summaryrefslogtreecommitdiff
path: root/fs/btrfs/disk-io.c
blob: 89e94ea2fef5b41d0c1cb8b17e1f531d1d5dbcc4 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/writeback.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <linux/uuid.h>
#include <linux/semaphore.h>
#include <linux/error-injection.h>
#include <linux/crc32c.h>
#include <linux/sched/mm.h>
#include <asm/unaligned.h>
#include <crypto/hash.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
#include "free-space-tree.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
#include "sysfs.h"
#include "qgroup.h"
#include "compression.h"
#include "tree-checker.h"
#include "ref-verify.h"
#include "block-group.h"
#include "discard.h"
#include "space-info.h"
#include "zoned.h"
#include "subpage.h"

#define BTRFS_SUPER_FLAG_SUPP	(BTRFS_HEADER_FLAG_WRITTEN |\
				 BTRFS_HEADER_FLAG_RELOC |\
				 BTRFS_SUPER_FLAG_ERROR |\
				 BTRFS_SUPER_FLAG_SEEDING |\
				 BTRFS_SUPER_FLAG_METADUMP |\
				 BTRFS_SUPER_FLAG_METADUMP_V2)

static void end_workqueue_fn(struct btrfs_work *work);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
				      struct btrfs_fs_info *fs_info);
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info,
					struct extent_io_tree *dirty_pages,
					int mark);
static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,
				       struct extent_io_tree *pinned_extents);
static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info);
static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info);

/*
 * btrfs_end_io_wq structs are used to do processing in task context when an IO
 * is complete.  This is used during reads to verify checksums, and it is used
 * by writes to insert metadata for new file extents after IO is complete.
 */
struct btrfs_end_io_wq {
	struct bio *bio;
	bio_end_io_t *end_io;
	void *private;
	struct btrfs_fs_info *info;
	blk_status_t status;
	enum btrfs_wq_endio_type metadata;
	struct btrfs_work work;
};

static struct kmem_cache *btrfs_end_io_wq_cache;

int __init btrfs_end_io_wq_init(void)
{
	btrfs_end_io_wq_cache = kmem_cache_create("btrfs_end_io_wq",
					sizeof(struct btrfs_end_io_wq),
					0,
					SLAB_MEM_SPREAD,
					NULL);
	if (!btrfs_end_io_wq_cache)
		return -ENOMEM;
	return 0;
}

void __cold btrfs_end_io_wq_exit(void)
{
	kmem_cache_destroy(btrfs_end_io_wq_cache);
}

static void btrfs_free_csum_hash(struct btrfs_fs_info *fs_info)
{
	if (fs_info->csum_shash)
		crypto_free_shash(fs_info->csum_shash);
}

/*
 * async submit bios are used to offload expensive checksumming
 * onto the worker threads.  They checksum file and metadata bios
 * just before they are sent down the IO stack.
 */
struct async_submit_bio {
	struct inode *inode;
	struct bio *bio;
	extent_submit_bio_start_t *submit_bio_start;
	int mirror_num;

	/* Optional parameter for submit_bio_start used by direct io */
	u64 dio_file_offset;
	struct btrfs_work work;
	blk_status_t status;
};

/*
 * Lockdep class keys for extent_buffer->lock's in this root.  For a given
 * eb, the lockdep key is determined by the btrfs_root it belongs to and
 * the level the eb occupies in the tree.
 *
 * Different roots are used for different purposes and may nest inside each
 * other and they require separate keysets.  As lockdep keys should be
 * static, assign keysets according to the purpose of the root as indicated
 * by btrfs_root->root_key.objectid.  This ensures that all special purpose
 * roots have separate keysets.
 *
 * Lock-nesting across peer nodes is always done with the immediate parent
 * node locked thus preventing deadlock.  As lockdep doesn't know this, use
 * subclass to avoid triggering lockdep warning in such cases.
 *
 * The key is set by the readpage_end_io_hook after the buffer has passed
 * csum validation but before the pages are unlocked.  It is also set by
 * btrfs_init_new_buffer on freshly allocated blocks.
 *
 * We also add a check to make sure the highest level of the tree is the
 * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
 * needs update as well.
 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# if BTRFS_MAX_LEVEL != 8
#  error
# endif

#define DEFINE_LEVEL(stem, level)					\
	.names[level] = "btrfs-" stem "-0" #level,

#define DEFINE_NAME(stem)						\
	DEFINE_LEVEL(stem, 0)						\
	DEFINE_LEVEL(stem, 1)						\
	DEFINE_LEVEL(stem, 2)						\
	DEFINE_LEVEL(stem, 3)						\
	DEFINE_LEVEL(stem, 4)						\
	DEFINE_LEVEL(stem, 5)						\
	DEFINE_LEVEL(stem, 6)						\
	DEFINE_LEVEL(stem, 7)

static struct btrfs_lockdep_keyset {
	u64			id;		/* root objectid */
	/* Longest entry: btrfs-free-space-00 */
	char			names[BTRFS_MAX_LEVEL][20];
	struct lock_class_key	keys[BTRFS_MAX_LEVEL];
} btrfs_lockdep_keysets[] = {
	{ .id = BTRFS_ROOT_TREE_OBJECTID,	DEFINE_NAME("root")	},
	{ .id = BTRFS_EXTENT_TREE_OBJECTID,	DEFINE_NAME("extent")	},
	{ .id = BTRFS_CHUNK_TREE_OBJECTID,	DEFINE_NAME("chunk")	},
	{ .id = BTRFS_DEV_TREE_OBJECTID,	DEFINE_NAME("dev")	},
	{ .id = BTRFS_CSUM_TREE_OBJECTID,	DEFINE_NAME("csum")	},
	{ .id = BTRFS_QUOTA_TREE_OBJECTID,	DEFINE_NAME("quota")	},
	{ .id = BTRFS_TREE_LOG_OBJECTID,	DEFINE_NAME("log")	},
	{ .id = BTRFS_TREE_RELOC_OBJECTID,	DEFINE_NAME("treloc")	},
	{ .id = BTRFS_DATA_RELOC_TREE_OBJECTID,	DEFINE_NAME("dreloc")	},
	{ .id = BTRFS_UUID_TREE_OBJECTID,	DEFINE_NAME("uuid")	},
	{ .id = BTRFS_FREE_SPACE_TREE_OBJECTID,	DEFINE_NAME("free-space") },
	{ .id = 0,				DEFINE_NAME("tree")	},
};

#undef DEFINE_LEVEL
#undef DEFINE_NAME

void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
				    int level)
{
	struct btrfs_lockdep_keyset *ks;

	BUG_ON(level >= ARRAY_SIZE(ks->keys));

	/* find the matching keyset, id 0 is the default entry */
	for (ks = btrfs_lockdep_keysets; ks->id; ks++)
		if (ks->id == objectid)
			break;

	lockdep_set_class_and_name(&eb->lock,
				   &ks->keys[level], ks->names[level]);
}

#endif

/*
 * Compute the csum of a btree block and store the result to provided buffer.
 */
static void csum_tree_block(struct extent_buffer *buf, u8 *result)
{
	struct btrfs_fs_info *fs_info = buf->fs_info;
	const int num_pages = num_extent_pages(buf);
	const int first_page_part = min_t(u32, PAGE_SIZE, fs_info->nodesize);
	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
	char *kaddr;
	int i;

	shash->tfm = fs_info->csum_shash;
	crypto_shash_init(shash);
	kaddr = page_address(buf->pages[0]) + offset_in_page(buf->start);
	crypto_shash_update(shash, kaddr + BTRFS_CSUM_SIZE,
			    first_page_part - BTRFS_CSUM_SIZE);

	for (i = 1; i < num_pages; i++) {
		kaddr = page_address(buf->pages[i]);
		crypto_shash_update(shash, kaddr, PAGE_SIZE);
	}
	memset(result, 0, BTRFS_CSUM_SIZE);
	crypto_shash_final(shash, result);
}

/*
 * we can't consider a given block up to date unless the transid of the
 * block matches the transid in the parent node's pointer.  This is how we
 * detect blocks that either didn't get written at all or got written
 * in the wrong place.
 */
static int verify_parent_transid(struct extent_io_tree *io_tree,
				 struct extent_buffer *eb, u64 parent_transid,
				 int atomic)
{
	struct extent_state *cached_state = NULL;
	int ret;

	if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
		return 0;

	if (atomic)
		return -EAGAIN;

	lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
			 &cached_state);
	if (extent_buffer_uptodate(eb) &&
	    btrfs_header_generation(eb) == parent_transid) {
		ret = 0;
		goto out;
	}
	btrfs_err_rl(eb->fs_info,
		"parent transid verify failed on %llu wanted %llu found %llu",
			eb->start,
			parent_transid, btrfs_header_generation(eb));
	ret = 1;
	clear_extent_buffer_uptodate(eb);
out:
	unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
			     &cached_state);
	return ret;
}

static bool btrfs_supported_super_csum(u16 csum_type)
{
	switch (csum_type) {
	case BTRFS_CSUM_TYPE_CRC32:
	case BTRFS_CSUM_TYPE_XXHASH:
	case BTRFS_CSUM_TYPE_SHA256:
	case BTRFS_CSUM_TYPE_BLAKE2:
		return true;
	default:
		return false;
	}
}

/*
 * Return 0 if the superblock checksum type matches the checksum value of that
 * algorithm. Pass the raw disk superblock data.
 */
static int btrfs_check_super_csum(struct btrfs_fs_info *fs_info,
				  char *raw_disk_sb)
{
	struct btrfs_super_block *disk_sb =
		(struct btrfs_super_block *)raw_disk_sb;
	char result[BTRFS_CSUM_SIZE];
	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);

	shash->tfm = fs_info->csum_shash;

	/*
	 * The super_block structure does not span the whole
	 * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space is
	 * filled with zeros and is included in the checksum.
	 */
	crypto_shash_digest(shash, raw_disk_sb + BTRFS_CSUM_SIZE,
			    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE, result);

	if (memcmp(disk_sb->csum, result, fs_info->csum_size))
		return 1;

	return 0;
}

int btrfs_verify_level_key(struct extent_buffer *eb, int level,
			   struct btrfs_key *first_key, u64 parent_transid)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	int found_level;
	struct btrfs_key found_key;
	int ret;

	found_level = btrfs_header_level(eb);
	if (found_level != level) {
		WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
		     KERN_ERR "BTRFS: tree level check failed\n");
		btrfs_err(fs_info,
"tree level mismatch detected, bytenr=%llu level expected=%u has=%u",
			  eb->start, level, found_level);
		return -EIO;
	}

	if (!first_key)
		return 0;

	/*
	 * For live tree block (new tree blocks in current transaction),
	 * we need proper lock context to avoid race, which is impossible here.
	 * So we only checks tree blocks which is read from disk, whose
	 * generation <= fs_info->last_trans_committed.
	 */
	if (btrfs_header_generation(eb) > fs_info->last_trans_committed)
		return 0;

	/* We have @first_key, so this @eb must have at least one item */
	if (btrfs_header_nritems(eb) == 0) {
		btrfs_err(fs_info,
		"invalid tree nritems, bytenr=%llu nritems=0 expect >0",
			  eb->start);
		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
		return -EUCLEAN;
	}

	if (found_level)
		btrfs_node_key_to_cpu(eb, &found_key, 0);
	else
		btrfs_item_key_to_cpu(eb, &found_key, 0);
	ret = btrfs_comp_cpu_keys(first_key, &found_key);

	if (ret) {
		WARN(IS_ENABLED(CONFIG_BTRFS_DEBUG),
		     KERN_ERR "BTRFS: tree first key check failed\n");
		btrfs_err(fs_info,
"tree first key mismatch detected, bytenr=%llu parent_transid=%llu key expected=(%llu,%u,%llu) has=(%llu,%u,%llu)",
			  eb->start, parent_transid, first_key->objectid,
			  first_key->type, first_key->offset,
			  found_key.objectid, found_key.type,
			  found_key.offset);
	}
	return ret;
}

/*
 * helper to read a given tree block, doing retries as required when
 * the checksums don't match and we have alternate mirrors to try.
 *
 * @parent_transid:	expected transid, skip check if 0
 * @level:		expected level, mandatory check
 * @first_key:		expected key of first slot, skip check if NULL
 */
int btrfs_read_extent_buffer(struct extent_buffer *eb,
			     u64 parent_transid, int level,
			     struct btrfs_key *first_key)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	struct extent_io_tree *io_tree;
	int failed = 0;
	int ret;
	int num_copies = 0;
	int mirror_num = 0;
	int failed_mirror = 0;

	io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
	while (1) {
		clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
		ret = read_extent_buffer_pages(eb, WAIT_COMPLETE, mirror_num);
		if (!ret) {
			if (verify_parent_transid(io_tree, eb,
						   parent_transid, 0))
				ret = -EIO;
			else if (btrfs_verify_level_key(eb, level,
						first_key, parent_transid))
				ret = -EUCLEAN;
			else
				break;
		}

		num_copies = btrfs_num_copies(fs_info,
					      eb->start, eb->len);
		if (num_copies == 1)
			break;

		if (!failed_mirror) {
			failed = 1;
			failed_mirror = eb->read_mirror;
		}

		mirror_num++;
		if (mirror_num == failed_mirror)
			mirror_num++;

		if (mirror_num > num_copies)
			break;
	}

	if (failed && !ret && failed_mirror)
		btrfs_repair_eb_io_failure(eb, failed_mirror);

	return ret;
}

static int csum_one_extent_buffer(struct extent_buffer *eb)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	u8 result[BTRFS_CSUM_SIZE];
	int ret;

	ASSERT(memcmp_extent_buffer(eb, fs_info->fs_devices->metadata_uuid,
				    offsetof(struct btrfs_header, fsid),
				    BTRFS_FSID_SIZE) == 0);
	csum_tree_block(eb, result);

	if (btrfs_header_level(eb))
		ret = btrfs_check_node(eb);
	else
		ret = btrfs_check_leaf_full(eb);

	if (ret < 0)
		goto error;

	/*
	 * Also check the generation, the eb reached here must be newer than
	 * last committed. Or something seriously wrong happened.
	 */
	if (unlikely(btrfs_header_generation(eb) <= fs_info->last_trans_committed)) {
		ret = -EUCLEAN;
		btrfs_err(fs_info,
			"block=%llu bad generation, have %llu expect > %llu",
			  eb->start, btrfs_header_generation(eb),
			  fs_info->last_trans_committed);
		goto error;
	}
	write_extent_buffer(eb, result, 0, fs_info->csum_size);

	return 0;

error:
	btrfs_print_tree(eb, 0);
	btrfs_err(fs_info, "block=%llu write time tree block corruption detected",
		  eb->start);
	WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
	return ret;
}

/* Checksum all dirty extent buffers in one bio_vec */
static int csum_dirty_subpage_buffers(struct btrfs_fs_info *fs_info,
				      struct bio_vec *bvec)
{
	struct page *page = bvec->bv_page;
	u64 bvec_start = page_offset(page) + bvec->bv_offset;
	u64 cur;
	int ret = 0;

	for (cur = bvec_start; cur < bvec_start + bvec->bv_len;
	     cur += fs_info->nodesize) {
		struct extent_buffer *eb;
		bool uptodate;

		eb = find_extent_buffer(fs_info, cur);
		uptodate = btrfs_subpage_test_uptodate(fs_info, page, cur,
						       fs_info->nodesize);

		/* A dirty eb shouldn't disappear from extent_buffers */
		if (WARN_ON(!eb))
			return -EUCLEAN;

		if (WARN_ON(cur != btrfs_header_bytenr(eb))) {
			free_extent_buffer(eb);
			return -EUCLEAN;
		}
		if (WARN_ON(!uptodate)) {
			free_extent_buffer(eb);
			return -EUCLEAN;
		}

		ret = csum_one_extent_buffer(eb);
		free_extent_buffer(eb);
		if (ret < 0)
			return ret;
	}
	return ret;
}

/*
 * Checksum a dirty tree block before IO.  This has extra checks to make sure
 * we only fill in the checksum field in the first page of a multi-page block.
 * For subpage extent buffers we need bvec to also read the offset in the page.
 */
static int csum_dirty_buffer(struct btrfs_fs_info *fs_info, struct bio_vec *bvec)
{
	struct page *page = bvec->bv_page;
	u64 start = page_offset(page);
	u64 found_start;
	struct extent_buffer *eb;

	if (fs_info->nodesize < PAGE_SIZE)
		return csum_dirty_subpage_buffers(fs_info, bvec);

	eb = (struct extent_buffer *)page->private;
	if (page != eb->pages[0])
		return 0;

	found_start = btrfs_header_bytenr(eb);

	if (test_bit(EXTENT_BUFFER_NO_CHECK, &eb->bflags)) {
		WARN_ON(found_start != 0);
		return 0;
	}

	/*
	 * Please do not consolidate these warnings into a single if.
	 * It is useful to know what went wrong.
	 */
	if (WARN_ON(found_start != start))
		return -EUCLEAN;
	if (WARN_ON(!PageUptodate(page)))
		return -EUCLEAN;

	return csum_one_extent_buffer(eb);
}

static int check_tree_block_fsid(struct extent_buffer *eb)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices, *seed_devs;
	u8 fsid[BTRFS_FSID_SIZE];
	u8 *metadata_uuid;

	read_extent_buffer(eb, fsid, offsetof(struct btrfs_header, fsid),
			   BTRFS_FSID_SIZE);
	/*
	 * Checking the incompat flag is only valid for the current fs. For
	 * seed devices it's forbidden to have their uuid changed so reading
	 * ->fsid in this case is fine
	 */
	if (btrfs_fs_incompat(fs_info, METADATA_UUID))
		metadata_uuid = fs_devices->metadata_uuid;
	else
		metadata_uuid = fs_devices->fsid;

	if (!memcmp(fsid, metadata_uuid, BTRFS_FSID_SIZE))
		return 0;

	list_for_each_entry(seed_devs, &fs_devices->seed_list, seed_list)
		if (!memcmp(fsid, seed_devs->fsid, BTRFS_FSID_SIZE))
			return 0;

	return 1;
}

/* Do basic extent buffer checks at read time */
static int validate_extent_buffer(struct extent_buffer *eb)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	u64 found_start;
	const u32 csum_size = fs_info->csum_size;
	u8 found_level;
	u8 result[BTRFS_CSUM_SIZE];
	const u8 *header_csum;
	int ret = 0;

	found_start = btrfs_header_bytenr(eb);
	if (found_start != eb->start) {
		btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu",
			     eb->start, found_start);
		ret = -EIO;
		goto out;
	}
	if (check_tree_block_fsid(eb)) {
		btrfs_err_rl(fs_info, "bad fsid on block %llu",
			     eb->start);
		ret = -EIO;
		goto out;
	}
	found_level = btrfs_header_level(eb);
	if (found_level >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "bad tree block level %d on %llu",
			  (int)btrfs_header_level(eb), eb->start);
		ret = -EIO;
		goto out;
	}

	csum_tree_block(eb, result);
	header_csum = page_address(eb->pages[0]) +
		get_eb_offset_in_page(eb, offsetof(struct btrfs_header, csum));

	if (memcmp(result, header_csum, csum_size) != 0) {
		btrfs_warn_rl(fs_info,
	"checksum verify failed on %llu wanted " CSUM_FMT " found " CSUM_FMT " level %d",
			      eb->start,
			      CSUM_FMT_VALUE(csum_size, header_csum),
			      CSUM_FMT_VALUE(csum_size, result),
			      btrfs_header_level(eb));
		ret = -EUCLEAN;
		goto out;
	}

	/*
	 * If this is a leaf block and it is corrupt, set the corrupt bit so
	 * that we don't try and read the other copies of this block, just
	 * return -EIO.
	 */
	if (found_level == 0 && btrfs_check_leaf_full(eb)) {
		set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
		ret = -EIO;
	}

	if (found_level > 0 && btrfs_check_node(eb))
		ret = -EIO;

	if (!ret)
		set_extent_buffer_uptodate(eb);
	else
		btrfs_err(fs_info,
			  "block=%llu read time tree block corruption detected",
			  eb->start);
out:
	return ret;
}

static int validate_subpage_buffer(struct page *page, u64 start, u64 end,
				   int mirror)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(page->mapping->host->i_sb);
	struct extent_buffer *eb;
	bool reads_done;
	int ret = 0;

	/*
	 * We don't allow bio merge for subpage metadata read, so we should
	 * only get one eb for each endio hook.
	 */
	ASSERT(end == start + fs_info->nodesize - 1);
	ASSERT(PagePrivate(page));

	eb = find_extent_buffer(fs_info, start);
	/*
	 * When we are reading one tree block, eb must have been inserted into
	 * the radix tree. If not, something is wrong.
	 */
	ASSERT(eb);

	reads_done = atomic_dec_and_test(&eb->io_pages);
	/* Subpage read must finish in page read */
	ASSERT(reads_done);

	eb->read_mirror = mirror;
	if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
		ret = -EIO;
		goto err;
	}
	ret = validate_extent_buffer(eb);
	if (ret < 0)
		goto err;

	set_extent_buffer_uptodate(eb);

	free_extent_buffer(eb);
	return ret;
err:
	/*
	 * end_bio_extent_readpage decrements io_pages in case of error,
	 * make sure it has something to decrement.
	 */
	atomic_inc(&eb->io_pages);
	clear_extent_buffer_uptodate(eb);
	free_extent_buffer(eb);
	return ret;
}

int btrfs_validate_metadata_buffer(struct btrfs_bio *bbio,
				   struct page *page, u64 start, u64 end,
				   int mirror)
{
	struct extent_buffer *eb;
	int ret = 0;
	int reads_done;

	ASSERT(page->private);

	if (btrfs_sb(page->mapping->host->i_sb)->nodesize < PAGE_SIZE)
		return validate_subpage_buffer(page, start, end, mirror);

	eb = (struct extent_buffer *)page->private;

	/*
	 * The pending IO might have been the only thing that kept this buffer
	 * in memory.  Make sure we have a ref for all this other checks
	 */
	atomic_inc(&eb->refs);

	reads_done = atomic_dec_and_test(&eb->io_pages);
	if (!reads_done)
		goto err;

	eb->read_mirror = mirror;
	if (test_bit(EXTENT_BUFFER_READ_ERR, &eb->bflags)) {
		ret = -EIO;
		goto err;
	}
	ret = validate_extent_buffer(eb);
err:
	if (ret) {
		/*
		 * our io error hook is going to dec the io pages
		 * again, we have to make sure it has something
		 * to decrement
		 */
		atomic_inc(&eb->io_pages);
		clear_extent_buffer_uptodate(eb);
	}
	free_extent_buffer(eb);

	return ret;
}

static void end_workqueue_bio(struct bio *bio)
{
	struct btrfs_end_io_wq *end_io_wq = bio->bi_private;
	struct btrfs_fs_info *fs_info;
	struct btrfs_workqueue *wq;

	fs_info = end_io_wq->info;
	end_io_wq->status = bio->bi_status;

	if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
			wq = fs_info->endio_meta_write_workers;
		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
			wq = fs_info->endio_freespace_worker;
		else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
			wq = fs_info->endio_raid56_workers;
		else
			wq = fs_info->endio_write_workers;
	} else {
		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
			wq = fs_info->endio_raid56_workers;
		else if (end_io_wq->metadata)
			wq = fs_info->endio_meta_workers;
		else
			wq = fs_info->endio_workers;
	}

	btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);
	btrfs_queue_work(wq, &end_io_wq->work);
}

blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
			enum btrfs_wq_endio_type metadata)
{
	struct btrfs_end_io_wq *end_io_wq;

	end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
	if (!end_io_wq)
		return BLK_STS_RESOURCE;

	end_io_wq->private = bio->bi_private;
	end_io_wq->end_io = bio->bi_end_io;
	end_io_wq->info = info;
	end_io_wq->status = 0;
	end_io_wq->bio = bio;
	end_io_wq->metadata = metadata;

	bio->bi_private = end_io_wq;
	bio->bi_end_io = end_workqueue_bio;
	return 0;
}

static void run_one_async_start(struct btrfs_work *work)
{
	struct async_submit_bio *async;
	blk_status_t ret;

	async = container_of(work, struct  async_submit_bio, work);
	ret = async->submit_bio_start(async->inode, async->bio,
				      async->dio_file_offset);
	if (ret)
		async->status = ret;
}

/*
 * In order to insert checksums into the metadata in large chunks, we wait
 * until bio submission time.   All the pages in the bio are checksummed and
 * sums are attached onto the ordered extent record.
 *
 * At IO completion time the csums attached on the ordered extent record are
 * inserted into the tree.
 */
static void run_one_async_done(struct btrfs_work *work)
{
	struct async_submit_bio *async;
	struct inode *inode;
	blk_status_t ret;

	async = container_of(work, struct  async_submit_bio, work);
	inode = async->inode;

	/* If an error occurred we just want to clean up the bio and move on */
	if (async->status) {
		async->bio->bi_status = async->status;
		bio_endio(async->bio);
		return;
	}

	/*
	 * All of the bios that pass through here are from async helpers.
	 * Use REQ_CGROUP_PUNT to issue them from the owning cgroup's context.
	 * This changes nothing when cgroups aren't in use.
	 */
	async->bio->bi_opf |= REQ_CGROUP_PUNT;
	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), async->bio, async->mirror_num);
	if (ret) {
		async->bio->bi_status = ret;
		bio_endio(async->bio);
	}
}

static void run_one_async_free(struct btrfs_work *work)
{
	struct async_submit_bio *async;

	async = container_of(work, struct  async_submit_bio, work);
	kfree(async);
}

blk_status_t btrfs_wq_submit_bio(struct inode *inode, struct bio *bio,
				 int mirror_num, u64 dio_file_offset,
				 extent_submit_bio_start_t *submit_bio_start)
{
	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
	struct async_submit_bio *async;

	async = kmalloc(sizeof(*async), GFP_NOFS);
	if (!async)
		return BLK_STS_RESOURCE;

	async->inode = inode;
	async->bio = bio;
	async->mirror_num = mirror_num;
	async->submit_bio_start = submit_bio_start;

	btrfs_init_work(&async->work, run_one_async_start, run_one_async_done,
			run_one_async_free);

	async->dio_file_offset = dio_file_offset;

	async->status = 0;

	if (op_is_sync(bio->bi_opf))
		btrfs_queue_work(fs_info->hipri_workers, &async->work);
	else
		btrfs_queue_work(fs_info->workers, &async->work);
	return 0;
}

static blk_status_t btree_csum_one_bio(struct bio *bio)
{
	struct bio_vec *bvec;
	struct btrfs_root *root;
	int ret = 0;
	struct bvec_iter_all iter_all;

	ASSERT(!bio_flagged(bio, BIO_CLONED));
	bio_for_each_segment_all(bvec, bio, iter_all) {
		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
		ret = csum_dirty_buffer(root->fs_info, bvec);
		if (ret)
			break;
	}

	return errno_to_blk_status(ret);
}

static blk_status_t btree_submit_bio_start(struct inode *inode, struct bio *bio,
					   u64 dio_file_offset)
{
	/*
	 * when we're called for a write, we're already in the async
	 * submission context.  Just jump into btrfs_map_bio
	 */
	return btree_csum_one_bio(bio);
}

static bool should_async_write(struct btrfs_fs_info *fs_info,
			     struct btrfs_inode *bi)
{
	if (btrfs_is_zoned(fs_info))
		return false;
	if (atomic_read(&bi->sync_writers))
		return false;
	if (test_bit(BTRFS_FS_CSUM_IMPL_FAST, &fs_info->flags))
		return false;
	return true;
}

void btrfs_submit_metadata_bio(struct inode *inode, struct bio *bio, int mirror_num)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	blk_status_t ret;

	if (btrfs_op(bio) != BTRFS_MAP_WRITE) {
		/*
		 * called for a read, do the setup so that checksum validation
		 * can happen in the async kernel threads
		 */
		ret = btrfs_bio_wq_end_io(fs_info, bio,
					  BTRFS_WQ_ENDIO_METADATA);
		if (!ret)
			ret = btrfs_map_bio(fs_info, bio, mirror_num);
	} else if (!should_async_write(fs_info, BTRFS_I(inode))) {
		ret = btree_csum_one_bio(bio);
		if (!ret)
			ret = btrfs_map_bio(fs_info, bio, mirror_num);
	} else {
		/*
		 * kthread helpers are used to submit writes so that
		 * checksumming can happen in parallel across all CPUs
		 */
		ret = btrfs_wq_submit_bio(inode, bio, mirror_num, 0,
					  btree_submit_bio_start);
	}

	if (ret) {
		bio->bi_status = ret;
		bio_endio(bio);
	}
}

#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
			struct page *newpage, struct page *page,
			enum migrate_mode mode)
{
	/*
	 * we can't safely write a btree page from here,
	 * we haven't done the locking hook
	 */
	if (PageDirty(page))
		return -EAGAIN;
	/*
	 * Buffers may be managed in a filesystem specific way.
	 * We must have no buffers or drop them.
	 */
	if (page_has_private(page) &&
	    !try_to_release_page(page, GFP_KERNEL))
		return -EAGAIN;
	return migrate_page(mapping, newpage, page, mode);
}
#endif


static int btree_writepages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
	struct btrfs_fs_info *fs_info;
	int ret;

	if (wbc->sync_mode == WB_SYNC_NONE) {

		if (wbc->for_kupdate)
			return 0;

		fs_info = BTRFS_I(mapping->host)->root->fs_info;
		/* this is a bit racy, but that's ok */
		ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
					     BTRFS_DIRTY_METADATA_THRESH,
					     fs_info->dirty_metadata_batch);
		if (ret < 0)
			return 0;
	}
	return btree_write_cache_pages(mapping, wbc);
}

static bool btree_release_folio(struct folio *folio, gfp_t gfp_flags)
{
	if (folio_test_writeback(folio) || folio_test_dirty(folio))
		return false;

	return try_release_extent_buffer(&folio->page);
}

static void btree_invalidate_folio(struct folio *folio, size_t offset,
				 size_t length)
{
	struct extent_io_tree *tree;
	tree = &BTRFS_I(folio->mapping->host)->io_tree;
	extent_invalidate_folio(tree, folio, offset);
	btree_release_folio(folio, GFP_NOFS);
	if (folio_get_private(folio)) {
		btrfs_warn(BTRFS_I(folio->mapping->host)->root->fs_info,
			   "folio private not zero on folio %llu",
			   (unsigned long long)folio_pos(folio));
		folio_detach_private(folio);
	}
}

#ifdef DEBUG
static bool btree_dirty_folio(struct address_space *mapping,
		struct folio *folio)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(mapping->host->i_sb);
	struct btrfs_subpage *subpage;
	struct extent_buffer *eb;
	int cur_bit = 0;
	u64 page_start = folio_pos(folio);

	if (fs_info->sectorsize == PAGE_SIZE) {
		eb = folio_get_private(folio);
		BUG_ON(!eb);
		BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
		BUG_ON(!atomic_read(&eb->refs));
		btrfs_assert_tree_write_locked(eb);
		return filemap_dirty_folio(mapping, folio);
	}
	subpage = folio_get_private(folio);

	ASSERT(subpage->dirty_bitmap);
	while (cur_bit < BTRFS_SUBPAGE_BITMAP_SIZE) {
		unsigned long flags;
		u64 cur;
		u16 tmp = (1 << cur_bit);

		spin_lock_irqsave(&subpage->lock, flags);
		if (!(tmp & subpage->dirty_bitmap)) {
			spin_unlock_irqrestore(&subpage->lock, flags);
			cur_bit++;
			continue;
		}
		spin_unlock_irqrestore(&subpage->lock, flags);
		cur = page_start + cur_bit * fs_info->sectorsize;

		eb = find_extent_buffer(fs_info, cur);
		ASSERT(eb);
		ASSERT(test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
		ASSERT(atomic_read(&eb->refs));
		btrfs_assert_tree_write_locked(eb);
		free_extent_buffer(eb);

		cur_bit += (fs_info->nodesize >> fs_info->sectorsize_bits);
	}
	return filemap_dirty_folio(mapping, folio);
}
#else
#define btree_dirty_folio filemap_dirty_folio
#endif

static const struct address_space_operations btree_aops = {
	.writepages	= btree_writepages,
	.release_folio	= btree_release_folio,
	.invalidate_folio = btree_invalidate_folio,
#ifdef CONFIG_MIGRATION
	.migratepage	= btree_migratepage,
#endif
	.dirty_folio = btree_dirty_folio,
};

struct extent_buffer *btrfs_find_create_tree_block(
						struct btrfs_fs_info *fs_info,
						u64 bytenr, u64 owner_root,
						int level)
{
	if (btrfs_is_testing(fs_info))
		return alloc_test_extent_buffer(fs_info, bytenr);
	return alloc_extent_buffer(fs_info, bytenr, owner_root, level);
}

/*
 * Read tree block at logical address @bytenr and do variant basic but critical
 * verification.
 *
 * @owner_root:		the objectid of the root owner for this block.
 * @parent_transid:	expected transid of this tree block, skip check if 0
 * @level:		expected level, mandatory check
 * @first_key:		expected key in slot 0, skip check if NULL
 */
struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
				      u64 owner_root, u64 parent_transid,
				      int level, struct btrfs_key *first_key)
{
	struct extent_buffer *buf = NULL;
	int ret;

	buf = btrfs_find_create_tree_block(fs_info, bytenr, owner_root, level);
	if (IS_ERR(buf))
		return buf;

	ret = btrfs_read_extent_buffer(buf, parent_transid, level, first_key);
	if (ret) {
		free_extent_buffer_stale(buf);
		return ERR_PTR(ret);
	}
	if (btrfs_check_eb_owner(buf, owner_root)) {
		free_extent_buffer_stale(buf);
		return ERR_PTR(-EUCLEAN);
	}
	return buf;

}

void btrfs_clean_tree_block(struct extent_buffer *buf)
{
	struct btrfs_fs_info *fs_info = buf->fs_info;
	if (btrfs_header_generation(buf) ==
	    fs_info->running_transaction->transid) {
		btrfs_assert_tree_write_locked(buf);

		if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
			percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
						 -buf->len,
						 fs_info->dirty_metadata_batch);
			clear_extent_buffer_dirty(buf);
		}
	}
}

static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
			 u64 objectid)
{
	bool dummy = test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);

	memset(&root->root_key, 0, sizeof(root->root_key));
	memset(&root->root_item, 0, sizeof(root->root_item));
	memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
	root->fs_info = fs_info;
	root->root_key.objectid = objectid;
	root->node = NULL;
	root->commit_root = NULL;
	root->state = 0;
	RB_CLEAR_NODE(&root->rb_node);

	root->last_trans = 0;
	root->free_objectid = 0;
	root->nr_delalloc_inodes = 0;
	root->nr_ordered_extents = 0;
	root->inode_tree = RB_ROOT;
	xa_init_flags(&root->delayed_nodes, GFP_ATOMIC);

	btrfs_init_root_block_rsv(root);

	INIT_LIST_HEAD(&root->dirty_list);
	INIT_LIST_HEAD(&root->root_list);
	INIT_LIST_HEAD(&root->delalloc_inodes);
	INIT_LIST_HEAD(&root->delalloc_root);
	INIT_LIST_HEAD(&root->ordered_extents);
	INIT_LIST_HEAD(&root->ordered_root);
	INIT_LIST_HEAD(&root->reloc_dirty_list);
	INIT_LIST_HEAD(&root->logged_list[0]);
	INIT_LIST_HEAD(&root->logged_list[1]);
	spin_lock_init(&root->inode_lock);
	spin_lock_init(&root->delalloc_lock);
	spin_lock_init(&root->ordered_extent_lock);
	spin_lock_init(&root->accounting_lock);
	spin_lock_init(&root->log_extents_lock[0]);
	spin_lock_init(&root->log_extents_lock[1]);
	spin_lock_init(&root->qgroup_meta_rsv_lock);
	mutex_init(&root->objectid_mutex);
	mutex_init(&root->log_mutex);
	mutex_init(&root->ordered_extent_mutex);
	mutex_init(&root->delalloc_mutex);
	init_waitqueue_head(&root->qgroup_flush_wait);
	init_waitqueue_head(&root->log_writer_wait);
	init_waitqueue_head(&root->log_commit_wait[0]);
	init_waitqueue_head(&root->log_commit_wait[1]);
	INIT_LIST_HEAD(&root->log_ctxs[0]);
	INIT_LIST_HEAD(&root->log_ctxs[1]);
	atomic_set(&root->log_commit[0], 0);
	atomic_set(&root->log_commit[1], 0);
	atomic_set(&root->log_writers, 0);
	atomic_set(&root->log_batch, 0);
	refcount_set(&root->refs, 1);
	atomic_set(&root->snapshot_force_cow, 0);
	atomic_set(&root->nr_swapfiles, 0);
	root->log_transid = 0;
	root->log_transid_committed = -1;
	root->last_log_commit = 0;
	root->anon_dev = 0;
	if (!dummy) {
		extent_io_tree_init(fs_info, &root->dirty_log_pages,
				    IO_TREE_ROOT_DIRTY_LOG_PAGES, NULL);
		extent_io_tree_init(fs_info, &root->log_csum_range,
				    IO_TREE_LOG_CSUM_RANGE, NULL);
	}

	spin_lock_init(&root->root_item_lock);
	btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
#ifdef CONFIG_BTRFS_DEBUG
	INIT_LIST_HEAD(&root->leak_list);
	spin_lock(&fs_info->fs_roots_lock);
	list_add_tail(&root->leak_list, &fs_info->allocated_roots);
	spin_unlock(&fs_info->fs_roots_lock);
#endif
}

static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,
					   u64 objectid, gfp_t flags)
{
	struct btrfs_root *root = kzalloc(sizeof(*root), flags);
	if (root)
		__setup_root(root, fs_info, objectid);
	return root;
}

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/* Should only be used by the testing infrastructure */
struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;

	if (!fs_info)
		return ERR_PTR(-EINVAL);

	root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID, GFP_KERNEL);
	if (!root)
		return ERR_PTR(-ENOMEM);

	/* We don't use the stripesize in selftest, set it as sectorsize */
	root->alloc_bytenr = 0;

	return root;
}
#endif

static int global_root_cmp(struct rb_node *a_node, const struct rb_node *b_node)
{
	const struct btrfs_root *a = rb_entry(a_node, struct btrfs_root, rb_node);
	const struct btrfs_root *b = rb_entry(b_node, struct btrfs_root, rb_node);

	return btrfs_comp_cpu_keys(&a->root_key, &b->root_key);
}

static int global_root_key_cmp(const void *k, const struct rb_node *node)
{
	const struct btrfs_key *key = k;
	const struct btrfs_root *root = rb_entry(node, struct btrfs_root, rb_node);

	return btrfs_comp_cpu_keys(key, &root->root_key);
}

int btrfs_global_root_insert(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct rb_node *tmp;

	write_lock(&fs_info->global_root_lock);
	tmp = rb_find_add(&root->rb_node, &fs_info->global_root_tree, global_root_cmp);
	write_unlock(&fs_info->global_root_lock);
	ASSERT(!tmp);

	return tmp ? -EEXIST : 0;
}

void btrfs_global_root_delete(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;

	write_lock(&fs_info->global_root_lock);
	rb_erase(&root->rb_node, &fs_info->global_root_tree);
	write_unlock(&fs_info->global_root_lock);
}

struct btrfs_root *btrfs_global_root(struct btrfs_fs_info *fs_info,
				     struct btrfs_key *key)
{
	struct rb_node *node;
	struct btrfs_root *root = NULL;

	read_lock(&fs_info->global_root_lock);
	node = rb_find(key, &fs_info->global_root_tree, global_root_key_cmp);
	if (node)
		root = container_of(node, struct btrfs_root, rb_node);
	read_unlock(&fs_info->global_root_lock);

	return root;
}

static u64 btrfs_global_root_id(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group *block_group;
	u64 ret;

	if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
		return 0;

	if (bytenr)
		block_group = btrfs_lookup_block_group(fs_info, bytenr);
	else
		block_group = btrfs_lookup_first_block_group(fs_info, bytenr);
	ASSERT(block_group);
	if (!block_group)
		return 0;
	ret = block_group->global_root_id;
	btrfs_put_block_group(block_group);

	return ret;
}

struct btrfs_root *btrfs_csum_root(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_key key = {
		.objectid = BTRFS_CSUM_TREE_OBJECTID,
		.type = BTRFS_ROOT_ITEM_KEY,
		.offset = btrfs_global_root_id(fs_info, bytenr),
	};

	return btrfs_global_root(fs_info, &key);
}

struct btrfs_root *btrfs_extent_root(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_key key = {
		.objectid = BTRFS_EXTENT_TREE_OBJECTID,
		.type = BTRFS_ROOT_ITEM_KEY,
		.offset = btrfs_global_root_id(fs_info, bytenr),
	};

	return btrfs_global_root(fs_info, &key);
}

struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
				     u64 objectid)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct extent_buffer *leaf;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root *root;
	struct btrfs_key key;
	unsigned int nofs_flag;
	int ret = 0;

	/*
	 * We're holding a transaction handle, so use a NOFS memory allocation
	 * context to avoid deadlock if reclaim happens.
	 */
	nofs_flag = memalloc_nofs_save();
	root = btrfs_alloc_root(fs_info, objectid, GFP_KERNEL);
	memalloc_nofs_restore(nofs_flag);
	if (!root)
		return ERR_PTR(-ENOMEM);

	root->root_key.objectid = objectid;
	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
	root->root_key.offset = 0;

	leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0,
				      BTRFS_NESTING_NORMAL);
	if (IS_ERR(leaf)) {
		ret = PTR_ERR(leaf);
		leaf = NULL;
		goto fail_unlock;
	}

	root->node = leaf;
	btrfs_mark_buffer_dirty(leaf);

	root->commit_root = btrfs_root_node(root);
	set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);

	btrfs_set_root_flags(&root->root_item, 0);
	btrfs_set_root_limit(&root->root_item, 0);
	btrfs_set_root_bytenr(&root->root_item, leaf->start);
	btrfs_set_root_generation(&root->root_item, trans->transid);
	btrfs_set_root_level(&root->root_item, 0);
	btrfs_set_root_refs(&root->root_item, 1);
	btrfs_set_root_used(&root->root_item, leaf->len);
	btrfs_set_root_last_snapshot(&root->root_item, 0);
	btrfs_set_root_dirid(&root->root_item, 0);
	if (is_fstree(objectid))
		generate_random_guid(root->root_item.uuid);
	else
		export_guid(root->root_item.uuid, &guid_null);
	btrfs_set_root_drop_level(&root->root_item, 0);

	btrfs_tree_unlock(leaf);

	key.objectid = objectid;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = 0;
	ret = btrfs_insert_root(trans, tree_root, &key, &root->root_item);
	if (ret)
		goto fail;

	return root;

fail_unlock:
	if (leaf)
		btrfs_tree_unlock(leaf);
fail:
	btrfs_put_root(root);

	return ERR_PTR(ret);
}

static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
					 struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;

	root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID, GFP_NOFS);
	if (!root)
		return ERR_PTR(-ENOMEM);

	root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
	root->root_key.type = BTRFS_ROOT_ITEM_KEY;
	root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;

	return root;
}

int btrfs_alloc_log_tree_node(struct btrfs_trans_handle *trans,
			      struct btrfs_root *root)
{
	struct extent_buffer *leaf;

	/*
	 * DON'T set SHAREABLE bit for log trees.
	 *
	 * Log trees are not exposed to user space thus can't be snapshotted,
	 * and they go away before a real commit is actually done.
	 *
	 * They do store pointers to file data extents, and those reference
	 * counts still get updated (along with back refs to the log tree).
	 */

	leaf = btrfs_alloc_tree_block(trans, root, 0, BTRFS_TREE_LOG_OBJECTID,
			NULL, 0, 0, 0, BTRFS_NESTING_NORMAL);
	if (IS_ERR(leaf))
		return PTR_ERR(leaf);

	root->node = leaf;

	btrfs_mark_buffer_dirty(root->node);
	btrfs_tree_unlock(root->node);

	return 0;
}

int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
			     struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *log_root;

	log_root = alloc_log_tree(trans, fs_info);
	if (IS_ERR(log_root))
		return PTR_ERR(log_root);

	if (!btrfs_is_zoned(fs_info)) {
		int ret = btrfs_alloc_log_tree_node(trans, log_root);

		if (ret) {
			btrfs_put_root(log_root);
			return ret;
		}
	}

	WARN_ON(fs_info->log_root_tree);
	fs_info->log_root_tree = log_root;
	return 0;
}

int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
		       struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_root *log_root;
	struct btrfs_inode_item *inode_item;
	int ret;

	log_root = alloc_log_tree(trans, fs_info);
	if (IS_ERR(log_root))
		return PTR_ERR(log_root);

	ret = btrfs_alloc_log_tree_node(trans, log_root);
	if (ret) {
		btrfs_put_root(log_root);
		return ret;
	}

	log_root->last_trans = trans->transid;
	log_root->root_key.offset = root->root_key.objectid;

	inode_item = &log_root->root_item.inode;
	btrfs_set_stack_inode_generation(inode_item, 1);
	btrfs_set_stack_inode_size(inode_item, 3);
	btrfs_set_stack_inode_nlink(inode_item, 1);
	btrfs_set_stack_inode_nbytes(inode_item,
				     fs_info->nodesize);
	btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);

	btrfs_set_root_node(&log_root->root_item, log_root->node);

	WARN_ON(root->log_root);
	root->log_root = log_root;
	root->log_transid = 0;
	root->log_transid_committed = -1;
	root->last_log_commit = 0;
	return 0;
}

static struct btrfs_root *read_tree_root_path(struct btrfs_root *tree_root,
					      struct btrfs_path *path,
					      struct btrfs_key *key)
{
	struct btrfs_root *root;
	struct btrfs_fs_info *fs_info = tree_root->fs_info;
	u64 generation;
	int ret;
	int level;

	root = btrfs_alloc_root(fs_info, key->objectid, GFP_NOFS);
	if (!root)
		return ERR_PTR(-ENOMEM);

	ret = btrfs_find_root(tree_root, key, path,
			      &root->root_item, &root->root_key);
	if (ret) {
		if (ret > 0)
			ret = -ENOENT;
		goto fail;
	}

	generation = btrfs_root_generation(&root->root_item);
	level = btrfs_root_level(&root->root_item);
	root->node = read_tree_block(fs_info,
				     btrfs_root_bytenr(&root->root_item),
				     key->objectid, generation, level, NULL);
	if (IS_ERR(root->node)) {
		ret = PTR_ERR(root->node);
		root->node = NULL;
		goto fail;
	}
	if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
		ret = -EIO;
		goto fail;
	}

	/*
	 * For real fs, and not log/reloc trees, root owner must
	 * match its root node owner
	 */
	if (!test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state) &&
	    root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
	    root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
	    root->root_key.objectid != btrfs_header_owner(root->node)) {
		btrfs_crit(fs_info,
"root=%llu block=%llu, tree root owner mismatch, have %llu expect %llu",
			   root->root_key.objectid, root->node->start,
			   btrfs_header_owner(root->node),
			   root->root_key.objectid);
		ret = -EUCLEAN;
		goto fail;
	}
	root->commit_root = btrfs_root_node(root);
	return root;
fail:
	btrfs_put_root(root);
	return ERR_PTR(ret);
}

struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
					struct btrfs_key *key)
{
	struct btrfs_root *root;
	struct btrfs_path *path;

	path = btrfs_alloc_path();
	if (!path)
		return ERR_PTR(-ENOMEM);
	root = read_tree_root_path(tree_root, path, key);
	btrfs_free_path(path);

	return root;
}

/*
 * Initialize subvolume root in-memory structure
 *
 * @anon_dev:	anonymous device to attach to the root, if zero, allocate new
 */
static int btrfs_init_fs_root(struct btrfs_root *root, dev_t anon_dev)
{
	int ret;
	unsigned int nofs_flag;

	/*
	 * We might be called under a transaction (e.g. indirect backref
	 * resolution) which could deadlock if it triggers memory reclaim
	 */
	nofs_flag = memalloc_nofs_save();
	ret = btrfs_drew_lock_init(&root->snapshot_lock);
	memalloc_nofs_restore(nofs_flag);
	if (ret)
		goto fail;

	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID &&
	    !btrfs_is_data_reloc_root(root)) {
		set_bit(BTRFS_ROOT_SHAREABLE, &root->state);
		btrfs_check_and_init_root_item(&root->root_item);
	}

	/*
	 * Don't assign anonymous block device to roots that are not exposed to
	 * userspace, the id pool is limited to 1M
	 */
	if (is_fstree(root->root_key.objectid) &&
	    btrfs_root_refs(&root->root_item) > 0) {
		if (!anon_dev) {
			ret = get_anon_bdev(&root->anon_dev);
			if (ret)
				goto fail;
		} else {
			root->anon_dev = anon_dev;
		}
	}

	mutex_lock(&root->objectid_mutex);
	ret = btrfs_init_root_free_objectid(root);
	if (ret) {
		mutex_unlock(&root->objectid_mutex);
		goto fail;
	}

	ASSERT(root->free_objectid <= BTRFS_LAST_FREE_OBJECTID);

	mutex_unlock(&root->objectid_mutex);

	return 0;
fail:
	/* The caller is responsible to call btrfs_free_fs_root */
	return ret;
}

static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
					       u64 root_id)
{
	struct btrfs_root *root;

	spin_lock(&fs_info->fs_roots_lock);
	root = xa_load(&fs_info->fs_roots, (unsigned long)root_id);
	if (root)
		root = btrfs_grab_root(root);
	spin_unlock(&fs_info->fs_roots_lock);
	return root;
}

static struct btrfs_root *btrfs_get_global_root(struct btrfs_fs_info *fs_info,
						u64 objectid)
{
	struct btrfs_key key = {
		.objectid = objectid,
		.type = BTRFS_ROOT_ITEM_KEY,
		.offset = 0,
	};

	if (objectid == BTRFS_ROOT_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->tree_root);
	if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
		return btrfs_grab_root(btrfs_global_root(fs_info, &key));
	if (objectid == BTRFS_CHUNK_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->chunk_root);
	if (objectid == BTRFS_DEV_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->dev_root);
	if (objectid == BTRFS_CSUM_TREE_OBJECTID)
		return btrfs_grab_root(btrfs_global_root(fs_info, &key));
	if (objectid == BTRFS_QUOTA_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->quota_root) ?
			fs_info->quota_root : ERR_PTR(-ENOENT);
	if (objectid == BTRFS_UUID_TREE_OBJECTID)
		return btrfs_grab_root(fs_info->uuid_root) ?
			fs_info->uuid_root : ERR_PTR(-ENOENT);
	if (objectid == BTRFS_FREE_SPACE_TREE_OBJECTID) {
		struct btrfs_root *root = btrfs_global_root(fs_info, &key);

		return btrfs_grab_root(root) ? root : ERR_PTR(-ENOENT);
	}
	return NULL;
}

int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
			 struct btrfs_root *root)
{
	int ret;

	spin_lock(&fs_info->fs_roots_lock);
	ret = xa_insert(&fs_info->fs_roots, (unsigned long)root->root_key.objectid,
			root, GFP_NOFS);
	if (ret == 0) {
		btrfs_grab_root(root);
		set_bit(BTRFS_ROOT_REGISTERED, &root->state);
	}
	spin_unlock(&fs_info->fs_roots_lock);

	return ret;
}

void btrfs_check_leaked_roots(struct btrfs_fs_info *fs_info)
{
#ifdef CONFIG_BTRFS_DEBUG
	struct btrfs_root *root;

	while (!list_empty(&fs_info->allocated_roots)) {
		char buf[BTRFS_ROOT_NAME_BUF_LEN];

		root = list_first_entry(&fs_info->allocated_roots,
					struct btrfs_root, leak_list);
		btrfs_err(fs_info, "leaked root %s refcount %d",
			  btrfs_root_name(&root->root_key, buf),
			  refcount_read(&root->refs));
		while (refcount_read(&root->refs) > 1)
			btrfs_put_root(root);
		btrfs_put_root(root);
	}
#endif
}

static void free_global_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;
	struct rb_node *node;

	while ((node = rb_first_postorder(&fs_info->global_root_tree)) != NULL) {
		root = rb_entry(node, struct btrfs_root, rb_node);
		rb_erase(&root->rb_node, &fs_info->global_root_tree);
		btrfs_put_root(root);
	}
}

void btrfs_free_fs_info(struct btrfs_fs_info *fs_info)
{
	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
	percpu_counter_destroy(&fs_info->delalloc_bytes);
	percpu_counter_destroy(&fs_info->ordered_bytes);
	percpu_counter_destroy(&fs_info->dev_replace.bio_counter);
	btrfs_free_csum_hash(fs_info);
	btrfs_free_stripe_hash_table(fs_info);
	btrfs_free_ref_cache(fs_info);
	kfree(fs_info->balance_ctl);
	kfree(fs_info->delayed_root);
	free_global_roots(fs_info);
	btrfs_put_root(fs_info->tree_root);
	btrfs_put_root(fs_info->chunk_root);
	btrfs_put_root(fs_info->dev_root);
	btrfs_put_root(fs_info->quota_root);
	btrfs_put_root(fs_info->uuid_root);
	btrfs_put_root(fs_info->fs_root);
	btrfs_put_root(fs_info->data_reloc_root);
	btrfs_put_root(fs_info->block_group_root);
	btrfs_check_leaked_roots(fs_info);
	btrfs_extent_buffer_leak_debug_check(fs_info);
	kfree(fs_info->super_copy);
	kfree(fs_info->super_for_commit);
	kfree(fs_info->subpage_info);
	kvfree(fs_info);
}


/*
 * Get an in-memory reference of a root structure.
 *
 * For essential trees like root/extent tree, we grab it from fs_info directly.
 * For subvolume trees, we check the cached filesystem roots first. If not
 * found, then read it from disk and add it to cached fs roots.
 *
 * Caller should release the root by calling btrfs_put_root() after the usage.
 *
 * NOTE: Reloc and log trees can't be read by this function as they share the
 *	 same root objectid.
 *
 * @objectid:	root id
 * @anon_dev:	preallocated anonymous block device number for new roots,
 * 		pass 0 for new allocation.
 * @check_ref:	whether to check root item references, If true, return -ENOENT
 *		for orphan roots
 */
static struct btrfs_root *btrfs_get_root_ref(struct btrfs_fs_info *fs_info,
					     u64 objectid, dev_t anon_dev,
					     bool check_ref)
{
	struct btrfs_root *root;
	struct btrfs_path *path;
	struct btrfs_key key;
	int ret;

	root = btrfs_get_global_root(fs_info, objectid);
	if (root)
		return root;
again:
	root = btrfs_lookup_fs_root(fs_info, objectid);
	if (root) {
		/* Shouldn't get preallocated anon_dev for cached roots */
		ASSERT(!anon_dev);
		if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
			btrfs_put_root(root);
			return ERR_PTR(-ENOENT);
		}
		return root;
	}

	key.objectid = objectid;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;
	root = btrfs_read_tree_root(fs_info->tree_root, &key);
	if (IS_ERR(root))
		return root;

	if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
		ret = -ENOENT;
		goto fail;
	}

	ret = btrfs_init_fs_root(root, anon_dev);
	if (ret)
		goto fail;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto fail;
	}
	key.objectid = BTRFS_ORPHAN_OBJECTID;
	key.type = BTRFS_ORPHAN_ITEM_KEY;
	key.offset = objectid;

	ret = btrfs_search_slot(NULL, fs_info->tree_root, &key, path, 0, 0);
	btrfs_free_path(path);
	if (ret < 0)
		goto fail;
	if (ret == 0)
		set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &root->state);

	ret = btrfs_insert_fs_root(fs_info, root);
	if (ret) {
		if (ret == -EEXIST) {
			btrfs_put_root(root);
			goto again;
		}
		goto fail;
	}
	return root;
fail:
	/*
	 * If our caller provided us an anonymous device, then it's his
	 * responsability to free it in case we fail. So we have to set our
	 * root's anon_dev to 0 to avoid a double free, once by btrfs_put_root()
	 * and once again by our caller.
	 */
	if (anon_dev)
		root->anon_dev = 0;
	btrfs_put_root(root);
	return ERR_PTR(ret);
}

/*
 * Get in-memory reference of a root structure
 *
 * @objectid:	tree objectid
 * @check_ref:	if set, verify that the tree exists and the item has at least
 *		one reference
 */
struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
				     u64 objectid, bool check_ref)
{
	return btrfs_get_root_ref(fs_info, objectid, 0, check_ref);
}

/*
 * Get in-memory reference of a root structure, created as new, optionally pass
 * the anonymous block device id
 *
 * @objectid:	tree objectid
 * @anon_dev:	if zero, allocate a new anonymous block device or use the
 *		parameter value
 */
struct btrfs_root *btrfs_get_new_fs_root(struct btrfs_fs_info *fs_info,
					 u64 objectid, dev_t anon_dev)
{
	return btrfs_get_root_ref(fs_info, objectid, anon_dev, true);
}

/*
 * btrfs_get_fs_root_commit_root - return a root for the given objectid
 * @fs_info:	the fs_info
 * @objectid:	the objectid we need to lookup
 *
 * This is exclusively used for backref walking, and exists specifically because
 * of how qgroups does lookups.  Qgroups will do a backref lookup at delayed ref
 * creation time, which means we may have to read the tree_root in order to look
 * up a fs root that is not in memory.  If the root is not in memory we will
 * read the tree root commit root and look up the fs root from there.  This is a
 * temporary root, it will not be inserted into the radix tree as it doesn't
 * have the most uptodate information, it'll simply be discarded once the
 * backref code is finished using the root.
 */
struct btrfs_root *btrfs_get_fs_root_commit_root(struct btrfs_fs_info *fs_info,
						 struct btrfs_path *path,
						 u64 objectid)
{
	struct btrfs_root *root;
	struct btrfs_key key;

	ASSERT(path->search_commit_root && path->skip_locking);

	/*
	 * This can return -ENOENT if we ask for a root that doesn't exist, but
	 * since this is called via the backref walking code we won't be looking
	 * up a root that doesn't exist, unless there's corruption.  So if root
	 * != NULL just return it.
	 */
	root = btrfs_get_global_root(fs_info, objectid);
	if (root)
		return root;

	root = btrfs_lookup_fs_root(fs_info, objectid);
	if (root)
		return root;

	key.objectid = objectid;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;
	root = read_tree_root_path(fs_info->tree_root, path, &key);
	btrfs_release_path(path);

	return root;
}

/*
 * called by the kthread helper functions to finally call the bio end_io
 * functions.  This is where read checksum verification actually happens
 */
static void end_workqueue_fn(struct btrfs_work *work)
{
	struct bio *bio;
	struct btrfs_end_io_wq *end_io_wq;

	end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
	bio = end_io_wq->bio;

	bio->bi_status = end_io_wq->status;
	bio->bi_private = end_io_wq->private;
	bio->bi_end_io = end_io_wq->end_io;
	bio_endio(bio);
	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
}

static int cleaner_kthread(void *arg)
{
	struct btrfs_fs_info *fs_info = arg;
	int again;

	while (1) {
		again = 0;

		set_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);

		/* Make the cleaner go to sleep early. */
		if (btrfs_need_cleaner_sleep(fs_info))
			goto sleep;

		/*
		 * Do not do anything if we might cause open_ctree() to block
		 * before we have finished mounting the filesystem.
		 */
		if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
			goto sleep;

		if (!mutex_trylock(&fs_info->cleaner_mutex))
			goto sleep;

		/*
		 * Avoid the problem that we change the status of the fs
		 * during the above check and trylock.
		 */
		if (btrfs_need_cleaner_sleep(fs_info)) {
			mutex_unlock(&fs_info->cleaner_mutex);
			goto sleep;
		}

		btrfs_run_delayed_iputs(fs_info);

		again = btrfs_clean_one_deleted_snapshot(fs_info);
		mutex_unlock(&fs_info->cleaner_mutex);

		/*
		 * The defragger has dealt with the R/O remount and umount,
		 * needn't do anything special here.
		 */
		btrfs_run_defrag_inodes(fs_info);

		/*
		 * Acquires fs_info->reclaim_bgs_lock to avoid racing
		 * with relocation (btrfs_relocate_chunk) and relocation
		 * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
		 * after acquiring fs_info->reclaim_bgs_lock. So we
		 * can't hold, nor need to, fs_info->cleaner_mutex when deleting
		 * unused block groups.
		 */
		btrfs_delete_unused_bgs(fs_info);

		/*
		 * Reclaim block groups in the reclaim_bgs list after we deleted
		 * all unused block_groups. This possibly gives us some more free
		 * space.
		 */
		btrfs_reclaim_bgs(fs_info);
sleep:
		clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
		if (kthread_should_park())
			kthread_parkme();
		if (kthread_should_stop())
			return 0;
		if (!again) {
			set_current_state(TASK_INTERRUPTIBLE);
			schedule();
			__set_current_state(TASK_RUNNING);
		}
	}
}

static int transaction_kthread(void *arg)
{
	struct btrfs_root *root = arg;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	struct btrfs_transaction *cur;
	u64 transid;
	time64_t delta;
	unsigned long delay;
	bool cannot_commit;

	do {
		cannot_commit = false;
		delay = msecs_to_jiffies(fs_info->commit_interval * 1000);
		mutex_lock(&fs_info->transaction_kthread_mutex);

		spin_lock(&fs_info->trans_lock);
		cur = fs_info->running_transaction;
		if (!cur) {
			spin_unlock(&fs_info->trans_lock);
			goto sleep;
		}

		delta = ktime_get_seconds() - cur->start_time;
		if (!test_and_clear_bit(BTRFS_FS_COMMIT_TRANS, &fs_info->flags) &&
		    cur->state < TRANS_STATE_COMMIT_START &&
		    delta < fs_info->commit_interval) {
			spin_unlock(&fs_info->trans_lock);
			delay -= msecs_to_jiffies((delta - 1) * 1000);
			delay = min(delay,
				    msecs_to_jiffies(fs_info->commit_interval * 1000));
			goto sleep;
		}
		transid = cur->transid;
		spin_unlock(&fs_info->trans_lock);

		/* If the file system is aborted, this will always fail. */
		trans = btrfs_attach_transaction(root);
		if (IS_ERR(trans)) {
			if (PTR_ERR(trans) != -ENOENT)
				cannot_commit = true;
			goto sleep;
		}
		if (transid == trans->transid) {
			btrfs_commit_transaction(trans);
		} else {
			btrfs_end_transaction(trans);
		}
sleep:
		wake_up_process(fs_info->cleaner_kthread);
		mutex_unlock(&fs_info->transaction_kthread_mutex);

		if (BTRFS_FS_ERROR(fs_info))
			btrfs_cleanup_transaction(fs_info);
		if (!kthread_should_stop() &&
				(!btrfs_transaction_blocked(fs_info) ||
				 cannot_commit))
			schedule_timeout_interruptible(delay);
	} while (!kthread_should_stop());
	return 0;
}

/*
 * This will find the highest generation in the array of root backups.  The
 * index of the highest array is returned, or -EINVAL if we can't find
 * anything.
 *
 * We check to make sure the array is valid by comparing the
 * generation of the latest  root in the array with the generation
 * in the super block.  If they don't match we pitch it.
 */
static int find_newest_super_backup(struct btrfs_fs_info *info)
{
	const u64 newest_gen = btrfs_super_generation(info->super_copy);
	u64 cur;
	struct btrfs_root_backup *root_backup;
	int i;

	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
		root_backup = info->super_copy->super_roots + i;
		cur = btrfs_backup_tree_root_gen(root_backup);
		if (cur == newest_gen)
			return i;
	}

	return -EINVAL;
}

/*
 * copy all the root pointers into the super backup array.
 * this will bump the backup pointer by one when it is
 * done
 */
static void backup_super_roots(struct btrfs_fs_info *info)
{
	const int next_backup = info->backup_root_index;
	struct btrfs_root_backup *root_backup;

	root_backup = info->super_for_commit->super_roots + next_backup;

	/*
	 * make sure all of our padding and empty slots get zero filled
	 * regardless of which ones we use today
	 */
	memset(root_backup, 0, sizeof(*root_backup));

	info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS;

	btrfs_set_backup_tree_root(root_backup, info->tree_root->node->start);
	btrfs_set_backup_tree_root_gen(root_backup,
			       btrfs_header_generation(info->tree_root->node));

	btrfs_set_backup_tree_root_level(root_backup,
			       btrfs_header_level(info->tree_root->node));

	btrfs_set_backup_chunk_root(root_backup, info->chunk_root->node->start);
	btrfs_set_backup_chunk_root_gen(root_backup,
			       btrfs_header_generation(info->chunk_root->node));
	btrfs_set_backup_chunk_root_level(root_backup,
			       btrfs_header_level(info->chunk_root->node));

	if (btrfs_fs_incompat(info, EXTENT_TREE_V2)) {
		btrfs_set_backup_block_group_root(root_backup,
					info->block_group_root->node->start);
		btrfs_set_backup_block_group_root_gen(root_backup,
			btrfs_header_generation(info->block_group_root->node));
		btrfs_set_backup_block_group_root_level(root_backup,
			btrfs_header_level(info->block_group_root->node));
	} else {
		struct btrfs_root *extent_root = btrfs_extent_root(info, 0);
		struct btrfs_root *csum_root = btrfs_csum_root(info, 0);

		btrfs_set_backup_extent_root(root_backup,
					     extent_root->node->start);
		btrfs_set_backup_extent_root_gen(root_backup,
				btrfs_header_generation(extent_root->node));
		btrfs_set_backup_extent_root_level(root_backup,
					btrfs_header_level(extent_root->node));

		btrfs_set_backup_csum_root(root_backup, csum_root->node->start);
		btrfs_set_backup_csum_root_gen(root_backup,
					       btrfs_header_generation(csum_root->node));
		btrfs_set_backup_csum_root_level(root_backup,
						 btrfs_header_level(csum_root->node));
	}

	/*
	 * we might commit during log recovery, which happens before we set
	 * the fs_root.  Make sure it is valid before we fill it in.
	 */
	if (info->fs_root && info->fs_root->node) {
		btrfs_set_backup_fs_root(root_backup,
					 info->fs_root->node->start);
		btrfs_set_backup_fs_root_gen(root_backup,
			       btrfs_header_generation(info->fs_root->node));
		btrfs_set_backup_fs_root_level(root_backup,
			       btrfs_header_level(info->fs_root->node));
	}

	btrfs_set_backup_dev_root(root_backup, info->dev_root->node->start);
	btrfs_set_backup_dev_root_gen(root_backup,
			       btrfs_header_generation(info->dev_root->node));
	btrfs_set_backup_dev_root_level(root_backup,
				       btrfs_header_level(info->dev_root->node));

	btrfs_set_backup_total_bytes(root_backup,
			     btrfs_super_total_bytes(info->super_copy));
	btrfs_set_backup_bytes_used(root_backup,
			     btrfs_super_bytes_used(info->super_copy));
	btrfs_set_backup_num_devices(root_backup,
			     btrfs_super_num_devices(info->super_copy));

	/*
	 * if we don't copy this out to the super_copy, it won't get remembered
	 * for the next commit
	 */
	memcpy(&info->super_copy->super_roots,
	       &info->super_for_commit->super_roots,
	       sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS);
}

/*
 * read_backup_root - Reads a backup root based on the passed priority. Prio 0
 * is the newest, prio 1/2/3 are 2nd newest/3rd newest/4th (oldest) backup roots
 *
 * fs_info - filesystem whose backup roots need to be read
 * priority - priority of backup root required
 *
 * Returns backup root index on success and -EINVAL otherwise.
 */
static int read_backup_root(struct btrfs_fs_info *fs_info, u8 priority)
{
	int backup_index = find_newest_super_backup(fs_info);
	struct btrfs_super_block *super = fs_info->super_copy;
	struct btrfs_root_backup *root_backup;

	if (priority < BTRFS_NUM_BACKUP_ROOTS && backup_index >= 0) {
		if (priority == 0)
			return backup_index;

		backup_index = backup_index + BTRFS_NUM_BACKUP_ROOTS - priority;
		backup_index %= BTRFS_NUM_BACKUP_ROOTS;
	} else {
		return -EINVAL;
	}

	root_backup = super->super_roots + backup_index;

	btrfs_set_super_generation(super,
				   btrfs_backup_tree_root_gen(root_backup));
	btrfs_set_super_root(super, btrfs_backup_tree_root(root_backup));
	btrfs_set_super_root_level(super,
				   btrfs_backup_tree_root_level(root_backup));
	btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));

	/*
	 * Fixme: the total bytes and num_devices need to match or we should
	 * need a fsck
	 */
	btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
	btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));

	return backup_index;
}

/* helper to cleanup workers */
static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
	btrfs_destroy_workqueue(fs_info->fixup_workers);
	btrfs_destroy_workqueue(fs_info->delalloc_workers);
	btrfs_destroy_workqueue(fs_info->hipri_workers);
	btrfs_destroy_workqueue(fs_info->workers);
	btrfs_destroy_workqueue(fs_info->endio_workers);
	btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
	if (fs_info->rmw_workers)
		destroy_workqueue(fs_info->rmw_workers);
	btrfs_destroy_workqueue(fs_info->endio_write_workers);
	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
	btrfs_destroy_workqueue(fs_info->delayed_workers);
	btrfs_destroy_workqueue(fs_info->caching_workers);
	btrfs_destroy_workqueue(fs_info->flush_workers);
	btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
	if (fs_info->discard_ctl.discard_workers)
		destroy_workqueue(fs_info->discard_ctl.discard_workers);
	/*
	 * Now that all other work queues are destroyed, we can safely destroy
	 * the queues used for metadata I/O, since tasks from those other work
	 * queues can do metadata I/O operations.
	 */
	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
}

static void free_root_extent_buffers(struct btrfs_root *root)
{
	if (root) {
		free_extent_buffer(root->node);
		free_extent_buffer(root->commit_root);
		root->node = NULL;
		root->commit_root = NULL;
	}
}

static void free_global_root_pointers(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root, *tmp;

	rbtree_postorder_for_each_entry_safe(root, tmp,
					     &fs_info->global_root_tree,
					     rb_node)
		free_root_extent_buffers(root);
}

/* helper to cleanup tree roots */
static void free_root_pointers(struct btrfs_fs_info *info, bool free_chunk_root)
{
	free_root_extent_buffers(info->tree_root);

	free_global_root_pointers(info);
	free_root_extent_buffers(info->dev_root);
	free_root_extent_buffers(info->quota_root);
	free_root_extent_buffers(info->uuid_root);
	free_root_extent_buffers(info->fs_root);
	free_root_extent_buffers(info->data_reloc_root);
	free_root_extent_buffers(info->block_group_root);
	if (free_chunk_root)
		free_root_extent_buffers(info->chunk_root);
}

void btrfs_put_root(struct btrfs_root *root)
{
	if (!root)
		return;

	if (refcount_dec_and_test(&root->refs)) {
		WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
		WARN_ON(test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state));
		if (root->anon_dev)
			free_anon_bdev(root->anon_dev);
		btrfs_drew_lock_destroy(&root->snapshot_lock);
		free_root_extent_buffers(root);
#ifdef CONFIG_BTRFS_DEBUG
		spin_lock(&root->fs_info->fs_roots_lock);
		list_del_init(&root->leak_list);
		spin_unlock(&root->fs_info->fs_roots_lock);
#endif
		kfree(root);
	}
}

void btrfs_free_fs_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;
	unsigned long index = 0;

	while (!list_empty(&fs_info->dead_roots)) {
		root = list_entry(fs_info->dead_roots.next,
				  struct btrfs_root, root_list);
		list_del(&root->root_list);

		if (test_bit(BTRFS_ROOT_REGISTERED, &root->state))
			btrfs_drop_and_free_fs_root(fs_info, root);
		btrfs_put_root(root);
	}

	xa_for_each(&fs_info->fs_roots, index, root) {
		btrfs_drop_and_free_fs_root(fs_info, root);
	}
}

static void btrfs_init_scrub(struct btrfs_fs_info *fs_info)
{
	mutex_init(&fs_info->scrub_lock);
	atomic_set(&fs_info->scrubs_running, 0);
	atomic_set(&fs_info->scrub_pause_req, 0);
	atomic_set(&fs_info->scrubs_paused, 0);
	atomic_set(&fs_info->scrub_cancel_req, 0);
	init_waitqueue_head(&fs_info->scrub_pause_wait);
	refcount_set(&fs_info->scrub_workers_refcnt, 0);
}

static void btrfs_init_balance(struct btrfs_fs_info *fs_info)
{
	spin_lock_init(&fs_info->balance_lock);
	mutex_init(&fs_info->balance_mutex);
	atomic_set(&fs_info->balance_pause_req, 0);
	atomic_set(&fs_info->balance_cancel_req, 0);
	fs_info->balance_ctl = NULL;
	init_waitqueue_head(&fs_info->balance_wait_q);
	atomic_set(&fs_info->reloc_cancel_req, 0);
}

static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
{
	struct inode *inode = fs_info->btree_inode;

	inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
	set_nlink(inode, 1);
	/*
	 * we set the i_size on the btree inode to the max possible int.
	 * the real end of the address space is determined by all of
	 * the devices in the system
	 */
	inode->i_size = OFFSET_MAX;
	inode->i_mapping->a_ops = &btree_aops;

	RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
	extent_io_tree_init(fs_info, &BTRFS_I(inode)->io_tree,
			    IO_TREE_BTREE_INODE_IO, inode);
	BTRFS_I(inode)->io_tree.track_uptodate = false;
	extent_map_tree_init(&BTRFS_I(inode)->extent_tree);

	BTRFS_I(inode)->root = btrfs_grab_root(fs_info->tree_root);
	memset(&BTRFS_I(inode)->location, 0, sizeof(struct btrfs_key));
	set_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags);
	btrfs_insert_inode_hash(inode);
}

static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
{
	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
	init_rwsem(&fs_info->dev_replace.rwsem);
	init_waitqueue_head(&fs_info->dev_replace.replace_wait);
}

static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
{
	spin_lock_init(&fs_info->qgroup_lock);
	mutex_init(&fs_info->qgroup_ioctl_lock);
	fs_info->qgroup_tree = RB_ROOT;
	INIT_LIST_HEAD(&fs_info->dirty_qgroups);
	fs_info->qgroup_seq = 1;
	fs_info->qgroup_ulist = NULL;
	fs_info->qgroup_rescan_running = false;
	mutex_init(&fs_info->qgroup_rescan_lock);
}

static int btrfs_init_workqueues(struct btrfs_fs_info *fs_info)
{
	u32 max_active = fs_info->thread_pool_size;
	unsigned int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;

	fs_info->workers =
		btrfs_alloc_workqueue(fs_info, "worker", flags, max_active, 16);
	fs_info->hipri_workers =
		btrfs_alloc_workqueue(fs_info, "worker-high",
				      flags | WQ_HIGHPRI, max_active, 16);

	fs_info->delalloc_workers =
		btrfs_alloc_workqueue(fs_info, "delalloc",
				      flags, max_active, 2);

	fs_info->flush_workers =
		btrfs_alloc_workqueue(fs_info, "flush_delalloc",
				      flags, max_active, 0);

	fs_info->caching_workers =
		btrfs_alloc_workqueue(fs_info, "cache", flags, max_active, 0);

	fs_info->fixup_workers =
		btrfs_alloc_workqueue(fs_info, "fixup", flags, 1, 0);

	/*
	 * endios are largely parallel and should have a very
	 * low idle thresh
	 */
	fs_info->endio_workers =
		btrfs_alloc_workqueue(fs_info, "endio", flags, max_active, 4);
	fs_info->endio_meta_workers =
		btrfs_alloc_workqueue(fs_info, "endio-meta", flags,
				      max_active, 4);
	fs_info->endio_meta_write_workers =
		btrfs_alloc_workqueue(fs_info, "endio-meta-write", flags,
				      max_active, 2);
	fs_info->endio_raid56_workers =
		btrfs_alloc_workqueue(fs_info, "endio-raid56", flags,
				      max_active, 4);
	fs_info->rmw_workers = alloc_workqueue("btrfs-rmw", flags, max_active);
	fs_info->endio_write_workers =
		btrfs_alloc_workqueue(fs_info, "endio-write", flags,
				      max_active, 2);
	fs_info->endio_freespace_worker =
		btrfs_alloc_workqueue(fs_info, "freespace-write", flags,
				      max_active, 0);
	fs_info->delayed_workers =
		btrfs_alloc_workqueue(fs_info, "delayed-meta", flags,
				      max_active, 0);
	fs_info->qgroup_rescan_workers =
		btrfs_alloc_workqueue(fs_info, "qgroup-rescan", flags, 1, 0);
	fs_info->discard_ctl.discard_workers =
		alloc_workqueue("btrfs_discard", WQ_UNBOUND | WQ_FREEZABLE, 1);

	if (!(fs_info->workers && fs_info->hipri_workers &&
	      fs_info->delalloc_workers && fs_info->flush_workers &&
	      fs_info->endio_workers && fs_info->endio_meta_workers &&
	      fs_info->endio_meta_write_workers &&
	      fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
	      fs_info->endio_freespace_worker && fs_info->rmw_workers &&
	      fs_info->caching_workers && fs_info->fixup_workers &&
	      fs_info->delayed_workers && fs_info->qgroup_rescan_workers &&
	      fs_info->discard_ctl.discard_workers)) {
		return -ENOMEM;
	}

	return 0;
}

static int btrfs_init_csum_hash(struct btrfs_fs_info *fs_info, u16 csum_type)
{
	struct crypto_shash *csum_shash;
	const char *csum_driver = btrfs_super_csum_driver(csum_type);

	csum_shash = crypto_alloc_shash(csum_driver, 0, 0);

	if (IS_ERR(csum_shash)) {
		btrfs_err(fs_info, "error allocating %s hash for checksum",
			  csum_driver);
		return PTR_ERR(csum_shash);
	}

	fs_info->csum_shash = csum_shash;

	return 0;
}

static int btrfs_replay_log(struct btrfs_fs_info *fs_info,
			    struct btrfs_fs_devices *fs_devices)
{
	int ret;
	struct btrfs_root *log_tree_root;
	struct btrfs_super_block *disk_super = fs_info->super_copy;
	u64 bytenr = btrfs_super_log_root(disk_super);
	int level = btrfs_super_log_root_level(disk_super);

	if (fs_devices->rw_devices == 0) {
		btrfs_warn(fs_info, "log replay required on RO media");
		return -EIO;
	}

	log_tree_root = btrfs_alloc_root(fs_info, BTRFS_TREE_LOG_OBJECTID,
					 GFP_KERNEL);
	if (!log_tree_root)
		return -ENOMEM;

	log_tree_root->node = read_tree_block(fs_info, bytenr,
					      BTRFS_TREE_LOG_OBJECTID,
					      fs_info->generation + 1, level,
					      NULL);
	if (IS_ERR(log_tree_root->node)) {
		btrfs_warn(fs_info, "failed to read log tree");
		ret = PTR_ERR(log_tree_root->node);
		log_tree_root->node = NULL;
		btrfs_put_root(log_tree_root);
		return ret;
	}
	if (!extent_buffer_uptodate(log_tree_root->node)) {
		btrfs_err(fs_info, "failed to read log tree");
		btrfs_put_root(log_tree_root);
		return -EIO;
	}

	/* returns with log_tree_root freed on success */
	ret = btrfs_recover_log_trees(log_tree_root);
	if (ret) {
		btrfs_handle_fs_error(fs_info, ret,
				      "Failed to recover log tree");
		btrfs_put_root(log_tree_root);
		return ret;
	}

	if (sb_rdonly(fs_info->sb)) {
		ret = btrfs_commit_super(fs_info);
		if (ret)
			return ret;
	}

	return 0;
}

static int load_global_roots_objectid(struct btrfs_root *tree_root,
				      struct btrfs_path *path, u64 objectid,
				      const char *name)
{
	struct btrfs_fs_info *fs_info = tree_root->fs_info;
	struct btrfs_root *root;
	u64 max_global_id = 0;
	int ret;
	struct btrfs_key key = {
		.objectid = objectid,
		.type = BTRFS_ROOT_ITEM_KEY,
		.offset = 0,
	};
	bool found = false;

	/* If we have IGNOREDATACSUMS skip loading these roots. */
	if (objectid == BTRFS_CSUM_TREE_OBJECTID &&
	    btrfs_test_opt(fs_info, IGNOREDATACSUMS)) {
		set_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);
		return 0;
	}

	while (1) {
		ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
		if (ret < 0)
			break;

		if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
			ret = btrfs_next_leaf(tree_root, path);
			if (ret) {
				if (ret > 0)
					ret = 0;
				break;
			}
		}
		ret = 0;

		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
		if (key.objectid != objectid)
			break;
		btrfs_release_path(path);

		/*
		 * Just worry about this for extent tree, it'll be the same for
		 * everybody.
		 */
		if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
			max_global_id = max(max_global_id, key.offset);

		found = true;
		root = read_tree_root_path(tree_root, path, &key);
		if (IS_ERR(root)) {
			if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
				ret = PTR_ERR(root);
			break;
		}
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		ret = btrfs_global_root_insert(root);
		if (ret) {
			btrfs_put_root(root);
			break;
		}
		key.offset++;
	}
	btrfs_release_path(path);

	if (objectid == BTRFS_EXTENT_TREE_OBJECTID)
		fs_info->nr_global_roots = max_global_id + 1;

	if (!found || ret) {
		if (objectid == BTRFS_CSUM_TREE_OBJECTID)
			set_bit(BTRFS_FS_STATE_NO_CSUMS, &fs_info->fs_state);

		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS))
			ret = ret ? ret : -ENOENT;
		else
			ret = 0;
		btrfs_err(fs_info, "failed to load root %s", name);
	}
	return ret;
}

static int load_global_roots(struct btrfs_root *tree_root)
{
	struct btrfs_path *path;
	int ret = 0;

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

	ret = load_global_roots_objectid(tree_root, path,
					 BTRFS_EXTENT_TREE_OBJECTID, "extent");
	if (ret)
		goto out;
	ret = load_global_roots_objectid(tree_root, path,
					 BTRFS_CSUM_TREE_OBJECTID, "csum");
	if (ret)
		goto out;
	if (!btrfs_fs_compat_ro(tree_root->fs_info, FREE_SPACE_TREE))
		goto out;
	ret = load_global_roots_objectid(tree_root, path,
					 BTRFS_FREE_SPACE_TREE_OBJECTID,
					 "free space");
out:
	btrfs_free_path(path);
	return ret;
}

static int btrfs_read_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root *root;
	struct btrfs_key location;
	int ret;

	BUG_ON(!fs_info->tree_root);

	ret = load_global_roots(tree_root);
	if (ret)
		return ret;

	location.objectid = BTRFS_DEV_TREE_OBJECTID;
	location.type = BTRFS_ROOT_ITEM_KEY;
	location.offset = 0;

	root = btrfs_read_tree_root(tree_root, &location);
	if (IS_ERR(root)) {
		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
			ret = PTR_ERR(root);
			goto out;
		}
	} else {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		fs_info->dev_root = root;
	}
	/* Initialize fs_info for all devices in any case */
	btrfs_init_devices_late(fs_info);

	/*
	 * This tree can share blocks with some other fs tree during relocation
	 * and we need a proper setup by btrfs_get_fs_root
	 */
	root = btrfs_get_fs_root(tree_root->fs_info,
				 BTRFS_DATA_RELOC_TREE_OBJECTID, true);
	if (IS_ERR(root)) {
		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
			ret = PTR_ERR(root);
			goto out;
		}
	} else {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		fs_info->data_reloc_root = root;
	}

	location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
	root = btrfs_read_tree_root(tree_root, &location);
	if (!IS_ERR(root)) {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
		fs_info->quota_root = root;
	}

	location.objectid = BTRFS_UUID_TREE_OBJECTID;
	root = btrfs_read_tree_root(tree_root, &location);
	if (IS_ERR(root)) {
		if (!btrfs_test_opt(fs_info, IGNOREBADROOTS)) {
			ret = PTR_ERR(root);
			if (ret != -ENOENT)
				goto out;
		}
	} else {
		set_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state);
		fs_info->uuid_root = root;
	}

	return 0;
out:
	btrfs_warn(fs_info, "failed to read root (objectid=%llu): %d",
		   location.objectid, ret);
	return ret;
}

/*
 * Real super block validation
 * NOTE: super csum type and incompat features will not be checked here.
 *
 * @sb:		super block to check
 * @mirror_num:	the super block number to check its bytenr:
 * 		0	the primary (1st) sb
 * 		1, 2	2nd and 3rd backup copy
 * 	       -1	skip bytenr check
 */
static int validate_super(struct btrfs_fs_info *fs_info,
			    struct btrfs_super_block *sb, int mirror_num)
{
	u64 nodesize = btrfs_super_nodesize(sb);
	u64 sectorsize = btrfs_super_sectorsize(sb);
	int ret = 0;

	if (btrfs_super_magic(sb) != BTRFS_MAGIC) {
		btrfs_err(fs_info, "no valid FS found");
		ret = -EINVAL;
	}
	if (btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP) {
		btrfs_err(fs_info, "unrecognized or unsupported super flag: %llu",
				btrfs_super_flags(sb) & ~BTRFS_SUPER_FLAG_SUPP);
		ret = -EINVAL;
	}
	if (btrfs_super_root_level(sb) >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "tree_root level too big: %d >= %d",
				btrfs_super_root_level(sb), BTRFS_MAX_LEVEL);
		ret = -EINVAL;
	}
	if (btrfs_super_chunk_root_level(sb) >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "chunk_root level too big: %d >= %d",
				btrfs_super_chunk_root_level(sb), BTRFS_MAX_LEVEL);
		ret = -EINVAL;
	}
	if (btrfs_super_log_root_level(sb) >= BTRFS_MAX_LEVEL) {
		btrfs_err(fs_info, "log_root level too big: %d >= %d",
				btrfs_super_log_root_level(sb), BTRFS_MAX_LEVEL);
		ret = -EINVAL;
	}

	/*
	 * Check sectorsize and nodesize first, other check will need it.
	 * Check all possible sectorsize(4K, 8K, 16K, 32K, 64K) here.
	 */
	if (!is_power_of_2(sectorsize) || sectorsize < 4096 ||
	    sectorsize > BTRFS_MAX_METADATA_BLOCKSIZE) {
		btrfs_err(fs_info, "invalid sectorsize %llu", sectorsize);
		ret = -EINVAL;
	}

	/*
	 * We only support at most two sectorsizes: 4K and PAGE_SIZE.
	 *
	 * We can support 16K sectorsize with 64K page size without problem,
	 * but such sectorsize/pagesize combination doesn't make much sense.
	 * 4K will be our future standard, PAGE_SIZE is supported from the very
	 * beginning.
	 */
	if (sectorsize > PAGE_SIZE || (sectorsize != SZ_4K && sectorsize != PAGE_SIZE)) {
		btrfs_err(fs_info,
			"sectorsize %llu not yet supported for page size %lu",
			sectorsize, PAGE_SIZE);
		ret = -EINVAL;
	}

	if (!is_power_of_2(nodesize) || nodesize < sectorsize ||
	    nodesize > BTRFS_MAX_METADATA_BLOCKSIZE) {
		btrfs_err(fs_info, "invalid nodesize %llu", nodesize);
		ret = -EINVAL;
	}
	if (nodesize != le32_to_cpu(sb->__unused_leafsize)) {
		btrfs_err(fs_info, "invalid leafsize %u, should be %llu",
			  le32_to_cpu(sb->__unused_leafsize), nodesize);
		ret = -EINVAL;
	}

	/* Root alignment check */
	if (!IS_ALIGNED(btrfs_super_root(sb), sectorsize)) {
		btrfs_warn(fs_info, "tree_root block unaligned: %llu",
			   btrfs_super_root(sb));
		ret = -EINVAL;
	}
	if (!IS_ALIGNED(btrfs_super_chunk_root(sb), sectorsize)) {
		btrfs_warn(fs_info, "chunk_root block unaligned: %llu",
			   btrfs_super_chunk_root(sb));
		ret = -EINVAL;
	}
	if (!IS_ALIGNED(btrfs_super_log_root(sb), sectorsize)) {
		btrfs_warn(fs_info, "log_root block unaligned: %llu",
			   btrfs_super_log_root(sb));
		ret = -EINVAL;
	}

	if (memcmp(fs_info->fs_devices->fsid, fs_info->super_copy->fsid,
		   BTRFS_FSID_SIZE)) {
		btrfs_err(fs_info,
		"superblock fsid doesn't match fsid of fs_devices: %pU != %pU",
			fs_info->super_copy->fsid, fs_info->fs_devices->fsid);
		ret = -EINVAL;
	}

	if (btrfs_fs_incompat(fs_info, METADATA_UUID) &&
	    memcmp(fs_info->fs_devices->metadata_uuid,
		   fs_info->super_copy->metadata_uuid, BTRFS_FSID_SIZE)) {
		btrfs_err(fs_info,
"superblock metadata_uuid doesn't match metadata uuid of fs_devices: %pU != %pU",
			fs_info->super_copy->metadata_uuid,
			fs_info->fs_devices->metadata_uuid);
		ret = -EINVAL;
	}

	if (memcmp(fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid,
		   BTRFS_FSID_SIZE) != 0) {
		btrfs_err(fs_info,
			"dev_item UUID does not match metadata fsid: %pU != %pU",
			fs_info->fs_devices->metadata_uuid, sb->dev_item.fsid);
		ret = -EINVAL;
	}

	/*
	 * Hint to catch really bogus numbers, bitflips or so, more exact checks are
	 * done later
	 */
	if (btrfs_super_bytes_used(sb) < 6 * btrfs_super_nodesize(sb)) {
		btrfs_err(fs_info, "bytes_used is too small %llu",
			  btrfs_super_bytes_used(sb));
		ret = -EINVAL;
	}
	if (!is_power_of_2(btrfs_super_stripesize(sb))) {
		btrfs_err(fs_info, "invalid stripesize %u",
			  btrfs_super_stripesize(sb));
		ret = -EINVAL;
	}
	if (btrfs_super_num_devices(sb) > (1UL << 31))
		btrfs_warn(fs_info, "suspicious number of devices: %llu",
			   btrfs_super_num_devices(sb));
	if (btrfs_super_num_devices(sb) == 0) {
		btrfs_err(fs_info, "number of devices is 0");
		ret = -EINVAL;
	}

	if (mirror_num >= 0 &&
	    btrfs_super_bytenr(sb) != btrfs_sb_offset(mirror_num)) {
		btrfs_err(fs_info, "super offset mismatch %llu != %u",
			  btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
		ret = -EINVAL;
	}

	/*
	 * Obvious sys_chunk_array corruptions, it must hold at least one key
	 * and one chunk
	 */
	if (btrfs_super_sys_array_size(sb) > BTRFS_SYSTEM_CHUNK_ARRAY_SIZE) {
		btrfs_err(fs_info, "system chunk array too big %u > %u",
			  btrfs_super_sys_array_size(sb),
			  BTRFS_SYSTEM_CHUNK_ARRAY_SIZE);
		ret = -EINVAL;
	}
	if (btrfs_super_sys_array_size(sb) < sizeof(struct btrfs_disk_key)
			+ sizeof(struct btrfs_chunk)) {
		btrfs_err(fs_info, "system chunk array too small %u < %zu",
			  btrfs_super_sys_array_size(sb),
			  sizeof(struct btrfs_disk_key)
			  + sizeof(struct btrfs_chunk));
		ret = -EINVAL;
	}

	/*
	 * The generation is a global counter, we'll trust it more than the others
	 * but it's still possible that it's the one that's wrong.
	 */
	if (btrfs_super_generation(sb) < btrfs_super_chunk_root_generation(sb))
		btrfs_warn(fs_info,
			"suspicious: generation < chunk_root_generation: %llu < %llu",
			btrfs_super_generation(sb),
			btrfs_super_chunk_root_generation(sb));
	if (btrfs_super_generation(sb) < btrfs_super_cache_generation(sb)
	    && btrfs_super_cache_generation(sb) != (u64)-1)
		btrfs_warn(fs_info,
			"suspicious: generation < cache_generation: %llu < %llu",
			btrfs_super_generation(sb),
			btrfs_super_cache_generation(sb));

	return ret;
}

/*
 * Validation of super block at mount time.
 * Some checks already done early at mount time, like csum type and incompat
 * flags will be skipped.
 */
static int btrfs_validate_mount_super(struct btrfs_fs_info *fs_info)
{
	return validate_super(fs_info, fs_info->super_copy, 0);
}

/*
 * Validation of super block at write time.
 * Some checks like bytenr check will be skipped as their values will be
 * overwritten soon.
 * Extra checks like csum type and incompat flags will be done here.
 */
static int btrfs_validate_write_super(struct btrfs_fs_info *fs_info,
				      struct btrfs_super_block *sb)
{
	int ret;

	ret = validate_super(fs_info, sb, -1);
	if (ret < 0)
		goto out;
	if (!btrfs_supported_super_csum(btrfs_super_csum_type(sb))) {
		ret = -EUCLEAN;
		btrfs_err(fs_info, "invalid csum type, has %u want %u",
			  btrfs_super_csum_type(sb), BTRFS_CSUM_TYPE_CRC32);
		goto out;
	}
	if (btrfs_super_incompat_flags(sb) & ~BTRFS_FEATURE_INCOMPAT_SUPP) {
		ret = -EUCLEAN;
		btrfs_err(fs_info,
		"invalid incompat flags, has 0x%llx valid mask 0x%llx",
			  btrfs_super_incompat_flags(sb),
			  (unsigned long long)BTRFS_FEATURE_INCOMPAT_SUPP);
		goto out;
	}
out:
	if (ret < 0)
		btrfs_err(fs_info,
		"super block corruption detected before writing it to disk");
	return ret;
}

static int load_super_root(struct btrfs_root *root, u64 bytenr, u64 gen, int level)
{
	int ret = 0;

	root->node = read_tree_block(root->fs_info, bytenr,
				     root->root_key.objectid, gen, level, NULL);
	if (IS_ERR(root->node)) {
		ret = PTR_ERR(root->node);
		root->node = NULL;
		return ret;
	}
	if (!extent_buffer_uptodate(root->node)) {
		free_extent_buffer(root->node);
		root->node = NULL;
		return -EIO;
	}

	btrfs_set_root_node(&root->root_item, root->node);
	root->commit_root = btrfs_root_node(root);
	btrfs_set_root_refs(&root->root_item, 1);
	return ret;
}

static int load_important_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_super_block *sb = fs_info->super_copy;
	u64 gen, bytenr;
	int level, ret;

	bytenr = btrfs_super_root(sb);
	gen = btrfs_super_generation(sb);
	level = btrfs_super_root_level(sb);
	ret = load_super_root(fs_info->tree_root, bytenr, gen, level);
	if (ret) {
		btrfs_warn(fs_info, "couldn't read tree root");
		return ret;
	}

	if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
		return 0;

	bytenr = btrfs_super_block_group_root(sb);
	gen = btrfs_super_block_group_root_generation(sb);
	level = btrfs_super_block_group_root_level(sb);
	ret = load_super_root(fs_info->block_group_root, bytenr, gen, level);
	if (ret)
		btrfs_warn(fs_info, "couldn't read block group root");
	return ret;
}

static int __cold init_tree_roots(struct btrfs_fs_info *fs_info)
{
	int backup_index = find_newest_super_backup(fs_info);
	struct btrfs_super_block *sb = fs_info->super_copy;
	struct btrfs_root *tree_root = fs_info->tree_root;
	bool handle_error = false;
	int ret = 0;
	int i;

	if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
		struct btrfs_root *root;

		root = btrfs_alloc_root(fs_info, BTRFS_BLOCK_GROUP_TREE_OBJECTID,
					GFP_KERNEL);
		if (!root)
			return -ENOMEM;
		fs_info->block_group_root = root;
	}

	for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
		if (handle_error) {
			if (!IS_ERR(tree_root->node))
				free_extent_buffer(tree_root->node);
			tree_root->node = NULL;

			if (!btrfs_test_opt(fs_info, USEBACKUPROOT))
				break;

			free_root_pointers(fs_info, 0);

			/*
			 * Don't use the log in recovery mode, it won't be
			 * valid
			 */
			btrfs_set_super_log_root(sb, 0);

			/* We can't trust the free space cache either */
			btrfs_set_opt(fs_info->mount_opt, CLEAR_CACHE);

			ret = read_backup_root(fs_info, i);
			backup_index = ret;
			if (ret < 0)
				return ret;
		}

		ret = load_important_roots(fs_info);
		if (ret) {
			handle_error = true;
			continue;
		}

		/*
		 * No need to hold btrfs_root::objectid_mutex since the fs
		 * hasn't been fully initialised and we are the only user
		 */
		ret = btrfs_init_root_free_objectid(tree_root);
		if (ret < 0) {
			handle_error = true;
			continue;
		}

		ASSERT(tree_root->free_objectid <= BTRFS_LAST_FREE_OBJECTID);

		ret = btrfs_read_roots(fs_info);
		if (ret < 0) {
			handle_error = true;
			continue;
		}

		/* All successful */
		fs_info->generation = btrfs_header_generation(tree_root->node);
		fs_info->last_trans_committed = fs_info->generation;
		fs_info->last_reloc_trans = 0;

		/* Always begin writing backup roots after the one being used */
		if (backup_index < 0) {
			fs_info->backup_root_index = 0;
		} else {
			fs_info->backup_root_index = backup_index + 1;
			fs_info->backup_root_index %= BTRFS_NUM_BACKUP_ROOTS;
		}
		break;
	}

	return ret;
}

void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
{
	xa_init_flags(&fs_info->fs_roots, GFP_ATOMIC);
	xa_init_flags(&fs_info->extent_buffers, GFP_ATOMIC);
	INIT_LIST_HEAD(&fs_info->trans_list);
	INIT_LIST_HEAD(&fs_info->dead_roots);
	INIT_LIST_HEAD(&fs_info->delayed_iputs);
	INIT_LIST_HEAD(&fs_info->delalloc_roots);
	INIT_LIST_HEAD(&fs_info->caching_block_groups);
	spin_lock_init(&fs_info->delalloc_root_lock);
	spin_lock_init(&fs_info->trans_lock);
	spin_lock_init(&fs_info->fs_roots_lock);
	spin_lock_init(&fs_info->delayed_iput_lock);
	spin_lock_init(&fs_info->defrag_inodes_lock);
	spin_lock_init(&fs_info->super_lock);
	spin_lock_init(&fs_info->buffer_lock);
	spin_lock_init(&fs_info->unused_bgs_lock);
	spin_lock_init(&fs_info->treelog_bg_lock);
	spin_lock_init(&fs_info->zone_active_bgs_lock);
	spin_lock_init(&fs_info->relocation_bg_lock);
	rwlock_init(&fs_info->tree_mod_log_lock);
	rwlock_init(&fs_info->global_root_lock);
	mutex_init(&fs_info->unused_bg_unpin_mutex);
	mutex_init(&fs_info->reclaim_bgs_lock);
	mutex_init(&fs_info->reloc_mutex);
	mutex_init(&fs_info->delalloc_root_mutex);
	mutex_init(&fs_info->zoned_meta_io_lock);
	mutex_init(&fs_info->zoned_data_reloc_io_lock);
	seqlock_init(&fs_info->profiles_lock);

	INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
	INIT_LIST_HEAD(&fs_info->space_info);
	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
	INIT_LIST_HEAD(&fs_info->unused_bgs);
	INIT_LIST_HEAD(&fs_info->reclaim_bgs);
	INIT_LIST_HEAD(&fs_info->zone_active_bgs);
#ifdef CONFIG_BTRFS_DEBUG
	INIT_LIST_HEAD(&fs_info->allocated_roots);
	INIT_LIST_HEAD(&fs_info->allocated_ebs);
	spin_lock_init(&fs_info->eb_leak_lock);
#endif
	extent_map_tree_init(&fs_info->mapping_tree);
	btrfs_init_block_rsv(&fs_info->global_block_rsv,
			     BTRFS_BLOCK_RSV_GLOBAL);
	btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
	btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK);
	btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
	btrfs_init_block_rsv(&fs_info->delayed_block_rsv,
			     BTRFS_BLOCK_RSV_DELOPS);
	btrfs_init_block_rsv(&fs_info->delayed_refs_rsv,
			     BTRFS_BLOCK_RSV_DELREFS);

	atomic_set(&fs_info->async_delalloc_pages, 0);
	atomic_set(&fs_info->defrag_running, 0);
	atomic_set(&fs_info->nr_delayed_iputs, 0);
	atomic64_set(&fs_info->tree_mod_seq, 0);
	fs_info->global_root_tree = RB_ROOT;
	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
	fs_info->metadata_ratio = 0;
	fs_info->defrag_inodes = RB_ROOT;
	atomic64_set(&fs_info->free_chunk_space, 0);
	fs_info->tree_mod_log = RB_ROOT;
	fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
	fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
	btrfs_init_ref_verify(fs_info);

	fs_info->thread_pool_size = min_t(unsigned long,
					  num_online_cpus() + 2, 8);

	INIT_LIST_HEAD(&fs_info->ordered_roots);
	spin_lock_init(&fs_info->ordered_root_lock);

	btrfs_init_scrub(fs_info);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	fs_info->check_integrity_print_mask = 0;
#endif
	btrfs_init_balance(fs_info);
	btrfs_init_async_reclaim_work(fs_info);

	rwlock_init(&fs_info->block_group_cache_lock);
	fs_info->block_group_cache_tree = RB_ROOT_CACHED;

	extent_io_tree_init(fs_info, &fs_info->excluded_extents,
			    IO_TREE_FS_EXCLUDED_EXTENTS, NULL);

	mutex_init(&fs_info->ordered_operations_mutex);
	mutex_init(&fs_info->tree_log_mutex);
	mutex_init(&fs_info->chunk_mutex);
	mutex_init(&fs_info->transaction_kthread_mutex);
	mutex_init(&fs_info->cleaner_mutex);
	mutex_init(&fs_info->ro_block_group_mutex);
	init_rwsem(&fs_info->commit_root_sem);
	init_rwsem(&fs_info->cleanup_work_sem);
	init_rwsem(&fs_info->subvol_sem);
	sema_init(&fs_info->uuid_tree_rescan_sem, 1);

	btrfs_init_dev_replace_locks(fs_info);
	btrfs_init_qgroup(fs_info);
	btrfs_discard_init(fs_info);

	btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
	btrfs_init_free_cluster(&fs_info->data_alloc_cluster);

	init_waitqueue_head(&fs_info->transaction_throttle);
	init_waitqueue_head(&fs_info->transaction_wait);
	init_waitqueue_head(&fs_info->transaction_blocked_wait);
	init_waitqueue_head(&fs_info->async_submit_wait);
	init_waitqueue_head(&fs_info->delayed_iputs_wait);

	/* Usable values until the real ones are cached from the superblock */
	fs_info->nodesize = 4096;
	fs_info->sectorsize = 4096;
	fs_info->sectorsize_bits = ilog2(4096);
	fs_info->stripesize = 4096;

	spin_lock_init(&fs_info->swapfile_pins_lock);
	fs_info->swapfile_pins = RB_ROOT;

	fs_info->bg_reclaim_threshold = BTRFS_DEFAULT_RECLAIM_THRESH;
	INIT_WORK(&fs_info->reclaim_bgs_work, btrfs_reclaim_bgs_work);
}

static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block *sb)
{
	int ret;

	fs_info->sb = sb;
	sb->s_blocksize = BTRFS_BDEV_BLOCKSIZE;
	sb->s_blocksize_bits = blksize_bits(BTRFS_BDEV_BLOCKSIZE);

	ret = percpu_counter_init(&fs_info->ordered_bytes, 0, GFP_KERNEL);
	if (ret)
		return ret;

	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
	if (ret)
		return ret;

	fs_info->dirty_metadata_batch = PAGE_SIZE *
					(1 + ilog2(nr_cpu_ids));

	ret = percpu_counter_init(&fs_info->delalloc_bytes, 0, GFP_KERNEL);
	if (ret)
		return ret;

	ret = percpu_counter_init(&fs_info->dev_replace.bio_counter, 0,
			GFP_KERNEL);
	if (ret)
		return ret;

	fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
					GFP_KERNEL);
	if (!fs_info->delayed_root)
		return -ENOMEM;
	btrfs_init_delayed_root(fs_info->delayed_root);

	if (sb_rdonly(sb))
		set_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state);

	return btrfs_alloc_stripe_hash_table(fs_info);
}

static int btrfs_uuid_rescan_kthread(void *data)
{
	struct btrfs_fs_info *fs_info = data;
	int ret;

	/*
	 * 1st step is to iterate through the existing UUID tree and
	 * to delete all entries that contain outdated data.
	 * 2nd step is to add all missing entries to the UUID tree.
	 */
	ret = btrfs_uuid_tree_iterate(fs_info);
	if (ret < 0) {
		if (ret != -EINTR)
			btrfs_warn(fs_info, "iterating uuid_tree failed %d",
				   ret);
		up(&fs_info->uuid_tree_rescan_sem);
		return ret;
	}
	return btrfs_uuid_scan_kthread(data);
}

static int btrfs_check_uuid_tree(struct btrfs_fs_info *fs_info)
{
	struct task_struct *task;

	down(&fs_info->uuid_tree_rescan_sem);
	task = kthread_run(btrfs_uuid_rescan_kthread, fs_info, "btrfs-uuid");
	if (IS_ERR(task)) {
		/* fs_info->update_uuid_tree_gen remains 0 in all error case */
		btrfs_warn(fs_info, "failed to start uuid_rescan task");
		up(&fs_info->uuid_tree_rescan_sem);
		return PTR_ERR(task);
	}

	return 0;
}

/*
 * Some options only have meaning at mount time and shouldn't persist across
 * remounts, or be displayed. Clear these at the end of mount and remount
 * code paths.
 */
void btrfs_clear_oneshot_options(struct btrfs_fs_info *fs_info)
{
	btrfs_clear_opt(fs_info->mount_opt, USEBACKUPROOT);
	btrfs_clear_opt(fs_info->mount_opt, CLEAR_CACHE);
}

/*
 * Mounting logic specific to read-write file systems. Shared by open_ctree
 * and btrfs_remount when remounting from read-only to read-write.
 */
int btrfs_start_pre_rw_mount(struct btrfs_fs_info *fs_info)
{
	int ret;
	const bool cache_opt = btrfs_test_opt(fs_info, SPACE_CACHE);
	bool clear_free_space_tree = false;

	if (btrfs_test_opt(fs_info, CLEAR_CACHE) &&
	    btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
		clear_free_space_tree = true;
	} else if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE) &&
		   !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID)) {
		btrfs_warn(fs_info, "free space tree is invalid");
		clear_free_space_tree = true;
	}

	if (clear_free_space_tree) {
		btrfs_info(fs_info, "clearing free space tree");
		ret = btrfs_clear_free_space_tree(fs_info);
		if (ret) {
			btrfs_warn(fs_info,
				   "failed to clear free space tree: %d", ret);
			goto out;
		}
	}

	/*
	 * btrfs_find_orphan_roots() is responsible for finding all the dead
	 * roots (with 0 refs), flag them with BTRFS_ROOT_DEAD_TREE and load
	 * them into the fs_info->fs_roots. This must be done before
	 * calling btrfs_orphan_cleanup() on the tree root. If we don't do it
	 * first, then btrfs_orphan_cleanup() will delete a dead root's orphan
	 * item before the root's tree is deleted - this means that if we unmount
	 * or crash before the deletion completes, on the next mount we will not
	 * delete what remains of the tree because the orphan item does not
	 * exists anymore, which is what tells us we have a pending deletion.
	 */
	ret = btrfs_find_orphan_roots(fs_info);
	if (ret)
		goto out;

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

	down_read(&fs_info->cleanup_work_sem);
	if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) ||
	    (ret = btrfs_orphan_cleanup(fs_info->tree_root))) {
		up_read(&fs_info->cleanup_work_sem);
		goto out;
	}
	up_read(&fs_info->cleanup_work_sem);

	mutex_lock(&fs_info->cleaner_mutex);
	ret = btrfs_recover_relocation(fs_info);
	mutex_unlock(&fs_info->cleaner_mutex);
	if (ret < 0) {
		btrfs_warn(fs_info, "failed to recover relocation: %d", ret);
		goto out;
	}

	if (btrfs_test_opt(fs_info, FREE_SPACE_TREE) &&
	    !btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE)) {
		btrfs_info(fs_info, "creating free space tree");
		ret = btrfs_create_free_space_tree(fs_info);
		if (ret) {
			btrfs_warn(fs_info,
				"failed to create free space tree: %d", ret);
			goto out;
		}
	}

	if (cache_opt != btrfs_free_space_cache_v1_active(fs_info)) {
		ret = btrfs_set_free_space_cache_v1_active(fs_info, cache_opt);
		if (ret)
			goto out;
	}

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

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

	btrfs_qgroup_rescan_resume(fs_info);

	if (!fs_info->uuid_root) {
		btrfs_info(fs_info, "creating UUID tree");
		ret = btrfs_create_uuid_tree(fs_info);
		if (ret) {
			btrfs_warn(fs_info,
				   "failed to create the UUID tree %d", ret);
			goto out;
		}
	}

out:
	return ret;
}

int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_devices,
		      char *options)
{
	u32 sectorsize;
	u32 nodesize;
	u32 stripesize;
	u64 generation;
	u64 features;
	u16 csum_type;
	struct btrfs_super_block *disk_super;
	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
	struct btrfs_root *tree_root;
	struct btrfs_root *chunk_root;
	int ret;
	int err = -EINVAL;
	int level;

	ret = init_mount_fs_info(fs_info, sb);
	if (ret) {
		err = ret;
		goto fail;
	}

	/* These need to be init'ed before we start creating inodes and such. */
	tree_root = btrfs_alloc_root(fs_info, BTRFS_ROOT_TREE_OBJECTID,
				     GFP_KERNEL);
	fs_info->tree_root = tree_root;
	chunk_root = btrfs_alloc_root(fs_info, BTRFS_CHUNK_TREE_OBJECTID,
				      GFP_KERNEL);
	fs_info->chunk_root = chunk_root;
	if (!tree_root || !chunk_root) {
		err = -ENOMEM;
		goto fail;
	}

	fs_info->btree_inode = new_inode(sb);
	if (!fs_info->btree_inode) {
		err = -ENOMEM;
		goto fail;
	}
	mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);
	btrfs_init_btree_inode(fs_info);

	invalidate_bdev(fs_devices->latest_dev->bdev);

	/*
	 * Read super block and check the signature bytes only
	 */
	disk_super = btrfs_read_dev_super(fs_devices->latest_dev->bdev);
	if (IS_ERR(disk_super)) {
		err = PTR_ERR(disk_super);
		goto fail_alloc;
	}

	/*
	 * Verify the type first, if that or the checksum value are
	 * corrupted, we'll find out
	 */
	csum_type = btrfs_super_csum_type(disk_super);
	if (!btrfs_supported_super_csum(csum_type)) {
		btrfs_err(fs_info, "unsupported checksum algorithm: %u",
			  csum_type);
		err = -EINVAL;
		btrfs_release_disk_super(disk_super);
		goto fail_alloc;
	}

	fs_info->csum_size = btrfs_super_csum_size(disk_super);

	ret = btrfs_init_csum_hash(fs_info, csum_type);
	if (ret) {
		err = ret;
		btrfs_release_disk_super(disk_super);
		goto fail_alloc;
	}

	/*
	 * We want to check superblock checksum, the type is stored inside.
	 * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
	 */
	if (btrfs_check_super_csum(fs_info, (u8 *)disk_super)) {
		btrfs_err(fs_info, "superblock checksum mismatch");
		err = -EINVAL;
		btrfs_release_disk_super(disk_super);
		goto fail_alloc;
	}

	/*
	 * super_copy is zeroed at allocation time and we never touch the
	 * following bytes up to INFO_SIZE, the checksum is calculated from
	 * the whole block of INFO_SIZE
	 */
	memcpy(fs_info->super_copy, disk_super, sizeof(*fs_info->super_copy));
	btrfs_release_disk_super(disk_super);

	disk_super = fs_info->super_copy;


	features = btrfs_super_flags(disk_super);
	if (features & BTRFS_SUPER_FLAG_CHANGING_FSID_V2) {
		features &= ~BTRFS_SUPER_FLAG_CHANGING_FSID_V2;
		btrfs_set_super_flags(disk_super, features);
		btrfs_info(fs_info,
			"found metadata UUID change in progress flag, clearing");
	}

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

	ret = btrfs_validate_mount_super(fs_info);
	if (ret) {
		btrfs_err(fs_info, "superblock contains fatal errors");
		err = -EINVAL;
		goto fail_alloc;
	}

	if (!btrfs_super_root(disk_super))
		goto fail_alloc;

	/* check FS state, whether FS is broken. */
	if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR)
		set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);

	/*
	 * In the long term, we'll store the compression type in the super
	 * block, and it'll be used for per file compression control.
	 */
	fs_info->compress_type = BTRFS_COMPRESS_ZLIB;

	/*
	 * Flag our filesystem as having big metadata blocks if they are bigger
	 * than the page size.
	 */
	if (btrfs_super_nodesize(disk_super) > PAGE_SIZE) {
		if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
			btrfs_info(fs_info,
				"flagging fs with big metadata feature");
		features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
	}

	/* Set up fs_info before parsing mount options */
	nodesize = btrfs_super_nodesize(disk_super);
	sectorsize = btrfs_super_sectorsize(disk_super);
	stripesize = sectorsize;
	fs_info->dirty_metadata_batch = nodesize * (1 + ilog2(nr_cpu_ids));
	fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));

	fs_info->nodesize = nodesize;
	fs_info->sectorsize = sectorsize;
	fs_info->sectorsize_bits = ilog2(sectorsize);
	fs_info->csums_per_leaf = BTRFS_MAX_ITEM_SIZE(fs_info) / fs_info->csum_size;
	fs_info->stripesize = stripesize;

	ret = btrfs_parse_options(fs_info, options, sb->s_flags);
	if (ret) {
		err = ret;
		goto fail_alloc;
	}

	features = btrfs_super_incompat_flags(disk_super) &
		~BTRFS_FEATURE_INCOMPAT_SUPP;
	if (features) {
		btrfs_err(fs_info,
		    "cannot mount because of unsupported optional features (0x%llx)",
		    features);
		err = -EINVAL;
		goto fail_alloc;
	}

	features = btrfs_super_incompat_flags(disk_super);
	features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
	if (fs_info->compress_type == BTRFS_COMPRESS_LZO)
		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;
	else if (fs_info->compress_type == BTRFS_COMPRESS_ZSTD)
		features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_ZSTD;

	if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
		btrfs_info(fs_info, "has skinny extents");

	/*
	 * mixed block groups end up with duplicate but slightly offset
	 * extent buffers for the same range.  It leads to corruptions
	 */
	if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
	    (sectorsize != nodesize)) {
		btrfs_err(fs_info,
"unequal nodesize/sectorsize (%u != %u) are not allowed for mixed block groups",
			nodesize, sectorsize);
		goto fail_alloc;
	}

	/*
	 * Needn't use the lock because there is no other task which will
	 * update the flag.
	 */
	btrfs_set_super_incompat_flags(disk_super, features);

	features = btrfs_super_compat_ro_flags(disk_super) &
		~BTRFS_FEATURE_COMPAT_RO_SUPP;
	if (!sb_rdonly(sb) && features) {
		btrfs_err(fs_info,
	"cannot mount read-write because of unsupported optional features (0x%llx)",
		       features);
		err = -EINVAL;
		goto fail_alloc;
	}

	if (sectorsize < PAGE_SIZE) {
		struct btrfs_subpage_info *subpage_info;

		/*
		 * V1 space cache has some hardcoded PAGE_SIZE usage, and is
		 * going to be deprecated.
		 *
		 * Force to use v2 cache for subpage case.
		 */
		btrfs_clear_opt(fs_info->mount_opt, SPACE_CACHE);
		btrfs_set_and_info(fs_info, FREE_SPACE_TREE,
			"forcing free space tree for sector size %u with page size %lu",
			sectorsize, PAGE_SIZE);

		btrfs_warn(fs_info,
		"read-write for sector size %u with page size %lu is experimental",
			   sectorsize, PAGE_SIZE);
		subpage_info = kzalloc(sizeof(*subpage_info), GFP_KERNEL);
		if (!subpage_info)
			goto fail_alloc;
		btrfs_init_subpage_info(subpage_info, sectorsize);
		fs_info->subpage_info = subpage_info;
	}

	ret = btrfs_init_workqueues(fs_info);
	if (ret) {
		err = ret;
		goto fail_sb_buffer;
	}

	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);

	sb->s_blocksize = sectorsize;
	sb->s_blocksize_bits = blksize_bits(sectorsize);
	memcpy(&sb->s_uuid, fs_info->fs_devices->fsid, BTRFS_FSID_SIZE);

	mutex_lock(&fs_info->chunk_mutex);
	ret = btrfs_read_sys_array(fs_info);
	mutex_unlock(&fs_info->chunk_mutex);
	if (ret) {
		btrfs_err(fs_info, "failed to read the system array: %d", ret);
		goto fail_sb_buffer;
	}

	generation = btrfs_super_chunk_root_generation(disk_super);
	level = btrfs_super_chunk_root_level(disk_super);
	ret = load_super_root(chunk_root, btrfs_super_chunk_root(disk_super),
			      generation, level);
	if (ret) {
		btrfs_err(fs_info, "failed to read chunk root");
		goto fail_tree_roots;
	}

	read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid,
			   offsetof(struct btrfs_header, chunk_tree_uuid),
			   BTRFS_UUID_SIZE);

	ret = btrfs_read_chunk_tree(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to read chunk tree: %d", ret);
		goto fail_tree_roots;
	}

	/*
	 * At this point we know all the devices that make this filesystem,
	 * including the seed devices but we don't know yet if the replace
	 * target is required. So free devices that are not part of this
	 * filesystem but skip the replace target device which is checked
	 * below in btrfs_init_dev_replace().
	 */
	btrfs_free_extra_devids(fs_devices);
	if (!fs_devices->latest_dev->bdev) {
		btrfs_err(fs_info, "failed to read devices");
		goto fail_tree_roots;
	}

	ret = init_tree_roots(fs_info);
	if (ret)
		goto fail_tree_roots;

	/*
	 * Get zone type information of zoned block devices. This will also
	 * handle emulation of a zoned filesystem if a regular device has the
	 * zoned incompat feature flag set.
	 */
	ret = btrfs_get_dev_zone_info_all_devices(fs_info);
	if (ret) {
		btrfs_err(fs_info,
			  "zoned: failed to read device zone info: %d",
			  ret);
		goto fail_block_groups;
	}

	/*
	 * If we have a uuid root and we're not being told to rescan we need to
	 * check the generation here so we can set the
	 * BTRFS_FS_UPDATE_UUID_TREE_GEN bit.  Otherwise we could commit the
	 * transaction during a balance or the log replay without updating the
	 * uuid generation, and then if we crash we would rescan the uuid tree,
	 * even though it was perfectly fine.
	 */
	if (fs_info->uuid_root && !btrfs_test_opt(fs_info, RESCAN_UUID_TREE) &&
	    fs_info->generation == btrfs_super_uuid_tree_generation(disk_super))
		set_bit(BTRFS_FS_UPDATE_UUID_TREE_GEN, &fs_info->flags);

	ret = btrfs_verify_dev_extents(fs_info);
	if (ret) {
		btrfs_err(fs_info,
			  "failed to verify dev extents against chunks: %d",
			  ret);
		goto fail_block_groups;
	}
	ret = btrfs_recover_balance(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to recover balance: %d", ret);
		goto fail_block_groups;
	}

	ret = btrfs_init_dev_stats(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to init dev_stats: %d", ret);
		goto fail_block_groups;
	}

	ret = btrfs_init_dev_replace(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to init dev_replace: %d", ret);
		goto fail_block_groups;
	}

	ret = btrfs_check_zoned_mode(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to initialize zoned mode: %d",
			  ret);
		goto fail_block_groups;
	}

	ret = btrfs_sysfs_add_fsid(fs_devices);
	if (ret) {
		btrfs_err(fs_info, "failed to init sysfs fsid interface: %d",
				ret);
		goto fail_block_groups;
	}

	ret = btrfs_sysfs_add_mounted(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to init sysfs interface: %d", ret);
		goto fail_fsdev_sysfs;
	}

	ret = btrfs_init_space_info(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to initialize space info: %d", ret);
		goto fail_sysfs;
	}

	ret = btrfs_read_block_groups(fs_info);
	if (ret) {
		btrfs_err(fs_info, "failed to read block groups: %d", ret);
		goto fail_sysfs;
	}

	btrfs_free_zone_cache(fs_info);

	if (!sb_rdonly(sb) && fs_info->fs_devices->missing_devices &&
	    !btrfs_check_rw_degradable(fs_info, NULL)) {
		btrfs_warn(fs_info,
		"writable mount is not allowed due to too many missing devices");
		goto fail_sysfs;
	}

	fs_info->cleaner_kthread = kthread_run(cleaner_kthread, fs_info,
					       "btrfs-cleaner");
	if (IS_ERR(fs_info->cleaner_kthread))
		goto fail_sysfs;

	fs_info->transaction_kthread = kthread_run(transaction_kthread,
						   tree_root,
						   "btrfs-transaction");
	if (IS_ERR(fs_info->transaction_kthread))
		goto fail_cleaner;

	if (!btrfs_test_opt(fs_info, NOSSD) &&
	    !fs_info->fs_devices->rotating) {
		btrfs_set_and_info(fs_info, SSD, "enabling ssd optimizations");
	}

	/*
	 * Mount does not set all options immediately, we can do it now and do
	 * not have to wait for transaction commit
	 */
	btrfs_apply_pending_changes(fs_info);

#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	if (btrfs_test_opt(fs_info, CHECK_INTEGRITY)) {
		ret = btrfsic_mount(fs_info, fs_devices,
				    btrfs_test_opt(fs_info,
					CHECK_INTEGRITY_DATA) ? 1 : 0,
				    fs_info->check_integrity_print_mask);
		if (ret)
			btrfs_warn(fs_info,
				"failed to initialize integrity check module: %d",
				ret);
	}
#endif
	ret = btrfs_read_qgroup_config(fs_info);
	if (ret)
		goto fail_trans_kthread;

	if (btrfs_build_ref_tree(fs_info))
		btrfs_err(fs_info, "couldn't build ref tree");

	/* do not make disk changes in broken FS or nologreplay is given */
	if (btrfs_super_log_root(disk_super) != 0 &&
	    !btrfs_test_opt(fs_info, NOLOGREPLAY)) {
		btrfs_info(fs_info, "start tree-log replay");
		ret = btrfs_replay_log(fs_info, fs_devices);
		if (ret) {
			err = ret;
			goto fail_qgroup;
		}
	}

	fs_info->fs_root = btrfs_get_fs_root(fs_info, BTRFS_FS_TREE_OBJECTID, true);
	if (IS_ERR(fs_info->fs_root)) {
		err = PTR_ERR(fs_info->fs_root);
		btrfs_warn(fs_info, "failed to read fs tree: %d", err);
		fs_info->fs_root = NULL;
		goto fail_qgroup;
	}

	if (sb_rdonly(sb))
		goto clear_oneshot;

	ret = btrfs_start_pre_rw_mount(fs_info);
	if (ret) {
		close_ctree(fs_info);
		return ret;
	}
	btrfs_discard_resume(fs_info);

	if (fs_info->uuid_root &&
	    (btrfs_test_opt(fs_info, RESCAN_UUID_TREE) ||
	     fs_info->generation != btrfs_super_uuid_tree_generation(disk_super))) {
		btrfs_info(fs_info, "checking UUID tree");
		ret = btrfs_check_uuid_tree(fs_info);
		if (ret) {
			btrfs_warn(fs_info,
				"failed to check the UUID tree: %d", ret);
			close_ctree(fs_info);
			return ret;
		}
	}

	set_bit(BTRFS_FS_OPEN, &fs_info->flags);

	/* Kick the cleaner thread so it'll start deleting snapshots. */
	if (test_bit(BTRFS_FS_UNFINISHED_DROPS, &fs_info->flags))
		wake_up_process(fs_info->cleaner_kthread);

clear_oneshot:
	btrfs_clear_oneshot_options(fs_info);
	return 0;

fail_qgroup:
	btrfs_free_qgroup_config(fs_info);
fail_trans_kthread:
	kthread_stop(fs_info->transaction_kthread);
	btrfs_cleanup_transaction(fs_info);
	btrfs_free_fs_roots(fs_info);
fail_cleaner:
	kthread_stop(fs_info->cleaner_kthread);

	/*
	 * make sure we're done with the btree inode before we stop our
	 * kthreads
	 */
	filemap_write_and_wait(fs_info->btree_inode->i_mapping);

fail_sysfs:
	btrfs_sysfs_remove_mounted(fs_info);

fail_fsdev_sysfs:
	btrfs_sysfs_remove_fsid(fs_info->fs_devices);

fail_block_groups:
	btrfs_put_block_group_cache(fs_info);

fail_tree_roots:
	if (fs_info->data_reloc_root)
		btrfs_drop_and_free_fs_root(fs_info, fs_info->data_reloc_root);
	free_root_pointers(fs_info, true);
	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);

fail_sb_buffer:
	btrfs_stop_all_workers(fs_info);
	btrfs_free_block_groups(fs_info);
fail_alloc:
	btrfs_mapping_tree_free(&fs_info->mapping_tree);

	iput(fs_info->btree_inode);
fail:
	btrfs_close_devices(fs_info->fs_devices);
	return err;
}
ALLOW_ERROR_INJECTION(open_ctree, ERRNO);

static void btrfs_end_super_write(struct bio *bio)
{
	struct btrfs_device *device = bio->bi_private;
	struct bio_vec *bvec;
	struct bvec_iter_all iter_all;
	struct page *page;

	bio_for_each_segment_all(bvec, bio, iter_all) {
		page = bvec->bv_page;

		if (bio->bi_status) {
			btrfs_warn_rl_in_rcu(device->fs_info,
				"lost page write due to IO error on %s (%d)",
				rcu_str_deref(device->name),
				blk_status_to_errno(bio->bi_status));
			ClearPageUptodate(page);
			SetPageError(page);
			btrfs_dev_stat_inc_and_print(device,
						     BTRFS_DEV_STAT_WRITE_ERRS);
		} else {
			SetPageUptodate(page);
		}

		put_page(page);
		unlock_page(page);
	}

	bio_put(bio);
}

struct btrfs_super_block *btrfs_read_dev_one_super(struct block_device *bdev,
						   int copy_num)
{
	struct btrfs_super_block *super;
	struct page *page;
	u64 bytenr, bytenr_orig;
	struct address_space *mapping = bdev->bd_inode->i_mapping;
	int ret;

	bytenr_orig = btrfs_sb_offset(copy_num);
	ret = btrfs_sb_log_location_bdev(bdev, copy_num, READ, &bytenr);
	if (ret == -ENOENT)
		return ERR_PTR(-EINVAL);
	else if (ret)
		return ERR_PTR(ret);

	if (bytenr + BTRFS_SUPER_INFO_SIZE >= bdev_nr_bytes(bdev))
		return ERR_PTR(-EINVAL);

	page = read_cache_page_gfp(mapping, bytenr >> PAGE_SHIFT, GFP_NOFS);
	if (IS_ERR(page))
		return ERR_CAST(page);

	super = page_address(page);
	if (btrfs_super_magic(super) != BTRFS_MAGIC) {
		btrfs_release_disk_super(super);
		return ERR_PTR(-ENODATA);
	}

	if (btrfs_super_bytenr(super) != bytenr_orig) {
		btrfs_release_disk_super(super);
		return ERR_PTR(-EINVAL);
	}

	return super;
}


struct btrfs_super_block *btrfs_read_dev_super(struct block_device *bdev)
{
	struct btrfs_super_block *super, *latest = NULL;
	int i;
	u64 transid = 0;

	/* we would like to check all the supers, but that would make
	 * a btrfs mount succeed after a mkfs from a different FS.
	 * So, we need to add a special mount option to scan for
	 * later supers, using BTRFS_SUPER_MIRROR_MAX instead
	 */
	for (i = 0; i < 1; i++) {
		super = btrfs_read_dev_one_super(bdev, i);
		if (IS_ERR(super))
			continue;

		if (!latest || btrfs_super_generation(super) > transid) {
			if (latest)
				btrfs_release_disk_super(super);

			latest = super;
			transid = btrfs_super_generation(super);
		}
	}

	return super;
}

/*
 * Write superblock @sb to the @device. Do not wait for completion, all the
 * pages we use for writing are locked.
 *
 * Write @max_mirrors copies of the superblock, where 0 means default that fit
 * the expected device size at commit time. Note that max_mirrors must be
 * same for write and wait phases.
 *
 * Return number of errors when page is not found or submission fails.
 */
static int write_dev_supers(struct btrfs_device *device,
			    struct btrfs_super_block *sb, int max_mirrors)
{
	struct btrfs_fs_info *fs_info = device->fs_info;
	struct address_space *mapping = device->bdev->bd_inode->i_mapping;
	SHASH_DESC_ON_STACK(shash, fs_info->csum_shash);
	int i;
	int errors = 0;
	int ret;
	u64 bytenr, bytenr_orig;

	if (max_mirrors == 0)
		max_mirrors = BTRFS_SUPER_MIRROR_MAX;

	shash->tfm = fs_info->csum_shash;

	for (i = 0; i < max_mirrors; i++) {
		struct page *page;
		struct bio *bio;
		struct btrfs_super_block *disk_super;

		bytenr_orig = btrfs_sb_offset(i);
		ret = btrfs_sb_log_location(device, i, WRITE, &bytenr);
		if (ret == -ENOENT) {
			continue;
		} else if (ret < 0) {
			btrfs_err(device->fs_info,
				"couldn't get super block location for mirror %d",
				i);
			errors++;
			continue;
		}
		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
		    device->commit_total_bytes)
			break;

		btrfs_set_super_bytenr(sb, bytenr_orig);

		crypto_shash_digest(shash, (const char *)sb + BTRFS_CSUM_SIZE,
				    BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE,
				    sb->csum);

		page = find_or_create_page(mapping, bytenr >> PAGE_SHIFT,
					   GFP_NOFS);
		if (!page) {
			btrfs_err(device->fs_info,
			    "couldn't get super block page for bytenr %llu",
			    bytenr);
			errors++;
			continue;
		}

		/* Bump the refcount for wait_dev_supers() */
		get_page(page);

		disk_super = page_address(page);
		memcpy(disk_super, sb, BTRFS_SUPER_INFO_SIZE);

		/*
		 * Directly use bios here instead of relying on the page cache
		 * to do I/O, so we don't lose the ability to do integrity
		 * checking.
		 */
		bio = bio_alloc(device->bdev, 1,
				REQ_OP_WRITE | REQ_SYNC | REQ_META | REQ_PRIO,
				GFP_NOFS);
		bio->bi_iter.bi_sector = bytenr >> SECTOR_SHIFT;
		bio->bi_private = device;
		bio->bi_end_io = btrfs_end_super_write;
		__bio_add_page(bio, page, BTRFS_SUPER_INFO_SIZE,
			       offset_in_page(bytenr));

		/*
		 * We FUA only the first super block.  The others we allow to
		 * go down lazy and there's a short window where the on-disk
		 * copies might still contain the older version.
		 */
		if (i == 0 && !btrfs_test_opt(device->fs_info, NOBARRIER))
			bio->bi_opf |= REQ_FUA;

		btrfsic_check_bio(bio);
		submit_bio(bio);

		if (btrfs_advance_sb_log(device, i))
			errors++;
	}
	return errors < i ? 0 : -1;
}

/*
 * Wait for write completion of superblocks done by write_dev_supers,
 * @max_mirrors same for write and wait phases.
 *
 * Return number of errors when page is not found or not marked up to
 * date.
 */
static int wait_dev_supers(struct btrfs_device *device, int max_mirrors)
{
	int i;
	int errors = 0;
	bool primary_failed = false;
	int ret;
	u64 bytenr;

	if (max_mirrors == 0)
		max_mirrors = BTRFS_SUPER_MIRROR_MAX;

	for (i = 0; i < max_mirrors; i++) {
		struct page *page;

		ret = btrfs_sb_log_location(device, i, READ, &bytenr);
		if (ret == -ENOENT) {
			break;
		} else if (ret < 0) {
			errors++;
			if (i == 0)
				primary_failed = true;
			continue;
		}
		if (bytenr + BTRFS_SUPER_INFO_SIZE >=
		    device->commit_total_bytes)
			break;

		page = find_get_page(device->bdev->bd_inode->i_mapping,
				     bytenr >> PAGE_SHIFT);
		if (!page) {
			errors++;
			if (i == 0)
				primary_failed = true;
			continue;
		}
		/* Page is submitted locked and unlocked once the IO completes */
		wait_on_page_locked(page);
		if (PageError(page)) {
			errors++;
			if (i == 0)
				primary_failed = true;
		}

		/* Drop our reference */
		put_page(page);

		/* Drop the reference from the writing run */
		put_page(page);
	}

	/* log error, force error return */
	if (primary_failed) {
		btrfs_err(device->fs_info, "error writing primary super block to device %llu",
			  device->devid);
		return -1;
	}

	return errors < i ? 0 : -1;
}

/*
 * endio for the write_dev_flush, this will wake anyone waiting
 * for the barrier when it is done
 */
static void btrfs_end_empty_barrier(struct bio *bio)
{
	bio_uninit(bio);
	complete(bio->bi_private);
}

/*
 * Submit a flush request to the device if it supports it. Error handling is
 * done in the waiting counterpart.
 */
static void write_dev_flush(struct btrfs_device *device)
{
	struct bio *bio = &device->flush_bio;

#ifndef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	/*
	 * When a disk has write caching disabled, we skip submission of a bio
	 * with flush and sync requests before writing the superblock, since
	 * it's not needed. However when the integrity checker is enabled, this
	 * results in reports that there are metadata blocks referred by a
	 * superblock that were not properly flushed. So don't skip the bio
	 * submission only when the integrity checker is enabled for the sake
	 * of simplicity, since this is a debug tool and not meant for use in
	 * non-debug builds.
	 */
	if (!bdev_write_cache(device->bdev))
		return;
#endif

	bio_init(bio, device->bdev, NULL, 0,
		 REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH);
	bio->bi_end_io = btrfs_end_empty_barrier;
	init_completion(&device->flush_wait);
	bio->bi_private = &device->flush_wait;

	btrfsic_check_bio(bio);
	submit_bio(bio);
	set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state);
}

/*
 * If the flush bio has been submitted by write_dev_flush, wait for it.
 */
static blk_status_t wait_dev_flush(struct btrfs_device *device)
{
	struct bio *bio = &device->flush_bio;

	if (!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state))
		return BLK_STS_OK;

	clear_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state);
	wait_for_completion_io(&device->flush_wait);

	return bio->bi_status;
}

static int check_barrier_error(struct btrfs_fs_info *fs_info)
{
	if (!btrfs_check_rw_degradable(fs_info, NULL))
		return -EIO;
	return 0;
}

/*
 * send an empty flush down to each device in parallel,
 * then wait for them
 */
static int barrier_all_devices(struct btrfs_fs_info *info)
{
	struct list_head *head;
	struct btrfs_device *dev;
	int errors_wait = 0;
	blk_status_t ret;

	lockdep_assert_held(&info->fs_devices->device_list_mutex);
	/* send down all the barriers */
	head = &info->fs_devices->devices;
	list_for_each_entry(dev, head, dev_list) {
		if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state))
			continue;
		if (!dev->bdev)
			continue;
		if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
		    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))
			continue;

		write_dev_flush(dev);
		dev->last_flush_error = BLK_STS_OK;
	}

	/* wait for all the barriers */
	list_for_each_entry(dev, head, dev_list) {
		if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state))
			continue;
		if (!dev->bdev) {
			errors_wait++;
			continue;
		}
		if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
		    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))
			continue;

		ret = wait_dev_flush(dev);
		if (ret) {
			dev->last_flush_error = ret;
			btrfs_dev_stat_inc_and_print(dev,
					BTRFS_DEV_STAT_FLUSH_ERRS);
			errors_wait++;
		}
	}

	if (errors_wait) {
		/*
		 * At some point we need the status of all disks
		 * to arrive at the volume status. So error checking
		 * is being pushed to a separate loop.
		 */
		return check_barrier_error(info);
	}
	return 0;
}

int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags)
{
	int raid_type;
	int min_tolerated = INT_MAX;

	if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0 ||
	    (flags & BTRFS_AVAIL_ALLOC_BIT_SINGLE))
		min_tolerated = min_t(int, min_tolerated,
				    btrfs_raid_array[BTRFS_RAID_SINGLE].
				    tolerated_failures);

	for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
		if (raid_type == BTRFS_RAID_SINGLE)
			continue;
		if (!(flags & btrfs_raid_array[raid_type].bg_flag))
			continue;
		min_tolerated = min_t(int, min_tolerated,
				    btrfs_raid_array[raid_type].
				    tolerated_failures);
	}

	if (min_tolerated == INT_MAX) {
		pr_warn("BTRFS: unknown raid flag: %llu", flags);
		min_tolerated = 0;
	}

	return min_tolerated;
}

int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
{
	struct list_head *head;
	struct btrfs_device *dev;
	struct btrfs_super_block *sb;
	struct btrfs_dev_item *dev_item;
	int ret;
	int do_barriers;
	int max_errors;
	int total_errors = 0;
	u64 flags;

	do_barriers = !btrfs_test_opt(fs_info, NOBARRIER);

	/*
	 * max_mirrors == 0 indicates we're from commit_transaction,
	 * not from fsync where the tree roots in fs_info have not
	 * been consistent on disk.
	 */
	if (max_mirrors == 0)
		backup_super_roots(fs_info);

	sb = fs_info->super_for_commit;
	dev_item = &sb->dev_item;

	mutex_lock(&fs_info->fs_devices->device_list_mutex);
	head = &fs_info->fs_devices->devices;
	max_errors = btrfs_super_num_devices(fs_info->super_copy) - 1;

	if (do_barriers) {
		ret = barrier_all_devices(fs_info);
		if (ret) {
			mutex_unlock(
				&fs_info->fs_devices->device_list_mutex);
			btrfs_handle_fs_error(fs_info, ret,
					      "errors while submitting device barriers.");
			return ret;
		}
	}

	list_for_each_entry(dev, head, dev_list) {
		if (!dev->bdev) {
			total_errors++;
			continue;
		}
		if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
		    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))
			continue;

		btrfs_set_stack_device_generation(dev_item, 0);
		btrfs_set_stack_device_type(dev_item, dev->type);
		btrfs_set_stack_device_id(dev_item, dev->devid);
		btrfs_set_stack_device_total_bytes(dev_item,
						   dev->commit_total_bytes);
		btrfs_set_stack_device_bytes_used(dev_item,
						  dev->commit_bytes_used);
		btrfs_set_stack_device_io_align(dev_item, dev->io_align);
		btrfs_set_stack_device_io_width(dev_item, dev->io_width);
		btrfs_set_stack_device_sector_size(dev_item, dev->sector_size);
		memcpy(dev_item->uuid, dev->uuid, BTRFS_UUID_SIZE);
		memcpy(dev_item->fsid, dev->fs_devices->metadata_uuid,
		       BTRFS_FSID_SIZE);

		flags = btrfs_super_flags(sb);
		btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN);

		ret = btrfs_validate_write_super(fs_info, sb);
		if (ret < 0) {
			mutex_unlock(&fs_info->fs_devices->device_list_mutex);
			btrfs_handle_fs_error(fs_info, -EUCLEAN,
				"unexpected superblock corruption detected");
			return -EUCLEAN;
		}

		ret = write_dev_supers(dev, sb, max_mirrors);
		if (ret)
			total_errors++;
	}
	if (total_errors > max_errors) {
		btrfs_err(fs_info, "%d errors while writing supers",
			  total_errors);
		mutex_unlock(&fs_info->fs_devices->device_list_mutex);

		/* FUA is masked off if unsupported and can't be the reason */
		btrfs_handle_fs_error(fs_info, -EIO,
				      "%d errors while writing supers",
				      total_errors);
		return -EIO;
	}

	total_errors = 0;
	list_for_each_entry(dev, head, dev_list) {
		if (!dev->bdev)
			continue;
		if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) ||
		    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state))
			continue;

		ret = wait_dev_supers(dev, max_mirrors);
		if (ret)
			total_errors++;
	}
	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
	if (total_errors > max_errors) {
		btrfs_handle_fs_error(fs_info, -EIO,
				      "%d errors while writing supers",
				      total_errors);
		return -EIO;
	}
	return 0;
}

/* Drop a fs root from the radix tree and free it. */
void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
				  struct btrfs_root *root)
{
	bool drop_ref = false;

	spin_lock(&fs_info->fs_roots_lock);
	xa_erase(&fs_info->fs_roots, (unsigned long)root->root_key.objectid);
	if (test_and_clear_bit(BTRFS_ROOT_REGISTERED, &root->state))
		drop_ref = true;
	spin_unlock(&fs_info->fs_roots_lock);

	if (BTRFS_FS_ERROR(fs_info)) {
		ASSERT(root->log_root == NULL);
		if (root->reloc_root) {
			btrfs_put_root(root->reloc_root);
			root->reloc_root = NULL;
		}
	}

	if (drop_ref)
		btrfs_put_root(root);
}

int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *roots[8];
	unsigned long index = 0;
	int i;
	int err = 0;
	int grabbed;

	while (1) {
		struct btrfs_root *root;

		spin_lock(&fs_info->fs_roots_lock);
		if (!xa_find(&fs_info->fs_roots, &index, ULONG_MAX, XA_PRESENT)) {
			spin_unlock(&fs_info->fs_roots_lock);
			return err;
		}

		grabbed = 0;
		xa_for_each_start(&fs_info->fs_roots, index, root, index) {
			/* Avoid grabbing roots in dead_roots */
			if (btrfs_root_refs(&root->root_item) > 0)
				roots[grabbed++] = btrfs_grab_root(root);
			if (grabbed >= ARRAY_SIZE(roots))
				break;
		}
		spin_unlock(&fs_info->fs_roots_lock);

		for (i = 0; i < grabbed; i++) {
			if (!roots[i])
				continue;
			index = roots[i]->root_key.objectid;
			err = btrfs_orphan_cleanup(roots[i]);
			if (err)
				goto out;
			btrfs_put_root(roots[i]);
		}
		index++;
	}

out:
	/* Release the roots that remain uncleaned due to error */
	for (; i < grabbed; i++) {
		if (roots[i])
			btrfs_put_root(roots[i]);
	}
	return err;
}

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

	mutex_lock(&fs_info->cleaner_mutex);
	btrfs_run_delayed_iputs(fs_info);
	mutex_unlock(&fs_info->cleaner_mutex);
	wake_up_process(fs_info->cleaner_kthread);

	/* wait until ongoing cleanup work done */
	down_write(&fs_info->cleanup_work_sem);
	up_write(&fs_info->cleanup_work_sem);

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

static void warn_about_uncommitted_trans(struct btrfs_fs_info *fs_info)
{
	struct btrfs_transaction *trans;
	struct btrfs_transaction *tmp;
	bool found = false;

	if (list_empty(&fs_info->trans_list))
		return;

	/*
	 * This function is only called at the very end of close_ctree(),
	 * thus no other running transaction, no need to take trans_lock.
	 */
	ASSERT(test_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags));
	list_for_each_entry_safe(trans, tmp, &fs_info->trans_list, list) {
		struct extent_state *cached = NULL;
		u64 dirty_bytes = 0;
		u64 cur = 0;
		u64 found_start;
		u64 found_end;

		found = true;
		while (!find_first_extent_bit(&trans->dirty_pages, cur,
			&found_start, &found_end, EXTENT_DIRTY, &cached)) {
			dirty_bytes += found_end + 1 - found_start;
			cur = found_end + 1;
		}
		btrfs_warn(fs_info,
	"transaction %llu (with %llu dirty metadata bytes) is not committed",
			   trans->transid, dirty_bytes);
		btrfs_cleanup_one_transaction(trans, fs_info);

		if (trans == fs_info->running_transaction)
			fs_info->running_transaction = NULL;
		list_del_init(&trans->list);

		btrfs_put_transaction(trans);
		trace_btrfs_transaction_commit(fs_info);
	}
	ASSERT(!found);
}

void __cold close_ctree(struct btrfs_fs_info *fs_info)
{
	int ret;

	set_bit(BTRFS_FS_CLOSING_START, &fs_info->flags);
	/*
	 * We don't want the cleaner to start new transactions, add more delayed
	 * iputs, etc. while we're closing. We can't use kthread_stop() yet
	 * because that frees the task_struct, and the transaction kthread might
	 * still try to wake up the cleaner.
	 */
	kthread_park(fs_info->cleaner_kthread);

	/*
	 * If we had UNFINISHED_DROPS we could still be processing them, so
	 * clear that bit and wake up relocation so it can stop.
	 */
	btrfs_wake_unfinished_drop(fs_info);

	/* wait for the qgroup rescan worker to stop */
	btrfs_qgroup_wait_for_completion(fs_info, false);

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

	/* pause restriper - we want to resume on mount */
	btrfs_pause_balance(fs_info);

	btrfs_dev_replace_suspend_for_unmount(fs_info);

	btrfs_scrub_cancel(fs_info);

	/* wait for any defraggers to finish */
	wait_event(fs_info->transaction_wait,
		   (atomic_read(&fs_info->defrag_running) == 0));

	/* clear out the rbtree of defraggable inodes */
	btrfs_cleanup_defrag_inodes(fs_info);

	cancel_work_sync(&fs_info->async_reclaim_work);
	cancel_work_sync(&fs_info->async_data_reclaim_work);
	cancel_work_sync(&fs_info->preempt_reclaim_work);

	cancel_work_sync(&fs_info->reclaim_bgs_work);

	/* Cancel or finish ongoing discard work */
	btrfs_discard_cleanup(fs_info);

	if (!sb_rdonly(fs_info->sb)) {
		/*
		 * The cleaner kthread is stopped, so do one final pass over
		 * unused block groups.
		 */
		btrfs_delete_unused_bgs(fs_info);

		/*
		 * There might be existing delayed inode workers still running
		 * and holding an empty delayed inode item. We must wait for
		 * them to complete first because they can create a transaction.
		 * This happens when someone calls btrfs_balance_delayed_items()
		 * and then a transaction commit runs the same delayed nodes
		 * before any delayed worker has done something with the nodes.
		 * We must wait for any worker here and not at transaction
		 * commit time since that could cause a deadlock.
		 * This is a very rare case.
		 */
		btrfs_flush_workqueue(fs_info->delayed_workers);

		ret = btrfs_commit_super(fs_info);
		if (ret)
			btrfs_err(fs_info, "commit super ret %d", ret);
	}

	if (BTRFS_FS_ERROR(fs_info))
		btrfs_error_commit_super(fs_info);

	kthread_stop(fs_info->transaction_kthread);
	kthread_stop(fs_info->cleaner_kthread);

	ASSERT(list_empty(&fs_info->delayed_iputs));
	set_bit(BTRFS_FS_CLOSING_DONE, &fs_info->flags);

	if (btrfs_check_quota_leak(fs_info)) {
		WARN_ON(IS_ENABLED(CONFIG_BTRFS_DEBUG));
		btrfs_err(fs_info, "qgroup reserved space leaked");
	}

	btrfs_free_qgroup_config(fs_info);
	ASSERT(list_empty(&fs_info->delalloc_roots));

	if (percpu_counter_sum(&fs_info->delalloc_bytes)) {
		btrfs_info(fs_info, "at unmount delalloc count %lld",
		       percpu_counter_sum(&fs_info->delalloc_bytes));
	}

	if (percpu_counter_sum(&fs_info->ordered_bytes))
		btrfs_info(fs_info, "at unmount dio bytes count %lld",
			   percpu_counter_sum(&fs_info->ordered_bytes));

	btrfs_sysfs_remove_mounted(fs_info);
	btrfs_sysfs_remove_fsid(fs_info->fs_devices);

	btrfs_put_block_group_cache(fs_info);

	/*
	 * we must make sure there is not any read request to
	 * submit after we stopping all workers.
	 */
	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
	btrfs_stop_all_workers(fs_info);

	/* We shouldn't have any transaction open at this point */
	warn_about_uncommitted_trans(fs_info);

	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
	free_root_pointers(fs_info, true);
	btrfs_free_fs_roots(fs_info);

	/*
	 * We must free the block groups after dropping the fs_roots as we could
	 * have had an IO error and have left over tree log blocks that aren't
	 * cleaned up until the fs roots are freed.  This makes the block group
	 * accounting appear to be wrong because there's pending reserved bytes,
	 * so make sure we do the block group cleanup afterwards.
	 */
	btrfs_free_block_groups(fs_info);

	iput(fs_info->btree_inode);

#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	if (btrfs_test_opt(fs_info, CHECK_INTEGRITY))
		btrfsic_unmount(fs_info->fs_devices);
#endif

	btrfs_mapping_tree_free(&fs_info->mapping_tree);
	btrfs_close_devices(fs_info->fs_devices);
}

int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
			  int atomic)
{
	int ret;
	struct inode *btree_inode = buf->pages[0]->mapping->host;

	ret = extent_buffer_uptodate(buf);
	if (!ret)
		return ret;

	ret = verify_parent_transid(&BTRFS_I(btree_inode)->io_tree, buf,
				    parent_transid, atomic);
	if (ret == -EAGAIN)
		return ret;
	return !ret;
}

void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
{
	struct btrfs_fs_info *fs_info = buf->fs_info;
	u64 transid = btrfs_header_generation(buf);
	int was_dirty;

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
	/*
	 * This is a fast path so only do this check if we have sanity tests
	 * enabled.  Normal people shouldn't be using unmapped buffers as dirty
	 * outside of the sanity tests.
	 */
	if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags)))
		return;
#endif
	btrfs_assert_tree_write_locked(buf);
	if (transid != fs_info->generation)
		WARN(1, KERN_CRIT "btrfs transid mismatch buffer %llu, found %llu running %llu\n",
			buf->start, transid, fs_info->generation);
	was_dirty = set_extent_buffer_dirty(buf);
	if (!was_dirty)
		percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
					 buf->len,
					 fs_info->dirty_metadata_batch);
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
	/*
	 * Since btrfs_mark_buffer_dirty() can be called with item pointer set
	 * but item data not updated.
	 * So here we should only check item pointers, not item data.
	 */
	if (btrfs_header_level(buf) == 0 &&
	    btrfs_check_leaf_relaxed(buf)) {
		btrfs_print_leaf(buf);
		ASSERT(0);
	}
#endif
}

static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info,
					int flush_delayed)
{
	/*
	 * looks as though older kernels can get into trouble with
	 * this code, they end up stuck in balance_dirty_pages forever
	 */
	int ret;

	if (current->flags & PF_MEMALLOC)
		return;

	if (flush_delayed)
		btrfs_balance_delayed_items(fs_info);

	ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
				     BTRFS_DIRTY_METADATA_THRESH,
				     fs_info->dirty_metadata_batch);
	if (ret > 0) {
		balance_dirty_pages_ratelimited(fs_info->btree_inode->i_mapping);
	}
}

void btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info)
{
	__btrfs_btree_balance_dirty(fs_info, 1);
}

void btrfs_btree_balance_dirty_nodelay(struct btrfs_fs_info *fs_info)
{
	__btrfs_btree_balance_dirty(fs_info, 0);
}

static void btrfs_error_commit_super(struct btrfs_fs_info *fs_info)
{
	/* cleanup FS via transaction */
	btrfs_cleanup_transaction(fs_info);

	mutex_lock(&fs_info->cleaner_mutex);
	btrfs_run_delayed_iputs(fs_info);
	mutex_unlock(&fs_info->cleaner_mutex);

	down_write(&fs_info->cleanup_work_sem);
	up_write(&fs_info->cleanup_work_sem);
}

static void btrfs_drop_all_logs(struct btrfs_fs_info *fs_info)
{
	unsigned long index = 0;
	int grabbed = 0;
	struct btrfs_root *roots[8];

	spin_lock(&fs_info->fs_roots_lock);
	while ((grabbed = xa_extract(&fs_info->fs_roots, (void **)roots, index,
				     ULONG_MAX, 8, XA_PRESENT))) {
		for (int i = 0; i < grabbed; i++)
			roots[i] = btrfs_grab_root(roots[i]);
		spin_unlock(&fs_info->fs_roots_lock);

		for (int i = 0; i < grabbed; i++) {
			if (!roots[i])
				continue;
			index = roots[i]->root_key.objectid;
			btrfs_free_log(NULL, roots[i]);
			btrfs_put_root(roots[i]);
		}
		index++;
		spin_lock(&fs_info->fs_roots_lock);
	}
	spin_unlock(&fs_info->fs_roots_lock);
	btrfs_free_log_root_tree(NULL, fs_info);
}

static void btrfs_destroy_ordered_extents(struct btrfs_root *root)
{
	struct btrfs_ordered_extent *ordered;

	spin_lock(&root->ordered_extent_lock);
	/*
	 * This will just short circuit the ordered completion stuff which will
	 * make sure the ordered extent gets properly cleaned up.
	 */
	list_for_each_entry(ordered, &root->ordered_extents,
			    root_extent_list)
		set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
	spin_unlock(&root->ordered_extent_lock);
}

static void btrfs_destroy_all_ordered_extents(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;
	struct list_head splice;

	INIT_LIST_HEAD(&splice);

	spin_lock(&fs_info->ordered_root_lock);
	list_splice_init(&fs_info->ordered_roots, &splice);
	while (!list_empty(&splice)) {
		root = list_first_entry(&splice, struct btrfs_root,
					ordered_root);
		list_move_tail(&root->ordered_root,
			       &fs_info->ordered_roots);

		spin_unlock(&fs_info->ordered_root_lock);
		btrfs_destroy_ordered_extents(root);

		cond_resched();
		spin_lock(&fs_info->ordered_root_lock);
	}
	spin_unlock(&fs_info->ordered_root_lock);

	/*
	 * We need this here because if we've been flipped read-only we won't
	 * get sync() from the umount, so we need to make sure any ordered
	 * extents that haven't had their dirty pages IO start writeout yet
	 * actually get run and error out properly.
	 */
	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
}

static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
				      struct btrfs_fs_info *fs_info)
{
	struct rb_node *node;
	struct btrfs_delayed_ref_root *delayed_refs;
	struct btrfs_delayed_ref_node *ref;
	int ret = 0;

	delayed_refs = &trans->delayed_refs;

	spin_lock(&delayed_refs->lock);
	if (atomic_read(&delayed_refs->num_entries) == 0) {
		spin_unlock(&delayed_refs->lock);
		btrfs_debug(fs_info, "delayed_refs has NO entry");
		return ret;
	}

	while ((node = rb_first_cached(&delayed_refs->href_root)) != NULL) {
		struct btrfs_delayed_ref_head *head;
		struct rb_node *n;
		bool pin_bytes = false;

		head = rb_entry(node, struct btrfs_delayed_ref_head,
				href_node);
		if (btrfs_delayed_ref_lock(delayed_refs, head))
			continue;

		spin_lock(&head->lock);
		while ((n = rb_first_cached(&head->ref_tree)) != NULL) {
			ref = rb_entry(n, struct btrfs_delayed_ref_node,
				       ref_node);
			ref->in_tree = 0;
			rb_erase_cached(&ref->ref_node, &head->ref_tree);
			RB_CLEAR_NODE(&ref->ref_node);
			if (!list_empty(&ref->add_list))
				list_del(&ref->add_list);
			atomic_dec(&delayed_refs->num_entries);
			btrfs_put_delayed_ref(ref);
		}
		if (head->must_insert_reserved)
			pin_bytes = true;
		btrfs_free_delayed_extent_op(head->extent_op);
		btrfs_delete_ref_head(delayed_refs, head);
		spin_unlock(&head->lock);
		spin_unlock(&delayed_refs->lock);
		mutex_unlock(&head->mutex);

		if (pin_bytes) {
			struct btrfs_block_group *cache;

			cache = btrfs_lookup_block_group(fs_info, head->bytenr);
			BUG_ON(!cache);

			spin_lock(&cache->space_info->lock);
			spin_lock(&cache->lock);
			cache->pinned += head->num_bytes;
			btrfs_space_info_update_bytes_pinned(fs_info,
				cache->space_info, head->num_bytes);
			cache->reserved -= head->num_bytes;
			cache->space_info->bytes_reserved -= head->num_bytes;
			spin_unlock(&cache->lock);
			spin_unlock(&cache->space_info->lock);

			btrfs_put_block_group(cache);

			btrfs_error_unpin_extent_range(fs_info, head->bytenr,
				head->bytenr + head->num_bytes - 1);
		}
		btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head);
		btrfs_put_delayed_ref_head(head);
		cond_resched();
		spin_lock(&delayed_refs->lock);
	}
	btrfs_qgroup_destroy_extent_records(trans);

	spin_unlock(&delayed_refs->lock);

	return ret;
}

static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root)
{
	struct btrfs_inode *btrfs_inode;
	struct list_head splice;

	INIT_LIST_HEAD(&splice);

	spin_lock(&root->delalloc_lock);
	list_splice_init(&root->delalloc_inodes, &splice);

	while (!list_empty(&splice)) {
		struct inode *inode = NULL;
		btrfs_inode = list_first_entry(&splice, struct btrfs_inode,
					       delalloc_inodes);
		__btrfs_del_delalloc_inode(root, btrfs_inode);
		spin_unlock(&root->delalloc_lock);

		/*
		 * Make sure we get a live inode and that it'll not disappear
		 * meanwhile.
		 */
		inode = igrab(&btrfs_inode->vfs_inode);
		if (inode) {
			invalidate_inode_pages2(inode->i_mapping);
			iput(inode);
		}
		spin_lock(&root->delalloc_lock);
	}
	spin_unlock(&root->delalloc_lock);
}

static void btrfs_destroy_all_delalloc_inodes(struct btrfs_fs_info *fs_info)
{
	struct btrfs_root *root;
	struct list_head splice;

	INIT_LIST_HEAD(&splice);

	spin_lock(&fs_info->delalloc_root_lock);
	list_splice_init(&fs_info->delalloc_roots, &splice);
	while (!list_empty(&splice)) {
		root = list_first_entry(&splice, struct btrfs_root,
					 delalloc_root);
		root = btrfs_grab_root(root);
		BUG_ON(!root);
		spin_unlock(&fs_info->delalloc_root_lock);

		btrfs_destroy_delalloc_inodes(root);
		btrfs_put_root(root);

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

static int btrfs_destroy_marked_extents(struct btrfs_fs_info *fs_info,
					struct extent_io_tree *dirty_pages,
					int mark)
{
	int ret;
	struct extent_buffer *eb;
	u64 start = 0;
	u64 end;

	while (1) {
		ret = find_first_extent_bit(dirty_pages, start, &start, &end,
					    mark, NULL);
		if (ret)
			break;

		clear_extent_bits(dirty_pages, start, end, mark);
		while (start <= end) {
			eb = find_extent_buffer(fs_info, start);
			start += fs_info->nodesize;
			if (!eb)
				continue;
			wait_on_extent_buffer_writeback(eb);

			if (test_and_clear_bit(EXTENT_BUFFER_DIRTY,
					       &eb->bflags))
				clear_extent_buffer_dirty(eb);
			free_extent_buffer_stale(eb);
		}
	}

	return ret;
}

static int btrfs_destroy_pinned_extent(struct btrfs_fs_info *fs_info,
				       struct extent_io_tree *unpin)
{
	u64 start;
	u64 end;
	int ret;

	while (1) {
		struct extent_state *cached_state = NULL;

		/*
		 * The btrfs_finish_extent_commit() may get the same range as
		 * ours between find_first_extent_bit and clear_extent_dirty.
		 * Hence, hold the unused_bg_unpin_mutex to avoid double unpin
		 * the same extent range.
		 */
		mutex_lock(&fs_info->unused_bg_unpin_mutex);
		ret = find_first_extent_bit(unpin, 0, &start, &end,
					    EXTENT_DIRTY, &cached_state);
		if (ret) {
			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
			break;
		}

		clear_extent_dirty(unpin, start, end, &cached_state);
		free_extent_state(cached_state);
		btrfs_error_unpin_extent_range(fs_info, start, end);
		mutex_unlock(&fs_info->unused_bg_unpin_mutex);
		cond_resched();
	}

	return 0;
}

static void btrfs_cleanup_bg_io(struct btrfs_block_group *cache)
{
	struct inode *inode;

	inode = cache->io_ctl.inode;
	if (inode) {
		invalidate_inode_pages2(inode->i_mapping);
		BTRFS_I(inode)->generation = 0;
		cache->io_ctl.inode = NULL;
		iput(inode);
	}
	ASSERT(cache->io_ctl.pages == NULL);
	btrfs_put_block_group(cache);
}

void btrfs_cleanup_dirty_bgs(struct btrfs_transaction *cur_trans,
			     struct btrfs_fs_info *fs_info)
{
	struct btrfs_block_group *cache;

	spin_lock(&cur_trans->dirty_bgs_lock);
	while (!list_empty(&cur_trans->dirty_bgs)) {
		cache = list_first_entry(&cur_trans->dirty_bgs,
					 struct btrfs_block_group,
					 dirty_list);

		if (!list_empty(&cache->io_list)) {
			spin_unlock(&cur_trans->dirty_bgs_lock);
			list_del_init(&cache->io_list);
			btrfs_cleanup_bg_io(cache);
			spin_lock(&cur_trans->dirty_bgs_lock);
		}

		list_del_init(&cache->dirty_list);
		spin_lock(&cache->lock);
		cache->disk_cache_state = BTRFS_DC_ERROR;
		spin_unlock(&cache->lock);

		spin_unlock(&cur_trans->dirty_bgs_lock);
		btrfs_put_block_group(cache);
		btrfs_delayed_refs_rsv_release(fs_info, 1);
		spin_lock(&cur_trans->dirty_bgs_lock);
	}
	spin_unlock(&cur_trans->dirty_bgs_lock);

	/*
	 * Refer to the definition of io_bgs member for details why it's safe
	 * to use it without any locking
	 */
	while (!list_empty(&cur_trans->io_bgs)) {
		cache = list_first_entry(&cur_trans->io_bgs,
					 struct btrfs_block_group,
					 io_list);

		list_del_init(&cache->io_list);
		spin_lock(&cache->lock);
		cache->disk_cache_state = BTRFS_DC_ERROR;
		spin_unlock(&cache->lock);
		btrfs_cleanup_bg_io(cache);
	}
}

void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
				   struct btrfs_fs_info *fs_info)
{
	struct btrfs_device *dev, *tmp;

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

	list_for_each_entry_safe(dev, tmp, &cur_trans->dev_update_list,
				 post_commit_list) {
		list_del_init(&dev->post_commit_list);
	}

	btrfs_destroy_delayed_refs(cur_trans, fs_info);

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

	cur_trans->state = TRANS_STATE_UNBLOCKED;
	wake_up(&fs_info->transaction_wait);

	btrfs_destroy_delayed_inodes(fs_info);

	btrfs_destroy_marked_extents(fs_info, &cur_trans->dirty_pages,
				     EXTENT_DIRTY);
	btrfs_destroy_pinned_extent(fs_info, &cur_trans->pinned_extents);

	btrfs_free_redirty_list(cur_trans);

	cur_trans->state =TRANS_STATE_COMPLETED;
	wake_up(&cur_trans->commit_wait);
}

static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
{
	struct btrfs_transaction *t;

	mutex_lock(&fs_info->transaction_kthread_mutex);

	spin_lock(&fs_info->trans_lock);
	while (!list_empty(&fs_info->trans_list)) {
		t = list_first_entry(&fs_info->trans_list,
				     struct btrfs_transaction, list);
		if (t->state >= TRANS_STATE_COMMIT_START) {
			refcount_inc(&t->use_count);
			spin_unlock(&fs_info->trans_lock);
			btrfs_wait_for_commit(fs_info, t->transid);
			btrfs_put_transaction(t);
			spin_lock(&fs_info->trans_lock);
			continue;
		}
		if (t == fs_info->running_transaction) {
			t->state = TRANS_STATE_COMMIT_DOING;
			spin_unlock(&fs_info->trans_lock);
			/*
			 * We wait for 0 num_writers since we don't hold a trans
			 * handle open currently for this transaction.
			 */
			wait_event(t->writer_wait,
				   atomic_read(&t->num_writers) == 0);
		} else {
			spin_unlock(&fs_info->trans_lock);
		}
		btrfs_cleanup_one_transaction(t, fs_info);

		spin_lock(&fs_info->trans_lock);
		if (t == fs_info->running_transaction)
			fs_info->running_transaction = NULL;
		list_del_init(&t->list);
		spin_unlock(&fs_info->trans_lock);

		btrfs_put_transaction(t);
		trace_btrfs_transaction_commit(fs_info);
		spin_lock(&fs_info->trans_lock);
	}
	spin_unlock(&fs_info->trans_lock);
	btrfs_destroy_all_ordered_extents(fs_info);
	btrfs_destroy_delayed_inodes(fs_info);
	btrfs_assert_delayed_root_empty(fs_info);
	btrfs_destroy_all_delalloc_inodes(fs_info);
	btrfs_drop_all_logs(fs_info);
	mutex_unlock(&fs_info->transaction_kthread_mutex);

	return 0;
}

int btrfs_init_root_free_objectid(struct btrfs_root *root)
{
	struct btrfs_path *path;
	int ret;
	struct extent_buffer *l;
	struct btrfs_key search_key;
	struct btrfs_key found_key;
	int slot;

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

	search_key.objectid = BTRFS_LAST_FREE_OBJECTID;
	search_key.type = -1;
	search_key.offset = (u64)-1;
	ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
	if (ret < 0)
		goto error;
	BUG_ON(ret == 0); /* Corruption */
	if (path->slots[0] > 0) {
		slot = path->slots[0] - 1;
		l = path->nodes[0];
		btrfs_item_key_to_cpu(l, &found_key, slot);
		root->free_objectid = max_t(u64, found_key.objectid + 1,
					    BTRFS_FIRST_FREE_OBJECTID);
	} else {
		root->free_objectid = BTRFS_FIRST_FREE_OBJECTID;
	}
	ret = 0;
error:
	btrfs_free_path(path);
	return ret;
}

int btrfs_get_free_objectid(struct btrfs_root *root, u64 *objectid)
{
	int ret;
	mutex_lock(&root->objectid_mutex);

	if (unlikely(root->free_objectid >= BTRFS_LAST_FREE_OBJECTID)) {
		btrfs_warn(root->fs_info,
			   "the objectid of root %llu reaches its highest value",
			   root->root_key.objectid);
		ret = -ENOSPC;
		goto out;
	}

	*objectid = root->free_objectid++;
	ret = 0;
out:
	mutex_unlock(&root->objectid_mutex);
	return ret;
}