	/*
	 * Errors here aren't a big deal, it just means we leave orphan items in
	 * the tree. They will be cleaned up on the next mount. If the inode
	 * number gets reused, cleanup deletes the orphan item without doing
	 * anything, and unlink reuses the existing orphan item.
	 *
	 * If it turns out that we are dropping too many of these, we might want
	 * to add a mechanism for retrying these after a commit.
	 */
	trans = evict_refill_and_join(root, rsv);
	if (!IS_ERR(trans)) {
		trans->block_rsv = rsv;
		btrfs_orphan_del(trans, BTRFS_I(inode));
		trans->block_rsv = &fs_info->trans_block_rsv;
		btrfs_end_transaction(trans);
	}

out:
	btrfs_free_block_rsv(fs_info, rsv);
	/*
	 * If we didn't successfully delete, the orphan item will still be in
	 * the tree and we'll retry on the next mount. Again, we might also want
	 * to retry these periodically in the future.
	 */
	btrfs_remove_delayed_node(BTRFS_I(inode));
	fsverity_cleanup_inode(inode);
	clear_inode(inode);
}

/*
 * Return the key found in the dir entry in the location pointer, fill @type
 * with BTRFS_FT_*, and return 0.
 *
 * If no dir entries were found, returns -ENOENT.
 * If found a corrupted location in dir entry, returns -EUCLEAN.
 */
static int btrfs_inode_by_name(struct btrfs_inode *dir, struct dentry *dentry,
			       struct btrfs_key *location, u8 *type)
{
	struct btrfs_dir_item *di;
	struct btrfs_path *path;
	struct btrfs_root *root = dir->root;
	int ret = 0;
	struct fscrypt_name fname;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = fscrypt_setup_filename(&dir->vfs_inode, &dentry->d_name, 1, &fname);
	if (ret < 0)
		goto out;
	/*
	 * fscrypt_setup_filename() should never return a positive value, but
	 * gcc on sparc/parisc thinks it can, so assert that doesn't happen.
	 */
	ASSERT(ret == 0);

	/* This needs to handle no-key deletions later on */

	di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(dir),
				   &fname.disk_name, 0);
	if (IS_ERR_OR_NULL(di)) {
		ret = di ? PTR_ERR(di) : -ENOENT;
		goto out;
	}

	btrfs_dir_item_key_to_cpu(path->nodes[0], di, location);
	if (location->type != BTRFS_INODE_ITEM_KEY &&
	    location->type != BTRFS_ROOT_ITEM_KEY) {
		ret = -EUCLEAN;
		btrfs_warn(root->fs_info,
"%s gets something invalid in DIR_ITEM (name %s, directory ino %llu, location(%llu %u %llu))",
			   __func__, fname.disk_name.name, btrfs_ino(dir),
			   location->objectid, location->type, location->offset);
	}
	if (!ret)
		*type = btrfs_dir_ftype(path->nodes[0], di);
out:
	fscrypt_free_filename(&fname);
	btrfs_free_path(path);
	return ret;
}

/*
 * when we hit a tree root in a directory, the btrfs part of the inode
 * needs to be changed to reflect the root directory of the tree root.  This
 * is kind of like crossing a mount point.
 */
static int fixup_tree_root_location(struct btrfs_fs_info *fs_info,
				    struct btrfs_inode *dir,
				    struct dentry *dentry,
				    struct btrfs_key *location,
				    struct btrfs_root **sub_root)
{
	struct btrfs_path *path;
	struct btrfs_root *new_root;
	struct btrfs_root_ref *ref;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	int ret;
	int err = 0;
	struct fscrypt_name fname;

	ret = fscrypt_setup_filename(&dir->vfs_inode, &dentry->d_name, 0, &fname);
	if (ret)
		return ret;

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

	err = -ENOENT;
	key.objectid = dir->root->root_key.objectid;
	key.type = BTRFS_ROOT_REF_KEY;
	key.offset = location->objectid;

	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
	if (ret) {
		if (ret < 0)
			err = ret;
		goto out;
	}

	leaf = path->nodes[0];
	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
	if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(dir) ||
	    btrfs_root_ref_name_len(leaf, ref) != fname.disk_name.len)
		goto out;

	ret = memcmp_extent_buffer(leaf, fname.disk_name.name,
				   (unsigned long)(ref + 1), fname.disk_name.len);
	if (ret)
		goto out;

	btrfs_release_path(path);

	new_root = btrfs_get_fs_root(fs_info, location->objectid, true);
	if (IS_ERR(new_root)) {
		err = PTR_ERR(new_root);
		goto out;
	}

	*sub_root = new_root;
	location->objectid = btrfs_root_dirid(&new_root->root_item);
	location->type = BTRFS_INODE_ITEM_KEY;
	location->offset = 0;
	err = 0;
out:
	btrfs_free_path(path);
	fscrypt_free_filename(&fname);
	return err;
}

static void inode_tree_add(struct btrfs_inode *inode)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_inode *entry;
	struct rb_node **p;
	struct rb_node *parent;
	struct rb_node *new = &inode->rb_node;
	u64 ino = btrfs_ino(inode);

	if (inode_unhashed(&inode->vfs_inode))
		return;
	parent = NULL;
	spin_lock(&root->inode_lock);
	p = &root->inode_tree.rb_node;
	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct btrfs_inode, rb_node);

		if (ino < btrfs_ino(entry))
			p = &parent->rb_left;
		else if (ino > btrfs_ino(entry))
			p = &parent->rb_right;
		else {
			WARN_ON(!(entry->vfs_inode.i_state &
				  (I_WILL_FREE | I_FREEING)));
			rb_replace_node(parent, new, &root->inode_tree);
			RB_CLEAR_NODE(parent);
			spin_unlock(&root->inode_lock);
			return;
		}
	}
	rb_link_node(new, parent, p);
	rb_insert_color(new, &root->inode_tree);
	spin_unlock(&root->inode_lock);
}

static void inode_tree_del(struct btrfs_inode *inode)
{
	struct btrfs_root *root = inode->root;
	int empty = 0;

	spin_lock(&root->inode_lock);
	if (!RB_EMPTY_NODE(&inode->rb_node)) {
		rb_erase(&inode->rb_node, &root->inode_tree);
		RB_CLEAR_NODE(&inode->rb_node);
		empty = RB_EMPTY_ROOT(&root->inode_tree);
	}
	spin_unlock(&root->inode_lock);

	if (empty && btrfs_root_refs(&root->root_item) == 0) {
		spin_lock(&root->inode_lock);
		empty = RB_EMPTY_ROOT(&root->inode_tree);
		spin_unlock(&root->inode_lock);
		if (empty)
			btrfs_add_dead_root(root);
	}
}


static int btrfs_init_locked_inode(struct inode *inode, void *p)
{
	struct btrfs_iget_args *args = p;

	inode->i_ino = args->ino;
	BTRFS_I(inode)->location.objectid = args->ino;
	BTRFS_I(inode)->location.type = BTRFS_INODE_ITEM_KEY;
	BTRFS_I(inode)->location.offset = 0;
	BTRFS_I(inode)->root = btrfs_grab_root(args->root);
	BUG_ON(args->root && !BTRFS_I(inode)->root);

	if (args->root && args->root == args->root->fs_info->tree_root &&
	    args->ino != BTRFS_BTREE_INODE_OBJECTID)
		set_bit(BTRFS_INODE_FREE_SPACE_INODE,
			&BTRFS_I(inode)->runtime_flags);
	return 0;
}

static int btrfs_find_actor(struct inode *inode, void *opaque)
{
	struct btrfs_iget_args *args = opaque;

	return args->ino == BTRFS_I(inode)->location.objectid &&
		args->root == BTRFS_I(inode)->root;
}

static struct inode *btrfs_iget_locked(struct super_block *s, u64 ino,
				       struct btrfs_root *root)
{
	struct inode *inode;
	struct btrfs_iget_args args;
	unsigned long hashval = btrfs_inode_hash(ino, root);

	args.ino = ino;
	args.root = root;

	inode = iget5_locked(s, hashval, btrfs_find_actor,
			     btrfs_init_locked_inode,
			     (void *)&args);
	return inode;
}

/*
 * Get an inode object given its inode number and corresponding root.
 * Path can be preallocated to prevent recursing back to iget through
 * allocator. NULL is also valid but may require an additional allocation
 * later.
 */
struct inode *btrfs_iget_path(struct super_block *s, u64 ino,
			      struct btrfs_root *root, struct btrfs_path *path)
{
	struct inode *inode;

	inode = btrfs_iget_locked(s, ino, root);
	if (!inode)
		return ERR_PTR(-ENOMEM);

	if (inode->i_state & I_NEW) {
		int ret;

		ret = btrfs_read_locked_inode(inode, path);
		if (!ret) {
			inode_tree_add(BTRFS_I(inode));
			unlock_new_inode(inode);
		} else {
			iget_failed(inode);
			/*
			 * ret > 0 can come from btrfs_search_slot called by
			 * btrfs_read_locked_inode, this means the inode item
			 * was not found.
			 */
			if (ret > 0)
				ret = -ENOENT;
			inode = ERR_PTR(ret);
		}
	}

	return inode;
}

struct inode *btrfs_iget(struct super_block *s, u64 ino, struct btrfs_root *root)
{
	return btrfs_iget_path(s, ino, root, NULL);
}

static struct inode *new_simple_dir(struct inode *dir,
				    struct btrfs_key *key,
				    struct btrfs_root *root)
{
	struct timespec64 ts;
	struct inode *inode = new_inode(dir->i_sb);

	if (!inode)
		return ERR_PTR(-ENOMEM);

	BTRFS_I(inode)->root = btrfs_grab_root(root);
	memcpy(&BTRFS_I(inode)->location, key, sizeof(*key));
	set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);

	inode->i_ino = BTRFS_EMPTY_SUBVOL_DIR_OBJECTID;
	/*
	 * We only need lookup, the rest is read-only and there's no inode
	 * associated with the dentry
	 */
	inode->i_op = &simple_dir_inode_operations;
	inode->i_opflags &= ~IOP_XATTR;
	inode->i_fop = &simple_dir_operations;
	inode->i_mode = S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO;

	ts = inode_set_ctime_current(inode);
	inode_set_mtime_to_ts(inode, ts);
	inode_set_atime_to_ts(inode, inode_get_atime(dir));
	BTRFS_I(inode)->i_otime_sec = ts.tv_sec;
	BTRFS_I(inode)->i_otime_nsec = ts.tv_nsec;

	inode->i_uid = dir->i_uid;
	inode->i_gid = dir->i_gid;

	return inode;
}

static_assert(BTRFS_FT_UNKNOWN == FT_UNKNOWN);
static_assert(BTRFS_FT_REG_FILE == FT_REG_FILE);
static_assert(BTRFS_FT_DIR == FT_DIR);
static_assert(BTRFS_FT_CHRDEV == FT_CHRDEV);
static_assert(BTRFS_FT_BLKDEV == FT_BLKDEV);
static_assert(BTRFS_FT_FIFO == FT_FIFO);
static_assert(BTRFS_FT_SOCK == FT_SOCK);
static_assert(BTRFS_FT_SYMLINK == FT_SYMLINK);

static inline u8 btrfs_inode_type(struct inode *inode)
{
	return fs_umode_to_ftype(inode->i_mode);
}

struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
	struct inode *inode;
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct btrfs_root *sub_root = root;
	struct btrfs_key location;
	u8 di_type = 0;
	int ret = 0;

	if (dentry->d_name.len > BTRFS_NAME_LEN)
		return ERR_PTR(-ENAMETOOLONG);

	ret = btrfs_inode_by_name(BTRFS_I(dir), dentry, &location, &di_type);
	if (ret < 0)
		return ERR_PTR(ret);

	if (location.type == BTRFS_INODE_ITEM_KEY) {
		inode = btrfs_iget(dir->i_sb, location.objectid, root);
		if (IS_ERR(inode))
			return inode;

		/* Do extra check against inode mode with di_type */
		if (btrfs_inode_type(inode) != di_type) {
			btrfs_crit(fs_info,
"inode mode mismatch with dir: inode mode=0%o btrfs type=%u dir type=%u",
				  inode->i_mode, btrfs_inode_type(inode),
				  di_type);
			iput(inode);
			return ERR_PTR(-EUCLEAN);
		}
		return inode;
	}

	ret = fixup_tree_root_location(fs_info, BTRFS_I(dir), dentry,
				       &location, &sub_root);
	if (ret < 0) {
		if (ret != -ENOENT)
			inode = ERR_PTR(ret);
		else
			inode = new_simple_dir(dir, &location, root);
	} else {
		inode = btrfs_iget(dir->i_sb, location.objectid, sub_root);
		btrfs_put_root(sub_root);

		if (IS_ERR(inode))
			return inode;

		down_read(&fs_info->cleanup_work_sem);
		if (!sb_rdonly(inode->i_sb))
			ret = btrfs_orphan_cleanup(sub_root);
		up_read(&fs_info->cleanup_work_sem);
		if (ret) {
			iput(inode);
			inode = ERR_PTR(ret);
		}
	}

	return inode;
}

static int btrfs_dentry_delete(const struct dentry *dentry)
{
	struct btrfs_root *root;
	struct inode *inode = d_inode(dentry);

	if (!inode && !IS_ROOT(dentry))
		inode = d_inode(dentry->d_parent);

	if (inode) {
		root = BTRFS_I(inode)->root;
		if (btrfs_root_refs(&root->root_item) == 0)
			return 1;

		if (btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
			return 1;
	}
	return 0;
}

static struct dentry *btrfs_lookup(struct inode *dir, struct dentry *dentry,
				   unsigned int flags)
{
	struct inode *inode = btrfs_lookup_dentry(dir, dentry);

	if (inode == ERR_PTR(-ENOENT))
		inode = NULL;
	return d_splice_alias(inode, dentry);
}

/*
 * Find the highest existing sequence number in a directory and then set the
 * in-memory index_cnt variable to the first free sequence number.
 */
static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_key key, found_key;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	int ret;

	key.objectid = btrfs_ino(inode);
	key.type = BTRFS_DIR_INDEX_KEY;
	key.offset = (u64)-1;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
	if (ret < 0)
		goto out;
	/* FIXME: we should be able to handle this */
	if (ret == 0)
		goto out;
	ret = 0;

	if (path->slots[0] == 0) {
		inode->index_cnt = BTRFS_DIR_START_INDEX;
		goto out;
	}

	path->slots[0]--;

	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);

	if (found_key.objectid != btrfs_ino(inode) ||
	    found_key.type != BTRFS_DIR_INDEX_KEY) {
		inode->index_cnt = BTRFS_DIR_START_INDEX;
		goto out;
	}

	inode->index_cnt = found_key.offset + 1;
out:
	btrfs_free_path(path);
	return ret;
}

static int btrfs_get_dir_last_index(struct btrfs_inode *dir, u64 *index)
{
	int ret = 0;

	btrfs_inode_lock(dir, 0);
	if (dir->index_cnt == (u64)-1) {
		ret = btrfs_inode_delayed_dir_index_count(dir);
		if (ret) {
			ret = btrfs_set_inode_index_count(dir);
			if (ret)
				goto out;
		}
	}

	/* index_cnt is the index number of next new entry, so decrement it. */
	*index = dir->index_cnt - 1;
out:
	btrfs_inode_unlock(dir, 0);

	return ret;
}

/*
 * All this infrastructure exists because dir_emit can fault, and we are holding
 * the tree lock when doing readdir.  For now just allocate a buffer and copy
 * our information into that, and then dir_emit from the buffer.  This is
 * similar to what NFS does, only we don't keep the buffer around in pagecache
 * because I'm afraid I'll mess that up.  Long term we need to make filldir do
 * copy_to_user_inatomic so we don't have to worry about page faulting under the
 * tree lock.
 */
static int btrfs_opendir(struct inode *inode, struct file *file)
{
	struct btrfs_file_private *private;
	u64 last_index;
	int ret;

	ret = btrfs_get_dir_last_index(BTRFS_I(inode), &last_index);
	if (ret)
		return ret;

	private = kzalloc(sizeof(struct btrfs_file_private), GFP_KERNEL);
	if (!private)
		return -ENOMEM;
	private->last_index = last_index;
	private->filldir_buf = kzalloc(PAGE_SIZE, GFP_KERNEL);
	if (!private->filldir_buf) {
		kfree(private);
		return -ENOMEM;
	}
	file->private_data = private;
	return 0;
}

static loff_t btrfs_dir_llseek(struct file *file, loff_t offset, int whence)
{
	struct btrfs_file_private *private = file->private_data;
	int ret;

	ret = btrfs_get_dir_last_index(BTRFS_I(file_inode(file)),
				       &private->last_index);
	if (ret)
		return ret;

	return generic_file_llseek(file, offset, whence);
}

struct dir_entry {
	u64 ino;
	u64 offset;
	unsigned type;
	int name_len;
};

static int btrfs_filldir(void *addr, int entries, struct dir_context *ctx)
{
	while (entries--) {
		struct dir_entry *entry = addr;
		char *name = (char *)(entry + 1);

		ctx->pos = get_unaligned(&entry->offset);
		if (!dir_emit(ctx, name, get_unaligned(&entry->name_len),
					 get_unaligned(&entry->ino),
					 get_unaligned(&entry->type)))
			return 1;
		addr += sizeof(struct dir_entry) +
			get_unaligned(&entry->name_len);
		ctx->pos++;
	}
	return 0;
}

static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
{
	struct inode *inode = file_inode(file);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_file_private *private = file->private_data;
	struct btrfs_dir_item *di;
	struct btrfs_key key;
	struct btrfs_key found_key;
	struct btrfs_path *path;
	void *addr;
	LIST_HEAD(ins_list);
	LIST_HEAD(del_list);
	int ret;
	char *name_ptr;
	int name_len;
	int entries = 0;
	int total_len = 0;
	bool put = false;
	struct btrfs_key location;

	if (!dir_emit_dots(file, ctx))
		return 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	addr = private->filldir_buf;
	path->reada = READA_FORWARD;

	put = btrfs_readdir_get_delayed_items(inode, private->last_index,
					      &ins_list, &del_list);

again:
	key.type = BTRFS_DIR_INDEX_KEY;
	key.offset = ctx->pos;
	key.objectid = btrfs_ino(BTRFS_I(inode));

	btrfs_for_each_slot(root, &key, &found_key, path, ret) {
		struct dir_entry *entry;
		struct extent_buffer *leaf = path->nodes[0];
		u8 ftype;

		if (found_key.objectid != key.objectid)
			break;
		if (found_key.type != BTRFS_DIR_INDEX_KEY)
			break;
		if (found_key.offset < ctx->pos)
			continue;
		if (found_key.offset > private->last_index)
			break;
		if (btrfs_should_delete_dir_index(&del_list, found_key.offset))
			continue;
		di = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item);
		name_len = btrfs_dir_name_len(leaf, di);
		if ((total_len + sizeof(struct dir_entry) + name_len) >=
		    PAGE_SIZE) {
			btrfs_release_path(path);
			ret = btrfs_filldir(private->filldir_buf, entries, ctx);
			if (ret)
				goto nopos;
			addr = private->filldir_buf;
			entries = 0;
			total_len = 0;
			goto again;
		}

		ftype = btrfs_dir_flags_to_ftype(btrfs_dir_flags(leaf, di));
		entry = addr;
		name_ptr = (char *)(entry + 1);
		read_extent_buffer(leaf, name_ptr,
				   (unsigned long)(di + 1), name_len);
		put_unaligned(name_len, &entry->name_len);
		put_unaligned(fs_ftype_to_dtype(ftype), &entry->type);
		btrfs_dir_item_key_to_cpu(leaf, di, &location);
		put_unaligned(location.objectid, &entry->ino);
		put_unaligned(found_key.offset, &entry->offset);
		entries++;
		addr += sizeof(struct dir_entry) + name_len;
		total_len += sizeof(struct dir_entry) + name_len;
	}
	/* Catch error encountered during iteration */
	if (ret < 0)
		goto err;

	btrfs_release_path(path);

	ret = btrfs_filldir(private->filldir_buf, entries, ctx);
	if (ret)
		goto nopos;

	ret = btrfs_readdir_delayed_dir_index(ctx, &ins_list);
	if (ret)
		goto nopos;

	/*
	 * Stop new entries from being returned after we return the last
	 * entry.
	 *
	 * New directory entries are assigned a strictly increasing
	 * offset.  This means that new entries created during readdir
	 * are *guaranteed* to be seen in the future by that readdir.
	 * This has broken buggy programs which operate on names as
	 * they're returned by readdir.  Until we re-use freed offsets
	 * we have this hack to stop new entries from being returned
	 * under the assumption that they'll never reach this huge
	 * offset.
	 *
	 * This is being careful not to overflow 32bit loff_t unless the
	 * last entry requires it because doing so has broken 32bit apps
	 * in the past.
	 */
	if (ctx->pos >= INT_MAX)
		ctx->pos = LLONG_MAX;
	else
		ctx->pos = INT_MAX;
nopos:
	ret = 0;
err:
	if (put)
		btrfs_readdir_put_delayed_items(inode, &ins_list, &del_list);
	btrfs_free_path(path);
	return ret;
}

/*
 * This is somewhat expensive, updating the tree every time the
 * inode changes.  But, it is most likely to find the inode in cache.
 * FIXME, needs more benchmarking...there are no reasons other than performance
 * to keep or drop this code.
 */
static int btrfs_dirty_inode(struct btrfs_inode *inode)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	int ret;

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

	trans = btrfs_join_transaction(root);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	ret = btrfs_update_inode(trans, inode);
	if (ret == -ENOSPC || ret == -EDQUOT) {
		/* whoops, lets try again with the full transaction */
		btrfs_end_transaction(trans);
		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans))
			return PTR_ERR(trans);

		ret = btrfs_update_inode(trans, inode);
	}
	btrfs_end_transaction(trans);
	if (inode->delayed_node)
		btrfs_balance_delayed_items(fs_info);

	return ret;
}

/*
 * This is a copy of file_update_time.  We need this so we can return error on
 * ENOSPC for updating the inode in the case of file write and mmap writes.
 */
static int btrfs_update_time(struct inode *inode, int flags)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	bool dirty;

	if (btrfs_root_readonly(root))
		return -EROFS;

	dirty = inode_update_timestamps(inode, flags);
	return dirty ? btrfs_dirty_inode(BTRFS_I(inode)) : 0;
}

/*
 * helper to find a free sequence number in a given directory.  This current
 * code is very simple, later versions will do smarter things in the btree
 */
int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index)
{
	int ret = 0;

	if (dir->index_cnt == (u64)-1) {
		ret = btrfs_inode_delayed_dir_index_count(dir);
		if (ret) {
			ret = btrfs_set_inode_index_count(dir);
			if (ret)
				return ret;
		}
	}

	*index = dir->index_cnt;
	dir->index_cnt++;

	return ret;
}

static int btrfs_insert_inode_locked(struct inode *inode)
{
	struct btrfs_iget_args args;

	args.ino = BTRFS_I(inode)->location.objectid;
	args.root = BTRFS_I(inode)->root;

	return insert_inode_locked4(inode,
		   btrfs_inode_hash(inode->i_ino, BTRFS_I(inode)->root),
		   btrfs_find_actor, &args);
}

int btrfs_new_inode_prepare(struct btrfs_new_inode_args *args,
			    unsigned int *trans_num_items)
{
	struct inode *dir = args->dir;
	struct inode *inode = args->inode;
	int ret;

	if (!args->orphan) {
		ret = fscrypt_setup_filename(dir, &args->dentry->d_name, 0,
					     &args->fname);
		if (ret)
			return ret;
	}

	ret = posix_acl_create(dir, &inode->i_mode, &args->default_acl, &args->acl);
	if (ret) {
		fscrypt_free_filename(&args->fname);
		return ret;
	}

	/* 1 to add inode item */
	*trans_num_items = 1;
	/* 1 to add compression property */
	if (BTRFS_I(dir)->prop_compress)
		(*trans_num_items)++;
	/* 1 to add default ACL xattr */
	if (args->default_acl)
		(*trans_num_items)++;
	/* 1 to add access ACL xattr */
	if (args->acl)
		(*trans_num_items)++;
#ifdef CONFIG_SECURITY
	/* 1 to add LSM xattr */
	if (dir->i_security)
		(*trans_num_items)++;
#endif
	if (args->orphan) {
		/* 1 to add orphan item */
		(*trans_num_items)++;
	} else {
		/*
		 * 1 to add dir item
		 * 1 to add dir index
		 * 1 to update parent inode item
		 *
		 * No need for 1 unit for the inode ref item because it is
		 * inserted in a batch together with the inode item at
		 * btrfs_create_new_inode().
		 */
		*trans_num_items += 3;
	}
	return 0;
}

void btrfs_new_inode_args_destroy(struct btrfs_new_inode_args *args)
{
	posix_acl_release(args->acl);
	posix_acl_release(args->default_acl);
	fscrypt_free_filename(&args->fname);
}

/*
 * Inherit flags from the parent inode.
 *
 * Currently only the compression flags and the cow flags are inherited.
 */
static void btrfs_inherit_iflags(struct btrfs_inode *inode, struct btrfs_inode *dir)
{
	unsigned int flags;

	flags = dir->flags;

	if (flags & BTRFS_INODE_NOCOMPRESS) {
		inode->flags &= ~BTRFS_INODE_COMPRESS;
		inode->flags |= BTRFS_INODE_NOCOMPRESS;
	} else if (flags & BTRFS_INODE_COMPRESS) {
		inode->flags &= ~BTRFS_INODE_NOCOMPRESS;
		inode->flags |= BTRFS_INODE_COMPRESS;
	}

	if (flags & BTRFS_INODE_NODATACOW) {
		inode->flags |= BTRFS_INODE_NODATACOW;
		if (S_ISREG(inode->vfs_inode.i_mode))
			inode->flags |= BTRFS_INODE_NODATASUM;
	}

	btrfs_sync_inode_flags_to_i_flags(&inode->vfs_inode);
}

int btrfs_create_new_inode(struct btrfs_trans_handle *trans,
			   struct btrfs_new_inode_args *args)
{
	struct timespec64 ts;
	struct inode *dir = args->dir;
	struct inode *inode = args->inode;
	const struct fscrypt_str *name = args->orphan ? NULL : &args->fname.disk_name;
	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
	struct btrfs_root *root;
	struct btrfs_inode_item *inode_item;
	struct btrfs_key *location;
	struct btrfs_path *path;
	u64 objectid;
	struct btrfs_inode_ref *ref;
	struct btrfs_key key[2];
	u32 sizes[2];
	struct btrfs_item_batch batch;
	unsigned long ptr;
	int ret;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;

	if (!args->subvol)
		BTRFS_I(inode)->root = btrfs_grab_root(BTRFS_I(dir)->root);
	root = BTRFS_I(inode)->root;

	ret = btrfs_get_free_objectid(root, &objectid);
	if (ret)
		goto out;
	inode->i_ino = objectid;

	if (args->orphan) {
		/*
		 * O_TMPFILE, set link count to 0, so that after this point, we
		 * fill in an inode item with the correct link count.
		 */
		set_nlink(inode, 0);
	} else {
		trace_btrfs_inode_request(dir);

		ret = btrfs_set_inode_index(BTRFS_I(dir), &BTRFS_I(inode)->dir_index);
		if (ret)
			goto out;
	}
	/* index_cnt is ignored for everything but a dir. */
	BTRFS_I(inode)->index_cnt = BTRFS_DIR_START_INDEX;
	BTRFS_I(inode)->generation = trans->transid;
	inode->i_generation = BTRFS_I(inode)->generation;

	/*
	 * We don't have any capability xattrs set here yet, shortcut any
	 * queries for the xattrs here.  If we add them later via the inode
	 * security init path or any other path this flag will be cleared.
	 */
	set_bit(BTRFS_INODE_NO_CAP_XATTR, &BTRFS_I(inode)->runtime_flags);

	/*
	 * Subvolumes don't inherit flags from their parent directory.
	 * Originally this was probably by accident, but we probably can't
	 * change it now without compatibility issues.
	 */
	if (!args->subvol)
		btrfs_inherit_iflags(BTRFS_I(inode), BTRFS_I(dir));

	if (S_ISREG(inode->i_mode)) {
		if (btrfs_test_opt(fs_info, NODATASUM))
			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
		if (btrfs_test_opt(fs_info, NODATACOW))
			BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW |
				BTRFS_INODE_NODATASUM;
	}

	location = &BTRFS_I(inode)->location;
	location->objectid = objectid;
	location->offset = 0;
	location->type = BTRFS_INODE_ITEM_KEY;

	ret = btrfs_insert_inode_locked(inode);
	if (ret < 0) {
		if (!args->orphan)
			BTRFS_I(dir)->index_cnt--;
		goto out;
	}

	/*
	 * We could have gotten an inode number from somebody who was fsynced
	 * and then removed in this same transaction, so let's just set full
	 * sync since it will be a full sync anyway and this will blow away the
	 * old info in the log.
	 */
	btrfs_set_inode_full_sync(BTRFS_I(inode));

	key[0].objectid = objectid;
	key[0].type = BTRFS_INODE_ITEM_KEY;
	key[0].offset = 0;

	sizes[0] = sizeof(struct btrfs_inode_item);

	if (!args->orphan) {
		/*
		 * Start new inodes with an inode_ref. This is slightly more
		 * efficient for small numbers of hard links since they will
		 * be packed into one item. Extended refs will kick in if we
		 * add more hard links than can fit in the ref item.
		 */
		key[1].objectid = objectid;
		key[1].type = BTRFS_INODE_REF_KEY;
		if (args->subvol) {
			key[1].offset = objectid;
			sizes[1] = 2 + sizeof(*ref);
		} else {
			key[1].offset = btrfs_ino(BTRFS_I(dir));
			sizes[1] = name->len + sizeof(*ref);
		}
	}

	batch.keys = &key[0];
	batch.data_sizes = &sizes[0];
	batch.total_data_size = sizes[0] + (args->orphan ? 0 : sizes[1]);
	batch.nr = args->orphan ? 1 : 2;
	ret = btrfs_insert_empty_items(trans, root, path, &batch);
	if (ret != 0) {
		btrfs_abort_transaction(trans, ret);
		goto discard;
	}

	ts = simple_inode_init_ts(inode);
	BTRFS_I(inode)->i_otime_sec = ts.tv_sec;
	BTRFS_I(inode)->i_otime_nsec = ts.tv_nsec;

	/*
	 * We're going to fill the inode item now, so at this point the inode
	 * must be fully initialized.
	 */

	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
				  struct btrfs_inode_item);
	memzero_extent_buffer(path->nodes[0], (unsigned long)inode_item,
			     sizeof(*inode_item));
	fill_inode_item(trans, path->nodes[0], inode_item, inode);

	if (!args->orphan) {
		ref = btrfs_item_ptr(path->nodes[0], path->slots[0] + 1,
				     struct btrfs_inode_ref);
		ptr = (unsigned long)(ref + 1);
		if (args->subvol) {
			btrfs_set_inode_ref_name_len(path->nodes[0], ref, 2);
			btrfs_set_inode_ref_index(path->nodes[0], ref, 0);
			write_extent_buffer(path->nodes[0], "..", ptr, 2);
		} else {
			btrfs_set_inode_ref_name_len(path->nodes[0], ref,
						     name->len);
			btrfs_set_inode_ref_index(path->nodes[0], ref,
						  BTRFS_I(inode)->dir_index);
			write_extent_buffer(path->nodes[0], name->name, ptr,
					    name->len);
		}
	}

	btrfs_mark_buffer_dirty(trans, path->nodes[0]);
	/*
	 * We don't need the path anymore, plus inheriting properties, adding
	 * ACLs, security xattrs, orphan item or adding the link, will result in
	 * allocating yet another path. So just free our path.
	 */
	btrfs_free_path(path);
	path = NULL;

	if (args->subvol) {
		struct inode *parent;

		/*
		 * Subvolumes inherit properties from their parent subvolume,
		 * not the directory they were created in.
		 */
		parent = btrfs_iget(fs_info->sb, BTRFS_FIRST_FREE_OBJECTID,
				    BTRFS_I(dir)->root);
		if (IS_ERR(parent)) {
			ret = PTR_ERR(parent);
		} else {
			ret = btrfs_inode_inherit_props(trans, inode, parent);
			iput(parent);
		}
	} else {
		ret = btrfs_inode_inherit_props(trans, inode, dir);
	}
	if (ret) {
		btrfs_err(fs_info,
			  "error inheriting props for ino %llu (root %llu): %d",
			  btrfs_ino(BTRFS_I(inode)), root->root_key.objectid,
			  ret);
	}

	/*
	 * Subvolumes don't inherit ACLs or get passed to the LSM. This is
	 * probably a bug.
	 */
	if (!args->subvol) {
		ret = btrfs_init_inode_security(trans, args);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto discard;
		}
	}

	inode_tree_add(BTRFS_I(inode));

	trace_btrfs_inode_new(inode);
	btrfs_set_inode_last_trans(trans, BTRFS_I(inode));

	btrfs_update_root_times(trans, root);

	if (args->orphan) {
		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
	} else {
		ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name,
				     0, BTRFS_I(inode)->dir_index);
	}
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto discard;
	}

	return 0;

discard:
	/*
	 * discard_new_inode() calls iput(), but the caller owns the reference
	 * to the inode.
	 */
	ihold(inode);
	discard_new_inode(inode);
out:
	btrfs_free_path(path);
	return ret;
}

/*
 * utility function to add 'inode' into 'parent_inode' with
 * a give name and a given sequence number.
 * if 'add_backref' is true, also insert a backref from the
 * inode to the parent directory.
 */
int btrfs_add_link(struct btrfs_trans_handle *trans,
		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
		   const struct fscrypt_str *name, int add_backref, u64 index)
{
	int ret = 0;
	struct btrfs_key key;
	struct btrfs_root *root = parent_inode->root;
	u64 ino = btrfs_ino(inode);
	u64 parent_ino = btrfs_ino(parent_inode);

	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
		memcpy(&key, &inode->root->root_key, sizeof(key));
	} else {
		key.objectid = ino;
		key.type = BTRFS_INODE_ITEM_KEY;
		key.offset = 0;
	}

	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
		ret = btrfs_add_root_ref(trans, key.objectid,
					 root->root_key.objectid, parent_ino,
					 index, name);
	} else if (add_backref) {
		ret = btrfs_insert_inode_ref(trans, root, name,
					     ino, parent_ino, index);
	}

	/* Nothing to clean up yet */
	if (ret)
		return ret;

	ret = btrfs_insert_dir_item(trans, name, parent_inode, &key,
				    btrfs_inode_type(&inode->vfs_inode), index);
	if (ret == -EEXIST || ret == -EOVERFLOW)
		goto fail_dir_item;
	else if (ret) {
		btrfs_abort_transaction(trans, ret);
		return ret;
	}

	btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size +
			   name->len * 2);
	inode_inc_iversion(&parent_inode->vfs_inode);
	/*
	 * If we are replaying a log tree, we do not want to update the mtime
	 * and ctime of the parent directory with the current time, since the
	 * log replay procedure is responsible for setting them to their correct
	 * values (the ones it had when the fsync was done).
	 */
	if (!test_bit(BTRFS_FS_LOG_RECOVERING, &root->fs_info->flags))
		inode_set_mtime_to_ts(&parent_inode->vfs_inode,
				      inode_set_ctime_current(&parent_inode->vfs_inode));

	ret = btrfs_update_inode(trans, parent_inode);
	if (ret)
		btrfs_abort_transaction(trans, ret);
	return ret;

fail_dir_item:
	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
		u64 local_index;
		int err;
		err = btrfs_del_root_ref(trans, key.objectid,
					 root->root_key.objectid, parent_ino,
					 &local_index, name);
		if (err)
			btrfs_abort_transaction(trans, err);
	} else if (add_backref) {
		u64 local_index;
		int err;

		err = btrfs_del_inode_ref(trans, root, name, ino, parent_ino,
					  &local_index);
		if (err)
			btrfs_abort_transaction(trans, err);
	}

	/* Return the original error code */
	return ret;
}

static int btrfs_create_common(struct inode *dir, struct dentry *dentry,
			       struct inode *inode)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct btrfs_new_inode_args new_inode_args = {
		.dir = dir,
		.dentry = dentry,
		.inode = inode,
	};
	unsigned int trans_num_items;
	struct btrfs_trans_handle *trans;
	int err;

	err = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
	if (err)
		goto out_inode;

	trans = btrfs_start_transaction(root, trans_num_items);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_new_inode_args;
	}

	err = btrfs_create_new_inode(trans, &new_inode_args);
	if (!err)
		d_instantiate_new(dentry, inode);

	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(fs_info);
out_new_inode_args:
	btrfs_new_inode_args_destroy(&new_inode_args);
out_inode:
	if (err)
		iput(inode);
	return err;
}

static int btrfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
		       struct dentry *dentry, umode_t mode, dev_t rdev)
{
	struct inode *inode;

	inode = new_inode(dir->i_sb);
	if (!inode)
		return -ENOMEM;
	inode_init_owner(idmap, inode, dir, mode);
	inode->i_op = &btrfs_special_inode_operations;
	init_special_inode(inode, inode->i_mode, rdev);
	return btrfs_create_common(dir, dentry, inode);
}

static int btrfs_create(struct mnt_idmap *idmap, struct inode *dir,
			struct dentry *dentry, umode_t mode, bool excl)
{
	struct inode *inode;

	inode = new_inode(dir->i_sb);
	if (!inode)
		return -ENOMEM;
	inode_init_owner(idmap, inode, dir, mode);
	inode->i_fop = &btrfs_file_operations;
	inode->i_op = &btrfs_file_inode_operations;
	inode->i_mapping->a_ops = &btrfs_aops;
	return btrfs_create_common(dir, dentry, inode);
}

static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
		      struct dentry *dentry)
{
	struct btrfs_trans_handle *trans = NULL;
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct inode *inode = d_inode(old_dentry);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct fscrypt_name fname;
	u64 index;
	int err;
	int drop_inode = 0;

	/* do not allow sys_link's with other subvols of the same device */
	if (root->root_key.objectid != BTRFS_I(inode)->root->root_key.objectid)
		return -EXDEV;

	if (inode->i_nlink >= BTRFS_LINK_MAX)
		return -EMLINK;

	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &fname);
	if (err)
		goto fail;

	err = btrfs_set_inode_index(BTRFS_I(dir), &index);
	if (err)
		goto fail;

	/*
	 * 2 items for inode and inode ref
	 * 2 items for dir items
	 * 1 item for parent inode
	 * 1 item for orphan item deletion if O_TMPFILE
	 */
	trans = btrfs_start_transaction(root, inode->i_nlink ? 5 : 6);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		trans = NULL;
		goto fail;
	}

	/* There are several dir indexes for this inode, clear the cache. */
	BTRFS_I(inode)->dir_index = 0ULL;
	inc_nlink(inode);
	inode_inc_iversion(inode);
	inode_set_ctime_current(inode);
	ihold(inode);
	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);

	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
			     &fname.disk_name, 1, index);

	if (err) {
		drop_inode = 1;
	} else {
		struct dentry *parent = dentry->d_parent;

		err = btrfs_update_inode(trans, BTRFS_I(inode));
		if (err)
			goto fail;
		if (inode->i_nlink == 1) {
			/*
			 * If new hard link count is 1, it's a file created
			 * with open(2) O_TMPFILE flag.
			 */
			err = btrfs_orphan_del(trans, BTRFS_I(inode));
			if (err)
				goto fail;
		}
		d_instantiate(dentry, inode);
		btrfs_log_new_name(trans, old_dentry, NULL, 0, parent);
	}

fail:
	fscrypt_free_filename(&fname);
	if (trans)
		btrfs_end_transaction(trans);
	if (drop_inode) {
		inode_dec_link_count(inode);
		iput(inode);
	}
	btrfs_btree_balance_dirty(fs_info);
	return err;
}

static int btrfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
		       struct dentry *dentry, umode_t mode)
{
	struct inode *inode;

	inode = new_inode(dir->i_sb);
	if (!inode)
		return -ENOMEM;
	inode_init_owner(idmap, inode, dir, S_IFDIR | mode);
	inode->i_op = &btrfs_dir_inode_operations;
	inode->i_fop = &btrfs_dir_file_operations;
	return btrfs_create_common(dir, dentry, inode);
}

static noinline int uncompress_inline(struct btrfs_path *path,
				      struct page *page,
				      struct btrfs_file_extent_item *item)
{
	int ret;
	struct extent_buffer *leaf = path->nodes[0];
	char *tmp;
	size_t max_size;
	unsigned long inline_size;
	unsigned long ptr;
	int compress_type;

	compress_type = btrfs_file_extent_compression(leaf, item);
	max_size = btrfs_file_extent_ram_bytes(leaf, item);
	inline_size = btrfs_file_extent_inline_item_len(leaf, path->slots[0]);
	tmp = kmalloc(inline_size, GFP_NOFS);
	if (!tmp)
		return -ENOMEM;
	ptr = btrfs_file_extent_inline_start(item);

	read_extent_buffer(leaf, tmp, ptr, inline_size);

	max_size = min_t(unsigned long, PAGE_SIZE, max_size);
	ret = btrfs_decompress(compress_type, tmp, page, 0, inline_size, max_size);

	/*
	 * decompression code contains a memset to fill in any space between the end
	 * of the uncompressed data and the end of max_size in case the decompressed
	 * data ends up shorter than ram_bytes.  That doesn't cover the hole between
	 * the end of an inline extent and the beginning of the next block, so we
	 * cover that region here.
	 */

	if (max_size < PAGE_SIZE)
		memzero_page(page, max_size, PAGE_SIZE - max_size);
	kfree(tmp);
	return ret;
}

static int read_inline_extent(struct btrfs_inode *inode, struct btrfs_path *path,
			      struct page *page)
{
	struct btrfs_file_extent_item *fi;
	void *kaddr;
	size_t copy_size;

	if (!page || PageUptodate(page))
		return 0;

	ASSERT(page_offset(page) == 0);

	fi = btrfs_item_ptr(path->nodes[0], path->slots[0],
			    struct btrfs_file_extent_item);
	if (btrfs_file_extent_compression(path->nodes[0], fi) != BTRFS_COMPRESS_NONE)
		return uncompress_inline(path, page, fi);

	copy_size = min_t(u64, PAGE_SIZE,
			  btrfs_file_extent_ram_bytes(path->nodes[0], fi));
	kaddr = kmap_local_page(page);
	read_extent_buffer(path->nodes[0], kaddr,
			   btrfs_file_extent_inline_start(fi), copy_size);
	kunmap_local(kaddr);
	if (copy_size < PAGE_SIZE)
		memzero_page(page, copy_size, PAGE_SIZE - copy_size);
	return 0;
}

/*
 * Lookup the first extent overlapping a range in a file.
 *
 * @inode:	file to search in
 * @page:	page to read extent data into if the extent is inline
 * @pg_offset:	offset into @page to copy to
 * @start:	file offset
 * @len:	length of range starting at @start
 *
 * Return the first &struct extent_map which overlaps the given range, reading
 * it from the B-tree and caching it if necessary. Note that there may be more
 * extents which overlap the given range after the returned extent_map.
 *
 * If @page is not NULL and the extent is inline, this also reads the extent
 * data directly into the page and marks the extent up to date in the io_tree.
 *
 * Return: ERR_PTR on error, non-NULL extent_map on success.
 */
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
				    struct page *page, size_t pg_offset,
				    u64 start, u64 len)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	int ret = 0;
	u64 extent_start = 0;
	u64 extent_end = 0;
	u64 objectid = btrfs_ino(inode);
	int extent_type = -1;
	struct btrfs_path *path = NULL;
	struct btrfs_root *root = inode->root;
	struct btrfs_file_extent_item *item;
	struct extent_buffer *leaf;
	struct btrfs_key found_key;
	struct extent_map *em = NULL;
	struct extent_map_tree *em_tree = &inode->extent_tree;

	read_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, start, len);
	read_unlock(&em_tree->lock);

	if (em) {
		if (em->start > start || em->start + em->len <= start)
			free_extent_map(em);
		else if (em->block_start == EXTENT_MAP_INLINE && page)
			free_extent_map(em);
		else
			goto out;
	}
	em = alloc_extent_map();
	if (!em) {
		ret = -ENOMEM;
		goto out;
	}
	em->start = EXTENT_MAP_HOLE;
	em->orig_start = EXTENT_MAP_HOLE;
	em->len = (u64)-1;
	em->block_len = (u64)-1;

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

	/* Chances are we'll be called again, so go ahead and do readahead */
	path->reada = READA_FORWARD;

	/*
	 * The same explanation in load_free_space_cache applies here as well,
	 * we only read when we're loading the free space cache, and at that
	 * point the commit_root has everything we need.
	 */
	if (btrfs_is_free_space_inode(inode)) {
		path->search_commit_root = 1;
		path->skip_locking = 1;
	}

	ret = btrfs_lookup_file_extent(NULL, root, path, objectid, start, 0);
	if (ret < 0) {
		goto out;
	} else if (ret > 0) {
		if (path->slots[0] == 0)
			goto not_found;
		path->slots[0]--;
		ret = 0;
	}

	leaf = path->nodes[0];
	item = btrfs_item_ptr(leaf, path->slots[0],
			      struct btrfs_file_extent_item);
	btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
	if (found_key.objectid != objectid ||
	    found_key.type != BTRFS_EXTENT_DATA_KEY) {
		/*
		 * If we backup past the first extent we want to move forward
		 * and see if there is an extent in front of us, otherwise we'll
		 * say there is a hole for our whole search range which can
		 * cause problems.
		 */
		extent_end = start;
		goto next;
	}

	extent_type = btrfs_file_extent_type(leaf, item);
	extent_start = found_key.offset;
	extent_end = btrfs_file_extent_end(path);
	if (extent_type == BTRFS_FILE_EXTENT_REG ||
	    extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
		/* Only regular file could have regular/prealloc extent */
		if (!S_ISREG(inode->vfs_inode.i_mode)) {
			ret = -EUCLEAN;
			btrfs_crit(fs_info,
		"regular/prealloc extent found for non-regular inode %llu",
				   btrfs_ino(inode));
			goto out;
		}
		trace_btrfs_get_extent_show_fi_regular(inode, leaf, item,
						       extent_start);
	} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
		trace_btrfs_get_extent_show_fi_inline(inode, leaf, item,
						      path->slots[0],
						      extent_start);
	}
next:
	if (start >= extent_end) {
		path->slots[0]++;
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				goto out;
			else if (ret > 0)
				goto not_found;

			leaf = path->nodes[0];
		}
		btrfs_item_key_to_cpu(leaf, &found_key, path->slots[0]);
		if (found_key.objectid != objectid ||
		    found_key.type != BTRFS_EXTENT_DATA_KEY)
			goto not_found;
		if (start + len <= found_key.offset)
			goto not_found;
		if (start > found_key.offset)
			goto next;

		/* New extent overlaps with existing one */
		em->start = start;
		em->orig_start = start;
		em->len = found_key.offset - start;
		em->block_start = EXTENT_MAP_HOLE;
		goto insert;
	}

	btrfs_extent_item_to_extent_map(inode, path, item, em);

	if (extent_type == BTRFS_FILE_EXTENT_REG ||
	    extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
		goto insert;
	} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
		/*
		 * Inline extent can only exist at file offset 0. This is
		 * ensured by tree-checker and inline extent creation path.
		 * Thus all members representing file offsets should be zero.
		 */
		ASSERT(pg_offset == 0);
		ASSERT(extent_start == 0);
		ASSERT(em->start == 0);

		/*
		 * btrfs_extent_item_to_extent_map() should have properly
		 * initialized em members already.
		 *
		 * Other members are not utilized for inline extents.
		 */
		ASSERT(em->block_start == EXTENT_MAP_INLINE);
		ASSERT(em->len == fs_info->sectorsize);

		ret = read_inline_extent(inode, path, page);
		if (ret < 0)
			goto out;
		goto insert;
	}
not_found:
	em->start = start;
	em->orig_start = start;
	em->len = len;
	em->block_start = EXTENT_MAP_HOLE;
insert:
	ret = 0;
	btrfs_release_path(path);
	if (em->start > start || extent_map_end(em) <= start) {
		btrfs_err(fs_info,
			  "bad extent! em: [%llu %llu] passed [%llu %llu]",
			  em->start, em->len, start, len);
		ret = -EIO;
		goto out;
	}

	write_lock(&em_tree->lock);
	ret = btrfs_add_extent_mapping(fs_info, em_tree, &em, start, len);
	write_unlock(&em_tree->lock);
out:
	btrfs_free_path(path);

	trace_btrfs_get_extent(root, inode, em);

	if (ret) {
		free_extent_map(em);
		return ERR_PTR(ret);
	}
	return em;
}

static struct extent_map *btrfs_create_dio_extent(struct btrfs_inode *inode,
						  struct btrfs_dio_data *dio_data,
						  const u64 start,
						  const u64 len,
						  const u64 orig_start,
						  const u64 block_start,
						  const u64 block_len,
						  const u64 orig_block_len,
						  const u64 ram_bytes,
						  const int type)
{
	struct extent_map *em = NULL;
	struct btrfs_ordered_extent *ordered;

	if (type != BTRFS_ORDERED_NOCOW) {
		em = create_io_em(inode, start, len, orig_start, block_start,
				  block_len, orig_block_len, ram_bytes,
				  BTRFS_COMPRESS_NONE, /* compress_type */
				  type);
		if (IS_ERR(em))
			goto out;
	}
	ordered = btrfs_alloc_ordered_extent(inode, start, len, len,
					     block_start, block_len, 0,
					     (1 << type) |
					     (1 << BTRFS_ORDERED_DIRECT),
					     BTRFS_COMPRESS_NONE);
	if (IS_ERR(ordered)) {
		if (em) {
			free_extent_map(em);
			btrfs_drop_extent_map_range(inode, start,
						    start + len - 1, false);
		}
		em = ERR_CAST(ordered);
	} else {
		ASSERT(!dio_data->ordered);
		dio_data->ordered = ordered;
	}
 out:

	return em;
}

static struct extent_map *btrfs_new_extent_direct(struct btrfs_inode *inode,
						  struct btrfs_dio_data *dio_data,
						  u64 start, u64 len)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct extent_map *em;
	struct btrfs_key ins;
	u64 alloc_hint;
	int ret;

	alloc_hint = get_extent_allocation_hint(inode, start, len);
again:
	ret = btrfs_reserve_extent(root, len, len, fs_info->sectorsize,
				   0, alloc_hint, &ins, 1, 1);
	if (ret == -EAGAIN) {
		ASSERT(btrfs_is_zoned(fs_info));
		wait_on_bit_io(&inode->root->fs_info->flags, BTRFS_FS_NEED_ZONE_FINISH,
			       TASK_UNINTERRUPTIBLE);
		goto again;
	}
	if (ret)
		return ERR_PTR(ret);

	em = btrfs_create_dio_extent(inode, dio_data, start, ins.offset, start,
				     ins.objectid, ins.offset, ins.offset,
				     ins.offset, BTRFS_ORDERED_REGULAR);
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	if (IS_ERR(em))
		btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset,
					   1);

	return em;
}

static bool btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group *block_group;
	bool readonly = false;

	block_group = btrfs_lookup_block_group(fs_info, bytenr);
	if (!block_group || block_group->ro)
		readonly = true;
	if (block_group)
		btrfs_put_block_group(block_group);
	return readonly;
}

/*
 * Check if we can do nocow write into the range [@offset, @offset + @len)
 *
 * @offset:	File offset
 * @len:	The length to write, will be updated to the nocow writeable
 *		range
 * @orig_start:	(optional) Return the original file offset of the file extent
 * @orig_len:	(optional) Return the original on-disk length of the file extent
 * @ram_bytes:	(optional) Return the ram_bytes of the file extent
 * @strict:	if true, omit optimizations that might force us into unnecessary
 *		cow. e.g., don't trust generation number.
 *
 * Return:
 * >0	and update @len if we can do nocow write
 *  0	if we can't do nocow write
 * <0	if error happened
 *
 * NOTE: This only checks the file extents, caller is responsible to wait for
 *	 any ordered extents.
 */
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
			      u64 *orig_start, u64 *orig_block_len,
			      u64 *ram_bytes, bool nowait, bool strict)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct can_nocow_file_extent_args nocow_args = { 0 };
	struct btrfs_path *path;
	int ret;
	struct extent_buffer *leaf;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct btrfs_file_extent_item *fi;
	struct btrfs_key key;
	int found_type;

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

	ret = btrfs_lookup_file_extent(NULL, root, path,
			btrfs_ino(BTRFS_I(inode)), offset, 0);
	if (ret < 0)
		goto out;

	if (ret == 1) {
		if (path->slots[0] == 0) {
			/* can't find the item, must cow */
			ret = 0;
			goto out;
		}
		path->slots[0]--;
	}
	ret = 0;
	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
	if (key.objectid != btrfs_ino(BTRFS_I(inode)) ||
	    key.type != BTRFS_EXTENT_DATA_KEY) {
		/* not our file or wrong item type, must cow */
		goto out;
	}

	if (key.offset > offset) {
		/* Wrong offset, must cow */
		goto out;
	}

	if (btrfs_file_extent_end(path) <= offset)
		goto out;

	fi = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);
	found_type = btrfs_file_extent_type(leaf, fi);
	if (ram_bytes)
		*ram_bytes = btrfs_file_extent_ram_bytes(leaf, fi);

	nocow_args.start = offset;
	nocow_args.end = offset + *len - 1;
	nocow_args.strict = strict;
	nocow_args.free_path = true;

	ret = can_nocow_file_extent(path, &key, BTRFS_I(inode), &nocow_args);
	/* can_nocow_file_extent() has freed the path. */
	path = NULL;

	if (ret != 1) {
		/* Treat errors as not being able to NOCOW. */
		ret = 0;
		goto out;
	}

	ret = 0;
	if (btrfs_extent_readonly(fs_info, nocow_args.disk_bytenr))
		goto out;

	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
		u64 range_end;

		range_end = round_up(offset + nocow_args.num_bytes,
				     root->fs_info->sectorsize) - 1;
		ret = test_range_bit_exists(io_tree, offset, range_end, EXTENT_DELALLOC);
		if (ret) {
			ret = -EAGAIN;
			goto out;
		}
	}

	if (orig_start)
		*orig_start = key.offset - nocow_args.extent_offset;
	if (orig_block_len)
		*orig_block_len = nocow_args.disk_num_bytes;

	*len = nocow_args.num_bytes;
	ret = 1;
out:
	btrfs_free_path(path);
	return ret;
}

static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
			      struct extent_state **cached_state,
			      unsigned int iomap_flags)
{
	const bool writing = (iomap_flags & IOMAP_WRITE);
	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct btrfs_ordered_extent *ordered;
	int ret = 0;

	while (1) {
		if (nowait) {
			if (!try_lock_extent(io_tree, lockstart, lockend,
					     cached_state))
				return -EAGAIN;
		} else {
			lock_extent(io_tree, lockstart, lockend, cached_state);
		}
		/*
		 * We're concerned with the entire range that we're going to be
		 * doing DIO to, so we need to make sure there's no ordered
		 * extents in this range.
		 */
		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart,
						     lockend - lockstart + 1);

		/*
		 * We need to make sure there are no buffered pages in this
		 * range either, we could have raced between the invalidate in
		 * generic_file_direct_write and locking the extent.  The
		 * invalidate needs to happen so that reads after a write do not
		 * get stale data.
		 */
		if (!ordered &&
		    (!writing || !filemap_range_has_page(inode->i_mapping,
							 lockstart, lockend)))
			break;

		unlock_extent(io_tree, lockstart, lockend, cached_state);

		if (ordered) {
			if (nowait) {
				btrfs_put_ordered_extent(ordered);
				ret = -EAGAIN;
				break;
			}
			/*
			 * If we are doing a DIO read and the ordered extent we
			 * found is for a buffered write, we can not wait for it
			 * to complete and retry, because if we do so we can
			 * deadlock with concurrent buffered writes on page
			 * locks. This happens only if our DIO read covers more
			 * than one extent map, if at this point has already
			 * created an ordered extent for a previous extent map
			 * and locked its range in the inode's io tree, and a
			 * concurrent write against that previous extent map's
			 * range and this range started (we unlock the ranges
			 * in the io tree only when the bios complete and
			 * buffered writes always lock pages before attempting
			 * to lock range in the io tree).
			 */
			if (writing ||
			    test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags))
				btrfs_start_ordered_extent(ordered);
			else
				ret = nowait ? -EAGAIN : -ENOTBLK;
			btrfs_put_ordered_extent(ordered);
		} else {
			/*
			 * We could trigger writeback for this range (and wait
			 * for it to complete) and then invalidate the pages for
			 * this range (through invalidate_inode_pages2_range()),
			 * but that can lead us to a deadlock with a concurrent
			 * call to readahead (a buffered read or a defrag call
			 * triggered a readahead) on a page lock due to an
			 * ordered dio extent we created before but did not have
			 * yet a corresponding bio submitted (whence it can not
			 * complete), which makes readahead wait for that
			 * ordered extent to complete while holding a lock on
			 * that page.
			 */
			ret = nowait ? -EAGAIN : -ENOTBLK;
		}

		if (ret)
			break;

		cond_resched();
	}

	return ret;
}

/* The callers of this must take lock_extent() */
static struct extent_map *create_io_em(struct btrfs_inode *inode, u64 start,
				       u64 len, u64 orig_start, u64 block_start,
				       u64 block_len, u64 orig_block_len,
				       u64 ram_bytes, int compress_type,
				       int type)
{
	struct extent_map *em;
	int ret;

	ASSERT(type == BTRFS_ORDERED_PREALLOC ||
	       type == BTRFS_ORDERED_COMPRESSED ||
	       type == BTRFS_ORDERED_NOCOW ||
	       type == BTRFS_ORDERED_REGULAR);

	em = alloc_extent_map();
	if (!em)
		return ERR_PTR(-ENOMEM);

	em->start = start;
	em->orig_start = orig_start;
	em->len = len;
	em->block_len = block_len;
	em->block_start = block_start;
	em->orig_block_len = orig_block_len;
	em->ram_bytes = ram_bytes;
	em->generation = -1;
	em->flags |= EXTENT_FLAG_PINNED;
	if (type == BTRFS_ORDERED_PREALLOC)
		em->flags |= EXTENT_FLAG_FILLING;
	else if (type == BTRFS_ORDERED_COMPRESSED)
		extent_map_set_compression(em, compress_type);

	ret = btrfs_replace_extent_map_range(inode, em, true);
	if (ret) {
		free_extent_map(em);
		return ERR_PTR(ret);
	}

	/* em got 2 refs now, callers needs to do free_extent_map once. */
	return em;
}


static int btrfs_get_blocks_direct_write(struct extent_map **map,
					 struct inode *inode,
					 struct btrfs_dio_data *dio_data,
					 u64 start, u64 *lenp,
					 unsigned int iomap_flags)
{
	const bool nowait = (iomap_flags & IOMAP_NOWAIT);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct extent_map *em = *map;
	int type;
	u64 block_start, orig_start, orig_block_len, ram_bytes;
	struct btrfs_block_group *bg;
	bool can_nocow = false;
	bool space_reserved = false;
	u64 len = *lenp;
	u64 prev_len;
	int ret = 0;

	/*
	 * We don't allocate a new extent in the following cases
	 *
	 * 1) The inode is marked as NODATACOW. In this case we'll just use the
	 * existing extent.
	 * 2) The extent is marked as PREALLOC. We're good to go here and can
	 * just use the extent.
	 *
	 */
	if ((em->flags & EXTENT_FLAG_PREALLOC) ||
	    ((BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW) &&
	     em->block_start != EXTENT_MAP_HOLE)) {
		if (em->flags & EXTENT_FLAG_PREALLOC)
			type = BTRFS_ORDERED_PREALLOC;
		else
			type = BTRFS_ORDERED_NOCOW;
		len = min(len, em->len - (start - em->start));
		block_start = em->block_start + (start - em->start);

		if (can_nocow_extent(inode, start, &len, &orig_start,
				     &orig_block_len, &ram_bytes, false, false) == 1) {
			bg = btrfs_inc_nocow_writers(fs_info, block_start);
			if (bg)
				can_nocow = true;
		}
	}

	prev_len = len;
	if (can_nocow) {
		struct extent_map *em2;

		/* We can NOCOW, so only need to reserve metadata space. */
		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len,
						      nowait);
		if (ret < 0) {
			/* Our caller expects us to free the input extent map. */
			free_extent_map(em);
			*map = NULL;
			btrfs_dec_nocow_writers(bg);
			if (nowait && (ret == -ENOSPC || ret == -EDQUOT))
				ret = -EAGAIN;
			goto out;
		}
		space_reserved = true;

		em2 = btrfs_create_dio_extent(BTRFS_I(inode), dio_data, start, len,
					      orig_start, block_start,
					      len, orig_block_len,
					      ram_bytes, type);
		btrfs_dec_nocow_writers(bg);
		if (type == BTRFS_ORDERED_PREALLOC) {
			free_extent_map(em);
			*map = em2;
			em = em2;
		}

		if (IS_ERR(em2)) {
			ret = PTR_ERR(em2);
			goto out;
		}

		dio_data->nocow_done = true;
	} else {
		/* Our caller expects us to free the input extent map. */
		free_extent_map(em);
		*map = NULL;

		if (nowait) {
			ret = -EAGAIN;
			goto out;
		}

		/*
		 * If we could not allocate data space before locking the file
		 * range and we can't do a NOCOW write, then we have to fail.
		 */
		if (!dio_data->data_space_reserved) {
			ret = -ENOSPC;
			goto out;
		}

		/*
		 * We have to COW and we have already reserved data space before,
		 * so now we reserve only metadata.
		 */
		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len, len,
						      false);
		if (ret < 0)
			goto out;
		space_reserved = true;

		em = btrfs_new_extent_direct(BTRFS_I(inode), dio_data, start, len);
		if (IS_ERR(em)) {
			ret = PTR_ERR(em);
			goto out;
		}
		*map = em;
		len = min(len, em->len - (start - em->start));
		if (len < prev_len)
			btrfs_delalloc_release_metadata(BTRFS_I(inode),
							prev_len - len, true);
	}

	/*
	 * We have created our ordered extent, so we can now release our reservation
	 * for an outstanding extent.
	 */
	btrfs_delalloc_release_extents(BTRFS_I(inode), prev_len);

	/*
	 * Need to update the i_size under the extent lock so buffered
	 * readers will get the updated i_size when we unlock.
	 */
	if (start + len > i_size_read(inode))
		i_size_write(inode, start + len);
out:
	if (ret && space_reserved) {
		btrfs_delalloc_release_extents(BTRFS_I(inode), len);
		btrfs_delalloc_release_metadata(BTRFS_I(inode), len, true);
	}
	*lenp = len;
	return ret;
}

static int btrfs_dio_iomap_begin(struct inode *inode, loff_t start,
		loff_t length, unsigned int flags, struct iomap *iomap,
		struct iomap *srcmap)
{
	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct extent_map *em;
	struct extent_state *cached_state = NULL;
	struct btrfs_dio_data *dio_data = iter->private;
	u64 lockstart, lockend;
	const bool write = !!(flags & IOMAP_WRITE);
	int ret = 0;
	u64 len = length;
	const u64 data_alloc_len = length;
	bool unlock_extents = false;

	/*
	 * We could potentially fault if we have a buffer > PAGE_SIZE, and if
	 * we're NOWAIT we may submit a bio for a partial range and return
	 * EIOCBQUEUED, which would result in an errant short read.
	 *
	 * The best way to handle this would be to allow for partial completions
	 * of iocb's, so we could submit the partial bio, return and fault in
	 * the rest of the pages, and then submit the io for the rest of the
	 * range.  However we don't have that currently, so simply return
	 * -EAGAIN at this point so that the normal path is used.
	 */
	if (!write && (flags & IOMAP_NOWAIT) && length > PAGE_SIZE)
		return -EAGAIN;

	/*
	 * Cap the size of reads to that usually seen in buffered I/O as we need
	 * to allocate a contiguous array for the checksums.
	 */
	if (!write)
		len = min_t(u64, len, fs_info->sectorsize * BTRFS_MAX_BIO_SECTORS);

	lockstart = start;
	lockend = start + len - 1;

	/*
	 * iomap_dio_rw() only does filemap_write_and_wait_range(), which isn't
	 * enough if we've written compressed pages to this area, so we need to
	 * flush the dirty pages again to make absolutely sure that any
	 * outstanding dirty pages are on disk - the first flush only starts
	 * compression on the data, while keeping the pages locked, so by the
	 * time the second flush returns we know bios for the compressed pages
	 * were submitted and finished, and the pages no longer under writeback.
	 *
	 * If we have a NOWAIT request and we have any pages in the range that
	 * are locked, likely due to compression still in progress, we don't want
	 * to block on page locks. We also don't want to block on pages marked as
	 * dirty or under writeback (same as for the non-compression case).
	 * iomap_dio_rw() did the same check, but after that and before we got
	 * here, mmap'ed writes may have happened or buffered reads started
	 * (readpage() and readahead(), which lock pages), as we haven't locked
	 * the file range yet.
	 */
	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
		     &BTRFS_I(inode)->runtime_flags)) {
		if (flags & IOMAP_NOWAIT) {
			if (filemap_range_needs_writeback(inode->i_mapping,
							  lockstart, lockend))
				return -EAGAIN;
		} else {
			ret = filemap_fdatawrite_range(inode->i_mapping, start,
						       start + length - 1);
			if (ret)
				return ret;
		}
	}

	memset(dio_data, 0, sizeof(*dio_data));

	/*
	 * We always try to allocate data space and must do it before locking
	 * the file range, to avoid deadlocks with concurrent writes to the same
	 * range if the range has several extents and the writes don't expand the
	 * current i_size (the inode lock is taken in shared mode). If we fail to
	 * allocate data space here we continue and later, after locking the
	 * file range, we fail with ENOSPC only if we figure out we can not do a
	 * NOCOW write.
	 */
	if (write && !(flags & IOMAP_NOWAIT)) {
		ret = btrfs_check_data_free_space(BTRFS_I(inode),
						  &dio_data->data_reserved,
						  start, data_alloc_len, false);
		if (!ret)
			dio_data->data_space_reserved = true;
		else if (ret && !(BTRFS_I(inode)->flags &
				  (BTRFS_INODE_NODATACOW | BTRFS_INODE_PREALLOC)))
			goto err;
	}

	/*
	 * If this errors out it's because we couldn't invalidate pagecache for
	 * this range and we need to fallback to buffered IO, or we are doing a
	 * NOWAIT read/write and we need to block.
	 */
	ret = lock_extent_direct(inode, lockstart, lockend, &cached_state, flags);
	if (ret < 0)
		goto err;

	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
	if (IS_ERR(em)) {
		ret = PTR_ERR(em);
		goto unlock_err;
	}

	/*
	 * Ok for INLINE and COMPRESSED extents we need to fallback on buffered
	 * io.  INLINE is special, and we could probably kludge it in here, but
	 * it's still buffered so for safety lets just fall back to the generic
	 * buffered path.
	 *
	 * For COMPRESSED we _have_ to read the entire extent in so we can
	 * decompress it, so there will be buffering required no matter what we
	 * do, so go ahead and fallback to buffered.
	 *
	 * We return -ENOTBLK because that's what makes DIO go ahead and go back
	 * to buffered IO.  Don't blame me, this is the price we pay for using
	 * the generic code.
	 */
	if (extent_map_is_compressed(em) ||
	    em->block_start == EXTENT_MAP_INLINE) {
		free_extent_map(em);
		/*
		 * If we are in a NOWAIT context, return -EAGAIN in order to
		 * fallback to buffered IO. This is not only because we can
		 * block with buffered IO (no support for NOWAIT semantics at
		 * the moment) but also to avoid returning short reads to user
		 * space - this happens if we were able to read some data from
		 * previous non-compressed extents and then when we fallback to
		 * buffered IO, at btrfs_file_read_iter() by calling
		 * filemap_read(), we fail to fault in pages for the read buffer,
		 * in which case filemap_read() returns a short read (the number
		 * of bytes previously read is > 0, so it does not return -EFAULT).
		 */
		ret = (flags & IOMAP_NOWAIT) ? -EAGAIN : -ENOTBLK;
		goto unlock_err;
	}

	len = min(len, em->len - (start - em->start));

	/*
	 * If we have a NOWAIT request and the range contains multiple extents
	 * (or a mix of extents and holes), then we return -EAGAIN to make the
	 * caller fallback to a context where it can do a blocking (without
	 * NOWAIT) request. This way we avoid doing partial IO and returning
	 * success to the caller, which is not optimal for writes and for reads
	 * it can result in unexpected behaviour for an application.
	 *
	 * When doing a read, because we use IOMAP_DIO_PARTIAL when calling
	 * iomap_dio_rw(), we can end up returning less data then what the caller
	 * asked for, resulting in an unexpected, and incorrect, short read.
	 * That is, the caller asked to read N bytes and we return less than that,
	 * which is wrong unless we are crossing EOF. This happens if we get a
	 * page fault error when trying to fault in pages for the buffer that is
	 * associated to the struct iov_iter passed to iomap_dio_rw(), and we
	 * have previously submitted bios for other extents in the range, in
	 * which case iomap_dio_rw() may return us EIOCBQUEUED if not all of
	 * those bios have completed by the time we get the page fault error,
	 * which we return back to our caller - we should only return EIOCBQUEUED
	 * after we have submitted bios for all the extents in the range.
	 */
	if ((flags & IOMAP_NOWAIT) && len < length) {
		free_extent_map(em);
		ret = -EAGAIN;
		goto unlock_err;
	}

	if (write) {
		ret = btrfs_get_blocks_direct_write(&em, inode, dio_data,
						    start, &len, flags);
		if (ret < 0)
			goto unlock_err;
		unlock_extents = true;
		/* Recalc len in case the new em is smaller than requested */
		len = min(len, em->len - (start - em->start));
		if (dio_data->data_space_reserved) {
			u64 release_offset;
			u64 release_len = 0;

			if (dio_data->nocow_done) {
				release_offset = start;
				release_len = data_alloc_len;
			} else if (len < data_alloc_len) {
				release_offset = start + len;
				release_len = data_alloc_len - len;
			}

			if (release_len > 0)
				btrfs_free_reserved_data_space(BTRFS_I(inode),
							       dio_data->data_reserved,
							       release_offset,
							       release_len);
		}
	} else {
		/*
		 * We need to unlock only the end area that we aren't using.
		 * The rest is going to be unlocked by the endio routine.
		 */
		lockstart = start + len;
		if (lockstart < lockend)
			unlock_extents = true;
	}

	if (unlock_extents)
		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
			      &cached_state);
	else
		free_extent_state(cached_state);

	/*
	 * Translate extent map information to iomap.
	 * We trim the extents (and move the addr) even though iomap code does
	 * that, since we have locked only the parts we are performing I/O in.
	 */
	if ((em->block_start == EXTENT_MAP_HOLE) ||
	    ((em->flags & EXTENT_FLAG_PREALLOC) && !write)) {
		iomap->addr = IOMAP_NULL_ADDR;
		iomap->type = IOMAP_HOLE;
	} else {
		iomap->addr = em->block_start + (start - em->start);
		iomap->type = IOMAP_MAPPED;
	}
	iomap->offset = start;
	iomap->bdev = fs_info->fs_devices->latest_dev->bdev;
	iomap->length = len;
	free_extent_map(em);

	return 0;

unlock_err:
	unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend,
		      &cached_state);
err:
	if (dio_data->data_space_reserved) {
		btrfs_free_reserved_data_space(BTRFS_I(inode),
					       dio_data->data_reserved,
					       start, data_alloc_len);
		extent_changeset_free(dio_data->data_reserved);
	}

	return ret;
}

static int btrfs_dio_iomap_end(struct inode *inode, loff_t pos, loff_t length,
		ssize_t written, unsigned int flags, struct iomap *iomap)
{
	struct iomap_iter *iter = container_of(iomap, struct iomap_iter, iomap);
	struct btrfs_dio_data *dio_data = iter->private;
	size_t submitted = dio_data->submitted;
	const bool write = !!(flags & IOMAP_WRITE);
	int ret = 0;

	if (!write && (iomap->type == IOMAP_HOLE)) {
		/* If reading from a hole, unlock and return */
		unlock_extent(&BTRFS_I(inode)->io_tree, pos, pos + length - 1,
			      NULL);
		return 0;
	}

	if (submitted < length) {
		pos += submitted;
		length -= submitted;
		if (write)
			btrfs_finish_ordered_extent(dio_data->ordered, NULL,
						    pos, length, false);
		else
			unlock_extent(&BTRFS_I(inode)->io_tree, pos,
				      pos + length - 1, NULL);
		ret = -ENOTBLK;
	}
	if (write) {
		btrfs_put_ordered_extent(dio_data->ordered);
		dio_data->ordered = NULL;
	}

	if (write)
		extent_changeset_free(dio_data->data_reserved);
	return ret;
}

static void btrfs_dio_end_io(struct btrfs_bio *bbio)
{
	struct btrfs_dio_private *dip =
		container_of(bbio, struct btrfs_dio_private, bbio);
	struct btrfs_inode *inode = bbio->inode;
	struct bio *bio = &bbio->bio;

	if (bio->bi_status) {
		btrfs_warn(inode->root->fs_info,
		"direct IO failed ino %llu op 0x%0x offset %#llx len %u err no %d",
			   btrfs_ino(inode), bio->bi_opf,
			   dip->file_offset, dip->bytes, bio->bi_status);
	}

	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
		btrfs_finish_ordered_extent(bbio->ordered, NULL,
					    dip->file_offset, dip->bytes,
					    !bio->bi_status);
	} else {
		unlock_extent(&inode->io_tree, dip->file_offset,
			      dip->file_offset + dip->bytes - 1, NULL);
	}

	bbio->bio.bi_private = bbio->private;
	iomap_dio_bio_end_io(bio);
}

static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio,
				loff_t file_offset)
{
	struct btrfs_bio *bbio = btrfs_bio(bio);
	struct btrfs_dio_private *dip =
		container_of(bbio, struct btrfs_dio_private, bbio);
	struct btrfs_dio_data *dio_data = iter->private;

	btrfs_bio_init(bbio, BTRFS_I(iter->inode)->root->fs_info,
		       btrfs_dio_end_io, bio->bi_private);
	bbio->inode = BTRFS_I(iter->inode);
	bbio->file_offset = file_offset;

	dip->file_offset = file_offset;
	dip->bytes = bio->bi_iter.bi_size;

	dio_data->submitted += bio->bi_iter.bi_size;

	/*
	 * Check if we are doing a partial write.  If we are, we need to split
	 * the ordered extent to match the submitted bio.  Hang on to the
	 * remaining unfinishable ordered_extent in dio_data so that it can be
	 * cancelled in iomap_end to avoid a deadlock wherein faulting the
	 * remaining pages is blocked on the outstanding ordered extent.
	 */
	if (iter->flags & IOMAP_WRITE) {
		int ret;

		ret = btrfs_extract_ordered_extent(bbio, dio_data->ordered);
		if (ret) {
			btrfs_finish_ordered_extent(dio_data->ordered, NULL,
						    file_offset, dip->bytes,
						    !ret);
			bio->bi_status = errno_to_blk_status(ret);
			iomap_dio_bio_end_io(bio);
			return;
		}
	}

	btrfs_submit_bio(bbio, 0);
}

static const struct iomap_ops btrfs_dio_iomap_ops = {
	.iomap_begin            = btrfs_dio_iomap_begin,
	.iomap_end              = btrfs_dio_iomap_end,
};

static const struct iomap_dio_ops btrfs_dio_ops = {
	.submit_io		= btrfs_dio_submit_io,
	.bio_set		= &btrfs_dio_bioset,
};

ssize_t btrfs_dio_read(struct kiocb *iocb, struct iov_iter *iter, size_t done_before)
{
	struct btrfs_dio_data data = { 0 };

	return iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
			    IOMAP_DIO_PARTIAL, &data, done_before);
}

struct iomap_dio *btrfs_dio_write(struct kiocb *iocb, struct iov_iter *iter,
				  size_t done_before)
{
	struct btrfs_dio_data data = { 0 };

	return __iomap_dio_rw(iocb, iter, &btrfs_dio_iomap_ops, &btrfs_dio_ops,
			    IOMAP_DIO_PARTIAL, &data, done_before);
}

static int btrfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
			u64 start, u64 len)
{
	int	ret;

	ret = fiemap_prep(inode, fieinfo, start, &len, 0);
	if (ret)
		return ret;

	/*
	 * fiemap_prep() called filemap_write_and_wait() for the whole possible
	 * file range (0 to LLONG_MAX), but that is not enough if we have
	 * compression enabled. The first filemap_fdatawrite_range() only kicks
	 * in the compression of data (in an async thread) and will return
	 * before the compression is done and writeback is started. A second
	 * filemap_fdatawrite_range() is needed to wait for the compression to
	 * complete and writeback to start. We also need to wait for ordered
	 * extents to complete, because our fiemap implementation uses mainly
	 * file extent items to list the extents, searching for extent maps
	 * only for file ranges with holes or prealloc extents to figure out
	 * if we have delalloc in those ranges.
	 */
	if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) {
		ret = btrfs_wait_ordered_range(inode, 0, LLONG_MAX);
		if (ret)
			return ret;
	}

	return extent_fiemap(BTRFS_I(inode), fieinfo, start, len);
}

static int btrfs_writepages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
	return extent_writepages(mapping, wbc);
}

static void btrfs_readahead(struct readahead_control *rac)
{
	extent_readahead(rac);
}

/*
 * For release_folio() and invalidate_folio() we have a race window where
 * folio_end_writeback() is called but the subpage spinlock is not yet released.
 * If we continue to release/invalidate the page, we could cause use-after-free
 * for subpage spinlock.  So this function is to spin and wait for subpage
 * spinlock.
 */
static void wait_subpage_spinlock(struct page *page)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
	struct folio *folio = page_folio(page);
	struct btrfs_subpage *subpage;

	if (!btrfs_is_subpage(fs_info, page->mapping))
		return;

	ASSERT(folio_test_private(folio) && folio_get_private(folio));
	subpage = folio_get_private(folio);

	/*
	 * This may look insane as we just acquire the spinlock and release it,
	 * without doing anything.  But we just want to make sure no one is
	 * still holding the subpage spinlock.
	 * And since the page is not dirty nor writeback, and we have page
	 * locked, the only possible way to hold a spinlock is from the endio
	 * function to clear page writeback.
	 *
	 * Here we just acquire the spinlock so that all existing callers
	 * should exit and we're safe to release/invalidate the page.
	 */
	spin_lock_irq(&subpage->lock);
	spin_unlock_irq(&subpage->lock);
}

static bool __btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
{
	int ret = try_release_extent_mapping(&folio->page, gfp_flags);

	if (ret == 1) {
		wait_subpage_spinlock(&folio->page);
		clear_page_extent_mapped(&folio->page);
	}
	return ret;
}

static bool btrfs_release_folio(struct folio *folio, gfp_t gfp_flags)
{
	if (folio_test_writeback(folio) || folio_test_dirty(folio))
		return false;
	return __btrfs_release_folio(folio, gfp_flags);
}

#ifdef CONFIG_MIGRATION
static int btrfs_migrate_folio(struct address_space *mapping,
			     struct folio *dst, struct folio *src,
			     enum migrate_mode mode)
{
	int ret = filemap_migrate_folio(mapping, dst, src, mode);

	if (ret != MIGRATEPAGE_SUCCESS)
		return ret;

	if (folio_test_ordered(src)) {
		folio_clear_ordered(src);
		folio_set_ordered(dst);
	}

	return MIGRATEPAGE_SUCCESS;
}
#else
#define btrfs_migrate_folio NULL
#endif

static void btrfs_invalidate_folio(struct folio *folio, size_t offset,
				 size_t length)
{
	struct btrfs_inode *inode = BTRFS_I(folio->mapping->host);
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct extent_io_tree *tree = &inode->io_tree;
	struct extent_state *cached_state = NULL;
	u64 page_start = folio_pos(folio);
	u64 page_end = page_start + folio_size(folio) - 1;
	u64 cur;
	int inode_evicting = inode->vfs_inode.i_state & I_FREEING;

	/*
	 * We have folio locked so no new ordered extent can be created on this
	 * page, nor bio can be submitted for this folio.
	 *
	 * But already submitted bio can still be finished on this folio.
	 * Furthermore, endio function won't skip folio which has Ordered
	 * (Private2) already cleared, so it's possible for endio and
	 * invalidate_folio to do the same ordered extent accounting twice
	 * on one folio.
	 *
	 * So here we wait for any submitted bios to finish, so that we won't
	 * do double ordered extent accounting on the same folio.
	 */
	folio_wait_writeback(folio);
	wait_subpage_spinlock(&folio->page);

	/*
	 * For subpage case, we have call sites like
	 * btrfs_punch_hole_lock_range() which passes range not aligned to
	 * sectorsize.
	 * If the range doesn't cover the full folio, we don't need to and
	 * shouldn't clear page extent mapped, as folio->private can still
	 * record subpage dirty bits for other part of the range.
	 *
	 * For cases that invalidate the full folio even the range doesn't
	 * cover the full folio, like invalidating the last folio, we're
	 * still safe to wait for ordered extent to finish.
	 */
	if (!(offset == 0 && length == folio_size(folio))) {
		btrfs_release_folio(folio, GFP_NOFS);
		return;
	}

	if (!inode_evicting)
		lock_extent(tree, page_start, page_end, &cached_state);

	cur = page_start;
	while (cur < page_end) {
		struct btrfs_ordered_extent *ordered;
		u64 range_end;
		u32 range_len;
		u32 extra_flags = 0;

		ordered = btrfs_lookup_first_ordered_range(inode, cur,
							   page_end + 1 - cur);
		if (!ordered) {
			range_end = page_end;
			/*
			 * No ordered extent covering this range, we are safe
			 * to delete all extent states in the range.
			 */
			extra_flags = EXTENT_CLEAR_ALL_BITS;
			goto next;
		}
		if (ordered->file_offset > cur) {
			/*
			 * There is a range between [cur, oe->file_offset) not
			 * covered by any ordered extent.
			 * We are safe to delete all extent states, and handle
			 * the ordered extent in the next iteration.
			 */
			range_end = ordered->file_offset - 1;
			extra_flags = EXTENT_CLEAR_ALL_BITS;
			goto next;
		}

		range_end = min(ordered->file_offset + ordered->num_bytes - 1,
				page_end);
		ASSERT(range_end + 1 - cur < U32_MAX);
		range_len = range_end + 1 - cur;
		if (!btrfs_folio_test_ordered(fs_info, folio, cur, range_len)) {
			/*
			 * If Ordered (Private2) is cleared, it means endio has
			 * already been executed for the range.
			 * We can't delete the extent states as
			 * btrfs_finish_ordered_io() may still use some of them.
			 */
			goto next;
		}
		btrfs_folio_clear_ordered(fs_info, folio, cur, range_len);

		/*
		 * IO on this page will never be started, so we need to account
		 * for any ordered extents now. Don't clear EXTENT_DELALLOC_NEW
		 * here, must leave that up for the ordered extent completion.
		 *
		 * This will also unlock the range for incoming
		 * btrfs_finish_ordered_io().
		 */
		if (!inode_evicting)
			clear_extent_bit(tree, cur, range_end,
					 EXTENT_DELALLOC |
					 EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
					 EXTENT_DEFRAG, &cached_state);

		spin_lock_irq(&inode->ordered_tree_lock);
		set_bit(BTRFS_ORDERED_TRUNCATED, &ordered->flags);
		ordered->truncated_len = min(ordered->truncated_len,
					     cur - ordered->file_offset);
		spin_unlock_irq(&inode->ordered_tree_lock);

		/*
		 * If the ordered extent has finished, we're safe to delete all
		 * the extent states of the range, otherwise
		 * btrfs_finish_ordered_io() will get executed by endio for
		 * other pages, so we can't delete extent states.
		 */
		if (btrfs_dec_test_ordered_pending(inode, &ordered,
						   cur, range_end + 1 - cur)) {
			btrfs_finish_ordered_io(ordered);
			/*
			 * The ordered extent has finished, now we're again
			 * safe to delete all extent states of the range.
			 */
			extra_flags = EXTENT_CLEAR_ALL_BITS;
		}
next:
		if (ordered)
			btrfs_put_ordered_extent(ordered);
		/*
		 * Qgroup reserved space handler
		 * Sector(s) here will be either:
		 *
		 * 1) Already written to disk or bio already finished
		 *    Then its QGROUP_RESERVED bit in io_tree is already cleared.
		 *    Qgroup will be handled by its qgroup_record then.
		 *    btrfs_qgroup_free_data() call will do nothing here.
		 *
		 * 2) Not written to disk yet
		 *    Then btrfs_qgroup_free_data() call will clear the
		 *    QGROUP_RESERVED bit of its io_tree, and free the qgroup
		 *    reserved data space.
		 *    Since the IO will never happen for this page.
		 */
		btrfs_qgroup_free_data(inode, NULL, cur, range_end + 1 - cur, NULL);
		if (!inode_evicting) {
			clear_extent_bit(tree, cur, range_end, EXTENT_LOCKED |
				 EXTENT_DELALLOC | EXTENT_UPTODATE |
				 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG |
				 extra_flags, &cached_state);
		}
		cur = range_end + 1;
	}
	/*
	 * We have iterated through all ordered extents of the page, the page
	 * should not have Ordered (Private2) anymore, or the above iteration
	 * did something wrong.
	 */
	ASSERT(!folio_test_ordered(folio));
	btrfs_folio_clear_checked(fs_info, folio, folio_pos(folio), folio_size(folio));
	if (!inode_evicting)
		__btrfs_release_folio(folio, GFP_NOFS);
	clear_page_extent_mapped(&folio->page);
}

/*
 * btrfs_page_mkwrite() is not allowed to change the file size as it gets
 * called from a page fault handler when a page is first dirtied. Hence we must
 * be careful to check for EOF conditions here. We set the page up correctly
 * for a written page which means we get ENOSPC checking when writing into
 * holes and correct delalloc and unwritten extent mapping on filesystems that
 * support these features.
 *
 * We are not allowed to take the i_mutex here so we have to play games to
 * protect against truncate races as the page could now be beyond EOF.  Because
 * truncate_setsize() writes the inode size before removing pages, once we have
 * the page lock we can determine safely if the page is beyond EOF. If it is not
 * beyond EOF, then the page is guaranteed safe against truncation until we
 * unlock the page.
 */
vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf)
{
	struct page *page = vmf->page;
	struct folio *folio = page_folio(page);
	struct inode *inode = file_inode(vmf->vma->vm_file);
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct btrfs_ordered_extent *ordered;
	struct extent_state *cached_state = NULL;
	struct extent_changeset *data_reserved = NULL;
	unsigned long zero_start;
	loff_t size;
	vm_fault_t ret;
	int ret2;
	int reserved = 0;
	u64 reserved_space;
	u64 page_start;
	u64 page_end;
	u64 end;

	ASSERT(folio_order(folio) == 0);

	reserved_space = PAGE_SIZE;

	sb_start_pagefault(inode->i_sb);
	page_start = page_offset(page);
	page_end = page_start + PAGE_SIZE - 1;
	end = page_end;

	/*
	 * Reserving delalloc space after obtaining the page lock can lead to
	 * deadlock. For example, if a dirty page is locked by this function
	 * and the call to btrfs_delalloc_reserve_space() ends up triggering
	 * dirty page write out, then the btrfs_writepages() function could
	 * end up waiting indefinitely to get a lock on the page currently
	 * being processed by btrfs_page_mkwrite() function.
	 */
	ret2 = btrfs_delalloc_reserve_space(BTRFS_I(inode), &data_reserved,
					    page_start, reserved_space);
	if (!ret2) {
		ret2 = file_update_time(vmf->vma->vm_file);
		reserved = 1;
	}
	if (ret2) {
		ret = vmf_error(ret2);
		if (reserved)
			goto out;
		goto out_noreserve;
	}

	ret = VM_FAULT_NOPAGE; /* make the VM retry the fault */
again:
	down_read(&BTRFS_I(inode)->i_mmap_lock);
	lock_page(page);
	size = i_size_read(inode);

	if ((page->mapping != inode->i_mapping) ||
	    (page_start >= size)) {
		/* page got truncated out from underneath us */
		goto out_unlock;
	}
	wait_on_page_writeback(page);

	lock_extent(io_tree, page_start, page_end, &cached_state);
	ret2 = set_page_extent_mapped(page);
	if (ret2 < 0) {
		ret = vmf_error(ret2);
		unlock_extent(io_tree, page_start, page_end, &cached_state);
		goto out_unlock;
	}

	/*
	 * we can't set the delalloc bits if there are pending ordered
	 * extents.  Drop our locks and wait for them to finish
	 */
	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
			PAGE_SIZE);
	if (ordered) {
		unlock_extent(io_tree, page_start, page_end, &cached_state);
		unlock_page(page);
		up_read(&BTRFS_I(inode)->i_mmap_lock);
		btrfs_start_ordered_extent(ordered);
		btrfs_put_ordered_extent(ordered);
		goto again;
	}

	if (page->index == ((size - 1) >> PAGE_SHIFT)) {
		reserved_space = round_up(size - page_start,
					  fs_info->sectorsize);
		if (reserved_space < PAGE_SIZE) {
			end = page_start + reserved_space - 1;
			btrfs_delalloc_release_space(BTRFS_I(inode),
					data_reserved, page_start,
					PAGE_SIZE - reserved_space, true);
		}
	}

	/*
	 * page_mkwrite gets called when the page is firstly dirtied after it's
	 * faulted in, but write(2) could also dirty a page and set delalloc
	 * bits, thus in this case for space account reason, we still need to
	 * clear any delalloc bits within this page range since we have to
	 * reserve data&meta space before lock_page() (see above comments).
	 */
	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
			  EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
			  EXTENT_DEFRAG, &cached_state);

	ret2 = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start, end, 0,
					&cached_state);
	if (ret2) {
		unlock_extent(io_tree, page_start, page_end, &cached_state);
		ret = VM_FAULT_SIGBUS;
		goto out_unlock;
	}

	/* page is wholly or partially inside EOF */
	if (page_start + PAGE_SIZE > size)
		zero_start = offset_in_page(size);
	else
		zero_start = PAGE_SIZE;

	if (zero_start != PAGE_SIZE)
		memzero_page(page, zero_start, PAGE_SIZE - zero_start);

	btrfs_folio_clear_checked(fs_info, folio, page_start, PAGE_SIZE);
	btrfs_folio_set_dirty(fs_info, folio, page_start, end + 1 - page_start);
	btrfs_folio_set_uptodate(fs_info, folio, page_start, end + 1 - page_start);

	btrfs_set_inode_last_sub_trans(BTRFS_I(inode));

	unlock_extent(io_tree, page_start, page_end, &cached_state);
	up_read(&BTRFS_I(inode)->i_mmap_lock);

	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
	sb_end_pagefault(inode->i_sb);
	extent_changeset_free(data_reserved);
	return VM_FAULT_LOCKED;

out_unlock:
	unlock_page(page);
	up_read(&BTRFS_I(inode)->i_mmap_lock);
out:
	btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
	btrfs_delalloc_release_space(BTRFS_I(inode), data_reserved, page_start,
				     reserved_space, (ret != 0));
out_noreserve:
	sb_end_pagefault(inode->i_sb);
	extent_changeset_free(data_reserved);
	return ret;
}

static int btrfs_truncate(struct btrfs_inode *inode, bool skip_writeback)
{
	struct btrfs_truncate_control control = {
		.inode = inode,
		.ino = btrfs_ino(inode),
		.min_type = BTRFS_EXTENT_DATA_KEY,
		.clear_extent_range = true,
	};
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *rsv;
	int ret;
	struct btrfs_trans_handle *trans;
	u64 mask = fs_info->sectorsize - 1;
	const u64 min_size = btrfs_calc_metadata_size(fs_info, 1);

	if (!skip_writeback) {
		ret = btrfs_wait_ordered_range(&inode->vfs_inode,
					       inode->vfs_inode.i_size & (~mask),
					       (u64)-1);
		if (ret)
			return ret;
	}

	/*
	 * Yes ladies and gentlemen, this is indeed ugly.  We have a couple of
	 * things going on here:
	 *
	 * 1) We need to reserve space to update our inode.
	 *
	 * 2) We need to have something to cache all the space that is going to
	 * be free'd up by the truncate operation, but also have some slack
	 * space reserved in case it uses space during the truncate (thank you
	 * very much snapshotting).
	 *
	 * And we need these to be separate.  The fact is we can use a lot of
	 * space doing the truncate, and we have no earthly idea how much space
	 * we will use, so we need the truncate reservation to be separate so it
	 * doesn't end up using space reserved for updating the inode.  We also
	 * need to be able to stop the transaction and start a new one, which
	 * means we need to be able to update the inode several times, and we
	 * have no idea of knowing how many times that will be, so we can't just
	 * reserve 1 item for the entirety of the operation, so that has to be
	 * done separately as well.
	 *
	 * So that leaves us with
	 *
	 * 1) rsv - for the truncate reservation, which we will steal from the
	 * transaction reservation.
	 * 2) fs_info->trans_block_rsv - this will have 1 items worth left for
	 * updating the inode.
	 */
	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
	if (!rsv)
		return -ENOMEM;
	rsv->size = min_size;
	rsv->failfast = true;

	/*
	 * 1 for the truncate slack space
	 * 1 for updating the inode.
	 */
	trans = btrfs_start_transaction(root, 2);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out;
	}

	/* Migrate the slack space for the truncate to our reserve */
	ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv, rsv,
				      min_size, false);
	/*
	 * We have reserved 2 metadata units when we started the transaction and
	 * min_size matches 1 unit, so this should never fail, but if it does,
	 * it's not critical we just fail truncation.
	 */
	if (WARN_ON(ret)) {
		btrfs_end_transaction(trans);
		goto out;
	}

	trans->block_rsv = rsv;

	while (1) {
		struct extent_state *cached_state = NULL;
		const u64 new_size = inode->vfs_inode.i_size;
		const u64 lock_start = ALIGN_DOWN(new_size, fs_info->sectorsize);

		control.new_size = new_size;
		lock_extent(&inode->io_tree, lock_start, (u64)-1, &cached_state);
		/*
		 * We want to drop from the next block forward in case this new
		 * size is not block aligned since we will be keeping the last
		 * block of the extent just the way it is.
		 */
		btrfs_drop_extent_map_range(inode,
					    ALIGN(new_size, fs_info->sectorsize),
					    (u64)-1, false);

		ret = btrfs_truncate_inode_items(trans, root, &control);

		inode_sub_bytes(&inode->vfs_inode, control.sub_bytes);
		btrfs_inode_safe_disk_i_size_write(inode, control.last_size);

		unlock_extent(&inode->io_tree, lock_start, (u64)-1, &cached_state);

		trans->block_rsv = &fs_info->trans_block_rsv;
		if (ret != -ENOSPC && ret != -EAGAIN)
			break;

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

		btrfs_end_transaction(trans);
		btrfs_btree_balance_dirty(fs_info);

		trans = btrfs_start_transaction(root, 2);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			trans = NULL;
			break;
		}

		btrfs_block_rsv_release(fs_info, rsv, -1, NULL);
		ret = btrfs_block_rsv_migrate(&fs_info->trans_block_rsv,
					      rsv, min_size, false);
		/*
		 * We have reserved 2 metadata units when we started the
		 * transaction and min_size matches 1 unit, so this should never
		 * fail, but if it does, it's not critical we just fail truncation.
		 */
		if (WARN_ON(ret))
			break;

		trans->block_rsv = rsv;
	}

	/*
	 * We can't call btrfs_truncate_block inside a trans handle as we could
	 * deadlock with freeze, if we got BTRFS_NEED_TRUNCATE_BLOCK then we
	 * know we've truncated everything except the last little bit, and can
	 * do btrfs_truncate_block and then update the disk_i_size.
	 */
	if (ret == BTRFS_NEED_TRUNCATE_BLOCK) {
		btrfs_end_transaction(trans);
		btrfs_btree_balance_dirty(fs_info);

		ret = btrfs_truncate_block(inode, inode->vfs_inode.i_size, 0, 0);
		if (ret)
			goto out;
		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			goto out;
		}
		btrfs_inode_safe_disk_i_size_write(inode, 0);
	}

	if (trans) {
		int ret2;

		trans->block_rsv = &fs_info->trans_block_rsv;
		ret2 = btrfs_update_inode(trans, inode);
		if (ret2 && !ret)
			ret = ret2;

		ret2 = btrfs_end_transaction(trans);
		if (ret2 && !ret)
			ret = ret2;
		btrfs_btree_balance_dirty(fs_info);
	}
out:
	btrfs_free_block_rsv(fs_info, rsv);
	/*
	 * So if we truncate and then write and fsync we normally would just
	 * write the extents that changed, which is a problem if we need to
	 * first truncate that entire inode.  So set this flag so we write out
	 * all of the extents in the inode to the sync log so we're completely
	 * safe.
	 *
	 * If no extents were dropped or trimmed we don't need to force the next
	 * fsync to truncate all the inode's items from the log and re-log them
	 * all. This means the truncate operation did not change the file size,
	 * or changed it to a smaller size but there was only an implicit hole
	 * between the old i_size and the new i_size, and there were no prealloc
	 * extents beyond i_size to drop.
	 */
	if (control.extents_found > 0)
		btrfs_set_inode_full_sync(inode);

	return ret;
}

struct inode *btrfs_new_subvol_inode(struct mnt_idmap *idmap,
				     struct inode *dir)
{
	struct inode *inode;

	inode = new_inode(dir->i_sb);
	if (inode) {
		/*
		 * Subvolumes don't inherit the sgid bit or the parent's gid if
		 * the parent's sgid bit is set. This is probably a bug.
		 */
		inode_init_owner(idmap, inode, NULL,
				 S_IFDIR | (~current_umask() & S_IRWXUGO));
		inode->i_op = &btrfs_dir_inode_operations;
		inode->i_fop = &btrfs_dir_file_operations;
	}
	return inode;
}

struct inode *btrfs_alloc_inode(struct super_block *sb)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
	struct btrfs_inode *ei;
	struct inode *inode;
	struct extent_io_tree *file_extent_tree = NULL;

	/* Self tests may pass a NULL fs_info. */
	if (fs_info && !btrfs_fs_incompat(fs_info, NO_HOLES)) {
		file_extent_tree = kmalloc(sizeof(struct extent_io_tree), GFP_KERNEL);
		if (!file_extent_tree)
			return NULL;
	}

	ei = alloc_inode_sb(sb, btrfs_inode_cachep, GFP_KERNEL);
	if (!ei) {
		kfree(file_extent_tree);
		return NULL;
	}

	ei->root = NULL;
	ei->generation = 0;
	ei->last_trans = 0;
	ei->last_sub_trans = 0;
	ei->logged_trans = 0;
	ei->delalloc_bytes = 0;
	ei->new_delalloc_bytes = 0;
	ei->defrag_bytes = 0;
	ei->disk_i_size = 0;
	ei->flags = 0;
	ei->ro_flags = 0;
	ei->csum_bytes = 0;
	ei->index_cnt = (u64)-1;
	ei->dir_index = 0;
	ei->last_unlink_trans = 0;
	ei->last_reflink_trans = 0;
	ei->last_log_commit = 0;

	spin_lock_init(&ei->lock);
	ei->outstanding_extents = 0;
	if (sb->s_magic != BTRFS_TEST_MAGIC)
		btrfs_init_metadata_block_rsv(fs_info, &ei->block_rsv,
					      BTRFS_BLOCK_RSV_DELALLOC);
	ei->runtime_flags = 0;
	ei->prop_compress = BTRFS_COMPRESS_NONE;
	ei->defrag_compress = BTRFS_COMPRESS_NONE;

	ei->delayed_node = NULL;

	ei->i_otime_sec = 0;
	ei->i_otime_nsec = 0;

	inode = &ei->vfs_inode;
	extent_map_tree_init(&ei->extent_tree);

	/* This io tree sets the valid inode. */
	extent_io_tree_init(fs_info, &ei->io_tree, IO_TREE_INODE_IO);
	ei->io_tree.inode = ei;

	ei->file_extent_tree = file_extent_tree;
	if (file_extent_tree) {
		extent_io_tree_init(fs_info, ei->file_extent_tree,
				    IO_TREE_INODE_FILE_EXTENT);
		/* Lockdep class is set only for the file extent tree. */
		lockdep_set_class(&ei->file_extent_tree->lock, &file_extent_tree_class);
	}
	mutex_init(&ei->log_mutex);
	spin_lock_init(&ei->ordered_tree_lock);
	ei->ordered_tree = RB_ROOT;
	ei->ordered_tree_last = NULL;
	INIT_LIST_HEAD(&ei->delalloc_inodes);
	INIT_LIST_HEAD(&ei->delayed_iput);
	RB_CLEAR_NODE(&ei->rb_node);
	init_rwsem(&ei->i_mmap_lock);

	return inode;
}

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
void btrfs_test_destroy_inode(struct inode *inode)
{
	btrfs_drop_extent_map_range(BTRFS_I(inode), 0, (u64)-1, false);
	kfree(BTRFS_I(inode)->file_extent_tree);
	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
}
#endif

void btrfs_free_inode(struct inode *inode)
{
	kfree(BTRFS_I(inode)->file_extent_tree);
	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
}

void btrfs_destroy_inode(struct inode *vfs_inode)
{
	struct btrfs_ordered_extent *ordered;
	struct btrfs_inode *inode = BTRFS_I(vfs_inode);
	struct btrfs_root *root = inode->root;
	bool freespace_inode;

	WARN_ON(!hlist_empty(&vfs_inode->i_dentry));
	WARN_ON(vfs_inode->i_data.nrpages);
	WARN_ON(inode->block_rsv.reserved);
	WARN_ON(inode->block_rsv.size);
	WARN_ON(inode->outstanding_extents);
	if (!S_ISDIR(vfs_inode->i_mode)) {
		WARN_ON(inode->delalloc_bytes);
		WARN_ON(inode->new_delalloc_bytes);
	}
	WARN_ON(inode->csum_bytes);
	WARN_ON(inode->defrag_bytes);

	/*
	 * This can happen where we create an inode, but somebody else also
	 * created the same inode and we need to destroy the one we already
	 * created.
	 */
	if (!root)
		return;

	/*
	 * If this is a free space inode do not take the ordered extents lockdep
	 * map.
	 */
	freespace_inode = btrfs_is_free_space_inode(inode);

	while (1) {
		ordered = btrfs_lookup_first_ordered_extent(inode, (u64)-1);
		if (!ordered)
			break;
		else {
			btrfs_err(root->fs_info,
				  "found ordered extent %llu %llu on inode cleanup",
				  ordered->file_offset, ordered->num_bytes);

			if (!freespace_inode)
				btrfs_lockdep_acquire(root->fs_info, btrfs_ordered_extent);

			btrfs_remove_ordered_extent(inode, ordered);
			btrfs_put_ordered_extent(ordered);
			btrfs_put_ordered_extent(ordered);
		}
	}
	btrfs_qgroup_check_reserved_leak(inode);
	inode_tree_del(inode);
	btrfs_drop_extent_map_range(inode, 0, (u64)-1, false);
	btrfs_inode_clear_file_extent_range(inode, 0, (u64)-1);
	btrfs_put_root(inode->root);
}

int btrfs_drop_inode(struct inode *inode)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;

	if (root == NULL)
		return 1;

	/* the snap/subvol tree is on deleting */
	if (btrfs_root_refs(&root->root_item) == 0)
		return 1;
	else
		return generic_drop_inode(inode);
}

static void init_once(void *foo)
{
	struct btrfs_inode *ei = foo;

	inode_init_once(&ei->vfs_inode);
}

void __cold btrfs_destroy_cachep(void)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	bioset_exit(&btrfs_dio_bioset);
	kmem_cache_destroy(btrfs_inode_cachep);
}

int __init btrfs_init_cachep(void)
{
	btrfs_inode_cachep = kmem_cache_create("btrfs_inode",
			sizeof(struct btrfs_inode), 0,
			SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT,
			init_once);
	if (!btrfs_inode_cachep)
		goto fail;

	if (bioset_init(&btrfs_dio_bioset, BIO_POOL_SIZE,
			offsetof(struct btrfs_dio_private, bbio.bio),
			BIOSET_NEED_BVECS))
		goto fail;

	return 0;
fail:
	btrfs_destroy_cachep();
	return -ENOMEM;
}

static int btrfs_getattr(struct mnt_idmap *idmap,
			 const struct path *path, struct kstat *stat,
			 u32 request_mask, unsigned int flags)
{
	u64 delalloc_bytes;
	u64 inode_bytes;
	struct inode *inode = d_inode(path->dentry);
	u32 blocksize = inode->i_sb->s_blocksize;
	u32 bi_flags = BTRFS_I(inode)->flags;
	u32 bi_ro_flags = BTRFS_I(inode)->ro_flags;

	stat->result_mask |= STATX_BTIME;
	stat->btime.tv_sec = BTRFS_I(inode)->i_otime_sec;
	stat->btime.tv_nsec = BTRFS_I(inode)->i_otime_nsec;
	if (bi_flags & BTRFS_INODE_APPEND)
		stat->attributes |= STATX_ATTR_APPEND;
	if (bi_flags & BTRFS_INODE_COMPRESS)
		stat->attributes |= STATX_ATTR_COMPRESSED;
	if (bi_flags & BTRFS_INODE_IMMUTABLE)
		stat->attributes |= STATX_ATTR_IMMUTABLE;
	if (bi_flags & BTRFS_INODE_NODUMP)
		stat->attributes |= STATX_ATTR_NODUMP;
	if (bi_ro_flags & BTRFS_INODE_RO_VERITY)
		stat->attributes |= STATX_ATTR_VERITY;

	stat->attributes_mask |= (STATX_ATTR_APPEND |
				  STATX_ATTR_COMPRESSED |
				  STATX_ATTR_IMMUTABLE |
				  STATX_ATTR_NODUMP);

	generic_fillattr(idmap, request_mask, inode, stat);
	stat->dev = BTRFS_I(inode)->root->anon_dev;

	spin_lock(&BTRFS_I(inode)->lock);
	delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes;
	inode_bytes = inode_get_bytes(inode);
	spin_unlock(&BTRFS_I(inode)->lock);
	stat->blocks = (ALIGN(inode_bytes, blocksize) +
			ALIGN(delalloc_bytes, blocksize)) >> SECTOR_SHIFT;
	return 0;
}

static int btrfs_rename_exchange(struct inode *old_dir,
			      struct dentry *old_dentry,
			      struct inode *new_dir,
			      struct dentry *new_dentry)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
	struct btrfs_trans_handle *trans;
	unsigned int trans_num_items;
	struct btrfs_root *root = BTRFS_I(old_dir)->root;
	struct btrfs_root *dest = BTRFS_I(new_dir)->root;
	struct inode *new_inode = new_dentry->d_inode;
	struct inode *old_inode = old_dentry->d_inode;
	struct btrfs_rename_ctx old_rename_ctx;
	struct btrfs_rename_ctx new_rename_ctx;
	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
	u64 new_ino = btrfs_ino(BTRFS_I(new_inode));
	u64 old_idx = 0;
	u64 new_idx = 0;
	int ret;
	int ret2;
	bool need_abort = false;
	struct fscrypt_name old_fname, new_fname;
	struct fscrypt_str *old_name, *new_name;

	/*
	 * For non-subvolumes allow exchange only within one subvolume, in the
	 * same inode namespace. Two subvolumes (represented as directory) can
	 * be exchanged as they're a logical link and have a fixed inode number.
	 */
	if (root != dest &&
	    (old_ino != BTRFS_FIRST_FREE_OBJECTID ||
	     new_ino != BTRFS_FIRST_FREE_OBJECTID))
		return -EXDEV;

	ret = fscrypt_setup_filename(old_dir, &old_dentry->d_name, 0, &old_fname);
	if (ret)
		return ret;

	ret = fscrypt_setup_filename(new_dir, &new_dentry->d_name, 0, &new_fname);
	if (ret) {
		fscrypt_free_filename(&old_fname);
		return ret;
	}

	old_name = &old_fname.disk_name;
	new_name = &new_fname.disk_name;

	/* close the race window with snapshot create/destroy ioctl */
	if (old_ino == BTRFS_FIRST_FREE_OBJECTID ||
	    new_ino == BTRFS_FIRST_FREE_OBJECTID)
		down_read(&fs_info->subvol_sem);

	/*
	 * For each inode:
	 * 1 to remove old dir item
	 * 1 to remove old dir index
	 * 1 to add new dir item
	 * 1 to add new dir index
	 * 1 to update parent inode
	 *
	 * If the parents are the same, we only need to account for one
	 */
	trans_num_items = (old_dir == new_dir ? 9 : 10);
	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
		/*
		 * 1 to remove old root ref
		 * 1 to remove old root backref
		 * 1 to add new root ref
		 * 1 to add new root backref
		 */
		trans_num_items += 4;
	} else {
		/*
		 * 1 to update inode item
		 * 1 to remove old inode ref
		 * 1 to add new inode ref
		 */
		trans_num_items += 3;
	}
	if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
		trans_num_items += 4;
	else
		trans_num_items += 3;
	trans = btrfs_start_transaction(root, trans_num_items);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out_notrans;
	}

	if (dest != root) {
		ret = btrfs_record_root_in_trans(trans, dest);
		if (ret)
			goto out_fail;
	}

	/*
	 * We need to find a free sequence number both in the source and
	 * in the destination directory for the exchange.
	 */
	ret = btrfs_set_inode_index(BTRFS_I(new_dir), &old_idx);
	if (ret)
		goto out_fail;
	ret = btrfs_set_inode_index(BTRFS_I(old_dir), &new_idx);
	if (ret)
		goto out_fail;

	BTRFS_I(old_inode)->dir_index = 0ULL;
	BTRFS_I(new_inode)->dir_index = 0ULL;

	/* Reference for the source. */
	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
		/* force full log commit if subvolume involved. */
		btrfs_set_log_full_commit(trans);
	} else {
		ret = btrfs_insert_inode_ref(trans, dest, new_name, old_ino,
					     btrfs_ino(BTRFS_I(new_dir)),
					     old_idx);
		if (ret)
			goto out_fail;
		need_abort = true;
	}

	/* And now for the dest. */
	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
		/* force full log commit if subvolume involved. */
		btrfs_set_log_full_commit(trans);
	} else {
		ret = btrfs_insert_inode_ref(trans, root, old_name, new_ino,
					     btrfs_ino(BTRFS_I(old_dir)),
					     new_idx);
		if (ret) {
			if (need_abort)
				btrfs_abort_transaction(trans, ret);
			goto out_fail;
		}
	}

	/* Update inode version and ctime/mtime. */
	inode_inc_iversion(old_dir);
	inode_inc_iversion(new_dir);
	inode_inc_iversion(old_inode);
	inode_inc_iversion(new_inode);
	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);

	if (old_dentry->d_parent != new_dentry->d_parent) {
		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
					BTRFS_I(old_inode), true);
		btrfs_record_unlink_dir(trans, BTRFS_I(new_dir),
					BTRFS_I(new_inode), true);
	}

	/* src is a subvolume */
	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
		ret = btrfs_unlink_subvol(trans, BTRFS_I(old_dir), old_dentry);
	} else { /* src is an inode */
		ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir),
					   BTRFS_I(old_dentry->d_inode),
					   old_name, &old_rename_ctx);
		if (!ret)
			ret = btrfs_update_inode(trans, BTRFS_I(old_inode));
	}
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_fail;
	}

	/* dest is a subvolume */
	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
		ret = btrfs_unlink_subvol(trans, BTRFS_I(new_dir), new_dentry);
	} else { /* dest is an inode */
		ret = __btrfs_unlink_inode(trans, BTRFS_I(new_dir),
					   BTRFS_I(new_dentry->d_inode),
					   new_name, &new_rename_ctx);
		if (!ret)
			ret = btrfs_update_inode(trans, BTRFS_I(new_inode));
	}
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_fail;
	}

	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
			     new_name, 0, old_idx);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_fail;
	}

	ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode),
			     old_name, 0, new_idx);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_fail;
	}

	if (old_inode->i_nlink == 1)
		BTRFS_I(old_inode)->dir_index = old_idx;
	if (new_inode->i_nlink == 1)
		BTRFS_I(new_inode)->dir_index = new_idx;

	/*
	 * Now pin the logs of the roots. We do it to ensure that no other task
	 * can sync the logs while we are in progress with the rename, because
	 * that could result in an inconsistency in case any of the inodes that
	 * are part of this rename operation were logged before.
	 */
	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
		btrfs_pin_log_trans(root);
	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
		btrfs_pin_log_trans(dest);

	/* Do the log updates for all inodes. */
	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
				   old_rename_ctx.index, new_dentry->d_parent);
	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
		btrfs_log_new_name(trans, new_dentry, BTRFS_I(new_dir),
				   new_rename_ctx.index, old_dentry->d_parent);

	/* Now unpin the logs. */
	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
		btrfs_end_log_trans(root);
	if (new_ino != BTRFS_FIRST_FREE_OBJECTID)
		btrfs_end_log_trans(dest);
out_fail:
	ret2 = btrfs_end_transaction(trans);
	ret = ret ? ret : ret2;
out_notrans:
	if (new_ino == BTRFS_FIRST_FREE_OBJECTID ||
	    old_ino == BTRFS_FIRST_FREE_OBJECTID)
		up_read(&fs_info->subvol_sem);

	fscrypt_free_filename(&new_fname);
	fscrypt_free_filename(&old_fname);
	return ret;
}

static struct inode *new_whiteout_inode(struct mnt_idmap *idmap,
					struct inode *dir)
{
	struct inode *inode;

	inode = new_inode(dir->i_sb);
	if (inode) {
		inode_init_owner(idmap, inode, dir,
				 S_IFCHR | WHITEOUT_MODE);
		inode->i_op = &btrfs_special_inode_operations;
		init_special_inode(inode, inode->i_mode, WHITEOUT_DEV);
	}
	return inode;
}

static int btrfs_rename(struct mnt_idmap *idmap,
			struct inode *old_dir, struct dentry *old_dentry,
			struct inode *new_dir, struct dentry *new_dentry,
			unsigned int flags)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(old_dir->i_sb);
	struct btrfs_new_inode_args whiteout_args = {
		.dir = old_dir,
		.dentry = old_dentry,
	};
	struct btrfs_trans_handle *trans;
	unsigned int trans_num_items;
	struct btrfs_root *root = BTRFS_I(old_dir)->root;
	struct btrfs_root *dest = BTRFS_I(new_dir)->root;
	struct inode *new_inode = d_inode(new_dentry);
	struct inode *old_inode = d_inode(old_dentry);
	struct btrfs_rename_ctx rename_ctx;
	u64 index = 0;
	int ret;
	int ret2;
	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
	struct fscrypt_name old_fname, new_fname;

	if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
		return -EPERM;

	/* we only allow rename subvolume link between subvolumes */
	if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
		return -EXDEV;

	if (old_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID ||
	    (new_inode && btrfs_ino(BTRFS_I(new_inode)) == BTRFS_FIRST_FREE_OBJECTID))
		return -ENOTEMPTY;

	if (S_ISDIR(old_inode->i_mode) && new_inode &&
	    new_inode->i_size > BTRFS_EMPTY_DIR_SIZE)
		return -ENOTEMPTY;

	ret = fscrypt_setup_filename(old_dir, &old_dentry->d_name, 0, &old_fname);
	if (ret)
		return ret;

	ret = fscrypt_setup_filename(new_dir, &new_dentry->d_name, 0, &new_fname);
	if (ret) {
		fscrypt_free_filename(&old_fname);
		return ret;
	}

	/* check for collisions, even if the  name isn't there */
	ret = btrfs_check_dir_item_collision(dest, new_dir->i_ino, &new_fname.disk_name);
	if (ret) {
		if (ret == -EEXIST) {
			/* we shouldn't get
			 * eexist without a new_inode */
			if (WARN_ON(!new_inode)) {
				goto out_fscrypt_names;
			}
		} else {
			/* maybe -EOVERFLOW */
			goto out_fscrypt_names;
		}
	}
	ret = 0;

	/*
	 * we're using rename to replace one file with another.  Start IO on it
	 * now so  we don't add too much work to the end of the transaction
	 */
	if (new_inode && S_ISREG(old_inode->i_mode) && new_inode->i_size)
		filemap_flush(old_inode->i_mapping);

	if (flags & RENAME_WHITEOUT) {
		whiteout_args.inode = new_whiteout_inode(idmap, old_dir);
		if (!whiteout_args.inode) {
			ret = -ENOMEM;
			goto out_fscrypt_names;
		}
		ret = btrfs_new_inode_prepare(&whiteout_args, &trans_num_items);
		if (ret)
			goto out_whiteout_inode;
	} else {
		/* 1 to update the old parent inode. */
		trans_num_items = 1;
	}

	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
		/* Close the race window with snapshot create/destroy ioctl */
		down_read(&fs_info->subvol_sem);
		/*
		 * 1 to remove old root ref
		 * 1 to remove old root backref
		 * 1 to add new root ref
		 * 1 to add new root backref
		 */
		trans_num_items += 4;
	} else {
		/*
		 * 1 to update inode
		 * 1 to remove old inode ref
		 * 1 to add new inode ref
		 */
		trans_num_items += 3;
	}
	/*
	 * 1 to remove old dir item
	 * 1 to remove old dir index
	 * 1 to add new dir item
	 * 1 to add new dir index
	 */
	trans_num_items += 4;
	/* 1 to update new parent inode if it's not the same as the old parent */
	if (new_dir != old_dir)
		trans_num_items++;
	if (new_inode) {
		/*
		 * 1 to update inode
		 * 1 to remove inode ref
		 * 1 to remove dir item
		 * 1 to remove dir index
		 * 1 to possibly add orphan item
		 */
		trans_num_items += 5;
	}
	trans = btrfs_start_transaction(root, trans_num_items);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out_notrans;
	}

	if (dest != root) {
		ret = btrfs_record_root_in_trans(trans, dest);
		if (ret)
			goto out_fail;
	}

	ret = btrfs_set_inode_index(BTRFS_I(new_dir), &index);
	if (ret)
		goto out_fail;

	BTRFS_I(old_inode)->dir_index = 0ULL;
	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
		/* force full log commit if subvolume involved. */
		btrfs_set_log_full_commit(trans);
	} else {
		ret = btrfs_insert_inode_ref(trans, dest, &new_fname.disk_name,
					     old_ino, btrfs_ino(BTRFS_I(new_dir)),
					     index);
		if (ret)
			goto out_fail;
	}

	inode_inc_iversion(old_dir);
	inode_inc_iversion(new_dir);
	inode_inc_iversion(old_inode);
	simple_rename_timestamp(old_dir, old_dentry, new_dir, new_dentry);

	if (old_dentry->d_parent != new_dentry->d_parent)
		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
					BTRFS_I(old_inode), true);

	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
		ret = btrfs_unlink_subvol(trans, BTRFS_I(old_dir), old_dentry);
	} else {
		ret = __btrfs_unlink_inode(trans, BTRFS_I(old_dir),
					   BTRFS_I(d_inode(old_dentry)),
					   &old_fname.disk_name, &rename_ctx);
		if (!ret)
			ret = btrfs_update_inode(trans, BTRFS_I(old_inode));
	}
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_fail;
	}

	if (new_inode) {
		inode_inc_iversion(new_inode);
		if (unlikely(btrfs_ino(BTRFS_I(new_inode)) ==
			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
			ret = btrfs_unlink_subvol(trans, BTRFS_I(new_dir), new_dentry);
			BUG_ON(new_inode->i_nlink == 0);
		} else {
			ret = btrfs_unlink_inode(trans, BTRFS_I(new_dir),
						 BTRFS_I(d_inode(new_dentry)),
						 &new_fname.disk_name);
		}
		if (!ret && new_inode->i_nlink == 0)
			ret = btrfs_orphan_add(trans,
					BTRFS_I(d_inode(new_dentry)));
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out_fail;
		}
	}

	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
			     &new_fname.disk_name, 0, index);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		goto out_fail;
	}

	if (old_inode->i_nlink == 1)
		BTRFS_I(old_inode)->dir_index = index;

	if (old_ino != BTRFS_FIRST_FREE_OBJECTID)
		btrfs_log_new_name(trans, old_dentry, BTRFS_I(old_dir),
				   rename_ctx.index, new_dentry->d_parent);

	if (flags & RENAME_WHITEOUT) {
		ret = btrfs_create_new_inode(trans, &whiteout_args);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out_fail;
		} else {
			unlock_new_inode(whiteout_args.inode);
			iput(whiteout_args.inode);
			whiteout_args.inode = NULL;
		}
	}
out_fail:
	ret2 = btrfs_end_transaction(trans);
	ret = ret ? ret : ret2;
out_notrans:
	if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
		up_read(&fs_info->subvol_sem);
	if (flags & RENAME_WHITEOUT)
		btrfs_new_inode_args_destroy(&whiteout_args);
out_whiteout_inode:
	if (flags & RENAME_WHITEOUT)
		iput(whiteout_args.inode);
out_fscrypt_names:
	fscrypt_free_filename(&old_fname);
	fscrypt_free_filename(&new_fname);
	return ret;
}

static int btrfs_rename2(struct mnt_idmap *idmap, struct inode *old_dir,
			 struct dentry *old_dentry, struct inode *new_dir,
			 struct dentry *new_dentry, unsigned int flags)
{
	int ret;

	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
		return -EINVAL;

	if (flags & RENAME_EXCHANGE)
		ret = btrfs_rename_exchange(old_dir, old_dentry, new_dir,
					    new_dentry);
	else
		ret = btrfs_rename(idmap, old_dir, old_dentry, new_dir,
				   new_dentry, flags);

	btrfs_btree_balance_dirty(BTRFS_I(new_dir)->root->fs_info);

	return ret;
}

struct btrfs_delalloc_work {
	struct inode *inode;
	struct completion completion;
	struct list_head list;
	struct btrfs_work work;
};

static void btrfs_run_delalloc_work(struct btrfs_work *work)
{
	struct btrfs_delalloc_work *delalloc_work;
	struct inode *inode;

	delalloc_work = container_of(work, struct btrfs_delalloc_work,
				     work);
	inode = delalloc_work->inode;
	filemap_flush(inode->i_mapping);
	if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
				&BTRFS_I(inode)->runtime_flags))
		filemap_flush(inode->i_mapping);

	iput(inode);
	complete(&delalloc_work->completion);
}

static struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode)
{
	struct btrfs_delalloc_work *work;

	work = kmalloc(sizeof(*work), GFP_NOFS);
	if (!work)
		return NULL;

	init_completion(&work->completion);
	INIT_LIST_HEAD(&work->list);
	work->inode = inode;
	btrfs_init_work(&work->work, btrfs_run_delalloc_work, NULL);

	return work;
}

/*
 * some fairly slow code that needs optimization. This walks the list
 * of all the inodes with pending delalloc and forces them to disk.
 */
static int start_delalloc_inodes(struct btrfs_root *root,
				 struct writeback_control *wbc, bool snapshot,
				 bool in_reclaim_context)
{
	struct btrfs_inode *binode;
	struct inode *inode;
	struct btrfs_delalloc_work *work, *next;
	LIST_HEAD(works);
	LIST_HEAD(splice);
	int ret = 0;
	bool full_flush = wbc->nr_to_write == LONG_MAX;

	mutex_lock(&root->delalloc_mutex);
	spin_lock(&root->delalloc_lock);
	list_splice_init(&root->delalloc_inodes, &splice);
	while (!list_empty(&splice)) {
		binode = list_entry(splice.next, struct btrfs_inode,
				    delalloc_inodes);

		list_move_tail(&binode->delalloc_inodes,
			       &root->delalloc_inodes);

		if (in_reclaim_context &&
		    test_bit(BTRFS_INODE_NO_DELALLOC_FLUSH, &binode->runtime_flags))
			continue;

		inode = igrab(&binode->vfs_inode);
		if (!inode) {
			cond_resched_lock(&root->delalloc_lock);
			continue;
		}
		spin_unlock(&root->delalloc_lock);

		if (snapshot)
			set_bit(BTRFS_INODE_SNAPSHOT_FLUSH,
				&binode->runtime_flags);
		if (full_flush) {
			work = btrfs_alloc_delalloc_work(inode);
			if (!work) {
				iput(inode);
				ret = -ENOMEM;
				goto out;
			}
			list_add_tail(&work->list, &works);
			btrfs_queue_work(root->fs_info->flush_workers,
					 &work->work);
		} else {
			ret = filemap_fdatawrite_wbc(inode->i_mapping, wbc);
			btrfs_add_delayed_iput(BTRFS_I(inode));
			if (ret || wbc->nr_to_write <= 0)
				goto out;
		}
		cond_resched();
		spin_lock(&root->delalloc_lock);
	}
	spin_unlock(&root->delalloc_lock);

out:
	list_for_each_entry_safe(work, next, &works, list) {
		list_del_init(&work->list);
		wait_for_completion(&work->completion);
		kfree(work);
	}

	if (!list_empty(&splice)) {
		spin_lock(&root->delalloc_lock);
		list_splice_tail(&splice, &root->delalloc_inodes);
		spin_unlock(&root->delalloc_lock);
	}
	mutex_unlock(&root->delalloc_mutex);
	return ret;
}

int btrfs_start_delalloc_snapshot(struct btrfs_root *root, bool in_reclaim_context)
{
	struct writeback_control wbc = {
		.nr_to_write = LONG_MAX,
		.sync_mode = WB_SYNC_NONE,
		.range_start = 0,
		.range_end = LLONG_MAX,
	};
	struct btrfs_fs_info *fs_info = root->fs_info;

	if (BTRFS_FS_ERROR(fs_info))
		return -EROFS;

	return start_delalloc_inodes(root, &wbc, true, in_reclaim_context);
}

int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr,
			       bool in_reclaim_context)
{
	struct writeback_control wbc = {
		.nr_to_write = nr,
		.sync_mode = WB_SYNC_NONE,
		.range_start = 0,
		.range_end = LLONG_MAX,
	};
	struct btrfs_root *root;
	LIST_HEAD(splice);
	int ret;

	if (BTRFS_FS_ERROR(fs_info))
		return -EROFS;

	mutex_lock(&fs_info->delalloc_root_mutex);
	spin_lock(&fs_info->delalloc_root_lock);
	list_splice_init(&fs_info->delalloc_roots, &splice);
	while (!list_empty(&splice)) {
		/*
		 * Reset nr_to_write here so we know that we're doing a full
		 * flush.
		 */
		if (nr == LONG_MAX)
			wbc.nr_to_write = LONG_MAX;

		root = list_first_entry(&splice, struct btrfs_root,
					delalloc_root);
		root = btrfs_grab_root(root);
		BUG_ON(!root);
		list_move_tail(&root->delalloc_root,
			       &fs_info->delalloc_roots);
		spin_unlock(&fs_info->delalloc_root_lock);

		ret = start_delalloc_inodes(root, &wbc, false, in_reclaim_context);
		btrfs_put_root(root);
		if (ret < 0 || wbc.nr_to_write <= 0)
			goto out;
		spin_lock(&fs_info->delalloc_root_lock);
	}
	spin_unlock(&fs_info->delalloc_root_lock);

	ret = 0;
out:
	if (!list_empty(&splice)) {
		spin_lock(&fs_info->delalloc_root_lock);
		list_splice_tail(&splice, &fs_info->delalloc_roots);
		spin_unlock(&fs_info->delalloc_root_lock);
	}
	mutex_unlock(&fs_info->delalloc_root_mutex);
	return ret;
}

static int btrfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
			 struct dentry *dentry, const char *symname)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct btrfs_path *path;
	struct btrfs_key key;
	struct inode *inode;
	struct btrfs_new_inode_args new_inode_args = {
		.dir = dir,
		.dentry = dentry,
	};
	unsigned int trans_num_items;
	int err;
	int name_len;
	int datasize;
	unsigned long ptr;
	struct btrfs_file_extent_item *ei;
	struct extent_buffer *leaf;

	name_len = strlen(symname);
	if (name_len > BTRFS_MAX_INLINE_DATA_SIZE(fs_info))
		return -ENAMETOOLONG;

	inode = new_inode(dir->i_sb);
	if (!inode)
		return -ENOMEM;
	inode_init_owner(idmap, inode, dir, S_IFLNK | S_IRWXUGO);
	inode->i_op = &btrfs_symlink_inode_operations;
	inode_nohighmem(inode);
	inode->i_mapping->a_ops = &btrfs_aops;
	btrfs_i_size_write(BTRFS_I(inode), name_len);
	inode_set_bytes(inode, name_len);

	new_inode_args.inode = inode;
	err = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
	if (err)
		goto out_inode;
	/* 1 additional item for the inline extent */
	trans_num_items++;

	trans = btrfs_start_transaction(root, trans_num_items);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_new_inode_args;
	}

	err = btrfs_create_new_inode(trans, &new_inode_args);
	if (err)
		goto out;

	path = btrfs_alloc_path();
	if (!path) {
		err = -ENOMEM;
		btrfs_abort_transaction(trans, err);
		discard_new_inode(inode);
		inode = NULL;
		goto out;
	}
	key.objectid = btrfs_ino(BTRFS_I(inode));
	key.offset = 0;
	key.type = BTRFS_EXTENT_DATA_KEY;
	datasize = btrfs_file_extent_calc_inline_size(name_len);
	err = btrfs_insert_empty_item(trans, root, path, &key,
				      datasize);
	if (err) {
		btrfs_abort_transaction(trans, err);
		btrfs_free_path(path);
		discard_new_inode(inode);
		inode = NULL;
		goto out;
	}
	leaf = path->nodes[0];
	ei = btrfs_item_ptr(leaf, path->slots[0],
			    struct btrfs_file_extent_item);
	btrfs_set_file_extent_generation(leaf, ei, trans->transid);
	btrfs_set_file_extent_type(leaf, ei,
				   BTRFS_FILE_EXTENT_INLINE);
	btrfs_set_file_extent_encryption(leaf, ei, 0);
	btrfs_set_file_extent_compression(leaf, ei, 0);
	btrfs_set_file_extent_other_encoding(leaf, ei, 0);
	btrfs_set_file_extent_ram_bytes(leaf, ei, name_len);

	ptr = btrfs_file_extent_inline_start(ei);
	write_extent_buffer(leaf, symname, ptr, name_len);
	btrfs_mark_buffer_dirty(trans, leaf);
	btrfs_free_path(path);

	d_instantiate_new(dentry, inode);
	err = 0;
out:
	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(fs_info);
out_new_inode_args:
	btrfs_new_inode_args_destroy(&new_inode_args);
out_inode:
	if (err)
		iput(inode);
	return err;
}

static struct btrfs_trans_handle *insert_prealloc_file_extent(
				       struct btrfs_trans_handle *trans_in,
				       struct btrfs_inode *inode,
				       struct btrfs_key *ins,
				       u64 file_offset)
{
	struct btrfs_file_extent_item stack_fi;
	struct btrfs_replace_extent_info extent_info;
	struct btrfs_trans_handle *trans = trans_in;
	struct btrfs_path *path;
	u64 start = ins->objectid;
	u64 len = ins->offset;
	u64 qgroup_released = 0;
	int ret;

	memset(&stack_fi, 0, sizeof(stack_fi));

	btrfs_set_stack_file_extent_type(&stack_fi, BTRFS_FILE_EXTENT_PREALLOC);
	btrfs_set_stack_file_extent_disk_bytenr(&stack_fi, start);
	btrfs_set_stack_file_extent_disk_num_bytes(&stack_fi, len);
	btrfs_set_stack_file_extent_num_bytes(&stack_fi, len);
	btrfs_set_stack_file_extent_ram_bytes(&stack_fi, len);
	btrfs_set_stack_file_extent_compression(&stack_fi, BTRFS_COMPRESS_NONE);
	/* Encryption and other encoding is reserved and all 0 */

	ret = btrfs_qgroup_release_data(inode, file_offset, len, &qgroup_released);
	if (ret < 0)
		return ERR_PTR(ret);

	if (trans) {
		ret = insert_reserved_file_extent(trans, inode,
						  file_offset, &stack_fi,
						  true, qgroup_released);
		if (ret)
			goto free_qgroup;
		return trans;
	}

	extent_info.disk_offset = start;
	extent_info.disk_len = len;
	extent_info.data_offset = 0;
	extent_info.data_len = len;
	extent_info.file_offset = file_offset;
	extent_info.extent_buf = (char *)&stack_fi;
	extent_info.is_new_extent = true;
	extent_info.update_times = true;
	extent_info.qgroup_reserved = qgroup_released;
	extent_info.insertions = 0;

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

	ret = btrfs_replace_file_extents(inode, path, file_offset,
				     file_offset + len - 1, &extent_info,
				     &trans);
	btrfs_free_path(path);
	if (ret)
		goto free_qgroup;
	return trans;

free_qgroup:
	/*
	 * We have released qgroup data range at the beginning of the function,
	 * and normally qgroup_released bytes will be freed when committing
	 * transaction.
	 * But if we error out early, we have to free what we have released
	 * or we leak qgroup data reservation.
	 */
	btrfs_qgroup_free_refroot(inode->root->fs_info,
			inode->root->root_key.objectid, qgroup_released,
			BTRFS_QGROUP_RSV_DATA);
	return ERR_PTR(ret);
}

static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
				       u64 start, u64 num_bytes, u64 min_size,
				       loff_t actual_len, u64 *alloc_hint,
				       struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct extent_map *em;
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_key ins;
	u64 cur_offset = start;
	u64 clear_offset = start;
	u64 i_size;
	u64 cur_bytes;
	u64 last_alloc = (u64)-1;
	int ret = 0;
	bool own_trans = true;
	u64 end = start + num_bytes - 1;

	if (trans)
		own_trans = false;
	while (num_bytes > 0) {
		cur_bytes = min_t(u64, num_bytes, SZ_256M);
		cur_bytes = max(cur_bytes, min_size);
		/*
		 * If we are severely fragmented we could end up with really
		 * small allocations, so if the allocator is returning small
		 * chunks lets make its job easier by only searching for those
		 * sized chunks.
		 */
		cur_bytes = min(cur_bytes, last_alloc);
		ret = btrfs_reserve_extent(root, cur_bytes, cur_bytes,
				min_size, 0, *alloc_hint, &ins, 1, 0);
		if (ret)
			break;

		/*
		 * We've reserved this space, and thus converted it from
		 * ->bytes_may_use to ->bytes_reserved.  Any error that happens
		 * from here on out we will only need to clear our reservation
		 * for the remaining unreserved area, so advance our
		 * clear_offset by our extent size.
		 */
		clear_offset += ins.offset;

		last_alloc = ins.offset;
		trans = insert_prealloc_file_extent(trans, BTRFS_I(inode),
						    &ins, cur_offset);
		/*
		 * Now that we inserted the prealloc extent we can finally
		 * decrement the number of reservations in the block group.
		 * If we did it before, we could race with relocation and have
		 * relocation miss the reserved extent, making it fail later.
		 */
		btrfs_dec_block_group_reservations(fs_info, ins.objectid);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			btrfs_free_reserved_extent(fs_info, ins.objectid,
						   ins.offset, 0);
			break;
		}

		em = alloc_extent_map();
		if (!em) {
			btrfs_drop_extent_map_range(BTRFS_I(inode), cur_offset,
					    cur_offset + ins.offset - 1, false);
			btrfs_set_inode_full_sync(BTRFS_I(inode));
			goto next;
		}

		em->start = cur_offset;
		em->orig_start = cur_offset;
		em->len = ins.offset;
		em->block_start = ins.objectid;
		em->block_len = ins.offset;
		em->orig_block_len = ins.offset;
		em->ram_bytes = ins.offset;
		em->flags |= EXTENT_FLAG_PREALLOC;
		em->generation = trans->transid;

		ret = btrfs_replace_extent_map_range(BTRFS_I(inode), em, true);
		free_extent_map(em);
next:
		num_bytes -= ins.offset;
		cur_offset += ins.offset;
		*alloc_hint = ins.objectid + ins.offset;

		inode_inc_iversion(inode);
		inode_set_ctime_current(inode);
		BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC;
		if (!(mode & FALLOC_FL_KEEP_SIZE) &&
		    (actual_len > inode->i_size) &&
		    (cur_offset > inode->i_size)) {
			if (cur_offset > actual_len)
				i_size = actual_len;
			else
				i_size = cur_offset;
			i_size_write(inode, i_size);
			btrfs_inode_safe_disk_i_size_write(BTRFS_I(inode), 0);
		}

		ret = btrfs_update_inode(trans, BTRFS_I(inode));

		if (ret) {
			btrfs_abort_transaction(trans, ret);
			if (own_trans)
				btrfs_end_transaction(trans);
			break;
		}

		if (own_trans) {
			btrfs_end_transaction(trans);
			trans = NULL;
		}
	}
	if (clear_offset < end)
		btrfs_free_reserved_data_space(BTRFS_I(inode), NULL, clear_offset,
			end - clear_offset + 1);
	return ret;
}

int btrfs_prealloc_file_range(struct inode *inode, int mode,
			      u64 start, u64 num_bytes, u64 min_size,
			      loff_t actual_len, u64 *alloc_hint)
{
	return __btrfs_prealloc_file_range(inode, mode, start, num_bytes,
					   min_size, actual_len, alloc_hint,
					   NULL);
}

int btrfs_prealloc_file_range_trans(struct inode *inode,
				    struct btrfs_trans_handle *trans, int mode,
				    u64 start, u64 num_bytes, u64 min_size,
				    loff_t actual_len, u64 *alloc_hint)
{
	return __btrfs_prealloc_file_range(inode, mode, start, num_bytes,
					   min_size, actual_len, alloc_hint, trans);
}

static int btrfs_permission(struct mnt_idmap *idmap,
			    struct inode *inode, int mask)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;
	umode_t mode = inode->i_mode;

	if (mask & MAY_WRITE &&
	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
		if (btrfs_root_readonly(root))
			return -EROFS;
		if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY)
			return -EACCES;
	}
	return generic_permission(idmap, inode, mask);
}

static int btrfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir,
			 struct file *file, umode_t mode)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(dir->i_sb);
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = BTRFS_I(dir)->root;
	struct inode *inode;
	struct btrfs_new_inode_args new_inode_args = {
		.dir = dir,
		.dentry = file->f_path.dentry,
		.orphan = true,
	};
	unsigned int trans_num_items;
	int ret;

	inode = new_inode(dir->i_sb);
	if (!inode)
		return -ENOMEM;
	inode_init_owner(idmap, inode, dir, mode);
	inode->i_fop = &btrfs_file_operations;
	inode->i_op = &btrfs_file_inode_operations;
	inode->i_mapping->a_ops = &btrfs_aops;

	new_inode_args.inode = inode;
	ret = btrfs_new_inode_prepare(&new_inode_args, &trans_num_items);
	if (ret)
		goto out_inode;

	trans = btrfs_start_transaction(root, trans_num_items);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out_new_inode_args;
	}

	ret = btrfs_create_new_inode(trans, &new_inode_args);

	/*
	 * We set number of links to 0 in btrfs_create_new_inode(), and here we
	 * set it to 1 because d_tmpfile() will issue a warning if the count is
	 * 0, through:
	 *
	 *    d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
	 */
	set_nlink(inode, 1);

	if (!ret) {
		d_tmpfile(file, inode);
		unlock_new_inode(inode);
		mark_inode_dirty(inode);
	}

	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(fs_info);
out_new_inode_args:
	btrfs_new_inode_args_destroy(&new_inode_args);
out_inode:
	if (ret)
		iput(inode);
	return finish_open_simple(file, ret);
}

void btrfs_set_range_writeback(struct btrfs_inode *inode, u64 start, u64 end)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	unsigned long index = start >> PAGE_SHIFT;
	unsigned long end_index = end >> PAGE_SHIFT;
	struct page *page;
	u32 len;

	ASSERT(end + 1 - start <= U32_MAX);
	len = end + 1 - start;
	while (index <= end_index) {
		page = find_get_page(inode->vfs_inode.i_mapping, index);
		ASSERT(page); /* Pages should be in the extent_io_tree */

		/* This is for data, which doesn't yet support larger folio. */
		ASSERT(folio_order(page_folio(page)) == 0);
		btrfs_folio_set_writeback(fs_info, page_folio(page), start, len);
		put_page(page);
		index++;
	}
}

int btrfs_encoded_io_compression_from_extent(struct btrfs_fs_info *fs_info,
					     int compress_type)
{
	switch (compress_type) {
	case BTRFS_COMPRESS_NONE:
		return BTRFS_ENCODED_IO_COMPRESSION_NONE;
	case BTRFS_COMPRESS_ZLIB:
		return BTRFS_ENCODED_IO_COMPRESSION_ZLIB;
	case BTRFS_COMPRESS_LZO:
		/*
		 * The LZO format depends on the sector size. 64K is the maximum
		 * sector size that we support.
		 */
		if (fs_info->sectorsize < SZ_4K || fs_info->sectorsize > SZ_64K)
			return -EINVAL;
		return BTRFS_ENCODED_IO_COMPRESSION_LZO_4K +
		       (fs_info->sectorsize_bits - 12);
	case BTRFS_COMPRESS_ZSTD:
		return BTRFS_ENCODED_IO_COMPRESSION_ZSTD;
	default:
		return -EUCLEAN;
	}
}

static ssize_t btrfs_encoded_read_inline(
				struct kiocb *iocb,
				struct iov_iter *iter, u64 start,
				u64 lockend,
				struct extent_state **cached_state,
				u64 extent_start, size_t count,
				struct btrfs_ioctl_encoded_io_args *encoded,
				bool *unlocked)
{
	struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp));
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct extent_io_tree *io_tree = &inode->io_tree;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_file_extent_item *item;
	u64 ram_bytes;
	unsigned long ptr;
	void *tmp;
	ssize_t ret;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}
	ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode),
				       extent_start, 0);
	if (ret) {
		if (ret > 0) {
			/* The extent item disappeared? */
			ret = -EIO;
		}
		goto out;
	}
	leaf = path->nodes[0];
	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_file_extent_item);

	ram_bytes = btrfs_file_extent_ram_bytes(leaf, item);
	ptr = btrfs_file_extent_inline_start(item);

	encoded->len = min_t(u64, extent_start + ram_bytes,
			     inode->vfs_inode.i_size) - iocb->ki_pos;
	ret = btrfs_encoded_io_compression_from_extent(fs_info,
				 btrfs_file_extent_compression(leaf, item));
	if (ret < 0)
		goto out;
	encoded->compression = ret;
	if (encoded->compression) {
		size_t inline_size;

		inline_size = btrfs_file_extent_inline_item_len(leaf,
								path->slots[0]);
		if (inline_size > count) {
			ret = -ENOBUFS;
			goto out;
		}
		count = inline_size;
		encoded->unencoded_len = ram_bytes;
		encoded->unencoded_offset = iocb->ki_pos - extent_start;
	} else {
		count = min_t(u64, count, encoded->len);
		encoded->len = count;
		encoded->unencoded_len = count;
		ptr += iocb->ki_pos - extent_start;
	}

	tmp = kmalloc(count, GFP_NOFS);
	if (!tmp) {
		ret = -ENOMEM;
		goto out;
	}
	read_extent_buffer(leaf, tmp, ptr, count);
	btrfs_release_path(path);
	unlock_extent(io_tree, start, lockend, cached_state);
	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
	*unlocked = true;

	ret = copy_to_iter(tmp, count, iter);
	if (ret != count)
		ret = -EFAULT;
	kfree(tmp);
out:
	btrfs_free_path(path);
	return ret;
}

struct btrfs_encoded_read_private {
	wait_queue_head_t wait;
	atomic_t pending;
	blk_status_t status;
};

static void btrfs_encoded_read_endio(struct btrfs_bio *bbio)
{
	struct btrfs_encoded_read_private *priv = bbio->private;

	if (bbio->bio.bi_status) {
		/*
		 * The memory barrier implied by the atomic_dec_return() here
		 * pairs with the memory barrier implied by the
		 * atomic_dec_return() or io_wait_event() in
		 * btrfs_encoded_read_regular_fill_pages() to ensure that this
		 * write is observed before the load of status in
		 * btrfs_encoded_read_regular_fill_pages().
		 */
		WRITE_ONCE(priv->status, bbio->bio.bi_status);
	}
	if (!atomic_dec_return(&priv->pending))
		wake_up(&priv->wait);
	bio_put(&bbio->bio);
}

int btrfs_encoded_read_regular_fill_pages(struct btrfs_inode *inode,
					  u64 file_offset, u64 disk_bytenr,
					  u64 disk_io_size, struct page **pages)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct btrfs_encoded_read_private priv = {
		.pending = ATOMIC_INIT(1),
	};
	unsigned long i = 0;
	struct btrfs_bio *bbio;

	init_waitqueue_head(&priv.wait);

	bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info,
			       btrfs_encoded_read_endio, &priv);
	bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
	bbio->inode = inode;

	do {
		size_t bytes = min_t(u64, disk_io_size, PAGE_SIZE);

		if (bio_add_page(&bbio->bio, pages[i], bytes, 0) < bytes) {
			atomic_inc(&priv.pending);
			btrfs_submit_bio(bbio, 0);

			bbio = btrfs_bio_alloc(BIO_MAX_VECS, REQ_OP_READ, fs_info,
					       btrfs_encoded_read_endio, &priv);
			bbio->bio.bi_iter.bi_sector = disk_bytenr >> SECTOR_SHIFT;
			bbio->inode = inode;
			continue;
		}

		i++;
		disk_bytenr += bytes;
		disk_io_size -= bytes;
	} while (disk_io_size);

	atomic_inc(&priv.pending);
	btrfs_submit_bio(bbio, 0);

	if (atomic_dec_return(&priv.pending))
		io_wait_event(priv.wait, !atomic_read(&priv.pending));
	/* See btrfs_encoded_read_endio() for ordering. */
	return blk_status_to_errno(READ_ONCE(priv.status));
}

static ssize_t btrfs_encoded_read_regular(struct kiocb *iocb,
					  struct iov_iter *iter,
					  u64 start, u64 lockend,
					  struct extent_state **cached_state,
					  u64 disk_bytenr, u64 disk_io_size,
					  size_t count, bool compressed,
					  bool *unlocked)
{
	struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp));
	struct extent_io_tree *io_tree = &inode->io_tree;
	struct page **pages;
	unsigned long nr_pages, i;
	u64 cur;
	size_t page_offset;
	ssize_t ret;

	nr_pages = DIV_ROUND_UP(disk_io_size, PAGE_SIZE);
	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
	if (!pages)
		return -ENOMEM;
	ret = btrfs_alloc_page_array(nr_pages, pages, 0);
	if (ret) {
		ret = -ENOMEM;
		goto out;
		}

	ret = btrfs_encoded_read_regular_fill_pages(inode, start, disk_bytenr,
						    disk_io_size, pages);
	if (ret)
		goto out;

	unlock_extent(io_tree, start, lockend, cached_state);
	btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
	*unlocked = true;

	if (compressed) {
		i = 0;
		page_offset = 0;
	} else {
		i = (iocb->ki_pos - start) >> PAGE_SHIFT;
		page_offset = (iocb->ki_pos - start) & (PAGE_SIZE - 1);
	}
	cur = 0;
	while (cur < count) {
		size_t bytes = min_t(size_t, count - cur,
				     PAGE_SIZE - page_offset);

		if (copy_page_to_iter(pages[i], page_offset, bytes,
				      iter) != bytes) {
			ret = -EFAULT;
			goto out;
		}
		i++;
		cur += bytes;
		page_offset = 0;
	}
	ret = count;
out:
	for (i = 0; i < nr_pages; i++) {
		if (pages[i])
			__free_page(pages[i]);
	}
	kfree(pages);
	return ret;
}

ssize_t btrfs_encoded_read(struct kiocb *iocb, struct iov_iter *iter,
			   struct btrfs_ioctl_encoded_io_args *encoded)
{
	struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp));
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct extent_io_tree *io_tree = &inode->io_tree;
	ssize_t ret;
	size_t count = iov_iter_count(iter);
	u64 start, lockend, disk_bytenr, disk_io_size;
	struct extent_state *cached_state = NULL;
	struct extent_map *em;
	bool unlocked = false;

	file_accessed(iocb->ki_filp);

	btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED);

	if (iocb->ki_pos >= inode->vfs_inode.i_size) {
		btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
		return 0;
	}
	start = ALIGN_DOWN(iocb->ki_pos, fs_info->sectorsize);
	/*
	 * We don't know how long the extent containing iocb->ki_pos is, but if
	 * it's compressed we know that it won't be longer than this.
	 */
	lockend = start + BTRFS_MAX_UNCOMPRESSED - 1;

	for (;;) {
		struct btrfs_ordered_extent *ordered;

		ret = btrfs_wait_ordered_range(&inode->vfs_inode, start,
					       lockend - start + 1);
		if (ret)
			goto out_unlock_inode;
		lock_extent(io_tree, start, lockend, &cached_state);
		ordered = btrfs_lookup_ordered_range(inode, start,
						     lockend - start + 1);
		if (!ordered)
			break;
		btrfs_put_ordered_extent(ordered);
		unlock_extent(io_tree, start, lockend, &cached_state);
		cond_resched();
	}

	em = btrfs_get_extent(inode, NULL, 0, start, lockend - start + 1);
	if (IS_ERR(em)) {
		ret = PTR_ERR(em);
		goto out_unlock_extent;
	}

	if (em->block_start == EXTENT_MAP_INLINE) {
		u64 extent_start = em->start;

		/*
		 * For inline extents we get everything we need out of the
		 * extent item.
		 */
		free_extent_map(em);
		em = NULL;
		ret = btrfs_encoded_read_inline(iocb, iter, start, lockend,
						&cached_state, extent_start,
						count, encoded, &unlocked);
		goto out;
	}

	/*
	 * We only want to return up to EOF even if the extent extends beyond
	 * that.
	 */
	encoded->len = min_t(u64, extent_map_end(em),
			     inode->vfs_inode.i_size) - iocb->ki_pos;
	if (em->block_start == EXTENT_MAP_HOLE ||
	    (em->flags & EXTENT_FLAG_PREALLOC)) {
		disk_bytenr = EXTENT_MAP_HOLE;
		count = min_t(u64, count, encoded->len);
		encoded->len = count;
		encoded->unencoded_len = count;
	} else if (extent_map_is_compressed(em)) {
		disk_bytenr = em->block_start;
		/*
		 * Bail if the buffer isn't large enough to return the whole
		 * compressed extent.
		 */
		if (em->block_len > count) {
			ret = -ENOBUFS;
			goto out_em;
		}
		disk_io_size = em->block_len;
		count = em->block_len;
		encoded->unencoded_len = em->ram_bytes;
		encoded->unencoded_offset = iocb->ki_pos - em->orig_start;
		ret = btrfs_encoded_io_compression_from_extent(fs_info,
							       extent_map_compression(em));
		if (ret < 0)
			goto out_em;
		encoded->compression = ret;
	} else {
		disk_bytenr = em->block_start + (start - em->start);
		if (encoded->len > count)
			encoded->len = count;
		/*
		 * Don't read beyond what we locked. This also limits the page
		 * allocations that we'll do.
		 */
		disk_io_size = min(lockend + 1, iocb->ki_pos + encoded->len) - start;
		count = start + disk_io_size - iocb->ki_pos;
		encoded->len = count;
		encoded->unencoded_len = count;
		disk_io_size = ALIGN(disk_io_size, fs_info->sectorsize);
	}
	free_extent_map(em);
	em = NULL;

	if (disk_bytenr == EXTENT_MAP_HOLE) {
		unlock_extent(io_tree, start, lockend, &cached_state);
		btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
		unlocked = true;
		ret = iov_iter_zero(count, iter);
		if (ret != count)
			ret = -EFAULT;
	} else {
		ret = btrfs_encoded_read_regular(iocb, iter, start, lockend,
						 &cached_state, disk_bytenr,
						 disk_io_size, count,
						 encoded->compression,
						 &unlocked);
	}

out:
	if (ret >= 0)
		iocb->ki_pos += encoded->len;
out_em:
	free_extent_map(em);
out_unlock_extent:
	if (!unlocked)
		unlock_extent(io_tree, start, lockend, &cached_state);
out_unlock_inode:
	if (!unlocked)
		btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED);
	return ret;
}

ssize_t btrfs_do_encoded_write(struct kiocb *iocb, struct iov_iter *from,
			       const struct btrfs_ioctl_encoded_io_args *encoded)
{
	struct btrfs_inode *inode = BTRFS_I(file_inode(iocb->ki_filp));
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct extent_io_tree *io_tree = &inode->io_tree;
	struct extent_changeset *data_reserved = NULL;
	struct extent_state *cached_state = NULL;
	struct btrfs_ordered_extent *ordered;
	int compression;
	size_t orig_count;
	u64 start, end;
	u64 num_bytes, ram_bytes, disk_num_bytes;
	unsigned long nr_pages, i;
	struct page **pages;
	struct btrfs_key ins;
	bool extent_reserved = false;
	struct extent_map *em;
	ssize_t ret;

	switch (encoded->compression) {
	case BTRFS_ENCODED_IO_COMPRESSION_ZLIB:
		compression = BTRFS_COMPRESS_ZLIB;
		break;
	case BTRFS_ENCODED_IO_COMPRESSION_ZSTD:
		compression = BTRFS_COMPRESS_ZSTD;
		break;
	case BTRFS_ENCODED_IO_COMPRESSION_LZO_4K:
	case BTRFS_ENCODED_IO_COMPRESSION_LZO_8K:
	case BTRFS_ENCODED_IO_COMPRESSION_LZO_16K:
	case BTRFS_ENCODED_IO_COMPRESSION_LZO_32K:
	case BTRFS_ENCODED_IO_COMPRESSION_LZO_64K:
		/* The sector size must match for LZO. */
		if (encoded->compression -
		    BTRFS_ENCODED_IO_COMPRESSION_LZO_4K + 12 !=
		    fs_info->sectorsize_bits)
			return -EINVAL;
		compression = BTRFS_COMPRESS_LZO;
		break;
	default:
		return -EINVAL;
	}
	if (encoded->encryption != BTRFS_ENCODED_IO_ENCRYPTION_NONE)
		return -EINVAL;

	/*
	 * Compressed extents should always have checksums, so error out if we
	 * have a NOCOW file or inode was created while mounted with NODATASUM.
	 */
	if (inode->flags & BTRFS_INODE_NODATASUM)
		return -EINVAL;

	orig_count = iov_iter_count(from);

	/* The extent size must be sane. */
	if (encoded->unencoded_len > BTRFS_MAX_UNCOMPRESSED ||
	    orig_count > BTRFS_MAX_COMPRESSED || orig_count == 0)
		return -EINVAL;

	/*
	 * The compressed data must be smaller than the decompressed data.
	 *
	 * It's of course possible for data to compress to larger or the same
	 * size, but the buffered I/O path falls back to no compression for such
	 * data, and we don't want to break any assumptions by creating these
	 * extents.
	 *
	 * Note that this is less strict than the current check we have that the
	 * compressed data must be at least one sector smaller than the
	 * decompressed data. We only want to enforce the weaker requirement
	 * from old kernels that it is at least one byte smaller.
	 */
	if (orig_count >= encoded->unencoded_len)
		return -EINVAL;

	/* The extent must start on a sector boundary. */
	start = iocb->ki_pos;
	if (!IS_ALIGNED(start, fs_info->sectorsize))
		return -EINVAL;

	/*
	 * The extent must end on a sector boundary. However, we allow a write
	 * which ends at or extends i_size to have an unaligned length; we round
	 * up the extent size and set i_size to the unaligned end.
	 */
	if (start + encoded->len < inode->vfs_inode.i_size &&
	    !IS_ALIGNED(start + encoded->len, fs_info->sectorsize))
		return -EINVAL;

	/* Finally, the offset in the unencoded data must be sector-aligned. */
	if (!IS_ALIGNED(encoded->unencoded_offset, fs_info->sectorsize))
		return -EINVAL;

	num_bytes = ALIGN(encoded->len, fs_info->sectorsize);
	ram_bytes = ALIGN(encoded->unencoded_len, fs_info->sectorsize);
	end = start + num_bytes - 1;

	/*
	 * If the extent cannot be inline, the compressed data on disk must be
	 * sector-aligned. For convenience, we extend it with zeroes if it
	 * isn't.
	 */
	disk_num_bytes = ALIGN(orig_count, fs_info->sectorsize);
	nr_pages = DIV_ROUND_UP(disk_num_bytes, PAGE_SIZE);
	pages = kvcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL_ACCOUNT);
	if (!pages)
		return -ENOMEM;
	for (i = 0; i < nr_pages; i++) {
		size_t bytes = min_t(size_t, PAGE_SIZE, iov_iter_count(from));
		char *kaddr;

		pages[i] = alloc_page(GFP_KERNEL_ACCOUNT);
		if (!pages[i]) {
			ret = -ENOMEM;
			goto out_pages;
		}
		kaddr = kmap_local_page(pages[i]);
		if (copy_from_iter(kaddr, bytes, from) != bytes) {
			kunmap_local(kaddr);
			ret = -EFAULT;
			goto out_pages;
		}
		if (bytes < PAGE_SIZE)
			memset(kaddr + bytes, 0, PAGE_SIZE - bytes);
		kunmap_local(kaddr);
	}

	for (;;) {
		struct btrfs_ordered_extent *ordered;

		ret = btrfs_wait_ordered_range(&inode->vfs_inode, start, num_bytes);
		if (ret)
			goto out_pages;
		ret = invalidate_inode_pages2_range(inode->vfs_inode.i_mapping,
						    start >> PAGE_SHIFT,
						    end >> PAGE_SHIFT);
		if (ret)
			goto out_pages;
		lock_extent(io_tree, start, end, &cached_state);
		ordered = btrfs_lookup_ordered_range(inode, start, num_bytes);
		if (!ordered &&
		    !filemap_range_has_page(inode->vfs_inode.i_mapping, start, end))
			break;
		if (ordered)
			btrfs_put_ordered_extent(ordered);
		unlock_extent(io_tree, start, end, &cached_state);
		cond_resched();
	}

	/*
	 * We don't use the higher-level delalloc space functions because our
	 * num_bytes and disk_num_bytes are different.
	 */
	ret = btrfs_alloc_data_chunk_ondemand(inode, disk_num_bytes);
	if (ret)
		goto out_unlock;
	ret = btrfs_qgroup_reserve_data(inode, &data_reserved, start, num_bytes);
	if (ret)
		goto out_free_data_space;
	ret = btrfs_delalloc_reserve_metadata(inode, num_bytes, disk_num_bytes,
					      false);
	if (ret)
		goto out_qgroup_free_data;

	/* Try an inline extent first. */
	if (start == 0 && encoded->unencoded_len == encoded->len &&
	    encoded->unencoded_offset == 0) {
		ret = cow_file_range_inline(inode, encoded->len, orig_count,
					    compression, pages, true);
		if (ret <= 0) {
			if (ret == 0)
				ret = orig_count;
			goto out_delalloc_release;
		}
	}

	ret = btrfs_reserve_extent(root, disk_num_bytes, disk_num_bytes,
				   disk_num_bytes, 0, 0, &ins, 1, 1);
	if (ret)
		goto out_delalloc_release;
	extent_reserved = true;

	em = create_io_em(inode, start, num_bytes,
			  start - encoded->unencoded_offset, ins.objectid,
			  ins.offset, ins.offset, ram_bytes, compression,
			  BTRFS_ORDERED_COMPRESSED);
	if (IS_ERR(em)) {
		ret = PTR_ERR(em);
		goto out_free_reserved;
	}
	free_extent_map(em);

	ordered = btrfs_alloc_ordered_extent(inode, start, num_bytes, ram_bytes,
				       ins.objectid, ins.offset,
				       encoded->unencoded_offset,
				       (1 << BTRFS_ORDERED_ENCODED) |
				       (1 << BTRFS_ORDERED_COMPRESSED),
				       compression);
	if (IS_ERR(ordered)) {
		btrfs_drop_extent_map_range(inode, start, end, false);
		ret = PTR_ERR(ordered);
		goto out_free_reserved;
	}
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);

	if (start + encoded->len > inode->vfs_inode.i_size)
		i_size_write(&inode->vfs_inode, start + encoded->len);

	unlock_extent(io_tree, start, end, &cached_state);

	btrfs_delalloc_release_extents(inode, num_bytes);

	btrfs_submit_compressed_write(ordered, pages, nr_pages, 0, false);
	ret = orig_count;
	goto out;

out_free_reserved:
	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
out_delalloc_release:
	btrfs_delalloc_release_extents(inode, num_bytes);
	btrfs_delalloc_release_metadata(inode, disk_num_bytes, ret < 0);
out_qgroup_free_data:
	if (ret < 0)
		btrfs_qgroup_free_data(inode, data_reserved, start, num_bytes, NULL);
out_free_data_space:
	/*
	 * If btrfs_reserve_extent() succeeded, then we already decremented
	 * bytes_may_use.
	 */
	if (!extent_reserved)
		btrfs_free_reserved_data_space_noquota(fs_info, disk_num_bytes);
out_unlock:
	unlock_extent(io_tree, start, end, &cached_state);
out_pages:
	for (i = 0; i < nr_pages; i++) {
		if (pages[i])
			__free_page(pages[i]);
	}
	kvfree(pages);
out:
	if (ret >= 0)
		iocb->ki_pos += encoded->len;
	return ret;
}

#ifdef CONFIG_SWAP
/*
 * Add an entry indicating a block group or device which is pinned by a
 * swapfile. Returns 0 on success, 1 if there is already an entry for it, or a
 * negative errno on failure.
 */
static int btrfs_add_swapfile_pin(struct inode *inode, void *ptr,
				  bool is_block_group)
{
	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
	struct btrfs_swapfile_pin *sp, *entry;
	struct rb_node **p;
	struct rb_node *parent = NULL;

	sp = kmalloc(sizeof(*sp), GFP_NOFS);
	if (!sp)
		return -ENOMEM;
	sp->ptr = ptr;
	sp->inode = inode;
	sp->is_block_group = is_block_group;
	sp->bg_extent_count = 1;

	spin_lock(&fs_info->swapfile_pins_lock);
	p = &fs_info->swapfile_pins.rb_node;
	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct btrfs_swapfile_pin, node);
		if (sp->ptr < entry->ptr ||
		    (sp->ptr == entry->ptr && sp->inode < entry->inode)) {
			p = &(*p)->rb_left;
		} else if (sp->ptr > entry->ptr ||
			   (sp->ptr == entry->ptr && sp->inode > entry->inode)) {
			p = &(*p)->rb_right;
		} else {
			if (is_block_group)
				entry->bg_extent_count++;
			spin_unlock(&fs_info->swapfile_pins_lock);
			kfree(sp);
			return 1;
		}
	}
	rb_link_node(&sp->node, parent, p);
	rb_insert_color(&sp->node, &fs_info->swapfile_pins);
	spin_unlock(&fs_info->swapfile_pins_lock);
	return 0;
}

/* Free all of the entries pinned by this swapfile. */
static void btrfs_free_swapfile_pins(struct inode *inode)
{
	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
	struct btrfs_swapfile_pin *sp;
	struct rb_node *node, *next;

	spin_lock(&fs_info->swapfile_pins_lock);
	node = rb_first(&fs_info->swapfile_pins);
	while (node) {
		next = rb_next(node);
		sp = rb_entry(node, struct btrfs_swapfile_pin, node);
		if (sp->inode == inode) {
			rb_erase(&sp->node, &fs_info->swapfile_pins);
			if (sp->is_block_group) {
				btrfs_dec_block_group_swap_extents(sp->ptr,
							   sp->bg_extent_count);
				btrfs_put_block_group(sp->ptr);
			}
			kfree(sp);
		}
		node = next;
	}
	spin_unlock(&fs_info->swapfile_pins_lock);
}

struct btrfs_swap_info {
	u64 start;
	u64 block_start;
	u64 block_len;
	u64 lowest_ppage;
	u64 highest_ppage;
	unsigned long nr_pages;
	int nr_extents;
};

static int btrfs_add_swap_extent(struct swap_info_struct *sis,
				 struct btrfs_swap_info *bsi)
{
	unsigned long nr_pages;
	unsigned long max_pages;
	u64 first_ppage, first_ppage_reported, next_ppage;
	int ret;

	/*
	 * Our swapfile may have had its size extended after the swap header was
	 * written. In that case activating the swapfile should not go beyond
	 * the max size set in the swap header.
	 */
	if (bsi->nr_pages >= sis->max)
		return 0;

	max_pages = sis->max - bsi->nr_pages;
	first_ppage = PAGE_ALIGN(bsi->block_start) >> PAGE_SHIFT;
	next_ppage = PAGE_ALIGN_DOWN(bsi->block_start + bsi->block_len) >> PAGE_SHIFT;

	if (first_ppage >= next_ppage)
		return 0;
	nr_pages = next_ppage - first_ppage;
	nr_pages = min(nr_pages, max_pages);

	first_ppage_reported = first_ppage;
	if (bsi->start == 0)
		first_ppage_reported++;
	if (bsi->lowest_ppage > first_ppage_reported)
		bsi->lowest_ppage = first_ppage_reported;
	if (bsi->highest_ppage < (next_ppage - 1))
		bsi->highest_ppage = next_ppage - 1;

	ret = add_swap_extent(sis, bsi->nr_pages, nr_pages, first_ppage);
	if (ret < 0)
		return ret;
	bsi->nr_extents += ret;
	bsi->nr_pages += nr_pages;
	return 0;
}

static void btrfs_swap_deactivate(struct file *file)
{
	struct inode *inode = file_inode(file);

	btrfs_free_swapfile_pins(inode);
	atomic_dec(&BTRFS_I(inode)->root->nr_swapfiles);
}

static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
			       sector_t *span)
{
	struct inode *inode = file_inode(file);
	struct btrfs_root *root = BTRFS_I(inode)->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct extent_state *cached_state = NULL;
	struct extent_map *em = NULL;
	struct btrfs_chunk_map *map = NULL;
	struct btrfs_device *device = NULL;
	struct btrfs_swap_info bsi = {
		.lowest_ppage = (sector_t)-1ULL,
	};
	int ret = 0;
	u64 isize;
	u64 start;

	/*
	 * If the swap file was just created, make sure delalloc is done. If the
	 * file changes again after this, the user is doing something stupid and
	 * we don't really care.
	 */
	ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
	if (ret)
		return ret;

	/*
	 * The inode is locked, so these flags won't change after we check them.
	 */
	if (BTRFS_I(inode)->flags & BTRFS_INODE_COMPRESS) {
		btrfs_warn(fs_info, "swapfile must not be compressed");
		return -EINVAL;
	}
	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW)) {
		btrfs_warn(fs_info, "swapfile must not be copy-on-write");
		return -EINVAL;
	}
	if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
		btrfs_warn(fs_info, "swapfile must not be checksummed");
		return -EINVAL;
	}

	/*
	 * Balance or device remove/replace/resize can move stuff around from
	 * under us. The exclop protection makes sure they aren't running/won't
	 * run concurrently while we are mapping the swap extents, and
	 * fs_info->swapfile_pins prevents them from running while the swap
	 * file is active and moving the extents. Note that this also prevents
	 * a concurrent device add which isn't actually necessary, but it's not
	 * really worth the trouble to allow it.
	 */
	if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_SWAP_ACTIVATE)) {
		btrfs_warn(fs_info,
	   "cannot activate swapfile while exclusive operation is running");
		return -EBUSY;
	}

	/*
	 * Prevent snapshot creation while we are activating the swap file.
	 * We do not want to race with snapshot creation. If snapshot creation
	 * already started before we bumped nr_swapfiles from 0 to 1 and
	 * completes before the first write into the swap file after it is
	 * activated, than that write would fallback to COW.
	 */
	if (!btrfs_drew_try_write_lock(&root->snapshot_lock)) {
		btrfs_exclop_finish(fs_info);
		btrfs_warn(fs_info,
	   "cannot activate swapfile because snapshot creation is in progress");
		return -EINVAL;
	}
	/*
	 * Snapshots can create extents which require COW even if NODATACOW is
	 * set. We use this counter to prevent snapshots. We must increment it
	 * before walking the extents because we don't want a concurrent
	 * snapshot to run after we've already checked the extents.
	 *
	 * It is possible that subvolume is marked for deletion but still not
	 * removed yet. To prevent this race, we check the root status before
	 * activating the swapfile.
	 */
	spin_lock(&root->root_item_lock);
	if (btrfs_root_dead(root)) {
		spin_unlock(&root->root_item_lock);

		btrfs_exclop_finish(fs_info);
		btrfs_warn(fs_info,
		"cannot activate swapfile because subvolume %llu is being deleted",
			root->root_key.objectid);
		return -EPERM;
	}
	atomic_inc(&root->nr_swapfiles);
	spin_unlock(&root->root_item_lock);

	isize = ALIGN_DOWN(inode->i_size, fs_info->sectorsize);

	lock_extent(io_tree, 0, isize - 1, &cached_state);
	start = 0;
	while (start < isize) {
		u64 logical_block_start, physical_block_start;
		struct btrfs_block_group *bg;
		u64 len = isize - start;

		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len);
		if (IS_ERR(em)) {
			ret = PTR_ERR(em);
			goto out;
		}

		if (em->block_start == EXTENT_MAP_HOLE) {
			btrfs_warn(fs_info, "swapfile must not have holes");
			ret = -EINVAL;
			goto out;
		}
		if (em->block_start == EXTENT_MAP_INLINE) {
			/*
			 * It's unlikely we'll ever actually find ourselves
			 * here, as a file small enough to fit inline won't be
			 * big enough to store more than the swap header, but in
			 * case something changes in the future, let's catch it
			 * here rather than later.
			 */
			btrfs_warn(fs_info, "swapfile must not be inline");
			ret = -EINVAL;
			goto out;
		}
		if (extent_map_is_compressed(em)) {
			btrfs_warn(fs_info, "swapfile must not be compressed");
			ret = -EINVAL;
			goto out;
		}

		logical_block_start = em->block_start + (start - em->start);
		len = min(len, em->len - (start - em->start));
		free_extent_map(em);
		em = NULL;

		ret = can_nocow_extent(inode, start, &len, NULL, NULL, NULL, false, true);
		if (ret < 0) {
			goto out;
		} else if (ret) {
			ret = 0;
		} else {
			btrfs_warn(fs_info,
				   "swapfile must not be copy-on-write");
			ret = -EINVAL;
			goto out;
		}

		map = btrfs_get_chunk_map(fs_info, logical_block_start, len);
		if (IS_ERR(map)) {
			ret = PTR_ERR(map);
			goto out;
		}

		if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
			btrfs_warn(fs_info,
				   "swapfile must have single data profile");
			ret = -EINVAL;
			goto out;
		}

		if (device == NULL) {
			device = map->stripes[0].dev;
			ret = btrfs_add_swapfile_pin(inode, device, false);
			if (ret == 1)
				ret = 0;
			else if (ret)
				goto out;
		} else if (device != map->stripes[0].dev) {
			btrfs_warn(fs_info, "swapfile must be on one device");
			ret = -EINVAL;
			goto out;
		}

		physical_block_start = (map->stripes[0].physical +
					(logical_block_start - map->start));
		len = min(len, map->chunk_len - (logical_block_start - map->start));
		btrfs_free_chunk_map(map);
		map = NULL;

		bg = btrfs_lookup_block_group(fs_info, logical_block_start);
		if (!bg) {
			btrfs_warn(fs_info,
			   "could not find block group containing swapfile");
			ret = -EINVAL;
			goto out;
		}

		if (!btrfs_inc_block_group_swap_extents(bg)) {
			btrfs_warn(fs_info,
			   "block group for swapfile at %llu is read-only%s",
			   bg->start,
			   atomic_read(&fs_info->scrubs_running) ?
				       " (scrub running)" : "");
			btrfs_put_block_group(bg);
			ret = -EINVAL;
			goto out;
		}

		ret = btrfs_add_swapfile_pin(inode, bg, true);
		if (ret) {
			btrfs_put_block_group(bg);
			if (ret == 1)
				ret = 0;
			else
				goto out;
		}

		if (bsi.block_len &&
		    bsi.block_start + bsi.block_len == physical_block_start) {
			bsi.block_len += len;
		} else {
			if (bsi.block_len) {
				ret = btrfs_add_swap_extent(sis, &bsi);
				if (ret)
					goto out;
			}
			bsi.start = start;
			bsi.block_start = physical_block_start;
			bsi.block_len = len;
		}

		start += len;
	}

	if (bsi.block_len)
		ret = btrfs_add_swap_extent(sis, &bsi);

out:
	if (!IS_ERR_OR_NULL(em))
		free_extent_map(em);
	if (!IS_ERR_OR_NULL(map))
		btrfs_free_chunk_map(map);

	unlock_extent(io_tree, 0, isize - 1, &cached_state);

	if (ret)
		btrfs_swap_deactivate(file);

	btrfs_drew_write_unlock(&root->snapshot_lock);

	btrfs_exclop_finish(fs_info);

	if (ret)
		return ret;

	if (device)
		sis->bdev = device->bdev;
	*span = bsi.highest_ppage - bsi.lowest_ppage + 1;
	sis->max = bsi.nr_pages;
	sis->pages = bsi.nr_pages - 1;
	sis->highest_bit = bsi.nr_pages - 1;
	return bsi.nr_extents;
}
#else
static void btrfs_swap_deactivate(struct file *file)
{
}

static int btrfs_swap_activate(struct swap_info_struct *sis, struct file *file,
			       sector_t *span)
{
	return -EOPNOTSUPP;
}
#endif

/*
 * Update the number of bytes used in the VFS' inode. When we replace extents in
 * a range (clone, dedupe, fallocate's zero range), we must update the number of
 * bytes used by the inode in an atomic manner, so that concurrent stat(2) calls
 * always get a correct value.
 */
void btrfs_update_inode_bytes(struct btrfs_inode *inode,
			      const u64 add_bytes,
			      const u64 del_bytes)
{
	if (add_bytes == del_bytes)
		return;

	spin_lock(&inode->lock);
	if (del_bytes > 0)
		inode_sub_bytes(&inode->vfs_inode, del_bytes);
	if (add_bytes > 0)
		inode_add_bytes(&inode->vfs_inode, add_bytes);
	spin_unlock(&inode->lock);
}

/*
 * Verify that there are no ordered extents for a given file range.
 *
 * @inode:   The target inode.
 * @start:   Start offset of the file range, should be sector size aligned.
 * @end:     End offset (inclusive) of the file range, its value +1 should be
 *           sector size aligned.
 *
 * This should typically be used for cases where we locked an inode's VFS lock in
 * exclusive mode, we have also locked the inode's i_mmap_lock in exclusive mode,
 * we have flushed all delalloc in the range, we have waited for all ordered
 * extents in the range to complete and finally we have locked the file range in
 * the inode's io_tree.
 */
void btrfs_assert_inode_range_clean(struct btrfs_inode *inode, u64 start, u64 end)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_ordered_extent *ordered;

	if (!IS_ENABLED(CONFIG_BTRFS_ASSERT))
		return;

	ordered = btrfs_lookup_first_ordered_range(inode, start, end + 1 - start);
	if (ordered) {
		btrfs_err(root->fs_info,
"found unexpected ordered extent in file range [%llu, %llu] for inode %llu root %llu (ordered range [%llu, %llu])",
			  start, end, btrfs_ino(inode), root->root_key.objectid,
			  ordered->file_offset,
			  ordered->file_offset + ordered->num_bytes - 1);
		btrfs_put_ordered_extent(ordered);
	}

	ASSERT(ordered == NULL);
}

static const struct inode_operations btrfs_dir_inode_operations = {
	.getattr	= btrfs_getattr,
	.lookup		= btrfs_lookup,
	.create		= btrfs_create,
	.unlink		= btrfs_unlink,
	.link		= btrfs_link,
	.mkdir		= btrfs_mkdir,
	.rmdir		= btrfs_rmdir,
	.rename		= btrfs_rename2,
	.symlink	= btrfs_symlink,
	.setattr	= btrfs_setattr,
	.mknod		= btrfs_mknod,
	.listxattr	= btrfs_listxattr,
	.permission	= btrfs_permission,
	.get_inode_acl	= btrfs_get_acl,
	.set_acl	= btrfs_set_acl,
	.update_time	= btrfs_update_time,
	.tmpfile        = btrfs_tmpfile,
	.fileattr_get	= btrfs_fileattr_get,
	.fileattr_set	= btrfs_fileattr_set,
};

static const struct file_operations btrfs_dir_file_operations = {
	.llseek		= btrfs_dir_llseek,
	.read		= generic_read_dir,
	.iterate_shared	= btrfs_real_readdir,
	.open		= btrfs_opendir,
	.unlocked_ioctl	= btrfs_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= btrfs_compat_ioctl,
#endif
	.release        = btrfs_release_file,
	.fsync		= btrfs_sync_file,
};

/*
 * btrfs doesn't support the bmap operation because swapfiles
 * use bmap to make a mapping of extents in the file.  They assume
 * these extents won't change over the life of the file and they
 * use the bmap result to do IO directly to the drive.
 *
 * the btrfs bmap call would return logical addresses that aren't
 * suitable for IO and they also will change frequently as COW
 * operations happen.  So, swapfile + btrfs == corruption.
 *
 * For now we're avoiding this by dropping bmap.
 */
static const struct address_space_operations btrfs_aops = {
	.read_folio	= btrfs_read_folio,
	.writepages	= btrfs_writepages,
	.readahead	= btrfs_readahead,
	.invalidate_folio = btrfs_invalidate_folio,
	.release_folio	= btrfs_release_folio,
	.migrate_folio	= btrfs_migrate_folio,
	.dirty_folio	= filemap_dirty_folio,
	.error_remove_folio = generic_error_remove_folio,
	.swap_activate	= btrfs_swap_activate,
	.swap_deactivate = btrfs_swap_deactivate,
};

static const struct inode_operations btrfs_file_inode_operations = {
	.getattr	= btrfs_getattr,
	.setattr	= btrfs_setattr,
	.listxattr      = btrfs_listxattr,
	.permission	= btrfs_permission,
	.fiemap		= btrfs_fiemap,
	.get_inode_acl	= btrfs_get_acl,
	.set_acl	= btrfs_set_acl,
	.update_time	= btrfs_update_time,
	.fileattr_get	= btrfs_fileattr_get,
	.fileattr_set	= btrfs_fileattr_set,
};
static const struct inode_operations btrfs_special_inode_operations = {
	.getattr	= btrfs_getattr,
	.setattr	= btrfs_setattr,
	.permission	= btrfs_permission,
	.listxattr	= btrfs_listxattr,
	.get_inode_acl	= btrfs_get_acl,
	.set_acl	= btrfs_set_acl,
	.update_time	= btrfs_update_time,
};
static const struct inode_operations btrfs_symlink_inode_operations = {
	.get_link	= page_get_link,
	.getattr	= btrfs_getattr,
	.setattr	= btrfs_setattr,
	.permission	= btrfs_permission,
	.listxattr	= btrfs_listxattr,
	.update_time	= btrfs_update_time,
};

const struct dentry_operations btrfs_dentry_operations = {
	.d_delete	= btrfs_dentry_delete,
};