summaryrefslogtreecommitdiff
path: root/fs/btrfs/extent-tree.c
blob: f79e477a378e7836bb3ad9739861cf0428afd1dc (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
4417
4418
4419
4420
4421
4422
4423
4424
4425
4426
4427
4428
4429
4430
4431
4432
4433
4434
4435
4436
4437
4438
4439
4440
4441
4442
4443
4444
4445
4446
4447
4448
4449
4450
4451
4452
4453
4454
4455
4456
4457
4458
4459
4460
4461
4462
4463
4464
4465
4466
4467
4468
4469
4470
4471
4472
4473
4474
4475
4476
4477
4478
4479
4480
4481
4482
4483
4484
4485
4486
4487
4488
4489
4490
4491
4492
4493
4494
4495
4496
4497
4498
4499
4500
4501
4502
4503
4504
4505
4506
4507
4508
4509
4510
4511
4512
4513
4514
4515
4516
4517
4518
4519
4520
4521
4522
4523
4524
4525
4526
4527
4528
4529
4530
4531
4532
4533
4534
4535
4536
4537
4538
4539
4540
4541
4542
4543
4544
4545
4546
4547
4548
4549
4550
4551
4552
4553
4554
4555
4556
4557
4558
4559
4560
4561
4562
4563
4564
4565
4566
4567
4568
4569
4570
4571
4572
4573
4574
4575
4576
4577
4578
4579
4580
4581
4582
4583
4584
4585
4586
4587
4588
4589
4590
4591
4592
4593
4594
4595
4596
4597
4598
4599
4600
4601
4602
4603
4604
4605
4606
4607
4608
4609
4610
4611
4612
4613
4614
4615
4616
4617
4618
4619
4620
4621
4622
4623
4624
4625
4626
4627
4628
4629
4630
4631
4632
4633
4634
4635
4636
4637
4638
4639
4640
4641
4642
4643
4644
4645
4646
4647
4648
4649
4650
4651
4652
4653
4654
4655
4656
4657
4658
4659
4660
4661
4662
4663
4664
4665
4666
4667
4668
4669
4670
4671
4672
4673
4674
4675
4676
4677
4678
4679
4680
4681
4682
4683
4684
4685
4686
4687
4688
4689
4690
4691
4692
4693
4694
4695
4696
4697
4698
4699
4700
4701
4702
4703
4704
4705
4706
4707
4708
4709
4710
4711
4712
4713
4714
4715
4716
4717
4718
4719
4720
4721
4722
4723
4724
4725
4726
4727
4728
4729
4730
4731
4732
4733
4734
4735
4736
4737
4738
4739
4740
4741
4742
4743
4744
4745
4746
4747
4748
4749
4750
4751
4752
4753
4754
4755
4756
4757
4758
4759
4760
4761
4762
4763
4764
4765
4766
4767
4768
4769
4770
4771
4772
4773
4774
4775
4776
4777
4778
4779
4780
4781
4782
4783
4784
4785
4786
4787
4788
4789
4790
4791
4792
4793
4794
4795
4796
4797
4798
4799
4800
4801
4802
4803
4804
4805
4806
4807
4808
4809
4810
4811
4812
4813
4814
4815
4816
4817
4818
4819
4820
4821
4822
4823
4824
4825
4826
4827
4828
4829
4830
4831
4832
4833
4834
4835
4836
4837
4838
4839
4840
4841
4842
4843
4844
4845
4846
4847
4848
4849
4850
4851
4852
4853
4854
4855
4856
4857
4858
4859
4860
4861
4862
4863
4864
4865
4866
4867
4868
4869
4870
4871
4872
4873
4874
4875
4876
4877
4878
4879
4880
4881
4882
4883
4884
4885
4886
4887
4888
4889
4890
4891
4892
4893
4894
4895
4896
4897
4898
4899
4900
4901
4902
4903
4904
4905
4906
4907
4908
4909
4910
4911
4912
4913
4914
4915
4916
4917
4918
4919
4920
4921
4922
4923
4924
4925
4926
4927
4928
4929
4930
4931
4932
4933
4934
4935
4936
4937
4938
4939
4940
4941
4942
4943
4944
4945
4946
4947
4948
4949
4950
4951
4952
4953
4954
4955
4956
4957
4958
4959
4960
4961
4962
4963
4964
4965
4966
4967
4968
4969
4970
4971
4972
4973
4974
4975
4976
4977
4978
4979
4980
4981
4982
4983
4984
4985
4986
4987
4988
4989
4990
4991
4992
4993
4994
4995
4996
4997
4998
4999
5000
5001
5002
5003
5004
5005
5006
5007
5008
5009
5010
5011
5012
5013
5014
5015
5016
5017
5018
5019
5020
5021
5022
5023
5024
5025
5026
5027
5028
5029
5030
5031
5032
5033
5034
5035
5036
5037
5038
5039
5040
5041
5042
5043
5044
5045
5046
5047
5048
5049
5050
5051
5052
5053
5054
5055
5056
5057
5058
5059
5060
5061
5062
5063
5064
5065
5066
5067
5068
5069
5070
5071
5072
5073
5074
5075
5076
5077
5078
5079
5080
5081
5082
5083
5084
5085
5086
5087
5088
5089
5090
5091
5092
5093
5094
5095
5096
5097
5098
5099
5100
5101
5102
5103
5104
5105
5106
5107
5108
5109
5110
5111
5112
5113
5114
5115
5116
5117
5118
5119
5120
5121
5122
5123
5124
5125
5126
5127
5128
5129
5130
5131
5132
5133
5134
5135
5136
5137
5138
5139
5140
5141
5142
5143
5144
5145
5146
5147
5148
5149
5150
5151
5152
5153
5154
5155
5156
5157
5158
5159
5160
5161
5162
5163
5164
5165
5166
5167
5168
5169
5170
5171
5172
5173
5174
5175
5176
5177
5178
5179
5180
5181
5182
5183
5184
5185
5186
5187
5188
5189
5190
5191
5192
5193
5194
5195
5196
5197
5198
5199
5200
5201
5202
5203
5204
5205
5206
5207
5208
5209
5210
5211
5212
5213
5214
5215
5216
5217
5218
5219
5220
5221
5222
5223
5224
5225
5226
5227
5228
5229
5230
5231
5232
5233
5234
5235
5236
5237
5238
5239
5240
5241
5242
5243
5244
5245
5246
5247
5248
5249
5250
5251
5252
5253
5254
5255
5256
5257
5258
5259
5260
5261
5262
5263
5264
5265
5266
5267
5268
5269
5270
5271
5272
5273
5274
5275
5276
5277
5278
5279
5280
5281
5282
5283
5284
5285
5286
5287
5288
5289
5290
5291
5292
5293
5294
5295
5296
5297
5298
5299
5300
5301
5302
5303
5304
5305
5306
5307
5308
5309
5310
5311
5312
5313
5314
5315
5316
5317
5318
5319
5320
5321
5322
5323
5324
5325
5326
5327
5328
5329
5330
5331
5332
5333
5334
5335
5336
5337
5338
5339
5340
5341
5342
5343
5344
5345
5346
5347
5348
5349
5350
5351
5352
5353
5354
5355
5356
5357
5358
5359
5360
5361
5362
5363
5364
5365
5366
5367
5368
5369
5370
5371
5372
5373
5374
5375
5376
5377
5378
5379
5380
5381
5382
5383
5384
5385
5386
5387
5388
5389
5390
5391
5392
5393
5394
5395
5396
5397
5398
5399
5400
5401
5402
5403
5404
5405
5406
5407
5408
5409
5410
5411
5412
5413
5414
5415
5416
5417
5418
5419
5420
5421
5422
5423
5424
5425
5426
5427
5428
5429
5430
5431
5432
5433
5434
5435
5436
5437
5438
5439
5440
5441
5442
5443
5444
5445
5446
5447
5448
5449
5450
5451
5452
5453
5454
5455
5456
5457
5458
5459
5460
5461
5462
5463
5464
5465
5466
5467
5468
5469
5470
5471
5472
5473
5474
5475
5476
5477
5478
5479
5480
5481
5482
5483
5484
5485
5486
5487
5488
5489
5490
5491
5492
5493
5494
5495
5496
5497
5498
5499
5500
5501
5502
5503
5504
5505
5506
5507
5508
5509
5510
5511
5512
5513
5514
5515
5516
5517
5518
5519
5520
5521
5522
5523
5524
5525
5526
5527
5528
5529
5530
5531
5532
5533
5534
5535
5536
5537
5538
5539
5540
5541
5542
5543
5544
5545
5546
5547
5548
5549
5550
5551
5552
5553
5554
5555
5556
5557
5558
5559
5560
5561
5562
5563
5564
5565
5566
5567
5568
5569
5570
5571
5572
5573
5574
5575
5576
5577
5578
5579
5580
5581
5582
5583
5584
5585
5586
5587
5588
5589
5590
5591
5592
5593
5594
5595
5596
5597
5598
5599
5600
5601
5602
5603
5604
5605
5606
5607
5608
5609
5610
5611
5612
5613
5614
5615
5616
5617
5618
5619
5620
5621
5622
5623
5624
5625
5626
5627
5628
5629
5630
5631
5632
5633
5634
5635
5636
5637
5638
5639
5640
5641
5642
5643
5644
5645
5646
5647
5648
5649
5650
5651
5652
5653
5654
5655
5656
5657
5658
5659
5660
5661
5662
5663
5664
5665
5666
5667
5668
5669
5670
5671
5672
5673
5674
5675
5676
5677
5678
5679
5680
5681
5682
5683
5684
5685
5686
5687
5688
5689
5690
5691
5692
5693
5694
5695
5696
5697
5698
5699
5700
5701
5702
5703
5704
5705
5706
5707
5708
5709
5710
5711
5712
5713
5714
5715
5716
5717
5718
5719
5720
5721
5722
5723
5724
5725
5726
5727
5728
5729
5730
5731
5732
5733
5734
5735
5736
5737
5738
5739
5740
5741
5742
5743
5744
5745
5746
5747
5748
5749
5750
5751
5752
5753
5754
5755
5756
5757
5758
5759
5760
5761
5762
5763
5764
5765
5766
5767
5768
5769
5770
5771
5772
5773
5774
5775
5776
5777
5778
5779
5780
5781
5782
5783
5784
5785
5786
5787
5788
5789
5790
5791
5792
5793
5794
5795
5796
5797
5798
5799
5800
5801
5802
5803
5804
5805
5806
5807
5808
5809
5810
5811
5812
5813
5814
5815
5816
5817
5818
5819
5820
5821
5822
5823
5824
5825
5826
5827
5828
5829
5830
5831
5832
5833
5834
5835
5836
5837
5838
5839
5840
5841
5842
5843
5844
5845
5846
5847
5848
5849
5850
5851
5852
5853
5854
5855
5856
5857
5858
5859
5860
5861
5862
5863
5864
5865
5866
5867
5868
5869
5870
5871
5872
5873
5874
5875
5876
5877
5878
5879
5880
5881
5882
5883
5884
5885
5886
5887
5888
5889
5890
5891
5892
5893
5894
5895
5896
5897
5898
5899
5900
5901
5902
5903
5904
5905
5906
5907
5908
5909
5910
5911
5912
5913
5914
5915
5916
5917
5918
5919
5920
5921
5922
5923
5924
5925
5926
5927
5928
5929
5930
5931
5932
5933
5934
5935
5936
5937
5938
5939
5940
5941
5942
5943
5944
5945
5946
5947
5948
5949
5950
5951
5952
5953
5954
5955
5956
5957
5958
5959
5960
5961
5962
5963
5964
5965
5966
5967
5968
5969
5970
5971
5972
5973
5974
5975
5976
5977
5978
5979
5980
5981
5982
5983
5984
5985
5986
5987
5988
5989
5990
5991
5992
5993
5994
5995
5996
5997
5998
5999
6000
6001
6002
6003
6004
6005
6006
6007
6008
6009
6010
6011
6012
6013
6014
6015
6016
6017
6018
6019
6020
6021
6022
6023
6024
6025
6026
6027
6028
6029
6030
6031
6032
6033
6034
6035
6036
6037
6038
6039
6040
6041
6042
6043
6044
6045
6046
6047
6048
6049
6050
6051
6052
6053
6054
6055
6056
6057
6058
6059
6060
6061
6062
6063
6064
6065
6066
6067
6068
6069
6070
6071
6072
6073
6074
6075
6076
6077
6078
6079
6080
6081
6082
6083
6084
6085
6086
6087
6088
6089
6090
6091
6092
6093
6094
6095
6096
6097
6098
6099
6100
6101
6102
6103
6104
6105
6106
6107
6108
6109
6110
6111
6112
6113
6114
6115
6116
6117
6118
6119
6120
6121
6122
6123
6124
6125
6126
6127
6128
6129
6130
6131
6132
6133
6134
6135
6136
6137
6138
6139
6140
6141
6142
6143
6144
6145
6146
6147
6148
6149
6150
6151
6152
6153
6154
6155
6156
6157
6158
6159
6160
6161
6162
6163
6164
6165
6166
6167
6168
6169
6170
6171
6172
6173
6174
6175
6176
6177
6178
6179
6180
6181
6182
6183
6184
6185
6186
6187
6188
6189
6190
6191
6192
6193
6194
6195
6196
6197
6198
6199
6200
6201
6202
6203
6204
6205
6206
6207
6208
6209
6210
6211
6212
6213
6214
6215
6216
6217
6218
6219
6220
6221
6222
6223
6224
6225
6226
6227
6228
6229
6230
6231
6232
6233
6234
6235
6236
6237
6238
6239
6240
6241
6242
6243
6244
6245
6246
6247
6248
6249
6250
6251
6252
6253
6254
6255
6256
6257
6258
6259
6260
6261
6262
6263
6264
6265
6266
6267
6268
6269
6270
6271
6272
6273
6274
6275
6276
6277
6278
6279
6280
6281
6282
6283
6284
6285
6286
6287
6288
6289
6290
6291
6292
6293
6294
6295
6296
6297
6298
6299
6300
6301
6302
6303
6304
6305
6306
6307
6308
6309
6310
6311
6312
6313
6314
6315
6316
6317
6318
6319
6320
6321
6322
6323
6324
6325
6326
6327
6328
6329
6330
6331
6332
6333
6334
6335
6336
6337
6338
6339
6340
6341
6342
6343
6344
6345
6346
6347
6348
6349
6350
6351
6352
6353
6354
6355
6356
6357
6358
6359
6360
6361
6362
6363
6364
6365
6366
6367
6368
6369
6370
6371
6372
6373
6374
6375
6376
6377
6378
6379
6380
6381
6382
6383
6384
6385
6386
6387
6388
6389
6390
6391
6392
6393
6394
6395
6396
6397
6398
6399
6400
6401
6402
6403
6404
6405
6406
6407
6408
6409
6410
6411
6412
6413
6414
6415
6416
6417
6418
6419
6420
6421
6422
6423
6424
6425
6426
6427
6428
6429
6430
6431
6432
6433
6434
6435
6436
6437
6438
6439
6440
6441
6442
6443
6444
6445
6446
6447
6448
6449
6450
6451
6452
6453
6454
6455
6456
6457
6458
6459
6460
6461
6462
6463
6464
6465
6466
6467
6468
6469
6470
6471
6472
6473
6474
6475
6476
6477
6478
6479
6480
6481
6482
6483
6484
6485
6486
6487
6488
6489
6490
6491
6492
6493
6494
6495
6496
6497
6498
6499
6500
6501
6502
6503
6504
6505
6506
6507
6508
6509
6510
6511
6512
6513
6514
6515
6516
6517
6518
6519
6520
6521
6522
6523
6524
6525
6526
6527
6528
6529
6530
6531
6532
6533
6534
6535
6536
6537
6538
6539
6540
6541
6542
6543
6544
6545
6546
6547
6548
6549
6550
6551
6552
6553
6554
6555
6556
6557
6558
6559
6560
6561
6562
6563
6564
6565
6566
6567
6568
6569
6570
6571
6572
6573
6574
6575
6576
6577
6578
6579
6580
6581
6582
6583
6584
6585
6586
6587
6588
6589
6590
6591
6592
6593
6594
6595
6596
6597
6598
6599
6600
6601
6602
6603
6604
6605
6606
6607
6608
6609
6610
6611
6612
6613
6614
6615
6616
6617
6618
6619
6620
6621
6622
6623
6624
6625
6626
6627
6628
6629
6630
6631
6632
6633
6634
6635
6636
6637
6638
6639
6640
6641
6642
6643
6644
6645
6646
6647
6648
6649
6650
6651
6652
6653
6654
6655
6656
6657
6658
6659
6660
6661
6662
6663
6664
6665
6666
6667
6668
6669
6670
6671
6672
6673
6674
6675
6676
6677
6678
6679
6680
6681
6682
6683
6684
6685
6686
6687
6688
6689
6690
6691
6692
6693
6694
6695
6696
6697
6698
6699
6700
6701
6702
6703
6704
6705
6706
6707
6708
6709
6710
6711
6712
6713
6714
6715
6716
6717
6718
6719
6720
6721
6722
6723
6724
6725
6726
6727
6728
6729
6730
6731
6732
6733
6734
6735
6736
6737
6738
6739
6740
6741
6742
6743
6744
6745
6746
6747
6748
6749
6750
6751
6752
6753
6754
6755
6756
6757
6758
6759
6760
6761
6762
6763
6764
6765
6766
6767
6768
6769
6770
6771
6772
6773
6774
6775
6776
6777
6778
6779
6780
6781
6782
6783
6784
6785
6786
6787
6788
6789
6790
6791
6792
6793
6794
6795
6796
6797
6798
6799
6800
6801
6802
6803
6804
6805
6806
6807
6808
6809
6810
6811
6812
6813
6814
6815
6816
6817
6818
6819
6820
6821
6822
6823
6824
6825
6826
6827
6828
6829
6830
6831
6832
6833
6834
6835
6836
6837
6838
6839
6840
6841
6842
6843
6844
6845
6846
6847
6848
6849
6850
6851
6852
6853
6854
6855
6856
6857
6858
6859
6860
6861
6862
6863
6864
6865
6866
6867
6868
6869
6870
6871
6872
6873
6874
6875
6876
6877
6878
6879
6880
6881
6882
6883
6884
6885
6886
6887
6888
6889
6890
6891
6892
6893
6894
6895
6896
6897
6898
6899
6900
6901
6902
6903
6904
6905
6906
6907
6908
6909
6910
6911
6912
6913
6914
6915
6916
6917
6918
6919
6920
6921
6922
6923
6924
6925
6926
6927
6928
6929
6930
6931
6932
6933
6934
6935
6936
6937
6938
6939
6940
6941
6942
6943
6944
6945
6946
6947
6948
6949
6950
6951
6952
6953
6954
6955
6956
6957
6958
6959
6960
6961
6962
6963
6964
6965
6966
6967
6968
6969
6970
6971
6972
6973
6974
6975
6976
6977
6978
6979
6980
6981
6982
6983
6984
6985
6986
6987
6988
6989
6990
6991
6992
6993
6994
6995
6996
6997
6998
6999
7000
7001
7002
7003
7004
7005
7006
7007
7008
7009
7010
7011
7012
7013
7014
7015
7016
7017
7018
7019
7020
7021
7022
7023
7024
7025
7026
7027
7028
7029
7030
7031
7032
7033
7034
7035
7036
7037
7038
7039
7040
7041
7042
7043
7044
7045
7046
7047
7048
7049
7050
7051
7052
7053
7054
7055
7056
7057
7058
7059
7060
7061
7062
7063
7064
7065
7066
7067
7068
7069
7070
7071
7072
7073
7074
7075
7076
7077
7078
7079
7080
7081
7082
7083
7084
7085
7086
7087
7088
7089
7090
7091
7092
7093
7094
7095
7096
7097
7098
7099
7100
7101
7102
7103
7104
7105
7106
7107
7108
7109
7110
7111
7112
7113
7114
7115
7116
7117
7118
7119
7120
7121
7122
7123
7124
7125
7126
7127
7128
7129
7130
7131
7132
7133
7134
7135
7136
7137
7138
7139
7140
7141
7142
7143
7144
7145
7146
7147
7148
7149
7150
7151
7152
7153
7154
7155
7156
7157
7158
7159
7160
7161
7162
7163
7164
7165
7166
7167
7168
7169
7170
7171
7172
7173
7174
7175
7176
7177
7178
7179
7180
7181
7182
7183
7184
7185
7186
7187
7188
7189
7190
7191
7192
7193
7194
7195
7196
7197
7198
7199
7200
7201
7202
7203
7204
7205
7206
7207
7208
7209
7210
7211
7212
7213
7214
7215
7216
7217
7218
7219
7220
7221
7222
7223
7224
7225
7226
7227
7228
7229
7230
7231
7232
7233
7234
7235
7236
7237
7238
7239
7240
7241
7242
7243
7244
7245
7246
7247
7248
7249
7250
7251
7252
7253
7254
7255
7256
7257
7258
7259
7260
7261
7262
7263
7264
7265
7266
7267
7268
7269
7270
7271
7272
7273
7274
7275
7276
7277
7278
7279
7280
7281
7282
7283
7284
7285
7286
7287
7288
7289
7290
7291
7292
7293
7294
7295
7296
7297
7298
7299
7300
7301
7302
7303
7304
7305
7306
7307
7308
7309
7310
7311
7312
7313
7314
7315
7316
7317
7318
7319
7320
7321
7322
7323
7324
7325
7326
7327
7328
7329
7330
7331
7332
7333
7334
7335
7336
7337
7338
7339
7340
7341
7342
7343
7344
7345
7346
7347
7348
7349
7350
7351
7352
7353
7354
7355
7356
7357
7358
7359
7360
7361
7362
7363
7364
7365
7366
7367
7368
7369
7370
7371
7372
7373
7374
7375
7376
7377
7378
7379
7380
7381
7382
7383
7384
7385
7386
7387
7388
7389
7390
7391
7392
7393
7394
7395
7396
7397
7398
7399
7400
7401
7402
7403
7404
7405
7406
7407
7408
7409
7410
7411
7412
7413
7414
7415
7416
7417
7418
7419
7420
7421
7422
7423
7424
7425
7426
7427
7428
7429
7430
7431
7432
7433
7434
7435
7436
7437
7438
7439
7440
7441
7442
7443
7444
7445
7446
7447
7448
7449
7450
7451
7452
7453
7454
7455
7456
7457
7458
7459
7460
7461
7462
7463
7464
7465
7466
7467
7468
7469
7470
7471
7472
7473
7474
7475
7476
7477
7478
7479
7480
7481
7482
7483
7484
7485
7486
7487
7488
7489
7490
7491
7492
7493
7494
7495
7496
7497
7498
7499
7500
7501
7502
7503
7504
7505
7506
7507
7508
7509
7510
7511
7512
7513
7514
7515
7516
7517
7518
7519
7520
7521
7522
7523
7524
7525
7526
7527
7528
7529
7530
7531
7532
7533
7534
7535
7536
7537
7538
7539
7540
7541
7542
7543
7544
7545
7546
7547
7548
7549
7550
7551
7552
7553
7554
7555
7556
7557
7558
7559
7560
7561
7562
7563
7564
7565
7566
7567
7568
7569
7570
7571
7572
7573
7574
7575
7576
7577
7578
7579
7580
7581
7582
7583
7584
7585
7586
7587
7588
7589
7590
7591
7592
7593
7594
7595
7596
7597
7598
7599
7600
7601
7602
7603
7604
7605
7606
7607
7608
7609
7610
7611
7612
7613
7614
7615
7616
7617
7618
7619
7620
7621
7622
7623
7624
7625
7626
7627
7628
7629
7630
7631
7632
7633
7634
7635
7636
7637
7638
7639
7640
7641
7642
7643
7644
7645
7646
7647
7648
7649
7650
7651
7652
7653
7654
7655
7656
7657
7658
7659
7660
7661
7662
7663
7664
7665
7666
7667
7668
7669
7670
7671
7672
7673
7674
7675
7676
7677
7678
7679
7680
7681
7682
7683
7684
7685
7686
7687
7688
7689
7690
7691
7692
7693
7694
7695
7696
7697
7698
7699
7700
7701
7702
7703
7704
7705
7706
7707
7708
7709
7710
7711
7712
7713
7714
7715
7716
7717
7718
7719
7720
7721
7722
7723
7724
7725
7726
7727
7728
7729
7730
7731
7732
7733
7734
7735
7736
7737
7738
7739
7740
7741
7742
7743
7744
7745
7746
7747
7748
7749
7750
7751
7752
7753
7754
7755
7756
7757
7758
7759
7760
7761
7762
7763
7764
7765
7766
7767
7768
7769
7770
7771
7772
7773
7774
7775
7776
7777
7778
7779
7780
7781
7782
7783
7784
7785
7786
7787
7788
7789
7790
7791
7792
7793
7794
7795
7796
7797
7798
7799
7800
7801
7802
7803
7804
7805
7806
7807
7808
7809
7810
7811
7812
7813
7814
7815
7816
7817
7818
7819
7820
7821
7822
7823
7824
7825
7826
7827
7828
7829
7830
7831
7832
7833
7834
7835
7836
7837
7838
7839
7840
7841
7842
7843
7844
7845
7846
7847
7848
7849
7850
7851
7852
7853
7854
7855
7856
7857
7858
7859
7860
7861
7862
7863
7864
7865
7866
7867
7868
7869
7870
7871
7872
7873
7874
7875
7876
7877
7878
7879
7880
7881
7882
7883
7884
7885
7886
7887
7888
7889
7890
7891
7892
7893
7894
7895
7896
7897
7898
7899
7900
7901
7902
7903
7904
7905
7906
7907
7908
7909
7910
7911
7912
7913
7914
7915
7916
7917
7918
7919
7920
7921
7922
7923
7924
7925
7926
7927
7928
7929
7930
7931
7932
7933
7934
7935
7936
7937
7938
7939
7940
7941
7942
7943
7944
7945
7946
7947
7948
7949
7950
7951
7952
7953
7954
7955
7956
7957
7958
7959
7960
7961
7962
7963
7964
7965
7966
7967
7968
7969
7970
7971
7972
7973
7974
7975
7976
7977
7978
7979
7980
7981
7982
7983
7984
7985
7986
7987
7988
7989
7990
7991
7992
7993
7994
7995
7996
7997
7998
7999
8000
8001
8002
8003
8004
8005
8006
8007
8008
8009
8010
8011
8012
8013
8014
8015
8016
8017
8018
8019
8020
8021
8022
8023
8024
8025
8026
8027
8028
8029
8030
8031
8032
8033
8034
8035
8036
8037
8038
8039
8040
8041
8042
8043
8044
8045
8046
8047
8048
8049
8050
8051
8052
8053
8054
8055
8056
8057
8058
8059
8060
8061
8062
8063
8064
8065
8066
8067
8068
8069
8070
8071
8072
8073
8074
8075
8076
8077
8078
8079
8080
8081
8082
8083
8084
8085
8086
8087
8088
8089
8090
8091
8092
8093
8094
8095
8096
8097
8098
8099
8100
8101
8102
8103
8104
8105
8106
8107
8108
8109
8110
8111
8112
8113
8114
8115
8116
8117
8118
8119
8120
8121
8122
8123
8124
8125
8126
8127
8128
8129
8130
8131
8132
8133
8134
8135
8136
8137
8138
8139
8140
8141
8142
8143
8144
8145
8146
8147
8148
8149
8150
8151
8152
8153
8154
8155
8156
8157
8158
8159
8160
8161
8162
8163
8164
8165
8166
8167
8168
8169
8170
8171
8172
8173
8174
8175
8176
8177
8178
8179
8180
8181
8182
8183
8184
8185
8186
8187
8188
8189
8190
8191
8192
8193
8194
8195
8196
8197
8198
8199
8200
8201
8202
8203
8204
8205
8206
8207
8208
8209
8210
8211
8212
8213
8214
8215
8216
8217
8218
8219
8220
8221
8222
8223
8224
8225
8226
8227
8228
8229
8230
8231
8232
8233
8234
8235
8236
8237
8238
8239
8240
8241
8242
8243
8244
8245
8246
8247
8248
8249
8250
8251
8252
8253
8254
8255
8256
8257
8258
8259
8260
8261
8262
8263
8264
8265
8266
8267
8268
8269
8270
8271
8272
8273
8274
8275
8276
8277
8278
8279
8280
8281
8282
8283
8284
8285
8286
8287
8288
8289
8290
8291
8292
8293
8294
8295
8296
8297
8298
8299
8300
8301
8302
8303
8304
8305
8306
8307
8308
8309
8310
8311
8312
8313
8314
8315
8316
8317
8318
8319
8320
8321
8322
8323
8324
8325
8326
8327
8328
8329
8330
8331
8332
8333
8334
8335
8336
8337
8338
8339
8340
8341
8342
8343
8344
8345
8346
8347
8348
8349
8350
8351
8352
8353
8354
8355
8356
8357
8358
8359
8360
8361
8362
8363
8364
8365
8366
8367
8368
8369
8370
8371
8372
8373
8374
8375
8376
8377
8378
8379
8380
8381
8382
8383
8384
8385
8386
8387
8388
8389
8390
8391
8392
8393
8394
8395
8396
8397
8398
8399
8400
8401
8402
8403
8404
8405
8406
8407
8408
8409
8410
8411
8412
8413
8414
8415
8416
8417
8418
8419
8420
8421
8422
8423
8424
8425
8426
8427
8428
8429
8430
8431
8432
8433
8434
8435
8436
8437
8438
8439
8440
8441
8442
8443
8444
8445
8446
8447
8448
8449
8450
8451
8452
8453
8454
8455
8456
8457
8458
8459
8460
8461
8462
8463
8464
8465
8466
8467
8468
8469
8470
8471
8472
8473
8474
8475
8476
8477
8478
8479
8480
8481
8482
8483
8484
8485
8486
8487
8488
8489
8490
8491
8492
8493
8494
8495
8496
8497
8498
8499
8500
8501
8502
8503
8504
8505
8506
8507
8508
8509
8510
8511
8512
8513
8514
8515
8516
8517
8518
8519
8520
8521
8522
8523
8524
8525
8526
8527
8528
8529
8530
8531
8532
8533
8534
8535
8536
8537
8538
8539
8540
8541
8542
8543
8544
8545
8546
8547
8548
8549
8550
8551
8552
8553
8554
8555
8556
8557
8558
8559
8560
8561
8562
8563
8564
8565
8566
8567
8568
8569
8570
8571
8572
8573
8574
8575
8576
8577
8578
8579
8580
8581
8582
8583
8584
8585
8586
8587
8588
8589
8590
8591
8592
8593
8594
8595
8596
8597
8598
8599
8600
8601
8602
8603
8604
8605
8606
8607
8608
8609
8610
8611
8612
8613
8614
8615
8616
8617
8618
8619
8620
8621
8622
8623
8624
8625
8626
8627
8628
8629
8630
8631
8632
8633
8634
8635
8636
8637
8638
8639
8640
8641
8642
8643
8644
8645
8646
8647
8648
8649
8650
8651
8652
8653
8654
8655
8656
8657
8658
8659
8660
8661
8662
8663
8664
8665
8666
8667
8668
8669
8670
8671
8672
8673
8674
8675
8676
8677
8678
8679
8680
8681
8682
8683
8684
8685
8686
8687
8688
8689
8690
8691
8692
8693
8694
8695
8696
8697
8698
8699
8700
8701
8702
8703
8704
8705
8706
8707
8708
8709
8710
8711
8712
8713
8714
8715
8716
8717
8718
8719
8720
8721
8722
8723
8724
8725
8726
8727
8728
8729
8730
8731
8732
8733
8734
8735
8736
8737
8738
8739
8740
8741
8742
8743
8744
8745
8746
8747
8748
8749
8750
8751
8752
8753
8754
8755
8756
8757
8758
8759
8760
8761
8762
8763
8764
8765
8766
8767
8768
8769
8770
8771
8772
8773
8774
8775
8776
8777
8778
8779
8780
8781
8782
8783
8784
8785
8786
8787
8788
8789
8790
8791
8792
8793
8794
8795
8796
8797
8798
8799
8800
8801
8802
8803
8804
8805
8806
8807
8808
8809
8810
8811
8812
8813
8814
8815
8816
8817
8818
8819
8820
8821
8822
8823
8824
8825
8826
8827
8828
8829
8830
8831
8832
8833
8834
8835
8836
8837
8838
8839
8840
8841
8842
8843
8844
8845
8846
8847
8848
8849
8850
8851
8852
8853
8854
8855
8856
8857
8858
8859
8860
8861
8862
8863
8864
8865
8866
8867
8868
8869
8870
8871
8872
8873
8874
8875
8876
8877
8878
8879
8880
8881
8882
8883
8884
8885
8886
8887
8888
8889
8890
8891
8892
8893
8894
8895
8896
8897
8898
8899
8900
8901
8902
8903
8904
8905
8906
8907
8908
8909
8910
8911
8912
8913
8914
8915
8916
8917
8918
8919
8920
8921
8922
8923
8924
8925
8926
8927
8928
8929
8930
8931
8932
8933
8934
8935
8936
8937
8938
8939
8940
8941
8942
8943
8944
8945
8946
8947
8948
8949
8950
8951
8952
8953
8954
8955
8956
8957
8958
8959
8960
8961
8962
8963
8964
8965
8966
8967
8968
8969
8970
8971
8972
8973
8974
8975
8976
8977
8978
8979
8980
8981
8982
8983
8984
8985
8986
8987
8988
8989
8990
8991
8992
8993
8994
8995
8996
8997
8998
8999
9000
9001
9002
9003
9004
9005
9006
9007
9008
9009
9010
9011
9012
9013
9014
9015
9016
9017
9018
9019
9020
9021
9022
9023
9024
9025
9026
9027
9028
9029
9030
9031
9032
9033
9034
9035
9036
9037
9038
9039
9040
9041
9042
9043
9044
9045
9046
9047
9048
9049
9050
9051
9052
9053
9054
9055
9056
9057
9058
9059
9060
9061
9062
9063
9064
9065
9066
9067
9068
9069
9070
9071
9072
9073
9074
9075
9076
9077
9078
9079
9080
9081
9082
9083
9084
9085
9086
9087
9088
9089
9090
9091
9092
9093
9094
9095
9096
9097
9098
9099
9100
9101
9102
9103
9104
9105
9106
9107
9108
9109
9110
9111
9112
9113
9114
9115
9116
9117
9118
9119
9120
9121
9122
9123
9124
9125
9126
9127
9128
9129
9130
9131
9132
9133
9134
9135
9136
9137
9138
9139
9140
9141
9142
9143
9144
9145
9146
9147
9148
9149
9150
9151
9152
9153
9154
9155
9156
9157
9158
9159
9160
9161
9162
9163
9164
9165
9166
9167
9168
9169
9170
9171
9172
9173
9174
9175
9176
9177
9178
9179
9180
9181
9182
9183
9184
9185
9186
9187
9188
9189
9190
9191
9192
9193
9194
9195
9196
9197
9198
9199
9200
9201
9202
9203
9204
9205
9206
9207
9208
9209
9210
9211
9212
9213
9214
9215
9216
9217
9218
9219
9220
9221
9222
9223
9224
9225
9226
9227
9228
9229
9230
9231
9232
9233
9234
9235
9236
9237
9238
9239
9240
9241
9242
9243
9244
9245
9246
9247
9248
9249
9250
9251
9252
9253
9254
9255
9256
9257
9258
9259
9260
9261
9262
9263
9264
9265
9266
9267
9268
9269
9270
9271
9272
9273
9274
9275
9276
9277
9278
9279
9280
9281
9282
9283
9284
9285
9286
9287
9288
9289
9290
9291
9292
9293
9294
9295
9296
9297
9298
9299
9300
9301
9302
9303
9304
9305
9306
9307
9308
9309
9310
9311
9312
9313
9314
9315
9316
9317
9318
9319
9320
9321
9322
9323
9324
9325
9326
9327
9328
9329
9330
9331
9332
9333
9334
9335
9336
9337
9338
9339
9340
9341
9342
9343
9344
9345
9346
9347
9348
9349
9350
9351
9352
9353
9354
9355
9356
9357
9358
9359
9360
9361
9362
9363
9364
9365
9366
9367
9368
9369
9370
9371
9372
9373
9374
9375
9376
9377
9378
9379
9380
9381
9382
9383
9384
9385
9386
9387
9388
9389
9390
9391
9392
9393
9394
9395
9396
9397
9398
9399
9400
9401
9402
9403
9404
9405
9406
9407
9408
9409
9410
9411
9412
9413
9414
9415
9416
9417
9418
9419
9420
9421
9422
9423
9424
9425
9426
9427
9428
9429
9430
9431
9432
9433
9434
9435
9436
9437
9438
9439
9440
9441
9442
9443
9444
9445
9446
9447
9448
9449
9450
9451
9452
9453
9454
9455
9456
9457
9458
9459
9460
9461
9462
9463
9464
9465
9466
9467
9468
9469
9470
9471
9472
9473
9474
9475
9476
9477
9478
9479
9480
9481
9482
9483
9484
9485
9486
9487
9488
9489
9490
9491
9492
9493
9494
9495
9496
9497
9498
9499
9500
9501
9502
9503
9504
9505
9506
9507
9508
9509
9510
9511
9512
9513
9514
9515
9516
9517
9518
9519
9520
9521
9522
9523
9524
9525
9526
9527
9528
9529
9530
9531
9532
9533
9534
9535
9536
9537
9538
9539
9540
9541
9542
9543
9544
9545
9546
9547
9548
9549
9550
9551
9552
9553
9554
9555
9556
9557
9558
9559
9560
9561
9562
9563
9564
9565
9566
9567
9568
9569
9570
9571
9572
9573
9574
9575
9576
9577
9578
9579
9580
9581
9582
9583
9584
9585
9586
9587
9588
9589
9590
9591
9592
9593
9594
9595
9596
9597
9598
9599
9600
9601
9602
9603
9604
9605
9606
9607
9608
9609
9610
9611
9612
9613
9614
9615
9616
9617
9618
9619
9620
9621
9622
9623
9624
9625
9626
9627
9628
9629
9630
9631
9632
9633
9634
9635
9636
9637
9638
9639
9640
9641
9642
9643
9644
9645
9646
9647
9648
9649
9650
9651
9652
9653
9654
9655
9656
9657
9658
9659
9660
9661
9662
9663
9664
9665
9666
9667
9668
9669
9670
9671
9672
9673
9674
9675
9676
9677
9678
9679
9680
9681
9682
9683
9684
9685
9686
9687
9688
9689
9690
9691
9692
9693
9694
9695
9696
9697
9698
9699
9700
9701
9702
9703
9704
9705
9706
9707
9708
9709
9710
9711
9712
9713
9714
9715
9716
9717
9718
9719
9720
9721
9722
9723
9724
9725
9726
9727
9728
9729
9730
9731
9732
9733
9734
9735
9736
9737
9738
9739
9740
9741
9742
9743
9744
9745
9746
9747
9748
9749
9750
9751
9752
9753
9754
9755
9756
9757
9758
9759
9760
9761
9762
9763
9764
9765
9766
9767
9768
9769
9770
9771
9772
9773
9774
9775
9776
9777
9778
9779
9780
9781
9782
9783
9784
9785
9786
9787
9788
9789
9790
9791
9792
9793
9794
9795
9796
9797
9798
9799
9800
9801
9802
9803
9804
9805
9806
9807
9808
9809
9810
9811
9812
9813
9814
9815
9816
9817
9818
9819
9820
9821
9822
9823
9824
9825
9826
9827
9828
9829
9830
9831
9832
9833
9834
9835
9836
9837
9838
9839
9840
9841
9842
9843
9844
9845
9846
9847
9848
9849
9850
9851
9852
9853
9854
9855
9856
9857
9858
9859
9860
9861
9862
9863
9864
9865
9866
9867
9868
9869
9870
9871
9872
9873
9874
9875
9876
9877
9878
9879
9880
9881
9882
9883
9884
9885
9886
9887
9888
9889
9890
9891
9892
9893
9894
9895
9896
9897
9898
9899
9900
9901
9902
9903
9904
9905
9906
9907
9908
9909
9910
9911
9912
9913
9914
9915
9916
9917
9918
9919
9920
9921
9922
9923
9924
9925
9926
9927
9928
9929
9930
9931
9932
9933
9934
9935
9936
9937
9938
9939
9940
9941
9942
9943
9944
9945
9946
9947
9948
9949
9950
9951
9952
9953
9954
9955
9956
9957
9958
9959
9960
9961
9962
9963
9964
9965
9966
9967
9968
9969
9970
9971
9972
9973
9974
9975
9976
9977
9978
9979
9980
9981
9982
9983
9984
9985
9986
9987
9988
9989
9990
9991
9992
9993
9994
9995
9996
9997
9998
9999
10000
10001
10002
10003
10004
10005
10006
10007
10008
10009
10010
10011
10012
10013
10014
10015
10016
10017
10018
10019
10020
10021
10022
10023
10024
10025
10026
10027
10028
10029
10030
10031
10032
10033
10034
10035
10036
10037
10038
10039
10040
10041
10042
10043
10044
10045
10046
10047
10048
10049
10050
10051
10052
10053
10054
10055
10056
10057
10058
10059
10060
10061
10062
10063
10064
10065
10066
10067
10068
10069
10070
10071
10072
10073
10074
10075
10076
10077
10078
10079
10080
10081
10082
10083
10084
10085
10086
10087
10088
10089
10090
10091
10092
10093
10094
10095
10096
10097
10098
10099
10100
10101
10102
10103
10104
10105
10106
10107
10108
10109
10110
10111
10112
10113
10114
10115
10116
10117
10118
10119
10120
10121
10122
10123
10124
10125
10126
10127
10128
10129
10130
10131
10132
10133
10134
10135
10136
10137
10138
10139
10140
10141
10142
10143
10144
10145
10146
10147
10148
10149
10150
10151
10152
10153
10154
10155
10156
10157
10158
10159
10160
10161
10162
10163
10164
10165
10166
10167
10168
10169
10170
10171
10172
10173
10174
10175
10176
10177
10178
10179
10180
10181
10182
10183
10184
10185
10186
10187
10188
10189
10190
10191
10192
10193
10194
10195
10196
10197
10198
10199
10200
10201
10202
10203
10204
10205
10206
10207
10208
10209
10210
10211
10212
10213
10214
10215
10216
10217
10218
10219
10220
10221
10222
10223
10224
10225
10226
10227
10228
10229
10230
10231
10232
10233
10234
10235
10236
10237
10238
10239
10240
10241
10242
10243
10244
10245
10246
10247
10248
10249
10250
10251
10252
10253
10254
10255
10256
10257
10258
10259
10260
10261
10262
10263
10264
10265
10266
10267
10268
10269
10270
10271
10272
10273
10274
10275
10276
10277
10278
10279
10280
10281
10282
10283
10284
10285
10286
10287
10288
10289
10290
10291
10292
10293
10294
10295
10296
10297
10298
10299
10300
10301
10302
10303
10304
10305
10306
10307
10308
10309
10310
10311
10312
10313
10314
10315
10316
10317
10318
10319
10320
10321
10322
10323
10324
10325
10326
10327
10328
10329
10330
10331
10332
10333
10334
10335
10336
10337
10338
10339
10340
10341
10342
10343
10344
10345
10346
10347
10348
10349
10350
10351
10352
10353
10354
10355
10356
10357
10358
10359
10360
10361
10362
10363
10364
10365
10366
10367
10368
10369
10370
10371
10372
10373
10374
10375
10376
10377
10378
10379
10380
10381
10382
10383
10384
10385
10386
10387
10388
10389
10390
10391
10392
10393
10394
10395
10396
10397
10398
10399
10400
10401
10402
10403
10404
10405
10406
10407
10408
10409
10410
10411
10412
10413
10414
10415
10416
10417
10418
10419
10420
10421
10422
10423
10424
10425
10426
10427
10428
10429
10430
10431
10432
10433
10434
10435
10436
10437
10438
10439
10440
10441
10442
10443
10444
10445
10446
10447
10448
10449
10450
10451
10452
10453
10454
10455
10456
10457
10458
10459
10460
10461
10462
10463
10464
10465
10466
10467
10468
10469
10470
10471
10472
10473
10474
10475
10476
10477
10478
10479
10480
10481
10482
10483
10484
10485
10486
10487
10488
10489
10490
10491
10492
10493
10494
10495
10496
10497
10498
10499
10500
10501
10502
10503
10504
10505
10506
10507
10508
10509
10510
10511
10512
10513
10514
10515
10516
10517
10518
10519
10520
10521
10522
10523
10524
10525
10526
10527
10528
10529
10530
10531
10532
10533
10534
10535
10536
10537
10538
10539
10540
10541
10542
10543
10544
10545
10546
10547
10548
10549
10550
10551
10552
10553
10554
10555
10556
10557
10558
10559
10560
10561
10562
10563
10564
10565
10566
10567
10568
10569
10570
10571
10572
10573
10574
10575
10576
10577
10578
10579
10580
10581
10582
10583
10584
10585
10586
10587
10588
10589
10590
10591
10592
10593
10594
10595
10596
10597
10598
10599
10600
10601
10602
10603
10604
10605
10606
10607
10608
10609
10610
10611
10612
10613
10614
10615
10616
10617
10618
10619
10620
10621
10622
10623
10624
10625
10626
10627
10628
10629
10630
10631
10632
10633
10634
10635
10636
10637
10638
10639
10640
10641
10642
10643
10644
10645
10646
10647
10648
10649
10650
10651
10652
10653
10654
10655
10656
10657
10658
10659
10660
10661
10662
10663
10664
10665
10666
10667
10668
10669
10670
10671
10672
10673
10674
10675
10676
10677
10678
10679
10680
10681
10682
10683
10684
10685
10686
10687
10688
10689
10690
10691
10692
10693
10694
10695
10696
10697
10698
10699
10700
10701
10702
10703
10704
10705
10706
10707
10708
10709
10710
10711
10712
10713
10714
10715
10716
10717
10718
10719
10720
10721
10722
10723
10724
10725
10726
10727
10728
10729
10730
10731
10732
10733
10734
10735
10736
10737
10738
10739
10740
10741
10742
10743
10744
10745
10746
10747
10748
10749
10750
10751
10752
10753
10754
10755
10756
10757
10758
10759
10760
10761
10762
10763
10764
10765
10766
10767
10768
10769
10770
10771
10772
10773
10774
10775
10776
10777
10778
10779
10780
10781
10782
10783
10784
10785
10786
10787
10788
10789
10790
10791
10792
10793
10794
10795
10796
10797
10798
10799
10800
10801
10802
10803
10804
10805
10806
10807
10808
10809
10810
10811
10812
10813
10814
10815
10816
10817
10818
10819
10820
10821
10822
10823
10824
10825
10826
10827
10828
10829
10830
10831
10832
10833
10834
10835
10836
10837
10838
10839
10840
10841
10842
10843
10844
10845
10846
10847
10848
10849
10850
10851
10852
10853
10854
10855
10856
10857
10858
10859
10860
10861
10862
10863
10864
10865
10866
10867
10868
10869
10870
10871
10872
10873
10874
10875
10876
10877
10878
10879
10880
10881
10882
10883
10884
10885
10886
10887
10888
10889
10890
10891
10892
10893
10894
10895
10896
10897
10898
10899
10900
10901
10902
10903
10904
10905
10906
10907
10908
10909
10910
10911
10912
10913
10914
10915
10916
10917
10918
10919
10920
10921
10922
10923
10924
10925
10926
10927
10928
10929
10930
10931
10932
10933
10934
10935
10936
10937
10938
10939
10940
10941
10942
10943
10944
10945
10946
10947
10948
10949
10950
10951
10952
10953
10954
10955
10956
10957
10958
10959
10960
10961
10962
10963
10964
10965
10966
10967
10968
10969
10970
10971
10972
10973
10974
10975
10976
10977
10978
10979
10980
10981
10982
10983
10984
10985
10986
10987
10988
10989
10990
10991
10992
10993
10994
10995
10996
10997
10998
10999
11000
11001
11002
11003
11004
11005
11006
11007
11008
11009
11010
11011
11012
11013
11014
11015
11016
11017
11018
11019
11020
11021
11022
11023
11024
11025
11026
11027
11028
11029
11030
11031
11032
11033
11034
11035
11036
11037
11038
11039
11040
11041
11042
11043
11044
11045
11046
11047
11048
11049
11050
11051
11052
11053
11054
11055
11056
11057
11058
11059
11060
11061
11062
11063
11064
11065
11066
11067
11068
11069
11070
11071
11072
11073
11074
11075
11076
11077
11078
11079
11080
11081
11082
11083
11084
11085
11086
11087
11088
11089
11090
11091
11092
11093
11094
11095
11096
11097
11098
11099
11100
11101
11102
11103
11104
11105
11106
11107
11108
11109
11110
11111
11112
11113
11114
11115
11116
11117
11118
11119
11120
11121
11122
11123
11124
11125
11126
11127
11128
11129
11130
11131
11132
11133
11134
11135
11136
11137
11138
11139
11140
11141
11142
11143
11144
11145
11146
11147
11148
11149
11150
11151
11152
11153
11154
11155
11156
11157
11158
11159
11160
11161
11162
11163
11164
11165
11166
11167
11168
11169
11170
11171
11172
11173
11174
11175
11176
11177
11178
11179
11180
11181
11182
11183
11184
11185
11186
11187
11188
11189
11190
11191
11192
11193
11194
11195
11196
11197
11198
11199
11200
11201
11202
11203
11204
11205
11206
11207
11208
11209
11210
11211
11212
11213
11214
11215
11216
11217
11218
11219
11220
11221
11222
11223
11224
11225
11226
11227
11228
11229
11230
11231
11232
11233
11234
11235
11236
11237
11238
11239
11240
11241
11242
11243
11244
11245
11246
11247
11248
11249
11250
11251
11252
11253
11254
11255
11256
11257
11258
11259
11260
11261
11262
11263
11264
11265
11266
11267
11268
11269
11270
11271
11272
11273
11274
11275
11276
11277
11278
11279
11280
11281
11282
11283
11284
11285
11286
11287
11288
11289
11290
11291
11292
11293
11294
11295
11296
11297
11298
11299
11300
11301
11302
11303
11304
11305
11306
11307
11308
11309
11310
11311
11312
11313
11314
11315
11316
11317
11318
11319
11320
11321
11322
11323
11324
11325
11326
11327
11328
11329
11330
11331
11332
11333
11334
11335
11336
11337
11338
11339
11340
11341
11342
11343
11344
11345
11346
11347
11348
11349
11350
11351
11352
11353
11354
11355
11356
11357
11358
11359
11360
11361
11362
11363
11364
11365
11366
11367
11368
11369
11370
11371
11372
11373
11374
11375
11376
11377
11378
11379
11380
11381
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/sort.h>
#include <linux/rcupdate.h>
#include <linux/kthread.h>
#include <linux/slab.h>
#include <linux/ratelimit.h>
#include <linux/percpu_counter.h>
#include <linux/lockdep.h>
#include <linux/crc32c.h>
#include "tree-log.h"
#include "disk-io.h"
#include "print-tree.h"
#include "volumes.h"
#include "raid56.h"
#include "locking.h"
#include "free-space-cache.h"
#include "free-space-tree.h"
#include "math.h"
#include "sysfs.h"
#include "qgroup.h"
#include "ref-verify.h"

#undef SCRAMBLE_DELAYED_REFS

/*
 * control flags for do_chunk_alloc's force field
 * CHUNK_ALLOC_NO_FORCE means to only allocate a chunk
 * if we really need one.
 *
 * CHUNK_ALLOC_LIMITED means to only try and allocate one
 * if we have very few chunks already allocated.  This is
 * used as part of the clustering code to help make sure
 * we have a good pool of storage to cluster in, without
 * filling the FS with empty chunks
 *
 * CHUNK_ALLOC_FORCE means it must try to allocate one
 *
 */
enum {
	CHUNK_ALLOC_NO_FORCE = 0,
	CHUNK_ALLOC_LIMITED = 1,
	CHUNK_ALLOC_FORCE = 2,
};

/*
 * Declare a helper function to detect underflow of various space info members
 */
#define DECLARE_SPACE_INFO_UPDATE(name)					\
static inline void update_##name(struct btrfs_space_info *sinfo,	\
				 s64 bytes)				\
{									\
	if (bytes < 0 && sinfo->name < -bytes) {			\
		WARN_ON(1);						\
		sinfo->name = 0;					\
		return;							\
	}								\
	sinfo->name += bytes;						\
}

DECLARE_SPACE_INFO_UPDATE(bytes_may_use);
DECLARE_SPACE_INFO_UPDATE(bytes_pinned);

static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
			       struct btrfs_delayed_ref_node *node, u64 parent,
			       u64 root_objectid, u64 owner_objectid,
			       u64 owner_offset, int refs_to_drop,
			       struct btrfs_delayed_extent_op *extra_op);
static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
				    struct extent_buffer *leaf,
				    struct btrfs_extent_item *ei);
static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
				      u64 parent, u64 root_objectid,
				      u64 flags, u64 owner, u64 offset,
				      struct btrfs_key *ins, int ref_mod);
static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
				     struct btrfs_delayed_ref_node *node,
				     struct btrfs_delayed_extent_op *extent_op);
static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
			  int force);
static int find_next_key(struct btrfs_path *path, int level,
			 struct btrfs_key *key);
static void dump_space_info(struct btrfs_fs_info *fs_info,
			    struct btrfs_space_info *info, u64 bytes,
			    int dump_block_groups);
static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
			       u64 num_bytes);
static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
				     struct btrfs_space_info *space_info,
				     u64 num_bytes);
static void space_info_add_old_bytes(struct btrfs_fs_info *fs_info,
				     struct btrfs_space_info *space_info,
				     u64 num_bytes);

static noinline int
block_group_cache_done(struct btrfs_block_group_cache *cache)
{
	smp_mb();
	return cache->cached == BTRFS_CACHE_FINISHED ||
		cache->cached == BTRFS_CACHE_ERROR;
}

static int block_group_bits(struct btrfs_block_group_cache *cache, u64 bits)
{
	return (cache->flags & bits) == bits;
}

void btrfs_get_block_group(struct btrfs_block_group_cache *cache)
{
	atomic_inc(&cache->count);
}

void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
{
	if (atomic_dec_and_test(&cache->count)) {
		WARN_ON(cache->pinned > 0);
		WARN_ON(cache->reserved > 0);

		/*
		 * If not empty, someone is still holding mutex of
		 * full_stripe_lock, which can only be released by caller.
		 * And it will definitely cause use-after-free when caller
		 * tries to release full stripe lock.
		 *
		 * No better way to resolve, but only to warn.
		 */
		WARN_ON(!RB_EMPTY_ROOT(&cache->full_stripe_locks_root.root));
		kfree(cache->free_space_ctl);
		kfree(cache);
	}
}

/*
 * this adds the block group to the fs_info rb tree for the block group
 * cache
 */
static int btrfs_add_block_group_cache(struct btrfs_fs_info *info,
				struct btrfs_block_group_cache *block_group)
{
	struct rb_node **p;
	struct rb_node *parent = NULL;
	struct btrfs_block_group_cache *cache;

	spin_lock(&info->block_group_cache_lock);
	p = &info->block_group_cache_tree.rb_node;

	while (*p) {
		parent = *p;
		cache = rb_entry(parent, struct btrfs_block_group_cache,
				 cache_node);
		if (block_group->key.objectid < cache->key.objectid) {
			p = &(*p)->rb_left;
		} else if (block_group->key.objectid > cache->key.objectid) {
			p = &(*p)->rb_right;
		} else {
			spin_unlock(&info->block_group_cache_lock);
			return -EEXIST;
		}
	}

	rb_link_node(&block_group->cache_node, parent, p);
	rb_insert_color(&block_group->cache_node,
			&info->block_group_cache_tree);

	if (info->first_logical_byte > block_group->key.objectid)
		info->first_logical_byte = block_group->key.objectid;

	spin_unlock(&info->block_group_cache_lock);

	return 0;
}

/*
 * This will return the block group at or after bytenr if contains is 0, else
 * it will return the block group that contains the bytenr
 */
static struct btrfs_block_group_cache *
block_group_cache_tree_search(struct btrfs_fs_info *info, u64 bytenr,
			      int contains)
{
	struct btrfs_block_group_cache *cache, *ret = NULL;
	struct rb_node *n;
	u64 end, start;

	spin_lock(&info->block_group_cache_lock);
	n = info->block_group_cache_tree.rb_node;

	while (n) {
		cache = rb_entry(n, struct btrfs_block_group_cache,
				 cache_node);
		end = cache->key.objectid + cache->key.offset - 1;
		start = cache->key.objectid;

		if (bytenr < start) {
			if (!contains && (!ret || start < ret->key.objectid))
				ret = cache;
			n = n->rb_left;
		} else if (bytenr > start) {
			if (contains && bytenr <= end) {
				ret = cache;
				break;
			}
			n = n->rb_right;
		} else {
			ret = cache;
			break;
		}
	}
	if (ret) {
		btrfs_get_block_group(ret);
		if (bytenr == 0 && info->first_logical_byte > ret->key.objectid)
			info->first_logical_byte = ret->key.objectid;
	}
	spin_unlock(&info->block_group_cache_lock);

	return ret;
}

static int add_excluded_extent(struct btrfs_fs_info *fs_info,
			       u64 start, u64 num_bytes)
{
	u64 end = start + num_bytes - 1;
	set_extent_bits(&fs_info->freed_extents[0],
			start, end, EXTENT_UPTODATE);
	set_extent_bits(&fs_info->freed_extents[1],
			start, end, EXTENT_UPTODATE);
	return 0;
}

static void free_excluded_extents(struct btrfs_block_group_cache *cache)
{
	struct btrfs_fs_info *fs_info = cache->fs_info;
	u64 start, end;

	start = cache->key.objectid;
	end = start + cache->key.offset - 1;

	clear_extent_bits(&fs_info->freed_extents[0],
			  start, end, EXTENT_UPTODATE);
	clear_extent_bits(&fs_info->freed_extents[1],
			  start, end, EXTENT_UPTODATE);
}

static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
{
	struct btrfs_fs_info *fs_info = cache->fs_info;
	u64 bytenr;
	u64 *logical;
	int stripe_len;
	int i, nr, ret;

	if (cache->key.objectid < BTRFS_SUPER_INFO_OFFSET) {
		stripe_len = BTRFS_SUPER_INFO_OFFSET - cache->key.objectid;
		cache->bytes_super += stripe_len;
		ret = add_excluded_extent(fs_info, cache->key.objectid,
					  stripe_len);
		if (ret)
			return ret;
	}

	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
		bytenr = btrfs_sb_offset(i);
		ret = btrfs_rmap_block(fs_info, cache->key.objectid,
				       bytenr, &logical, &nr, &stripe_len);
		if (ret)
			return ret;

		while (nr--) {
			u64 start, len;

			if (logical[nr] > cache->key.objectid +
			    cache->key.offset)
				continue;

			if (logical[nr] + stripe_len <= cache->key.objectid)
				continue;

			start = logical[nr];
			if (start < cache->key.objectid) {
				start = cache->key.objectid;
				len = (logical[nr] + stripe_len) - start;
			} else {
				len = min_t(u64, stripe_len,
					    cache->key.objectid +
					    cache->key.offset - start);
			}

			cache->bytes_super += len;
			ret = add_excluded_extent(fs_info, start, len);
			if (ret) {
				kfree(logical);
				return ret;
			}
		}

		kfree(logical);
	}
	return 0;
}

static struct btrfs_caching_control *
get_caching_control(struct btrfs_block_group_cache *cache)
{
	struct btrfs_caching_control *ctl;

	spin_lock(&cache->lock);
	if (!cache->caching_ctl) {
		spin_unlock(&cache->lock);
		return NULL;
	}

	ctl = cache->caching_ctl;
	refcount_inc(&ctl->count);
	spin_unlock(&cache->lock);
	return ctl;
}

static void put_caching_control(struct btrfs_caching_control *ctl)
{
	if (refcount_dec_and_test(&ctl->count))
		kfree(ctl);
}

#ifdef CONFIG_BTRFS_DEBUG
static void fragment_free_space(struct btrfs_block_group_cache *block_group)
{
	struct btrfs_fs_info *fs_info = block_group->fs_info;
	u64 start = block_group->key.objectid;
	u64 len = block_group->key.offset;
	u64 chunk = block_group->flags & BTRFS_BLOCK_GROUP_METADATA ?
		fs_info->nodesize : fs_info->sectorsize;
	u64 step = chunk << 1;

	while (len > chunk) {
		btrfs_remove_free_space(block_group, start, chunk);
		start += step;
		if (len < step)
			len = 0;
		else
			len -= step;
	}
}
#endif

/*
 * this is only called by cache_block_group, since we could have freed extents
 * we need to check the pinned_extents for any extents that can't be used yet
 * since their free space will be released as soon as the transaction commits.
 */
u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
		       u64 start, u64 end)
{
	struct btrfs_fs_info *info = block_group->fs_info;
	u64 extent_start, extent_end, size, total_added = 0;
	int ret;

	while (start < end) {
		ret = find_first_extent_bit(info->pinned_extents, start,
					    &extent_start, &extent_end,
					    EXTENT_DIRTY | EXTENT_UPTODATE,
					    NULL);
		if (ret)
			break;

		if (extent_start <= start) {
			start = extent_end + 1;
		} else if (extent_start > start && extent_start < end) {
			size = extent_start - start;
			total_added += size;
			ret = btrfs_add_free_space(block_group, start,
						   size);
			BUG_ON(ret); /* -ENOMEM or logic error */
			start = extent_end + 1;
		} else {
			break;
		}
	}

	if (start < end) {
		size = end - start;
		total_added += size;
		ret = btrfs_add_free_space(block_group, start, size);
		BUG_ON(ret); /* -ENOMEM or logic error */
	}

	return total_added;
}

static int load_extent_tree_free(struct btrfs_caching_control *caching_ctl)
{
	struct btrfs_block_group_cache *block_group = caching_ctl->block_group;
	struct btrfs_fs_info *fs_info = block_group->fs_info;
	struct btrfs_root *extent_root = fs_info->extent_root;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	u64 total_found = 0;
	u64 last = 0;
	u32 nritems;
	int ret;
	bool wakeup = true;

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

	last = max_t(u64, block_group->key.objectid, BTRFS_SUPER_INFO_OFFSET);

#ifdef CONFIG_BTRFS_DEBUG
	/*
	 * If we're fragmenting we don't want to make anybody think we can
	 * allocate from this block group until we've had a chance to fragment
	 * the free space.
	 */
	if (btrfs_should_fragment_free_space(block_group))
		wakeup = false;
#endif
	/*
	 * We don't want to deadlock with somebody trying to allocate a new
	 * extent for the extent root while also trying to search the extent
	 * root to add free space.  So we skip locking and search the commit
	 * root, since its read-only
	 */
	path->skip_locking = 1;
	path->search_commit_root = 1;
	path->reada = READA_FORWARD;

	key.objectid = last;
	key.offset = 0;
	key.type = BTRFS_EXTENT_ITEM_KEY;

next:
	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
	if (ret < 0)
		goto out;

	leaf = path->nodes[0];
	nritems = btrfs_header_nritems(leaf);

	while (1) {
		if (btrfs_fs_closing(fs_info) > 1) {
			last = (u64)-1;
			break;
		}

		if (path->slots[0] < nritems) {
			btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		} else {
			ret = find_next_key(path, 0, &key);
			if (ret)
				break;

			if (need_resched() ||
			    rwsem_is_contended(&fs_info->commit_root_sem)) {
				if (wakeup)
					caching_ctl->progress = last;
				btrfs_release_path(path);
				up_read(&fs_info->commit_root_sem);
				mutex_unlock(&caching_ctl->mutex);
				cond_resched();
				mutex_lock(&caching_ctl->mutex);
				down_read(&fs_info->commit_root_sem);
				goto next;
			}

			ret = btrfs_next_leaf(extent_root, path);
			if (ret < 0)
				goto out;
			if (ret)
				break;
			leaf = path->nodes[0];
			nritems = btrfs_header_nritems(leaf);
			continue;
		}

		if (key.objectid < last) {
			key.objectid = last;
			key.offset = 0;
			key.type = BTRFS_EXTENT_ITEM_KEY;

			if (wakeup)
				caching_ctl->progress = last;
			btrfs_release_path(path);
			goto next;
		}

		if (key.objectid < block_group->key.objectid) {
			path->slots[0]++;
			continue;
		}

		if (key.objectid >= block_group->key.objectid +
		    block_group->key.offset)
			break;

		if (key.type == BTRFS_EXTENT_ITEM_KEY ||
		    key.type == BTRFS_METADATA_ITEM_KEY) {
			total_found += add_new_free_space(block_group, last,
							  key.objectid);
			if (key.type == BTRFS_METADATA_ITEM_KEY)
				last = key.objectid +
					fs_info->nodesize;
			else
				last = key.objectid + key.offset;

			if (total_found > CACHING_CTL_WAKE_UP) {
				total_found = 0;
				if (wakeup)
					wake_up(&caching_ctl->wait);
			}
		}
		path->slots[0]++;
	}
	ret = 0;

	total_found += add_new_free_space(block_group, last,
					  block_group->key.objectid +
					  block_group->key.offset);
	caching_ctl->progress = (u64)-1;

out:
	btrfs_free_path(path);
	return ret;
}

static noinline void caching_thread(struct btrfs_work *work)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_fs_info *fs_info;
	struct btrfs_caching_control *caching_ctl;
	int ret;

	caching_ctl = container_of(work, struct btrfs_caching_control, work);
	block_group = caching_ctl->block_group;
	fs_info = block_group->fs_info;

	mutex_lock(&caching_ctl->mutex);
	down_read(&fs_info->commit_root_sem);

	if (btrfs_fs_compat_ro(fs_info, FREE_SPACE_TREE))
		ret = load_free_space_tree(caching_ctl);
	else
		ret = load_extent_tree_free(caching_ctl);

	spin_lock(&block_group->lock);
	block_group->caching_ctl = NULL;
	block_group->cached = ret ? BTRFS_CACHE_ERROR : BTRFS_CACHE_FINISHED;
	spin_unlock(&block_group->lock);

#ifdef CONFIG_BTRFS_DEBUG
	if (btrfs_should_fragment_free_space(block_group)) {
		u64 bytes_used;

		spin_lock(&block_group->space_info->lock);
		spin_lock(&block_group->lock);
		bytes_used = block_group->key.offset -
			btrfs_block_group_used(&block_group->item);
		block_group->space_info->bytes_used += bytes_used >> 1;
		spin_unlock(&block_group->lock);
		spin_unlock(&block_group->space_info->lock);
		fragment_free_space(block_group);
	}
#endif

	caching_ctl->progress = (u64)-1;

	up_read(&fs_info->commit_root_sem);
	free_excluded_extents(block_group);
	mutex_unlock(&caching_ctl->mutex);

	wake_up(&caching_ctl->wait);

	put_caching_control(caching_ctl);
	btrfs_put_block_group(block_group);
}

static int cache_block_group(struct btrfs_block_group_cache *cache,
			     int load_cache_only)
{
	DEFINE_WAIT(wait);
	struct btrfs_fs_info *fs_info = cache->fs_info;
	struct btrfs_caching_control *caching_ctl;
	int ret = 0;

	caching_ctl = kzalloc(sizeof(*caching_ctl), GFP_NOFS);
	if (!caching_ctl)
		return -ENOMEM;

	INIT_LIST_HEAD(&caching_ctl->list);
	mutex_init(&caching_ctl->mutex);
	init_waitqueue_head(&caching_ctl->wait);
	caching_ctl->block_group = cache;
	caching_ctl->progress = cache->key.objectid;
	refcount_set(&caching_ctl->count, 1);
	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
			caching_thread, NULL, NULL);

	spin_lock(&cache->lock);
	/*
	 * This should be a rare occasion, but this could happen I think in the
	 * case where one thread starts to load the space cache info, and then
	 * some other thread starts a transaction commit which tries to do an
	 * allocation while the other thread is still loading the space cache
	 * info.  The previous loop should have kept us from choosing this block
	 * group, but if we've moved to the state where we will wait on caching
	 * block groups we need to first check if we're doing a fast load here,
	 * so we can wait for it to finish, otherwise we could end up allocating
	 * from a block group who's cache gets evicted for one reason or
	 * another.
	 */
	while (cache->cached == BTRFS_CACHE_FAST) {
		struct btrfs_caching_control *ctl;

		ctl = cache->caching_ctl;
		refcount_inc(&ctl->count);
		prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
		spin_unlock(&cache->lock);

		schedule();

		finish_wait(&ctl->wait, &wait);
		put_caching_control(ctl);
		spin_lock(&cache->lock);
	}

	if (cache->cached != BTRFS_CACHE_NO) {
		spin_unlock(&cache->lock);
		kfree(caching_ctl);
		return 0;
	}
	WARN_ON(cache->caching_ctl);
	cache->caching_ctl = caching_ctl;
	cache->cached = BTRFS_CACHE_FAST;
	spin_unlock(&cache->lock);

	if (btrfs_test_opt(fs_info, SPACE_CACHE)) {
		mutex_lock(&caching_ctl->mutex);
		ret = load_free_space_cache(cache);

		spin_lock(&cache->lock);
		if (ret == 1) {
			cache->caching_ctl = NULL;
			cache->cached = BTRFS_CACHE_FINISHED;
			cache->last_byte_to_unpin = (u64)-1;
			caching_ctl->progress = (u64)-1;
		} else {
			if (load_cache_only) {
				cache->caching_ctl = NULL;
				cache->cached = BTRFS_CACHE_NO;
			} else {
				cache->cached = BTRFS_CACHE_STARTED;
				cache->has_caching_ctl = 1;
			}
		}
		spin_unlock(&cache->lock);
#ifdef CONFIG_BTRFS_DEBUG
		if (ret == 1 &&
		    btrfs_should_fragment_free_space(cache)) {
			u64 bytes_used;

			spin_lock(&cache->space_info->lock);
			spin_lock(&cache->lock);
			bytes_used = cache->key.offset -
				btrfs_block_group_used(&cache->item);
			cache->space_info->bytes_used += bytes_used >> 1;
			spin_unlock(&cache->lock);
			spin_unlock(&cache->space_info->lock);
			fragment_free_space(cache);
		}
#endif
		mutex_unlock(&caching_ctl->mutex);

		wake_up(&caching_ctl->wait);
		if (ret == 1) {
			put_caching_control(caching_ctl);
			free_excluded_extents(cache);
			return 0;
		}
	} else {
		/*
		 * We're either using the free space tree or no caching at all.
		 * Set cached to the appropriate value and wakeup any waiters.
		 */
		spin_lock(&cache->lock);
		if (load_cache_only) {
			cache->caching_ctl = NULL;
			cache->cached = BTRFS_CACHE_NO;
		} else {
			cache->cached = BTRFS_CACHE_STARTED;
			cache->has_caching_ctl = 1;
		}
		spin_unlock(&cache->lock);
		wake_up(&caching_ctl->wait);
	}

	if (load_cache_only) {
		put_caching_control(caching_ctl);
		return 0;
	}

	down_write(&fs_info->commit_root_sem);
	refcount_inc(&caching_ctl->count);
	list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
	up_write(&fs_info->commit_root_sem);

	btrfs_get_block_group(cache);

	btrfs_queue_work(fs_info->caching_workers, &caching_ctl->work);

	return ret;
}

/*
 * return the block group that starts at or after bytenr
 */
static struct btrfs_block_group_cache *
btrfs_lookup_first_block_group(struct btrfs_fs_info *info, u64 bytenr)
{
	return block_group_cache_tree_search(info, bytenr, 0);
}

/*
 * return the block group that contains the given bytenr
 */
struct btrfs_block_group_cache *btrfs_lookup_block_group(
						 struct btrfs_fs_info *info,
						 u64 bytenr)
{
	return block_group_cache_tree_search(info, bytenr, 1);
}

static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
						  u64 flags)
{
	struct list_head *head = &info->space_info;
	struct btrfs_space_info *found;

	flags &= BTRFS_BLOCK_GROUP_TYPE_MASK;

	rcu_read_lock();
	list_for_each_entry_rcu(found, head, list) {
		if (found->flags & flags) {
			rcu_read_unlock();
			return found;
		}
	}
	rcu_read_unlock();
	return NULL;
}

static void add_pinned_bytes(struct btrfs_fs_info *fs_info,
			     struct btrfs_ref *ref)
{
	struct btrfs_space_info *space_info;
	s64 num_bytes = -ref->len;
	u64 flags;

	if (ref->type == BTRFS_REF_METADATA) {
		if (ref->tree_ref.root == BTRFS_CHUNK_TREE_OBJECTID)
			flags = BTRFS_BLOCK_GROUP_SYSTEM;
		else
			flags = BTRFS_BLOCK_GROUP_METADATA;
	} else {
		flags = BTRFS_BLOCK_GROUP_DATA;
	}

	space_info = __find_space_info(fs_info, flags);
	ASSERT(space_info);
	percpu_counter_add_batch(&space_info->total_bytes_pinned, num_bytes,
		    BTRFS_TOTAL_BYTES_PINNED_BATCH);
}

/*
 * after adding space to the filesystem, we need to clear the full flags
 * on all the space infos.
 */
void btrfs_clear_space_info_full(struct btrfs_fs_info *info)
{
	struct list_head *head = &info->space_info;
	struct btrfs_space_info *found;

	rcu_read_lock();
	list_for_each_entry_rcu(found, head, list)
		found->full = 0;
	rcu_read_unlock();
}

/* simple helper to search for an existing data extent at a given offset */
int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len)
{
	int ret;
	struct btrfs_key key;
	struct btrfs_path *path;

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

	key.objectid = start;
	key.offset = len;
	key.type = BTRFS_EXTENT_ITEM_KEY;
	ret = btrfs_search_slot(NULL, fs_info->extent_root, &key, path, 0, 0);
	btrfs_free_path(path);
	return ret;
}

/*
 * helper function to lookup reference count and flags of a tree block.
 *
 * the head node for delayed ref is used to store the sum of all the
 * reference count modifications queued up in the rbtree. the head
 * node may also store the extent flags to set. This way you can check
 * to see what the reference count and extent flags would be if all of
 * the delayed refs are not processed.
 */
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
			     struct btrfs_fs_info *fs_info, u64 bytenr,
			     u64 offset, int metadata, u64 *refs, u64 *flags)
{
	struct btrfs_delayed_ref_head *head;
	struct btrfs_delayed_ref_root *delayed_refs;
	struct btrfs_path *path;
	struct btrfs_extent_item *ei;
	struct extent_buffer *leaf;
	struct btrfs_key key;
	u32 item_size;
	u64 num_refs;
	u64 extent_flags;
	int ret;

	/*
	 * If we don't have skinny metadata, don't bother doing anything
	 * different
	 */
	if (metadata && !btrfs_fs_incompat(fs_info, SKINNY_METADATA)) {
		offset = fs_info->nodesize;
		metadata = 0;
	}

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

	if (!trans) {
		path->skip_locking = 1;
		path->search_commit_root = 1;
	}

search_again:
	key.objectid = bytenr;
	key.offset = offset;
	if (metadata)
		key.type = BTRFS_METADATA_ITEM_KEY;
	else
		key.type = BTRFS_EXTENT_ITEM_KEY;

	ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0);
	if (ret < 0)
		goto out_free;

	if (ret > 0 && metadata && key.type == BTRFS_METADATA_ITEM_KEY) {
		if (path->slots[0]) {
			path->slots[0]--;
			btrfs_item_key_to_cpu(path->nodes[0], &key,
					      path->slots[0]);
			if (key.objectid == bytenr &&
			    key.type == BTRFS_EXTENT_ITEM_KEY &&
			    key.offset == fs_info->nodesize)
				ret = 0;
		}
	}

	if (ret == 0) {
		leaf = path->nodes[0];
		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
		if (item_size >= sizeof(*ei)) {
			ei = btrfs_item_ptr(leaf, path->slots[0],
					    struct btrfs_extent_item);
			num_refs = btrfs_extent_refs(leaf, ei);
			extent_flags = btrfs_extent_flags(leaf, ei);
		} else {
			ret = -EINVAL;
			btrfs_print_v0_err(fs_info);
			if (trans)
				btrfs_abort_transaction(trans, ret);
			else
				btrfs_handle_fs_error(fs_info, ret, NULL);

			goto out_free;
		}

		BUG_ON(num_refs == 0);
	} else {
		num_refs = 0;
		extent_flags = 0;
		ret = 0;
	}

	if (!trans)
		goto out;

	delayed_refs = &trans->transaction->delayed_refs;
	spin_lock(&delayed_refs->lock);
	head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
	if (head) {
		if (!mutex_trylock(&head->mutex)) {
			refcount_inc(&head->refs);
			spin_unlock(&delayed_refs->lock);

			btrfs_release_path(path);

			/*
			 * Mutex was contended, block until it's released and try
			 * again
			 */
			mutex_lock(&head->mutex);
			mutex_unlock(&head->mutex);
			btrfs_put_delayed_ref_head(head);
			goto search_again;
		}
		spin_lock(&head->lock);
		if (head->extent_op && head->extent_op->update_flags)
			extent_flags |= head->extent_op->flags_to_set;
		else
			BUG_ON(num_refs == 0);

		num_refs += head->ref_mod;
		spin_unlock(&head->lock);
		mutex_unlock(&head->mutex);
	}
	spin_unlock(&delayed_refs->lock);
out:
	WARN_ON(num_refs == 0);
	if (refs)
		*refs = num_refs;
	if (flags)
		*flags = extent_flags;
out_free:
	btrfs_free_path(path);
	return ret;
}

/*
 * Back reference rules.  Back refs have three main goals:
 *
 * 1) differentiate between all holders of references to an extent so that
 *    when a reference is dropped we can make sure it was a valid reference
 *    before freeing the extent.
 *
 * 2) Provide enough information to quickly find the holders of an extent
 *    if we notice a given block is corrupted or bad.
 *
 * 3) Make it easy to migrate blocks for FS shrinking or storage pool
 *    maintenance.  This is actually the same as #2, but with a slightly
 *    different use case.
 *
 * There are two kinds of back refs. The implicit back refs is optimized
 * for pointers in non-shared tree blocks. For a given pointer in a block,
 * back refs of this kind provide information about the block's owner tree
 * and the pointer's key. These information allow us to find the block by
 * b-tree searching. The full back refs is for pointers in tree blocks not
 * referenced by their owner trees. The location of tree block is recorded
 * in the back refs. Actually the full back refs is generic, and can be
 * used in all cases the implicit back refs is used. The major shortcoming
 * of the full back refs is its overhead. Every time a tree block gets
 * COWed, we have to update back refs entry for all pointers in it.
 *
 * For a newly allocated tree block, we use implicit back refs for
 * pointers in it. This means most tree related operations only involve
 * implicit back refs. For a tree block created in old transaction, the
 * only way to drop a reference to it is COW it. So we can detect the
 * event that tree block loses its owner tree's reference and do the
 * back refs conversion.
 *
 * When a tree block is COWed through a tree, there are four cases:
 *
 * The reference count of the block is one and the tree is the block's
 * owner tree. Nothing to do in this case.
 *
 * The reference count of the block is one and the tree is not the
 * block's owner tree. In this case, full back refs is used for pointers
 * in the block. Remove these full back refs, add implicit back refs for
 * every pointers in the new block.
 *
 * The reference count of the block is greater than one and the tree is
 * the block's owner tree. In this case, implicit back refs is used for
 * pointers in the block. Add full back refs for every pointers in the
 * block, increase lower level extents' reference counts. The original
 * implicit back refs are entailed to the new block.
 *
 * The reference count of the block is greater than one and the tree is
 * not the block's owner tree. Add implicit back refs for every pointer in
 * the new block, increase lower level extents' reference count.
 *
 * Back Reference Key composing:
 *
 * The key objectid corresponds to the first byte in the extent,
 * The key type is used to differentiate between types of back refs.
 * There are different meanings of the key offset for different types
 * of back refs.
 *
 * File extents can be referenced by:
 *
 * - multiple snapshots, subvolumes, or different generations in one subvol
 * - different files inside a single subvolume
 * - different offsets inside a file (bookend extents in file.c)
 *
 * The extent ref structure for the implicit back refs has fields for:
 *
 * - Objectid of the subvolume root
 * - objectid of the file holding the reference
 * - original offset in the file
 * - how many bookend extents
 *
 * The key offset for the implicit back refs is hash of the first
 * three fields.
 *
 * The extent ref structure for the full back refs has field for:
 *
 * - number of pointers in the tree leaf
 *
 * The key offset for the implicit back refs is the first byte of
 * the tree leaf
 *
 * When a file extent is allocated, The implicit back refs is used.
 * the fields are filled in:
 *
 *     (root_key.objectid, inode objectid, offset in file, 1)
 *
 * When a file extent is removed file truncation, we find the
 * corresponding implicit back refs and check the following fields:
 *
 *     (btrfs_header_owner(leaf), inode objectid, offset in file)
 *
 * Btree extents can be referenced by:
 *
 * - Different subvolumes
 *
 * Both the implicit back refs and the full back refs for tree blocks
 * only consist of key. The key offset for the implicit back refs is
 * objectid of block's owner tree. The key offset for the full back refs
 * is the first byte of parent block.
 *
 * When implicit back refs is used, information about the lowest key and
 * level of the tree block are required. These information are stored in
 * tree block info structure.
 */

/*
 * is_data == BTRFS_REF_TYPE_BLOCK, tree block type is required,
 * is_data == BTRFS_REF_TYPE_DATA, data type is requiried,
 * is_data == BTRFS_REF_TYPE_ANY, either type is OK.
 */
int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
				     struct btrfs_extent_inline_ref *iref,
				     enum btrfs_inline_ref_type is_data)
{
	int type = btrfs_extent_inline_ref_type(eb, iref);
	u64 offset = btrfs_extent_inline_ref_offset(eb, iref);

	if (type == BTRFS_TREE_BLOCK_REF_KEY ||
	    type == BTRFS_SHARED_BLOCK_REF_KEY ||
	    type == BTRFS_SHARED_DATA_REF_KEY ||
	    type == BTRFS_EXTENT_DATA_REF_KEY) {
		if (is_data == BTRFS_REF_TYPE_BLOCK) {
			if (type == BTRFS_TREE_BLOCK_REF_KEY)
				return type;
			if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
				ASSERT(eb->fs_info);
				/*
				 * Every shared one has parent tree
				 * block, which must be aligned to
				 * nodesize.
				 */
				if (offset &&
				    IS_ALIGNED(offset, eb->fs_info->nodesize))
					return type;
			}
		} else if (is_data == BTRFS_REF_TYPE_DATA) {
			if (type == BTRFS_EXTENT_DATA_REF_KEY)
				return type;
			if (type == BTRFS_SHARED_DATA_REF_KEY) {
				ASSERT(eb->fs_info);
				/*
				 * Every shared one has parent tree
				 * block, which must be aligned to
				 * nodesize.
				 */
				if (offset &&
				    IS_ALIGNED(offset, eb->fs_info->nodesize))
					return type;
			}
		} else {
			ASSERT(is_data == BTRFS_REF_TYPE_ANY);
			return type;
		}
	}

	btrfs_print_leaf((struct extent_buffer *)eb);
	btrfs_err(eb->fs_info, "eb %llu invalid extent inline ref type %d",
		  eb->start, type);
	WARN_ON(1);

	return BTRFS_REF_TYPE_INVALID;
}

static u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset)
{
	u32 high_crc = ~(u32)0;
	u32 low_crc = ~(u32)0;
	__le64 lenum;

	lenum = cpu_to_le64(root_objectid);
	high_crc = crc32c(high_crc, &lenum, sizeof(lenum));
	lenum = cpu_to_le64(owner);
	low_crc = crc32c(low_crc, &lenum, sizeof(lenum));
	lenum = cpu_to_le64(offset);
	low_crc = crc32c(low_crc, &lenum, sizeof(lenum));

	return ((u64)high_crc << 31) ^ (u64)low_crc;
}

static u64 hash_extent_data_ref_item(struct extent_buffer *leaf,
				     struct btrfs_extent_data_ref *ref)
{
	return hash_extent_data_ref(btrfs_extent_data_ref_root(leaf, ref),
				    btrfs_extent_data_ref_objectid(leaf, ref),
				    btrfs_extent_data_ref_offset(leaf, ref));
}

static int match_extent_data_ref(struct extent_buffer *leaf,
				 struct btrfs_extent_data_ref *ref,
				 u64 root_objectid, u64 owner, u64 offset)
{
	if (btrfs_extent_data_ref_root(leaf, ref) != root_objectid ||
	    btrfs_extent_data_ref_objectid(leaf, ref) != owner ||
	    btrfs_extent_data_ref_offset(leaf, ref) != offset)
		return 0;
	return 1;
}

static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
					   struct btrfs_path *path,
					   u64 bytenr, u64 parent,
					   u64 root_objectid,
					   u64 owner, u64 offset)
{
	struct btrfs_root *root = trans->fs_info->extent_root;
	struct btrfs_key key;
	struct btrfs_extent_data_ref *ref;
	struct extent_buffer *leaf;
	u32 nritems;
	int ret;
	int recow;
	int err = -ENOENT;

	key.objectid = bytenr;
	if (parent) {
		key.type = BTRFS_SHARED_DATA_REF_KEY;
		key.offset = parent;
	} else {
		key.type = BTRFS_EXTENT_DATA_REF_KEY;
		key.offset = hash_extent_data_ref(root_objectid,
						  owner, offset);
	}
again:
	recow = 0;
	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
	if (ret < 0) {
		err = ret;
		goto fail;
	}

	if (parent) {
		if (!ret)
			return 0;
		goto fail;
	}

	leaf = path->nodes[0];
	nritems = btrfs_header_nritems(leaf);
	while (1) {
		if (path->slots[0] >= nritems) {
			ret = btrfs_next_leaf(root, path);
			if (ret < 0)
				err = ret;
			if (ret)
				goto fail;

			leaf = path->nodes[0];
			nritems = btrfs_header_nritems(leaf);
			recow = 1;
		}

		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		if (key.objectid != bytenr ||
		    key.type != BTRFS_EXTENT_DATA_REF_KEY)
			goto fail;

		ref = btrfs_item_ptr(leaf, path->slots[0],
				     struct btrfs_extent_data_ref);

		if (match_extent_data_ref(leaf, ref, root_objectid,
					  owner, offset)) {
			if (recow) {
				btrfs_release_path(path);
				goto again;
			}
			err = 0;
			break;
		}
		path->slots[0]++;
	}
fail:
	return err;
}

static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
					   struct btrfs_path *path,
					   u64 bytenr, u64 parent,
					   u64 root_objectid, u64 owner,
					   u64 offset, int refs_to_add)
{
	struct btrfs_root *root = trans->fs_info->extent_root;
	struct btrfs_key key;
	struct extent_buffer *leaf;
	u32 size;
	u32 num_refs;
	int ret;

	key.objectid = bytenr;
	if (parent) {
		key.type = BTRFS_SHARED_DATA_REF_KEY;
		key.offset = parent;
		size = sizeof(struct btrfs_shared_data_ref);
	} else {
		key.type = BTRFS_EXTENT_DATA_REF_KEY;
		key.offset = hash_extent_data_ref(root_objectid,
						  owner, offset);
		size = sizeof(struct btrfs_extent_data_ref);
	}

	ret = btrfs_insert_empty_item(trans, root, path, &key, size);
	if (ret && ret != -EEXIST)
		goto fail;

	leaf = path->nodes[0];
	if (parent) {
		struct btrfs_shared_data_ref *ref;
		ref = btrfs_item_ptr(leaf, path->slots[0],
				     struct btrfs_shared_data_ref);
		if (ret == 0) {
			btrfs_set_shared_data_ref_count(leaf, ref, refs_to_add);
		} else {
			num_refs = btrfs_shared_data_ref_count(leaf, ref);
			num_refs += refs_to_add;
			btrfs_set_shared_data_ref_count(leaf, ref, num_refs);
		}
	} else {
		struct btrfs_extent_data_ref *ref;
		while (ret == -EEXIST) {
			ref = btrfs_item_ptr(leaf, path->slots[0],
					     struct btrfs_extent_data_ref);
			if (match_extent_data_ref(leaf, ref, root_objectid,
						  owner, offset))
				break;
			btrfs_release_path(path);
			key.offset++;
			ret = btrfs_insert_empty_item(trans, root, path, &key,
						      size);
			if (ret && ret != -EEXIST)
				goto fail;

			leaf = path->nodes[0];
		}
		ref = btrfs_item_ptr(leaf, path->slots[0],
				     struct btrfs_extent_data_ref);
		if (ret == 0) {
			btrfs_set_extent_data_ref_root(leaf, ref,
						       root_objectid);
			btrfs_set_extent_data_ref_objectid(leaf, ref, owner);
			btrfs_set_extent_data_ref_offset(leaf, ref, offset);
			btrfs_set_extent_data_ref_count(leaf, ref, refs_to_add);
		} else {
			num_refs = btrfs_extent_data_ref_count(leaf, ref);
			num_refs += refs_to_add;
			btrfs_set_extent_data_ref_count(leaf, ref, num_refs);
		}
	}
	btrfs_mark_buffer_dirty(leaf);
	ret = 0;
fail:
	btrfs_release_path(path);
	return ret;
}

static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
					   struct btrfs_path *path,
					   int refs_to_drop, int *last_ref)
{
	struct btrfs_key key;
	struct btrfs_extent_data_ref *ref1 = NULL;
	struct btrfs_shared_data_ref *ref2 = NULL;
	struct extent_buffer *leaf;
	u32 num_refs = 0;
	int ret = 0;

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

	if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
		ref1 = btrfs_item_ptr(leaf, path->slots[0],
				      struct btrfs_extent_data_ref);
		num_refs = btrfs_extent_data_ref_count(leaf, ref1);
	} else if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
		ref2 = btrfs_item_ptr(leaf, path->slots[0],
				      struct btrfs_shared_data_ref);
		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
	} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
		btrfs_print_v0_err(trans->fs_info);
		btrfs_abort_transaction(trans, -EINVAL);
		return -EINVAL;
	} else {
		BUG();
	}

	BUG_ON(num_refs < refs_to_drop);
	num_refs -= refs_to_drop;

	if (num_refs == 0) {
		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
		*last_ref = 1;
	} else {
		if (key.type == BTRFS_EXTENT_DATA_REF_KEY)
			btrfs_set_extent_data_ref_count(leaf, ref1, num_refs);
		else if (key.type == BTRFS_SHARED_DATA_REF_KEY)
			btrfs_set_shared_data_ref_count(leaf, ref2, num_refs);
		btrfs_mark_buffer_dirty(leaf);
	}
	return ret;
}

static noinline u32 extent_data_ref_count(struct btrfs_path *path,
					  struct btrfs_extent_inline_ref *iref)
{
	struct btrfs_key key;
	struct extent_buffer *leaf;
	struct btrfs_extent_data_ref *ref1;
	struct btrfs_shared_data_ref *ref2;
	u32 num_refs = 0;
	int type;

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

	BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
	if (iref) {
		/*
		 * If type is invalid, we should have bailed out earlier than
		 * this call.
		 */
		type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA);
		ASSERT(type != BTRFS_REF_TYPE_INVALID);
		if (type == BTRFS_EXTENT_DATA_REF_KEY) {
			ref1 = (struct btrfs_extent_data_ref *)(&iref->offset);
			num_refs = btrfs_extent_data_ref_count(leaf, ref1);
		} else {
			ref2 = (struct btrfs_shared_data_ref *)(iref + 1);
			num_refs = btrfs_shared_data_ref_count(leaf, ref2);
		}
	} else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
		ref1 = btrfs_item_ptr(leaf, path->slots[0],
				      struct btrfs_extent_data_ref);
		num_refs = btrfs_extent_data_ref_count(leaf, ref1);
	} else if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
		ref2 = btrfs_item_ptr(leaf, path->slots[0],
				      struct btrfs_shared_data_ref);
		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
	} else {
		WARN_ON(1);
	}
	return num_refs;
}

static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
					  struct btrfs_path *path,
					  u64 bytenr, u64 parent,
					  u64 root_objectid)
{
	struct btrfs_root *root = trans->fs_info->extent_root;
	struct btrfs_key key;
	int ret;

	key.objectid = bytenr;
	if (parent) {
		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
		key.offset = parent;
	} else {
		key.type = BTRFS_TREE_BLOCK_REF_KEY;
		key.offset = root_objectid;
	}

	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
	if (ret > 0)
		ret = -ENOENT;
	return ret;
}

static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
					  struct btrfs_path *path,
					  u64 bytenr, u64 parent,
					  u64 root_objectid)
{
	struct btrfs_key key;
	int ret;

	key.objectid = bytenr;
	if (parent) {
		key.type = BTRFS_SHARED_BLOCK_REF_KEY;
		key.offset = parent;
	} else {
		key.type = BTRFS_TREE_BLOCK_REF_KEY;
		key.offset = root_objectid;
	}

	ret = btrfs_insert_empty_item(trans, trans->fs_info->extent_root,
				      path, &key, 0);
	btrfs_release_path(path);
	return ret;
}

static inline int extent_ref_type(u64 parent, u64 owner)
{
	int type;
	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
		if (parent > 0)
			type = BTRFS_SHARED_BLOCK_REF_KEY;
		else
			type = BTRFS_TREE_BLOCK_REF_KEY;
	} else {
		if (parent > 0)
			type = BTRFS_SHARED_DATA_REF_KEY;
		else
			type = BTRFS_EXTENT_DATA_REF_KEY;
	}
	return type;
}

static int find_next_key(struct btrfs_path *path, int level,
			 struct btrfs_key *key)

{
	for (; level < BTRFS_MAX_LEVEL; level++) {
		if (!path->nodes[level])
			break;
		if (path->slots[level] + 1 >=
		    btrfs_header_nritems(path->nodes[level]))
			continue;
		if (level == 0)
			btrfs_item_key_to_cpu(path->nodes[level], key,
					      path->slots[level] + 1);
		else
			btrfs_node_key_to_cpu(path->nodes[level], key,
					      path->slots[level] + 1);
		return 0;
	}
	return 1;
}

/*
 * look for inline back ref. if back ref is found, *ref_ret is set
 * to the address of inline back ref, and 0 is returned.
 *
 * if back ref isn't found, *ref_ret is set to the address where it
 * should be inserted, and -ENOENT is returned.
 *
 * if insert is true and there are too many inline back refs, the path
 * points to the extent item, and -EAGAIN is returned.
 *
 * NOTE: inline back refs are ordered in the same way that back ref
 *	 items in the tree are ordered.
 */
static noinline_for_stack
int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
				 struct btrfs_path *path,
				 struct btrfs_extent_inline_ref **ref_ret,
				 u64 bytenr, u64 num_bytes,
				 u64 parent, u64 root_objectid,
				 u64 owner, u64 offset, int insert)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *root = fs_info->extent_root;
	struct btrfs_key key;
	struct extent_buffer *leaf;
	struct btrfs_extent_item *ei;
	struct btrfs_extent_inline_ref *iref;
	u64 flags;
	u64 item_size;
	unsigned long ptr;
	unsigned long end;
	int extra_size;
	int type;
	int want;
	int ret;
	int err = 0;
	bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);
	int needed;

	key.objectid = bytenr;
	key.type = BTRFS_EXTENT_ITEM_KEY;
	key.offset = num_bytes;

	want = extent_ref_type(parent, owner);
	if (insert) {
		extra_size = btrfs_extent_inline_ref_size(want);
		path->keep_locks = 1;
	} else
		extra_size = -1;

	/*
	 * Owner is our level, so we can just add one to get the level for the
	 * block we are interested in.
	 */
	if (skinny_metadata && owner < BTRFS_FIRST_FREE_OBJECTID) {
		key.type = BTRFS_METADATA_ITEM_KEY;
		key.offset = owner;
	}

again:
	ret = btrfs_search_slot(trans, root, &key, path, extra_size, 1);
	if (ret < 0) {
		err = ret;
		goto out;
	}

	/*
	 * We may be a newly converted file system which still has the old fat
	 * extent entries for metadata, so try and see if we have one of those.
	 */
	if (ret > 0 && skinny_metadata) {
		skinny_metadata = false;
		if (path->slots[0]) {
			path->slots[0]--;
			btrfs_item_key_to_cpu(path->nodes[0], &key,
					      path->slots[0]);
			if (key.objectid == bytenr &&
			    key.type == BTRFS_EXTENT_ITEM_KEY &&
			    key.offset == num_bytes)
				ret = 0;
		}
		if (ret) {
			key.objectid = bytenr;
			key.type = BTRFS_EXTENT_ITEM_KEY;
			key.offset = num_bytes;
			btrfs_release_path(path);
			goto again;
		}
	}

	if (ret && !insert) {
		err = -ENOENT;
		goto out;
	} else if (WARN_ON(ret)) {
		err = -EIO;
		goto out;
	}

	leaf = path->nodes[0];
	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
	if (unlikely(item_size < sizeof(*ei))) {
		err = -EINVAL;
		btrfs_print_v0_err(fs_info);
		btrfs_abort_transaction(trans, err);
		goto out;
	}

	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
	flags = btrfs_extent_flags(leaf, ei);

	ptr = (unsigned long)(ei + 1);
	end = (unsigned long)ei + item_size;

	if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK && !skinny_metadata) {
		ptr += sizeof(struct btrfs_tree_block_info);
		BUG_ON(ptr > end);
	}

	if (owner >= BTRFS_FIRST_FREE_OBJECTID)
		needed = BTRFS_REF_TYPE_DATA;
	else
		needed = BTRFS_REF_TYPE_BLOCK;

	err = -ENOENT;
	while (1) {
		if (ptr >= end) {
			WARN_ON(ptr > end);
			break;
		}
		iref = (struct btrfs_extent_inline_ref *)ptr;
		type = btrfs_get_extent_inline_ref_type(leaf, iref, needed);
		if (type == BTRFS_REF_TYPE_INVALID) {
			err = -EUCLEAN;
			goto out;
		}

		if (want < type)
			break;
		if (want > type) {
			ptr += btrfs_extent_inline_ref_size(type);
			continue;
		}

		if (type == BTRFS_EXTENT_DATA_REF_KEY) {
			struct btrfs_extent_data_ref *dref;
			dref = (struct btrfs_extent_data_ref *)(&iref->offset);
			if (match_extent_data_ref(leaf, dref, root_objectid,
						  owner, offset)) {
				err = 0;
				break;
			}
			if (hash_extent_data_ref_item(leaf, dref) <
			    hash_extent_data_ref(root_objectid, owner, offset))
				break;
		} else {
			u64 ref_offset;
			ref_offset = btrfs_extent_inline_ref_offset(leaf, iref);
			if (parent > 0) {
				if (parent == ref_offset) {
					err = 0;
					break;
				}
				if (ref_offset < parent)
					break;
			} else {
				if (root_objectid == ref_offset) {
					err = 0;
					break;
				}
				if (ref_offset < root_objectid)
					break;
			}
		}
		ptr += btrfs_extent_inline_ref_size(type);
	}
	if (err == -ENOENT && insert) {
		if (item_size + extra_size >=
		    BTRFS_MAX_EXTENT_ITEM_SIZE(root)) {
			err = -EAGAIN;
			goto out;
		}
		/*
		 * To add new inline back ref, we have to make sure
		 * there is no corresponding back ref item.
		 * For simplicity, we just do not add new inline back
		 * ref if there is any kind of item for this block
		 */
		if (find_next_key(path, 0, &key) == 0 &&
		    key.objectid == bytenr &&
		    key.type < BTRFS_BLOCK_GROUP_ITEM_KEY) {
			err = -EAGAIN;
			goto out;
		}
	}
	*ref_ret = (struct btrfs_extent_inline_ref *)ptr;
out:
	if (insert) {
		path->keep_locks = 0;
		btrfs_unlock_up_safe(path, 1);
	}
	return err;
}

/*
 * helper to add new inline back ref
 */
static noinline_for_stack
void setup_inline_extent_backref(struct btrfs_fs_info *fs_info,
				 struct btrfs_path *path,
				 struct btrfs_extent_inline_ref *iref,
				 u64 parent, u64 root_objectid,
				 u64 owner, u64 offset, int refs_to_add,
				 struct btrfs_delayed_extent_op *extent_op)
{
	struct extent_buffer *leaf;
	struct btrfs_extent_item *ei;
	unsigned long ptr;
	unsigned long end;
	unsigned long item_offset;
	u64 refs;
	int size;
	int type;

	leaf = path->nodes[0];
	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
	item_offset = (unsigned long)iref - (unsigned long)ei;

	type = extent_ref_type(parent, owner);
	size = btrfs_extent_inline_ref_size(type);

	btrfs_extend_item(path, size);

	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
	refs = btrfs_extent_refs(leaf, ei);
	refs += refs_to_add;
	btrfs_set_extent_refs(leaf, ei, refs);
	if (extent_op)
		__run_delayed_extent_op(extent_op, leaf, ei);

	ptr = (unsigned long)ei + item_offset;
	end = (unsigned long)ei + btrfs_item_size_nr(leaf, path->slots[0]);
	if (ptr < end - size)
		memmove_extent_buffer(leaf, ptr + size, ptr,
				      end - size - ptr);

	iref = (struct btrfs_extent_inline_ref *)ptr;
	btrfs_set_extent_inline_ref_type(leaf, iref, type);
	if (type == BTRFS_EXTENT_DATA_REF_KEY) {
		struct btrfs_extent_data_ref *dref;
		dref = (struct btrfs_extent_data_ref *)(&iref->offset);
		btrfs_set_extent_data_ref_root(leaf, dref, root_objectid);
		btrfs_set_extent_data_ref_objectid(leaf, dref, owner);
		btrfs_set_extent_data_ref_offset(leaf, dref, offset);
		btrfs_set_extent_data_ref_count(leaf, dref, refs_to_add);
	} else if (type == BTRFS_SHARED_DATA_REF_KEY) {
		struct btrfs_shared_data_ref *sref;
		sref = (struct btrfs_shared_data_ref *)(iref + 1);
		btrfs_set_shared_data_ref_count(leaf, sref, refs_to_add);
		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
	} else if (type == BTRFS_SHARED_BLOCK_REF_KEY) {
		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
	} else {
		btrfs_set_extent_inline_ref_offset(leaf, iref, root_objectid);
	}
	btrfs_mark_buffer_dirty(leaf);
}

static int lookup_extent_backref(struct btrfs_trans_handle *trans,
				 struct btrfs_path *path,
				 struct btrfs_extent_inline_ref **ref_ret,
				 u64 bytenr, u64 num_bytes, u64 parent,
				 u64 root_objectid, u64 owner, u64 offset)
{
	int ret;

	ret = lookup_inline_extent_backref(trans, path, ref_ret, bytenr,
					   num_bytes, parent, root_objectid,
					   owner, offset, 0);
	if (ret != -ENOENT)
		return ret;

	btrfs_release_path(path);
	*ref_ret = NULL;

	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
		ret = lookup_tree_block_ref(trans, path, bytenr, parent,
					    root_objectid);
	} else {
		ret = lookup_extent_data_ref(trans, path, bytenr, parent,
					     root_objectid, owner, offset);
	}
	return ret;
}

/*
 * helper to update/remove inline back ref
 */
static noinline_for_stack
void update_inline_extent_backref(struct btrfs_path *path,
				  struct btrfs_extent_inline_ref *iref,
				  int refs_to_mod,
				  struct btrfs_delayed_extent_op *extent_op,
				  int *last_ref)
{
	struct extent_buffer *leaf = path->nodes[0];
	struct btrfs_extent_item *ei;
	struct btrfs_extent_data_ref *dref = NULL;
	struct btrfs_shared_data_ref *sref = NULL;
	unsigned long ptr;
	unsigned long end;
	u32 item_size;
	int size;
	int type;
	u64 refs;

	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
	refs = btrfs_extent_refs(leaf, ei);
	WARN_ON(refs_to_mod < 0 && refs + refs_to_mod <= 0);
	refs += refs_to_mod;
	btrfs_set_extent_refs(leaf, ei, refs);
	if (extent_op)
		__run_delayed_extent_op(extent_op, leaf, ei);

	/*
	 * If type is invalid, we should have bailed out after
	 * lookup_inline_extent_backref().
	 */
	type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_ANY);
	ASSERT(type != BTRFS_REF_TYPE_INVALID);

	if (type == BTRFS_EXTENT_DATA_REF_KEY) {
		dref = (struct btrfs_extent_data_ref *)(&iref->offset);
		refs = btrfs_extent_data_ref_count(leaf, dref);
	} else if (type == BTRFS_SHARED_DATA_REF_KEY) {
		sref = (struct btrfs_shared_data_ref *)(iref + 1);
		refs = btrfs_shared_data_ref_count(leaf, sref);
	} else {
		refs = 1;
		BUG_ON(refs_to_mod != -1);
	}

	BUG_ON(refs_to_mod < 0 && refs < -refs_to_mod);
	refs += refs_to_mod;

	if (refs > 0) {
		if (type == BTRFS_EXTENT_DATA_REF_KEY)
			btrfs_set_extent_data_ref_count(leaf, dref, refs);
		else
			btrfs_set_shared_data_ref_count(leaf, sref, refs);
	} else {
		*last_ref = 1;
		size =  btrfs_extent_inline_ref_size(type);
		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
		ptr = (unsigned long)iref;
		end = (unsigned long)ei + item_size;
		if (ptr + size < end)
			memmove_extent_buffer(leaf, ptr, ptr + size,
					      end - ptr - size);
		item_size -= size;
		btrfs_truncate_item(path, item_size, 1);
	}
	btrfs_mark_buffer_dirty(leaf);
}

static noinline_for_stack
int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
				 struct btrfs_path *path,
				 u64 bytenr, u64 num_bytes, u64 parent,
				 u64 root_objectid, u64 owner,
				 u64 offset, int refs_to_add,
				 struct btrfs_delayed_extent_op *extent_op)
{
	struct btrfs_extent_inline_ref *iref;
	int ret;

	ret = lookup_inline_extent_backref(trans, path, &iref, bytenr,
					   num_bytes, parent, root_objectid,
					   owner, offset, 1);
	if (ret == 0) {
		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
		update_inline_extent_backref(path, iref, refs_to_add,
					     extent_op, NULL);
	} else if (ret == -ENOENT) {
		setup_inline_extent_backref(trans->fs_info, path, iref, parent,
					    root_objectid, owner, offset,
					    refs_to_add, extent_op);
		ret = 0;
	}
	return ret;
}

static int insert_extent_backref(struct btrfs_trans_handle *trans,
				 struct btrfs_path *path,
				 u64 bytenr, u64 parent, u64 root_objectid,
				 u64 owner, u64 offset, int refs_to_add)
{
	int ret;
	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
		BUG_ON(refs_to_add != 1);
		ret = insert_tree_block_ref(trans, path, bytenr, parent,
					    root_objectid);
	} else {
		ret = insert_extent_data_ref(trans, path, bytenr, parent,
					     root_objectid, owner, offset,
					     refs_to_add);
	}
	return ret;
}

static int remove_extent_backref(struct btrfs_trans_handle *trans,
				 struct btrfs_path *path,
				 struct btrfs_extent_inline_ref *iref,
				 int refs_to_drop, int is_data, int *last_ref)
{
	int ret = 0;

	BUG_ON(!is_data && refs_to_drop != 1);
	if (iref) {
		update_inline_extent_backref(path, iref, -refs_to_drop, NULL,
					     last_ref);
	} else if (is_data) {
		ret = remove_extent_data_ref(trans, path, refs_to_drop,
					     last_ref);
	} else {
		*last_ref = 1;
		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
	}
	return ret;
}

static int btrfs_issue_discard(struct block_device *bdev, u64 start, u64 len,
			       u64 *discarded_bytes)
{
	int j, ret = 0;
	u64 bytes_left, end;
	u64 aligned_start = ALIGN(start, 1 << 9);

	if (WARN_ON(start != aligned_start)) {
		len -= aligned_start - start;
		len = round_down(len, 1 << 9);
		start = aligned_start;
	}

	*discarded_bytes = 0;

	if (!len)
		return 0;

	end = start + len;
	bytes_left = len;

	/* Skip any superblocks on this device. */
	for (j = 0; j < BTRFS_SUPER_MIRROR_MAX; j++) {
		u64 sb_start = btrfs_sb_offset(j);
		u64 sb_end = sb_start + BTRFS_SUPER_INFO_SIZE;
		u64 size = sb_start - start;

		if (!in_range(sb_start, start, bytes_left) &&
		    !in_range(sb_end, start, bytes_left) &&
		    !in_range(start, sb_start, BTRFS_SUPER_INFO_SIZE))
			continue;

		/*
		 * Superblock spans beginning of range.  Adjust start and
		 * try again.
		 */
		if (sb_start <= start) {
			start += sb_end - start;
			if (start > end) {
				bytes_left = 0;
				break;
			}
			bytes_left = end - start;
			continue;
		}

		if (size) {
			ret = blkdev_issue_discard(bdev, start >> 9, size >> 9,
						   GFP_NOFS, 0);
			if (!ret)
				*discarded_bytes += size;
			else if (ret != -EOPNOTSUPP)
				return ret;
		}

		start = sb_end;
		if (start > end) {
			bytes_left = 0;
			break;
		}
		bytes_left = end - start;
	}

	if (bytes_left) {
		ret = blkdev_issue_discard(bdev, start >> 9, bytes_left >> 9,
					   GFP_NOFS, 0);
		if (!ret)
			*discarded_bytes += bytes_left;
	}
	return ret;
}

int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
			 u64 num_bytes, u64 *actual_bytes)
{
	int ret;
	u64 discarded_bytes = 0;
	struct btrfs_bio *bbio = NULL;


	/*
	 * Avoid races with device replace and make sure our bbio has devices
	 * associated to its stripes that don't go away while we are discarding.
	 */
	btrfs_bio_counter_inc_blocked(fs_info);
	/* Tell the block device(s) that the sectors can be discarded */
	ret = btrfs_map_block(fs_info, BTRFS_MAP_DISCARD, bytenr, &num_bytes,
			      &bbio, 0);
	/* Error condition is -ENOMEM */
	if (!ret) {
		struct btrfs_bio_stripe *stripe = bbio->stripes;
		int i;


		for (i = 0; i < bbio->num_stripes; i++, stripe++) {
			u64 bytes;
			struct request_queue *req_q;

			if (!stripe->dev->bdev) {
				ASSERT(btrfs_test_opt(fs_info, DEGRADED));
				continue;
			}
			req_q = bdev_get_queue(stripe->dev->bdev);
			if (!blk_queue_discard(req_q))
				continue;

			ret = btrfs_issue_discard(stripe->dev->bdev,
						  stripe->physical,
						  stripe->length,
						  &bytes);
			if (!ret)
				discarded_bytes += bytes;
			else if (ret != -EOPNOTSUPP)
				break; /* Logic errors or -ENOMEM, or -EIO but I don't know how that could happen JDM */

			/*
			 * Just in case we get back EOPNOTSUPP for some reason,
			 * just ignore the return value so we don't screw up
			 * people calling discard_extent.
			 */
			ret = 0;
		}
		btrfs_put_bbio(bbio);
	}
	btrfs_bio_counter_dec(fs_info);

	if (actual_bytes)
		*actual_bytes = discarded_bytes;


	if (ret == -EOPNOTSUPP)
		ret = 0;
	return ret;
}

/* Can return -ENOMEM */
int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
			 struct btrfs_ref *generic_ref)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	int old_ref_mod, new_ref_mod;
	int ret;

	ASSERT(generic_ref->type != BTRFS_REF_NOT_SET &&
	       generic_ref->action);
	BUG_ON(generic_ref->type == BTRFS_REF_METADATA &&
	       generic_ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID);

	if (generic_ref->type == BTRFS_REF_METADATA)
		ret = btrfs_add_delayed_tree_ref(trans, generic_ref,
				NULL, &old_ref_mod, &new_ref_mod);
	else
		ret = btrfs_add_delayed_data_ref(trans, generic_ref, 0,
						 &old_ref_mod, &new_ref_mod);

	btrfs_ref_tree_mod(fs_info, generic_ref);

	if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0)
		add_pinned_bytes(fs_info, generic_ref);

	return ret;
}

/*
 * __btrfs_inc_extent_ref - insert backreference for a given extent
 *
 * @trans:	    Handle of transaction
 *
 * @node:	    The delayed ref node used to get the bytenr/length for
 *		    extent whose references are incremented.
 *
 * @parent:	    If this is a shared extent (BTRFS_SHARED_DATA_REF_KEY/
 *		    BTRFS_SHARED_BLOCK_REF_KEY) then it holds the logical
 *		    bytenr of the parent block. Since new extents are always
 *		    created with indirect references, this will only be the case
 *		    when relocating a shared extent. In that case, root_objectid
 *		    will be BTRFS_TREE_RELOC_OBJECTID. Otheriwse, parent must
 *		    be 0
 *
 * @root_objectid:  The id of the root where this modification has originated,
 *		    this can be either one of the well-known metadata trees or
 *		    the subvolume id which references this extent.
 *
 * @owner:	    For data extents it is the inode number of the owning file.
 *		    For metadata extents this parameter holds the level in the
 *		    tree of the extent.
 *
 * @offset:	    For metadata extents the offset is ignored and is currently
 *		    always passed as 0. For data extents it is the fileoffset
 *		    this extent belongs to.
 *
 * @refs_to_add     Number of references to add
 *
 * @extent_op       Pointer to a structure, holding information necessary when
 *                  updating a tree block's flags
 *
 */
static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
				  struct btrfs_delayed_ref_node *node,
				  u64 parent, u64 root_objectid,
				  u64 owner, u64 offset, int refs_to_add,
				  struct btrfs_delayed_extent_op *extent_op)
{
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_extent_item *item;
	struct btrfs_key key;
	u64 bytenr = node->bytenr;
	u64 num_bytes = node->num_bytes;
	u64 refs;
	int ret;

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

	path->reada = READA_FORWARD;
	path->leave_spinning = 1;
	/* this will setup the path even if it fails to insert the back ref */
	ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes,
					   parent, root_objectid, owner,
					   offset, refs_to_add, extent_op);
	if ((ret < 0 && ret != -EAGAIN) || !ret)
		goto out;

	/*
	 * Ok we had -EAGAIN which means we didn't have space to insert and
	 * inline extent ref, so just update the reference count and add a
	 * normal backref.
	 */
	leaf = path->nodes[0];
	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
	refs = btrfs_extent_refs(leaf, item);
	btrfs_set_extent_refs(leaf, item, refs + refs_to_add);
	if (extent_op)
		__run_delayed_extent_op(extent_op, leaf, item);

	btrfs_mark_buffer_dirty(leaf);
	btrfs_release_path(path);

	path->reada = READA_FORWARD;
	path->leave_spinning = 1;
	/* now insert the actual backref */
	ret = insert_extent_backref(trans, path, bytenr, parent, root_objectid,
				    owner, offset, refs_to_add);
	if (ret)
		btrfs_abort_transaction(trans, ret);
out:
	btrfs_free_path(path);
	return ret;
}

static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
				struct btrfs_delayed_ref_node *node,
				struct btrfs_delayed_extent_op *extent_op,
				int insert_reserved)
{
	int ret = 0;
	struct btrfs_delayed_data_ref *ref;
	struct btrfs_key ins;
	u64 parent = 0;
	u64 ref_root = 0;
	u64 flags = 0;

	ins.objectid = node->bytenr;
	ins.offset = node->num_bytes;
	ins.type = BTRFS_EXTENT_ITEM_KEY;

	ref = btrfs_delayed_node_to_data_ref(node);
	trace_run_delayed_data_ref(trans->fs_info, node, ref, node->action);

	if (node->type == BTRFS_SHARED_DATA_REF_KEY)
		parent = ref->parent;
	ref_root = ref->root;

	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
		if (extent_op)
			flags |= extent_op->flags_to_set;
		ret = alloc_reserved_file_extent(trans, parent, ref_root,
						 flags, ref->objectid,
						 ref->offset, &ins,
						 node->ref_mod);
	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
					     ref->objectid, ref->offset,
					     node->ref_mod, extent_op);
	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
		ret = __btrfs_free_extent(trans, node, parent,
					  ref_root, ref->objectid,
					  ref->offset, node->ref_mod,
					  extent_op);
	} else {
		BUG();
	}
	return ret;
}

static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
				    struct extent_buffer *leaf,
				    struct btrfs_extent_item *ei)
{
	u64 flags = btrfs_extent_flags(leaf, ei);
	if (extent_op->update_flags) {
		flags |= extent_op->flags_to_set;
		btrfs_set_extent_flags(leaf, ei, flags);
	}

	if (extent_op->update_key) {
		struct btrfs_tree_block_info *bi;
		BUG_ON(!(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK));
		bi = (struct btrfs_tree_block_info *)(ei + 1);
		btrfs_set_tree_block_key(leaf, bi, &extent_op->key);
	}
}

static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
				 struct btrfs_delayed_ref_head *head,
				 struct btrfs_delayed_extent_op *extent_op)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_key key;
	struct btrfs_path *path;
	struct btrfs_extent_item *ei;
	struct extent_buffer *leaf;
	u32 item_size;
	int ret;
	int err = 0;
	int metadata = !extent_op->is_data;

	if (trans->aborted)
		return 0;

	if (metadata && !btrfs_fs_incompat(fs_info, SKINNY_METADATA))
		metadata = 0;

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

	key.objectid = head->bytenr;

	if (metadata) {
		key.type = BTRFS_METADATA_ITEM_KEY;
		key.offset = extent_op->level;
	} else {
		key.type = BTRFS_EXTENT_ITEM_KEY;
		key.offset = head->num_bytes;
	}

again:
	path->reada = READA_FORWARD;
	path->leave_spinning = 1;
	ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 1);
	if (ret < 0) {
		err = ret;
		goto out;
	}
	if (ret > 0) {
		if (metadata) {
			if (path->slots[0] > 0) {
				path->slots[0]--;
				btrfs_item_key_to_cpu(path->nodes[0], &key,
						      path->slots[0]);
				if (key.objectid == head->bytenr &&
				    key.type == BTRFS_EXTENT_ITEM_KEY &&
				    key.offset == head->num_bytes)
					ret = 0;
			}
			if (ret > 0) {
				btrfs_release_path(path);
				metadata = 0;

				key.objectid = head->bytenr;
				key.offset = head->num_bytes;
				key.type = BTRFS_EXTENT_ITEM_KEY;
				goto again;
			}
		} else {
			err = -EIO;
			goto out;
		}
	}

	leaf = path->nodes[0];
	item_size = btrfs_item_size_nr(leaf, path->slots[0]);

	if (unlikely(item_size < sizeof(*ei))) {
		err = -EINVAL;
		btrfs_print_v0_err(fs_info);
		btrfs_abort_transaction(trans, err);
		goto out;
	}

	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
	__run_delayed_extent_op(extent_op, leaf, ei);

	btrfs_mark_buffer_dirty(leaf);
out:
	btrfs_free_path(path);
	return err;
}

static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
				struct btrfs_delayed_ref_node *node,
				struct btrfs_delayed_extent_op *extent_op,
				int insert_reserved)
{
	int ret = 0;
	struct btrfs_delayed_tree_ref *ref;
	u64 parent = 0;
	u64 ref_root = 0;

	ref = btrfs_delayed_node_to_tree_ref(node);
	trace_run_delayed_tree_ref(trans->fs_info, node, ref, node->action);

	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
		parent = ref->parent;
	ref_root = ref->root;

	if (node->ref_mod != 1) {
		btrfs_err(trans->fs_info,
	"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
			  node->bytenr, node->ref_mod, node->action, ref_root,
			  parent);
		return -EIO;
	}
	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
		BUG_ON(!extent_op || !extent_op->update_flags);
		ret = alloc_reserved_tree_block(trans, node, extent_op);
	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
					     ref->level, 0, 1, extent_op);
	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
		ret = __btrfs_free_extent(trans, node, parent, ref_root,
					  ref->level, 0, 1, extent_op);
	} else {
		BUG();
	}
	return ret;
}

/* helper function to actually process a single delayed ref entry */
static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
			       struct btrfs_delayed_ref_node *node,
			       struct btrfs_delayed_extent_op *extent_op,
			       int insert_reserved)
{
	int ret = 0;

	if (trans->aborted) {
		if (insert_reserved)
			btrfs_pin_extent(trans->fs_info, node->bytenr,
					 node->num_bytes, 1);
		return 0;
	}

	if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
	    node->type == BTRFS_SHARED_BLOCK_REF_KEY)
		ret = run_delayed_tree_ref(trans, node, extent_op,
					   insert_reserved);
	else if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
		 node->type == BTRFS_SHARED_DATA_REF_KEY)
		ret = run_delayed_data_ref(trans, node, extent_op,
					   insert_reserved);
	else
		BUG();
	if (ret && insert_reserved)
		btrfs_pin_extent(trans->fs_info, node->bytenr,
				 node->num_bytes, 1);
	return ret;
}

static inline struct btrfs_delayed_ref_node *
select_delayed_ref(struct btrfs_delayed_ref_head *head)
{
	struct btrfs_delayed_ref_node *ref;

	if (RB_EMPTY_ROOT(&head->ref_tree.rb_root))
		return NULL;

	/*
	 * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first.
	 * This is to prevent a ref count from going down to zero, which deletes
	 * the extent item from the extent tree, when there still are references
	 * to add, which would fail because they would not find the extent item.
	 */
	if (!list_empty(&head->ref_add_list))
		return list_first_entry(&head->ref_add_list,
				struct btrfs_delayed_ref_node, add_list);

	ref = rb_entry(rb_first_cached(&head->ref_tree),
		       struct btrfs_delayed_ref_node, ref_node);
	ASSERT(list_empty(&ref->add_list));
	return ref;
}

static void unselect_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs,
				      struct btrfs_delayed_ref_head *head)
{
	spin_lock(&delayed_refs->lock);
	head->processing = 0;
	delayed_refs->num_heads_ready++;
	spin_unlock(&delayed_refs->lock);
	btrfs_delayed_ref_unlock(head);
}

static struct btrfs_delayed_extent_op *cleanup_extent_op(
				struct btrfs_delayed_ref_head *head)
{
	struct btrfs_delayed_extent_op *extent_op = head->extent_op;

	if (!extent_op)
		return NULL;

	if (head->must_insert_reserved) {
		head->extent_op = NULL;
		btrfs_free_delayed_extent_op(extent_op);
		return NULL;
	}
	return extent_op;
}

static int run_and_cleanup_extent_op(struct btrfs_trans_handle *trans,
				     struct btrfs_delayed_ref_head *head)
{
	struct btrfs_delayed_extent_op *extent_op;
	int ret;

	extent_op = cleanup_extent_op(head);
	if (!extent_op)
		return 0;
	head->extent_op = NULL;
	spin_unlock(&head->lock);
	ret = run_delayed_extent_op(trans, head, extent_op);
	btrfs_free_delayed_extent_op(extent_op);
	return ret ? ret : 1;
}

void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
				  struct btrfs_delayed_ref_root *delayed_refs,
				  struct btrfs_delayed_ref_head *head)
{
	int nr_items = 1;	/* Dropping this ref head update. */

	if (head->total_ref_mod < 0) {
		struct btrfs_space_info *space_info;
		u64 flags;

		if (head->is_data)
			flags = BTRFS_BLOCK_GROUP_DATA;
		else if (head->is_system)
			flags = BTRFS_BLOCK_GROUP_SYSTEM;
		else
			flags = BTRFS_BLOCK_GROUP_METADATA;
		space_info = __find_space_info(fs_info, flags);
		ASSERT(space_info);
		percpu_counter_add_batch(&space_info->total_bytes_pinned,
				   -head->num_bytes,
				   BTRFS_TOTAL_BYTES_PINNED_BATCH);

		/*
		 * We had csum deletions accounted for in our delayed refs rsv,
		 * we need to drop the csum leaves for this update from our
		 * delayed_refs_rsv.
		 */
		if (head->is_data) {
			spin_lock(&delayed_refs->lock);
			delayed_refs->pending_csums -= head->num_bytes;
			spin_unlock(&delayed_refs->lock);
			nr_items += btrfs_csum_bytes_to_leaves(fs_info,
				head->num_bytes);
		}
	}

	btrfs_delayed_refs_rsv_release(fs_info, nr_items);
}

static int cleanup_ref_head(struct btrfs_trans_handle *trans,
			    struct btrfs_delayed_ref_head *head)
{

	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_delayed_ref_root *delayed_refs;
	int ret;

	delayed_refs = &trans->transaction->delayed_refs;

	ret = run_and_cleanup_extent_op(trans, head);
	if (ret < 0) {
		unselect_delayed_ref_head(delayed_refs, head);
		btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
		return ret;
	} else if (ret) {
		return ret;
	}

	/*
	 * Need to drop our head ref lock and re-acquire the delayed ref lock
	 * and then re-check to make sure nobody got added.
	 */
	spin_unlock(&head->lock);
	spin_lock(&delayed_refs->lock);
	spin_lock(&head->lock);
	if (!RB_EMPTY_ROOT(&head->ref_tree.rb_root) || head->extent_op) {
		spin_unlock(&head->lock);
		spin_unlock(&delayed_refs->lock);
		return 1;
	}
	btrfs_delete_ref_head(delayed_refs, head);
	spin_unlock(&head->lock);
	spin_unlock(&delayed_refs->lock);

	if (head->must_insert_reserved) {
		btrfs_pin_extent(fs_info, head->bytenr,
				 head->num_bytes, 1);
		if (head->is_data) {
			ret = btrfs_del_csums(trans, fs_info, head->bytenr,
					      head->num_bytes);
		}
	}

	btrfs_cleanup_ref_head_accounting(fs_info, delayed_refs, head);

	trace_run_delayed_ref_head(fs_info, head, 0);
	btrfs_delayed_ref_unlock(head);
	btrfs_put_delayed_ref_head(head);
	return 0;
}

static struct btrfs_delayed_ref_head *btrfs_obtain_ref_head(
					struct btrfs_trans_handle *trans)
{
	struct btrfs_delayed_ref_root *delayed_refs =
		&trans->transaction->delayed_refs;
	struct btrfs_delayed_ref_head *head = NULL;
	int ret;

	spin_lock(&delayed_refs->lock);
	head = btrfs_select_ref_head(delayed_refs);
	if (!head) {
		spin_unlock(&delayed_refs->lock);
		return head;
	}

	/*
	 * Grab the lock that says we are going to process all the refs for
	 * this head
	 */
	ret = btrfs_delayed_ref_lock(delayed_refs, head);
	spin_unlock(&delayed_refs->lock);

	/*
	 * We may have dropped the spin lock to get the head mutex lock, and
	 * that might have given someone else time to free the head.  If that's
	 * true, it has been removed from our list and we can move on.
	 */
	if (ret == -EAGAIN)
		head = ERR_PTR(-EAGAIN);

	return head;
}

static int btrfs_run_delayed_refs_for_head(struct btrfs_trans_handle *trans,
				    struct btrfs_delayed_ref_head *locked_ref,
				    unsigned long *run_refs)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_delayed_ref_root *delayed_refs;
	struct btrfs_delayed_extent_op *extent_op;
	struct btrfs_delayed_ref_node *ref;
	int must_insert_reserved = 0;
	int ret;

	delayed_refs = &trans->transaction->delayed_refs;

	lockdep_assert_held(&locked_ref->mutex);
	lockdep_assert_held(&locked_ref->lock);

	while ((ref = select_delayed_ref(locked_ref))) {
		if (ref->seq &&
		    btrfs_check_delayed_seq(fs_info, ref->seq)) {
			spin_unlock(&locked_ref->lock);
			unselect_delayed_ref_head(delayed_refs, locked_ref);
			return -EAGAIN;
		}

		(*run_refs)++;
		ref->in_tree = 0;
		rb_erase_cached(&ref->ref_node, &locked_ref->ref_tree);
		RB_CLEAR_NODE(&ref->ref_node);
		if (!list_empty(&ref->add_list))
			list_del(&ref->add_list);
		/*
		 * When we play the delayed ref, also correct the ref_mod on
		 * head
		 */
		switch (ref->action) {
		case BTRFS_ADD_DELAYED_REF:
		case BTRFS_ADD_DELAYED_EXTENT:
			locked_ref->ref_mod -= ref->ref_mod;
			break;
		case BTRFS_DROP_DELAYED_REF:
			locked_ref->ref_mod += ref->ref_mod;
			break;
		default:
			WARN_ON(1);
		}
		atomic_dec(&delayed_refs->num_entries);

		/*
		 * Record the must_insert_reserved flag before we drop the
		 * spin lock.
		 */
		must_insert_reserved = locked_ref->must_insert_reserved;
		locked_ref->must_insert_reserved = 0;

		extent_op = locked_ref->extent_op;
		locked_ref->extent_op = NULL;
		spin_unlock(&locked_ref->lock);

		ret = run_one_delayed_ref(trans, ref, extent_op,
					  must_insert_reserved);

		btrfs_free_delayed_extent_op(extent_op);
		if (ret) {
			unselect_delayed_ref_head(delayed_refs, locked_ref);
			btrfs_put_delayed_ref(ref);
			btrfs_debug(fs_info, "run_one_delayed_ref returned %d",
				    ret);
			return ret;
		}

		btrfs_put_delayed_ref(ref);
		cond_resched();

		spin_lock(&locked_ref->lock);
		btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref);
	}

	return 0;
}

/*
 * Returns 0 on success or if called with an already aborted transaction.
 * Returns -ENOMEM or -EIO on failure and will abort the transaction.
 */
static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
					     unsigned long nr)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_delayed_ref_root *delayed_refs;
	struct btrfs_delayed_ref_head *locked_ref = NULL;
	ktime_t start = ktime_get();
	int ret;
	unsigned long count = 0;
	unsigned long actual_count = 0;

	delayed_refs = &trans->transaction->delayed_refs;
	do {
		if (!locked_ref) {
			locked_ref = btrfs_obtain_ref_head(trans);
			if (IS_ERR_OR_NULL(locked_ref)) {
				if (PTR_ERR(locked_ref) == -EAGAIN) {
					continue;
				} else {
					break;
				}
			}
			count++;
		}
		/*
		 * We need to try and merge add/drops of the same ref since we
		 * can run into issues with relocate dropping the implicit ref
		 * and then it being added back again before the drop can
		 * finish.  If we merged anything we need to re-loop so we can
		 * get a good ref.
		 * Or we can get node references of the same type that weren't
		 * merged when created due to bumps in the tree mod seq, and
		 * we need to merge them to prevent adding an inline extent
		 * backref before dropping it (triggering a BUG_ON at
		 * insert_inline_extent_backref()).
		 */
		spin_lock(&locked_ref->lock);
		btrfs_merge_delayed_refs(trans, delayed_refs, locked_ref);

		ret = btrfs_run_delayed_refs_for_head(trans, locked_ref,
						      &actual_count);
		if (ret < 0 && ret != -EAGAIN) {
			/*
			 * Error, btrfs_run_delayed_refs_for_head already
			 * unlocked everything so just bail out
			 */
			return ret;
		} else if (!ret) {
			/*
			 * Success, perform the usual cleanup of a processed
			 * head
			 */
			ret = cleanup_ref_head(trans, locked_ref);
			if (ret > 0 ) {
				/* We dropped our lock, we need to loop. */
				ret = 0;
				continue;
			} else if (ret) {
				return ret;
			}
		}

		/*
		 * Either success case or btrfs_run_delayed_refs_for_head
		 * returned -EAGAIN, meaning we need to select another head
		 */

		locked_ref = NULL;
		cond_resched();
	} while ((nr != -1 && count < nr) || locked_ref);

	/*
	 * We don't want to include ref heads since we can have empty ref heads
	 * and those will drastically skew our runtime down since we just do
	 * accounting, no actual extent tree updates.
	 */
	if (actual_count > 0) {
		u64 runtime = ktime_to_ns(ktime_sub(ktime_get(), start));
		u64 avg;

		/*
		 * We weigh the current average higher than our current runtime
		 * to avoid large swings in the average.
		 */
		spin_lock(&delayed_refs->lock);
		avg = fs_info->avg_delayed_ref_runtime * 3 + runtime;
		fs_info->avg_delayed_ref_runtime = avg >> 2;	/* div by 4 */
		spin_unlock(&delayed_refs->lock);
	}
	return 0;
}

#ifdef SCRAMBLE_DELAYED_REFS
/*
 * Normally delayed refs get processed in ascending bytenr order. This
 * correlates in most cases to the order added. To expose dependencies on this
 * order, we start to process the tree in the middle instead of the beginning
 */
static u64 find_middle(struct rb_root *root)
{
	struct rb_node *n = root->rb_node;
	struct btrfs_delayed_ref_node *entry;
	int alt = 1;
	u64 middle;
	u64 first = 0, last = 0;

	n = rb_first(root);
	if (n) {
		entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node);
		first = entry->bytenr;
	}
	n = rb_last(root);
	if (n) {
		entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node);
		last = entry->bytenr;
	}
	n = root->rb_node;

	while (n) {
		entry = rb_entry(n, struct btrfs_delayed_ref_node, rb_node);
		WARN_ON(!entry->in_tree);

		middle = entry->bytenr;

		if (alt)
			n = n->rb_left;
		else
			n = n->rb_right;

		alt = 1 - alt;
	}
	return middle;
}
#endif

static inline u64 heads_to_leaves(struct btrfs_fs_info *fs_info, u64 heads)
{
	u64 num_bytes;

	num_bytes = heads * (sizeof(struct btrfs_extent_item) +
			     sizeof(struct btrfs_extent_inline_ref));
	if (!btrfs_fs_incompat(fs_info, SKINNY_METADATA))
		num_bytes += heads * sizeof(struct btrfs_tree_block_info);

	/*
	 * We don't ever fill up leaves all the way so multiply by 2 just to be
	 * closer to what we're really going to want to use.
	 */
	return div_u64(num_bytes, BTRFS_LEAF_DATA_SIZE(fs_info));
}

/*
 * Takes the number of bytes to be csumm'ed and figures out how many leaves it
 * would require to store the csums for that many bytes.
 */
u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes)
{
	u64 csum_size;
	u64 num_csums_per_leaf;
	u64 num_csums;

	csum_size = BTRFS_MAX_ITEM_SIZE(fs_info);
	num_csums_per_leaf = div64_u64(csum_size,
			(u64)btrfs_super_csum_size(fs_info->super_copy));
	num_csums = div64_u64(csum_bytes, fs_info->sectorsize);
	num_csums += num_csums_per_leaf - 1;
	num_csums = div64_u64(num_csums, num_csums_per_leaf);
	return num_csums;
}

bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info)
{
	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	bool ret = false;
	u64 reserved;

	spin_lock(&global_rsv->lock);
	reserved = global_rsv->reserved;
	spin_unlock(&global_rsv->lock);

	/*
	 * Since the global reserve is just kind of magic we don't really want
	 * to rely on it to save our bacon, so if our size is more than the
	 * delayed_refs_rsv and the global rsv then it's time to think about
	 * bailing.
	 */
	spin_lock(&delayed_refs_rsv->lock);
	reserved += delayed_refs_rsv->reserved;
	if (delayed_refs_rsv->size >= reserved)
		ret = true;
	spin_unlock(&delayed_refs_rsv->lock);
	return ret;
}

int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans)
{
	u64 num_entries =
		atomic_read(&trans->transaction->delayed_refs.num_entries);
	u64 avg_runtime;
	u64 val;

	smp_mb();
	avg_runtime = trans->fs_info->avg_delayed_ref_runtime;
	val = num_entries * avg_runtime;
	if (val >= NSEC_PER_SEC)
		return 1;
	if (val >= NSEC_PER_SEC / 2)
		return 2;

	return btrfs_check_space_for_delayed_refs(trans->fs_info);
}

/*
 * this starts processing the delayed reference count updates and
 * extent insertions we have queued up so far.  count can be
 * 0, which means to process everything in the tree at the start
 * of the run (but not newly added entries), or it can be some target
 * number you'd like to process.
 *
 * Returns 0 on success or if called with an aborted transaction
 * Returns <0 on error and aborts the transaction
 */
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
			   unsigned long count)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct rb_node *node;
	struct btrfs_delayed_ref_root *delayed_refs;
	struct btrfs_delayed_ref_head *head;
	int ret;
	int run_all = count == (unsigned long)-1;

	/* We'll clean this up in btrfs_cleanup_transaction */
	if (trans->aborted)
		return 0;

	if (test_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags))
		return 0;

	delayed_refs = &trans->transaction->delayed_refs;
	if (count == 0)
		count = atomic_read(&delayed_refs->num_entries) * 2;

again:
#ifdef SCRAMBLE_DELAYED_REFS
	delayed_refs->run_delayed_start = find_middle(&delayed_refs->root);
#endif
	ret = __btrfs_run_delayed_refs(trans, count);
	if (ret < 0) {
		btrfs_abort_transaction(trans, ret);
		return ret;
	}

	if (run_all) {
		btrfs_create_pending_block_groups(trans);

		spin_lock(&delayed_refs->lock);
		node = rb_first_cached(&delayed_refs->href_root);
		if (!node) {
			spin_unlock(&delayed_refs->lock);
			goto out;
		}
		head = rb_entry(node, struct btrfs_delayed_ref_head,
				href_node);
		refcount_inc(&head->refs);
		spin_unlock(&delayed_refs->lock);

		/* Mutex was contended, block until it's released and retry. */
		mutex_lock(&head->mutex);
		mutex_unlock(&head->mutex);

		btrfs_put_delayed_ref_head(head);
		cond_resched();
		goto again;
	}
out:
	return 0;
}

int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
				u64 bytenr, u64 num_bytes, u64 flags,
				int level, int is_data)
{
	struct btrfs_delayed_extent_op *extent_op;
	int ret;

	extent_op = btrfs_alloc_delayed_extent_op();
	if (!extent_op)
		return -ENOMEM;

	extent_op->flags_to_set = flags;
	extent_op->update_flags = true;
	extent_op->update_key = false;
	extent_op->is_data = is_data ? true : false;
	extent_op->level = level;

	ret = btrfs_add_delayed_extent_op(trans, bytenr, num_bytes, extent_op);
	if (ret)
		btrfs_free_delayed_extent_op(extent_op);
	return ret;
}

static noinline int check_delayed_ref(struct btrfs_root *root,
				      struct btrfs_path *path,
				      u64 objectid, u64 offset, u64 bytenr)
{
	struct btrfs_delayed_ref_head *head;
	struct btrfs_delayed_ref_node *ref;
	struct btrfs_delayed_data_ref *data_ref;
	struct btrfs_delayed_ref_root *delayed_refs;
	struct btrfs_transaction *cur_trans;
	struct rb_node *node;
	int ret = 0;

	spin_lock(&root->fs_info->trans_lock);
	cur_trans = root->fs_info->running_transaction;
	if (cur_trans)
		refcount_inc(&cur_trans->use_count);
	spin_unlock(&root->fs_info->trans_lock);
	if (!cur_trans)
		return 0;

	delayed_refs = &cur_trans->delayed_refs;
	spin_lock(&delayed_refs->lock);
	head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
	if (!head) {
		spin_unlock(&delayed_refs->lock);
		btrfs_put_transaction(cur_trans);
		return 0;
	}

	if (!mutex_trylock(&head->mutex)) {
		refcount_inc(&head->refs);
		spin_unlock(&delayed_refs->lock);

		btrfs_release_path(path);

		/*
		 * Mutex was contended, block until it's released and let
		 * caller try again
		 */
		mutex_lock(&head->mutex);
		mutex_unlock(&head->mutex);
		btrfs_put_delayed_ref_head(head);
		btrfs_put_transaction(cur_trans);
		return -EAGAIN;
	}
	spin_unlock(&delayed_refs->lock);

	spin_lock(&head->lock);
	/*
	 * XXX: We should replace this with a proper search function in the
	 * future.
	 */
	for (node = rb_first_cached(&head->ref_tree); node;
	     node = rb_next(node)) {
		ref = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
		/* If it's a shared ref we know a cross reference exists */
		if (ref->type != BTRFS_EXTENT_DATA_REF_KEY) {
			ret = 1;
			break;
		}

		data_ref = btrfs_delayed_node_to_data_ref(ref);

		/*
		 * If our ref doesn't match the one we're currently looking at
		 * then we have a cross reference.
		 */
		if (data_ref->root != root->root_key.objectid ||
		    data_ref->objectid != objectid ||
		    data_ref->offset != offset) {
			ret = 1;
			break;
		}
	}
	spin_unlock(&head->lock);
	mutex_unlock(&head->mutex);
	btrfs_put_transaction(cur_trans);
	return ret;
}

static noinline int check_committed_ref(struct btrfs_root *root,
					struct btrfs_path *path,
					u64 objectid, u64 offset, u64 bytenr)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_root *extent_root = fs_info->extent_root;
	struct extent_buffer *leaf;
	struct btrfs_extent_data_ref *ref;
	struct btrfs_extent_inline_ref *iref;
	struct btrfs_extent_item *ei;
	struct btrfs_key key;
	u32 item_size;
	int type;
	int ret;

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

	ret = btrfs_search_slot(NULL, extent_root, &key, path, 0, 0);
	if (ret < 0)
		goto out;
	BUG_ON(ret == 0); /* Corruption */

	ret = -ENOENT;
	if (path->slots[0] == 0)
		goto out;

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

	if (key.objectid != bytenr || key.type != BTRFS_EXTENT_ITEM_KEY)
		goto out;

	ret = 1;
	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);

	if (item_size != sizeof(*ei) +
	    btrfs_extent_inline_ref_size(BTRFS_EXTENT_DATA_REF_KEY))
		goto out;

	if (btrfs_extent_generation(leaf, ei) <=
	    btrfs_root_last_snapshot(&root->root_item))
		goto out;

	iref = (struct btrfs_extent_inline_ref *)(ei + 1);

	type = btrfs_get_extent_inline_ref_type(leaf, iref, BTRFS_REF_TYPE_DATA);
	if (type != BTRFS_EXTENT_DATA_REF_KEY)
		goto out;

	ref = (struct btrfs_extent_data_ref *)(&iref->offset);
	if (btrfs_extent_refs(leaf, ei) !=
	    btrfs_extent_data_ref_count(leaf, ref) ||
	    btrfs_extent_data_ref_root(leaf, ref) !=
	    root->root_key.objectid ||
	    btrfs_extent_data_ref_objectid(leaf, ref) != objectid ||
	    btrfs_extent_data_ref_offset(leaf, ref) != offset)
		goto out;

	ret = 0;
out:
	return ret;
}

int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
			  u64 bytenr)
{
	struct btrfs_path *path;
	int ret;

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

	do {
		ret = check_committed_ref(root, path, objectid,
					  offset, bytenr);
		if (ret && ret != -ENOENT)
			goto out;

		ret = check_delayed_ref(root, path, objectid, offset, bytenr);
	} while (ret == -EAGAIN);

out:
	btrfs_free_path(path);
	if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
		WARN_ON(ret > 0);
	return ret;
}

static int __btrfs_mod_ref(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root,
			   struct extent_buffer *buf,
			   int full_backref, int inc)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 bytenr;
	u64 num_bytes;
	u64 parent;
	u64 ref_root;
	u32 nritems;
	struct btrfs_key key;
	struct btrfs_file_extent_item *fi;
	struct btrfs_ref generic_ref = { 0 };
	bool for_reloc = btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC);
	int i;
	int action;
	int level;
	int ret = 0;

	if (btrfs_is_testing(fs_info))
		return 0;

	ref_root = btrfs_header_owner(buf);
	nritems = btrfs_header_nritems(buf);
	level = btrfs_header_level(buf);

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

	if (full_backref)
		parent = buf->start;
	else
		parent = 0;
	if (inc)
		action = BTRFS_ADD_DELAYED_REF;
	else
		action = BTRFS_DROP_DELAYED_REF;

	for (i = 0; i < nritems; i++) {
		if (level == 0) {
			btrfs_item_key_to_cpu(buf, &key, i);
			if (key.type != BTRFS_EXTENT_DATA_KEY)
				continue;
			fi = btrfs_item_ptr(buf, i,
					    struct btrfs_file_extent_item);
			if (btrfs_file_extent_type(buf, fi) ==
			    BTRFS_FILE_EXTENT_INLINE)
				continue;
			bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
			if (bytenr == 0)
				continue;

			num_bytes = btrfs_file_extent_disk_num_bytes(buf, fi);
			key.offset -= btrfs_file_extent_offset(buf, fi);
			btrfs_init_generic_ref(&generic_ref, action, bytenr,
					       num_bytes, parent);
			generic_ref.real_root = root->root_key.objectid;
			btrfs_init_data_ref(&generic_ref, ref_root, key.objectid,
					    key.offset);
			generic_ref.skip_qgroup = for_reloc;
			if (inc)
				ret = btrfs_inc_extent_ref(trans, &generic_ref);
			else
				ret = btrfs_free_extent(trans, &generic_ref);
			if (ret)
				goto fail;
		} else {
			bytenr = btrfs_node_blockptr(buf, i);
			num_bytes = fs_info->nodesize;
			btrfs_init_generic_ref(&generic_ref, action, bytenr,
					       num_bytes, parent);
			generic_ref.real_root = root->root_key.objectid;
			btrfs_init_tree_ref(&generic_ref, level - 1, ref_root);
			generic_ref.skip_qgroup = for_reloc;
			if (inc)
				ret = btrfs_inc_extent_ref(trans, &generic_ref);
			else
				ret = btrfs_free_extent(trans, &generic_ref);
			if (ret)
				goto fail;
		}
	}
	return 0;
fail:
	return ret;
}

int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		  struct extent_buffer *buf, int full_backref)
{
	return __btrfs_mod_ref(trans, root, buf, full_backref, 1);
}

int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		  struct extent_buffer *buf, int full_backref)
{
	return __btrfs_mod_ref(trans, root, buf, full_backref, 0);
}

static int write_one_cache_group(struct btrfs_trans_handle *trans,
				 struct btrfs_path *path,
				 struct btrfs_block_group_cache *cache)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	int ret;
	struct btrfs_root *extent_root = fs_info->extent_root;
	unsigned long bi;
	struct extent_buffer *leaf;

	ret = btrfs_search_slot(trans, extent_root, &cache->key, path, 0, 1);
	if (ret) {
		if (ret > 0)
			ret = -ENOENT;
		goto fail;
	}

	leaf = path->nodes[0];
	bi = btrfs_item_ptr_offset(leaf, path->slots[0]);
	write_extent_buffer(leaf, &cache->item, bi, sizeof(cache->item));
	btrfs_mark_buffer_dirty(leaf);
fail:
	btrfs_release_path(path);
	return ret;

}

static struct btrfs_block_group_cache *next_block_group(
		struct btrfs_block_group_cache *cache)
{
	struct btrfs_fs_info *fs_info = cache->fs_info;
	struct rb_node *node;

	spin_lock(&fs_info->block_group_cache_lock);

	/* If our block group was removed, we need a full search. */
	if (RB_EMPTY_NODE(&cache->cache_node)) {
		const u64 next_bytenr = cache->key.objectid + cache->key.offset;

		spin_unlock(&fs_info->block_group_cache_lock);
		btrfs_put_block_group(cache);
		cache = btrfs_lookup_first_block_group(fs_info, next_bytenr); return cache;
	}
	node = rb_next(&cache->cache_node);
	btrfs_put_block_group(cache);
	if (node) {
		cache = rb_entry(node, struct btrfs_block_group_cache,
				 cache_node);
		btrfs_get_block_group(cache);
	} else
		cache = NULL;
	spin_unlock(&fs_info->block_group_cache_lock);
	return cache;
}

static int cache_save_setup(struct btrfs_block_group_cache *block_group,
			    struct btrfs_trans_handle *trans,
			    struct btrfs_path *path)
{
	struct btrfs_fs_info *fs_info = block_group->fs_info;
	struct btrfs_root *root = fs_info->tree_root;
	struct inode *inode = NULL;
	struct extent_changeset *data_reserved = NULL;
	u64 alloc_hint = 0;
	int dcs = BTRFS_DC_ERROR;
	u64 num_pages = 0;
	int retries = 0;
	int ret = 0;

	/*
	 * If this block group is smaller than 100 megs don't bother caching the
	 * block group.
	 */
	if (block_group->key.offset < (100 * SZ_1M)) {
		spin_lock(&block_group->lock);
		block_group->disk_cache_state = BTRFS_DC_WRITTEN;
		spin_unlock(&block_group->lock);
		return 0;
	}

	if (trans->aborted)
		return 0;
again:
	inode = lookup_free_space_inode(block_group, path);
	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
		ret = PTR_ERR(inode);
		btrfs_release_path(path);
		goto out;
	}

	if (IS_ERR(inode)) {
		BUG_ON(retries);
		retries++;

		if (block_group->ro)
			goto out_free;

		ret = create_free_space_inode(trans, block_group, path);
		if (ret)
			goto out_free;
		goto again;
	}

	/*
	 * We want to set the generation to 0, that way if anything goes wrong
	 * from here on out we know not to trust this cache when we load up next
	 * time.
	 */
	BTRFS_I(inode)->generation = 0;
	ret = btrfs_update_inode(trans, root, inode);
	if (ret) {
		/*
		 * So theoretically we could recover from this, simply set the
		 * super cache generation to 0 so we know to invalidate the
		 * cache, but then we'd have to keep track of the block groups
		 * that fail this way so we know we _have_ to reset this cache
		 * before the next commit or risk reading stale cache.  So to
		 * limit our exposure to horrible edge cases lets just abort the
		 * transaction, this only happens in really bad situations
		 * anyway.
		 */
		btrfs_abort_transaction(trans, ret);
		goto out_put;
	}
	WARN_ON(ret);

	/* We've already setup this transaction, go ahead and exit */
	if (block_group->cache_generation == trans->transid &&
	    i_size_read(inode)) {
		dcs = BTRFS_DC_SETUP;
		goto out_put;
	}

	if (i_size_read(inode) > 0) {
		ret = btrfs_check_trunc_cache_free_space(fs_info,
					&fs_info->global_block_rsv);
		if (ret)
			goto out_put;

		ret = btrfs_truncate_free_space_cache(trans, NULL, inode);
		if (ret)
			goto out_put;
	}

	spin_lock(&block_group->lock);
	if (block_group->cached != BTRFS_CACHE_FINISHED ||
	    !btrfs_test_opt(fs_info, SPACE_CACHE)) {
		/*
		 * don't bother trying to write stuff out _if_
		 * a) we're not cached,
		 * b) we're with nospace_cache mount option,
		 * c) we're with v2 space_cache (FREE_SPACE_TREE).
		 */
		dcs = BTRFS_DC_WRITTEN;
		spin_unlock(&block_group->lock);
		goto out_put;
	}
	spin_unlock(&block_group->lock);

	/*
	 * We hit an ENOSPC when setting up the cache in this transaction, just
	 * skip doing the setup, we've already cleared the cache so we're safe.
	 */
	if (test_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags)) {
		ret = -ENOSPC;
		goto out_put;
	}

	/*
	 * Try to preallocate enough space based on how big the block group is.
	 * Keep in mind this has to include any pinned space which could end up
	 * taking up quite a bit since it's not folded into the other space
	 * cache.
	 */
	num_pages = div_u64(block_group->key.offset, SZ_256M);
	if (!num_pages)
		num_pages = 1;

	num_pages *= 16;
	num_pages *= PAGE_SIZE;

	ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages);
	if (ret)
		goto out_put;

	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, num_pages,
					      num_pages, num_pages,
					      &alloc_hint);
	/*
	 * Our cache requires contiguous chunks so that we don't modify a bunch
	 * of metadata or split extents when writing the cache out, which means
	 * we can enospc if we are heavily fragmented in addition to just normal
	 * out of space conditions.  So if we hit this just skip setting up any
	 * other block groups for this transaction, maybe we'll unpin enough
	 * space the next time around.
	 */
	if (!ret)
		dcs = BTRFS_DC_SETUP;
	else if (ret == -ENOSPC)
		set_bit(BTRFS_TRANS_CACHE_ENOSPC, &trans->transaction->flags);

out_put:
	iput(inode);
out_free:
	btrfs_release_path(path);
out:
	spin_lock(&block_group->lock);
	if (!ret && dcs == BTRFS_DC_SETUP)
		block_group->cache_generation = trans->transid;
	block_group->disk_cache_state = dcs;
	spin_unlock(&block_group->lock);

	extent_changeset_free(data_reserved);
	return ret;
}

int btrfs_setup_space_cache(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache, *tmp;
	struct btrfs_transaction *cur_trans = trans->transaction;
	struct btrfs_path *path;

	if (list_empty(&cur_trans->dirty_bgs) ||
	    !btrfs_test_opt(fs_info, SPACE_CACHE))
		return 0;

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

	/* Could add new block groups, use _safe just in case */
	list_for_each_entry_safe(cache, tmp, &cur_trans->dirty_bgs,
				 dirty_list) {
		if (cache->disk_cache_state == BTRFS_DC_CLEAR)
			cache_save_setup(cache, trans, path);
	}

	btrfs_free_path(path);
	return 0;
}

/*
 * transaction commit does final block group cache writeback during a
 * critical section where nothing is allowed to change the FS.  This is
 * required in order for the cache to actually match the block group,
 * but can introduce a lot of latency into the commit.
 *
 * So, btrfs_start_dirty_block_groups is here to kick off block group
 * cache IO.  There's a chance we'll have to redo some of it if the
 * block group changes again during the commit, but it greatly reduces
 * the commit latency by getting rid of the easy block groups while
 * we're still allowing others to join the commit.
 */
int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache;
	struct btrfs_transaction *cur_trans = trans->transaction;
	int ret = 0;
	int should_put;
	struct btrfs_path *path = NULL;
	LIST_HEAD(dirty);
	struct list_head *io = &cur_trans->io_bgs;
	int num_started = 0;
	int loops = 0;

	spin_lock(&cur_trans->dirty_bgs_lock);
	if (list_empty(&cur_trans->dirty_bgs)) {
		spin_unlock(&cur_trans->dirty_bgs_lock);
		return 0;
	}
	list_splice_init(&cur_trans->dirty_bgs, &dirty);
	spin_unlock(&cur_trans->dirty_bgs_lock);

again:
	/*
	 * make sure all the block groups on our dirty list actually
	 * exist
	 */
	btrfs_create_pending_block_groups(trans);

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

	/*
	 * cache_write_mutex is here only to save us from balance or automatic
	 * removal of empty block groups deleting this block group while we are
	 * writing out the cache
	 */
	mutex_lock(&trans->transaction->cache_write_mutex);
	while (!list_empty(&dirty)) {
		bool drop_reserve = true;

		cache = list_first_entry(&dirty,
					 struct btrfs_block_group_cache,
					 dirty_list);
		/*
		 * this can happen if something re-dirties a block
		 * group that is already under IO.  Just wait for it to
		 * finish and then do it all again
		 */
		if (!list_empty(&cache->io_list)) {
			list_del_init(&cache->io_list);
			btrfs_wait_cache_io(trans, cache, path);
			btrfs_put_block_group(cache);
		}


		/*
		 * btrfs_wait_cache_io uses the cache->dirty_list to decide
		 * if it should update the cache_state.  Don't delete
		 * until after we wait.
		 *
		 * Since we're not running in the commit critical section
		 * we need the dirty_bgs_lock to protect from update_block_group
		 */
		spin_lock(&cur_trans->dirty_bgs_lock);
		list_del_init(&cache->dirty_list);
		spin_unlock(&cur_trans->dirty_bgs_lock);

		should_put = 1;

		cache_save_setup(cache, trans, path);

		if (cache->disk_cache_state == BTRFS_DC_SETUP) {
			cache->io_ctl.inode = NULL;
			ret = btrfs_write_out_cache(trans, cache, path);
			if (ret == 0 && cache->io_ctl.inode) {
				num_started++;
				should_put = 0;

				/*
				 * The cache_write_mutex is protecting the
				 * io_list, also refer to the definition of
				 * btrfs_transaction::io_bgs for more details
				 */
				list_add_tail(&cache->io_list, io);
			} else {
				/*
				 * if we failed to write the cache, the
				 * generation will be bad and life goes on
				 */
				ret = 0;
			}
		}
		if (!ret) {
			ret = write_one_cache_group(trans, path, cache);
			/*
			 * Our block group might still be attached to the list
			 * of new block groups in the transaction handle of some
			 * other task (struct btrfs_trans_handle->new_bgs). This
			 * means its block group item isn't yet in the extent
			 * tree. If this happens ignore the error, as we will
			 * try again later in the critical section of the
			 * transaction commit.
			 */
			if (ret == -ENOENT) {
				ret = 0;
				spin_lock(&cur_trans->dirty_bgs_lock);
				if (list_empty(&cache->dirty_list)) {
					list_add_tail(&cache->dirty_list,
						      &cur_trans->dirty_bgs);
					btrfs_get_block_group(cache);
					drop_reserve = false;
				}
				spin_unlock(&cur_trans->dirty_bgs_lock);
			} else if (ret) {
				btrfs_abort_transaction(trans, ret);
			}
		}

		/* if it's not on the io list, we need to put the block group */
		if (should_put)
			btrfs_put_block_group(cache);
		if (drop_reserve)
			btrfs_delayed_refs_rsv_release(fs_info, 1);

		if (ret)
			break;

		/*
		 * Avoid blocking other tasks for too long. It might even save
		 * us from writing caches for block groups that are going to be
		 * removed.
		 */
		mutex_unlock(&trans->transaction->cache_write_mutex);
		mutex_lock(&trans->transaction->cache_write_mutex);
	}
	mutex_unlock(&trans->transaction->cache_write_mutex);

	/*
	 * go through delayed refs for all the stuff we've just kicked off
	 * and then loop back (just once)
	 */
	ret = btrfs_run_delayed_refs(trans, 0);
	if (!ret && loops == 0) {
		loops++;
		spin_lock(&cur_trans->dirty_bgs_lock);
		list_splice_init(&cur_trans->dirty_bgs, &dirty);
		/*
		 * dirty_bgs_lock protects us from concurrent block group
		 * deletes too (not just cache_write_mutex).
		 */
		if (!list_empty(&dirty)) {
			spin_unlock(&cur_trans->dirty_bgs_lock);
			goto again;
		}
		spin_unlock(&cur_trans->dirty_bgs_lock);
	} else if (ret < 0) {
		btrfs_cleanup_dirty_bgs(cur_trans, fs_info);
	}

	btrfs_free_path(path);
	return ret;
}

int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache;
	struct btrfs_transaction *cur_trans = trans->transaction;
	int ret = 0;
	int should_put;
	struct btrfs_path *path;
	struct list_head *io = &cur_trans->io_bgs;
	int num_started = 0;

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

	/*
	 * Even though we are in the critical section of the transaction commit,
	 * we can still have concurrent tasks adding elements to this
	 * transaction's list of dirty block groups. These tasks correspond to
	 * endio free space workers started when writeback finishes for a
	 * space cache, which run inode.c:btrfs_finish_ordered_io(), and can
	 * allocate new block groups as a result of COWing nodes of the root
	 * tree when updating the free space inode. The writeback for the space
	 * caches is triggered by an earlier call to
	 * btrfs_start_dirty_block_groups() and iterations of the following
	 * loop.
	 * Also we want to do the cache_save_setup first and then run the
	 * delayed refs to make sure we have the best chance at doing this all
	 * in one shot.
	 */
	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_cache,
					 dirty_list);

		/*
		 * this can happen if cache_save_setup re-dirties a block
		 * group that is already under IO.  Just wait for it to
		 * finish and then do it all again
		 */
		if (!list_empty(&cache->io_list)) {
			spin_unlock(&cur_trans->dirty_bgs_lock);
			list_del_init(&cache->io_list);
			btrfs_wait_cache_io(trans, cache, path);
			btrfs_put_block_group(cache);
			spin_lock(&cur_trans->dirty_bgs_lock);
		}

		/*
		 * don't remove from the dirty list until after we've waited
		 * on any pending IO
		 */
		list_del_init(&cache->dirty_list);
		spin_unlock(&cur_trans->dirty_bgs_lock);
		should_put = 1;

		cache_save_setup(cache, trans, path);

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

		if (!ret && cache->disk_cache_state == BTRFS_DC_SETUP) {
			cache->io_ctl.inode = NULL;
			ret = btrfs_write_out_cache(trans, cache, path);
			if (ret == 0 && cache->io_ctl.inode) {
				num_started++;
				should_put = 0;
				list_add_tail(&cache->io_list, io);
			} else {
				/*
				 * if we failed to write the cache, the
				 * generation will be bad and life goes on
				 */
				ret = 0;
			}
		}
		if (!ret) {
			ret = write_one_cache_group(trans, path, cache);
			/*
			 * One of the free space endio workers might have
			 * created a new block group while updating a free space
			 * cache's inode (at inode.c:btrfs_finish_ordered_io())
			 * and hasn't released its transaction handle yet, in
			 * which case the new block group is still attached to
			 * its transaction handle and its creation has not
			 * finished yet (no block group item in the extent tree
			 * yet, etc). If this is the case, wait for all free
			 * space endio workers to finish and retry. This is a
			 * a very rare case so no need for a more efficient and
			 * complex approach.
			 */
			if (ret == -ENOENT) {
				wait_event(cur_trans->writer_wait,
				   atomic_read(&cur_trans->num_writers) == 1);
				ret = write_one_cache_group(trans, path, cache);
			}
			if (ret)
				btrfs_abort_transaction(trans, ret);
		}

		/* if its not on the io list, we need to put the block group */
		if (should_put)
			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(io)) {
		cache = list_first_entry(io, struct btrfs_block_group_cache,
					 io_list);
		list_del_init(&cache->io_list);
		btrfs_wait_cache_io(trans, cache, path);
		btrfs_put_block_group(cache);
	}

	btrfs_free_path(path);
	return ret;
}

int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group_cache *block_group;
	int readonly = 0;

	block_group = btrfs_lookup_block_group(fs_info, bytenr);
	if (!block_group || block_group->ro)
		readonly = 1;
	if (block_group)
		btrfs_put_block_group(block_group);
	return readonly;
}

bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group_cache *bg;
	bool ret = true;

	bg = btrfs_lookup_block_group(fs_info, bytenr);
	if (!bg)
		return false;

	spin_lock(&bg->lock);
	if (bg->ro)
		ret = false;
	else
		atomic_inc(&bg->nocow_writers);
	spin_unlock(&bg->lock);

	/* no put on block group, done by btrfs_dec_nocow_writers */
	if (!ret)
		btrfs_put_block_group(bg);

	return ret;

}

void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group_cache *bg;

	bg = btrfs_lookup_block_group(fs_info, bytenr);
	ASSERT(bg);
	if (atomic_dec_and_test(&bg->nocow_writers))
		wake_up_var(&bg->nocow_writers);
	/*
	 * Once for our lookup and once for the lookup done by a previous call
	 * to btrfs_inc_nocow_writers()
	 */
	btrfs_put_block_group(bg);
	btrfs_put_block_group(bg);
}

void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
{
	wait_var_event(&bg->nocow_writers, !atomic_read(&bg->nocow_writers));
}

static const char *alloc_name(u64 flags)
{
	switch (flags) {
	case BTRFS_BLOCK_GROUP_METADATA|BTRFS_BLOCK_GROUP_DATA:
		return "mixed";
	case BTRFS_BLOCK_GROUP_METADATA:
		return "metadata";
	case BTRFS_BLOCK_GROUP_DATA:
		return "data";
	case BTRFS_BLOCK_GROUP_SYSTEM:
		return "system";
	default:
		WARN_ON(1);
		return "invalid-combination";
	};
}

static int create_space_info(struct btrfs_fs_info *info, u64 flags)
{

	struct btrfs_space_info *space_info;
	int i;
	int ret;

	space_info = kzalloc(sizeof(*space_info), GFP_NOFS);
	if (!space_info)
		return -ENOMEM;

	ret = percpu_counter_init(&space_info->total_bytes_pinned, 0,
				 GFP_KERNEL);
	if (ret) {
		kfree(space_info);
		return ret;
	}

	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
		INIT_LIST_HEAD(&space_info->block_groups[i]);
	init_rwsem(&space_info->groups_sem);
	spin_lock_init(&space_info->lock);
	space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
	init_waitqueue_head(&space_info->wait);
	INIT_LIST_HEAD(&space_info->ro_bgs);
	INIT_LIST_HEAD(&space_info->tickets);
	INIT_LIST_HEAD(&space_info->priority_tickets);

	ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype,
				    info->space_info_kobj, "%s",
				    alloc_name(space_info->flags));
	if (ret) {
		percpu_counter_destroy(&space_info->total_bytes_pinned);
		kfree(space_info);
		return ret;
	}

	list_add_rcu(&space_info->list, &info->space_info);
	if (flags & BTRFS_BLOCK_GROUP_DATA)
		info->data_sinfo = space_info;

	return ret;
}

static void update_space_info(struct btrfs_fs_info *info, u64 flags,
			     u64 total_bytes, u64 bytes_used,
			     u64 bytes_readonly,
			     struct btrfs_space_info **space_info)
{
	struct btrfs_space_info *found;
	int factor;

	factor = btrfs_bg_type_to_factor(flags);

	found = __find_space_info(info, flags);
	ASSERT(found);
	spin_lock(&found->lock);
	found->total_bytes += total_bytes;
	found->disk_total += total_bytes * factor;
	found->bytes_used += bytes_used;
	found->disk_used += bytes_used * factor;
	found->bytes_readonly += bytes_readonly;
	if (total_bytes > 0)
		found->full = 0;
	space_info_add_new_bytes(info, found, total_bytes -
				 bytes_used - bytes_readonly);
	spin_unlock(&found->lock);
	*space_info = found;
}

static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
	u64 extra_flags = chunk_to_extended(flags) &
				BTRFS_EXTENDED_PROFILE_MASK;

	write_seqlock(&fs_info->profiles_lock);
	if (flags & BTRFS_BLOCK_GROUP_DATA)
		fs_info->avail_data_alloc_bits |= extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_METADATA)
		fs_info->avail_metadata_alloc_bits |= extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
		fs_info->avail_system_alloc_bits |= extra_flags;
	write_sequnlock(&fs_info->profiles_lock);
}

/*
 * returns target flags in extended format or 0 if restripe for this
 * chunk_type is not in progress
 *
 * should be called with balance_lock held
 */
static u64 get_restripe_target(struct btrfs_fs_info *fs_info, u64 flags)
{
	struct btrfs_balance_control *bctl = fs_info->balance_ctl;
	u64 target = 0;

	if (!bctl)
		return 0;

	if (flags & BTRFS_BLOCK_GROUP_DATA &&
	    bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) {
		target = BTRFS_BLOCK_GROUP_DATA | bctl->data.target;
	} else if (flags & BTRFS_BLOCK_GROUP_SYSTEM &&
		   bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
		target = BTRFS_BLOCK_GROUP_SYSTEM | bctl->sys.target;
	} else if (flags & BTRFS_BLOCK_GROUP_METADATA &&
		   bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) {
		target = BTRFS_BLOCK_GROUP_METADATA | bctl->meta.target;
	}

	return target;
}

/*
 * @flags: available profiles in extended format (see ctree.h)
 *
 * Returns reduced profile in chunk format.  If profile changing is in
 * progress (either running or paused) picks the target profile (if it's
 * already available), otherwise falls back to plain reducing.
 */
static u64 btrfs_reduce_alloc_profile(struct btrfs_fs_info *fs_info, u64 flags)
{
	u64 num_devices = fs_info->fs_devices->rw_devices;
	u64 target;
	u64 raid_type;
	u64 allowed = 0;

	/*
	 * see if restripe for this chunk_type is in progress, if so
	 * try to reduce to the target profile
	 */
	spin_lock(&fs_info->balance_lock);
	target = get_restripe_target(fs_info, flags);
	if (target) {
		/* pick target profile only if it's already available */
		if ((flags & target) & BTRFS_EXTENDED_PROFILE_MASK) {
			spin_unlock(&fs_info->balance_lock);
			return extended_to_chunk(target);
		}
	}
	spin_unlock(&fs_info->balance_lock);

	/* First, mask out the RAID levels which aren't possible */
	for (raid_type = 0; raid_type < BTRFS_NR_RAID_TYPES; raid_type++) {
		if (num_devices >= btrfs_raid_array[raid_type].devs_min)
			allowed |= btrfs_raid_array[raid_type].bg_flag;
	}
	allowed &= flags;

	if (allowed & BTRFS_BLOCK_GROUP_RAID6)
		allowed = BTRFS_BLOCK_GROUP_RAID6;
	else if (allowed & BTRFS_BLOCK_GROUP_RAID5)
		allowed = BTRFS_BLOCK_GROUP_RAID5;
	else if (allowed & BTRFS_BLOCK_GROUP_RAID10)
		allowed = BTRFS_BLOCK_GROUP_RAID10;
	else if (allowed & BTRFS_BLOCK_GROUP_RAID1)
		allowed = BTRFS_BLOCK_GROUP_RAID1;
	else if (allowed & BTRFS_BLOCK_GROUP_RAID0)
		allowed = BTRFS_BLOCK_GROUP_RAID0;

	flags &= ~BTRFS_BLOCK_GROUP_PROFILE_MASK;

	return extended_to_chunk(flags | allowed);
}

static u64 get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
{
	unsigned seq;
	u64 flags;

	do {
		flags = orig_flags;
		seq = read_seqbegin(&fs_info->profiles_lock);

		if (flags & BTRFS_BLOCK_GROUP_DATA)
			flags |= fs_info->avail_data_alloc_bits;
		else if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
			flags |= fs_info->avail_system_alloc_bits;
		else if (flags & BTRFS_BLOCK_GROUP_METADATA)
			flags |= fs_info->avail_metadata_alloc_bits;
	} while (read_seqretry(&fs_info->profiles_lock, seq));

	return btrfs_reduce_alloc_profile(fs_info, flags);
}

static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 flags;
	u64 ret;

	if (data)
		flags = BTRFS_BLOCK_GROUP_DATA;
	else if (root == fs_info->chunk_root)
		flags = BTRFS_BLOCK_GROUP_SYSTEM;
	else
		flags = BTRFS_BLOCK_GROUP_METADATA;

	ret = get_alloc_profile(fs_info, flags);
	return ret;
}

u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
{
	return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
}

u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
{
	return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
}

u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
{
	return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
}

static u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
				 bool may_use_included)
{
	ASSERT(s_info);
	return s_info->bytes_used + s_info->bytes_reserved +
		s_info->bytes_pinned + s_info->bytes_readonly +
		(may_use_included ? s_info->bytes_may_use : 0);
}

int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_space_info *data_sinfo = fs_info->data_sinfo;
	u64 used;
	int ret = 0;
	int need_commit = 2;
	int have_pinned_space;

	/* make sure bytes are sectorsize aligned */
	bytes = ALIGN(bytes, fs_info->sectorsize);

	if (btrfs_is_free_space_inode(inode)) {
		need_commit = 0;
		ASSERT(current->journal_info);
	}

again:
	/* make sure we have enough space to handle the data first */
	spin_lock(&data_sinfo->lock);
	used = btrfs_space_info_used(data_sinfo, true);

	if (used + bytes > data_sinfo->total_bytes) {
		struct btrfs_trans_handle *trans;

		/*
		 * if we don't have enough free bytes in this space then we need
		 * to alloc a new chunk.
		 */
		if (!data_sinfo->full) {
			u64 alloc_target;

			data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
			spin_unlock(&data_sinfo->lock);

			alloc_target = btrfs_data_alloc_profile(fs_info);
			/*
			 * It is ugly that we don't call nolock join
			 * transaction for the free space inode case here.
			 * But it is safe because we only do the data space
			 * reservation for the free space cache in the
			 * transaction context, the common join transaction
			 * just increase the counter of the current transaction
			 * handler, doesn't try to acquire the trans_lock of
			 * the fs.
			 */
			trans = btrfs_join_transaction(root);
			if (IS_ERR(trans))
				return PTR_ERR(trans);

			ret = do_chunk_alloc(trans, alloc_target,
					     CHUNK_ALLOC_NO_FORCE);
			btrfs_end_transaction(trans);
			if (ret < 0) {
				if (ret != -ENOSPC)
					return ret;
				else {
					have_pinned_space = 1;
					goto commit_trans;
				}
			}

			goto again;
		}

		/*
		 * If we don't have enough pinned space to deal with this
		 * allocation, and no removed chunk in current transaction,
		 * don't bother committing the transaction.
		 */
		have_pinned_space = __percpu_counter_compare(
			&data_sinfo->total_bytes_pinned,
			used + bytes - data_sinfo->total_bytes,
			BTRFS_TOTAL_BYTES_PINNED_BATCH);
		spin_unlock(&data_sinfo->lock);

		/* commit the current transaction and try again */
commit_trans:
		if (need_commit) {
			need_commit--;

			if (need_commit > 0) {
				btrfs_start_delalloc_roots(fs_info, -1);
				btrfs_wait_ordered_roots(fs_info, U64_MAX, 0,
							 (u64)-1);
			}

			trans = btrfs_join_transaction(root);
			if (IS_ERR(trans))
				return PTR_ERR(trans);
			if (have_pinned_space >= 0 ||
			    test_bit(BTRFS_TRANS_HAVE_FREE_BGS,
				     &trans->transaction->flags) ||
			    need_commit > 0) {
				ret = btrfs_commit_transaction(trans);
				if (ret)
					return ret;
				/*
				 * The cleaner kthread might still be doing iput
				 * operations. Wait for it to finish so that
				 * more space is released.  We don't need to
				 * explicitly run the delayed iputs here because
				 * the commit_transaction would have woken up
				 * the cleaner.
				 */
				ret = btrfs_wait_on_delayed_iputs(fs_info);
				if (ret)
					return ret;
				goto again;
			} else {
				btrfs_end_transaction(trans);
			}
		}

		trace_btrfs_space_reservation(fs_info,
					      "space_info:enospc",
					      data_sinfo->flags, bytes, 1);
		return -ENOSPC;
	}
	update_bytes_may_use(data_sinfo, bytes);
	trace_btrfs_space_reservation(fs_info, "space_info",
				      data_sinfo->flags, bytes, 1);
	spin_unlock(&data_sinfo->lock);

	return 0;
}

int btrfs_check_data_free_space(struct inode *inode,
			struct extent_changeset **reserved, u64 start, u64 len)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	int ret;

	/* align the range */
	len = round_up(start + len, fs_info->sectorsize) -
	      round_down(start, fs_info->sectorsize);
	start = round_down(start, fs_info->sectorsize);

	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len);
	if (ret < 0)
		return ret;

	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
	if (ret < 0)
		btrfs_free_reserved_data_space_noquota(inode, start, len);
	else
		ret = 0;
	return ret;
}

/*
 * Called if we need to clear a data reservation for this inode
 * Normally in a error case.
 *
 * This one will *NOT* use accurate qgroup reserved space API, just for case
 * which we can't sleep and is sure it won't affect qgroup reserved space.
 * Like clear_bit_hook().
 */
void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
					    u64 len)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct btrfs_space_info *data_sinfo;

	/* Make sure the range is aligned to sectorsize */
	len = round_up(start + len, fs_info->sectorsize) -
	      round_down(start, fs_info->sectorsize);
	start = round_down(start, fs_info->sectorsize);

	data_sinfo = fs_info->data_sinfo;
	spin_lock(&data_sinfo->lock);
	update_bytes_may_use(data_sinfo, -len);
	trace_btrfs_space_reservation(fs_info, "space_info",
				      data_sinfo->flags, len, 0);
	spin_unlock(&data_sinfo->lock);
}

/*
 * Called if we need to clear a data reservation for this inode
 * Normally in a error case.
 *
 * This one will handle the per-inode data rsv map for accurate reserved
 * space framework.
 */
void btrfs_free_reserved_data_space(struct inode *inode,
			struct extent_changeset *reserved, u64 start, u64 len)
{
	struct btrfs_root *root = BTRFS_I(inode)->root;

	/* Make sure the range is aligned to sectorsize */
	len = round_up(start + len, root->fs_info->sectorsize) -
	      round_down(start, root->fs_info->sectorsize);
	start = round_down(start, root->fs_info->sectorsize);

	btrfs_free_reserved_data_space_noquota(inode, start, len);
	btrfs_qgroup_free_data(inode, reserved, start, len);
}

static void force_metadata_allocation(struct btrfs_fs_info *info)
{
	struct list_head *head = &info->space_info;
	struct btrfs_space_info *found;

	rcu_read_lock();
	list_for_each_entry_rcu(found, head, list) {
		if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
			found->force_alloc = CHUNK_ALLOC_FORCE;
	}
	rcu_read_unlock();
}

static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global)
{
	return (global->size << 1);
}

static int should_alloc_chunk(struct btrfs_fs_info *fs_info,
			      struct btrfs_space_info *sinfo, int force)
{
	u64 bytes_used = btrfs_space_info_used(sinfo, false);
	u64 thresh;

	if (force == CHUNK_ALLOC_FORCE)
		return 1;

	/*
	 * in limited mode, we want to have some free space up to
	 * about 1% of the FS size.
	 */
	if (force == CHUNK_ALLOC_LIMITED) {
		thresh = btrfs_super_total_bytes(fs_info->super_copy);
		thresh = max_t(u64, SZ_64M, div_factor_fine(thresh, 1));

		if (sinfo->total_bytes - bytes_used < thresh)
			return 1;
	}

	if (bytes_used + SZ_2M < div_factor(sinfo->total_bytes, 8))
		return 0;
	return 1;
}

static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
{
	u64 num_dev;

	if (type & (BTRFS_BLOCK_GROUP_RAID10 |
		    BTRFS_BLOCK_GROUP_RAID0 |
		    BTRFS_BLOCK_GROUP_RAID5 |
		    BTRFS_BLOCK_GROUP_RAID6))
		num_dev = fs_info->fs_devices->rw_devices;
	else if (type & BTRFS_BLOCK_GROUP_RAID1)
		num_dev = 2;
	else
		num_dev = 1;	/* DUP or single */

	return num_dev;
}

/*
 * If @is_allocation is true, reserve space in the system space info necessary
 * for allocating a chunk, otherwise if it's false, reserve space necessary for
 * removing a chunk.
 */
void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_space_info *info;
	u64 left;
	u64 thresh;
	int ret = 0;
	u64 num_devs;

	/*
	 * Needed because we can end up allocating a system chunk and for an
	 * atomic and race free space reservation in the chunk block reserve.
	 */
	lockdep_assert_held(&fs_info->chunk_mutex);

	info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
	spin_lock(&info->lock);
	left = info->total_bytes - btrfs_space_info_used(info, true);
	spin_unlock(&info->lock);

	num_devs = get_profile_num_devs(fs_info, type);

	/* num_devs device items to update and 1 chunk item to add or remove */
	thresh = btrfs_calc_trunc_metadata_size(fs_info, num_devs) +
		btrfs_calc_trans_metadata_size(fs_info, 1);

	if (left < thresh && btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
		btrfs_info(fs_info, "left=%llu, need=%llu, flags=%llu",
			   left, thresh, type);
		dump_space_info(fs_info, info, 0, 0);
	}

	if (left < thresh) {
		u64 flags = btrfs_system_alloc_profile(fs_info);

		/*
		 * Ignore failure to create system chunk. We might end up not
		 * needing it, as we might not need to COW all nodes/leafs from
		 * the paths we visit in the chunk tree (they were already COWed
		 * or created in the current transaction for example).
		 */
		ret = btrfs_alloc_chunk(trans, flags);
	}

	if (!ret) {
		ret = btrfs_block_rsv_add(fs_info->chunk_root,
					  &fs_info->chunk_block_rsv,
					  thresh, BTRFS_RESERVE_NO_FLUSH);
		if (!ret)
			trans->chunk_bytes_reserved += thresh;
	}
}

/*
 * If force is CHUNK_ALLOC_FORCE:
 *    - return 1 if it successfully allocates a chunk,
 *    - return errors including -ENOSPC otherwise.
 * If force is NOT CHUNK_ALLOC_FORCE:
 *    - return 0 if it doesn't need to allocate a new chunk,
 *    - return 1 if it successfully allocates a chunk,
 *    - return errors including -ENOSPC otherwise.
 */
static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
			  int force)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_space_info *space_info;
	bool wait_for_alloc = false;
	bool should_alloc = false;
	int ret = 0;

	/* Don't re-enter if we're already allocating a chunk */
	if (trans->allocating_chunk)
		return -ENOSPC;

	space_info = __find_space_info(fs_info, flags);
	ASSERT(space_info);

	do {
		spin_lock(&space_info->lock);
		if (force < space_info->force_alloc)
			force = space_info->force_alloc;
		should_alloc = should_alloc_chunk(fs_info, space_info, force);
		if (space_info->full) {
			/* No more free physical space */
			if (should_alloc)
				ret = -ENOSPC;
			else
				ret = 0;
			spin_unlock(&space_info->lock);
			return ret;
		} else if (!should_alloc) {
			spin_unlock(&space_info->lock);
			return 0;
		} else if (space_info->chunk_alloc) {
			/*
			 * Someone is already allocating, so we need to block
			 * until this someone is finished and then loop to
			 * recheck if we should continue with our allocation
			 * attempt.
			 */
			wait_for_alloc = true;
			spin_unlock(&space_info->lock);
			mutex_lock(&fs_info->chunk_mutex);
			mutex_unlock(&fs_info->chunk_mutex);
		} else {
			/* Proceed with allocation */
			space_info->chunk_alloc = 1;
			wait_for_alloc = false;
			spin_unlock(&space_info->lock);
		}

		cond_resched();
	} while (wait_for_alloc);

	mutex_lock(&fs_info->chunk_mutex);
	trans->allocating_chunk = true;

	/*
	 * If we have mixed data/metadata chunks we want to make sure we keep
	 * allocating mixed chunks instead of individual chunks.
	 */
	if (btrfs_mixed_space_info(space_info))
		flags |= (BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA);

	/*
	 * if we're doing a data chunk, go ahead and make sure that
	 * we keep a reasonable number of metadata chunks allocated in the
	 * FS as well.
	 */
	if (flags & BTRFS_BLOCK_GROUP_DATA && fs_info->metadata_ratio) {
		fs_info->data_chunk_allocations++;
		if (!(fs_info->data_chunk_allocations %
		      fs_info->metadata_ratio))
			force_metadata_allocation(fs_info);
	}

	/*
	 * Check if we have enough space in SYSTEM chunk because we may need
	 * to update devices.
	 */
	check_system_chunk(trans, flags);

	ret = btrfs_alloc_chunk(trans, flags);
	trans->allocating_chunk = false;

	spin_lock(&space_info->lock);
	if (ret < 0) {
		if (ret == -ENOSPC)
			space_info->full = 1;
		else
			goto out;
	} else {
		ret = 1;
		space_info->max_extent_size = 0;
	}

	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
out:
	space_info->chunk_alloc = 0;
	spin_unlock(&space_info->lock);
	mutex_unlock(&fs_info->chunk_mutex);
	/*
	 * When we allocate a new chunk we reserve space in the chunk block
	 * reserve to make sure we can COW nodes/leafs in the chunk tree or
	 * add new nodes/leafs to it if we end up needing to do it when
	 * inserting the chunk item and updating device items as part of the
	 * second phase of chunk allocation, performed by
	 * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a
	 * large number of new block groups to create in our transaction
	 * handle's new_bgs list to avoid exhausting the chunk block reserve
	 * in extreme cases - like having a single transaction create many new
	 * block groups when starting to write out the free space caches of all
	 * the block groups that were made dirty during the lifetime of the
	 * transaction.
	 */
	if (trans->chunk_bytes_reserved >= (u64)SZ_2M)
		btrfs_create_pending_block_groups(trans);

	return ret;
}

static int can_overcommit(struct btrfs_fs_info *fs_info,
			  struct btrfs_space_info *space_info, u64 bytes,
			  enum btrfs_reserve_flush_enum flush,
			  bool system_chunk)
{
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	u64 profile;
	u64 space_size;
	u64 avail;
	u64 used;
	int factor;

	/* Don't overcommit when in mixed mode. */
	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
		return 0;

	if (system_chunk)
		profile = btrfs_system_alloc_profile(fs_info);
	else
		profile = btrfs_metadata_alloc_profile(fs_info);

	used = btrfs_space_info_used(space_info, false);

	/*
	 * We only want to allow over committing if we have lots of actual space
	 * free, but if we don't have enough space to handle the global reserve
	 * space then we could end up having a real enospc problem when trying
	 * to allocate a chunk or some other such important allocation.
	 */
	spin_lock(&global_rsv->lock);
	space_size = calc_global_rsv_need_space(global_rsv);
	spin_unlock(&global_rsv->lock);
	if (used + space_size >= space_info->total_bytes)
		return 0;

	used += space_info->bytes_may_use;

	avail = atomic64_read(&fs_info->free_chunk_space);

	/*
	 * If we have dup, raid1 or raid10 then only half of the free
	 * space is actually usable.  For raid56, the space info used
	 * doesn't include the parity drive, so we don't have to
	 * change the math
	 */
	factor = btrfs_bg_type_to_factor(profile);
	avail = div_u64(avail, factor);

	/*
	 * If we aren't flushing all things, let us overcommit up to
	 * 1/2th of the space. If we can flush, don't let us overcommit
	 * too much, let it overcommit up to 1/8 of the space.
	 */
	if (flush == BTRFS_RESERVE_FLUSH_ALL)
		avail >>= 3;
	else
		avail >>= 1;

	if (used + bytes < space_info->total_bytes + avail)
		return 1;
	return 0;
}

static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info,
					 unsigned long nr_pages, int nr_items)
{
	struct super_block *sb = fs_info->sb;

	if (down_read_trylock(&sb->s_umount)) {
		writeback_inodes_sb_nr(sb, nr_pages, WB_REASON_FS_FREE_SPACE);
		up_read(&sb->s_umount);
	} else {
		/*
		 * We needn't worry the filesystem going from r/w to r/o though
		 * we don't acquire ->s_umount mutex, because the filesystem
		 * should guarantee the delalloc inodes list be empty after
		 * the filesystem is readonly(all dirty pages are written to
		 * the disk).
		 */
		btrfs_start_delalloc_roots(fs_info, nr_items);
		if (!current->journal_info)
			btrfs_wait_ordered_roots(fs_info, nr_items, 0, (u64)-1);
	}
}

static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
					u64 to_reclaim)
{
	u64 bytes;
	u64 nr;

	bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
	nr = div64_u64(to_reclaim, bytes);
	if (!nr)
		nr = 1;
	return nr;
}

#define EXTENT_SIZE_PER_ITEM	SZ_256K

/*
 * shrink metadata reservation for delalloc
 */
static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim,
			    u64 orig, bool wait_ordered)
{
	struct btrfs_space_info *space_info;
	struct btrfs_trans_handle *trans;
	u64 delalloc_bytes;
	u64 dio_bytes;
	u64 async_pages;
	u64 items;
	long time_left;
	unsigned long nr_pages;
	int loops;

	/* Calc the number of the pages we need flush for space reservation */
	items = calc_reclaim_items_nr(fs_info, to_reclaim);
	to_reclaim = items * EXTENT_SIZE_PER_ITEM;

	trans = (struct btrfs_trans_handle *)current->journal_info;
	space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);

	delalloc_bytes = percpu_counter_sum_positive(
						&fs_info->delalloc_bytes);
	dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
	if (delalloc_bytes == 0 && dio_bytes == 0) {
		if (trans)
			return;
		if (wait_ordered)
			btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
		return;
	}

	/*
	 * If we are doing more ordered than delalloc we need to just wait on
	 * ordered extents, otherwise we'll waste time trying to flush delalloc
	 * that likely won't give us the space back we need.
	 */
	if (dio_bytes > delalloc_bytes)
		wait_ordered = true;

	loops = 0;
	while ((delalloc_bytes || dio_bytes) && loops < 3) {
		nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;

		/*
		 * Triggers inode writeback for up to nr_pages. This will invoke
		 * ->writepages callback and trigger delalloc filling
		 *  (btrfs_run_delalloc_range()).
		 */
		btrfs_writeback_inodes_sb_nr(fs_info, nr_pages, items);

		/*
		 * We need to wait for the compressed pages to start before
		 * we continue.
		 */
		async_pages = atomic_read(&fs_info->async_delalloc_pages);
		if (!async_pages)
			goto skip_async;

		/*
		 * Calculate how many compressed pages we want to be written
		 * before we continue. I.e if there are more async pages than we
		 * require wait_event will wait until nr_pages are written.
		 */
		if (async_pages <= nr_pages)
			async_pages = 0;
		else
			async_pages -= nr_pages;

		wait_event(fs_info->async_submit_wait,
			   atomic_read(&fs_info->async_delalloc_pages) <=
			   (int)async_pages);
skip_async:
		spin_lock(&space_info->lock);
		if (list_empty(&space_info->tickets) &&
		    list_empty(&space_info->priority_tickets)) {
			spin_unlock(&space_info->lock);
			break;
		}
		spin_unlock(&space_info->lock);

		loops++;
		if (wait_ordered && !trans) {
			btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
		} else {
			time_left = schedule_timeout_killable(1);
			if (time_left)
				break;
		}
		delalloc_bytes = percpu_counter_sum_positive(
						&fs_info->delalloc_bytes);
		dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
	}
}

struct reserve_ticket {
	u64 orig_bytes;
	u64 bytes;
	int error;
	struct list_head list;
	wait_queue_head_t wait;
};

/**
 * maybe_commit_transaction - possibly commit the transaction if its ok to
 * @root - the root we're allocating for
 * @bytes - the number of bytes we want to reserve
 * @force - force the commit
 *
 * This will check to make sure that committing the transaction will actually
 * get us somewhere and then commit the transaction if it does.  Otherwise it
 * will return -ENOSPC.
 */
static int may_commit_transaction(struct btrfs_fs_info *fs_info,
				  struct btrfs_space_info *space_info)
{
	struct reserve_ticket *ticket = NULL;
	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv;
	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
	struct btrfs_trans_handle *trans;
	u64 bytes_needed;
	u64 reclaim_bytes = 0;

	trans = (struct btrfs_trans_handle *)current->journal_info;
	if (trans)
		return -EAGAIN;

	spin_lock(&space_info->lock);
	if (!list_empty(&space_info->priority_tickets))
		ticket = list_first_entry(&space_info->priority_tickets,
					  struct reserve_ticket, list);
	else if (!list_empty(&space_info->tickets))
		ticket = list_first_entry(&space_info->tickets,
					  struct reserve_ticket, list);
	bytes_needed = (ticket) ? ticket->bytes : 0;
	spin_unlock(&space_info->lock);

	if (!bytes_needed)
		return 0;

	trans = btrfs_join_transaction(fs_info->extent_root);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	/*
	 * See if there is enough pinned space to make this reservation, or if
	 * we have block groups that are going to be freed, allowing us to
	 * possibly do a chunk allocation the next loop through.
	 */
	if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags) ||
	    __percpu_counter_compare(&space_info->total_bytes_pinned,
				     bytes_needed,
				     BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
		goto commit;

	/*
	 * See if there is some space in the delayed insertion reservation for
	 * this reservation.
	 */
	if (space_info != delayed_rsv->space_info)
		goto enospc;

	spin_lock(&delayed_rsv->lock);
	reclaim_bytes += delayed_rsv->reserved;
	spin_unlock(&delayed_rsv->lock);

	spin_lock(&delayed_refs_rsv->lock);
	reclaim_bytes += delayed_refs_rsv->reserved;
	spin_unlock(&delayed_refs_rsv->lock);
	if (reclaim_bytes >= bytes_needed)
		goto commit;
	bytes_needed -= reclaim_bytes;

	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
				   bytes_needed,
				   BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0)
		goto enospc;

commit:
	return btrfs_commit_transaction(trans);
enospc:
	btrfs_end_transaction(trans);
	return -ENOSPC;
}

/*
 * Try to flush some data based on policy set by @state. This is only advisory
 * and may fail for various reasons. The caller is supposed to examine the
 * state of @space_info to detect the outcome.
 */
static void flush_space(struct btrfs_fs_info *fs_info,
		       struct btrfs_space_info *space_info, u64 num_bytes,
		       int state)
{
	struct btrfs_root *root = fs_info->extent_root;
	struct btrfs_trans_handle *trans;
	int nr;
	int ret = 0;

	switch (state) {
	case FLUSH_DELAYED_ITEMS_NR:
	case FLUSH_DELAYED_ITEMS:
		if (state == FLUSH_DELAYED_ITEMS_NR)
			nr = calc_reclaim_items_nr(fs_info, num_bytes) * 2;
		else
			nr = -1;

		trans = btrfs_join_transaction(root);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			break;
		}
		ret = btrfs_run_delayed_items_nr(trans, nr);
		btrfs_end_transaction(trans);
		break;
	case FLUSH_DELALLOC:
	case FLUSH_DELALLOC_WAIT:
		shrink_delalloc(fs_info, num_bytes * 2, num_bytes,
				state == FLUSH_DELALLOC_WAIT);
		break;
	case FLUSH_DELAYED_REFS_NR:
	case FLUSH_DELAYED_REFS:
		trans = btrfs_join_transaction(root);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			break;
		}
		if (state == FLUSH_DELAYED_REFS_NR)
			nr = calc_reclaim_items_nr(fs_info, num_bytes);
		else
			nr = 0;
		btrfs_run_delayed_refs(trans, nr);
		btrfs_end_transaction(trans);
		break;
	case ALLOC_CHUNK:
	case ALLOC_CHUNK_FORCE:
		trans = btrfs_join_transaction(root);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			break;
		}
		ret = do_chunk_alloc(trans,
				     btrfs_metadata_alloc_profile(fs_info),
				     (state == ALLOC_CHUNK) ?
				      CHUNK_ALLOC_NO_FORCE : CHUNK_ALLOC_FORCE);
		btrfs_end_transaction(trans);
		if (ret > 0 || ret == -ENOSPC)
			ret = 0;
		break;
	case COMMIT_TRANS:
		/*
		 * If we have pending delayed iputs then we could free up a
		 * bunch of pinned space, so make sure we run the iputs before
		 * we do our pinned bytes check below.
		 */
		btrfs_run_delayed_iputs(fs_info);
		btrfs_wait_on_delayed_iputs(fs_info);

		ret = may_commit_transaction(fs_info, space_info);
		break;
	default:
		ret = -ENOSPC;
		break;
	}

	trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, state,
				ret);
	return;
}

static inline u64
btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
				 struct btrfs_space_info *space_info,
				 bool system_chunk)
{
	struct reserve_ticket *ticket;
	u64 used;
	u64 expected;
	u64 to_reclaim = 0;

	list_for_each_entry(ticket, &space_info->tickets, list)
		to_reclaim += ticket->bytes;
	list_for_each_entry(ticket, &space_info->priority_tickets, list)
		to_reclaim += ticket->bytes;
	if (to_reclaim)
		return to_reclaim;

	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
	if (can_overcommit(fs_info, space_info, to_reclaim,
			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
		return 0;

	used = btrfs_space_info_used(space_info, true);

	if (can_overcommit(fs_info, space_info, SZ_1M,
			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
		expected = div_factor_fine(space_info->total_bytes, 95);
	else
		expected = div_factor_fine(space_info->total_bytes, 90);

	if (used > expected)
		to_reclaim = used - expected;
	else
		to_reclaim = 0;
	to_reclaim = min(to_reclaim, space_info->bytes_may_use +
				     space_info->bytes_reserved);
	return to_reclaim;
}

static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
					struct btrfs_space_info *space_info,
					u64 used, bool system_chunk)
{
	u64 thresh = div_factor_fine(space_info->total_bytes, 98);

	/* If we're just plain full then async reclaim just slows us down. */
	if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
		return 0;

	if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info,
					      system_chunk))
		return 0;

	return (used >= thresh && !btrfs_fs_closing(fs_info) &&
		!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
}

static bool wake_all_tickets(struct list_head *head)
{
	struct reserve_ticket *ticket;

	while (!list_empty(head)) {
		ticket = list_first_entry(head, struct reserve_ticket, list);
		list_del_init(&ticket->list);
		ticket->error = -ENOSPC;
		wake_up(&ticket->wait);
		if (ticket->bytes != ticket->orig_bytes)
			return true;
	}
	return false;
}

/*
 * This is for normal flushers, we can wait all goddamned day if we want to.  We
 * will loop and continuously try to flush as long as we are making progress.
 * We count progress as clearing off tickets each time we have to loop.
 */
static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
{
	struct btrfs_fs_info *fs_info;
	struct btrfs_space_info *space_info;
	u64 to_reclaim;
	int flush_state;
	int commit_cycles = 0;
	u64 last_tickets_id;

	fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
	space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);

	spin_lock(&space_info->lock);
	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
						      false);
	if (!to_reclaim) {
		space_info->flush = 0;
		spin_unlock(&space_info->lock);
		return;
	}
	last_tickets_id = space_info->tickets_id;
	spin_unlock(&space_info->lock);

	flush_state = FLUSH_DELAYED_ITEMS_NR;
	do {
		flush_space(fs_info, space_info, to_reclaim, flush_state);
		spin_lock(&space_info->lock);
		if (list_empty(&space_info->tickets)) {
			space_info->flush = 0;
			spin_unlock(&space_info->lock);
			return;
		}
		to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info,
							      space_info,
							      false);
		if (last_tickets_id == space_info->tickets_id) {
			flush_state++;
		} else {
			last_tickets_id = space_info->tickets_id;
			flush_state = FLUSH_DELAYED_ITEMS_NR;
			if (commit_cycles)
				commit_cycles--;
		}

		/*
		 * We don't want to force a chunk allocation until we've tried
		 * pretty hard to reclaim space.  Think of the case where we
		 * freed up a bunch of space and so have a lot of pinned space
		 * to reclaim.  We would rather use that than possibly create a
		 * underutilized metadata chunk.  So if this is our first run
		 * through the flushing state machine skip ALLOC_CHUNK_FORCE and
		 * commit the transaction.  If nothing has changed the next go
		 * around then we can force a chunk allocation.
		 */
		if (flush_state == ALLOC_CHUNK_FORCE && !commit_cycles)
			flush_state++;

		if (flush_state > COMMIT_TRANS) {
			commit_cycles++;
			if (commit_cycles > 2) {
				if (wake_all_tickets(&space_info->tickets)) {
					flush_state = FLUSH_DELAYED_ITEMS_NR;
					commit_cycles--;
				} else {
					space_info->flush = 0;
				}
			} else {
				flush_state = FLUSH_DELAYED_ITEMS_NR;
			}
		}
		spin_unlock(&space_info->lock);
	} while (flush_state <= COMMIT_TRANS);
}

void btrfs_init_async_reclaim_work(struct work_struct *work)
{
	INIT_WORK(work, btrfs_async_reclaim_metadata_space);
}

static const enum btrfs_flush_state priority_flush_states[] = {
	FLUSH_DELAYED_ITEMS_NR,
	FLUSH_DELAYED_ITEMS,
	ALLOC_CHUNK,
};

static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
					    struct btrfs_space_info *space_info,
					    struct reserve_ticket *ticket)
{
	u64 to_reclaim;
	int flush_state;

	spin_lock(&space_info->lock);
	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
						      false);
	if (!to_reclaim) {
		spin_unlock(&space_info->lock);
		return;
	}
	spin_unlock(&space_info->lock);

	flush_state = 0;
	do {
		flush_space(fs_info, space_info, to_reclaim,
			    priority_flush_states[flush_state]);
		flush_state++;
		spin_lock(&space_info->lock);
		if (ticket->bytes == 0) {
			spin_unlock(&space_info->lock);
			return;
		}
		spin_unlock(&space_info->lock);
	} while (flush_state < ARRAY_SIZE(priority_flush_states));
}

static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
			       struct btrfs_space_info *space_info,
			       struct reserve_ticket *ticket)

{
	DEFINE_WAIT(wait);
	u64 reclaim_bytes = 0;
	int ret = 0;

	spin_lock(&space_info->lock);
	while (ticket->bytes > 0 && ticket->error == 0) {
		ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
		if (ret) {
			ret = -EINTR;
			break;
		}
		spin_unlock(&space_info->lock);

		schedule();

		finish_wait(&ticket->wait, &wait);
		spin_lock(&space_info->lock);
	}
	if (!ret)
		ret = ticket->error;
	if (!list_empty(&ticket->list))
		list_del_init(&ticket->list);
	if (ticket->bytes && ticket->bytes < ticket->orig_bytes)
		reclaim_bytes = ticket->orig_bytes - ticket->bytes;
	spin_unlock(&space_info->lock);

	if (reclaim_bytes)
		space_info_add_old_bytes(fs_info, space_info, reclaim_bytes);
	return ret;
}

/**
 * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
 * @root - the root we're allocating for
 * @space_info - the space info we want to allocate from
 * @orig_bytes - the number of bytes we want
 * @flush - whether or not we can flush to make our reservation
 *
 * This will reserve orig_bytes number of bytes from the space info associated
 * with the block_rsv.  If there is not enough space it will make an attempt to
 * flush out space to make room.  It will do this by flushing delalloc if
 * possible or committing the transaction.  If flush is 0 then no attempts to
 * regain reservations will be made and this will fail if there is not enough
 * space already.
 */
static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
				    struct btrfs_space_info *space_info,
				    u64 orig_bytes,
				    enum btrfs_reserve_flush_enum flush,
				    bool system_chunk)
{
	struct reserve_ticket ticket;
	u64 used;
	u64 reclaim_bytes = 0;
	int ret = 0;

	ASSERT(orig_bytes);
	ASSERT(!current->journal_info || flush != BTRFS_RESERVE_FLUSH_ALL);

	spin_lock(&space_info->lock);
	ret = -ENOSPC;
	used = btrfs_space_info_used(space_info, true);

	/*
	 * If we have enough space then hooray, make our reservation and carry
	 * on.  If not see if we can overcommit, and if we can, hooray carry on.
	 * If not things get more complicated.
	 */
	if (used + orig_bytes <= space_info->total_bytes) {
		update_bytes_may_use(space_info, orig_bytes);
		trace_btrfs_space_reservation(fs_info, "space_info",
					      space_info->flags, orig_bytes, 1);
		ret = 0;
	} else if (can_overcommit(fs_info, space_info, orig_bytes, flush,
				  system_chunk)) {
		update_bytes_may_use(space_info, orig_bytes);
		trace_btrfs_space_reservation(fs_info, "space_info",
					      space_info->flags, orig_bytes, 1);
		ret = 0;
	}

	/*
	 * If we couldn't make a reservation then setup our reservation ticket
	 * and kick the async worker if it's not already running.
	 *
	 * If we are a priority flusher then we just need to add our ticket to
	 * the list and we will do our own flushing further down.
	 */
	if (ret && flush != BTRFS_RESERVE_NO_FLUSH) {
		ticket.orig_bytes = orig_bytes;
		ticket.bytes = orig_bytes;
		ticket.error = 0;
		init_waitqueue_head(&ticket.wait);
		if (flush == BTRFS_RESERVE_FLUSH_ALL) {
			list_add_tail(&ticket.list, &space_info->tickets);
			if (!space_info->flush) {
				space_info->flush = 1;
				trace_btrfs_trigger_flush(fs_info,
							  space_info->flags,
							  orig_bytes, flush,
							  "enospc");
				queue_work(system_unbound_wq,
					   &fs_info->async_reclaim_work);
			}
		} else {
			list_add_tail(&ticket.list,
				      &space_info->priority_tickets);
		}
	} else if (!ret && space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
		used += orig_bytes;
		/*
		 * We will do the space reservation dance during log replay,
		 * which means we won't have fs_info->fs_root set, so don't do
		 * the async reclaim as we will panic.
		 */
		if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) &&
		    need_do_async_reclaim(fs_info, space_info,
					  used, system_chunk) &&
		    !work_busy(&fs_info->async_reclaim_work)) {
			trace_btrfs_trigger_flush(fs_info, space_info->flags,
						  orig_bytes, flush, "preempt");
			queue_work(system_unbound_wq,
				   &fs_info->async_reclaim_work);
		}
	}
	spin_unlock(&space_info->lock);
	if (!ret || flush == BTRFS_RESERVE_NO_FLUSH)
		return ret;

	if (flush == BTRFS_RESERVE_FLUSH_ALL)
		return wait_reserve_ticket(fs_info, space_info, &ticket);

	ret = 0;
	priority_reclaim_metadata_space(fs_info, space_info, &ticket);
	spin_lock(&space_info->lock);
	if (ticket.bytes) {
		if (ticket.bytes < orig_bytes)
			reclaim_bytes = orig_bytes - ticket.bytes;
		list_del_init(&ticket.list);
		ret = -ENOSPC;
	}
	spin_unlock(&space_info->lock);

	if (reclaim_bytes)
		space_info_add_old_bytes(fs_info, space_info, reclaim_bytes);
	ASSERT(list_empty(&ticket.list));
	return ret;
}

/**
 * reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
 * @root - the root we're allocating for
 * @block_rsv - the block_rsv we're allocating for
 * @orig_bytes - the number of bytes we want
 * @flush - whether or not we can flush to make our reservation
 *
 * This will reserve orig_bytes number of bytes from the space info associated
 * with the block_rsv.  If there is not enough space it will make an attempt to
 * flush out space to make room.  It will do this by flushing delalloc if
 * possible or committing the transaction.  If flush is 0 then no attempts to
 * regain reservations will be made and this will fail if there is not enough
 * space already.
 */
static int reserve_metadata_bytes(struct btrfs_root *root,
				  struct btrfs_block_rsv *block_rsv,
				  u64 orig_bytes,
				  enum btrfs_reserve_flush_enum flush)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	int ret;
	bool system_chunk = (root == fs_info->chunk_root);

	ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info,
				       orig_bytes, flush, system_chunk);
	if (ret == -ENOSPC &&
	    unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) {
		if (block_rsv != global_rsv &&
		    !block_rsv_use_bytes(global_rsv, orig_bytes))
			ret = 0;
	}
	if (ret == -ENOSPC) {
		trace_btrfs_space_reservation(fs_info, "space_info:enospc",
					      block_rsv->space_info->flags,
					      orig_bytes, 1);

		if (btrfs_test_opt(fs_info, ENOSPC_DEBUG))
			dump_space_info(fs_info, block_rsv->space_info,
					orig_bytes, 0);
	}
	return ret;
}

static struct btrfs_block_rsv *get_block_rsv(
					const struct btrfs_trans_handle *trans,
					const struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *block_rsv = NULL;

	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
	    (root == fs_info->csum_root && trans->adding_csums) ||
	    (root == fs_info->uuid_root))
		block_rsv = trans->block_rsv;

	if (!block_rsv)
		block_rsv = root->block_rsv;

	if (!block_rsv)
		block_rsv = &fs_info->empty_block_rsv;

	return block_rsv;
}

static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
			       u64 num_bytes)
{
	int ret = -ENOSPC;
	spin_lock(&block_rsv->lock);
	if (block_rsv->reserved >= num_bytes) {
		block_rsv->reserved -= num_bytes;
		if (block_rsv->reserved < block_rsv->size)
			block_rsv->full = 0;
		ret = 0;
	}
	spin_unlock(&block_rsv->lock);
	return ret;
}

static void block_rsv_add_bytes(struct btrfs_block_rsv *block_rsv,
				u64 num_bytes, bool update_size)
{
	spin_lock(&block_rsv->lock);
	block_rsv->reserved += num_bytes;
	if (update_size)
		block_rsv->size += num_bytes;
	else if (block_rsv->reserved >= block_rsv->size)
		block_rsv->full = 1;
	spin_unlock(&block_rsv->lock);
}

int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
			     struct btrfs_block_rsv *dest, u64 num_bytes,
			     int min_factor)
{
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	u64 min_bytes;

	if (global_rsv->space_info != dest->space_info)
		return -ENOSPC;

	spin_lock(&global_rsv->lock);
	min_bytes = div_factor(global_rsv->size, min_factor);
	if (global_rsv->reserved < min_bytes + num_bytes) {
		spin_unlock(&global_rsv->lock);
		return -ENOSPC;
	}
	global_rsv->reserved -= num_bytes;
	if (global_rsv->reserved < global_rsv->size)
		global_rsv->full = 0;
	spin_unlock(&global_rsv->lock);

	block_rsv_add_bytes(dest, num_bytes, true);
	return 0;
}

/**
 * btrfs_migrate_to_delayed_refs_rsv - transfer bytes to our delayed refs rsv.
 * @fs_info - the fs info for our fs.
 * @src - the source block rsv to transfer from.
 * @num_bytes - the number of bytes to transfer.
 *
 * This transfers up to the num_bytes amount from the src rsv to the
 * delayed_refs_rsv.  Any extra bytes are returned to the space info.
 */
void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
				       struct btrfs_block_rsv *src,
				       u64 num_bytes)
{
	struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
	u64 to_free = 0;

	spin_lock(&src->lock);
	src->reserved -= num_bytes;
	src->size -= num_bytes;
	spin_unlock(&src->lock);

	spin_lock(&delayed_refs_rsv->lock);
	if (delayed_refs_rsv->size > delayed_refs_rsv->reserved) {
		u64 delta = delayed_refs_rsv->size -
			delayed_refs_rsv->reserved;
		if (num_bytes > delta) {
			to_free = num_bytes - delta;
			num_bytes = delta;
		}
	} else {
		to_free = num_bytes;
		num_bytes = 0;
	}

	if (num_bytes)
		delayed_refs_rsv->reserved += num_bytes;
	if (delayed_refs_rsv->reserved >= delayed_refs_rsv->size)
		delayed_refs_rsv->full = 1;
	spin_unlock(&delayed_refs_rsv->lock);

	if (num_bytes)
		trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
					      0, num_bytes, 1);
	if (to_free)
		space_info_add_old_bytes(fs_info, delayed_refs_rsv->space_info,
					 to_free);
}

/**
 * btrfs_delayed_refs_rsv_refill - refill based on our delayed refs usage.
 * @fs_info - the fs_info for our fs.
 * @flush - control how we can flush for this reservation.
 *
 * This will refill the delayed block_rsv up to 1 items size worth of space and
 * will return -ENOSPC if we can't make the reservation.
 */
int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
				  enum btrfs_reserve_flush_enum flush)
{
	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
	u64 limit = btrfs_calc_trans_metadata_size(fs_info, 1);
	u64 num_bytes = 0;
	int ret = -ENOSPC;

	spin_lock(&block_rsv->lock);
	if (block_rsv->reserved < block_rsv->size) {
		num_bytes = block_rsv->size - block_rsv->reserved;
		num_bytes = min(num_bytes, limit);
	}
	spin_unlock(&block_rsv->lock);

	if (!num_bytes)
		return 0;

	ret = reserve_metadata_bytes(fs_info->extent_root, block_rsv,
				     num_bytes, flush);
	if (ret)
		return ret;
	block_rsv_add_bytes(block_rsv, num_bytes, 0);
	trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
				      0, num_bytes, 1);
	return 0;
}

/*
 * This is for space we already have accounted in space_info->bytes_may_use, so
 * basically when we're returning space from block_rsv's.
 */
static void space_info_add_old_bytes(struct btrfs_fs_info *fs_info,
				     struct btrfs_space_info *space_info,
				     u64 num_bytes)
{
	struct reserve_ticket *ticket;
	struct list_head *head;
	u64 used;
	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_NO_FLUSH;
	bool check_overcommit = false;

	spin_lock(&space_info->lock);
	head = &space_info->priority_tickets;

	/*
	 * If we are over our limit then we need to check and see if we can
	 * overcommit, and if we can't then we just need to free up our space
	 * and not satisfy any requests.
	 */
	used = btrfs_space_info_used(space_info, true);
	if (used - num_bytes >= space_info->total_bytes)
		check_overcommit = true;
again:
	while (!list_empty(head) && num_bytes) {
		ticket = list_first_entry(head, struct reserve_ticket,
					  list);
		/*
		 * We use 0 bytes because this space is already reserved, so
		 * adding the ticket space would be a double count.
		 */
		if (check_overcommit &&
		    !can_overcommit(fs_info, space_info, 0, flush, false))
			break;
		if (num_bytes >= ticket->bytes) {
			list_del_init(&ticket->list);
			num_bytes -= ticket->bytes;
			ticket->bytes = 0;
			space_info->tickets_id++;
			wake_up(&ticket->wait);
		} else {
			ticket->bytes -= num_bytes;
			num_bytes = 0;
		}
	}

	if (num_bytes && head == &space_info->priority_tickets) {
		head = &space_info->tickets;
		flush = BTRFS_RESERVE_FLUSH_ALL;
		goto again;
	}
	update_bytes_may_use(space_info, -num_bytes);
	trace_btrfs_space_reservation(fs_info, "space_info",
				      space_info->flags, num_bytes, 0);
	spin_unlock(&space_info->lock);
}

/*
 * This is for newly allocated space that isn't accounted in
 * space_info->bytes_may_use yet.  So if we allocate a chunk or unpin an extent
 * we use this helper.
 */
static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
				     struct btrfs_space_info *space_info,
				     u64 num_bytes)
{
	struct reserve_ticket *ticket;
	struct list_head *head = &space_info->priority_tickets;

again:
	while (!list_empty(head) && num_bytes) {
		ticket = list_first_entry(head, struct reserve_ticket,
					  list);
		if (num_bytes >= ticket->bytes) {
			trace_btrfs_space_reservation(fs_info, "space_info",
						      space_info->flags,
						      ticket->bytes, 1);
			list_del_init(&ticket->list);
			num_bytes -= ticket->bytes;
			update_bytes_may_use(space_info, ticket->bytes);
			ticket->bytes = 0;
			space_info->tickets_id++;
			wake_up(&ticket->wait);
		} else {
			trace_btrfs_space_reservation(fs_info, "space_info",
						      space_info->flags,
						      num_bytes, 1);
			update_bytes_may_use(space_info, num_bytes);
			ticket->bytes -= num_bytes;
			num_bytes = 0;
		}
	}

	if (num_bytes && head == &space_info->priority_tickets) {
		head = &space_info->tickets;
		goto again;
	}
}

static u64 block_rsv_release_bytes(struct btrfs_fs_info *fs_info,
				    struct btrfs_block_rsv *block_rsv,
				    struct btrfs_block_rsv *dest, u64 num_bytes,
				    u64 *qgroup_to_release_ret)
{
	struct btrfs_space_info *space_info = block_rsv->space_info;
	u64 qgroup_to_release = 0;
	u64 ret;

	spin_lock(&block_rsv->lock);
	if (num_bytes == (u64)-1) {
		num_bytes = block_rsv->size;
		qgroup_to_release = block_rsv->qgroup_rsv_size;
	}
	block_rsv->size -= num_bytes;
	if (block_rsv->reserved >= block_rsv->size) {
		num_bytes = block_rsv->reserved - block_rsv->size;
		block_rsv->reserved = block_rsv->size;
		block_rsv->full = 1;
	} else {
		num_bytes = 0;
	}
	if (block_rsv->qgroup_rsv_reserved >= block_rsv->qgroup_rsv_size) {
		qgroup_to_release = block_rsv->qgroup_rsv_reserved -
				    block_rsv->qgroup_rsv_size;
		block_rsv->qgroup_rsv_reserved = block_rsv->qgroup_rsv_size;
	} else {
		qgroup_to_release = 0;
	}
	spin_unlock(&block_rsv->lock);

	ret = num_bytes;
	if (num_bytes > 0) {
		if (dest) {
			spin_lock(&dest->lock);
			if (!dest->full) {
				u64 bytes_to_add;

				bytes_to_add = dest->size - dest->reserved;
				bytes_to_add = min(num_bytes, bytes_to_add);
				dest->reserved += bytes_to_add;
				if (dest->reserved >= dest->size)
					dest->full = 1;
				num_bytes -= bytes_to_add;
			}
			spin_unlock(&dest->lock);
		}
		if (num_bytes)
			space_info_add_old_bytes(fs_info, space_info,
						 num_bytes);
	}
	if (qgroup_to_release_ret)
		*qgroup_to_release_ret = qgroup_to_release;
	return ret;
}

int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src,
			    struct btrfs_block_rsv *dst, u64 num_bytes,
			    bool update_size)
{
	int ret;

	ret = block_rsv_use_bytes(src, num_bytes);
	if (ret)
		return ret;

	block_rsv_add_bytes(dst, num_bytes, update_size);
	return 0;
}

void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type)
{
	memset(rsv, 0, sizeof(*rsv));
	spin_lock_init(&rsv->lock);
	rsv->type = type;
}

void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
				   struct btrfs_block_rsv *rsv,
				   unsigned short type)
{
	btrfs_init_block_rsv(rsv, type);
	rsv->space_info = __find_space_info(fs_info,
					    BTRFS_BLOCK_GROUP_METADATA);
}

struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
					      unsigned short type)
{
	struct btrfs_block_rsv *block_rsv;

	block_rsv = kmalloc(sizeof(*block_rsv), GFP_NOFS);
	if (!block_rsv)
		return NULL;

	btrfs_init_metadata_block_rsv(fs_info, block_rsv, type);
	return block_rsv;
}

void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
			  struct btrfs_block_rsv *rsv)
{
	if (!rsv)
		return;
	btrfs_block_rsv_release(fs_info, rsv, (u64)-1);
	kfree(rsv);
}

int btrfs_block_rsv_add(struct btrfs_root *root,
			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
			enum btrfs_reserve_flush_enum flush)
{
	int ret;

	if (num_bytes == 0)
		return 0;

	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
	if (!ret)
		block_rsv_add_bytes(block_rsv, num_bytes, true);

	return ret;
}

int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_factor)
{
	u64 num_bytes = 0;
	int ret = -ENOSPC;

	if (!block_rsv)
		return 0;

	spin_lock(&block_rsv->lock);
	num_bytes = div_factor(block_rsv->size, min_factor);
	if (block_rsv->reserved >= num_bytes)
		ret = 0;
	spin_unlock(&block_rsv->lock);

	return ret;
}

int btrfs_block_rsv_refill(struct btrfs_root *root,
			   struct btrfs_block_rsv *block_rsv, u64 min_reserved,
			   enum btrfs_reserve_flush_enum flush)
{
	u64 num_bytes = 0;
	int ret = -ENOSPC;

	if (!block_rsv)
		return 0;

	spin_lock(&block_rsv->lock);
	num_bytes = min_reserved;
	if (block_rsv->reserved >= num_bytes)
		ret = 0;
	else
		num_bytes -= block_rsv->reserved;
	spin_unlock(&block_rsv->lock);

	if (!ret)
		return 0;

	ret = reserve_metadata_bytes(root, block_rsv, num_bytes, flush);
	if (!ret) {
		block_rsv_add_bytes(block_rsv, num_bytes, false);
		return 0;
	}

	return ret;
}

static u64 __btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
				     struct btrfs_block_rsv *block_rsv,
				     u64 num_bytes, u64 *qgroup_to_release)
{
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
	struct btrfs_block_rsv *target = delayed_rsv;

	if (target->full || target == block_rsv)
		target = global_rsv;

	if (block_rsv->space_info != target->space_info)
		target = NULL;

	return block_rsv_release_bytes(fs_info, block_rsv, target, num_bytes,
				       qgroup_to_release);
}

void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
			     struct btrfs_block_rsv *block_rsv,
			     u64 num_bytes)
{
	__btrfs_block_rsv_release(fs_info, block_rsv, num_bytes, NULL);
}

/**
 * btrfs_inode_rsv_release - release any excessive reservation.
 * @inode - the inode we need to release from.
 * @qgroup_free - free or convert qgroup meta.
 *   Unlike normal operation, qgroup meta reservation needs to know if we are
 *   freeing qgroup reservation or just converting it into per-trans.  Normally
 *   @qgroup_free is true for error handling, and false for normal release.
 *
 * This is the same as btrfs_block_rsv_release, except that it handles the
 * tracepoint for the reservation.
 */
static void btrfs_inode_rsv_release(struct btrfs_inode *inode, bool qgroup_free)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
	u64 released = 0;
	u64 qgroup_to_release = 0;

	/*
	 * Since we statically set the block_rsv->size we just want to say we
	 * are releasing 0 bytes, and then we'll just get the reservation over
	 * the size free'd.
	 */
	released = __btrfs_block_rsv_release(fs_info, block_rsv, 0,
					     &qgroup_to_release);
	if (released > 0)
		trace_btrfs_space_reservation(fs_info, "delalloc",
					      btrfs_ino(inode), released, 0);
	if (qgroup_free)
		btrfs_qgroup_free_meta_prealloc(inode->root, qgroup_to_release);
	else
		btrfs_qgroup_convert_reserved_meta(inode->root,
						   qgroup_to_release);
}

/**
 * btrfs_delayed_refs_rsv_release - release a ref head's reservation.
 * @fs_info - the fs_info for our fs.
 * @nr - the number of items to drop.
 *
 * This drops the delayed ref head's count from the delayed refs rsv and frees
 * any excess reservation we had.
 */
void btrfs_delayed_refs_rsv_release(struct btrfs_fs_info *fs_info, int nr)
{
	struct btrfs_block_rsv *block_rsv = &fs_info->delayed_refs_rsv;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, nr);
	u64 released = 0;

	released = block_rsv_release_bytes(fs_info, block_rsv, global_rsv,
					   num_bytes, NULL);
	if (released)
		trace_btrfs_space_reservation(fs_info, "delayed_refs_rsv",
					      0, released, 0);
}

static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
{
	struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
	struct btrfs_space_info *sinfo = block_rsv->space_info;
	u64 num_bytes;

	/*
	 * The global block rsv is based on the size of the extent tree, the
	 * checksum tree and the root tree.  If the fs is empty we want to set
	 * it to a minimal amount for safety.
	 */
	num_bytes = btrfs_root_used(&fs_info->extent_root->root_item) +
		btrfs_root_used(&fs_info->csum_root->root_item) +
		btrfs_root_used(&fs_info->tree_root->root_item);
	num_bytes = max_t(u64, num_bytes, SZ_16M);

	spin_lock(&sinfo->lock);
	spin_lock(&block_rsv->lock);

	block_rsv->size = min_t(u64, num_bytes, SZ_512M);

	if (block_rsv->reserved < block_rsv->size) {
		num_bytes = btrfs_space_info_used(sinfo, true);
		if (sinfo->total_bytes > num_bytes) {
			num_bytes = sinfo->total_bytes - num_bytes;
			num_bytes = min(num_bytes,
					block_rsv->size - block_rsv->reserved);
			block_rsv->reserved += num_bytes;
			update_bytes_may_use(sinfo, num_bytes);
			trace_btrfs_space_reservation(fs_info, "space_info",
						      sinfo->flags, num_bytes,
						      1);
		}
	} else if (block_rsv->reserved > block_rsv->size) {
		num_bytes = block_rsv->reserved - block_rsv->size;
		update_bytes_may_use(sinfo, -num_bytes);
		trace_btrfs_space_reservation(fs_info, "space_info",
				      sinfo->flags, num_bytes, 0);
		block_rsv->reserved = block_rsv->size;
	}

	if (block_rsv->reserved == block_rsv->size)
		block_rsv->full = 1;
	else
		block_rsv->full = 0;

	spin_unlock(&block_rsv->lock);
	spin_unlock(&sinfo->lock);
}

static void init_global_block_rsv(struct btrfs_fs_info *fs_info)
{
	struct btrfs_space_info *space_info;

	space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
	fs_info->chunk_block_rsv.space_info = space_info;

	space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
	fs_info->global_block_rsv.space_info = space_info;
	fs_info->trans_block_rsv.space_info = space_info;
	fs_info->empty_block_rsv.space_info = space_info;
	fs_info->delayed_block_rsv.space_info = space_info;
	fs_info->delayed_refs_rsv.space_info = space_info;

	fs_info->extent_root->block_rsv = &fs_info->delayed_refs_rsv;
	fs_info->csum_root->block_rsv = &fs_info->delayed_refs_rsv;
	fs_info->dev_root->block_rsv = &fs_info->global_block_rsv;
	fs_info->tree_root->block_rsv = &fs_info->global_block_rsv;
	if (fs_info->quota_root)
		fs_info->quota_root->block_rsv = &fs_info->global_block_rsv;
	fs_info->chunk_root->block_rsv = &fs_info->chunk_block_rsv;

	update_global_block_rsv(fs_info);
}

static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
{
	block_rsv_release_bytes(fs_info, &fs_info->global_block_rsv, NULL,
				(u64)-1, NULL);
	WARN_ON(fs_info->trans_block_rsv.size > 0);
	WARN_ON(fs_info->trans_block_rsv.reserved > 0);
	WARN_ON(fs_info->chunk_block_rsv.size > 0);
	WARN_ON(fs_info->chunk_block_rsv.reserved > 0);
	WARN_ON(fs_info->delayed_block_rsv.size > 0);
	WARN_ON(fs_info->delayed_block_rsv.reserved > 0);
	WARN_ON(fs_info->delayed_refs_rsv.reserved > 0);
	WARN_ON(fs_info->delayed_refs_rsv.size > 0);
}

/*
 * btrfs_update_delayed_refs_rsv - adjust the size of the delayed refs rsv
 * @trans - the trans that may have generated delayed refs
 *
 * This is to be called anytime we may have adjusted trans->delayed_ref_updates,
 * it'll calculate the additional size and add it to the delayed_refs_rsv.
 */
void btrfs_update_delayed_refs_rsv(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_refs_rsv;
	u64 num_bytes;

	if (!trans->delayed_ref_updates)
		return;

	num_bytes = btrfs_calc_trans_metadata_size(fs_info,
						   trans->delayed_ref_updates);
	spin_lock(&delayed_rsv->lock);
	delayed_rsv->size += num_bytes;
	delayed_rsv->full = 0;
	spin_unlock(&delayed_rsv->lock);
	trans->delayed_ref_updates = 0;
}

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

	if (!trans->chunk_bytes_reserved)
		return;

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

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

/*
 * btrfs_subvolume_reserve_metadata() - reserve space for subvolume operation
 * root: the root of the parent directory
 * rsv: block reservation
 * items: the number of items that we need do reservation
 * use_global_rsv: allow fallback to the global block reservation
 *
 * This function is used to reserve the space for snapshot/subvolume
 * creation and deletion. Those operations are different with the
 * common file/directory operations, they change two fs/file trees
 * and root tree, the number of items that the qgroup reserves is
 * different with the free space reservation. So we can not use
 * the space reservation mechanism in start_transaction().
 */
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
				     struct btrfs_block_rsv *rsv, int items,
				     bool use_global_rsv)
{
	u64 qgroup_num_bytes = 0;
	u64 num_bytes;
	int ret;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;

	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
		/* One for parent inode, two for dir entries */
		qgroup_num_bytes = 3 * fs_info->nodesize;
		ret = btrfs_qgroup_reserve_meta_prealloc(root,
				qgroup_num_bytes, true);
		if (ret)
			return ret;
	}

	num_bytes = btrfs_calc_trans_metadata_size(fs_info, items);
	rsv->space_info = __find_space_info(fs_info,
					    BTRFS_BLOCK_GROUP_METADATA);
	ret = btrfs_block_rsv_add(root, rsv, num_bytes,
				  BTRFS_RESERVE_FLUSH_ALL);

	if (ret == -ENOSPC && use_global_rsv)
		ret = btrfs_block_rsv_migrate(global_rsv, rsv, num_bytes, true);

	if (ret && qgroup_num_bytes)
		btrfs_qgroup_free_meta_prealloc(root, qgroup_num_bytes);

	return ret;
}

void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
				      struct btrfs_block_rsv *rsv)
{
	btrfs_block_rsv_release(fs_info, rsv, (u64)-1);
}

static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
						 struct btrfs_inode *inode)
{
	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
	u64 reserve_size = 0;
	u64 qgroup_rsv_size = 0;
	u64 csum_leaves;
	unsigned outstanding_extents;

	lockdep_assert_held(&inode->lock);
	outstanding_extents = inode->outstanding_extents;
	if (outstanding_extents)
		reserve_size = btrfs_calc_trans_metadata_size(fs_info,
						outstanding_extents + 1);
	csum_leaves = btrfs_csum_bytes_to_leaves(fs_info,
						 inode->csum_bytes);
	reserve_size += btrfs_calc_trans_metadata_size(fs_info,
						       csum_leaves);
	/*
	 * For qgroup rsv, the calculation is very simple:
	 * account one nodesize for each outstanding extent
	 *
	 * This is overestimating in most cases.
	 */
	qgroup_rsv_size = (u64)outstanding_extents * fs_info->nodesize;

	spin_lock(&block_rsv->lock);
	block_rsv->size = reserve_size;
	block_rsv->qgroup_rsv_size = qgroup_rsv_size;
	spin_unlock(&block_rsv->lock);
}

static void calc_inode_reservations(struct btrfs_fs_info *fs_info,
				    u64 num_bytes, u64 *meta_reserve,
				    u64 *qgroup_reserve)
{
	u64 nr_extents = count_max_extents(num_bytes);
	u64 csum_leaves = btrfs_csum_bytes_to_leaves(fs_info, num_bytes);

	/* We add one for the inode update at finish ordered time */
	*meta_reserve = btrfs_calc_trans_metadata_size(fs_info,
						nr_extents + csum_leaves + 1);
	*qgroup_reserve = nr_extents * fs_info->nodesize;
}

int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *block_rsv = &inode->block_rsv;
	u64 meta_reserve, qgroup_reserve;
	unsigned nr_extents;
	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
	int ret = 0;
	bool delalloc_lock = true;

	/* If we are a free space inode we need to not flush since we will be in
	 * the middle of a transaction commit.  We also don't need the delalloc
	 * mutex since we won't race with anybody.  We need this mostly to make
	 * lockdep shut its filthy mouth.
	 *
	 * If we have a transaction open (can happen if we call truncate_block
	 * from truncate), then we need FLUSH_LIMIT so we don't deadlock.
	 */
	if (btrfs_is_free_space_inode(inode)) {
		flush = BTRFS_RESERVE_NO_FLUSH;
		delalloc_lock = false;
	} else {
		if (current->journal_info)
			flush = BTRFS_RESERVE_FLUSH_LIMIT;

		if (btrfs_transaction_in_commit(fs_info))
			schedule_timeout(1);
	}

	if (delalloc_lock)
		mutex_lock(&inode->delalloc_mutex);

	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);

	/*
	 * We always want to do it this way, every other way is wrong and ends
	 * in tears.  Pre-reserving the amount we are going to add will always
	 * be the right way, because otherwise if we have enough parallelism we
	 * could end up with thousands of inodes all holding little bits of
	 * reservations they were able to make previously and the only way to
	 * reclaim that space is to ENOSPC out the operations and clear
	 * everything out and try again, which is bad.  This way we just
	 * over-reserve slightly, and clean up the mess when we are done.
	 */
	calc_inode_reservations(fs_info, num_bytes, &meta_reserve,
				&qgroup_reserve);
	ret = btrfs_qgroup_reserve_meta_prealloc(root, qgroup_reserve, true);
	if (ret)
		goto out_fail;
	ret = reserve_metadata_bytes(root, block_rsv, meta_reserve, flush);
	if (ret)
		goto out_qgroup;

	/*
	 * Now we need to update our outstanding extents and csum bytes _first_
	 * and then add the reservation to the block_rsv.  This keeps us from
	 * racing with an ordered completion or some such that would think it
	 * needs to free the reservation we just made.
	 */
	spin_lock(&inode->lock);
	nr_extents = count_max_extents(num_bytes);
	btrfs_mod_outstanding_extents(inode, nr_extents);
	inode->csum_bytes += num_bytes;
	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
	spin_unlock(&inode->lock);

	/* Now we can safely add our space to our block rsv */
	block_rsv_add_bytes(block_rsv, meta_reserve, false);
	trace_btrfs_space_reservation(root->fs_info, "delalloc",
				      btrfs_ino(inode), meta_reserve, 1);

	spin_lock(&block_rsv->lock);
	block_rsv->qgroup_rsv_reserved += qgroup_reserve;
	spin_unlock(&block_rsv->lock);

	if (delalloc_lock)
		mutex_unlock(&inode->delalloc_mutex);
	return 0;
out_qgroup:
	btrfs_qgroup_free_meta_prealloc(root, qgroup_reserve);
out_fail:
	btrfs_inode_rsv_release(inode, true);
	if (delalloc_lock)
		mutex_unlock(&inode->delalloc_mutex);
	return ret;
}

/**
 * btrfs_delalloc_release_metadata - release a metadata reservation for an inode
 * @inode: the inode to release the reservation for.
 * @num_bytes: the number of bytes we are releasing.
 * @qgroup_free: free qgroup reservation or convert it to per-trans reservation
 *
 * This will release the metadata reservation for an inode.  This can be called
 * once we complete IO for a given set of bytes to release their metadata
 * reservations, or on error for the same reason.
 */
void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
				     bool qgroup_free)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;

	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
	spin_lock(&inode->lock);
	inode->csum_bytes -= num_bytes;
	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
	spin_unlock(&inode->lock);

	if (btrfs_is_testing(fs_info))
		return;

	btrfs_inode_rsv_release(inode, qgroup_free);
}

/**
 * btrfs_delalloc_release_extents - release our outstanding_extents
 * @inode: the inode to balance the reservation for.
 * @num_bytes: the number of bytes we originally reserved with
 * @qgroup_free: do we need to free qgroup meta reservation or convert them.
 *
 * When we reserve space we increase outstanding_extents for the extents we may
 * add.  Once we've set the range as delalloc or created our ordered extents we
 * have outstanding_extents to track the real usage, so we use this to free our
 * temporarily tracked outstanding_extents.  This _must_ be used in conjunction
 * with btrfs_delalloc_reserve_metadata.
 */
void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
				    bool qgroup_free)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	unsigned num_extents;

	spin_lock(&inode->lock);
	num_extents = count_max_extents(num_bytes);
	btrfs_mod_outstanding_extents(inode, -num_extents);
	btrfs_calculate_inode_block_rsv_size(fs_info, inode);
	spin_unlock(&inode->lock);

	if (btrfs_is_testing(fs_info))
		return;

	btrfs_inode_rsv_release(inode, qgroup_free);
}

/**
 * btrfs_delalloc_reserve_space - reserve data and metadata space for
 * delalloc
 * @inode: inode we're writing to
 * @start: start range we are writing to
 * @len: how long the range we are writing to
 * @reserved: mandatory parameter, record actually reserved qgroup ranges of
 * 	      current reservation.
 *
 * This will do the following things
 *
 * o reserve space in data space info for num bytes
 *   and reserve precious corresponding qgroup space
 *   (Done in check_data_free_space)
 *
 * o reserve space for metadata space, based on the number of outstanding
 *   extents and how much csums will be needed
 *   also reserve metadata space in a per root over-reserve method.
 * o add to the inodes->delalloc_bytes
 * o add it to the fs_info's delalloc inodes list.
 *   (Above 3 all done in delalloc_reserve_metadata)
 *
 * Return 0 for success
 * Return <0 for error(-ENOSPC or -EQUOT)
 */
int btrfs_delalloc_reserve_space(struct inode *inode,
			struct extent_changeset **reserved, u64 start, u64 len)
{
	int ret;

	ret = btrfs_check_data_free_space(inode, reserved, start, len);
	if (ret < 0)
		return ret;
	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);
	if (ret < 0)
		btrfs_free_reserved_data_space(inode, *reserved, start, len);
	return ret;
}

/**
 * btrfs_delalloc_release_space - release data and metadata space for delalloc
 * @inode: inode we're releasing space for
 * @start: start position of the space already reserved
 * @len: the len of the space already reserved
 * @release_bytes: the len of the space we consumed or didn't use
 *
 * This function will release the metadata space that was not used and will
 * decrement ->delalloc_bytes and remove it from the fs_info delalloc_inodes
 * list if there are no delalloc bytes left.
 * Also it will handle the qgroup reserved space.
 */
void btrfs_delalloc_release_space(struct inode *inode,
				  struct extent_changeset *reserved,
				  u64 start, u64 len, bool qgroup_free)
{
	btrfs_delalloc_release_metadata(BTRFS_I(inode), len, qgroup_free);
	btrfs_free_reserved_data_space(inode, reserved, start, len);
}

static int update_block_group(struct btrfs_trans_handle *trans,
			      u64 bytenr, u64 num_bytes, int alloc)
{
	struct btrfs_fs_info *info = trans->fs_info;
	struct btrfs_block_group_cache *cache = NULL;
	u64 total = num_bytes;
	u64 old_val;
	u64 byte_in_group;
	int factor;
	int ret = 0;

	/* block accounting for super block */
	spin_lock(&info->delalloc_root_lock);
	old_val = btrfs_super_bytes_used(info->super_copy);
	if (alloc)
		old_val += num_bytes;
	else
		old_val -= num_bytes;
	btrfs_set_super_bytes_used(info->super_copy, old_val);
	spin_unlock(&info->delalloc_root_lock);

	while (total) {
		cache = btrfs_lookup_block_group(info, bytenr);
		if (!cache) {
			ret = -ENOENT;
			break;
		}
		factor = btrfs_bg_type_to_factor(cache->flags);

		/*
		 * If this block group has free space cache written out, we
		 * need to make sure to load it if we are removing space.  This
		 * is because we need the unpinning stage to actually add the
		 * space back to the block group, otherwise we will leak space.
		 */
		if (!alloc && cache->cached == BTRFS_CACHE_NO)
			cache_block_group(cache, 1);

		byte_in_group = bytenr - cache->key.objectid;
		WARN_ON(byte_in_group > cache->key.offset);

		spin_lock(&cache->space_info->lock);
		spin_lock(&cache->lock);

		if (btrfs_test_opt(info, SPACE_CACHE) &&
		    cache->disk_cache_state < BTRFS_DC_CLEAR)
			cache->disk_cache_state = BTRFS_DC_CLEAR;

		old_val = btrfs_block_group_used(&cache->item);
		num_bytes = min(total, cache->key.offset - byte_in_group);
		if (alloc) {
			old_val += num_bytes;
			btrfs_set_block_group_used(&cache->item, old_val);
			cache->reserved -= num_bytes;
			cache->space_info->bytes_reserved -= num_bytes;
			cache->space_info->bytes_used += num_bytes;
			cache->space_info->disk_used += num_bytes * factor;
			spin_unlock(&cache->lock);
			spin_unlock(&cache->space_info->lock);
		} else {
			old_val -= num_bytes;
			btrfs_set_block_group_used(&cache->item, old_val);
			cache->pinned += num_bytes;
			update_bytes_pinned(cache->space_info, num_bytes);
			cache->space_info->bytes_used -= num_bytes;
			cache->space_info->disk_used -= num_bytes * factor;
			spin_unlock(&cache->lock);
			spin_unlock(&cache->space_info->lock);

			trace_btrfs_space_reservation(info, "pinned",
						      cache->space_info->flags,
						      num_bytes, 1);
			percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
					   num_bytes,
					   BTRFS_TOTAL_BYTES_PINNED_BATCH);
			set_extent_dirty(info->pinned_extents,
					 bytenr, bytenr + num_bytes - 1,
					 GFP_NOFS | __GFP_NOFAIL);
		}

		spin_lock(&trans->transaction->dirty_bgs_lock);
		if (list_empty(&cache->dirty_list)) {
			list_add_tail(&cache->dirty_list,
				      &trans->transaction->dirty_bgs);
			trans->delayed_ref_updates++;
			btrfs_get_block_group(cache);
		}
		spin_unlock(&trans->transaction->dirty_bgs_lock);

		/*
		 * No longer have used bytes in this block group, queue it for
		 * deletion. We do this after adding the block group to the
		 * dirty list to avoid races between cleaner kthread and space
		 * cache writeout.
		 */
		if (!alloc && old_val == 0)
			btrfs_mark_bg_unused(cache);

		btrfs_put_block_group(cache);
		total -= num_bytes;
		bytenr += num_bytes;
	}

	/* Modified block groups are accounted for in the delayed_refs_rsv. */
	btrfs_update_delayed_refs_rsv(trans);
	return ret;
}

static u64 first_logical_byte(struct btrfs_fs_info *fs_info, u64 search_start)
{
	struct btrfs_block_group_cache *cache;
	u64 bytenr;

	spin_lock(&fs_info->block_group_cache_lock);
	bytenr = fs_info->first_logical_byte;
	spin_unlock(&fs_info->block_group_cache_lock);

	if (bytenr < (u64)-1)
		return bytenr;

	cache = btrfs_lookup_first_block_group(fs_info, search_start);
	if (!cache)
		return 0;

	bytenr = cache->key.objectid;
	btrfs_put_block_group(cache);

	return bytenr;
}

static int pin_down_extent(struct btrfs_block_group_cache *cache,
			   u64 bytenr, u64 num_bytes, int reserved)
{
	struct btrfs_fs_info *fs_info = cache->fs_info;

	spin_lock(&cache->space_info->lock);
	spin_lock(&cache->lock);
	cache->pinned += num_bytes;
	update_bytes_pinned(cache->space_info, num_bytes);
	if (reserved) {
		cache->reserved -= num_bytes;
		cache->space_info->bytes_reserved -= num_bytes;
	}
	spin_unlock(&cache->lock);
	spin_unlock(&cache->space_info->lock);

	trace_btrfs_space_reservation(fs_info, "pinned",
				      cache->space_info->flags, num_bytes, 1);
	percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
		    num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH);
	set_extent_dirty(fs_info->pinned_extents, bytenr,
			 bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL);
	return 0;
}

/*
 * this function must be called within transaction
 */
int btrfs_pin_extent(struct btrfs_fs_info *fs_info,
		     u64 bytenr, u64 num_bytes, int reserved)
{
	struct btrfs_block_group_cache *cache;

	cache = btrfs_lookup_block_group(fs_info, bytenr);
	BUG_ON(!cache); /* Logic error */

	pin_down_extent(cache, bytenr, num_bytes, reserved);

	btrfs_put_block_group(cache);
	return 0;
}

/*
 * this function must be called within transaction
 */
int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
				    u64 bytenr, u64 num_bytes)
{
	struct btrfs_block_group_cache *cache;
	int ret;

	cache = btrfs_lookup_block_group(fs_info, bytenr);
	if (!cache)
		return -EINVAL;

	/*
	 * pull in the free space cache (if any) so that our pin
	 * removes the free space from the cache.  We have load_only set
	 * to one because the slow code to read in the free extents does check
	 * the pinned extents.
	 */
	cache_block_group(cache, 1);

	pin_down_extent(cache, bytenr, num_bytes, 0);

	/* remove us from the free space cache (if we're there at all) */
	ret = btrfs_remove_free_space(cache, bytenr, num_bytes);
	btrfs_put_block_group(cache);
	return ret;
}

static int __exclude_logged_extent(struct btrfs_fs_info *fs_info,
				   u64 start, u64 num_bytes)
{
	int ret;
	struct btrfs_block_group_cache *block_group;
	struct btrfs_caching_control *caching_ctl;

	block_group = btrfs_lookup_block_group(fs_info, start);
	if (!block_group)
		return -EINVAL;

	cache_block_group(block_group, 0);
	caching_ctl = get_caching_control(block_group);

	if (!caching_ctl) {
		/* Logic error */
		BUG_ON(!block_group_cache_done(block_group));
		ret = btrfs_remove_free_space(block_group, start, num_bytes);
	} else {
		mutex_lock(&caching_ctl->mutex);

		if (start >= caching_ctl->progress) {
			ret = add_excluded_extent(fs_info, start, num_bytes);
		} else if (start + num_bytes <= caching_ctl->progress) {
			ret = btrfs_remove_free_space(block_group,
						      start, num_bytes);
		} else {
			num_bytes = caching_ctl->progress - start;
			ret = btrfs_remove_free_space(block_group,
						      start, num_bytes);
			if (ret)
				goto out_lock;

			num_bytes = (start + num_bytes) -
				caching_ctl->progress;
			start = caching_ctl->progress;
			ret = add_excluded_extent(fs_info, start, num_bytes);
		}
out_lock:
		mutex_unlock(&caching_ctl->mutex);
		put_caching_control(caching_ctl);
	}
	btrfs_put_block_group(block_group);
	return ret;
}

int btrfs_exclude_logged_extents(struct extent_buffer *eb)
{
	struct btrfs_fs_info *fs_info = eb->fs_info;
	struct btrfs_file_extent_item *item;
	struct btrfs_key key;
	int found_type;
	int i;
	int ret = 0;

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

	for (i = 0; i < btrfs_header_nritems(eb); i++) {
		btrfs_item_key_to_cpu(eb, &key, i);
		if (key.type != BTRFS_EXTENT_DATA_KEY)
			continue;
		item = btrfs_item_ptr(eb, i, struct btrfs_file_extent_item);
		found_type = btrfs_file_extent_type(eb, item);
		if (found_type == BTRFS_FILE_EXTENT_INLINE)
			continue;
		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
			continue;
		key.objectid = btrfs_file_extent_disk_bytenr(eb, item);
		key.offset = btrfs_file_extent_disk_num_bytes(eb, item);
		ret = __exclude_logged_extent(fs_info, key.objectid, key.offset);
		if (ret)
			break;
	}

	return ret;
}

static void
btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
{
	atomic_inc(&bg->reservations);
}

void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
					const u64 start)
{
	struct btrfs_block_group_cache *bg;

	bg = btrfs_lookup_block_group(fs_info, start);
	ASSERT(bg);
	if (atomic_dec_and_test(&bg->reservations))
		wake_up_var(&bg->reservations);
	btrfs_put_block_group(bg);
}

void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
{
	struct btrfs_space_info *space_info = bg->space_info;

	ASSERT(bg->ro);

	if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA))
		return;

	/*
	 * Our block group is read only but before we set it to read only,
	 * some task might have had allocated an extent from it already, but it
	 * has not yet created a respective ordered extent (and added it to a
	 * root's list of ordered extents).
	 * Therefore wait for any task currently allocating extents, since the
	 * block group's reservations counter is incremented while a read lock
	 * on the groups' semaphore is held and decremented after releasing
	 * the read access on that semaphore and creating the ordered extent.
	 */
	down_write(&space_info->groups_sem);
	up_write(&space_info->groups_sem);

	wait_var_event(&bg->reservations, !atomic_read(&bg->reservations));
}

/**
 * btrfs_add_reserved_bytes - update the block_group and space info counters
 * @cache:	The cache we are manipulating
 * @ram_bytes:  The number of bytes of file content, and will be same to
 *              @num_bytes except for the compress path.
 * @num_bytes:	The number of bytes in question
 * @delalloc:   The blocks are allocated for the delalloc write
 *
 * This is called by the allocator when it reserves space. If this is a
 * reservation and the block group has become read only we cannot make the
 * reservation and return -EAGAIN, otherwise this function always succeeds.
 */
static int btrfs_add_reserved_bytes(struct btrfs_block_group_cache *cache,
				    u64 ram_bytes, u64 num_bytes, int delalloc)
{
	struct btrfs_space_info *space_info = cache->space_info;
	int ret = 0;

	spin_lock(&space_info->lock);
	spin_lock(&cache->lock);
	if (cache->ro) {
		ret = -EAGAIN;
	} else {
		cache->reserved += num_bytes;
		space_info->bytes_reserved += num_bytes;
		update_bytes_may_use(space_info, -ram_bytes);
		if (delalloc)
			cache->delalloc_bytes += num_bytes;
	}
	spin_unlock(&cache->lock);
	spin_unlock(&space_info->lock);
	return ret;
}

/**
 * btrfs_free_reserved_bytes - update the block_group and space info counters
 * @cache:      The cache we are manipulating
 * @num_bytes:  The number of bytes in question
 * @delalloc:   The blocks are allocated for the delalloc write
 *
 * This is called by somebody who is freeing space that was never actually used
 * on disk.  For example if you reserve some space for a new leaf in transaction
 * A and before transaction A commits you free that leaf, you call this with
 * reserve set to 0 in order to clear the reservation.
 */

static void btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
				      u64 num_bytes, int delalloc)
{
	struct btrfs_space_info *space_info = cache->space_info;

	spin_lock(&space_info->lock);
	spin_lock(&cache->lock);
	if (cache->ro)
		space_info->bytes_readonly += num_bytes;
	cache->reserved -= num_bytes;
	space_info->bytes_reserved -= num_bytes;
	space_info->max_extent_size = 0;

	if (delalloc)
		cache->delalloc_bytes -= num_bytes;
	spin_unlock(&cache->lock);
	spin_unlock(&space_info->lock);
}
void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info)
{
	struct btrfs_caching_control *next;
	struct btrfs_caching_control *caching_ctl;
	struct btrfs_block_group_cache *cache;

	down_write(&fs_info->commit_root_sem);

	list_for_each_entry_safe(caching_ctl, next,
				 &fs_info->caching_block_groups, list) {
		cache = caching_ctl->block_group;
		if (block_group_cache_done(cache)) {
			cache->last_byte_to_unpin = (u64)-1;
			list_del_init(&caching_ctl->list);
			put_caching_control(caching_ctl);
		} else {
			cache->last_byte_to_unpin = caching_ctl->progress;
		}
	}

	if (fs_info->pinned_extents == &fs_info->freed_extents[0])
		fs_info->pinned_extents = &fs_info->freed_extents[1];
	else
		fs_info->pinned_extents = &fs_info->freed_extents[0];

	up_write(&fs_info->commit_root_sem);

	update_global_block_rsv(fs_info);
}

/*
 * Returns the free cluster for the given space info and sets empty_cluster to
 * what it should be based on the mount options.
 */
static struct btrfs_free_cluster *
fetch_cluster_info(struct btrfs_fs_info *fs_info,
		   struct btrfs_space_info *space_info, u64 *empty_cluster)
{
	struct btrfs_free_cluster *ret = NULL;

	*empty_cluster = 0;
	if (btrfs_mixed_space_info(space_info))
		return ret;

	if (space_info->flags & BTRFS_BLOCK_GROUP_METADATA) {
		ret = &fs_info->meta_alloc_cluster;
		if (btrfs_test_opt(fs_info, SSD))
			*empty_cluster = SZ_2M;
		else
			*empty_cluster = SZ_64K;
	} else if ((space_info->flags & BTRFS_BLOCK_GROUP_DATA) &&
		   btrfs_test_opt(fs_info, SSD_SPREAD)) {
		*empty_cluster = SZ_2M;
		ret = &fs_info->data_alloc_cluster;
	}

	return ret;
}

static int unpin_extent_range(struct btrfs_fs_info *fs_info,
			      u64 start, u64 end,
			      const bool return_free_space)
{
	struct btrfs_block_group_cache *cache = NULL;
	struct btrfs_space_info *space_info;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	struct btrfs_free_cluster *cluster = NULL;
	u64 len;
	u64 total_unpinned = 0;
	u64 empty_cluster = 0;
	bool readonly;

	while (start <= end) {
		readonly = false;
		if (!cache ||
		    start >= cache->key.objectid + cache->key.offset) {
			if (cache)
				btrfs_put_block_group(cache);
			total_unpinned = 0;
			cache = btrfs_lookup_block_group(fs_info, start);
			BUG_ON(!cache); /* Logic error */

			cluster = fetch_cluster_info(fs_info,
						     cache->space_info,
						     &empty_cluster);
			empty_cluster <<= 1;
		}

		len = cache->key.objectid + cache->key.offset - start;
		len = min(len, end + 1 - start);

		if (start < cache->last_byte_to_unpin) {
			len = min(len, cache->last_byte_to_unpin - start);
			if (return_free_space)
				btrfs_add_free_space(cache, start, len);
		}

		start += len;
		total_unpinned += len;
		space_info = cache->space_info;

		/*
		 * If this space cluster has been marked as fragmented and we've
		 * unpinned enough in this block group to potentially allow a
		 * cluster to be created inside of it go ahead and clear the
		 * fragmented check.
		 */
		if (cluster && cluster->fragmented &&
		    total_unpinned > empty_cluster) {
			spin_lock(&cluster->lock);
			cluster->fragmented = 0;
			spin_unlock(&cluster->lock);
		}

		spin_lock(&space_info->lock);
		spin_lock(&cache->lock);
		cache->pinned -= len;
		update_bytes_pinned(space_info, -len);

		trace_btrfs_space_reservation(fs_info, "pinned",
					      space_info->flags, len, 0);
		space_info->max_extent_size = 0;
		percpu_counter_add_batch(&space_info->total_bytes_pinned,
			    -len, BTRFS_TOTAL_BYTES_PINNED_BATCH);
		if (cache->ro) {
			space_info->bytes_readonly += len;
			readonly = true;
		}
		spin_unlock(&cache->lock);
		if (!readonly && return_free_space &&
		    global_rsv->space_info == space_info) {
			u64 to_add = len;

			spin_lock(&global_rsv->lock);
			if (!global_rsv->full) {
				to_add = min(len, global_rsv->size -
					     global_rsv->reserved);
				global_rsv->reserved += to_add;
				update_bytes_may_use(space_info, to_add);
				if (global_rsv->reserved >= global_rsv->size)
					global_rsv->full = 1;
				trace_btrfs_space_reservation(fs_info,
							      "space_info",
							      space_info->flags,
							      to_add, 1);
				len -= to_add;
			}
			spin_unlock(&global_rsv->lock);
			/* Add to any tickets we may have */
			if (len)
				space_info_add_new_bytes(fs_info, space_info,
							 len);
		}
		spin_unlock(&space_info->lock);
	}

	if (cache)
		btrfs_put_block_group(cache);
	return 0;
}

int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *block_group, *tmp;
	struct list_head *deleted_bgs;
	struct extent_io_tree *unpin;
	u64 start;
	u64 end;
	int ret;

	if (fs_info->pinned_extents == &fs_info->freed_extents[0])
		unpin = &fs_info->freed_extents[1];
	else
		unpin = &fs_info->freed_extents[0];

	while (!trans->aborted) {
		struct extent_state *cached_state = NULL;

		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;
		}

		if (btrfs_test_opt(fs_info, DISCARD))
			ret = btrfs_discard_extent(fs_info, start,
						   end + 1 - start, NULL);

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

	/*
	 * Transaction is finished.  We don't need the lock anymore.  We
	 * do need to clean up the block groups in case of a transaction
	 * abort.
	 */
	deleted_bgs = &trans->transaction->deleted_bgs;
	list_for_each_entry_safe(block_group, tmp, deleted_bgs, bg_list) {
		u64 trimmed = 0;

		ret = -EROFS;
		if (!trans->aborted)
			ret = btrfs_discard_extent(fs_info,
						   block_group->key.objectid,
						   block_group->key.offset,
						   &trimmed);

		list_del_init(&block_group->bg_list);
		btrfs_put_block_group_trimming(block_group);
		btrfs_put_block_group(block_group);

		if (ret) {
			const char *errstr = btrfs_decode_error(ret);
			btrfs_warn(fs_info,
			   "discard failed while removing blockgroup: errno=%d %s",
				   ret, errstr);
		}
	}

	return 0;
}

static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
			       struct btrfs_delayed_ref_node *node, u64 parent,
			       u64 root_objectid, u64 owner_objectid,
			       u64 owner_offset, int refs_to_drop,
			       struct btrfs_delayed_extent_op *extent_op)
{
	struct btrfs_fs_info *info = trans->fs_info;
	struct btrfs_key key;
	struct btrfs_path *path;
	struct btrfs_root *extent_root = info->extent_root;
	struct extent_buffer *leaf;
	struct btrfs_extent_item *ei;
	struct btrfs_extent_inline_ref *iref;
	int ret;
	int is_data;
	int extent_slot = 0;
	int found_extent = 0;
	int num_to_del = 1;
	u32 item_size;
	u64 refs;
	u64 bytenr = node->bytenr;
	u64 num_bytes = node->num_bytes;
	int last_ref = 0;
	bool skinny_metadata = btrfs_fs_incompat(info, SKINNY_METADATA);

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

	path->reada = READA_FORWARD;
	path->leave_spinning = 1;

	is_data = owner_objectid >= BTRFS_FIRST_FREE_OBJECTID;
	BUG_ON(!is_data && refs_to_drop != 1);

	if (is_data)
		skinny_metadata = false;

	ret = lookup_extent_backref(trans, path, &iref, bytenr, num_bytes,
				    parent, root_objectid, owner_objectid,
				    owner_offset);
	if (ret == 0) {
		extent_slot = path->slots[0];
		while (extent_slot >= 0) {
			btrfs_item_key_to_cpu(path->nodes[0], &key,
					      extent_slot);
			if (key.objectid != bytenr)
				break;
			if (key.type == BTRFS_EXTENT_ITEM_KEY &&
			    key.offset == num_bytes) {
				found_extent = 1;
				break;
			}
			if (key.type == BTRFS_METADATA_ITEM_KEY &&
			    key.offset == owner_objectid) {
				found_extent = 1;
				break;
			}
			if (path->slots[0] - extent_slot > 5)
				break;
			extent_slot--;
		}

		if (!found_extent) {
			BUG_ON(iref);
			ret = remove_extent_backref(trans, path, NULL,
						    refs_to_drop,
						    is_data, &last_ref);
			if (ret) {
				btrfs_abort_transaction(trans, ret);
				goto out;
			}
			btrfs_release_path(path);
			path->leave_spinning = 1;

			key.objectid = bytenr;
			key.type = BTRFS_EXTENT_ITEM_KEY;
			key.offset = num_bytes;

			if (!is_data && skinny_metadata) {
				key.type = BTRFS_METADATA_ITEM_KEY;
				key.offset = owner_objectid;
			}

			ret = btrfs_search_slot(trans, extent_root,
						&key, path, -1, 1);
			if (ret > 0 && skinny_metadata && path->slots[0]) {
				/*
				 * Couldn't find our skinny metadata item,
				 * see if we have ye olde extent item.
				 */
				path->slots[0]--;
				btrfs_item_key_to_cpu(path->nodes[0], &key,
						      path->slots[0]);
				if (key.objectid == bytenr &&
				    key.type == BTRFS_EXTENT_ITEM_KEY &&
				    key.offset == num_bytes)
					ret = 0;
			}

			if (ret > 0 && skinny_metadata) {
				skinny_metadata = false;
				key.objectid = bytenr;
				key.type = BTRFS_EXTENT_ITEM_KEY;
				key.offset = num_bytes;
				btrfs_release_path(path);
				ret = btrfs_search_slot(trans, extent_root,
							&key, path, -1, 1);
			}

			if (ret) {
				btrfs_err(info,
					  "umm, got %d back from search, was looking for %llu",
					  ret, bytenr);
				if (ret > 0)
					btrfs_print_leaf(path->nodes[0]);
			}
			if (ret < 0) {
				btrfs_abort_transaction(trans, ret);
				goto out;
			}
			extent_slot = path->slots[0];
		}
	} else if (WARN_ON(ret == -ENOENT)) {
		btrfs_print_leaf(path->nodes[0]);
		btrfs_err(info,
			"unable to find ref byte nr %llu parent %llu root %llu  owner %llu offset %llu",
			bytenr, parent, root_objectid, owner_objectid,
			owner_offset);
		btrfs_abort_transaction(trans, ret);
		goto out;
	} else {
		btrfs_abort_transaction(trans, ret);
		goto out;
	}

	leaf = path->nodes[0];
	item_size = btrfs_item_size_nr(leaf, extent_slot);
	if (unlikely(item_size < sizeof(*ei))) {
		ret = -EINVAL;
		btrfs_print_v0_err(info);
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	ei = btrfs_item_ptr(leaf, extent_slot,
			    struct btrfs_extent_item);
	if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID &&
	    key.type == BTRFS_EXTENT_ITEM_KEY) {
		struct btrfs_tree_block_info *bi;
		BUG_ON(item_size < sizeof(*ei) + sizeof(*bi));
		bi = (struct btrfs_tree_block_info *)(ei + 1);
		WARN_ON(owner_objectid != btrfs_tree_block_level(leaf, bi));
	}

	refs = btrfs_extent_refs(leaf, ei);
	if (refs < refs_to_drop) {
		btrfs_err(info,
			  "trying to drop %d refs but we only have %Lu for bytenr %Lu",
			  refs_to_drop, refs, bytenr);
		ret = -EINVAL;
		btrfs_abort_transaction(trans, ret);
		goto out;
	}
	refs -= refs_to_drop;

	if (refs > 0) {
		if (extent_op)
			__run_delayed_extent_op(extent_op, leaf, ei);
		/*
		 * In the case of inline back ref, reference count will
		 * be updated by remove_extent_backref
		 */
		if (iref) {
			BUG_ON(!found_extent);
		} else {
			btrfs_set_extent_refs(leaf, ei, refs);
			btrfs_mark_buffer_dirty(leaf);
		}
		if (found_extent) {
			ret = remove_extent_backref(trans, path, iref,
						    refs_to_drop, is_data,
						    &last_ref);
			if (ret) {
				btrfs_abort_transaction(trans, ret);
				goto out;
			}
		}
	} else {
		if (found_extent) {
			BUG_ON(is_data && refs_to_drop !=
			       extent_data_ref_count(path, iref));
			if (iref) {
				BUG_ON(path->slots[0] != extent_slot);
			} else {
				BUG_ON(path->slots[0] != extent_slot + 1);
				path->slots[0] = extent_slot;
				num_to_del = 2;
			}
		}

		last_ref = 1;
		ret = btrfs_del_items(trans, extent_root, path, path->slots[0],
				      num_to_del);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
		btrfs_release_path(path);

		if (is_data) {
			ret = btrfs_del_csums(trans, info, bytenr, num_bytes);
			if (ret) {
				btrfs_abort_transaction(trans, ret);
				goto out;
			}
		}

		ret = add_to_free_space_tree(trans, bytenr, num_bytes);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}

		ret = update_block_group(trans, bytenr, num_bytes, 0);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			goto out;
		}
	}
	btrfs_release_path(path);

out:
	btrfs_free_path(path);
	return ret;
}

/*
 * when we free an block, it is possible (and likely) that we free the last
 * delayed ref for that extent as well.  This searches the delayed ref tree for
 * a given extent, and if there are no other delayed refs to be processed, it
 * removes it from the tree.
 */
static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
				      u64 bytenr)
{
	struct btrfs_delayed_ref_head *head;
	struct btrfs_delayed_ref_root *delayed_refs;
	int ret = 0;

	delayed_refs = &trans->transaction->delayed_refs;
	spin_lock(&delayed_refs->lock);
	head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
	if (!head)
		goto out_delayed_unlock;

	spin_lock(&head->lock);
	if (!RB_EMPTY_ROOT(&head->ref_tree.rb_root))
		goto out;

	if (cleanup_extent_op(head) != NULL)
		goto out;

	/*
	 * waiting for the lock here would deadlock.  If someone else has it
	 * locked they are already in the process of dropping it anyway
	 */
	if (!mutex_trylock(&head->mutex))
		goto out;

	btrfs_delete_ref_head(delayed_refs, head);
	head->processing = 0;

	spin_unlock(&head->lock);
	spin_unlock(&delayed_refs->lock);

	BUG_ON(head->extent_op);
	if (head->must_insert_reserved)
		ret = 1;

	btrfs_cleanup_ref_head_accounting(trans->fs_info, delayed_refs, head);
	mutex_unlock(&head->mutex);
	btrfs_put_delayed_ref_head(head);
	return ret;
out:
	spin_unlock(&head->lock);

out_delayed_unlock:
	spin_unlock(&delayed_refs->lock);
	return 0;
}

void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
			   struct btrfs_root *root,
			   struct extent_buffer *buf,
			   u64 parent, int last_ref)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_ref generic_ref = { 0 };
	int pin = 1;
	int ret;

	btrfs_init_generic_ref(&generic_ref, BTRFS_DROP_DELAYED_REF,
			       buf->start, buf->len, parent);
	btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf),
			    root->root_key.objectid);

	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
		int old_ref_mod, new_ref_mod;

		btrfs_ref_tree_mod(fs_info, &generic_ref);
		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL,
						 &old_ref_mod, &new_ref_mod);
		BUG_ON(ret); /* -ENOMEM */
		pin = old_ref_mod >= 0 && new_ref_mod < 0;
	}

	if (last_ref && btrfs_header_generation(buf) == trans->transid) {
		struct btrfs_block_group_cache *cache;

		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
			ret = check_ref_cleanup(trans, buf->start);
			if (!ret)
				goto out;
		}

		pin = 0;
		cache = btrfs_lookup_block_group(fs_info, buf->start);

		if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
			pin_down_extent(cache, buf->start, buf->len, 1);
			btrfs_put_block_group(cache);
			goto out;
		}

		WARN_ON(test_bit(EXTENT_BUFFER_DIRTY, &buf->bflags));

		btrfs_add_free_space(cache, buf->start, buf->len);
		btrfs_free_reserved_bytes(cache, buf->len, 0);
		btrfs_put_block_group(cache);
		trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len);
	}
out:
	if (pin)
		add_pinned_bytes(fs_info, &generic_ref);

	if (last_ref) {
		/*
		 * Deleting the buffer, clear the corrupt flag since it doesn't
		 * matter anymore.
		 */
		clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
	}
}

/* Can return -ENOMEM */
int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	int old_ref_mod, new_ref_mod;
	int ret;

	if (btrfs_is_testing(fs_info))
		return 0;

	/*
	 * tree log blocks never actually go into the extent allocation
	 * tree, just update pinning info and exit early.
	 */
	if ((ref->type == BTRFS_REF_METADATA &&
	     ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID) ||
	    (ref->type == BTRFS_REF_DATA &&
	     ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)) {
		/* unlocks the pinned mutex */
		btrfs_pin_extent(fs_info, ref->bytenr, ref->len, 1);
		old_ref_mod = new_ref_mod = 0;
		ret = 0;
	} else if (ref->type == BTRFS_REF_METADATA) {
		ret = btrfs_add_delayed_tree_ref(trans, ref, NULL,
						 &old_ref_mod, &new_ref_mod);
	} else {
		ret = btrfs_add_delayed_data_ref(trans, ref, 0,
						 &old_ref_mod, &new_ref_mod);
	}

	if (!((ref->type == BTRFS_REF_METADATA &&
	       ref->tree_ref.root == BTRFS_TREE_LOG_OBJECTID) ||
	      (ref->type == BTRFS_REF_DATA &&
	       ref->data_ref.ref_root == BTRFS_TREE_LOG_OBJECTID)))
		btrfs_ref_tree_mod(fs_info, ref);

	if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0)
		add_pinned_bytes(fs_info, ref);

	return ret;
}

/*
 * when we wait for progress in the block group caching, its because
 * our allocation attempt failed at least once.  So, we must sleep
 * and let some progress happen before we try again.
 *
 * This function will sleep at least once waiting for new free space to
 * show up, and then it will check the block group free space numbers
 * for our min num_bytes.  Another option is to have it go ahead
 * and look in the rbtree for a free extent of a given size, but this
 * is a good start.
 *
 * Callers of this must check if cache->cached == BTRFS_CACHE_ERROR before using
 * any of the information in this block group.
 */
static noinline void
wait_block_group_cache_progress(struct btrfs_block_group_cache *cache,
				u64 num_bytes)
{
	struct btrfs_caching_control *caching_ctl;

	caching_ctl = get_caching_control(cache);
	if (!caching_ctl)
		return;

	wait_event(caching_ctl->wait, block_group_cache_done(cache) ||
		   (cache->free_space_ctl->free_space >= num_bytes));

	put_caching_control(caching_ctl);
}

static noinline int
wait_block_group_cache_done(struct btrfs_block_group_cache *cache)
{
	struct btrfs_caching_control *caching_ctl;
	int ret = 0;

	caching_ctl = get_caching_control(cache);
	if (!caching_ctl)
		return (cache->cached == BTRFS_CACHE_ERROR) ? -EIO : 0;

	wait_event(caching_ctl->wait, block_group_cache_done(cache));
	if (cache->cached == BTRFS_CACHE_ERROR)
		ret = -EIO;
	put_caching_control(caching_ctl);
	return ret;
}

enum btrfs_loop_type {
	LOOP_CACHING_NOWAIT = 0,
	LOOP_CACHING_WAIT = 1,
	LOOP_ALLOC_CHUNK = 2,
	LOOP_NO_EMPTY_SIZE = 3,
};

static inline void
btrfs_lock_block_group(struct btrfs_block_group_cache *cache,
		       int delalloc)
{
	if (delalloc)
		down_read(&cache->data_rwsem);
}

static inline void
btrfs_grab_block_group(struct btrfs_block_group_cache *cache,
		       int delalloc)
{
	btrfs_get_block_group(cache);
	if (delalloc)
		down_read(&cache->data_rwsem);
}

static struct btrfs_block_group_cache *
btrfs_lock_cluster(struct btrfs_block_group_cache *block_group,
		   struct btrfs_free_cluster *cluster,
		   int delalloc)
{
	struct btrfs_block_group_cache *used_bg = NULL;

	spin_lock(&cluster->refill_lock);
	while (1) {
		used_bg = cluster->block_group;
		if (!used_bg)
			return NULL;

		if (used_bg == block_group)
			return used_bg;

		btrfs_get_block_group(used_bg);

		if (!delalloc)
			return used_bg;

		if (down_read_trylock(&used_bg->data_rwsem))
			return used_bg;

		spin_unlock(&cluster->refill_lock);

		/* We should only have one-level nested. */
		down_read_nested(&used_bg->data_rwsem, SINGLE_DEPTH_NESTING);

		spin_lock(&cluster->refill_lock);
		if (used_bg == cluster->block_group)
			return used_bg;

		up_read(&used_bg->data_rwsem);
		btrfs_put_block_group(used_bg);
	}
}

static inline void
btrfs_release_block_group(struct btrfs_block_group_cache *cache,
			 int delalloc)
{
	if (delalloc)
		up_read(&cache->data_rwsem);
	btrfs_put_block_group(cache);
}

/*
 * Structure used internally for find_free_extent() function.  Wraps needed
 * parameters.
 */
struct find_free_extent_ctl {
	/* Basic allocation info */
	u64 ram_bytes;
	u64 num_bytes;
	u64 empty_size;
	u64 flags;
	int delalloc;

	/* Where to start the search inside the bg */
	u64 search_start;

	/* For clustered allocation */
	u64 empty_cluster;

	bool have_caching_bg;
	bool orig_have_caching_bg;

	/* RAID index, converted from flags */
	int index;

	/*
	 * Current loop number, check find_free_extent_update_loop() for details
	 */
	int loop;

	/*
	 * Whether we're refilling a cluster, if true we need to re-search
	 * current block group but don't try to refill the cluster again.
	 */
	bool retry_clustered;

	/*
	 * Whether we're updating free space cache, if true we need to re-search
	 * current block group but don't try updating free space cache again.
	 */
	bool retry_unclustered;

	/* If current block group is cached */
	int cached;

	/* Max contiguous hole found */
	u64 max_extent_size;

	/* Total free space from free space cache, not always contiguous */
	u64 total_free_space;

	/* Found result */
	u64 found_offset;
};


/*
 * Helper function for find_free_extent().
 *
 * Return -ENOENT to inform caller that we need fallback to unclustered mode.
 * Return -EAGAIN to inform caller that we need to re-search this block group
 * Return >0 to inform caller that we find nothing
 * Return 0 means we have found a location and set ffe_ctl->found_offset.
 */
static int find_free_extent_clustered(struct btrfs_block_group_cache *bg,
		struct btrfs_free_cluster *last_ptr,
		struct find_free_extent_ctl *ffe_ctl,
		struct btrfs_block_group_cache **cluster_bg_ret)
{
	struct btrfs_block_group_cache *cluster_bg;
	u64 aligned_cluster;
	u64 offset;
	int ret;

	cluster_bg = btrfs_lock_cluster(bg, last_ptr, ffe_ctl->delalloc);
	if (!cluster_bg)
		goto refill_cluster;
	if (cluster_bg != bg && (cluster_bg->ro ||
	    !block_group_bits(cluster_bg, ffe_ctl->flags)))
		goto release_cluster;

	offset = btrfs_alloc_from_cluster(cluster_bg, last_ptr,
			ffe_ctl->num_bytes, cluster_bg->key.objectid,
			&ffe_ctl->max_extent_size);
	if (offset) {
		/* We have a block, we're done */
		spin_unlock(&last_ptr->refill_lock);
		trace_btrfs_reserve_extent_cluster(cluster_bg,
				ffe_ctl->search_start, ffe_ctl->num_bytes);
		*cluster_bg_ret = cluster_bg;
		ffe_ctl->found_offset = offset;
		return 0;
	}
	WARN_ON(last_ptr->block_group != cluster_bg);

release_cluster:
	/*
	 * If we are on LOOP_NO_EMPTY_SIZE, we can't set up a new clusters, so
	 * lets just skip it and let the allocator find whatever block it can
	 * find. If we reach this point, we will have tried the cluster
	 * allocator plenty of times and not have found anything, so we are
	 * likely way too fragmented for the clustering stuff to find anything.
	 *
	 * However, if the cluster is taken from the current block group,
	 * release the cluster first, so that we stand a better chance of
	 * succeeding in the unclustered allocation.
	 */
	if (ffe_ctl->loop >= LOOP_NO_EMPTY_SIZE && cluster_bg != bg) {
		spin_unlock(&last_ptr->refill_lock);
		btrfs_release_block_group(cluster_bg, ffe_ctl->delalloc);
		return -ENOENT;
	}

	/* This cluster didn't work out, free it and start over */
	btrfs_return_cluster_to_free_space(NULL, last_ptr);

	if (cluster_bg != bg)
		btrfs_release_block_group(cluster_bg, ffe_ctl->delalloc);

refill_cluster:
	if (ffe_ctl->loop >= LOOP_NO_EMPTY_SIZE) {
		spin_unlock(&last_ptr->refill_lock);
		return -ENOENT;
	}

	aligned_cluster = max_t(u64,
			ffe_ctl->empty_cluster + ffe_ctl->empty_size,
			bg->full_stripe_len);
	ret = btrfs_find_space_cluster(bg, last_ptr, ffe_ctl->search_start,
			ffe_ctl->num_bytes, aligned_cluster);
	if (ret == 0) {
		/* Now pull our allocation out of this cluster */
		offset = btrfs_alloc_from_cluster(bg, last_ptr,
				ffe_ctl->num_bytes, ffe_ctl->search_start,
				&ffe_ctl->max_extent_size);
		if (offset) {
			/* We found one, proceed */
			spin_unlock(&last_ptr->refill_lock);
			trace_btrfs_reserve_extent_cluster(bg,
					ffe_ctl->search_start,
					ffe_ctl->num_bytes);
			ffe_ctl->found_offset = offset;
			return 0;
		}
	} else if (!ffe_ctl->cached && ffe_ctl->loop > LOOP_CACHING_NOWAIT &&
		   !ffe_ctl->retry_clustered) {
		spin_unlock(&last_ptr->refill_lock);

		ffe_ctl->retry_clustered = true;
		wait_block_group_cache_progress(bg, ffe_ctl->num_bytes +
				ffe_ctl->empty_cluster + ffe_ctl->empty_size);
		return -EAGAIN;
	}
	/*
	 * At this point we either didn't find a cluster or we weren't able to
	 * allocate a block from our cluster.  Free the cluster we've been
	 * trying to use, and go to the next block group.
	 */
	btrfs_return_cluster_to_free_space(NULL, last_ptr);
	spin_unlock(&last_ptr->refill_lock);
	return 1;
}

/*
 * Return >0 to inform caller that we find nothing
 * Return 0 when we found an free extent and set ffe_ctrl->found_offset
 * Return -EAGAIN to inform caller that we need to re-search this block group
 */
static int find_free_extent_unclustered(struct btrfs_block_group_cache *bg,
		struct btrfs_free_cluster *last_ptr,
		struct find_free_extent_ctl *ffe_ctl)
{
	u64 offset;

	/*
	 * We are doing an unclustered allocation, set the fragmented flag so
	 * we don't bother trying to setup a cluster again until we get more
	 * space.
	 */
	if (unlikely(last_ptr)) {
		spin_lock(&last_ptr->lock);
		last_ptr->fragmented = 1;
		spin_unlock(&last_ptr->lock);
	}
	if (ffe_ctl->cached) {
		struct btrfs_free_space_ctl *free_space_ctl;

		free_space_ctl = bg->free_space_ctl;
		spin_lock(&free_space_ctl->tree_lock);
		if (free_space_ctl->free_space <
		    ffe_ctl->num_bytes + ffe_ctl->empty_cluster +
		    ffe_ctl->empty_size) {
			ffe_ctl->total_free_space = max_t(u64,
					ffe_ctl->total_free_space,
					free_space_ctl->free_space);
			spin_unlock(&free_space_ctl->tree_lock);
			return 1;
		}
		spin_unlock(&free_space_ctl->tree_lock);
	}

	offset = btrfs_find_space_for_alloc(bg, ffe_ctl->search_start,
			ffe_ctl->num_bytes, ffe_ctl->empty_size,
			&ffe_ctl->max_extent_size);

	/*
	 * If we didn't find a chunk, and we haven't failed on this block group
	 * before, and this block group is in the middle of caching and we are
	 * ok with waiting, then go ahead and wait for progress to be made, and
	 * set @retry_unclustered to true.
	 *
	 * If @retry_unclustered is true then we've already waited on this
	 * block group once and should move on to the next block group.
	 */
	if (!offset && !ffe_ctl->retry_unclustered && !ffe_ctl->cached &&
	    ffe_ctl->loop > LOOP_CACHING_NOWAIT) {
		wait_block_group_cache_progress(bg, ffe_ctl->num_bytes +
						ffe_ctl->empty_size);
		ffe_ctl->retry_unclustered = true;
		return -EAGAIN;
	} else if (!offset) {
		return 1;
	}
	ffe_ctl->found_offset = offset;
	return 0;
}

/*
 * Return >0 means caller needs to re-search for free extent
 * Return 0 means we have the needed free extent.
 * Return <0 means we failed to locate any free extent.
 */
static int find_free_extent_update_loop(struct btrfs_fs_info *fs_info,
					struct btrfs_free_cluster *last_ptr,
					struct btrfs_key *ins,
					struct find_free_extent_ctl *ffe_ctl,
					int full_search, bool use_cluster)
{
	struct btrfs_root *root = fs_info->extent_root;
	int ret;

	if ((ffe_ctl->loop == LOOP_CACHING_NOWAIT) &&
	    ffe_ctl->have_caching_bg && !ffe_ctl->orig_have_caching_bg)
		ffe_ctl->orig_have_caching_bg = true;

	if (!ins->objectid && ffe_ctl->loop >= LOOP_CACHING_WAIT &&
	    ffe_ctl->have_caching_bg)
		return 1;

	if (!ins->objectid && ++(ffe_ctl->index) < BTRFS_NR_RAID_TYPES)
		return 1;

	if (ins->objectid) {
		if (!use_cluster && last_ptr) {
			spin_lock(&last_ptr->lock);
			last_ptr->window_start = ins->objectid;
			spin_unlock(&last_ptr->lock);
		}
		return 0;
	}

	/*
	 * LOOP_CACHING_NOWAIT, search partially cached block groups, kicking
	 *			caching kthreads as we move along
	 * LOOP_CACHING_WAIT, search everything, and wait if our bg is caching
	 * LOOP_ALLOC_CHUNK, force a chunk allocation and try again
	 * LOOP_NO_EMPTY_SIZE, set empty_size and empty_cluster to 0 and try
	 *		       again
	 */
	if (ffe_ctl->loop < LOOP_NO_EMPTY_SIZE) {
		ffe_ctl->index = 0;
		if (ffe_ctl->loop == LOOP_CACHING_NOWAIT) {
			/*
			 * We want to skip the LOOP_CACHING_WAIT step if we
			 * don't have any uncached bgs and we've already done a
			 * full search through.
			 */
			if (ffe_ctl->orig_have_caching_bg || !full_search)
				ffe_ctl->loop = LOOP_CACHING_WAIT;
			else
				ffe_ctl->loop = LOOP_ALLOC_CHUNK;
		} else {
			ffe_ctl->loop++;
		}

		if (ffe_ctl->loop == LOOP_ALLOC_CHUNK) {
			struct btrfs_trans_handle *trans;
			int exist = 0;

			trans = current->journal_info;
			if (trans)
				exist = 1;
			else
				trans = btrfs_join_transaction(root);

			if (IS_ERR(trans)) {
				ret = PTR_ERR(trans);
				return ret;
			}

			ret = do_chunk_alloc(trans, ffe_ctl->flags,
					     CHUNK_ALLOC_FORCE);

			/*
			 * If we can't allocate a new chunk we've already looped
			 * through at least once, move on to the NO_EMPTY_SIZE
			 * case.
			 */
			if (ret == -ENOSPC)
				ffe_ctl->loop = LOOP_NO_EMPTY_SIZE;

			/* Do not bail out on ENOSPC since we can do more. */
			if (ret < 0 && ret != -ENOSPC)
				btrfs_abort_transaction(trans, ret);
			else
				ret = 0;
			if (!exist)
				btrfs_end_transaction(trans);
			if (ret)
				return ret;
		}

		if (ffe_ctl->loop == LOOP_NO_EMPTY_SIZE) {
			/*
			 * Don't loop again if we already have no empty_size and
			 * no empty_cluster.
			 */
			if (ffe_ctl->empty_size == 0 &&
			    ffe_ctl->empty_cluster == 0)
				return -ENOSPC;
			ffe_ctl->empty_size = 0;
			ffe_ctl->empty_cluster = 0;
		}
		return 1;
	}
	return -ENOSPC;
}

/*
 * walks the btree of allocated extents and find a hole of a given size.
 * The key ins is changed to record the hole:
 * ins->objectid == start position
 * ins->flags = BTRFS_EXTENT_ITEM_KEY
 * ins->offset == the size of the hole.
 * Any available blocks before search_start are skipped.
 *
 * If there is no suitable free space, we will record the max size of
 * the free space extent currently.
 *
 * The overall logic and call chain:
 *
 * find_free_extent()
 * |- Iterate through all block groups
 * |  |- Get a valid block group
 * |  |- Try to do clustered allocation in that block group
 * |  |- Try to do unclustered allocation in that block group
 * |  |- Check if the result is valid
 * |  |  |- If valid, then exit
 * |  |- Jump to next block group
 * |
 * |- Push harder to find free extents
 *    |- If not found, re-iterate all block groups
 */
static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
				u64 ram_bytes, u64 num_bytes, u64 empty_size,
				u64 hint_byte, struct btrfs_key *ins,
				u64 flags, int delalloc)
{
	int ret = 0;
	struct btrfs_free_cluster *last_ptr = NULL;
	struct btrfs_block_group_cache *block_group = NULL;
	struct find_free_extent_ctl ffe_ctl = {0};
	struct btrfs_space_info *space_info;
	bool use_cluster = true;
	bool full_search = false;

	WARN_ON(num_bytes < fs_info->sectorsize);

	ffe_ctl.ram_bytes = ram_bytes;
	ffe_ctl.num_bytes = num_bytes;
	ffe_ctl.empty_size = empty_size;
	ffe_ctl.flags = flags;
	ffe_ctl.search_start = 0;
	ffe_ctl.retry_clustered = false;
	ffe_ctl.retry_unclustered = false;
	ffe_ctl.delalloc = delalloc;
	ffe_ctl.index = btrfs_bg_flags_to_raid_index(flags);
	ffe_ctl.have_caching_bg = false;
	ffe_ctl.orig_have_caching_bg = false;
	ffe_ctl.found_offset = 0;

	ins->type = BTRFS_EXTENT_ITEM_KEY;
	ins->objectid = 0;
	ins->offset = 0;

	trace_find_free_extent(fs_info, num_bytes, empty_size, flags);

	space_info = __find_space_info(fs_info, flags);
	if (!space_info) {
		btrfs_err(fs_info, "No space info for %llu", flags);
		return -ENOSPC;
	}

	/*
	 * If our free space is heavily fragmented we may not be able to make
	 * big contiguous allocations, so instead of doing the expensive search
	 * for free space, simply return ENOSPC with our max_extent_size so we
	 * can go ahead and search for a more manageable chunk.
	 *
	 * If our max_extent_size is large enough for our allocation simply
	 * disable clustering since we will likely not be able to find enough
	 * space to create a cluster and induce latency trying.
	 */
	if (unlikely(space_info->max_extent_size)) {
		spin_lock(&space_info->lock);
		if (space_info->max_extent_size &&
		    num_bytes > space_info->max_extent_size) {
			ins->offset = space_info->max_extent_size;
			spin_unlock(&space_info->lock);
			return -ENOSPC;
		} else if (space_info->max_extent_size) {
			use_cluster = false;
		}
		spin_unlock(&space_info->lock);
	}

	last_ptr = fetch_cluster_info(fs_info, space_info,
				      &ffe_ctl.empty_cluster);
	if (last_ptr) {
		spin_lock(&last_ptr->lock);
		if (last_ptr->block_group)
			hint_byte = last_ptr->window_start;
		if (last_ptr->fragmented) {
			/*
			 * We still set window_start so we can keep track of the
			 * last place we found an allocation to try and save
			 * some time.
			 */
			hint_byte = last_ptr->window_start;
			use_cluster = false;
		}
		spin_unlock(&last_ptr->lock);
	}

	ffe_ctl.search_start = max(ffe_ctl.search_start,
				   first_logical_byte(fs_info, 0));
	ffe_ctl.search_start = max(ffe_ctl.search_start, hint_byte);
	if (ffe_ctl.search_start == hint_byte) {
		block_group = btrfs_lookup_block_group(fs_info,
						       ffe_ctl.search_start);
		/*
		 * we don't want to use the block group if it doesn't match our
		 * allocation bits, or if its not cached.
		 *
		 * However if we are re-searching with an ideal block group
		 * picked out then we don't care that the block group is cached.
		 */
		if (block_group && block_group_bits(block_group, flags) &&
		    block_group->cached != BTRFS_CACHE_NO) {
			down_read(&space_info->groups_sem);
			if (list_empty(&block_group->list) ||
			    block_group->ro) {
				/*
				 * someone is removing this block group,
				 * we can't jump into the have_block_group
				 * target because our list pointers are not
				 * valid
				 */
				btrfs_put_block_group(block_group);
				up_read(&space_info->groups_sem);
			} else {
				ffe_ctl.index = btrfs_bg_flags_to_raid_index(
						block_group->flags);
				btrfs_lock_block_group(block_group, delalloc);
				goto have_block_group;
			}
		} else if (block_group) {
			btrfs_put_block_group(block_group);
		}
	}
search:
	ffe_ctl.have_caching_bg = false;
	if (ffe_ctl.index == btrfs_bg_flags_to_raid_index(flags) ||
	    ffe_ctl.index == 0)
		full_search = true;
	down_read(&space_info->groups_sem);
	list_for_each_entry(block_group,
			    &space_info->block_groups[ffe_ctl.index], list) {
		/* If the block group is read-only, we can skip it entirely. */
		if (unlikely(block_group->ro))
			continue;

		btrfs_grab_block_group(block_group, delalloc);
		ffe_ctl.search_start = block_group->key.objectid;

		/*
		 * this can happen if we end up cycling through all the
		 * raid types, but we want to make sure we only allocate
		 * for the proper type.
		 */
		if (!block_group_bits(block_group, flags)) {
			u64 extra = BTRFS_BLOCK_GROUP_DUP |
				BTRFS_BLOCK_GROUP_RAID1 |
				BTRFS_BLOCK_GROUP_RAID5 |
				BTRFS_BLOCK_GROUP_RAID6 |
				BTRFS_BLOCK_GROUP_RAID10;

			/*
			 * if they asked for extra copies and this block group
			 * doesn't provide them, bail.  This does allow us to
			 * fill raid0 from raid1.
			 */
			if ((flags & extra) && !(block_group->flags & extra))
				goto loop;
		}

have_block_group:
		ffe_ctl.cached = block_group_cache_done(block_group);
		if (unlikely(!ffe_ctl.cached)) {
			ffe_ctl.have_caching_bg = true;
			ret = cache_block_group(block_group, 0);
			BUG_ON(ret < 0);
			ret = 0;
		}

		if (unlikely(block_group->cached == BTRFS_CACHE_ERROR))
			goto loop;

		/*
		 * Ok we want to try and use the cluster allocator, so
		 * lets look there
		 */
		if (last_ptr && use_cluster) {
			struct btrfs_block_group_cache *cluster_bg = NULL;

			ret = find_free_extent_clustered(block_group, last_ptr,
							 &ffe_ctl, &cluster_bg);

			if (ret == 0) {
				if (cluster_bg && cluster_bg != block_group) {
					btrfs_release_block_group(block_group,
								  delalloc);
					block_group = cluster_bg;
				}
				goto checks;
			} else if (ret == -EAGAIN) {
				goto have_block_group;
			} else if (ret > 0) {
				goto loop;
			}
			/* ret == -ENOENT case falls through */
		}

		ret = find_free_extent_unclustered(block_group, last_ptr,
						   &ffe_ctl);
		if (ret == -EAGAIN)
			goto have_block_group;
		else if (ret > 0)
			goto loop;
		/* ret == 0 case falls through */
checks:
		ffe_ctl.search_start = round_up(ffe_ctl.found_offset,
					     fs_info->stripesize);

		/* move on to the next group */
		if (ffe_ctl.search_start + num_bytes >
		    block_group->key.objectid + block_group->key.offset) {
			btrfs_add_free_space(block_group, ffe_ctl.found_offset,
					     num_bytes);
			goto loop;
		}

		if (ffe_ctl.found_offset < ffe_ctl.search_start)
			btrfs_add_free_space(block_group, ffe_ctl.found_offset,
				ffe_ctl.search_start - ffe_ctl.found_offset);

		ret = btrfs_add_reserved_bytes(block_group, ram_bytes,
				num_bytes, delalloc);
		if (ret == -EAGAIN) {
			btrfs_add_free_space(block_group, ffe_ctl.found_offset,
					     num_bytes);
			goto loop;
		}
		btrfs_inc_block_group_reservations(block_group);

		/* we are all good, lets return */
		ins->objectid = ffe_ctl.search_start;
		ins->offset = num_bytes;

		trace_btrfs_reserve_extent(block_group, ffe_ctl.search_start,
					   num_bytes);
		btrfs_release_block_group(block_group, delalloc);
		break;
loop:
		ffe_ctl.retry_clustered = false;
		ffe_ctl.retry_unclustered = false;
		BUG_ON(btrfs_bg_flags_to_raid_index(block_group->flags) !=
		       ffe_ctl.index);
		btrfs_release_block_group(block_group, delalloc);
		cond_resched();
	}
	up_read(&space_info->groups_sem);

	ret = find_free_extent_update_loop(fs_info, last_ptr, ins, &ffe_ctl,
					   full_search, use_cluster);
	if (ret > 0)
		goto search;

	if (ret == -ENOSPC) {
		/*
		 * Use ffe_ctl->total_free_space as fallback if we can't find
		 * any contiguous hole.
		 */
		if (!ffe_ctl.max_extent_size)
			ffe_ctl.max_extent_size = ffe_ctl.total_free_space;
		spin_lock(&space_info->lock);
		space_info->max_extent_size = ffe_ctl.max_extent_size;
		spin_unlock(&space_info->lock);
		ins->offset = ffe_ctl.max_extent_size;
	}
	return ret;
}

#define DUMP_BLOCK_RSV(fs_info, rsv_name)				\
do {									\
	struct btrfs_block_rsv *__rsv = &(fs_info)->rsv_name;		\
	spin_lock(&__rsv->lock);					\
	btrfs_info(fs_info, #rsv_name ": size %llu reserved %llu",	\
		   __rsv->size, __rsv->reserved);			\
	spin_unlock(&__rsv->lock);					\
} while (0)

static void dump_space_info(struct btrfs_fs_info *fs_info,
			    struct btrfs_space_info *info, u64 bytes,
			    int dump_block_groups)
{
	struct btrfs_block_group_cache *cache;
	int index = 0;

	spin_lock(&info->lock);
	btrfs_info(fs_info, "space_info %llu has %llu free, is %sfull",
		   info->flags,
		   info->total_bytes - btrfs_space_info_used(info, true),
		   info->full ? "" : "not ");
	btrfs_info(fs_info,
		"space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu",
		info->total_bytes, info->bytes_used, info->bytes_pinned,
		info->bytes_reserved, info->bytes_may_use,
		info->bytes_readonly);
	spin_unlock(&info->lock);

	DUMP_BLOCK_RSV(fs_info, global_block_rsv);
	DUMP_BLOCK_RSV(fs_info, trans_block_rsv);
	DUMP_BLOCK_RSV(fs_info, chunk_block_rsv);
	DUMP_BLOCK_RSV(fs_info, delayed_block_rsv);
	DUMP_BLOCK_RSV(fs_info, delayed_refs_rsv);

	if (!dump_block_groups)
		return;

	down_read(&info->groups_sem);
again:
	list_for_each_entry(cache, &info->block_groups[index], list) {
		spin_lock(&cache->lock);
		btrfs_info(fs_info,
			"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s",
			cache->key.objectid, cache->key.offset,
			btrfs_block_group_used(&cache->item), cache->pinned,
			cache->reserved, cache->ro ? "[readonly]" : "");
		btrfs_dump_free_space(cache, bytes);
		spin_unlock(&cache->lock);
	}
	if (++index < BTRFS_NR_RAID_TYPES)
		goto again;
	up_read(&info->groups_sem);
}

/*
 * btrfs_reserve_extent - entry point to the extent allocator. Tries to find a
 *			  hole that is at least as big as @num_bytes.
 *
 * @root           -	The root that will contain this extent
 *
 * @ram_bytes      -	The amount of space in ram that @num_bytes take. This
 *			is used for accounting purposes. This value differs
 *			from @num_bytes only in the case of compressed extents.
 *
 * @num_bytes      -	Number of bytes to allocate on-disk.
 *
 * @min_alloc_size -	Indicates the minimum amount of space that the
 *			allocator should try to satisfy. In some cases
 *			@num_bytes may be larger than what is required and if
 *			the filesystem is fragmented then allocation fails.
 *			However, the presence of @min_alloc_size gives a
 *			chance to try and satisfy the smaller allocation.
 *
 * @empty_size     -	A hint that you plan on doing more COW. This is the
 *			size in bytes the allocator should try to find free
 *			next to the block it returns.  This is just a hint and
 *			may be ignored by the allocator.
 *
 * @hint_byte      -	Hint to the allocator to start searching above the byte
 *			address passed. It might be ignored.
 *
 * @ins            -	This key is modified to record the found hole. It will
 *			have the following values:
 *			ins->objectid == start position
 *			ins->flags = BTRFS_EXTENT_ITEM_KEY
 *			ins->offset == the size of the hole.
 *
 * @is_data        -	Boolean flag indicating whether an extent is
 *			allocated for data (true) or metadata (false)
 *
 * @delalloc       -	Boolean flag indicating whether this allocation is for
 *			delalloc or not. If 'true' data_rwsem of block groups
 *			is going to be acquired.
 *
 *
 * Returns 0 when an allocation succeeded or < 0 when an error occurred. In
 * case -ENOSPC is returned then @ins->offset will contain the size of the
 * largest available hole the allocator managed to find.
 */
int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
			 u64 num_bytes, u64 min_alloc_size,
			 u64 empty_size, u64 hint_byte,
			 struct btrfs_key *ins, int is_data, int delalloc)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	bool final_tried = num_bytes == min_alloc_size;
	u64 flags;
	int ret;

	flags = get_alloc_profile_by_root(root, is_data);
again:
	WARN_ON(num_bytes < fs_info->sectorsize);
	ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size,
			       hint_byte, ins, flags, delalloc);
	if (!ret && !is_data) {
		btrfs_dec_block_group_reservations(fs_info, ins->objectid);
	} else if (ret == -ENOSPC) {
		if (!final_tried && ins->offset) {
			num_bytes = min(num_bytes >> 1, ins->offset);
			num_bytes = round_down(num_bytes,
					       fs_info->sectorsize);
			num_bytes = max(num_bytes, min_alloc_size);
			ram_bytes = num_bytes;
			if (num_bytes == min_alloc_size)
				final_tried = true;
			goto again;
		} else if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
			struct btrfs_space_info *sinfo;

			sinfo = __find_space_info(fs_info, flags);
			btrfs_err(fs_info,
				  "allocation failed flags %llu, wanted %llu",
				  flags, num_bytes);
			if (sinfo)
				dump_space_info(fs_info, sinfo, num_bytes, 1);
		}
	}

	return ret;
}

static int __btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
					u64 start, u64 len,
					int pin, int delalloc)
{
	struct btrfs_block_group_cache *cache;
	int ret = 0;

	cache = btrfs_lookup_block_group(fs_info, start);
	if (!cache) {
		btrfs_err(fs_info, "Unable to find block group for %llu",
			  start);
		return -ENOSPC;
	}

	if (pin)
		pin_down_extent(cache, start, len, 1);
	else {
		if (btrfs_test_opt(fs_info, DISCARD))
			ret = btrfs_discard_extent(fs_info, start, len, NULL);
		btrfs_add_free_space(cache, start, len);
		btrfs_free_reserved_bytes(cache, len, delalloc);
		trace_btrfs_reserved_extent_free(fs_info, start, len);
	}

	btrfs_put_block_group(cache);
	return ret;
}

int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
			       u64 start, u64 len, int delalloc)
{
	return __btrfs_free_reserved_extent(fs_info, start, len, 0, delalloc);
}

int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
				       u64 start, u64 len)
{
	return __btrfs_free_reserved_extent(fs_info, start, len, 1, 0);
}

static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
				      u64 parent, u64 root_objectid,
				      u64 flags, u64 owner, u64 offset,
				      struct btrfs_key *ins, int ref_mod)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	int ret;
	struct btrfs_extent_item *extent_item;
	struct btrfs_extent_inline_ref *iref;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	int type;
	u32 size;

	if (parent > 0)
		type = BTRFS_SHARED_DATA_REF_KEY;
	else
		type = BTRFS_EXTENT_DATA_REF_KEY;

	size = sizeof(*extent_item) + btrfs_extent_inline_ref_size(type);

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

	path->leave_spinning = 1;
	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
				      ins, size);
	if (ret) {
		btrfs_free_path(path);
		return ret;
	}

	leaf = path->nodes[0];
	extent_item = btrfs_item_ptr(leaf, path->slots[0],
				     struct btrfs_extent_item);
	btrfs_set_extent_refs(leaf, extent_item, ref_mod);
	btrfs_set_extent_generation(leaf, extent_item, trans->transid);
	btrfs_set_extent_flags(leaf, extent_item,
			       flags | BTRFS_EXTENT_FLAG_DATA);

	iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
	btrfs_set_extent_inline_ref_type(leaf, iref, type);
	if (parent > 0) {
		struct btrfs_shared_data_ref *ref;
		ref = (struct btrfs_shared_data_ref *)(iref + 1);
		btrfs_set_extent_inline_ref_offset(leaf, iref, parent);
		btrfs_set_shared_data_ref_count(leaf, ref, ref_mod);
	} else {
		struct btrfs_extent_data_ref *ref;
		ref = (struct btrfs_extent_data_ref *)(&iref->offset);
		btrfs_set_extent_data_ref_root(leaf, ref, root_objectid);
		btrfs_set_extent_data_ref_objectid(leaf, ref, owner);
		btrfs_set_extent_data_ref_offset(leaf, ref, offset);
		btrfs_set_extent_data_ref_count(leaf, ref, ref_mod);
	}

	btrfs_mark_buffer_dirty(path->nodes[0]);
	btrfs_free_path(path);

	ret = remove_from_free_space_tree(trans, ins->objectid, ins->offset);
	if (ret)
		return ret;

	ret = update_block_group(trans, ins->objectid, ins->offset, 1);
	if (ret) { /* -ENOENT, logic error */
		btrfs_err(fs_info, "update block group failed for %llu %llu",
			ins->objectid, ins->offset);
		BUG();
	}
	trace_btrfs_reserved_extent_alloc(fs_info, ins->objectid, ins->offset);
	return ret;
}

static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
				     struct btrfs_delayed_ref_node *node,
				     struct btrfs_delayed_extent_op *extent_op)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	int ret;
	struct btrfs_extent_item *extent_item;
	struct btrfs_key extent_key;
	struct btrfs_tree_block_info *block_info;
	struct btrfs_extent_inline_ref *iref;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct btrfs_delayed_tree_ref *ref;
	u32 size = sizeof(*extent_item) + sizeof(*iref);
	u64 num_bytes;
	u64 flags = extent_op->flags_to_set;
	bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);

	ref = btrfs_delayed_node_to_tree_ref(node);

	extent_key.objectid = node->bytenr;
	if (skinny_metadata) {
		extent_key.offset = ref->level;
		extent_key.type = BTRFS_METADATA_ITEM_KEY;
		num_bytes = fs_info->nodesize;
	} else {
		extent_key.offset = node->num_bytes;
		extent_key.type = BTRFS_EXTENT_ITEM_KEY;
		size += sizeof(*block_info);
		num_bytes = node->num_bytes;
	}

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

	path->leave_spinning = 1;
	ret = btrfs_insert_empty_item(trans, fs_info->extent_root, path,
				      &extent_key, size);
	if (ret) {
		btrfs_free_path(path);
		return ret;
	}

	leaf = path->nodes[0];
	extent_item = btrfs_item_ptr(leaf, path->slots[0],
				     struct btrfs_extent_item);
	btrfs_set_extent_refs(leaf, extent_item, 1);
	btrfs_set_extent_generation(leaf, extent_item, trans->transid);
	btrfs_set_extent_flags(leaf, extent_item,
			       flags | BTRFS_EXTENT_FLAG_TREE_BLOCK);

	if (skinny_metadata) {
		iref = (struct btrfs_extent_inline_ref *)(extent_item + 1);
	} else {
		block_info = (struct btrfs_tree_block_info *)(extent_item + 1);
		btrfs_set_tree_block_key(leaf, block_info, &extent_op->key);
		btrfs_set_tree_block_level(leaf, block_info, ref->level);
		iref = (struct btrfs_extent_inline_ref *)(block_info + 1);
	}

	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY) {
		BUG_ON(!(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
		btrfs_set_extent_inline_ref_type(leaf, iref,
						 BTRFS_SHARED_BLOCK_REF_KEY);
		btrfs_set_extent_inline_ref_offset(leaf, iref, ref->parent);
	} else {
		btrfs_set_extent_inline_ref_type(leaf, iref,
						 BTRFS_TREE_BLOCK_REF_KEY);
		btrfs_set_extent_inline_ref_offset(leaf, iref, ref->root);
	}

	btrfs_mark_buffer_dirty(leaf);
	btrfs_free_path(path);

	ret = remove_from_free_space_tree(trans, extent_key.objectid,
					  num_bytes);
	if (ret)
		return ret;

	ret = update_block_group(trans, extent_key.objectid,
				 fs_info->nodesize, 1);
	if (ret) { /* -ENOENT, logic error */
		btrfs_err(fs_info, "update block group failed for %llu %llu",
			extent_key.objectid, extent_key.offset);
		BUG();
	}

	trace_btrfs_reserved_extent_alloc(fs_info, extent_key.objectid,
					  fs_info->nodesize);
	return ret;
}

int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
				     struct btrfs_root *root, u64 owner,
				     u64 offset, u64 ram_bytes,
				     struct btrfs_key *ins)
{
	struct btrfs_ref generic_ref = { 0 };
	int ret;

	BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);

	btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT,
			       ins->objectid, ins->offset, 0);
	btrfs_init_data_ref(&generic_ref, root->root_key.objectid, owner, offset);
	btrfs_ref_tree_mod(root->fs_info, &generic_ref);
	ret = btrfs_add_delayed_data_ref(trans, &generic_ref,
					 ram_bytes, NULL, NULL);
	return ret;
}

/*
 * this is used by the tree logging recovery code.  It records that
 * an extent has been allocated and makes sure to clear the free
 * space cache bits as well
 */
int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
				   u64 root_objectid, u64 owner, u64 offset,
				   struct btrfs_key *ins)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	int ret;
	struct btrfs_block_group_cache *block_group;
	struct btrfs_space_info *space_info;

	/*
	 * Mixed block groups will exclude before processing the log so we only
	 * need to do the exclude dance if this fs isn't mixed.
	 */
	if (!btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
		ret = __exclude_logged_extent(fs_info, ins->objectid,
					      ins->offset);
		if (ret)
			return ret;
	}

	block_group = btrfs_lookup_block_group(fs_info, ins->objectid);
	if (!block_group)
		return -EINVAL;

	space_info = block_group->space_info;
	spin_lock(&space_info->lock);
	spin_lock(&block_group->lock);
	space_info->bytes_reserved += ins->offset;
	block_group->reserved += ins->offset;
	spin_unlock(&block_group->lock);
	spin_unlock(&space_info->lock);

	ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner,
					 offset, ins, 1);
	btrfs_put_block_group(block_group);
	return ret;
}

static struct extent_buffer *
btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
		      u64 bytenr, int level, u64 owner)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct extent_buffer *buf;

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

	/*
	 * Extra safety check in case the extent tree is corrupted and extent
	 * allocator chooses to use a tree block which is already used and
	 * locked.
	 */
	if (buf->lock_owner == current->pid) {
		btrfs_err_rl(fs_info,
"tree block %llu owner %llu already locked by pid=%d, extent tree corruption detected",
			buf->start, btrfs_header_owner(buf), current->pid);
		free_extent_buffer(buf);
		return ERR_PTR(-EUCLEAN);
	}

	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
	btrfs_tree_lock(buf);
	btrfs_clean_tree_block(buf);
	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);

	btrfs_set_lock_blocking_write(buf);
	set_extent_buffer_uptodate(buf);

	memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header));
	btrfs_set_header_level(buf, level);
	btrfs_set_header_bytenr(buf, buf->start);
	btrfs_set_header_generation(buf, trans->transid);
	btrfs_set_header_backref_rev(buf, BTRFS_MIXED_BACKREF_REV);
	btrfs_set_header_owner(buf, owner);
	write_extent_buffer_fsid(buf, fs_info->fs_devices->metadata_uuid);
	write_extent_buffer_chunk_tree_uuid(buf, fs_info->chunk_tree_uuid);
	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
		buf->log_index = root->log_transid % 2;
		/*
		 * we allow two log transactions at a time, use different
		 * EXTENT bit to differentiate dirty pages.
		 */
		if (buf->log_index == 0)
			set_extent_dirty(&root->dirty_log_pages, buf->start,
					buf->start + buf->len - 1, GFP_NOFS);
		else
			set_extent_new(&root->dirty_log_pages, buf->start,
					buf->start + buf->len - 1);
	} else {
		buf->log_index = -1;
		set_extent_dirty(&trans->transaction->dirty_pages, buf->start,
			 buf->start + buf->len - 1, GFP_NOFS);
	}
	trans->dirty = true;
	/* this returns a buffer locked for blocking */
	return buf;
}

static struct btrfs_block_rsv *
use_block_rsv(struct btrfs_trans_handle *trans,
	      struct btrfs_root *root, u32 blocksize)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_block_rsv *block_rsv;
	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
	int ret;
	bool global_updated = false;

	block_rsv = get_block_rsv(trans, root);

	if (unlikely(block_rsv->size == 0))
		goto try_reserve;
again:
	ret = block_rsv_use_bytes(block_rsv, blocksize);
	if (!ret)
		return block_rsv;

	if (block_rsv->failfast)
		return ERR_PTR(ret);

	if (block_rsv->type == BTRFS_BLOCK_RSV_GLOBAL && !global_updated) {
		global_updated = true;
		update_global_block_rsv(fs_info);
		goto again;
	}

	/*
	 * The global reserve still exists to save us from ourselves, so don't
	 * warn_on if we are short on our delayed refs reserve.
	 */
	if (block_rsv->type != BTRFS_BLOCK_RSV_DELREFS &&
	    btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
		static DEFINE_RATELIMIT_STATE(_rs,
				DEFAULT_RATELIMIT_INTERVAL * 10,
				/*DEFAULT_RATELIMIT_BURST*/ 1);
		if (__ratelimit(&_rs))
			WARN(1, KERN_DEBUG
				"BTRFS: block rsv returned %d\n", ret);
	}
try_reserve:
	ret = reserve_metadata_bytes(root, block_rsv, blocksize,
				     BTRFS_RESERVE_NO_FLUSH);
	if (!ret)
		return block_rsv;
	/*
	 * If we couldn't reserve metadata bytes try and use some from
	 * the global reserve if its space type is the same as the global
	 * reservation.
	 */
	if (block_rsv->type != BTRFS_BLOCK_RSV_GLOBAL &&
	    block_rsv->space_info == global_rsv->space_info) {
		ret = block_rsv_use_bytes(global_rsv, blocksize);
		if (!ret)
			return global_rsv;
	}
	return ERR_PTR(ret);
}

static void unuse_block_rsv(struct btrfs_fs_info *fs_info,
			    struct btrfs_block_rsv *block_rsv, u32 blocksize)
{
	block_rsv_add_bytes(block_rsv, blocksize, false);
	block_rsv_release_bytes(fs_info, block_rsv, NULL, 0, NULL);
}

/*
 * finds a free extent and does all the dirty work required for allocation
 * returns the tree buffer or an ERR_PTR on error.
 */
struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
					     struct btrfs_root *root,
					     u64 parent, u64 root_objectid,
					     const struct btrfs_disk_key *key,
					     int level, u64 hint,
					     u64 empty_size)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_key ins;
	struct btrfs_block_rsv *block_rsv;
	struct extent_buffer *buf;
	struct btrfs_delayed_extent_op *extent_op;
	struct btrfs_ref generic_ref = { 0 };
	u64 flags = 0;
	int ret;
	u32 blocksize = fs_info->nodesize;
	bool skinny_metadata = btrfs_fs_incompat(fs_info, SKINNY_METADATA);

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
	if (btrfs_is_testing(fs_info)) {
		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
					    level, root_objectid);
		if (!IS_ERR(buf))
			root->alloc_bytenr += blocksize;
		return buf;
	}
#endif

	block_rsv = use_block_rsv(trans, root, blocksize);
	if (IS_ERR(block_rsv))
		return ERR_CAST(block_rsv);

	ret = btrfs_reserve_extent(root, blocksize, blocksize, blocksize,
				   empty_size, hint, &ins, 0, 0);
	if (ret)
		goto out_unuse;

	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level,
				    root_objectid);
	if (IS_ERR(buf)) {
		ret = PTR_ERR(buf);
		goto out_free_reserved;
	}

	if (root_objectid == BTRFS_TREE_RELOC_OBJECTID) {
		if (parent == 0)
			parent = ins.objectid;
		flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
	} else
		BUG_ON(parent > 0);

	if (root_objectid != BTRFS_TREE_LOG_OBJECTID) {
		extent_op = btrfs_alloc_delayed_extent_op();
		if (!extent_op) {
			ret = -ENOMEM;
			goto out_free_buf;
		}
		if (key)
			memcpy(&extent_op->key, key, sizeof(extent_op->key));
		else
			memset(&extent_op->key, 0, sizeof(extent_op->key));
		extent_op->flags_to_set = flags;
		extent_op->update_key = skinny_metadata ? false : true;
		extent_op->update_flags = true;
		extent_op->is_data = false;
		extent_op->level = level;

		btrfs_init_generic_ref(&generic_ref, BTRFS_ADD_DELAYED_EXTENT,
				       ins.objectid, ins.offset, parent);
		generic_ref.real_root = root->root_key.objectid;
		btrfs_init_tree_ref(&generic_ref, level, root_objectid);
		btrfs_ref_tree_mod(fs_info, &generic_ref);
		ret = btrfs_add_delayed_tree_ref(trans, &generic_ref,
						 extent_op, NULL, NULL);
		if (ret)
			goto out_free_delayed;
	}
	return buf;

out_free_delayed:
	btrfs_free_delayed_extent_op(extent_op);
out_free_buf:
	free_extent_buffer(buf);
out_free_reserved:
	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 0);
out_unuse:
	unuse_block_rsv(fs_info, block_rsv, blocksize);
	return ERR_PTR(ret);
}

struct walk_control {
	u64 refs[BTRFS_MAX_LEVEL];
	u64 flags[BTRFS_MAX_LEVEL];
	struct btrfs_key update_progress;
	struct btrfs_key drop_progress;
	int drop_level;
	int stage;
	int level;
	int shared_level;
	int update_ref;
	int keep_locks;
	int reada_slot;
	int reada_count;
	int restarted;
};

#define DROP_REFERENCE	1
#define UPDATE_BACKREF	2

static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
				     struct btrfs_root *root,
				     struct walk_control *wc,
				     struct btrfs_path *path)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 bytenr;
	u64 generation;
	u64 refs;
	u64 flags;
	u32 nritems;
	struct btrfs_key key;
	struct extent_buffer *eb;
	int ret;
	int slot;
	int nread = 0;

	if (path->slots[wc->level] < wc->reada_slot) {
		wc->reada_count = wc->reada_count * 2 / 3;
		wc->reada_count = max(wc->reada_count, 2);
	} else {
		wc->reada_count = wc->reada_count * 3 / 2;
		wc->reada_count = min_t(int, wc->reada_count,
					BTRFS_NODEPTRS_PER_BLOCK(fs_info));
	}

	eb = path->nodes[wc->level];
	nritems = btrfs_header_nritems(eb);

	for (slot = path->slots[wc->level]; slot < nritems; slot++) {
		if (nread >= wc->reada_count)
			break;

		cond_resched();
		bytenr = btrfs_node_blockptr(eb, slot);
		generation = btrfs_node_ptr_generation(eb, slot);

		if (slot == path->slots[wc->level])
			goto reada;

		if (wc->stage == UPDATE_BACKREF &&
		    generation <= root->root_key.offset)
			continue;

		/* We don't lock the tree block, it's OK to be racy here */
		ret = btrfs_lookup_extent_info(trans, fs_info, bytenr,
					       wc->level - 1, 1, &refs,
					       &flags);
		/* We don't care about errors in readahead. */
		if (ret < 0)
			continue;
		BUG_ON(refs == 0);

		if (wc->stage == DROP_REFERENCE) {
			if (refs == 1)
				goto reada;

			if (wc->level == 1 &&
			    (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))
				continue;
			if (!wc->update_ref ||
			    generation <= root->root_key.offset)
				continue;
			btrfs_node_key_to_cpu(eb, &key, slot);
			ret = btrfs_comp_cpu_keys(&key,
						  &wc->update_progress);
			if (ret < 0)
				continue;
		} else {
			if (wc->level == 1 &&
			    (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))
				continue;
		}
reada:
		readahead_tree_block(fs_info, bytenr);
		nread++;
	}
	wc->reada_slot = slot;
}

/*
 * helper to process tree block while walking down the tree.
 *
 * when wc->stage == UPDATE_BACKREF, this function updates
 * back refs for pointers in the block.
 *
 * NOTE: return value 1 means we should stop walking down.
 */
static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
				   struct btrfs_root *root,
				   struct btrfs_path *path,
				   struct walk_control *wc, int lookup_info)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	int level = wc->level;
	struct extent_buffer *eb = path->nodes[level];
	u64 flag = BTRFS_BLOCK_FLAG_FULL_BACKREF;
	int ret;

	if (wc->stage == UPDATE_BACKREF &&
	    btrfs_header_owner(eb) != root->root_key.objectid)
		return 1;

	/*
	 * when reference count of tree block is 1, it won't increase
	 * again. once full backref flag is set, we never clear it.
	 */
	if (lookup_info &&
	    ((wc->stage == DROP_REFERENCE && wc->refs[level] != 1) ||
	     (wc->stage == UPDATE_BACKREF && !(wc->flags[level] & flag)))) {
		BUG_ON(!path->locks[level]);
		ret = btrfs_lookup_extent_info(trans, fs_info,
					       eb->start, level, 1,
					       &wc->refs[level],
					       &wc->flags[level]);
		BUG_ON(ret == -ENOMEM);
		if (ret)
			return ret;
		BUG_ON(wc->refs[level] == 0);
	}

	if (wc->stage == DROP_REFERENCE) {
		if (wc->refs[level] > 1)
			return 1;

		if (path->locks[level] && !wc->keep_locks) {
			btrfs_tree_unlock_rw(eb, path->locks[level]);
			path->locks[level] = 0;
		}
		return 0;
	}

	/* wc->stage == UPDATE_BACKREF */
	if (!(wc->flags[level] & flag)) {
		BUG_ON(!path->locks[level]);
		ret = btrfs_inc_ref(trans, root, eb, 1);
		BUG_ON(ret); /* -ENOMEM */
		ret = btrfs_dec_ref(trans, root, eb, 0);
		BUG_ON(ret); /* -ENOMEM */
		ret = btrfs_set_disk_extent_flags(trans, eb->start,
						  eb->len, flag,
						  btrfs_header_level(eb), 0);
		BUG_ON(ret); /* -ENOMEM */
		wc->flags[level] |= flag;
	}

	/*
	 * the block is shared by multiple trees, so it's not good to
	 * keep the tree lock
	 */
	if (path->locks[level] && level > 0) {
		btrfs_tree_unlock_rw(eb, path->locks[level]);
		path->locks[level] = 0;
	}
	return 0;
}

/*
 * This is used to verify a ref exists for this root to deal with a bug where we
 * would have a drop_progress key that hadn't been updated properly.
 */
static int check_ref_exists(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root, u64 bytenr, u64 parent,
			    int level)
{
	struct btrfs_path *path;
	struct btrfs_extent_inline_ref *iref;
	int ret;

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

	ret = lookup_extent_backref(trans, path, &iref, bytenr,
				    root->fs_info->nodesize, parent,
				    root->root_key.objectid, level, 0);
	btrfs_free_path(path);
	if (ret == -ENOENT)
		return 0;
	if (ret < 0)
		return ret;
	return 1;
}

/*
 * helper to process tree block pointer.
 *
 * when wc->stage == DROP_REFERENCE, this function checks
 * reference count of the block pointed to. if the block
 * is shared and we need update back refs for the subtree
 * rooted at the block, this function changes wc->stage to
 * UPDATE_BACKREF. if the block is shared and there is no
 * need to update back, this function drops the reference
 * to the block.
 *
 * NOTE: return value 1 means we should stop walking down.
 */
static noinline int do_walk_down(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root,
				 struct btrfs_path *path,
				 struct walk_control *wc, int *lookup_info)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 bytenr;
	u64 generation;
	u64 parent;
	struct btrfs_key key;
	struct btrfs_key first_key;
	struct btrfs_ref ref = { 0 };
	struct extent_buffer *next;
	int level = wc->level;
	int reada = 0;
	int ret = 0;
	bool need_account = false;

	generation = btrfs_node_ptr_generation(path->nodes[level],
					       path->slots[level]);
	/*
	 * if the lower level block was created before the snapshot
	 * was created, we know there is no need to update back refs
	 * for the subtree
	 */
	if (wc->stage == UPDATE_BACKREF &&
	    generation <= root->root_key.offset) {
		*lookup_info = 1;
		return 1;
	}

	bytenr = btrfs_node_blockptr(path->nodes[level], path->slots[level]);
	btrfs_node_key_to_cpu(path->nodes[level], &first_key,
			      path->slots[level]);

	next = find_extent_buffer(fs_info, bytenr);
	if (!next) {
		next = btrfs_find_create_tree_block(fs_info, bytenr);
		if (IS_ERR(next))
			return PTR_ERR(next);

		btrfs_set_buffer_lockdep_class(root->root_key.objectid, next,
					       level - 1);
		reada = 1;
	}
	btrfs_tree_lock(next);
	btrfs_set_lock_blocking_write(next);

	ret = btrfs_lookup_extent_info(trans, fs_info, bytenr, level - 1, 1,
				       &wc->refs[level - 1],
				       &wc->flags[level - 1]);
	if (ret < 0)
		goto out_unlock;

	if (unlikely(wc->refs[level - 1] == 0)) {
		btrfs_err(fs_info, "Missing references.");
		ret = -EIO;
		goto out_unlock;
	}
	*lookup_info = 0;

	if (wc->stage == DROP_REFERENCE) {
		if (wc->refs[level - 1] > 1) {
			need_account = true;
			if (level == 1 &&
			    (wc->flags[0] & BTRFS_BLOCK_FLAG_FULL_BACKREF))
				goto skip;

			if (!wc->update_ref ||
			    generation <= root->root_key.offset)
				goto skip;

			btrfs_node_key_to_cpu(path->nodes[level], &key,
					      path->slots[level]);
			ret = btrfs_comp_cpu_keys(&key, &wc->update_progress);
			if (ret < 0)
				goto skip;

			wc->stage = UPDATE_BACKREF;
			wc->shared_level = level - 1;
		}
	} else {
		if (level == 1 &&
		    (wc->flags[0] & BTRFS_BLOCK_FLAG_FULL_BACKREF))
			goto skip;
	}

	if (!btrfs_buffer_uptodate(next, generation, 0)) {
		btrfs_tree_unlock(next);
		free_extent_buffer(next);
		next = NULL;
		*lookup_info = 1;
	}

	if (!next) {
		if (reada && level == 1)
			reada_walk_down(trans, root, wc, path);
		next = read_tree_block(fs_info, bytenr, generation, level - 1,
				       &first_key);
		if (IS_ERR(next)) {
			return PTR_ERR(next);
		} else if (!extent_buffer_uptodate(next)) {
			free_extent_buffer(next);
			return -EIO;
		}
		btrfs_tree_lock(next);
		btrfs_set_lock_blocking_write(next);
	}

	level--;
	ASSERT(level == btrfs_header_level(next));
	if (level != btrfs_header_level(next)) {
		btrfs_err(root->fs_info, "mismatched level");
		ret = -EIO;
		goto out_unlock;
	}
	path->nodes[level] = next;
	path->slots[level] = 0;
	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
	wc->level = level;
	if (wc->level == 1)
		wc->reada_slot = 0;
	return 0;
skip:
	wc->refs[level - 1] = 0;
	wc->flags[level - 1] = 0;
	if (wc->stage == DROP_REFERENCE) {
		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
			parent = path->nodes[level]->start;
		} else {
			ASSERT(root->root_key.objectid ==
			       btrfs_header_owner(path->nodes[level]));
			if (root->root_key.objectid !=
			    btrfs_header_owner(path->nodes[level])) {
				btrfs_err(root->fs_info,
						"mismatched block owner");
				ret = -EIO;
				goto out_unlock;
			}
			parent = 0;
		}

		/*
		 * If we had a drop_progress we need to verify the refs are set
		 * as expected.  If we find our ref then we know that from here
		 * on out everything should be correct, and we can clear the
		 * ->restarted flag.
		 */
		if (wc->restarted) {
			ret = check_ref_exists(trans, root, bytenr, parent,
					       level - 1);
			if (ret < 0)
				goto out_unlock;
			if (ret == 0)
				goto no_delete;
			ret = 0;
			wc->restarted = 0;
		}

		/*
		 * Reloc tree doesn't contribute to qgroup numbers, and we have
		 * already accounted them at merge time (replace_path),
		 * thus we could skip expensive subtree trace here.
		 */
		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
		    need_account) {
			ret = btrfs_qgroup_trace_subtree(trans, next,
							 generation, level - 1);
			if (ret) {
				btrfs_err_rl(fs_info,
					     "Error %d accounting shared subtree. Quota is out of sync, rescan required.",
					     ret);
			}
		}

		/*
		 * We need to update the next key in our walk control so we can
		 * update the drop_progress key accordingly.  We don't care if
		 * find_next_key doesn't find a key because that means we're at
		 * the end and are going to clean up now.
		 */
		wc->drop_level = level;
		find_next_key(path, level, &wc->drop_progress);

		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
				       fs_info->nodesize, parent);
		btrfs_init_tree_ref(&ref, level - 1, root->root_key.objectid);
		ret = btrfs_free_extent(trans, &ref);
		if (ret)
			goto out_unlock;
	}
no_delete:
	*lookup_info = 1;
	ret = 1;

out_unlock:
	btrfs_tree_unlock(next);
	free_extent_buffer(next);

	return ret;
}

/*
 * helper to process tree block while walking up the tree.
 *
 * when wc->stage == DROP_REFERENCE, this function drops
 * reference count on the block.
 *
 * when wc->stage == UPDATE_BACKREF, this function changes
 * wc->stage back to DROP_REFERENCE if we changed wc->stage
 * to UPDATE_BACKREF previously while processing the block.
 *
 * NOTE: return value 1 means we should stop walking up.
 */
static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root,
				 struct btrfs_path *path,
				 struct walk_control *wc)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	int ret;
	int level = wc->level;
	struct extent_buffer *eb = path->nodes[level];
	u64 parent = 0;

	if (wc->stage == UPDATE_BACKREF) {
		BUG_ON(wc->shared_level < level);
		if (level < wc->shared_level)
			goto out;

		ret = find_next_key(path, level + 1, &wc->update_progress);
		if (ret > 0)
			wc->update_ref = 0;

		wc->stage = DROP_REFERENCE;
		wc->shared_level = -1;
		path->slots[level] = 0;

		/*
		 * check reference count again if the block isn't locked.
		 * we should start walking down the tree again if reference
		 * count is one.
		 */
		if (!path->locks[level]) {
			BUG_ON(level == 0);
			btrfs_tree_lock(eb);
			btrfs_set_lock_blocking_write(eb);
			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;

			ret = btrfs_lookup_extent_info(trans, fs_info,
						       eb->start, level, 1,
						       &wc->refs[level],
						       &wc->flags[level]);
			if (ret < 0) {
				btrfs_tree_unlock_rw(eb, path->locks[level]);
				path->locks[level] = 0;
				return ret;
			}
			BUG_ON(wc->refs[level] == 0);
			if (wc->refs[level] == 1) {
				btrfs_tree_unlock_rw(eb, path->locks[level]);
				path->locks[level] = 0;
				return 1;
			}
		}
	}

	/* wc->stage == DROP_REFERENCE */
	BUG_ON(wc->refs[level] > 1 && !path->locks[level]);

	if (wc->refs[level] == 1) {
		if (level == 0) {
			if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
				ret = btrfs_dec_ref(trans, root, eb, 1);
			else
				ret = btrfs_dec_ref(trans, root, eb, 0);
			BUG_ON(ret); /* -ENOMEM */
			if (is_fstree(root->root_key.objectid)) {
				ret = btrfs_qgroup_trace_leaf_items(trans, eb);
				if (ret) {
					btrfs_err_rl(fs_info,
	"error %d accounting leaf items, quota is out of sync, rescan required",
					     ret);
				}
			}
		}
		/* make block locked assertion in btrfs_clean_tree_block happy */
		if (!path->locks[level] &&
		    btrfs_header_generation(eb) == trans->transid) {
			btrfs_tree_lock(eb);
			btrfs_set_lock_blocking_write(eb);
			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
		}
		btrfs_clean_tree_block(eb);
	}

	if (eb == root->node) {
		if (wc->flags[level] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
			parent = eb->start;
		else if (root->root_key.objectid != btrfs_header_owner(eb))
			goto owner_mismatch;
	} else {
		if (wc->flags[level + 1] & BTRFS_BLOCK_FLAG_FULL_BACKREF)
			parent = path->nodes[level + 1]->start;
		else if (root->root_key.objectid !=
			 btrfs_header_owner(path->nodes[level + 1]))
			goto owner_mismatch;
	}

	btrfs_free_tree_block(trans, root, eb, parent, wc->refs[level] == 1);
out:
	wc->refs[level] = 0;
	wc->flags[level] = 0;
	return 0;

owner_mismatch:
	btrfs_err_rl(fs_info, "unexpected tree owner, have %llu expect %llu",
		     btrfs_header_owner(eb), root->root_key.objectid);
	return -EUCLEAN;
}

static noinline int walk_down_tree(struct btrfs_trans_handle *trans,
				   struct btrfs_root *root,
				   struct btrfs_path *path,
				   struct walk_control *wc)
{
	int level = wc->level;
	int lookup_info = 1;
	int ret;

	while (level >= 0) {
		ret = walk_down_proc(trans, root, path, wc, lookup_info);
		if (ret > 0)
			break;

		if (level == 0)
			break;

		if (path->slots[level] >=
		    btrfs_header_nritems(path->nodes[level]))
			break;

		ret = do_walk_down(trans, root, path, wc, &lookup_info);
		if (ret > 0) {
			path->slots[level]++;
			continue;
		} else if (ret < 0)
			return ret;
		level = wc->level;
	}
	return 0;
}

static noinline int walk_up_tree(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root,
				 struct btrfs_path *path,
				 struct walk_control *wc, int max_level)
{
	int level = wc->level;
	int ret;

	path->slots[level] = btrfs_header_nritems(path->nodes[level]);
	while (level < max_level && path->nodes[level]) {
		wc->level = level;
		if (path->slots[level] + 1 <
		    btrfs_header_nritems(path->nodes[level])) {
			path->slots[level]++;
			return 0;
		} else {
			ret = walk_up_proc(trans, root, path, wc);
			if (ret > 0)
				return 0;
			if (ret < 0)
				return ret;

			if (path->locks[level]) {
				btrfs_tree_unlock_rw(path->nodes[level],
						     path->locks[level]);
				path->locks[level] = 0;
			}
			free_extent_buffer(path->nodes[level]);
			path->nodes[level] = NULL;
			level++;
		}
	}
	return 1;
}

/*
 * drop a subvolume tree.
 *
 * this function traverses the tree freeing any blocks that only
 * referenced by the tree.
 *
 * when a shared tree block is found. this function decreases its
 * reference count by one. if update_ref is true, this function
 * also make sure backrefs for the shared block and all lower level
 * blocks are properly updated.
 *
 * If called with for_reloc == 0, may exit early with -EAGAIN
 */
int btrfs_drop_snapshot(struct btrfs_root *root,
			 struct btrfs_block_rsv *block_rsv, int update_ref,
			 int for_reloc)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct btrfs_trans_handle *trans;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_root_item *root_item = &root->root_item;
	struct walk_control *wc;
	struct btrfs_key key;
	int err = 0;
	int ret;
	int level;
	bool root_dropped = false;

	btrfs_debug(fs_info, "Drop subvolume %llu", root->root_key.objectid);

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

	wc = kzalloc(sizeof(*wc), GFP_NOFS);
	if (!wc) {
		btrfs_free_path(path);
		err = -ENOMEM;
		goto out;
	}

	trans = btrfs_start_transaction(tree_root, 0);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_free;
	}

	err = btrfs_run_delayed_items(trans);
	if (err)
		goto out_end_trans;

	if (block_rsv)
		trans->block_rsv = block_rsv;

	/*
	 * This will help us catch people modifying the fs tree while we're
	 * dropping it.  It is unsafe to mess with the fs tree while it's being
	 * dropped as we unlock the root node and parent nodes as we walk down
	 * the tree, assuming nothing will change.  If something does change
	 * then we'll have stale information and drop references to blocks we've
	 * already dropped.
	 */
	set_bit(BTRFS_ROOT_DELETING, &root->state);
	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
		level = btrfs_header_level(root->node);
		path->nodes[level] = btrfs_lock_root_node(root);
		btrfs_set_lock_blocking_write(path->nodes[level]);
		path->slots[level] = 0;
		path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
		memset(&wc->update_progress, 0,
		       sizeof(wc->update_progress));
	} else {
		btrfs_disk_key_to_cpu(&key, &root_item->drop_progress);
		memcpy(&wc->update_progress, &key,
		       sizeof(wc->update_progress));

		level = root_item->drop_level;
		BUG_ON(level == 0);
		path->lowest_level = level;
		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
		path->lowest_level = 0;
		if (ret < 0) {
			err = ret;
			goto out_end_trans;
		}
		WARN_ON(ret > 0);

		/*
		 * unlock our path, this is safe because only this
		 * function is allowed to delete this snapshot
		 */
		btrfs_unlock_up_safe(path, 0);

		level = btrfs_header_level(root->node);
		while (1) {
			btrfs_tree_lock(path->nodes[level]);
			btrfs_set_lock_blocking_write(path->nodes[level]);
			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;

			ret = btrfs_lookup_extent_info(trans, fs_info,
						path->nodes[level]->start,
						level, 1, &wc->refs[level],
						&wc->flags[level]);
			if (ret < 0) {
				err = ret;
				goto out_end_trans;
			}
			BUG_ON(wc->refs[level] == 0);

			if (level == root_item->drop_level)
				break;

			btrfs_tree_unlock(path->nodes[level]);
			path->locks[level] = 0;
			WARN_ON(wc->refs[level] != 1);
			level--;
		}
	}

	wc->restarted = test_bit(BTRFS_ROOT_DEAD_TREE, &root->state);
	wc->level = level;
	wc->shared_level = -1;
	wc->stage = DROP_REFERENCE;
	wc->update_ref = update_ref;
	wc->keep_locks = 0;
	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);

	while (1) {

		ret = walk_down_tree(trans, root, path, wc);
		if (ret < 0) {
			err = ret;
			break;
		}

		ret = walk_up_tree(trans, root, path, wc, BTRFS_MAX_LEVEL);
		if (ret < 0) {
			err = ret;
			break;
		}

		if (ret > 0) {
			BUG_ON(wc->stage != DROP_REFERENCE);
			break;
		}

		if (wc->stage == DROP_REFERENCE) {
			wc->drop_level = wc->level;
			btrfs_node_key_to_cpu(path->nodes[wc->drop_level],
					      &wc->drop_progress,
					      path->slots[wc->drop_level]);
		}
		btrfs_cpu_key_to_disk(&root_item->drop_progress,
				      &wc->drop_progress);
		root_item->drop_level = wc->drop_level;

		BUG_ON(wc->level == 0);
		if (btrfs_should_end_transaction(trans) ||
		    (!for_reloc && btrfs_need_cleaner_sleep(fs_info))) {
			ret = btrfs_update_root(trans, tree_root,
						&root->root_key,
						root_item);
			if (ret) {
				btrfs_abort_transaction(trans, ret);
				err = ret;
				goto out_end_trans;
			}

			btrfs_end_transaction_throttle(trans);
			if (!for_reloc && btrfs_need_cleaner_sleep(fs_info)) {
				btrfs_debug(fs_info,
					    "drop snapshot early exit");
				err = -EAGAIN;
				goto out_free;
			}

			trans = btrfs_start_transaction(tree_root, 0);
			if (IS_ERR(trans)) {
				err = PTR_ERR(trans);
				goto out_free;
			}
			if (block_rsv)
				trans->block_rsv = block_rsv;
		}
	}
	btrfs_release_path(path);
	if (err)
		goto out_end_trans;

	ret = btrfs_del_root(trans, &root->root_key);
	if (ret) {
		btrfs_abort_transaction(trans, ret);
		err = ret;
		goto out_end_trans;
	}

	if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
		ret = btrfs_find_root(tree_root, &root->root_key, path,
				      NULL, NULL);
		if (ret < 0) {
			btrfs_abort_transaction(trans, ret);
			err = ret;
			goto out_end_trans;
		} else if (ret > 0) {
			/* if we fail to delete the orphan item this time
			 * around, it'll get picked up the next time.
			 *
			 * The most common failure here is just -ENOENT.
			 */
			btrfs_del_orphan_item(trans, tree_root,
					      root->root_key.objectid);
		}
	}

	if (test_bit(BTRFS_ROOT_IN_RADIX, &root->state)) {
		btrfs_add_dropped_root(trans, root);
	} else {
		free_extent_buffer(root->node);
		free_extent_buffer(root->commit_root);
		btrfs_put_fs_root(root);
	}
	root_dropped = true;
out_end_trans:
	btrfs_end_transaction_throttle(trans);
out_free:
	kfree(wc);
	btrfs_free_path(path);
out:
	/*
	 * So if we need to stop dropping the snapshot for whatever reason we
	 * need to make sure to add it back to the dead root list so that we
	 * keep trying to do the work later.  This also cleans up roots if we
	 * don't have it in the radix (like when we recover after a power fail
	 * or unmount) so we don't leak memory.
	 */
	if (!for_reloc && !root_dropped)
		btrfs_add_dead_root(root);
	if (err && err != -EAGAIN)
		btrfs_handle_fs_error(fs_info, err, NULL);
	return err;
}

/*
 * drop subtree rooted at tree block 'node'.
 *
 * NOTE: this function will unlock and release tree block 'node'
 * only used by relocation code
 */
int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
			struct btrfs_root *root,
			struct extent_buffer *node,
			struct extent_buffer *parent)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_path *path;
	struct walk_control *wc;
	int level;
	int parent_level;
	int ret = 0;
	int wret;

	BUG_ON(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);

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

	wc = kzalloc(sizeof(*wc), GFP_NOFS);
	if (!wc) {
		btrfs_free_path(path);
		return -ENOMEM;
	}

	btrfs_assert_tree_locked(parent);
	parent_level = btrfs_header_level(parent);
	extent_buffer_get(parent);
	path->nodes[parent_level] = parent;
	path->slots[parent_level] = btrfs_header_nritems(parent);

	btrfs_assert_tree_locked(node);
	level = btrfs_header_level(node);
	path->nodes[level] = node;
	path->slots[level] = 0;
	path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;

	wc->refs[parent_level] = 1;
	wc->flags[parent_level] = BTRFS_BLOCK_FLAG_FULL_BACKREF;
	wc->level = level;
	wc->shared_level = -1;
	wc->stage = DROP_REFERENCE;
	wc->update_ref = 0;
	wc->keep_locks = 1;
	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);

	while (1) {
		wret = walk_down_tree(trans, root, path, wc);
		if (wret < 0) {
			ret = wret;
			break;
		}

		wret = walk_up_tree(trans, root, path, wc, parent_level);
		if (wret < 0)
			ret = wret;
		if (wret != 0)
			break;
	}

	kfree(wc);
	btrfs_free_path(path);
	return ret;
}

static u64 update_block_group_flags(struct btrfs_fs_info *fs_info, u64 flags)
{
	u64 num_devices;
	u64 stripped;

	/*
	 * if restripe for this chunk_type is on pick target profile and
	 * return, otherwise do the usual balance
	 */
	stripped = get_restripe_target(fs_info, flags);
	if (stripped)
		return extended_to_chunk(stripped);

	num_devices = fs_info->fs_devices->rw_devices;

	stripped = BTRFS_BLOCK_GROUP_RAID0 |
		BTRFS_BLOCK_GROUP_RAID5 | BTRFS_BLOCK_GROUP_RAID6 |
		BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10;

	if (num_devices == 1) {
		stripped |= BTRFS_BLOCK_GROUP_DUP;
		stripped = flags & ~stripped;

		/* turn raid0 into single device chunks */
		if (flags & BTRFS_BLOCK_GROUP_RAID0)
			return stripped;

		/* turn mirroring into duplication */
		if (flags & (BTRFS_BLOCK_GROUP_RAID1 |
			     BTRFS_BLOCK_GROUP_RAID10))
			return stripped | BTRFS_BLOCK_GROUP_DUP;
	} else {
		/* they already had raid on here, just return */
		if (flags & stripped)
			return flags;

		stripped |= BTRFS_BLOCK_GROUP_DUP;
		stripped = flags & ~stripped;

		/* switch duplicated blocks with raid1 */
		if (flags & BTRFS_BLOCK_GROUP_DUP)
			return stripped | BTRFS_BLOCK_GROUP_RAID1;

		/* this is drive concat, leave it alone */
	}

	return flags;
}

static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
{
	struct btrfs_space_info *sinfo = cache->space_info;
	u64 num_bytes;
	u64 sinfo_used;
	u64 min_allocable_bytes;
	int ret = -ENOSPC;

	/*
	 * We need some metadata space and system metadata space for
	 * allocating chunks in some corner cases until we force to set
	 * it to be readonly.
	 */
	if ((sinfo->flags &
	     (BTRFS_BLOCK_GROUP_SYSTEM | BTRFS_BLOCK_GROUP_METADATA)) &&
	    !force)
		min_allocable_bytes = SZ_1M;
	else
		min_allocable_bytes = 0;

	spin_lock(&sinfo->lock);
	spin_lock(&cache->lock);

	if (cache->ro) {
		cache->ro++;
		ret = 0;
		goto out;
	}

	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
		    cache->bytes_super - btrfs_block_group_used(&cache->item);
	sinfo_used = btrfs_space_info_used(sinfo, true);

	if (sinfo_used + num_bytes + min_allocable_bytes <=
	    sinfo->total_bytes) {
		sinfo->bytes_readonly += num_bytes;
		cache->ro++;
		list_add_tail(&cache->ro_list, &sinfo->ro_bgs);
		ret = 0;
	}
out:
	spin_unlock(&cache->lock);
	spin_unlock(&sinfo->lock);
	if (ret == -ENOSPC && btrfs_test_opt(cache->fs_info, ENOSPC_DEBUG)) {
		btrfs_info(cache->fs_info,
			"unable to make block group %llu ro",
			cache->key.objectid);
		btrfs_info(cache->fs_info,
			"sinfo_used=%llu bg_num_bytes=%llu min_allocable=%llu",
			sinfo_used, num_bytes, min_allocable_bytes);
		dump_space_info(cache->fs_info, cache->space_info, 0, 0);
	}
	return ret;
}

int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)

{
	struct btrfs_fs_info *fs_info = cache->fs_info;
	struct btrfs_trans_handle *trans;
	u64 alloc_flags;
	int ret;

again:
	trans = btrfs_join_transaction(fs_info->extent_root);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	/*
	 * we're not allowed to set block groups readonly after the dirty
	 * block groups cache has started writing.  If it already started,
	 * back off and let this transaction commit
	 */
	mutex_lock(&fs_info->ro_block_group_mutex);
	if (test_bit(BTRFS_TRANS_DIRTY_BG_RUN, &trans->transaction->flags)) {
		u64 transid = trans->transid;

		mutex_unlock(&fs_info->ro_block_group_mutex);
		btrfs_end_transaction(trans);

		ret = btrfs_wait_for_commit(fs_info, transid);
		if (ret)
			return ret;
		goto again;
	}

	/*
	 * if we are changing raid levels, try to allocate a corresponding
	 * block group with the new raid level.
	 */
	alloc_flags = update_block_group_flags(fs_info, cache->flags);
	if (alloc_flags != cache->flags) {
		ret = do_chunk_alloc(trans, alloc_flags,
				     CHUNK_ALLOC_FORCE);
		/*
		 * ENOSPC is allowed here, we may have enough space
		 * already allocated at the new raid level to
		 * carry on
		 */
		if (ret == -ENOSPC)
			ret = 0;
		if (ret < 0)
			goto out;
	}

	ret = inc_block_group_ro(cache, 0);
	if (!ret)
		goto out;
	alloc_flags = get_alloc_profile(fs_info, cache->space_info->flags);
	ret = do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
	if (ret < 0)
		goto out;
	ret = inc_block_group_ro(cache, 0);
out:
	if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
		alloc_flags = update_block_group_flags(fs_info, cache->flags);
		mutex_lock(&fs_info->chunk_mutex);
		check_system_chunk(trans, alloc_flags);
		mutex_unlock(&fs_info->chunk_mutex);
	}
	mutex_unlock(&fs_info->ro_block_group_mutex);

	btrfs_end_transaction(trans);
	return ret;
}

int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type)
{
	u64 alloc_flags = get_alloc_profile(trans->fs_info, type);

	return do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
}

/*
 * helper to account the unused space of all the readonly block group in the
 * space_info. takes mirrors into account.
 */
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
{
	struct btrfs_block_group_cache *block_group;
	u64 free_bytes = 0;
	int factor;

	/* It's df, we don't care if it's racy */
	if (list_empty(&sinfo->ro_bgs))
		return 0;

	spin_lock(&sinfo->lock);
	list_for_each_entry(block_group, &sinfo->ro_bgs, ro_list) {
		spin_lock(&block_group->lock);

		if (!block_group->ro) {
			spin_unlock(&block_group->lock);
			continue;
		}

		factor = btrfs_bg_type_to_factor(block_group->flags);
		free_bytes += (block_group->key.offset -
			       btrfs_block_group_used(&block_group->item)) *
			       factor;

		spin_unlock(&block_group->lock);
	}
	spin_unlock(&sinfo->lock);

	return free_bytes;
}

void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache)
{
	struct btrfs_space_info *sinfo = cache->space_info;
	u64 num_bytes;

	BUG_ON(!cache->ro);

	spin_lock(&sinfo->lock);
	spin_lock(&cache->lock);
	if (!--cache->ro) {
		num_bytes = cache->key.offset - cache->reserved -
			    cache->pinned - cache->bytes_super -
			    btrfs_block_group_used(&cache->item);
		sinfo->bytes_readonly -= num_bytes;
		list_del_init(&cache->ro_list);
	}
	spin_unlock(&cache->lock);
	spin_unlock(&sinfo->lock);
}

/*
 * Checks to see if it's even possible to relocate this block group.
 *
 * @return - -1 if it's not a good idea to relocate this block group, 0 if its
 * ok to go ahead and try.
 */
int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_space_info *space_info;
	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
	struct btrfs_device *device;
	u64 min_free;
	u64 dev_min = 1;
	u64 dev_nr = 0;
	u64 target;
	int debug;
	int index;
	int full = 0;
	int ret = 0;

	debug = btrfs_test_opt(fs_info, ENOSPC_DEBUG);

	block_group = btrfs_lookup_block_group(fs_info, bytenr);

	/* odd, couldn't find the block group, leave it alone */
	if (!block_group) {
		if (debug)
			btrfs_warn(fs_info,
				   "can't find block group for bytenr %llu",
				   bytenr);
		return -1;
	}

	min_free = btrfs_block_group_used(&block_group->item);

	/* no bytes used, we're good */
	if (!min_free)
		goto out;

	space_info = block_group->space_info;
	spin_lock(&space_info->lock);

	full = space_info->full;

	/*
	 * if this is the last block group we have in this space, we can't
	 * relocate it unless we're able to allocate a new chunk below.
	 *
	 * Otherwise, we need to make sure we have room in the space to handle
	 * all of the extents from this block group.  If we can, we're good
	 */
	if ((space_info->total_bytes != block_group->key.offset) &&
	    (btrfs_space_info_used(space_info, false) + min_free <
	     space_info->total_bytes)) {
		spin_unlock(&space_info->lock);
		goto out;
	}
	spin_unlock(&space_info->lock);

	/*
	 * ok we don't have enough space, but maybe we have free space on our
	 * devices to allocate new chunks for relocation, so loop through our
	 * alloc devices and guess if we have enough space.  if this block
	 * group is going to be restriped, run checks against the target
	 * profile instead of the current one.
	 */
	ret = -1;

	/*
	 * index:
	 *      0: raid10
	 *      1: raid1
	 *      2: dup
	 *      3: raid0
	 *      4: single
	 */
	target = get_restripe_target(fs_info, block_group->flags);
	if (target) {
		index = btrfs_bg_flags_to_raid_index(extended_to_chunk(target));
	} else {
		/*
		 * this is just a balance, so if we were marked as full
		 * we know there is no space for a new chunk
		 */
		if (full) {
			if (debug)
				btrfs_warn(fs_info,
					   "no space to alloc new chunk for block group %llu",
					   block_group->key.objectid);
			goto out;
		}

		index = btrfs_bg_flags_to_raid_index(block_group->flags);
	}

	if (index == BTRFS_RAID_RAID10) {
		dev_min = 4;
		/* Divide by 2 */
		min_free >>= 1;
	} else if (index == BTRFS_RAID_RAID1) {
		dev_min = 2;
	} else if (index == BTRFS_RAID_DUP) {
		/* Multiply by 2 */
		min_free <<= 1;
	} else if (index == BTRFS_RAID_RAID0) {
		dev_min = fs_devices->rw_devices;
		min_free = div64_u64(min_free, dev_min);
	}

	mutex_lock(&fs_info->chunk_mutex);
	list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) {
		u64 dev_offset;

		/*
		 * check to make sure we can actually find a chunk with enough
		 * space to fit our block group in.
		 */
		if (device->total_bytes > device->bytes_used + min_free &&
		    !test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state)) {
			ret = find_free_dev_extent(device, min_free,
						   &dev_offset, NULL);
			if (!ret)
				dev_nr++;

			if (dev_nr >= dev_min)
				break;

			ret = -1;
		}
	}
	if (debug && ret == -1)
		btrfs_warn(fs_info,
			   "no space to allocate a new chunk for block group %llu",
			   block_group->key.objectid);
	mutex_unlock(&fs_info->chunk_mutex);
out:
	btrfs_put_block_group(block_group);
	return ret;
}

static int find_first_block_group(struct btrfs_fs_info *fs_info,
				  struct btrfs_path *path,
				  struct btrfs_key *key)
{
	struct btrfs_root *root = fs_info->extent_root;
	int ret = 0;
	struct btrfs_key found_key;
	struct extent_buffer *leaf;
	struct btrfs_block_group_item bg;
	u64 flags;
	int slot;

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

	while (1) {
		slot = path->slots[0];
		leaf = path->nodes[0];
		if (slot >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(root, path);
			if (ret == 0)
				continue;
			if (ret < 0)
				goto out;
			break;
		}
		btrfs_item_key_to_cpu(leaf, &found_key, slot);

		if (found_key.objectid >= key->objectid &&
		    found_key.type == BTRFS_BLOCK_GROUP_ITEM_KEY) {
			struct extent_map_tree *em_tree;
			struct extent_map *em;

			em_tree = &root->fs_info->mapping_tree.map_tree;
			read_lock(&em_tree->lock);
			em = lookup_extent_mapping(em_tree, found_key.objectid,
						   found_key.offset);
			read_unlock(&em_tree->lock);
			if (!em) {
				btrfs_err(fs_info,
			"logical %llu len %llu found bg but no related chunk",
					  found_key.objectid, found_key.offset);
				ret = -ENOENT;
			} else if (em->start != found_key.objectid ||
				   em->len != found_key.offset) {
				btrfs_err(fs_info,
		"block group %llu len %llu mismatch with chunk %llu len %llu",
					  found_key.objectid, found_key.offset,
					  em->start, em->len);
				ret = -EUCLEAN;
			} else {
				read_extent_buffer(leaf, &bg,
					btrfs_item_ptr_offset(leaf, slot),
					sizeof(bg));
				flags = btrfs_block_group_flags(&bg) &
					BTRFS_BLOCK_GROUP_TYPE_MASK;

				if (flags != (em->map_lookup->type &
					      BTRFS_BLOCK_GROUP_TYPE_MASK)) {
					btrfs_err(fs_info,
"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
						found_key.objectid,
						found_key.offset, flags,
						(BTRFS_BLOCK_GROUP_TYPE_MASK &
						 em->map_lookup->type));
					ret = -EUCLEAN;
				} else {
					ret = 0;
				}
			}
			free_extent_map(em);
			goto out;
		}
		path->slots[0]++;
	}
out:
	return ret;
}

void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
{
	struct btrfs_block_group_cache *block_group;
	u64 last = 0;

	while (1) {
		struct inode *inode;

		block_group = btrfs_lookup_first_block_group(info, last);
		while (block_group) {
			wait_block_group_cache_done(block_group);
			spin_lock(&block_group->lock);
			if (block_group->iref)
				break;
			spin_unlock(&block_group->lock);
			block_group = next_block_group(block_group);
		}
		if (!block_group) {
			if (last == 0)
				break;
			last = 0;
			continue;
		}

		inode = block_group->inode;
		block_group->iref = 0;
		block_group->inode = NULL;
		spin_unlock(&block_group->lock);
		ASSERT(block_group->io_ctl.inode == NULL);
		iput(inode);
		last = block_group->key.objectid + block_group->key.offset;
		btrfs_put_block_group(block_group);
	}
}

/*
 * Must be called only after stopping all workers, since we could have block
 * group caching kthreads running, and therefore they could race with us if we
 * freed the block groups before stopping them.
 */
int btrfs_free_block_groups(struct btrfs_fs_info *info)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_space_info *space_info;
	struct btrfs_caching_control *caching_ctl;
	struct rb_node *n;

	down_write(&info->commit_root_sem);
	while (!list_empty(&info->caching_block_groups)) {
		caching_ctl = list_entry(info->caching_block_groups.next,
					 struct btrfs_caching_control, list);
		list_del(&caching_ctl->list);
		put_caching_control(caching_ctl);
	}
	up_write(&info->commit_root_sem);

	spin_lock(&info->unused_bgs_lock);
	while (!list_empty(&info->unused_bgs)) {
		block_group = list_first_entry(&info->unused_bgs,
					       struct btrfs_block_group_cache,
					       bg_list);
		list_del_init(&block_group->bg_list);
		btrfs_put_block_group(block_group);
	}
	spin_unlock(&info->unused_bgs_lock);

	spin_lock(&info->block_group_cache_lock);
	while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
		block_group = rb_entry(n, struct btrfs_block_group_cache,
				       cache_node);
		rb_erase(&block_group->cache_node,
			 &info->block_group_cache_tree);
		RB_CLEAR_NODE(&block_group->cache_node);
		spin_unlock(&info->block_group_cache_lock);

		down_write(&block_group->space_info->groups_sem);
		list_del(&block_group->list);
		up_write(&block_group->space_info->groups_sem);

		/*
		 * We haven't cached this block group, which means we could
		 * possibly have excluded extents on this block group.
		 */
		if (block_group->cached == BTRFS_CACHE_NO ||
		    block_group->cached == BTRFS_CACHE_ERROR)
			free_excluded_extents(block_group);

		btrfs_remove_free_space_cache(block_group);
		ASSERT(block_group->cached != BTRFS_CACHE_STARTED);
		ASSERT(list_empty(&block_group->dirty_list));
		ASSERT(list_empty(&block_group->io_list));
		ASSERT(list_empty(&block_group->bg_list));
		ASSERT(atomic_read(&block_group->count) == 1);
		btrfs_put_block_group(block_group);

		spin_lock(&info->block_group_cache_lock);
	}
	spin_unlock(&info->block_group_cache_lock);

	/* now that all the block groups are freed, go through and
	 * free all the space_info structs.  This is only called during
	 * the final stages of unmount, and so we know nobody is
	 * using them.  We call synchronize_rcu() once before we start,
	 * just to be on the safe side.
	 */
	synchronize_rcu();

	release_global_block_rsv(info);

	while (!list_empty(&info->space_info)) {
		int i;

		space_info = list_entry(info->space_info.next,
					struct btrfs_space_info,
					list);

		/*
		 * Do not hide this behind enospc_debug, this is actually
		 * important and indicates a real bug if this happens.
		 */
		if (WARN_ON(space_info->bytes_pinned > 0 ||
			    space_info->bytes_reserved > 0 ||
			    space_info->bytes_may_use > 0))
			dump_space_info(info, space_info, 0, 0);
		list_del(&space_info->list);
		for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
			struct kobject *kobj;
			kobj = space_info->block_group_kobjs[i];
			space_info->block_group_kobjs[i] = NULL;
			if (kobj) {
				kobject_del(kobj);
				kobject_put(kobj);
			}
		}
		kobject_del(&space_info->kobj);
		kobject_put(&space_info->kobj);
	}
	return 0;
}

/* link_block_group will queue up kobjects to add when we're reclaim-safe */
void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info)
{
	struct btrfs_space_info *space_info;
	struct raid_kobject *rkobj;
	LIST_HEAD(list);
	int index;
	int ret = 0;

	spin_lock(&fs_info->pending_raid_kobjs_lock);
	list_splice_init(&fs_info->pending_raid_kobjs, &list);
	spin_unlock(&fs_info->pending_raid_kobjs_lock);

	list_for_each_entry(rkobj, &list, list) {
		space_info = __find_space_info(fs_info, rkobj->flags);
		index = btrfs_bg_flags_to_raid_index(rkobj->flags);

		ret = kobject_add(&rkobj->kobj, &space_info->kobj,
				  "%s", get_raid_name(index));
		if (ret) {
			kobject_put(&rkobj->kobj);
			break;
		}
	}
	if (ret)
		btrfs_warn(fs_info,
			   "failed to add kobject for block cache, ignoring");
}

static void link_block_group(struct btrfs_block_group_cache *cache)
{
	struct btrfs_space_info *space_info = cache->space_info;
	struct btrfs_fs_info *fs_info = cache->fs_info;
	int index = btrfs_bg_flags_to_raid_index(cache->flags);
	bool first = false;

	down_write(&space_info->groups_sem);
	if (list_empty(&space_info->block_groups[index]))
		first = true;
	list_add_tail(&cache->list, &space_info->block_groups[index]);
	up_write(&space_info->groups_sem);

	if (first) {
		struct raid_kobject *rkobj = kzalloc(sizeof(*rkobj), GFP_NOFS);
		if (!rkobj) {
			btrfs_warn(cache->fs_info,
				"couldn't alloc memory for raid level kobject");
			return;
		}
		rkobj->flags = cache->flags;
		kobject_init(&rkobj->kobj, &btrfs_raid_ktype);

		spin_lock(&fs_info->pending_raid_kobjs_lock);
		list_add_tail(&rkobj->list, &fs_info->pending_raid_kobjs);
		spin_unlock(&fs_info->pending_raid_kobjs_lock);
		space_info->block_group_kobjs[index] = &rkobj->kobj;
	}
}

static struct btrfs_block_group_cache *
btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info,
			       u64 start, u64 size)
{
	struct btrfs_block_group_cache *cache;

	cache = kzalloc(sizeof(*cache), GFP_NOFS);
	if (!cache)
		return NULL;

	cache->free_space_ctl = kzalloc(sizeof(*cache->free_space_ctl),
					GFP_NOFS);
	if (!cache->free_space_ctl) {
		kfree(cache);
		return NULL;
	}

	cache->key.objectid = start;
	cache->key.offset = size;
	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;

	cache->fs_info = fs_info;
	cache->full_stripe_len = btrfs_full_stripe_len(fs_info, start);
	set_free_space_tree_thresholds(cache);

	atomic_set(&cache->count, 1);
	spin_lock_init(&cache->lock);
	init_rwsem(&cache->data_rwsem);
	INIT_LIST_HEAD(&cache->list);
	INIT_LIST_HEAD(&cache->cluster_list);
	INIT_LIST_HEAD(&cache->bg_list);
	INIT_LIST_HEAD(&cache->ro_list);
	INIT_LIST_HEAD(&cache->dirty_list);
	INIT_LIST_HEAD(&cache->io_list);
	btrfs_init_free_space_ctl(cache);
	atomic_set(&cache->trimming, 0);
	mutex_init(&cache->free_space_lock);
	btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);

	return cache;
}


/*
 * Iterate all chunks and verify that each of them has the corresponding block
 * group
 */
static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
{
	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
	struct extent_map *em;
	struct btrfs_block_group_cache *bg;
	u64 start = 0;
	int ret = 0;

	while (1) {
		read_lock(&map_tree->map_tree.lock);
		/*
		 * lookup_extent_mapping will return the first extent map
		 * intersecting the range, so setting @len to 1 is enough to
		 * get the first chunk.
		 */
		em = lookup_extent_mapping(&map_tree->map_tree, start, 1);
		read_unlock(&map_tree->map_tree.lock);
		if (!em)
			break;

		bg = btrfs_lookup_block_group(fs_info, em->start);
		if (!bg) {
			btrfs_err(fs_info,
	"chunk start=%llu len=%llu doesn't have corresponding block group",
				     em->start, em->len);
			ret = -EUCLEAN;
			free_extent_map(em);
			break;
		}
		if (bg->key.objectid != em->start ||
		    bg->key.offset != em->len ||
		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
			btrfs_err(fs_info,
"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
				em->start, em->len,
				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
				bg->key.objectid, bg->key.offset,
				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
			ret = -EUCLEAN;
			free_extent_map(em);
			btrfs_put_block_group(bg);
			break;
		}
		start = em->start + em->len;
		free_extent_map(em);
		btrfs_put_block_group(bg);
	}
	return ret;
}

int btrfs_read_block_groups(struct btrfs_fs_info *info)
{
	struct btrfs_path *path;
	int ret;
	struct btrfs_block_group_cache *cache;
	struct btrfs_space_info *space_info;
	struct btrfs_key key;
	struct btrfs_key found_key;
	struct extent_buffer *leaf;
	int need_clear = 0;
	u64 cache_gen;
	u64 feature;
	int mixed;

	feature = btrfs_super_incompat_flags(info->super_copy);
	mixed = !!(feature & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS);

	key.objectid = 0;
	key.offset = 0;
	key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
	path->reada = READA_FORWARD;

	cache_gen = btrfs_super_cache_generation(info->super_copy);
	if (btrfs_test_opt(info, SPACE_CACHE) &&
	    btrfs_super_generation(info->super_copy) != cache_gen)
		need_clear = 1;
	if (btrfs_test_opt(info, CLEAR_CACHE))
		need_clear = 1;

	while (1) {
		ret = find_first_block_group(info, path, &key);
		if (ret > 0)
			break;
		if (ret != 0)
			goto error;

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

		cache = btrfs_create_block_group_cache(info, found_key.objectid,
						       found_key.offset);
		if (!cache) {
			ret = -ENOMEM;
			goto error;
		}

		if (need_clear) {
			/*
			 * When we mount with old space cache, we need to
			 * set BTRFS_DC_CLEAR and set dirty flag.
			 *
			 * a) Setting 'BTRFS_DC_CLEAR' makes sure that we
			 *    truncate the old free space cache inode and
			 *    setup a new one.
			 * b) Setting 'dirty flag' makes sure that we flush
			 *    the new space cache info onto disk.
			 */
			if (btrfs_test_opt(info, SPACE_CACHE))
				cache->disk_cache_state = BTRFS_DC_CLEAR;
		}

		read_extent_buffer(leaf, &cache->item,
				   btrfs_item_ptr_offset(leaf, path->slots[0]),
				   sizeof(cache->item));
		cache->flags = btrfs_block_group_flags(&cache->item);
		if (!mixed &&
		    ((cache->flags & BTRFS_BLOCK_GROUP_METADATA) &&
		    (cache->flags & BTRFS_BLOCK_GROUP_DATA))) {
			btrfs_err(info,
"bg %llu is a mixed block group but filesystem hasn't enabled mixed block groups",
				  cache->key.objectid);
			ret = -EINVAL;
			goto error;
		}

		key.objectid = found_key.objectid + found_key.offset;
		btrfs_release_path(path);

		/*
		 * We need to exclude the super stripes now so that the space
		 * info has super bytes accounted for, otherwise we'll think
		 * we have more space than we actually do.
		 */
		ret = exclude_super_stripes(cache);
		if (ret) {
			/*
			 * We may have excluded something, so call this just in
			 * case.
			 */
			free_excluded_extents(cache);
			btrfs_put_block_group(cache);
			goto error;
		}

		/*
		 * check for two cases, either we are full, and therefore
		 * don't need to bother with the caching work since we won't
		 * find any space, or we are empty, and we can just add all
		 * the space in and be done with it.  This saves us _a_lot_ of
		 * time, particularly in the full case.
		 */
		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
			cache->last_byte_to_unpin = (u64)-1;
			cache->cached = BTRFS_CACHE_FINISHED;
			free_excluded_extents(cache);
		} else if (btrfs_block_group_used(&cache->item) == 0) {
			cache->last_byte_to_unpin = (u64)-1;
			cache->cached = BTRFS_CACHE_FINISHED;
			add_new_free_space(cache, found_key.objectid,
					   found_key.objectid +
					   found_key.offset);
			free_excluded_extents(cache);
		}

		ret = btrfs_add_block_group_cache(info, cache);
		if (ret) {
			btrfs_remove_free_space_cache(cache);
			btrfs_put_block_group(cache);
			goto error;
		}

		trace_btrfs_add_block_group(info, cache, 0);
		update_space_info(info, cache->flags, found_key.offset,
				  btrfs_block_group_used(&cache->item),
				  cache->bytes_super, &space_info);

		cache->space_info = space_info;

		link_block_group(cache);

		set_avail_alloc_bits(info, cache->flags);
		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
			inc_block_group_ro(cache, 1);
		} else if (btrfs_block_group_used(&cache->item) == 0) {
			ASSERT(list_empty(&cache->bg_list));
			btrfs_mark_bg_unused(cache);
		}
	}

	list_for_each_entry_rcu(space_info, &info->space_info, list) {
		if (!(get_alloc_profile(info, space_info->flags) &
		      (BTRFS_BLOCK_GROUP_RAID10 |
		       BTRFS_BLOCK_GROUP_RAID1 |
		       BTRFS_BLOCK_GROUP_RAID5 |
		       BTRFS_BLOCK_GROUP_RAID6 |
		       BTRFS_BLOCK_GROUP_DUP)))
			continue;
		/*
		 * avoid allocating from un-mirrored block group if there are
		 * mirrored block groups.
		 */
		list_for_each_entry(cache,
				&space_info->block_groups[BTRFS_RAID_RAID0],
				list)
			inc_block_group_ro(cache, 1);
		list_for_each_entry(cache,
				&space_info->block_groups[BTRFS_RAID_SINGLE],
				list)
			inc_block_group_ro(cache, 1);
	}

	btrfs_add_raid_kobjects(info);
	init_global_block_rsv(info);
	ret = check_chunk_block_group_mappings(info);
error:
	btrfs_free_path(path);
	return ret;
}

void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *block_group;
	struct btrfs_root *extent_root = fs_info->extent_root;
	struct btrfs_block_group_item item;
	struct btrfs_key key;
	int ret = 0;

	if (!trans->can_flush_pending_bgs)
		return;

	while (!list_empty(&trans->new_bgs)) {
		block_group = list_first_entry(&trans->new_bgs,
					       struct btrfs_block_group_cache,
					       bg_list);
		if (ret)
			goto next;

		spin_lock(&block_group->lock);
		memcpy(&item, &block_group->item, sizeof(item));
		memcpy(&key, &block_group->key, sizeof(key));
		spin_unlock(&block_group->lock);

		ret = btrfs_insert_item(trans, extent_root, &key, &item,
					sizeof(item));
		if (ret)
			btrfs_abort_transaction(trans, ret);
		ret = btrfs_finish_chunk_alloc(trans, key.objectid, key.offset);
		if (ret)
			btrfs_abort_transaction(trans, ret);
		add_block_group_free_space(trans, block_group);
		/* already aborted the transaction if it failed. */
next:
		btrfs_delayed_refs_rsv_release(fs_info, 1);
		list_del_init(&block_group->bg_list);
	}
	btrfs_trans_release_chunk_metadata(trans);
}

int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
			   u64 type, u64 chunk_offset, u64 size)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_block_group_cache *cache;
	int ret;

	btrfs_set_log_full_commit(trans);

	cache = btrfs_create_block_group_cache(fs_info, chunk_offset, size);
	if (!cache)
		return -ENOMEM;

	btrfs_set_block_group_used(&cache->item, bytes_used);
	btrfs_set_block_group_chunk_objectid(&cache->item,
					     BTRFS_FIRST_CHUNK_TREE_OBJECTID);
	btrfs_set_block_group_flags(&cache->item, type);

	cache->flags = type;
	cache->last_byte_to_unpin = (u64)-1;
	cache->cached = BTRFS_CACHE_FINISHED;
	cache->needs_free_space = 1;
	ret = exclude_super_stripes(cache);
	if (ret) {
		/*
		 * We may have excluded something, so call this just in
		 * case.
		 */
		free_excluded_extents(cache);
		btrfs_put_block_group(cache);
		return ret;
	}

	add_new_free_space(cache, chunk_offset, chunk_offset + size);

	free_excluded_extents(cache);

#ifdef CONFIG_BTRFS_DEBUG
	if (btrfs_should_fragment_free_space(cache)) {
		u64 new_bytes_used = size - bytes_used;

		bytes_used += new_bytes_used >> 1;
		fragment_free_space(cache);
	}
#endif
	/*
	 * Ensure the corresponding space_info object is created and
	 * assigned to our block group. We want our bg to be added to the rbtree
	 * with its ->space_info set.
	 */
	cache->space_info = __find_space_info(fs_info, cache->flags);
	ASSERT(cache->space_info);

	ret = btrfs_add_block_group_cache(fs_info, cache);
	if (ret) {
		btrfs_remove_free_space_cache(cache);
		btrfs_put_block_group(cache);
		return ret;
	}

	/*
	 * Now that our block group has its ->space_info set and is inserted in
	 * the rbtree, update the space info's counters.
	 */
	trace_btrfs_add_block_group(fs_info, cache, 1);
	update_space_info(fs_info, cache->flags, size, bytes_used,
				cache->bytes_super, &cache->space_info);
	update_global_block_rsv(fs_info);

	link_block_group(cache);

	list_add_tail(&cache->bg_list, &trans->new_bgs);
	trans->delayed_ref_updates++;
	btrfs_update_delayed_refs_rsv(trans);

	set_avail_alloc_bits(fs_info, type);
	return 0;
}

static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
{
	u64 extra_flags = chunk_to_extended(flags) &
				BTRFS_EXTENDED_PROFILE_MASK;

	write_seqlock(&fs_info->profiles_lock);
	if (flags & BTRFS_BLOCK_GROUP_DATA)
		fs_info->avail_data_alloc_bits &= ~extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_METADATA)
		fs_info->avail_metadata_alloc_bits &= ~extra_flags;
	if (flags & BTRFS_BLOCK_GROUP_SYSTEM)
		fs_info->avail_system_alloc_bits &= ~extra_flags;
	write_sequnlock(&fs_info->profiles_lock);
}

int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
			     u64 group_start, struct extent_map *em)
{
	struct btrfs_fs_info *fs_info = trans->fs_info;
	struct btrfs_root *root = fs_info->extent_root;
	struct btrfs_path *path;
	struct btrfs_block_group_cache *block_group;
	struct btrfs_free_cluster *cluster;
	struct btrfs_root *tree_root = fs_info->tree_root;
	struct btrfs_key key;
	struct inode *inode;
	struct kobject *kobj = NULL;
	int ret;
	int index;
	int factor;
	struct btrfs_caching_control *caching_ctl = NULL;
	bool remove_em;
	bool remove_rsv = false;

	block_group = btrfs_lookup_block_group(fs_info, group_start);
	BUG_ON(!block_group);
	BUG_ON(!block_group->ro);

	trace_btrfs_remove_block_group(block_group);
	/*
	 * Free the reserved super bytes from this block group before
	 * remove it.
	 */
	free_excluded_extents(block_group);
	btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
				  block_group->key.offset);

	memcpy(&key, &block_group->key, sizeof(key));
	index = btrfs_bg_flags_to_raid_index(block_group->flags);
	factor = btrfs_bg_type_to_factor(block_group->flags);

	/* make sure this block group isn't part of an allocation cluster */
	cluster = &fs_info->data_alloc_cluster;
	spin_lock(&cluster->refill_lock);
	btrfs_return_cluster_to_free_space(block_group, cluster);
	spin_unlock(&cluster->refill_lock);

	/*
	 * make sure this block group isn't part of a metadata
	 * allocation cluster
	 */
	cluster = &fs_info->meta_alloc_cluster;
	spin_lock(&cluster->refill_lock);
	btrfs_return_cluster_to_free_space(block_group, cluster);
	spin_unlock(&cluster->refill_lock);

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

	/*
	 * get the inode first so any iput calls done for the io_list
	 * aren't the final iput (no unlinks allowed now)
	 */
	inode = lookup_free_space_inode(block_group, path);

	mutex_lock(&trans->transaction->cache_write_mutex);
	/*
	 * Make sure our free space cache IO is done before removing the
	 * free space inode
	 */
	spin_lock(&trans->transaction->dirty_bgs_lock);
	if (!list_empty(&block_group->io_list)) {
		list_del_init(&block_group->io_list);

		WARN_ON(!IS_ERR(inode) && inode != block_group->io_ctl.inode);

		spin_unlock(&trans->transaction->dirty_bgs_lock);
		btrfs_wait_cache_io(trans, block_group, path);
		btrfs_put_block_group(block_group);
		spin_lock(&trans->transaction->dirty_bgs_lock);
	}

	if (!list_empty(&block_group->dirty_list)) {
		list_del_init(&block_group->dirty_list);
		remove_rsv = true;
		btrfs_put_block_group(block_group);
	}
	spin_unlock(&trans->transaction->dirty_bgs_lock);
	mutex_unlock(&trans->transaction->cache_write_mutex);

	if (!IS_ERR(inode)) {
		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
		if (ret) {
			btrfs_add_delayed_iput(inode);
			goto out;
		}
		clear_nlink(inode);
		/* One for the block groups ref */
		spin_lock(&block_group->lock);
		if (block_group->iref) {
			block_group->iref = 0;
			block_group->inode = NULL;
			spin_unlock(&block_group->lock);
			iput(inode);
		} else {
			spin_unlock(&block_group->lock);
		}
		/* One for our lookup ref */
		btrfs_add_delayed_iput(inode);
	}

	key.objectid = BTRFS_FREE_SPACE_OBJECTID;
	key.offset = block_group->key.objectid;
	key.type = 0;

	ret = btrfs_search_slot(trans, tree_root, &key, path, -1, 1);
	if (ret < 0)
		goto out;
	if (ret > 0)
		btrfs_release_path(path);
	if (ret == 0) {
		ret = btrfs_del_item(trans, tree_root, path);
		if (ret)
			goto out;
		btrfs_release_path(path);
	}

	spin_lock(&fs_info->block_group_cache_lock);
	rb_erase(&block_group->cache_node,
		 &fs_info->block_group_cache_tree);
	RB_CLEAR_NODE(&block_group->cache_node);

	if (fs_info->first_logical_byte == block_group->key.objectid)
		fs_info->first_logical_byte = (u64)-1;
	spin_unlock(&fs_info->block_group_cache_lock);

	down_write(&block_group->space_info->groups_sem);
	/*
	 * we must use list_del_init so people can check to see if they
	 * are still on the list after taking the semaphore
	 */
	list_del_init(&block_group->list);
	if (list_empty(&block_group->space_info->block_groups[index])) {
		kobj = block_group->space_info->block_group_kobjs[index];
		block_group->space_info->block_group_kobjs[index] = NULL;
		clear_avail_alloc_bits(fs_info, block_group->flags);
	}
	up_write(&block_group->space_info->groups_sem);
	if (kobj) {
		kobject_del(kobj);
		kobject_put(kobj);
	}

	if (block_group->has_caching_ctl)
		caching_ctl = get_caching_control(block_group);
	if (block_group->cached == BTRFS_CACHE_STARTED)
		wait_block_group_cache_done(block_group);
	if (block_group->has_caching_ctl) {
		down_write(&fs_info->commit_root_sem);
		if (!caching_ctl) {
			struct btrfs_caching_control *ctl;

			list_for_each_entry(ctl,
				    &fs_info->caching_block_groups, list)
				if (ctl->block_group == block_group) {
					caching_ctl = ctl;
					refcount_inc(&caching_ctl->count);
					break;
				}
		}
		if (caching_ctl)
			list_del_init(&caching_ctl->list);
		up_write(&fs_info->commit_root_sem);
		if (caching_ctl) {
			/* Once for the caching bgs list and once for us. */
			put_caching_control(caching_ctl);
			put_caching_control(caching_ctl);
		}
	}

	spin_lock(&trans->transaction->dirty_bgs_lock);
	WARN_ON(!list_empty(&block_group->dirty_list));
	WARN_ON(!list_empty(&block_group->io_list));
	spin_unlock(&trans->transaction->dirty_bgs_lock);

	btrfs_remove_free_space_cache(block_group);

	spin_lock(&block_group->space_info->lock);
	list_del_init(&block_group->ro_list);

	if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
		WARN_ON(block_group->space_info->total_bytes
			< block_group->key.offset);
		WARN_ON(block_group->space_info->bytes_readonly
			< block_group->key.offset);
		WARN_ON(block_group->space_info->disk_total
			< block_group->key.offset * factor);
	}
	block_group->space_info->total_bytes -= block_group->key.offset;
	block_group->space_info->bytes_readonly -= block_group->key.offset;
	block_group->space_info->disk_total -= block_group->key.offset * factor;

	spin_unlock(&block_group->space_info->lock);

	memcpy(&key, &block_group->key, sizeof(key));

	mutex_lock(&fs_info->chunk_mutex);
	spin_lock(&block_group->lock);
	block_group->removed = 1;
	/*
	 * At this point trimming can't start on this block group, because we
	 * removed the block group from the tree fs_info->block_group_cache_tree
	 * so no one can't find it anymore and even if someone already got this
	 * block group before we removed it from the rbtree, they have already
	 * incremented block_group->trimming - if they didn't, they won't find
	 * any free space entries because we already removed them all when we
	 * called btrfs_remove_free_space_cache().
	 *
	 * And we must not remove the extent map from the fs_info->mapping_tree
	 * to prevent the same logical address range and physical device space
	 * ranges from being reused for a new block group. This is because our
	 * fs trim operation (btrfs_trim_fs() / btrfs_ioctl_fitrim()) is
	 * completely transactionless, so while it is trimming a range the
	 * currently running transaction might finish and a new one start,
	 * allowing for new block groups to be created that can reuse the same
	 * physical device locations unless we take this special care.
	 *
	 * There may also be an implicit trim operation if the file system
	 * is mounted with -odiscard. The same protections must remain
	 * in place until the extents have been discarded completely when
	 * the transaction commit has completed.
	 */
	remove_em = (atomic_read(&block_group->trimming) == 0);
	spin_unlock(&block_group->lock);

	if (remove_em) {
		struct extent_map_tree *em_tree;

		em_tree = &fs_info->mapping_tree.map_tree;
		write_lock(&em_tree->lock);
		remove_extent_mapping(em_tree, em);
		write_unlock(&em_tree->lock);
		/* once for the tree */
		free_extent_map(em);
	}

	mutex_unlock(&fs_info->chunk_mutex);

	ret = remove_block_group_free_space(trans, block_group);
	if (ret)
		goto out;

	btrfs_put_block_group(block_group);
	btrfs_put_block_group(block_group);

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

	ret = btrfs_del_item(trans, root, path);
out:
	if (remove_rsv)
		btrfs_delayed_refs_rsv_release(fs_info, 1);
	btrfs_free_path(path);
	return ret;
}

struct btrfs_trans_handle *
btrfs_start_trans_remove_block_group(struct btrfs_fs_info *fs_info,
				     const u64 chunk_offset)
{
	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
	struct extent_map *em;
	struct map_lookup *map;
	unsigned int num_items;

	read_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
	read_unlock(&em_tree->lock);
	ASSERT(em && em->start == chunk_offset);

	/*
	 * We need to reserve 3 + N units from the metadata space info in order
	 * to remove a block group (done at btrfs_remove_chunk() and at
	 * btrfs_remove_block_group()), which are used for:
	 *
	 * 1 unit for adding the free space inode's orphan (located in the tree
	 * of tree roots).
	 * 1 unit for deleting the block group item (located in the extent
	 * tree).
	 * 1 unit for deleting the free space item (located in tree of tree
	 * roots).
	 * N units for deleting N device extent items corresponding to each
	 * stripe (located in the device tree).
	 *
	 * In order to remove a block group we also need to reserve units in the
	 * system space info in order to update the chunk tree (update one or
	 * more device items and remove one chunk item), but this is done at
	 * btrfs_remove_chunk() through a call to check_system_chunk().
	 */
	map = em->map_lookup;
	num_items = 3 + map->num_stripes;
	free_extent_map(em);

	return btrfs_start_transaction_fallback_global_rsv(fs_info->extent_root,
							   num_items, 1);
}

/*
 * Process the unused_bgs list and remove any that don't have any allocated
 * space inside of them.
 */
void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
{
	struct btrfs_block_group_cache *block_group;
	struct btrfs_space_info *space_info;
	struct btrfs_trans_handle *trans;
	int ret = 0;

	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
		return;

	spin_lock(&fs_info->unused_bgs_lock);
	while (!list_empty(&fs_info->unused_bgs)) {
		u64 start, end;
		int trimming;

		block_group = list_first_entry(&fs_info->unused_bgs,
					       struct btrfs_block_group_cache,
					       bg_list);
		list_del_init(&block_group->bg_list);

		space_info = block_group->space_info;

		if (ret || btrfs_mixed_space_info(space_info)) {
			btrfs_put_block_group(block_group);
			continue;
		}
		spin_unlock(&fs_info->unused_bgs_lock);

		mutex_lock(&fs_info->delete_unused_bgs_mutex);

		/* Don't want to race with allocators so take the groups_sem */
		down_write(&space_info->groups_sem);
		spin_lock(&block_group->lock);
		if (block_group->reserved || block_group->pinned ||
		    btrfs_block_group_used(&block_group->item) ||
		    block_group->ro ||
		    list_is_singular(&block_group->list)) {
			/*
			 * We want to bail if we made new allocations or have
			 * outstanding allocations in this block group.  We do
			 * the ro check in case balance is currently acting on
			 * this block group.
			 */
			trace_btrfs_skip_unused_block_group(block_group);
			spin_unlock(&block_group->lock);
			up_write(&space_info->groups_sem);
			goto next;
		}
		spin_unlock(&block_group->lock);

		/* We don't want to force the issue, only flip if it's ok. */
		ret = inc_block_group_ro(block_group, 0);
		up_write(&space_info->groups_sem);
		if (ret < 0) {
			ret = 0;
			goto next;
		}

		/*
		 * Want to do this before we do anything else so we can recover
		 * properly if we fail to join the transaction.
		 */
		trans = btrfs_start_trans_remove_block_group(fs_info,
						     block_group->key.objectid);
		if (IS_ERR(trans)) {
			btrfs_dec_block_group_ro(block_group);
			ret = PTR_ERR(trans);
			goto next;
		}

		/*
		 * We could have pending pinned extents for this block group,
		 * just delete them, we don't care about them anymore.
		 */
		start = block_group->key.objectid;
		end = start + block_group->key.offset - 1;
		/*
		 * Hold the unused_bg_unpin_mutex lock to avoid racing with
		 * btrfs_finish_extent_commit(). If we are at transaction N,
		 * another task might be running finish_extent_commit() for the
		 * previous transaction N - 1, and have seen a range belonging
		 * to the block group in freed_extents[] before we were able to
		 * clear the whole block group range from freed_extents[]. This
		 * means that task can lookup for the block group after we
		 * unpinned it from freed_extents[] and removed it, leading to
		 * a BUG_ON() at btrfs_unpin_extent_range().
		 */
		mutex_lock(&fs_info->unused_bg_unpin_mutex);
		ret = clear_extent_bits(&fs_info->freed_extents[0], start, end,
				  EXTENT_DIRTY);
		if (ret) {
			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
			btrfs_dec_block_group_ro(block_group);
			goto end_trans;
		}
		ret = clear_extent_bits(&fs_info->freed_extents[1], start, end,
				  EXTENT_DIRTY);
		if (ret) {
			mutex_unlock(&fs_info->unused_bg_unpin_mutex);
			btrfs_dec_block_group_ro(block_group);
			goto end_trans;
		}
		mutex_unlock(&fs_info->unused_bg_unpin_mutex);

		/* Reset pinned so btrfs_put_block_group doesn't complain */
		spin_lock(&space_info->lock);
		spin_lock(&block_group->lock);

		update_bytes_pinned(space_info, -block_group->pinned);
		space_info->bytes_readonly += block_group->pinned;
		percpu_counter_add_batch(&space_info->total_bytes_pinned,
				   -block_group->pinned,
				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
		block_group->pinned = 0;

		spin_unlock(&block_group->lock);
		spin_unlock(&space_info->lock);

		/* DISCARD can flip during remount */
		trimming = btrfs_test_opt(fs_info, DISCARD);

		/* Implicit trim during transaction commit. */
		if (trimming)
			btrfs_get_block_group_trimming(block_group);

		/*
		 * Btrfs_remove_chunk will abort the transaction if things go
		 * horribly wrong.
		 */
		ret = btrfs_remove_chunk(trans, block_group->key.objectid);

		if (ret) {
			if (trimming)
				btrfs_put_block_group_trimming(block_group);
			goto end_trans;
		}

		/*
		 * If we're not mounted with -odiscard, we can just forget
		 * about this block group. Otherwise we'll need to wait
		 * until transaction commit to do the actual discard.
		 */
		if (trimming) {
			spin_lock(&fs_info->unused_bgs_lock);
			/*
			 * A concurrent scrub might have added us to the list
			 * fs_info->unused_bgs, so use a list_move operation
			 * to add the block group to the deleted_bgs list.
			 */
			list_move(&block_group->bg_list,
				  &trans->transaction->deleted_bgs);
			spin_unlock(&fs_info->unused_bgs_lock);
			btrfs_get_block_group(block_group);
		}
end_trans:
		btrfs_end_transaction(trans);
next:
		mutex_unlock(&fs_info->delete_unused_bgs_mutex);
		btrfs_put_block_group(block_group);
		spin_lock(&fs_info->unused_bgs_lock);
	}
	spin_unlock(&fs_info->unused_bgs_lock);
}

int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
{
	struct btrfs_super_block *disk_super;
	u64 features;
	u64 flags;
	int mixed = 0;
	int ret;

	disk_super = fs_info->super_copy;
	if (!btrfs_super_root(disk_super))
		return -EINVAL;

	features = btrfs_super_incompat_flags(disk_super);
	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
		mixed = 1;

	flags = BTRFS_BLOCK_GROUP_SYSTEM;
	ret = create_space_info(fs_info, flags);
	if (ret)
		goto out;

	if (mixed) {
		flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
		ret = create_space_info(fs_info, flags);
	} else {
		flags = BTRFS_BLOCK_GROUP_METADATA;
		ret = create_space_info(fs_info, flags);
		if (ret)
			goto out;

		flags = BTRFS_BLOCK_GROUP_DATA;
		ret = create_space_info(fs_info, flags);
	}
out:
	return ret;
}

int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
				   u64 start, u64 end)
{
	return unpin_extent_range(fs_info, start, end, false);
}

/*
 * It used to be that old block groups would be left around forever.
 * Iterating over them would be enough to trim unused space.  Since we
 * now automatically remove them, we also need to iterate over unallocated
 * space.
 *
 * We don't want a transaction for this since the discard may take a
 * substantial amount of time.  We don't require that a transaction be
 * running, but we do need to take a running transaction into account
 * to ensure that we're not discarding chunks that were released or
 * allocated in the current transaction.
 *
 * Holding the chunks lock will prevent other threads from allocating
 * or releasing chunks, but it won't prevent a running transaction
 * from committing and releasing the memory that the pending chunks
 * list head uses.  For that, we need to take a reference to the
 * transaction and hold the commit root sem.  We only need to hold
 * it while performing the free space search since we have already
 * held back allocations.
 */
static int btrfs_trim_free_extents(struct btrfs_device *device,
				   struct fstrim_range *range, u64 *trimmed)
{
	u64 start, len = 0, end = 0;
	int ret;

	start = max_t(u64, range->start, SZ_1M);
	*trimmed = 0;

	/* Discard not supported = nothing to do. */
	if (!blk_queue_discard(bdev_get_queue(device->bdev)))
		return 0;

	/* Not writable = nothing to do. */
	if (!test_bit(BTRFS_DEV_STATE_WRITEABLE, &device->dev_state))
		return 0;

	/* No free space = nothing to do. */
	if (device->total_bytes <= device->bytes_used)
		return 0;

	ret = 0;

	while (1) {
		struct btrfs_fs_info *fs_info = device->fs_info;
		u64 bytes;

		ret = mutex_lock_interruptible(&fs_info->chunk_mutex);
		if (ret)
			break;

		find_first_clear_extent_bit(&device->alloc_state, start,
					    &start, &end,
					    CHUNK_TRIMMED | CHUNK_ALLOCATED);
		/*
		 * If find_first_clear_extent_bit find a range that spans the
		 * end of the device it will set end to -1, in this case it's up
		 * to the caller to trim the value to the size of the device.
		 */
		end = min(end, device->total_bytes - 1);
		len = end - start + 1;

		/* We didn't find any extents */
		if (!len) {
			mutex_unlock(&fs_info->chunk_mutex);
			ret = 0;
			break;
		}

		/* Keep going until we satisfy minlen or reach end of space */
		if (len < range->minlen) {
			mutex_unlock(&fs_info->chunk_mutex);
			start += len;
			continue;
		}

		/* If we are out of the passed range break */
		if (start > range->start + range->len - 1) {
			mutex_unlock(&fs_info->chunk_mutex);
			break;
		}

		start = max(range->start, start);
		len = min(range->len, len);

		ret = btrfs_issue_discard(device->bdev, start, len,
					  &bytes);
		if (!ret)
			set_extent_bits(&device->alloc_state, start,
					start + bytes - 1,
					CHUNK_TRIMMED);
		mutex_unlock(&fs_info->chunk_mutex);

		if (ret)
			break;

		start += len;
		*trimmed += bytes;

		/* We've trimmed enough */
		if (*trimmed >= range->len)
			break;

		if (fatal_signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}

		cond_resched();
	}

	return ret;
}

/*
 * Trim the whole filesystem by:
 * 1) trimming the free space in each block group
 * 2) trimming the unallocated space on each device
 *
 * This will also continue trimming even if a block group or device encounters
 * an error.  The return value will be the last error, or 0 if nothing bad
 * happens.
 */
int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
{
	struct btrfs_block_group_cache *cache = NULL;
	struct btrfs_device *device;
	struct list_head *devices;
	u64 group_trimmed;
	u64 start;
	u64 end;
	u64 trimmed = 0;
	u64 bg_failed = 0;
	u64 dev_failed = 0;
	int bg_ret = 0;
	int dev_ret = 0;
	int ret = 0;

	cache = btrfs_lookup_first_block_group(fs_info, range->start);
	for (; cache; cache = next_block_group(cache)) {
		if (cache->key.objectid >= (range->start + range->len)) {
			btrfs_put_block_group(cache);
			break;
		}

		start = max(range->start, cache->key.objectid);
		end = min(range->start + range->len,
				cache->key.objectid + cache->key.offset);

		if (end - start >= range->minlen) {
			if (!block_group_cache_done(cache)) {
				ret = cache_block_group(cache, 0);
				if (ret) {
					bg_failed++;
					bg_ret = ret;
					continue;
				}
				ret = wait_block_group_cache_done(cache);
				if (ret) {
					bg_failed++;
					bg_ret = ret;
					continue;
				}
			}
			ret = btrfs_trim_block_group(cache,
						     &group_trimmed,
						     start,
						     end,
						     range->minlen);

			trimmed += group_trimmed;
			if (ret) {
				bg_failed++;
				bg_ret = ret;
				continue;
			}
		}
	}

	if (bg_failed)
		btrfs_warn(fs_info,
			"failed to trim %llu block group(s), last error %d",
			bg_failed, bg_ret);
	mutex_lock(&fs_info->fs_devices->device_list_mutex);
	devices = &fs_info->fs_devices->devices;
	list_for_each_entry(device, devices, dev_list) {
		ret = btrfs_trim_free_extents(device, range, &group_trimmed);
		if (ret) {
			dev_failed++;
			dev_ret = ret;
			break;
		}

		trimmed += group_trimmed;
	}
	mutex_unlock(&fs_info->fs_devices->device_list_mutex);

	if (dev_failed)
		btrfs_warn(fs_info,
			"failed to trim %llu device(s), last error %d",
			dev_failed, dev_ret);
	range->len = trimmed;
	if (bg_ret)
		return bg_ret;
	return dev_ret;
}

/*
 * btrfs_{start,end}_write_no_snapshotting() are similar to
 * mnt_{want,drop}_write(), they are used to prevent some tasks from writing
 * data into the page cache through nocow before the subvolume is snapshoted,
 * but flush the data into disk after the snapshot creation, or to prevent
 * operations while snapshotting is ongoing and that cause the snapshot to be
 * inconsistent (writes followed by expanding truncates for example).
 */
void btrfs_end_write_no_snapshotting(struct btrfs_root *root)
{
	percpu_counter_dec(&root->subv_writers->counter);
	cond_wake_up(&root->subv_writers->wait);
}

int btrfs_start_write_no_snapshotting(struct btrfs_root *root)
{
	if (atomic_read(&root->will_be_snapshotted))
		return 0;

	percpu_counter_inc(&root->subv_writers->counter);
	/*
	 * Make sure counter is updated before we check for snapshot creation.
	 */
	smp_mb();
	if (atomic_read(&root->will_be_snapshotted)) {
		btrfs_end_write_no_snapshotting(root);
		return 0;
	}
	return 1;
}

void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
{
	while (true) {
		int ret;

		ret = btrfs_start_write_no_snapshotting(root);
		if (ret)
			break;
		wait_var_event(&root->will_be_snapshotted,
			       !atomic_read(&root->will_be_snapshotted));
	}
}

void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
{
	struct btrfs_fs_info *fs_info = bg->fs_info;

	spin_lock(&fs_info->unused_bgs_lock);
	if (list_empty(&bg->bg_list)) {
		btrfs_get_block_group(bg);
		trace_btrfs_add_unused_block_group(bg);
		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
	}
	spin_unlock(&fs_info->unused_bgs_lock);
}