summaryrefslogtreecommitdiff
path: root/fs/btrfs/relocation.c
blob: 232d5da7b7bef334c5595f14b6d357d9a39da9b0 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2009 Oracle.  All rights reserved.
 */

#include <linux/sched.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/rbtree.h>
#include <linux/slab.h>
#include <linux/error-injection.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "volumes.h"
#include "locking.h"
#include "btrfs_inode.h"
#include "async-thread.h"
#include "free-space-cache.h"
#include "qgroup.h"
#include "print-tree.h"
#include "delalloc-space.h"
#include "block-group.h"
#include "backref.h"
#include "misc.h"

/*
 * Relocation overview
 *
 * [What does relocation do]
 *
 * The objective of relocation is to relocate all extents of the target block
 * group to other block groups.
 * This is utilized by resize (shrink only), profile converting, compacting
 * space, or balance routine to spread chunks over devices.
 *
 * 		Before		|		After
 * ------------------------------------------------------------------
 *  BG A: 10 data extents	| BG A: deleted
 *  BG B:  2 data extents	| BG B: 10 data extents (2 old + 8 relocated)
 *  BG C:  1 extents		| BG C:  3 data extents (1 old + 2 relocated)
 *
 * [How does relocation work]
 *
 * 1.   Mark the target block group read-only
 *      New extents won't be allocated from the target block group.
 *
 * 2.1  Record each extent in the target block group
 *      To build a proper map of extents to be relocated.
 *
 * 2.2  Build data reloc tree and reloc trees
 *      Data reloc tree will contain an inode, recording all newly relocated
 *      data extents.
 *      There will be only one data reloc tree for one data block group.
 *
 *      Reloc tree will be a special snapshot of its source tree, containing
 *      relocated tree blocks.
 *      Each tree referring to a tree block in target block group will get its
 *      reloc tree built.
 *
 * 2.3  Swap source tree with its corresponding reloc tree
 *      Each involved tree only refers to new extents after swap.
 *
 * 3.   Cleanup reloc trees and data reloc tree.
 *      As old extents in the target block group are still referenced by reloc
 *      trees, we need to clean them up before really freeing the target block
 *      group.
 *
 * The main complexity is in steps 2.2 and 2.3.
 *
 * The entry point of relocation is relocate_block_group() function.
 */

#define RELOCATION_RESERVED_NODES	256
/*
 * map address of tree root to tree
 */
struct mapping_node {
	struct {
		struct rb_node rb_node;
		u64 bytenr;
	}; /* Use rb_simle_node for search/insert */
	void *data;
};

struct mapping_tree {
	struct rb_root rb_root;
	spinlock_t lock;
};

/*
 * present a tree block to process
 */
struct tree_block {
	struct {
		struct rb_node rb_node;
		u64 bytenr;
	}; /* Use rb_simple_node for search/insert */
	u64 owner;
	struct btrfs_key key;
	unsigned int level:8;
	unsigned int key_ready:1;
};

#define MAX_EXTENTS 128

struct file_extent_cluster {
	u64 start;
	u64 end;
	u64 boundary[MAX_EXTENTS];
	unsigned int nr;
};

struct reloc_control {
	/* block group to relocate */
	struct btrfs_block_group *block_group;
	/* extent tree */
	struct btrfs_root *extent_root;
	/* inode for moving data */
	struct inode *data_inode;

	struct btrfs_block_rsv *block_rsv;

	struct btrfs_backref_cache backref_cache;

	struct file_extent_cluster cluster;
	/* tree blocks have been processed */
	struct extent_io_tree processed_blocks;
	/* map start of tree root to corresponding reloc tree */
	struct mapping_tree reloc_root_tree;
	/* list of reloc trees */
	struct list_head reloc_roots;
	/* list of subvolume trees that get relocated */
	struct list_head dirty_subvol_roots;
	/* size of metadata reservation for merging reloc trees */
	u64 merging_rsv_size;
	/* size of relocated tree nodes */
	u64 nodes_relocated;
	/* reserved size for block group relocation*/
	u64 reserved_bytes;

	u64 search_start;
	u64 extents_found;

	unsigned int stage:8;
	unsigned int create_reloc_tree:1;
	unsigned int merge_reloc_tree:1;
	unsigned int found_file_extent:1;
};

/* stages of data relocation */
#define MOVE_DATA_EXTENTS	0
#define UPDATE_DATA_PTRS	1

static void mark_block_processed(struct reloc_control *rc,
				 struct btrfs_backref_node *node)
{
	u32 blocksize;

	if (node->level == 0 ||
	    in_range(node->bytenr, rc->block_group->start,
		     rc->block_group->length)) {
		blocksize = rc->extent_root->fs_info->nodesize;
		set_extent_bits(&rc->processed_blocks, node->bytenr,
				node->bytenr + blocksize - 1, EXTENT_DIRTY);
	}
	node->processed = 1;
}


static void mapping_tree_init(struct mapping_tree *tree)
{
	tree->rb_root = RB_ROOT;
	spin_lock_init(&tree->lock);
}

/*
 * walk up backref nodes until reach node presents tree root
 */
static struct btrfs_backref_node *walk_up_backref(
		struct btrfs_backref_node *node,
		struct btrfs_backref_edge *edges[], int *index)
{
	struct btrfs_backref_edge *edge;
	int idx = *index;

	while (!list_empty(&node->upper)) {
		edge = list_entry(node->upper.next,
				  struct btrfs_backref_edge, list[LOWER]);
		edges[idx++] = edge;
		node = edge->node[UPPER];
	}
	BUG_ON(node->detached);
	*index = idx;
	return node;
}

/*
 * walk down backref nodes to find start of next reference path
 */
static struct btrfs_backref_node *walk_down_backref(
		struct btrfs_backref_edge *edges[], int *index)
{
	struct btrfs_backref_edge *edge;
	struct btrfs_backref_node *lower;
	int idx = *index;

	while (idx > 0) {
		edge = edges[idx - 1];
		lower = edge->node[LOWER];
		if (list_is_last(&edge->list[LOWER], &lower->upper)) {
			idx--;
			continue;
		}
		edge = list_entry(edge->list[LOWER].next,
				  struct btrfs_backref_edge, list[LOWER]);
		edges[idx - 1] = edge;
		*index = idx;
		return edge->node[UPPER];
	}
	*index = 0;
	return NULL;
}

static void update_backref_node(struct btrfs_backref_cache *cache,
				struct btrfs_backref_node *node, u64 bytenr)
{
	struct rb_node *rb_node;
	rb_erase(&node->rb_node, &cache->rb_root);
	node->bytenr = bytenr;
	rb_node = rb_simple_insert(&cache->rb_root, node->bytenr, &node->rb_node);
	if (rb_node)
		btrfs_backref_panic(cache->fs_info, bytenr, -EEXIST);
}

/*
 * update backref cache after a transaction commit
 */
static int update_backref_cache(struct btrfs_trans_handle *trans,
				struct btrfs_backref_cache *cache)
{
	struct btrfs_backref_node *node;
	int level = 0;

	if (cache->last_trans == 0) {
		cache->last_trans = trans->transid;
		return 0;
	}

	if (cache->last_trans == trans->transid)
		return 0;

	/*
	 * detached nodes are used to avoid unnecessary backref
	 * lookup. transaction commit changes the extent tree.
	 * so the detached nodes are no longer useful.
	 */
	while (!list_empty(&cache->detached)) {
		node = list_entry(cache->detached.next,
				  struct btrfs_backref_node, list);
		btrfs_backref_cleanup_node(cache, node);
	}

	while (!list_empty(&cache->changed)) {
		node = list_entry(cache->changed.next,
				  struct btrfs_backref_node, list);
		list_del_init(&node->list);
		BUG_ON(node->pending);
		update_backref_node(cache, node, node->new_bytenr);
	}

	/*
	 * some nodes can be left in the pending list if there were
	 * errors during processing the pending nodes.
	 */
	for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
		list_for_each_entry(node, &cache->pending[level], list) {
			BUG_ON(!node->pending);
			if (node->bytenr == node->new_bytenr)
				continue;
			update_backref_node(cache, node, node->new_bytenr);
		}
	}

	cache->last_trans = 0;
	return 1;
}

static bool reloc_root_is_dead(struct btrfs_root *root)
{
	/*
	 * Pair with set_bit/clear_bit in clean_dirty_subvols and
	 * btrfs_update_reloc_root. We need to see the updated bit before
	 * trying to access reloc_root
	 */
	smp_rmb();
	if (test_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state))
		return true;
	return false;
}

/*
 * Check if this subvolume tree has valid reloc tree.
 *
 * Reloc tree after swap is considered dead, thus not considered as valid.
 * This is enough for most callers, as they don't distinguish dead reloc root
 * from no reloc root.  But btrfs_should_ignore_reloc_root() below is a
 * special case.
 */
static bool have_reloc_root(struct btrfs_root *root)
{
	if (reloc_root_is_dead(root))
		return false;
	if (!root->reloc_root)
		return false;
	return true;
}

int btrfs_should_ignore_reloc_root(struct btrfs_root *root)
{
	struct btrfs_root *reloc_root;

	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
		return 0;

	/* This root has been merged with its reloc tree, we can ignore it */
	if (reloc_root_is_dead(root))
		return 1;

	reloc_root = root->reloc_root;
	if (!reloc_root)
		return 0;

	if (btrfs_header_generation(reloc_root->commit_root) ==
	    root->fs_info->running_transaction->transid)
		return 0;
	/*
	 * if there is reloc tree and it was created in previous
	 * transaction backref lookup can find the reloc tree,
	 * so backref node for the fs tree root is useless for
	 * relocation.
	 */
	return 1;
}

/*
 * find reloc tree by address of tree root
 */
struct btrfs_root *find_reloc_root(struct btrfs_fs_info *fs_info, u64 bytenr)
{
	struct reloc_control *rc = fs_info->reloc_ctl;
	struct rb_node *rb_node;
	struct mapping_node *node;
	struct btrfs_root *root = NULL;

	ASSERT(rc);
	spin_lock(&rc->reloc_root_tree.lock);
	rb_node = rb_simple_search(&rc->reloc_root_tree.rb_root, bytenr);
	if (rb_node) {
		node = rb_entry(rb_node, struct mapping_node, rb_node);
		root = (struct btrfs_root *)node->data;
	}
	spin_unlock(&rc->reloc_root_tree.lock);
	return btrfs_grab_root(root);
}

/*
 * For useless nodes, do two major clean ups:
 *
 * - Cleanup the children edges and nodes
 *   If child node is also orphan (no parent) during cleanup, then the child
 *   node will also be cleaned up.
 *
 * - Freeing up leaves (level 0), keeps nodes detached
 *   For nodes, the node is still cached as "detached"
 *
 * Return false if @node is not in the @useless_nodes list.
 * Return true if @node is in the @useless_nodes list.
 */
static bool handle_useless_nodes(struct reloc_control *rc,
				 struct btrfs_backref_node *node)
{
	struct btrfs_backref_cache *cache = &rc->backref_cache;
	struct list_head *useless_node = &cache->useless_node;
	bool ret = false;

	while (!list_empty(useless_node)) {
		struct btrfs_backref_node *cur;

		cur = list_first_entry(useless_node, struct btrfs_backref_node,
				 list);
		list_del_init(&cur->list);

		/* Only tree root nodes can be added to @useless_nodes */
		ASSERT(list_empty(&cur->upper));

		if (cur == node)
			ret = true;

		/* The node is the lowest node */
		if (cur->lowest) {
			list_del_init(&cur->lower);
			cur->lowest = 0;
		}

		/* Cleanup the lower edges */
		while (!list_empty(&cur->lower)) {
			struct btrfs_backref_edge *edge;
			struct btrfs_backref_node *lower;

			edge = list_entry(cur->lower.next,
					struct btrfs_backref_edge, list[UPPER]);
			list_del(&edge->list[UPPER]);
			list_del(&edge->list[LOWER]);
			lower = edge->node[LOWER];
			btrfs_backref_free_edge(cache, edge);

			/* Child node is also orphan, queue for cleanup */
			if (list_empty(&lower->upper))
				list_add(&lower->list, useless_node);
		}
		/* Mark this block processed for relocation */
		mark_block_processed(rc, cur);

		/*
		 * Backref nodes for tree leaves are deleted from the cache.
		 * Backref nodes for upper level tree blocks are left in the
		 * cache to avoid unnecessary backref lookup.
		 */
		if (cur->level > 0) {
			list_add(&cur->list, &cache->detached);
			cur->detached = 1;
		} else {
			rb_erase(&cur->rb_node, &cache->rb_root);
			btrfs_backref_free_node(cache, cur);
		}
	}
	return ret;
}

/*
 * Build backref tree for a given tree block. Root of the backref tree
 * corresponds the tree block, leaves of the backref tree correspond roots of
 * b-trees that reference the tree block.
 *
 * The basic idea of this function is check backrefs of a given block to find
 * upper level blocks that reference the block, and then check backrefs of
 * these upper level blocks recursively. The recursion stops when tree root is
 * reached or backrefs for the block is cached.
 *
 * NOTE: if we find that backrefs for a block are cached, we know backrefs for
 * all upper level blocks that directly/indirectly reference the block are also
 * cached.
 */
static noinline_for_stack struct btrfs_backref_node *build_backref_tree(
			struct reloc_control *rc, struct btrfs_key *node_key,
			int level, u64 bytenr)
{
	struct btrfs_backref_iter *iter;
	struct btrfs_backref_cache *cache = &rc->backref_cache;
	/* For searching parent of TREE_BLOCK_REF */
	struct btrfs_path *path;
	struct btrfs_backref_node *cur;
	struct btrfs_backref_node *node = NULL;
	struct btrfs_backref_edge *edge;
	int ret;
	int err = 0;

	iter = btrfs_backref_iter_alloc(rc->extent_root->fs_info, GFP_NOFS);
	if (!iter)
		return ERR_PTR(-ENOMEM);
	path = btrfs_alloc_path();
	if (!path) {
		err = -ENOMEM;
		goto out;
	}

	node = btrfs_backref_alloc_node(cache, bytenr, level);
	if (!node) {
		err = -ENOMEM;
		goto out;
	}

	node->lowest = 1;
	cur = node;

	/* Breadth-first search to build backref cache */
	do {
		ret = btrfs_backref_add_tree_node(cache, path, iter, node_key,
						  cur);
		if (ret < 0) {
			err = ret;
			goto out;
		}
		edge = list_first_entry_or_null(&cache->pending_edge,
				struct btrfs_backref_edge, list[UPPER]);
		/*
		 * The pending list isn't empty, take the first block to
		 * process
		 */
		if (edge) {
			list_del_init(&edge->list[UPPER]);
			cur = edge->node[UPPER];
		}
	} while (edge);

	/* Finish the upper linkage of newly added edges/nodes */
	ret = btrfs_backref_finish_upper_links(cache, node);
	if (ret < 0) {
		err = ret;
		goto out;
	}

	if (handle_useless_nodes(rc, node))
		node = NULL;
out:
	btrfs_backref_iter_free(iter);
	btrfs_free_path(path);
	if (err) {
		btrfs_backref_error_cleanup(cache, node);
		return ERR_PTR(err);
	}
	ASSERT(!node || !node->detached);
	ASSERT(list_empty(&cache->useless_node) &&
	       list_empty(&cache->pending_edge));
	return node;
}

/*
 * helper to add backref node for the newly created snapshot.
 * the backref node is created by cloning backref node that
 * corresponds to root of source tree
 */
static int clone_backref_node(struct btrfs_trans_handle *trans,
			      struct reloc_control *rc,
			      struct btrfs_root *src,
			      struct btrfs_root *dest)
{
	struct btrfs_root *reloc_root = src->reloc_root;
	struct btrfs_backref_cache *cache = &rc->backref_cache;
	struct btrfs_backref_node *node = NULL;
	struct btrfs_backref_node *new_node;
	struct btrfs_backref_edge *edge;
	struct btrfs_backref_edge *new_edge;
	struct rb_node *rb_node;

	if (cache->last_trans > 0)
		update_backref_cache(trans, cache);

	rb_node = rb_simple_search(&cache->rb_root, src->commit_root->start);
	if (rb_node) {
		node = rb_entry(rb_node, struct btrfs_backref_node, rb_node);
		if (node->detached)
			node = NULL;
		else
			BUG_ON(node->new_bytenr != reloc_root->node->start);
	}

	if (!node) {
		rb_node = rb_simple_search(&cache->rb_root,
					   reloc_root->commit_root->start);
		if (rb_node) {
			node = rb_entry(rb_node, struct btrfs_backref_node,
					rb_node);
			BUG_ON(node->detached);
		}
	}

	if (!node)
		return 0;

	new_node = btrfs_backref_alloc_node(cache, dest->node->start,
					    node->level);
	if (!new_node)
		return -ENOMEM;

	new_node->lowest = node->lowest;
	new_node->checked = 1;
	new_node->root = btrfs_grab_root(dest);
	ASSERT(new_node->root);

	if (!node->lowest) {
		list_for_each_entry(edge, &node->lower, list[UPPER]) {
			new_edge = btrfs_backref_alloc_edge(cache);
			if (!new_edge)
				goto fail;

			btrfs_backref_link_edge(new_edge, edge->node[LOWER],
						new_node, LINK_UPPER);
		}
	} else {
		list_add_tail(&new_node->lower, &cache->leaves);
	}

	rb_node = rb_simple_insert(&cache->rb_root, new_node->bytenr,
				   &new_node->rb_node);
	if (rb_node)
		btrfs_backref_panic(trans->fs_info, new_node->bytenr, -EEXIST);

	if (!new_node->lowest) {
		list_for_each_entry(new_edge, &new_node->lower, list[UPPER]) {
			list_add_tail(&new_edge->list[LOWER],
				      &new_edge->node[LOWER]->upper);
		}
	}
	return 0;
fail:
	while (!list_empty(&new_node->lower)) {
		new_edge = list_entry(new_node->lower.next,
				      struct btrfs_backref_edge, list[UPPER]);
		list_del(&new_edge->list[UPPER]);
		btrfs_backref_free_edge(cache, new_edge);
	}
	btrfs_backref_free_node(cache, new_node);
	return -ENOMEM;
}

/*
 * helper to add 'address of tree root -> reloc tree' mapping
 */
static int __must_check __add_reloc_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct rb_node *rb_node;
	struct mapping_node *node;
	struct reloc_control *rc = fs_info->reloc_ctl;

	node = kmalloc(sizeof(*node), GFP_NOFS);
	if (!node)
		return -ENOMEM;

	node->bytenr = root->commit_root->start;
	node->data = root;

	spin_lock(&rc->reloc_root_tree.lock);
	rb_node = rb_simple_insert(&rc->reloc_root_tree.rb_root,
				   node->bytenr, &node->rb_node);
	spin_unlock(&rc->reloc_root_tree.lock);
	if (rb_node) {
		btrfs_panic(fs_info, -EEXIST,
			    "Duplicate root found for start=%llu while inserting into relocation tree",
			    node->bytenr);
	}

	list_add_tail(&root->root_list, &rc->reloc_roots);
	return 0;
}

/*
 * helper to delete the 'address of tree root -> reloc tree'
 * mapping
 */
static void __del_reloc_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct rb_node *rb_node;
	struct mapping_node *node = NULL;
	struct reloc_control *rc = fs_info->reloc_ctl;
	bool put_ref = false;

	if (rc && root->node) {
		spin_lock(&rc->reloc_root_tree.lock);
		rb_node = rb_simple_search(&rc->reloc_root_tree.rb_root,
					   root->commit_root->start);
		if (rb_node) {
			node = rb_entry(rb_node, struct mapping_node, rb_node);
			rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
			RB_CLEAR_NODE(&node->rb_node);
		}
		spin_unlock(&rc->reloc_root_tree.lock);
		ASSERT(!node || (struct btrfs_root *)node->data == root);
	}

	/*
	 * We only put the reloc root here if it's on the list.  There's a lot
	 * of places where the pattern is to splice the rc->reloc_roots, process
	 * the reloc roots, and then add the reloc root back onto
	 * rc->reloc_roots.  If we call __del_reloc_root while it's off of the
	 * list we don't want the reference being dropped, because the guy
	 * messing with the list is in charge of the reference.
	 */
	spin_lock(&fs_info->trans_lock);
	if (!list_empty(&root->root_list)) {
		put_ref = true;
		list_del_init(&root->root_list);
	}
	spin_unlock(&fs_info->trans_lock);
	if (put_ref)
		btrfs_put_root(root);
	kfree(node);
}

/*
 * helper to update the 'address of tree root -> reloc tree'
 * mapping
 */
static int __update_reloc_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct rb_node *rb_node;
	struct mapping_node *node = NULL;
	struct reloc_control *rc = fs_info->reloc_ctl;

	spin_lock(&rc->reloc_root_tree.lock);
	rb_node = rb_simple_search(&rc->reloc_root_tree.rb_root,
				   root->commit_root->start);
	if (rb_node) {
		node = rb_entry(rb_node, struct mapping_node, rb_node);
		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
	}
	spin_unlock(&rc->reloc_root_tree.lock);

	if (!node)
		return 0;
	BUG_ON((struct btrfs_root *)node->data != root);

	spin_lock(&rc->reloc_root_tree.lock);
	node->bytenr = root->node->start;
	rb_node = rb_simple_insert(&rc->reloc_root_tree.rb_root,
				   node->bytenr, &node->rb_node);
	spin_unlock(&rc->reloc_root_tree.lock);
	if (rb_node)
		btrfs_backref_panic(fs_info, node->bytenr, -EEXIST);
	return 0;
}

static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
					struct btrfs_root *root, u64 objectid)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_root *reloc_root;
	struct extent_buffer *eb;
	struct btrfs_root_item *root_item;
	struct btrfs_key root_key;
	int ret;

	root_item = kmalloc(sizeof(*root_item), GFP_NOFS);
	BUG_ON(!root_item);

	root_key.objectid = BTRFS_TREE_RELOC_OBJECTID;
	root_key.type = BTRFS_ROOT_ITEM_KEY;
	root_key.offset = objectid;

	if (root->root_key.objectid == objectid) {
		u64 commit_root_gen;

		/* called by btrfs_init_reloc_root */
		ret = btrfs_copy_root(trans, root, root->commit_root, &eb,
				      BTRFS_TREE_RELOC_OBJECTID);
		BUG_ON(ret);
		/*
		 * Set the last_snapshot field to the generation of the commit
		 * root - like this ctree.c:btrfs_block_can_be_shared() behaves
		 * correctly (returns true) when the relocation root is created
		 * either inside the critical section of a transaction commit
		 * (through transaction.c:qgroup_account_snapshot()) and when
		 * it's created before the transaction commit is started.
		 */
		commit_root_gen = btrfs_header_generation(root->commit_root);
		btrfs_set_root_last_snapshot(&root->root_item, commit_root_gen);
	} else {
		/*
		 * called by btrfs_reloc_post_snapshot_hook.
		 * the source tree is a reloc tree, all tree blocks
		 * modified after it was created have RELOC flag
		 * set in their headers. so it's OK to not update
		 * the 'last_snapshot'.
		 */
		ret = btrfs_copy_root(trans, root, root->node, &eb,
				      BTRFS_TREE_RELOC_OBJECTID);
		BUG_ON(ret);
	}

	memcpy(root_item, &root->root_item, sizeof(*root_item));
	btrfs_set_root_bytenr(root_item, eb->start);
	btrfs_set_root_level(root_item, btrfs_header_level(eb));
	btrfs_set_root_generation(root_item, trans->transid);

	if (root->root_key.objectid == objectid) {
		btrfs_set_root_refs(root_item, 0);
		memset(&root_item->drop_progress, 0,
		       sizeof(struct btrfs_disk_key));
		btrfs_set_root_drop_level(root_item, 0);
	}

	btrfs_tree_unlock(eb);
	free_extent_buffer(eb);

	ret = btrfs_insert_root(trans, fs_info->tree_root,
				&root_key, root_item);
	BUG_ON(ret);
	kfree(root_item);

	reloc_root = btrfs_read_tree_root(fs_info->tree_root, &root_key);
	BUG_ON(IS_ERR(reloc_root));
	set_bit(BTRFS_ROOT_SHAREABLE, &reloc_root->state);
	reloc_root->last_trans = trans->transid;
	return reloc_root;
}

/*
 * create reloc tree for a given fs tree. reloc tree is just a
 * snapshot of the fs tree with special root objectid.
 *
 * The reloc_root comes out of here with two references, one for
 * root->reloc_root, and another for being on the rc->reloc_roots list.
 */
int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_root *reloc_root;
	struct reloc_control *rc = fs_info->reloc_ctl;
	struct btrfs_block_rsv *rsv;
	int clear_rsv = 0;
	int ret;

	if (!rc)
		return 0;

	/*
	 * The subvolume has reloc tree but the swap is finished, no need to
	 * create/update the dead reloc tree
	 */
	if (reloc_root_is_dead(root))
		return 0;

	/*
	 * This is subtle but important.  We do not do
	 * record_root_in_transaction for reloc roots, instead we record their
	 * corresponding fs root, and then here we update the last trans for the
	 * reloc root.  This means that we have to do this for the entire life
	 * of the reloc root, regardless of which stage of the relocation we are
	 * in.
	 */
	if (root->reloc_root) {
		reloc_root = root->reloc_root;
		reloc_root->last_trans = trans->transid;
		return 0;
	}

	/*
	 * We are merging reloc roots, we do not need new reloc trees.  Also
	 * reloc trees never need their own reloc tree.
	 */
	if (!rc->create_reloc_tree ||
	    root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
		return 0;

	if (!trans->reloc_reserved) {
		rsv = trans->block_rsv;
		trans->block_rsv = rc->block_rsv;
		clear_rsv = 1;
	}
	reloc_root = create_reloc_root(trans, root, root->root_key.objectid);
	if (clear_rsv)
		trans->block_rsv = rsv;

	ret = __add_reloc_root(reloc_root);
	BUG_ON(ret < 0);
	root->reloc_root = btrfs_grab_root(reloc_root);
	return 0;
}

/*
 * update root item of reloc tree
 */
int btrfs_update_reloc_root(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_root *reloc_root;
	struct btrfs_root_item *root_item;
	int ret;

	if (!have_reloc_root(root))
		goto out;

	reloc_root = root->reloc_root;
	root_item = &reloc_root->root_item;

	/*
	 * We are probably ok here, but __del_reloc_root() will drop its ref of
	 * the root.  We have the ref for root->reloc_root, but just in case
	 * hold it while we update the reloc root.
	 */
	btrfs_grab_root(reloc_root);

	/* root->reloc_root will stay until current relocation finished */
	if (fs_info->reloc_ctl->merge_reloc_tree &&
	    btrfs_root_refs(root_item) == 0) {
		set_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
		/*
		 * Mark the tree as dead before we change reloc_root so
		 * have_reloc_root will not touch it from now on.
		 */
		smp_wmb();
		__del_reloc_root(reloc_root);
	}

	if (reloc_root->commit_root != reloc_root->node) {
		__update_reloc_root(reloc_root);
		btrfs_set_root_node(root_item, reloc_root->node);
		free_extent_buffer(reloc_root->commit_root);
		reloc_root->commit_root = btrfs_root_node(reloc_root);
	}

	ret = btrfs_update_root(trans, fs_info->tree_root,
				&reloc_root->root_key, root_item);
	BUG_ON(ret);
	btrfs_put_root(reloc_root);
out:
	return 0;
}

/*
 * helper to find first cached inode with inode number >= objectid
 * in a subvolume
 */
static struct inode *find_next_inode(struct btrfs_root *root, u64 objectid)
{
	struct rb_node *node;
	struct rb_node *prev;
	struct btrfs_inode *entry;
	struct inode *inode;

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

		if (objectid < btrfs_ino(entry))
			node = node->rb_left;
		else if (objectid > btrfs_ino(entry))
			node = node->rb_right;
		else
			break;
	}
	if (!node) {
		while (prev) {
			entry = rb_entry(prev, struct btrfs_inode, rb_node);
			if (objectid <= btrfs_ino(entry)) {
				node = prev;
				break;
			}
			prev = rb_next(prev);
		}
	}
	while (node) {
		entry = rb_entry(node, struct btrfs_inode, rb_node);
		inode = igrab(&entry->vfs_inode);
		if (inode) {
			spin_unlock(&root->inode_lock);
			return inode;
		}

		objectid = btrfs_ino(entry) + 1;
		if (cond_resched_lock(&root->inode_lock))
			goto again;

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

/*
 * get new location of data
 */
static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr,
			    u64 bytenr, u64 num_bytes)
{
	struct btrfs_root *root = BTRFS_I(reloc_inode)->root;
	struct btrfs_path *path;
	struct btrfs_file_extent_item *fi;
	struct extent_buffer *leaf;
	int ret;

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

	bytenr -= BTRFS_I(reloc_inode)->index_cnt;
	ret = btrfs_lookup_file_extent(NULL, root, path,
			btrfs_ino(BTRFS_I(reloc_inode)), bytenr, 0);
	if (ret < 0)
		goto out;
	if (ret > 0) {
		ret = -ENOENT;
		goto out;
	}

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

	BUG_ON(btrfs_file_extent_offset(leaf, fi) ||
	       btrfs_file_extent_compression(leaf, fi) ||
	       btrfs_file_extent_encryption(leaf, fi) ||
	       btrfs_file_extent_other_encoding(leaf, fi));

	if (num_bytes != btrfs_file_extent_disk_num_bytes(leaf, fi)) {
		ret = -EINVAL;
		goto out;
	}

	*new_bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
	ret = 0;
out:
	btrfs_free_path(path);
	return ret;
}

/*
 * update file extent items in the tree leaf to point to
 * the new locations.
 */
static noinline_for_stack
int replace_file_extents(struct btrfs_trans_handle *trans,
			 struct reloc_control *rc,
			 struct btrfs_root *root,
			 struct extent_buffer *leaf)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_key key;
	struct btrfs_file_extent_item *fi;
	struct inode *inode = NULL;
	u64 parent;
	u64 bytenr;
	u64 new_bytenr = 0;
	u64 num_bytes;
	u64 end;
	u32 nritems;
	u32 i;
	int ret = 0;
	int first = 1;
	int dirty = 0;

	if (rc->stage != UPDATE_DATA_PTRS)
		return 0;

	/* reloc trees always use full backref */
	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
		parent = leaf->start;
	else
		parent = 0;

	nritems = btrfs_header_nritems(leaf);
	for (i = 0; i < nritems; i++) {
		struct btrfs_ref ref = { 0 };

		cond_resched();
		btrfs_item_key_to_cpu(leaf, &key, i);
		if (key.type != BTRFS_EXTENT_DATA_KEY)
			continue;
		fi = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
		if (btrfs_file_extent_type(leaf, fi) ==
		    BTRFS_FILE_EXTENT_INLINE)
			continue;
		bytenr = btrfs_file_extent_disk_bytenr(leaf, fi);
		num_bytes = btrfs_file_extent_disk_num_bytes(leaf, fi);
		if (bytenr == 0)
			continue;
		if (!in_range(bytenr, rc->block_group->start,
			      rc->block_group->length))
			continue;

		/*
		 * if we are modifying block in fs tree, wait for readpage
		 * to complete and drop the extent cache
		 */
		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
			if (first) {
				inode = find_next_inode(root, key.objectid);
				first = 0;
			} else if (inode && btrfs_ino(BTRFS_I(inode)) < key.objectid) {
				btrfs_add_delayed_iput(inode);
				inode = find_next_inode(root, key.objectid);
			}
			if (inode && btrfs_ino(BTRFS_I(inode)) == key.objectid) {
				end = key.offset +
				      btrfs_file_extent_num_bytes(leaf, fi);
				WARN_ON(!IS_ALIGNED(key.offset,
						    fs_info->sectorsize));
				WARN_ON(!IS_ALIGNED(end, fs_info->sectorsize));
				end--;
				ret = try_lock_extent(&BTRFS_I(inode)->io_tree,
						      key.offset, end);
				if (!ret)
					continue;

				btrfs_drop_extent_cache(BTRFS_I(inode),
						key.offset,	end, 1);
				unlock_extent(&BTRFS_I(inode)->io_tree,
					      key.offset, end);
			}
		}

		ret = get_new_location(rc->data_inode, &new_bytenr,
				       bytenr, num_bytes);
		if (ret) {
			/*
			 * Don't have to abort since we've not changed anything
			 * in the file extent yet.
			 */
			break;
		}

		btrfs_set_file_extent_disk_bytenr(leaf, fi, new_bytenr);
		dirty = 1;

		key.offset -= btrfs_file_extent_offset(leaf, fi);
		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr,
				       num_bytes, parent);
		ref.real_root = root->root_key.objectid;
		btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
				    key.objectid, key.offset);
		ret = btrfs_inc_extent_ref(trans, &ref);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			break;
		}

		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, bytenr,
				       num_bytes, parent);
		ref.real_root = root->root_key.objectid;
		btrfs_init_data_ref(&ref, btrfs_header_owner(leaf),
				    key.objectid, key.offset);
		ret = btrfs_free_extent(trans, &ref);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			break;
		}
	}
	if (dirty)
		btrfs_mark_buffer_dirty(leaf);
	if (inode)
		btrfs_add_delayed_iput(inode);
	return ret;
}

static noinline_for_stack
int memcmp_node_keys(struct extent_buffer *eb, int slot,
		     struct btrfs_path *path, int level)
{
	struct btrfs_disk_key key1;
	struct btrfs_disk_key key2;
	btrfs_node_key(eb, &key1, slot);
	btrfs_node_key(path->nodes[level], &key2, path->slots[level]);
	return memcmp(&key1, &key2, sizeof(key1));
}

/*
 * try to replace tree blocks in fs tree with the new blocks
 * in reloc tree. tree blocks haven't been modified since the
 * reloc tree was create can be replaced.
 *
 * if a block was replaced, level of the block + 1 is returned.
 * if no block got replaced, 0 is returned. if there are other
 * errors, a negative error number is returned.
 */
static noinline_for_stack
int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc,
		 struct btrfs_root *dest, struct btrfs_root *src,
		 struct btrfs_path *path, struct btrfs_key *next_key,
		 int lowest_level, int max_level)
{
	struct btrfs_fs_info *fs_info = dest->fs_info;
	struct extent_buffer *eb;
	struct extent_buffer *parent;
	struct btrfs_ref ref = { 0 };
	struct btrfs_key key;
	u64 old_bytenr;
	u64 new_bytenr;
	u64 old_ptr_gen;
	u64 new_ptr_gen;
	u64 last_snapshot;
	u32 blocksize;
	int cow = 0;
	int level;
	int ret;
	int slot;

	BUG_ON(src->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
	BUG_ON(dest->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID);

	last_snapshot = btrfs_root_last_snapshot(&src->root_item);
again:
	slot = path->slots[lowest_level];
	btrfs_node_key_to_cpu(path->nodes[lowest_level], &key, slot);

	eb = btrfs_lock_root_node(dest);
	level = btrfs_header_level(eb);

	if (level < lowest_level) {
		btrfs_tree_unlock(eb);
		free_extent_buffer(eb);
		return 0;
	}

	if (cow) {
		ret = btrfs_cow_block(trans, dest, eb, NULL, 0, &eb,
				      BTRFS_NESTING_COW);
		BUG_ON(ret);
	}

	if (next_key) {
		next_key->objectid = (u64)-1;
		next_key->type = (u8)-1;
		next_key->offset = (u64)-1;
	}

	parent = eb;
	while (1) {
		level = btrfs_header_level(parent);
		BUG_ON(level < lowest_level);

		ret = btrfs_bin_search(parent, &key, &slot);
		if (ret < 0)
			break;
		if (ret && slot > 0)
			slot--;

		if (next_key && slot + 1 < btrfs_header_nritems(parent))
			btrfs_node_key_to_cpu(parent, next_key, slot + 1);

		old_bytenr = btrfs_node_blockptr(parent, slot);
		blocksize = fs_info->nodesize;
		old_ptr_gen = btrfs_node_ptr_generation(parent, slot);

		if (level <= max_level) {
			eb = path->nodes[level];
			new_bytenr = btrfs_node_blockptr(eb,
							path->slots[level]);
			new_ptr_gen = btrfs_node_ptr_generation(eb,
							path->slots[level]);
		} else {
			new_bytenr = 0;
			new_ptr_gen = 0;
		}

		if (WARN_ON(new_bytenr > 0 && new_bytenr == old_bytenr)) {
			ret = level;
			break;
		}

		if (new_bytenr == 0 || old_ptr_gen > last_snapshot ||
		    memcmp_node_keys(parent, slot, path, level)) {
			if (level <= lowest_level) {
				ret = 0;
				break;
			}

			eb = btrfs_read_node_slot(parent, slot);
			if (IS_ERR(eb)) {
				ret = PTR_ERR(eb);
				break;
			}
			btrfs_tree_lock(eb);
			if (cow) {
				ret = btrfs_cow_block(trans, dest, eb, parent,
						      slot, &eb,
						      BTRFS_NESTING_COW);
				BUG_ON(ret);
			}

			btrfs_tree_unlock(parent);
			free_extent_buffer(parent);

			parent = eb;
			continue;
		}

		if (!cow) {
			btrfs_tree_unlock(parent);
			free_extent_buffer(parent);
			cow = 1;
			goto again;
		}

		btrfs_node_key_to_cpu(path->nodes[level], &key,
				      path->slots[level]);
		btrfs_release_path(path);

		path->lowest_level = level;
		ret = btrfs_search_slot(trans, src, &key, path, 0, 1);
		path->lowest_level = 0;
		BUG_ON(ret);

		/*
		 * Info qgroup to trace both subtrees.
		 *
		 * We must trace both trees.
		 * 1) Tree reloc subtree
		 *    If not traced, we will leak data numbers
		 * 2) Fs subtree
		 *    If not traced, we will double count old data
		 *
		 * We don't scan the subtree right now, but only record
		 * the swapped tree blocks.
		 * The real subtree rescan is delayed until we have new
		 * CoW on the subtree root node before transaction commit.
		 */
		ret = btrfs_qgroup_add_swapped_blocks(trans, dest,
				rc->block_group, parent, slot,
				path->nodes[level], path->slots[level],
				last_snapshot);
		if (ret < 0)
			break;
		/*
		 * swap blocks in fs tree and reloc tree.
		 */
		btrfs_set_node_blockptr(parent, slot, new_bytenr);
		btrfs_set_node_ptr_generation(parent, slot, new_ptr_gen);
		btrfs_mark_buffer_dirty(parent);

		btrfs_set_node_blockptr(path->nodes[level],
					path->slots[level], old_bytenr);
		btrfs_set_node_ptr_generation(path->nodes[level],
					      path->slots[level], old_ptr_gen);
		btrfs_mark_buffer_dirty(path->nodes[level]);

		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, old_bytenr,
				       blocksize, path->nodes[level]->start);
		ref.skip_qgroup = true;
		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
		ret = btrfs_inc_extent_ref(trans, &ref);
		BUG_ON(ret);
		btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF, new_bytenr,
				       blocksize, 0);
		ref.skip_qgroup = true;
		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
		ret = btrfs_inc_extent_ref(trans, &ref);
		BUG_ON(ret);

		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, new_bytenr,
				       blocksize, path->nodes[level]->start);
		btrfs_init_tree_ref(&ref, level - 1, src->root_key.objectid);
		ref.skip_qgroup = true;
		ret = btrfs_free_extent(trans, &ref);
		BUG_ON(ret);

		btrfs_init_generic_ref(&ref, BTRFS_DROP_DELAYED_REF, old_bytenr,
				       blocksize, 0);
		btrfs_init_tree_ref(&ref, level - 1, dest->root_key.objectid);
		ref.skip_qgroup = true;
		ret = btrfs_free_extent(trans, &ref);
		BUG_ON(ret);

		btrfs_unlock_up_safe(path, 0);

		ret = level;
		break;
	}
	btrfs_tree_unlock(parent);
	free_extent_buffer(parent);
	return ret;
}

/*
 * helper to find next relocated block in reloc tree
 */
static noinline_for_stack
int walk_up_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
		       int *level)
{
	struct extent_buffer *eb;
	int i;
	u64 last_snapshot;
	u32 nritems;

	last_snapshot = btrfs_root_last_snapshot(&root->root_item);

	for (i = 0; i < *level; i++) {
		free_extent_buffer(path->nodes[i]);
		path->nodes[i] = NULL;
	}

	for (i = *level; i < BTRFS_MAX_LEVEL && path->nodes[i]; i++) {
		eb = path->nodes[i];
		nritems = btrfs_header_nritems(eb);
		while (path->slots[i] + 1 < nritems) {
			path->slots[i]++;
			if (btrfs_node_ptr_generation(eb, path->slots[i]) <=
			    last_snapshot)
				continue;

			*level = i;
			return 0;
		}
		free_extent_buffer(path->nodes[i]);
		path->nodes[i] = NULL;
	}
	return 1;
}

/*
 * walk down reloc tree to find relocated block of lowest level
 */
static noinline_for_stack
int walk_down_reloc_tree(struct btrfs_root *root, struct btrfs_path *path,
			 int *level)
{
	struct extent_buffer *eb = NULL;
	int i;
	u64 ptr_gen = 0;
	u64 last_snapshot;
	u32 nritems;

	last_snapshot = btrfs_root_last_snapshot(&root->root_item);

	for (i = *level; i > 0; i--) {
		eb = path->nodes[i];
		nritems = btrfs_header_nritems(eb);
		while (path->slots[i] < nritems) {
			ptr_gen = btrfs_node_ptr_generation(eb, path->slots[i]);
			if (ptr_gen > last_snapshot)
				break;
			path->slots[i]++;
		}
		if (path->slots[i] >= nritems) {
			if (i == *level)
				break;
			*level = i + 1;
			return 0;
		}
		if (i == 1) {
			*level = i;
			return 0;
		}

		eb = btrfs_read_node_slot(eb, path->slots[i]);
		if (IS_ERR(eb))
			return PTR_ERR(eb);
		BUG_ON(btrfs_header_level(eb) != i - 1);
		path->nodes[i - 1] = eb;
		path->slots[i - 1] = 0;
	}
	return 1;
}

/*
 * invalidate extent cache for file extents whose key in range of
 * [min_key, max_key)
 */
static int invalidate_extent_cache(struct btrfs_root *root,
				   struct btrfs_key *min_key,
				   struct btrfs_key *max_key)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct inode *inode = NULL;
	u64 objectid;
	u64 start, end;
	u64 ino;

	objectid = min_key->objectid;
	while (1) {
		cond_resched();
		iput(inode);

		if (objectid > max_key->objectid)
			break;

		inode = find_next_inode(root, objectid);
		if (!inode)
			break;
		ino = btrfs_ino(BTRFS_I(inode));

		if (ino > max_key->objectid) {
			iput(inode);
			break;
		}

		objectid = ino + 1;
		if (!S_ISREG(inode->i_mode))
			continue;

		if (unlikely(min_key->objectid == ino)) {
			if (min_key->type > BTRFS_EXTENT_DATA_KEY)
				continue;
			if (min_key->type < BTRFS_EXTENT_DATA_KEY)
				start = 0;
			else {
				start = min_key->offset;
				WARN_ON(!IS_ALIGNED(start, fs_info->sectorsize));
			}
		} else {
			start = 0;
		}

		if (unlikely(max_key->objectid == ino)) {
			if (max_key->type < BTRFS_EXTENT_DATA_KEY)
				continue;
			if (max_key->type > BTRFS_EXTENT_DATA_KEY) {
				end = (u64)-1;
			} else {
				if (max_key->offset == 0)
					continue;
				end = max_key->offset;
				WARN_ON(!IS_ALIGNED(end, fs_info->sectorsize));
				end--;
			}
		} else {
			end = (u64)-1;
		}

		/* the lock_extent waits for readpage to complete */
		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 1);
		unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
	}
	return 0;
}

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

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

/*
 * Insert current subvolume into reloc_control::dirty_subvol_roots
 */
static void insert_dirty_subvol(struct btrfs_trans_handle *trans,
				struct reloc_control *rc,
				struct btrfs_root *root)
{
	struct btrfs_root *reloc_root = root->reloc_root;
	struct btrfs_root_item *reloc_root_item;

	/* @root must be a subvolume tree root with a valid reloc tree */
	ASSERT(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID);
	ASSERT(reloc_root);

	reloc_root_item = &reloc_root->root_item;
	memset(&reloc_root_item->drop_progress, 0,
		sizeof(reloc_root_item->drop_progress));
	btrfs_set_root_drop_level(reloc_root_item, 0);
	btrfs_set_root_refs(reloc_root_item, 0);
	btrfs_update_reloc_root(trans, root);

	if (list_empty(&root->reloc_dirty_list)) {
		btrfs_grab_root(root);
		list_add_tail(&root->reloc_dirty_list, &rc->dirty_subvol_roots);
	}
}

static int clean_dirty_subvols(struct reloc_control *rc)
{
	struct btrfs_root *root;
	struct btrfs_root *next;
	int ret = 0;
	int ret2;

	list_for_each_entry_safe(root, next, &rc->dirty_subvol_roots,
				 reloc_dirty_list) {
		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID) {
			/* Merged subvolume, cleanup its reloc root */
			struct btrfs_root *reloc_root = root->reloc_root;

			list_del_init(&root->reloc_dirty_list);
			root->reloc_root = NULL;
			/*
			 * Need barrier to ensure clear_bit() only happens after
			 * root->reloc_root = NULL. Pairs with have_reloc_root.
			 */
			smp_wmb();
			clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE, &root->state);
			if (reloc_root) {
				/*
				 * btrfs_drop_snapshot drops our ref we hold for
				 * ->reloc_root.  If it fails however we must
				 * drop the ref ourselves.
				 */
				ret2 = btrfs_drop_snapshot(reloc_root, 0, 1);
				if (ret2 < 0) {
					btrfs_put_root(reloc_root);
					if (!ret)
						ret = ret2;
				}
			}
			btrfs_put_root(root);
		} else {
			/* Orphan reloc tree, just clean it up */
			ret2 = btrfs_drop_snapshot(root, 0, 1);
			if (ret2 < 0) {
				btrfs_put_root(root);
				if (!ret)
					ret = ret2;
			}
		}
	}
	return ret;
}

/*
 * merge the relocated tree blocks in reloc tree with corresponding
 * fs tree.
 */
static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
					       struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct btrfs_key key;
	struct btrfs_key next_key;
	struct btrfs_trans_handle *trans = NULL;
	struct btrfs_root *reloc_root;
	struct btrfs_root_item *root_item;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	int reserve_level;
	int level;
	int max_level;
	int replaced = 0;
	int ret = 0;
	u32 min_reserved;

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

	reloc_root = root->reloc_root;
	root_item = &reloc_root->root_item;

	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
		level = btrfs_root_level(root_item);
		atomic_inc(&reloc_root->node->refs);
		path->nodes[level] = reloc_root->node;
		path->slots[level] = 0;
	} else {
		btrfs_disk_key_to_cpu(&key, &root_item->drop_progress);

		level = btrfs_root_drop_level(root_item);
		BUG_ON(level == 0);
		path->lowest_level = level;
		ret = btrfs_search_slot(NULL, reloc_root, &key, path, 0, 0);
		path->lowest_level = 0;
		if (ret < 0) {
			btrfs_free_path(path);
			return ret;
		}

		btrfs_node_key_to_cpu(path->nodes[level], &next_key,
				      path->slots[level]);
		WARN_ON(memcmp(&key, &next_key, sizeof(key)));

		btrfs_unlock_up_safe(path, 0);
	}

	/*
	 * In merge_reloc_root(), we modify the upper level pointer to swap the
	 * tree blocks between reloc tree and subvolume tree.  Thus for tree
	 * block COW, we COW at most from level 1 to root level for each tree.
	 *
	 * Thus the needed metadata size is at most root_level * nodesize,
	 * and * 2 since we have two trees to COW.
	 */
	reserve_level = max_t(int, 1, btrfs_root_level(root_item));
	min_reserved = fs_info->nodesize * reserve_level * 2;
	memset(&next_key, 0, sizeof(next_key));

	while (1) {
		ret = btrfs_block_rsv_refill(root, rc->block_rsv, min_reserved,
					     BTRFS_RESERVE_FLUSH_LIMIT);
		if (ret)
			goto out;
		trans = btrfs_start_transaction(root, 0);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			trans = NULL;
			goto out;
		}

		/*
		 * At this point we no longer have a reloc_control, so we can't
		 * depend on btrfs_init_reloc_root to update our last_trans.
		 *
		 * But that's ok, we started the trans handle on our
		 * corresponding fs_root, which means it's been added to the
		 * dirty list.  At commit time we'll still call
		 * btrfs_update_reloc_root() and update our root item
		 * appropriately.
		 */
		reloc_root->last_trans = trans->transid;
		trans->block_rsv = rc->block_rsv;

		replaced = 0;
		max_level = level;

		ret = walk_down_reloc_tree(reloc_root, path, &level);
		if (ret < 0)
			goto out;
		if (ret > 0)
			break;

		if (!find_next_key(path, level, &key) &&
		    btrfs_comp_cpu_keys(&next_key, &key) >= 0) {
			ret = 0;
		} else {
			ret = replace_path(trans, rc, root, reloc_root, path,
					   &next_key, level, max_level);
		}
		if (ret < 0)
			goto out;
		if (ret > 0) {
			level = ret;
			btrfs_node_key_to_cpu(path->nodes[level], &key,
					      path->slots[level]);
			replaced = 1;
		}

		ret = walk_up_reloc_tree(reloc_root, path, &level);
		if (ret > 0)
			break;

		BUG_ON(level == 0);
		/*
		 * save the merging progress in the drop_progress.
		 * this is OK since root refs == 1 in this case.
		 */
		btrfs_node_key(path->nodes[level], &root_item->drop_progress,
			       path->slots[level]);
		btrfs_set_root_drop_level(root_item, level);

		btrfs_end_transaction_throttle(trans);
		trans = NULL;

		btrfs_btree_balance_dirty(fs_info);

		if (replaced && rc->stage == UPDATE_DATA_PTRS)
			invalidate_extent_cache(root, &key, &next_key);
	}

	/*
	 * handle the case only one block in the fs tree need to be
	 * relocated and the block is tree root.
	 */
	leaf = btrfs_lock_root_node(root);
	ret = btrfs_cow_block(trans, root, leaf, NULL, 0, &leaf,
			      BTRFS_NESTING_COW);
	btrfs_tree_unlock(leaf);
	free_extent_buffer(leaf);
out:
	btrfs_free_path(path);

	if (ret == 0)
		insert_dirty_subvol(trans, rc, root);

	if (trans)
		btrfs_end_transaction_throttle(trans);

	btrfs_btree_balance_dirty(fs_info);

	if (replaced && rc->stage == UPDATE_DATA_PTRS)
		invalidate_extent_cache(root, &key, &next_key);

	return ret;
}

static noinline_for_stack
int prepare_to_merge(struct reloc_control *rc, int err)
{
	struct btrfs_root *root = rc->extent_root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_root *reloc_root;
	struct btrfs_trans_handle *trans;
	LIST_HEAD(reloc_roots);
	u64 num_bytes = 0;
	int ret;

	mutex_lock(&fs_info->reloc_mutex);
	rc->merging_rsv_size += fs_info->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
	rc->merging_rsv_size += rc->nodes_relocated * 2;
	mutex_unlock(&fs_info->reloc_mutex);

again:
	if (!err) {
		num_bytes = rc->merging_rsv_size;
		ret = btrfs_block_rsv_add(root, rc->block_rsv, num_bytes,
					  BTRFS_RESERVE_FLUSH_ALL);
		if (ret)
			err = ret;
	}

	trans = btrfs_join_transaction(rc->extent_root);
	if (IS_ERR(trans)) {
		if (!err)
			btrfs_block_rsv_release(fs_info, rc->block_rsv,
						num_bytes, NULL);
		return PTR_ERR(trans);
	}

	if (!err) {
		if (num_bytes != rc->merging_rsv_size) {
			btrfs_end_transaction(trans);
			btrfs_block_rsv_release(fs_info, rc->block_rsv,
						num_bytes, NULL);
			goto again;
		}
	}

	rc->merge_reloc_tree = 1;

	while (!list_empty(&rc->reloc_roots)) {
		reloc_root = list_entry(rc->reloc_roots.next,
					struct btrfs_root, root_list);
		list_del_init(&reloc_root->root_list);

		root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
				false);
		BUG_ON(IS_ERR(root));
		BUG_ON(root->reloc_root != reloc_root);

		/*
		 * set reference count to 1, so btrfs_recover_relocation
		 * knows it should resumes merging
		 */
		if (!err)
			btrfs_set_root_refs(&reloc_root->root_item, 1);
		btrfs_update_reloc_root(trans, root);

		list_add(&reloc_root->root_list, &reloc_roots);
		btrfs_put_root(root);
	}

	list_splice(&reloc_roots, &rc->reloc_roots);

	if (!err)
		btrfs_commit_transaction(trans);
	else
		btrfs_end_transaction(trans);
	return err;
}

static noinline_for_stack
void free_reloc_roots(struct list_head *list)
{
	struct btrfs_root *reloc_root, *tmp;

	list_for_each_entry_safe(reloc_root, tmp, list, root_list)
		__del_reloc_root(reloc_root);
}

static noinline_for_stack
void merge_reloc_roots(struct reloc_control *rc)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct btrfs_root *root;
	struct btrfs_root *reloc_root;
	LIST_HEAD(reloc_roots);
	int found = 0;
	int ret = 0;
again:
	root = rc->extent_root;

	/*
	 * this serializes us with btrfs_record_root_in_transaction,
	 * we have to make sure nobody is in the middle of
	 * adding their roots to the list while we are
	 * doing this splice
	 */
	mutex_lock(&fs_info->reloc_mutex);
	list_splice_init(&rc->reloc_roots, &reloc_roots);
	mutex_unlock(&fs_info->reloc_mutex);

	while (!list_empty(&reloc_roots)) {
		found = 1;
		reloc_root = list_entry(reloc_roots.next,
					struct btrfs_root, root_list);

		root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
					 false);
		if (btrfs_root_refs(&reloc_root->root_item) > 0) {
			BUG_ON(IS_ERR(root));
			BUG_ON(root->reloc_root != reloc_root);
			ret = merge_reloc_root(rc, root);
			btrfs_put_root(root);
			if (ret) {
				if (list_empty(&reloc_root->root_list))
					list_add_tail(&reloc_root->root_list,
						      &reloc_roots);
				goto out;
			}
		} else {
			if (!IS_ERR(root)) {
				if (root->reloc_root == reloc_root) {
					root->reloc_root = NULL;
					btrfs_put_root(reloc_root);
				}
				clear_bit(BTRFS_ROOT_DEAD_RELOC_TREE,
					  &root->state);
				btrfs_put_root(root);
			}

			list_del_init(&reloc_root->root_list);
			/* Don't forget to queue this reloc root for cleanup */
			list_add_tail(&reloc_root->reloc_dirty_list,
				      &rc->dirty_subvol_roots);
		}
	}

	if (found) {
		found = 0;
		goto again;
	}
out:
	if (ret) {
		btrfs_handle_fs_error(fs_info, ret, NULL);
		free_reloc_roots(&reloc_roots);

		/* new reloc root may be added */
		mutex_lock(&fs_info->reloc_mutex);
		list_splice_init(&rc->reloc_roots, &reloc_roots);
		mutex_unlock(&fs_info->reloc_mutex);
		free_reloc_roots(&reloc_roots);
	}

	/*
	 * We used to have
	 *
	 * BUG_ON(!RB_EMPTY_ROOT(&rc->reloc_root_tree.rb_root));
	 *
	 * here, but it's wrong.  If we fail to start the transaction in
	 * prepare_to_merge() we will have only 0 ref reloc roots, none of which
	 * have actually been removed from the reloc_root_tree rb tree.  This is
	 * fine because we're bailing here, and we hold a reference on the root
	 * for the list that holds it, so these roots will be cleaned up when we
	 * do the reloc_dirty_list afterwards.  Meanwhile the root->reloc_root
	 * will be cleaned up on unmount.
	 *
	 * The remaining nodes will be cleaned up by free_reloc_control.
	 */
}

static void free_block_list(struct rb_root *blocks)
{
	struct tree_block *block;
	struct rb_node *rb_node;
	while ((rb_node = rb_first(blocks))) {
		block = rb_entry(rb_node, struct tree_block, rb_node);
		rb_erase(rb_node, blocks);
		kfree(block);
	}
}

static int record_reloc_root_in_trans(struct btrfs_trans_handle *trans,
				      struct btrfs_root *reloc_root)
{
	struct btrfs_fs_info *fs_info = reloc_root->fs_info;
	struct btrfs_root *root;
	int ret;

	if (reloc_root->last_trans == trans->transid)
		return 0;

	root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset, false);
	BUG_ON(IS_ERR(root));
	BUG_ON(root->reloc_root != reloc_root);
	ret = btrfs_record_root_in_trans(trans, root);
	btrfs_put_root(root);

	return ret;
}

static noinline_for_stack
struct btrfs_root *select_reloc_root(struct btrfs_trans_handle *trans,
				     struct reloc_control *rc,
				     struct btrfs_backref_node *node,
				     struct btrfs_backref_edge *edges[])
{
	struct btrfs_backref_node *next;
	struct btrfs_root *root;
	int index = 0;

	next = node;
	while (1) {
		cond_resched();
		next = walk_up_backref(next, edges, &index);
		root = next->root;
		BUG_ON(!root);
		BUG_ON(!test_bit(BTRFS_ROOT_SHAREABLE, &root->state));

		if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) {
			record_reloc_root_in_trans(trans, root);
			break;
		}

		btrfs_record_root_in_trans(trans, root);
		root = root->reloc_root;

		if (next->new_bytenr != root->node->start) {
			BUG_ON(next->new_bytenr);
			BUG_ON(!list_empty(&next->list));
			next->new_bytenr = root->node->start;
			btrfs_put_root(next->root);
			next->root = btrfs_grab_root(root);
			ASSERT(next->root);
			list_add_tail(&next->list,
				      &rc->backref_cache.changed);
			mark_block_processed(rc, next);
			break;
		}

		WARN_ON(1);
		root = NULL;
		next = walk_down_backref(edges, &index);
		if (!next || next->level <= node->level)
			break;
	}
	if (!root)
		return NULL;

	next = node;
	/* setup backref node path for btrfs_reloc_cow_block */
	while (1) {
		rc->backref_cache.path[next->level] = next;
		if (--index < 0)
			break;
		next = edges[index]->node[UPPER];
	}
	return root;
}

/*
 * Select a tree root for relocation.
 *
 * Return NULL if the block is not shareable. We should use do_relocation() in
 * this case.
 *
 * Return a tree root pointer if the block is shareable.
 * Return -ENOENT if the block is root of reloc tree.
 */
static noinline_for_stack
struct btrfs_root *select_one_root(struct btrfs_backref_node *node)
{
	struct btrfs_backref_node *next;
	struct btrfs_root *root;
	struct btrfs_root *fs_root = NULL;
	struct btrfs_backref_edge *edges[BTRFS_MAX_LEVEL - 1];
	int index = 0;

	next = node;
	while (1) {
		cond_resched();
		next = walk_up_backref(next, edges, &index);
		root = next->root;
		BUG_ON(!root);

		/* No other choice for non-shareable tree */
		if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
			return root;

		if (root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID)
			fs_root = root;

		if (next != node)
			return NULL;

		next = walk_down_backref(edges, &index);
		if (!next || next->level <= node->level)
			break;
	}

	if (!fs_root)
		return ERR_PTR(-ENOENT);
	return fs_root;
}

static noinline_for_stack
u64 calcu_metadata_size(struct reloc_control *rc,
			struct btrfs_backref_node *node, int reserve)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct btrfs_backref_node *next = node;
	struct btrfs_backref_edge *edge;
	struct btrfs_backref_edge *edges[BTRFS_MAX_LEVEL - 1];
	u64 num_bytes = 0;
	int index = 0;

	BUG_ON(reserve && node->processed);

	while (next) {
		cond_resched();
		while (1) {
			if (next->processed && (reserve || next != node))
				break;

			num_bytes += fs_info->nodesize;

			if (list_empty(&next->upper))
				break;

			edge = list_entry(next->upper.next,
					struct btrfs_backref_edge, list[LOWER]);
			edges[index++] = edge;
			next = edge->node[UPPER];
		}
		next = walk_down_backref(edges, &index);
	}
	return num_bytes;
}

static int reserve_metadata_space(struct btrfs_trans_handle *trans,
				  struct reloc_control *rc,
				  struct btrfs_backref_node *node)
{
	struct btrfs_root *root = rc->extent_root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	u64 num_bytes;
	int ret;
	u64 tmp;

	num_bytes = calcu_metadata_size(rc, node, 1) * 2;

	trans->block_rsv = rc->block_rsv;
	rc->reserved_bytes += num_bytes;

	/*
	 * We are under a transaction here so we can only do limited flushing.
	 * If we get an enospc just kick back -EAGAIN so we know to drop the
	 * transaction and try to refill when we can flush all the things.
	 */
	ret = btrfs_block_rsv_refill(root, rc->block_rsv, num_bytes,
				BTRFS_RESERVE_FLUSH_LIMIT);
	if (ret) {
		tmp = fs_info->nodesize * RELOCATION_RESERVED_NODES;
		while (tmp <= rc->reserved_bytes)
			tmp <<= 1;
		/*
		 * only one thread can access block_rsv at this point,
		 * so we don't need hold lock to protect block_rsv.
		 * we expand more reservation size here to allow enough
		 * space for relocation and we will return earlier in
		 * enospc case.
		 */
		rc->block_rsv->size = tmp + fs_info->nodesize *
				      RELOCATION_RESERVED_NODES;
		return -EAGAIN;
	}

	return 0;
}

/*
 * relocate a block tree, and then update pointers in upper level
 * blocks that reference the block to point to the new location.
 *
 * if called by link_to_upper, the block has already been relocated.
 * in that case this function just updates pointers.
 */
static int do_relocation(struct btrfs_trans_handle *trans,
			 struct reloc_control *rc,
			 struct btrfs_backref_node *node,
			 struct btrfs_key *key,
			 struct btrfs_path *path, int lowest)
{
	struct btrfs_backref_node *upper;
	struct btrfs_backref_edge *edge;
	struct btrfs_backref_edge *edges[BTRFS_MAX_LEVEL - 1];
	struct btrfs_root *root;
	struct extent_buffer *eb;
	u32 blocksize;
	u64 bytenr;
	int slot;
	int ret = 0;

	BUG_ON(lowest && node->eb);

	path->lowest_level = node->level + 1;
	rc->backref_cache.path[node->level] = node;
	list_for_each_entry(edge, &node->upper, list[LOWER]) {
		struct btrfs_ref ref = { 0 };

		cond_resched();

		upper = edge->node[UPPER];
		root = select_reloc_root(trans, rc, upper, edges);
		BUG_ON(!root);

		if (upper->eb && !upper->locked) {
			if (!lowest) {
				ret = btrfs_bin_search(upper->eb, key, &slot);
				if (ret < 0)
					goto next;
				BUG_ON(ret);
				bytenr = btrfs_node_blockptr(upper->eb, slot);
				if (node->eb->start == bytenr)
					goto next;
			}
			btrfs_backref_drop_node_buffer(upper);
		}

		if (!upper->eb) {
			ret = btrfs_search_slot(trans, root, key, path, 0, 1);
			if (ret) {
				if (ret > 0)
					ret = -ENOENT;

				btrfs_release_path(path);
				break;
			}

			if (!upper->eb) {
				upper->eb = path->nodes[upper->level];
				path->nodes[upper->level] = NULL;
			} else {
				BUG_ON(upper->eb != path->nodes[upper->level]);
			}

			upper->locked = 1;
			path->locks[upper->level] = 0;

			slot = path->slots[upper->level];
			btrfs_release_path(path);
		} else {
			ret = btrfs_bin_search(upper->eb, key, &slot);
			if (ret < 0)
				goto next;
			BUG_ON(ret);
		}

		bytenr = btrfs_node_blockptr(upper->eb, slot);
		if (lowest) {
			if (bytenr != node->bytenr) {
				btrfs_err(root->fs_info,
		"lowest leaf/node mismatch: bytenr %llu node->bytenr %llu slot %d upper %llu",
					  bytenr, node->bytenr, slot,
					  upper->eb->start);
				ret = -EIO;
				goto next;
			}
		} else {
			if (node->eb->start == bytenr)
				goto next;
		}

		blocksize = root->fs_info->nodesize;
		eb = btrfs_read_node_slot(upper->eb, slot);
		if (IS_ERR(eb)) {
			ret = PTR_ERR(eb);
			goto next;
		}
		btrfs_tree_lock(eb);

		if (!node->eb) {
			ret = btrfs_cow_block(trans, root, eb, upper->eb,
					      slot, &eb, BTRFS_NESTING_COW);
			btrfs_tree_unlock(eb);
			free_extent_buffer(eb);
			if (ret < 0)
				goto next;
			BUG_ON(node->eb != eb);
		} else {
			btrfs_set_node_blockptr(upper->eb, slot,
						node->eb->start);
			btrfs_set_node_ptr_generation(upper->eb, slot,
						      trans->transid);
			btrfs_mark_buffer_dirty(upper->eb);

			btrfs_init_generic_ref(&ref, BTRFS_ADD_DELAYED_REF,
					       node->eb->start, blocksize,
					       upper->eb->start);
			ref.real_root = root->root_key.objectid;
			btrfs_init_tree_ref(&ref, node->level,
					    btrfs_header_owner(upper->eb));
			ret = btrfs_inc_extent_ref(trans, &ref);
			BUG_ON(ret);

			ret = btrfs_drop_subtree(trans, root, eb, upper->eb);
			BUG_ON(ret);
		}
next:
		if (!upper->pending)
			btrfs_backref_drop_node_buffer(upper);
		else
			btrfs_backref_unlock_node_buffer(upper);
		if (ret)
			break;
	}

	if (!ret && node->pending) {
		btrfs_backref_drop_node_buffer(node);
		list_move_tail(&node->list, &rc->backref_cache.changed);
		node->pending = 0;
	}

	path->lowest_level = 0;
	BUG_ON(ret == -ENOSPC);
	return ret;
}

static int link_to_upper(struct btrfs_trans_handle *trans,
			 struct reloc_control *rc,
			 struct btrfs_backref_node *node,
			 struct btrfs_path *path)
{
	struct btrfs_key key;

	btrfs_node_key_to_cpu(node->eb, &key, 0);
	return do_relocation(trans, rc, node, &key, path, 0);
}

static int finish_pending_nodes(struct btrfs_trans_handle *trans,
				struct reloc_control *rc,
				struct btrfs_path *path, int err)
{
	LIST_HEAD(list);
	struct btrfs_backref_cache *cache = &rc->backref_cache;
	struct btrfs_backref_node *node;
	int level;
	int ret;

	for (level = 0; level < BTRFS_MAX_LEVEL; level++) {
		while (!list_empty(&cache->pending[level])) {
			node = list_entry(cache->pending[level].next,
					  struct btrfs_backref_node, list);
			list_move_tail(&node->list, &list);
			BUG_ON(!node->pending);

			if (!err) {
				ret = link_to_upper(trans, rc, node, path);
				if (ret < 0)
					err = ret;
			}
		}
		list_splice_init(&list, &cache->pending[level]);
	}
	return err;
}

/*
 * mark a block and all blocks directly/indirectly reference the block
 * as processed.
 */
static void update_processed_blocks(struct reloc_control *rc,
				    struct btrfs_backref_node *node)
{
	struct btrfs_backref_node *next = node;
	struct btrfs_backref_edge *edge;
	struct btrfs_backref_edge *edges[BTRFS_MAX_LEVEL - 1];
	int index = 0;

	while (next) {
		cond_resched();
		while (1) {
			if (next->processed)
				break;

			mark_block_processed(rc, next);

			if (list_empty(&next->upper))
				break;

			edge = list_entry(next->upper.next,
					struct btrfs_backref_edge, list[LOWER]);
			edges[index++] = edge;
			next = edge->node[UPPER];
		}
		next = walk_down_backref(edges, &index);
	}
}

static int tree_block_processed(u64 bytenr, struct reloc_control *rc)
{
	u32 blocksize = rc->extent_root->fs_info->nodesize;

	if (test_range_bit(&rc->processed_blocks, bytenr,
			   bytenr + blocksize - 1, EXTENT_DIRTY, 1, NULL))
		return 1;
	return 0;
}

static int get_tree_block_key(struct btrfs_fs_info *fs_info,
			      struct tree_block *block)
{
	struct extent_buffer *eb;

	eb = read_tree_block(fs_info, block->bytenr, block->owner,
			     block->key.offset, block->level, NULL);
	if (IS_ERR(eb)) {
		return PTR_ERR(eb);
	} else if (!extent_buffer_uptodate(eb)) {
		free_extent_buffer(eb);
		return -EIO;
	}
	if (block->level == 0)
		btrfs_item_key_to_cpu(eb, &block->key, 0);
	else
		btrfs_node_key_to_cpu(eb, &block->key, 0);
	free_extent_buffer(eb);
	block->key_ready = 1;
	return 0;
}

/*
 * helper function to relocate a tree block
 */
static int relocate_tree_block(struct btrfs_trans_handle *trans,
				struct reloc_control *rc,
				struct btrfs_backref_node *node,
				struct btrfs_key *key,
				struct btrfs_path *path)
{
	struct btrfs_root *root;
	int ret = 0;

	if (!node)
		return 0;

	/*
	 * If we fail here we want to drop our backref_node because we are going
	 * to start over and regenerate the tree for it.
	 */
	ret = reserve_metadata_space(trans, rc, node);
	if (ret)
		goto out;

	BUG_ON(node->processed);
	root = select_one_root(node);
	if (root == ERR_PTR(-ENOENT)) {
		update_processed_blocks(rc, node);
		goto out;
	}

	if (root) {
		if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) {
			BUG_ON(node->new_bytenr);
			BUG_ON(!list_empty(&node->list));
			btrfs_record_root_in_trans(trans, root);
			root = root->reloc_root;
			node->new_bytenr = root->node->start;
			btrfs_put_root(node->root);
			node->root = btrfs_grab_root(root);
			ASSERT(node->root);
			list_add_tail(&node->list, &rc->backref_cache.changed);
		} else {
			path->lowest_level = node->level;
			ret = btrfs_search_slot(trans, root, key, path, 0, 1);
			btrfs_release_path(path);
			if (ret > 0)
				ret = 0;
		}
		if (!ret)
			update_processed_blocks(rc, node);
	} else {
		ret = do_relocation(trans, rc, node, key, path, 1);
	}
out:
	if (ret || node->level == 0 || node->cowonly)
		btrfs_backref_cleanup_node(&rc->backref_cache, node);
	return ret;
}

/*
 * relocate a list of blocks
 */
static noinline_for_stack
int relocate_tree_blocks(struct btrfs_trans_handle *trans,
			 struct reloc_control *rc, struct rb_root *blocks)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct btrfs_backref_node *node;
	struct btrfs_path *path;
	struct tree_block *block;
	struct tree_block *next;
	int ret;
	int err = 0;

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

	/* Kick in readahead for tree blocks with missing keys */
	rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) {
		if (!block->key_ready)
			btrfs_readahead_tree_block(fs_info, block->bytenr,
						   block->owner, 0,
						   block->level);
	}

	/* Get first keys */
	rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) {
		if (!block->key_ready) {
			err = get_tree_block_key(fs_info, block);
			if (err)
				goto out_free_path;
		}
	}

	/* Do tree relocation */
	rbtree_postorder_for_each_entry_safe(block, next, blocks, rb_node) {
		node = build_backref_tree(rc, &block->key,
					  block->level, block->bytenr);
		if (IS_ERR(node)) {
			err = PTR_ERR(node);
			goto out;
		}

		ret = relocate_tree_block(trans, rc, node, &block->key,
					  path);
		if (ret < 0) {
			err = ret;
			break;
		}
	}
out:
	err = finish_pending_nodes(trans, rc, path, err);

out_free_path:
	btrfs_free_path(path);
out_free_blocks:
	free_block_list(blocks);
	return err;
}

static noinline_for_stack int prealloc_file_extent_cluster(
				struct btrfs_inode *inode,
				struct file_extent_cluster *cluster)
{
	u64 alloc_hint = 0;
	u64 start;
	u64 end;
	u64 offset = inode->index_cnt;
	u64 num_bytes;
	int nr;
	int ret = 0;
	u64 prealloc_start = cluster->start - offset;
	u64 prealloc_end = cluster->end - offset;
	u64 cur_offset = prealloc_start;

	BUG_ON(cluster->start != cluster->boundary[0]);
	ret = btrfs_alloc_data_chunk_ondemand(inode,
					      prealloc_end + 1 - prealloc_start);
	if (ret)
		return ret;

	/*
	 * On a zoned filesystem, we cannot preallocate the file region.
	 * Instead, we dirty and fiemap_write the region.
	 */
	if (btrfs_is_zoned(inode->root->fs_info)) {
		struct btrfs_root *root = inode->root;
		struct btrfs_trans_handle *trans;

		end = cluster->end - offset + 1;
		trans = btrfs_start_transaction(root, 1);
		if (IS_ERR(trans))
			return PTR_ERR(trans);

		inode->vfs_inode.i_ctime = current_time(&inode->vfs_inode);
		i_size_write(&inode->vfs_inode, end);
		ret = btrfs_update_inode(trans, root, inode);
		if (ret) {
			btrfs_abort_transaction(trans, ret);
			btrfs_end_transaction(trans);
			return ret;
		}

		return btrfs_end_transaction(trans);
	}

	inode_lock(&inode->vfs_inode);
	for (nr = 0; nr < cluster->nr; nr++) {
		start = cluster->boundary[nr] - offset;
		if (nr + 1 < cluster->nr)
			end = cluster->boundary[nr + 1] - 1 - offset;
		else
			end = cluster->end - offset;

		lock_extent(&inode->io_tree, start, end);
		num_bytes = end + 1 - start;
		ret = btrfs_prealloc_file_range(&inode->vfs_inode, 0, start,
						num_bytes, num_bytes,
						end + 1, &alloc_hint);
		cur_offset = end + 1;
		unlock_extent(&inode->io_tree, start, end);
		if (ret)
			break;
	}
	inode_unlock(&inode->vfs_inode);

	if (cur_offset < prealloc_end)
		btrfs_free_reserved_data_space_noquota(inode->root->fs_info,
					       prealloc_end + 1 - cur_offset);
	return ret;
}

static noinline_for_stack
int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
			 u64 block_start)
{
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	struct extent_map *em;
	int ret = 0;

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

	em->start = start;
	em->len = end + 1 - start;
	em->block_len = em->len;
	em->block_start = block_start;
	set_bit(EXTENT_FLAG_PINNED, &em->flags);

	lock_extent(&BTRFS_I(inode)->io_tree, start, end);
	while (1) {
		write_lock(&em_tree->lock);
		ret = add_extent_mapping(em_tree, em, 0);
		write_unlock(&em_tree->lock);
		if (ret != -EEXIST) {
			free_extent_map(em);
			break;
		}
		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
	}
	unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
	return ret;
}

/*
 * Allow error injection to test balance cancellation
 */
noinline int btrfs_should_cancel_balance(struct btrfs_fs_info *fs_info)
{
	return atomic_read(&fs_info->balance_cancel_req) ||
		fatal_signal_pending(current);
}
ALLOW_ERROR_INJECTION(btrfs_should_cancel_balance, TRUE);

static int relocate_file_extent_cluster(struct inode *inode,
					struct file_extent_cluster *cluster)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	u64 page_start;
	u64 page_end;
	u64 offset = BTRFS_I(inode)->index_cnt;
	unsigned long index;
	unsigned long last_index;
	struct page *page;
	struct file_ra_state *ra;
	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
	int nr = 0;
	int ret = 0;

	if (!cluster->nr)
		return 0;

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

	ret = prealloc_file_extent_cluster(BTRFS_I(inode), cluster);
	if (ret)
		goto out;

	file_ra_state_init(ra, inode->i_mapping);

	ret = setup_extent_mapping(inode, cluster->start - offset,
				   cluster->end - offset, cluster->start);
	if (ret)
		goto out;

	index = (cluster->start - offset) >> PAGE_SHIFT;
	last_index = (cluster->end - offset) >> PAGE_SHIFT;
	while (index <= last_index) {
		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
				PAGE_SIZE);
		if (ret)
			goto out;

		page = find_lock_page(inode->i_mapping, index);
		if (!page) {
			page_cache_sync_readahead(inode->i_mapping,
						  ra, NULL, index,
						  last_index + 1 - index);
			page = find_or_create_page(inode->i_mapping, index,
						   mask);
			if (!page) {
				btrfs_delalloc_release_metadata(BTRFS_I(inode),
							PAGE_SIZE, true);
				btrfs_delalloc_release_extents(BTRFS_I(inode),
							PAGE_SIZE);
				ret = -ENOMEM;
				goto out;
			}
		}
		ret = set_page_extent_mapped(page);
		if (ret < 0) {
			btrfs_delalloc_release_metadata(BTRFS_I(inode),
							PAGE_SIZE, true);
			btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
			unlock_page(page);
			put_page(page);
			goto out;
		}

		if (PageReadahead(page)) {
			page_cache_async_readahead(inode->i_mapping,
						   ra, NULL, page, index,
						   last_index + 1 - index);
		}

		if (!PageUptodate(page)) {
			btrfs_readpage(NULL, page);
			lock_page(page);
			if (!PageUptodate(page)) {
				unlock_page(page);
				put_page(page);
				btrfs_delalloc_release_metadata(BTRFS_I(inode),
							PAGE_SIZE, true);
				btrfs_delalloc_release_extents(BTRFS_I(inode),
							       PAGE_SIZE);
				ret = -EIO;
				goto out;
			}
		}

		page_start = page_offset(page);
		page_end = page_start + PAGE_SIZE - 1;

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

		if (nr < cluster->nr &&
		    page_start + offset == cluster->boundary[nr]) {
			set_extent_bits(&BTRFS_I(inode)->io_tree,
					page_start, page_end,
					EXTENT_BOUNDARY);
			nr++;
		}

		ret = btrfs_set_extent_delalloc(BTRFS_I(inode), page_start,
						page_end, 0, NULL);
		if (ret) {
			unlock_page(page);
			put_page(page);
			btrfs_delalloc_release_metadata(BTRFS_I(inode),
							 PAGE_SIZE, true);
			btrfs_delalloc_release_extents(BTRFS_I(inode),
			                               PAGE_SIZE);

			clear_extent_bits(&BTRFS_I(inode)->io_tree,
					  page_start, page_end,
					  EXTENT_LOCKED | EXTENT_BOUNDARY);
			goto out;

		}
		set_page_dirty(page);

		unlock_extent(&BTRFS_I(inode)->io_tree,
			      page_start, page_end);
		unlock_page(page);
		put_page(page);

		index++;
		btrfs_delalloc_release_extents(BTRFS_I(inode), PAGE_SIZE);
		balance_dirty_pages_ratelimited(inode->i_mapping);
		btrfs_throttle(fs_info);
		if (btrfs_should_cancel_balance(fs_info)) {
			ret = -ECANCELED;
			goto out;
		}
	}
	WARN_ON(nr != cluster->nr);
	if (btrfs_is_zoned(fs_info) && !ret)
		ret = btrfs_wait_ordered_range(inode, 0, (u64)-1);
out:
	kfree(ra);
	return ret;
}

static noinline_for_stack
int relocate_data_extent(struct inode *inode, struct btrfs_key *extent_key,
			 struct file_extent_cluster *cluster)
{
	int ret;

	if (cluster->nr > 0 && extent_key->objectid != cluster->end + 1) {
		ret = relocate_file_extent_cluster(inode, cluster);
		if (ret)
			return ret;
		cluster->nr = 0;
	}

	if (!cluster->nr)
		cluster->start = extent_key->objectid;
	else
		BUG_ON(cluster->nr >= MAX_EXTENTS);
	cluster->end = extent_key->objectid + extent_key->offset - 1;
	cluster->boundary[cluster->nr] = extent_key->objectid;
	cluster->nr++;

	if (cluster->nr >= MAX_EXTENTS) {
		ret = relocate_file_extent_cluster(inode, cluster);
		if (ret)
			return ret;
		cluster->nr = 0;
	}
	return 0;
}

/*
 * helper to add a tree block to the list.
 * the major work is getting the generation and level of the block
 */
static int add_tree_block(struct reloc_control *rc,
			  struct btrfs_key *extent_key,
			  struct btrfs_path *path,
			  struct rb_root *blocks)
{
	struct extent_buffer *eb;
	struct btrfs_extent_item *ei;
	struct btrfs_tree_block_info *bi;
	struct tree_block *block;
	struct rb_node *rb_node;
	u32 item_size;
	int level = -1;
	u64 generation;
	u64 owner = 0;

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

	if (extent_key->type == BTRFS_METADATA_ITEM_KEY ||
	    item_size >= sizeof(*ei) + sizeof(*bi)) {
		unsigned long ptr = 0, end;

		ei = btrfs_item_ptr(eb, path->slots[0],
				struct btrfs_extent_item);
		end = (unsigned long)ei + item_size;
		if (extent_key->type == BTRFS_EXTENT_ITEM_KEY) {
			bi = (struct btrfs_tree_block_info *)(ei + 1);
			level = btrfs_tree_block_level(eb, bi);
			ptr = (unsigned long)(bi + 1);
		} else {
			level = (int)extent_key->offset;
			ptr = (unsigned long)(ei + 1);
		}
		generation = btrfs_extent_generation(eb, ei);

		/*
		 * We're reading random blocks without knowing their owner ahead
		 * of time.  This is ok most of the time, as all reloc roots and
		 * fs roots have the same lock type.  However normal trees do
		 * not, and the only way to know ahead of time is to read the
		 * inline ref offset.  We know it's an fs root if
		 *
		 * 1. There's more than one ref.
		 * 2. There's a SHARED_DATA_REF_KEY set.
		 * 3. FULL_BACKREF is set on the flags.
		 *
		 * Otherwise it's safe to assume that the ref offset == the
		 * owner of this block, so we can use that when calling
		 * read_tree_block.
		 */
		if (btrfs_extent_refs(eb, ei) == 1 &&
		    !(btrfs_extent_flags(eb, ei) &
		      BTRFS_BLOCK_FLAG_FULL_BACKREF) &&
		    ptr < end) {
			struct btrfs_extent_inline_ref *iref;
			int type;

			iref = (struct btrfs_extent_inline_ref *)ptr;
			type = btrfs_get_extent_inline_ref_type(eb, iref,
							BTRFS_REF_TYPE_BLOCK);
			if (type == BTRFS_REF_TYPE_INVALID)
				return -EINVAL;
			if (type == BTRFS_TREE_BLOCK_REF_KEY)
				owner = btrfs_extent_inline_ref_offset(eb, iref);
		}
	} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
		btrfs_print_v0_err(eb->fs_info);
		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
		return -EINVAL;
	} else {
		BUG();
	}

	btrfs_release_path(path);

	BUG_ON(level == -1);

	block = kmalloc(sizeof(*block), GFP_NOFS);
	if (!block)
		return -ENOMEM;

	block->bytenr = extent_key->objectid;
	block->key.objectid = rc->extent_root->fs_info->nodesize;
	block->key.offset = generation;
	block->level = level;
	block->key_ready = 0;
	block->owner = owner;

	rb_node = rb_simple_insert(blocks, block->bytenr, &block->rb_node);
	if (rb_node)
		btrfs_backref_panic(rc->extent_root->fs_info, block->bytenr,
				    -EEXIST);

	return 0;
}

/*
 * helper to add tree blocks for backref of type BTRFS_SHARED_DATA_REF_KEY
 */
static int __add_tree_block(struct reloc_control *rc,
			    u64 bytenr, u32 blocksize,
			    struct rb_root *blocks)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct btrfs_path *path;
	struct btrfs_key key;
	int ret;
	bool skinny = btrfs_fs_incompat(fs_info, SKINNY_METADATA);

	if (tree_block_processed(bytenr, rc))
		return 0;

	if (rb_simple_search(blocks, bytenr))
		return 0;

	path = btrfs_alloc_path();
	if (!path)
		return -ENOMEM;
again:
	key.objectid = bytenr;
	if (skinny) {
		key.type = BTRFS_METADATA_ITEM_KEY;
		key.offset = (u64)-1;
	} else {
		key.type = BTRFS_EXTENT_ITEM_KEY;
		key.offset = blocksize;
	}

	path->search_commit_root = 1;
	path->skip_locking = 1;
	ret = btrfs_search_slot(NULL, rc->extent_root, &key, path, 0, 0);
	if (ret < 0)
		goto out;

	if (ret > 0 && skinny) {
		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_METADATA_ITEM_KEY ||
			     (key.type == BTRFS_EXTENT_ITEM_KEY &&
			      key.offset == blocksize)))
				ret = 0;
		}

		if (ret) {
			skinny = false;
			btrfs_release_path(path);
			goto again;
		}
	}
	if (ret) {
		ASSERT(ret == 1);
		btrfs_print_leaf(path->nodes[0]);
		btrfs_err(fs_info,
	     "tree block extent item (%llu) is not found in extent tree",
		     bytenr);
		WARN_ON(1);
		ret = -EINVAL;
		goto out;
	}

	ret = add_tree_block(rc, &key, path, blocks);
out:
	btrfs_free_path(path);
	return ret;
}

static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
				    struct btrfs_block_group *block_group,
				    struct inode *inode,
				    u64 ino)
{
	struct btrfs_root *root = fs_info->tree_root;
	struct btrfs_trans_handle *trans;
	int ret = 0;

	if (inode)
		goto truncate;

	inode = btrfs_iget(fs_info->sb, ino, root);
	if (IS_ERR(inode))
		return -ENOENT;

truncate:
	ret = btrfs_check_trunc_cache_free_space(fs_info,
						 &fs_info->global_block_rsv);
	if (ret)
		goto out;

	trans = btrfs_join_transaction(root);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		goto out;
	}

	ret = btrfs_truncate_free_space_cache(trans, block_group, inode);

	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(fs_info);
out:
	iput(inode);
	return ret;
}

/*
 * Locate the free space cache EXTENT_DATA in root tree leaf and delete the
 * cache inode, to avoid free space cache data extent blocking data relocation.
 */
static int delete_v1_space_cache(struct extent_buffer *leaf,
				 struct btrfs_block_group *block_group,
				 u64 data_bytenr)
{
	u64 space_cache_ino;
	struct btrfs_file_extent_item *ei;
	struct btrfs_key key;
	bool found = false;
	int i;
	int ret;

	if (btrfs_header_owner(leaf) != BTRFS_ROOT_TREE_OBJECTID)
		return 0;

	for (i = 0; i < btrfs_header_nritems(leaf); i++) {
		u8 type;

		btrfs_item_key_to_cpu(leaf, &key, i);
		if (key.type != BTRFS_EXTENT_DATA_KEY)
			continue;
		ei = btrfs_item_ptr(leaf, i, struct btrfs_file_extent_item);
		type = btrfs_file_extent_type(leaf, ei);

		if ((type == BTRFS_FILE_EXTENT_REG ||
		     type == BTRFS_FILE_EXTENT_PREALLOC) &&
		    btrfs_file_extent_disk_bytenr(leaf, ei) == data_bytenr) {
			found = true;
			space_cache_ino = key.objectid;
			break;
		}
	}
	if (!found)
		return -ENOENT;
	ret = delete_block_group_cache(leaf->fs_info, block_group, NULL,
					space_cache_ino);
	return ret;
}

/*
 * helper to find all tree blocks that reference a given data extent
 */
static noinline_for_stack
int add_data_references(struct reloc_control *rc,
			struct btrfs_key *extent_key,
			struct btrfs_path *path,
			struct rb_root *blocks)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct ulist *leaves = NULL;
	struct ulist_iterator leaf_uiter;
	struct ulist_node *ref_node = NULL;
	const u32 blocksize = fs_info->nodesize;
	int ret = 0;

	btrfs_release_path(path);
	ret = btrfs_find_all_leafs(NULL, fs_info, extent_key->objectid,
				   0, &leaves, NULL, true);
	if (ret < 0)
		return ret;

	ULIST_ITER_INIT(&leaf_uiter);
	while ((ref_node = ulist_next(leaves, &leaf_uiter))) {
		struct extent_buffer *eb;

		eb = read_tree_block(fs_info, ref_node->val, 0, 0, 0, NULL);
		if (IS_ERR(eb)) {
			ret = PTR_ERR(eb);
			break;
		}
		ret = delete_v1_space_cache(eb, rc->block_group,
					    extent_key->objectid);
		free_extent_buffer(eb);
		if (ret < 0)
			break;
		ret = __add_tree_block(rc, ref_node->val, blocksize, blocks);
		if (ret < 0)
			break;
	}
	if (ret < 0)
		free_block_list(blocks);
	ulist_free(leaves);
	return ret;
}

/*
 * helper to find next unprocessed extent
 */
static noinline_for_stack
int find_next_extent(struct reloc_control *rc, struct btrfs_path *path,
		     struct btrfs_key *extent_key)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct btrfs_key key;
	struct extent_buffer *leaf;
	u64 start, end, last;
	int ret;

	last = rc->block_group->start + rc->block_group->length;
	while (1) {
		cond_resched();
		if (rc->search_start >= last) {
			ret = 1;
			break;
		}

		key.objectid = rc->search_start;
		key.type = BTRFS_EXTENT_ITEM_KEY;
		key.offset = 0;

		path->search_commit_root = 1;
		path->skip_locking = 1;
		ret = btrfs_search_slot(NULL, rc->extent_root, &key, path,
					0, 0);
		if (ret < 0)
			break;
next:
		leaf = path->nodes[0];
		if (path->slots[0] >= btrfs_header_nritems(leaf)) {
			ret = btrfs_next_leaf(rc->extent_root, path);
			if (ret != 0)
				break;
			leaf = path->nodes[0];
		}

		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		if (key.objectid >= last) {
			ret = 1;
			break;
		}

		if (key.type != BTRFS_EXTENT_ITEM_KEY &&
		    key.type != BTRFS_METADATA_ITEM_KEY) {
			path->slots[0]++;
			goto next;
		}

		if (key.type == BTRFS_EXTENT_ITEM_KEY &&
		    key.objectid + key.offset <= rc->search_start) {
			path->slots[0]++;
			goto next;
		}

		if (key.type == BTRFS_METADATA_ITEM_KEY &&
		    key.objectid + fs_info->nodesize <=
		    rc->search_start) {
			path->slots[0]++;
			goto next;
		}

		ret = find_first_extent_bit(&rc->processed_blocks,
					    key.objectid, &start, &end,
					    EXTENT_DIRTY, NULL);

		if (ret == 0 && start <= key.objectid) {
			btrfs_release_path(path);
			rc->search_start = end + 1;
		} else {
			if (key.type == BTRFS_EXTENT_ITEM_KEY)
				rc->search_start = key.objectid + key.offset;
			else
				rc->search_start = key.objectid +
					fs_info->nodesize;
			memcpy(extent_key, &key, sizeof(key));
			return 0;
		}
	}
	btrfs_release_path(path);
	return ret;
}

static void set_reloc_control(struct reloc_control *rc)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;

	mutex_lock(&fs_info->reloc_mutex);
	fs_info->reloc_ctl = rc;
	mutex_unlock(&fs_info->reloc_mutex);
}

static void unset_reloc_control(struct reloc_control *rc)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;

	mutex_lock(&fs_info->reloc_mutex);
	fs_info->reloc_ctl = NULL;
	mutex_unlock(&fs_info->reloc_mutex);
}

static int check_extent_flags(u64 flags)
{
	if ((flags & BTRFS_EXTENT_FLAG_DATA) &&
	    (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK))
		return 1;
	if (!(flags & BTRFS_EXTENT_FLAG_DATA) &&
	    !(flags & BTRFS_EXTENT_FLAG_TREE_BLOCK))
		return 1;
	if ((flags & BTRFS_EXTENT_FLAG_DATA) &&
	    (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))
		return 1;
	return 0;
}

static noinline_for_stack
int prepare_to_relocate(struct reloc_control *rc)
{
	struct btrfs_trans_handle *trans;
	int ret;

	rc->block_rsv = btrfs_alloc_block_rsv(rc->extent_root->fs_info,
					      BTRFS_BLOCK_RSV_TEMP);
	if (!rc->block_rsv)
		return -ENOMEM;

	memset(&rc->cluster, 0, sizeof(rc->cluster));
	rc->search_start = rc->block_group->start;
	rc->extents_found = 0;
	rc->nodes_relocated = 0;
	rc->merging_rsv_size = 0;
	rc->reserved_bytes = 0;
	rc->block_rsv->size = rc->extent_root->fs_info->nodesize *
			      RELOCATION_RESERVED_NODES;
	ret = btrfs_block_rsv_refill(rc->extent_root,
				     rc->block_rsv, rc->block_rsv->size,
				     BTRFS_RESERVE_FLUSH_ALL);
	if (ret)
		return ret;

	rc->create_reloc_tree = 1;
	set_reloc_control(rc);

	trans = btrfs_join_transaction(rc->extent_root);
	if (IS_ERR(trans)) {
		unset_reloc_control(rc);
		/*
		 * extent tree is not a ref_cow tree and has no reloc_root to
		 * cleanup.  And callers are responsible to free the above
		 * block rsv.
		 */
		return PTR_ERR(trans);
	}
	btrfs_commit_transaction(trans);
	return 0;
}

static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
{
	struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
	struct rb_root blocks = RB_ROOT;
	struct btrfs_key key;
	struct btrfs_trans_handle *trans = NULL;
	struct btrfs_path *path;
	struct btrfs_extent_item *ei;
	u64 flags;
	u32 item_size;
	int ret;
	int err = 0;
	int progress = 0;

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

	ret = prepare_to_relocate(rc);
	if (ret) {
		err = ret;
		goto out_free;
	}

	while (1) {
		rc->reserved_bytes = 0;
		ret = btrfs_block_rsv_refill(rc->extent_root,
					rc->block_rsv, rc->block_rsv->size,
					BTRFS_RESERVE_FLUSH_ALL);
		if (ret) {
			err = ret;
			break;
		}
		progress++;
		trans = btrfs_start_transaction(rc->extent_root, 0);
		if (IS_ERR(trans)) {
			err = PTR_ERR(trans);
			trans = NULL;
			break;
		}
restart:
		if (update_backref_cache(trans, &rc->backref_cache)) {
			btrfs_end_transaction(trans);
			trans = NULL;
			continue;
		}

		ret = find_next_extent(rc, path, &key);
		if (ret < 0)
			err = ret;
		if (ret != 0)
			break;

		rc->extents_found++;

		ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
				    struct btrfs_extent_item);
		item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
		if (item_size >= sizeof(*ei)) {
			flags = btrfs_extent_flags(path->nodes[0], ei);
			ret = check_extent_flags(flags);
			BUG_ON(ret);
		} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
			err = -EINVAL;
			btrfs_print_v0_err(trans->fs_info);
			btrfs_abort_transaction(trans, err);
			break;
		} else {
			BUG();
		}

		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
			ret = add_tree_block(rc, &key, path, &blocks);
		} else if (rc->stage == UPDATE_DATA_PTRS &&
			   (flags & BTRFS_EXTENT_FLAG_DATA)) {
			ret = add_data_references(rc, &key, path, &blocks);
		} else {
			btrfs_release_path(path);
			ret = 0;
		}
		if (ret < 0) {
			err = ret;
			break;
		}

		if (!RB_EMPTY_ROOT(&blocks)) {
			ret = relocate_tree_blocks(trans, rc, &blocks);
			if (ret < 0) {
				if (ret != -EAGAIN) {
					err = ret;
					break;
				}
				rc->extents_found--;
				rc->search_start = key.objectid;
			}
		}

		btrfs_end_transaction_throttle(trans);
		btrfs_btree_balance_dirty(fs_info);
		trans = NULL;

		if (rc->stage == MOVE_DATA_EXTENTS &&
		    (flags & BTRFS_EXTENT_FLAG_DATA)) {
			rc->found_file_extent = 1;
			ret = relocate_data_extent(rc->data_inode,
						   &key, &rc->cluster);
			if (ret < 0) {
				err = ret;
				break;
			}
		}
		if (btrfs_should_cancel_balance(fs_info)) {
			err = -ECANCELED;
			break;
		}
	}
	if (trans && progress && err == -ENOSPC) {
		ret = btrfs_force_chunk_alloc(trans, rc->block_group->flags);
		if (ret == 1) {
			err = 0;
			progress = 0;
			goto restart;
		}
	}

	btrfs_release_path(path);
	clear_extent_bits(&rc->processed_blocks, 0, (u64)-1, EXTENT_DIRTY);

	if (trans) {
		btrfs_end_transaction_throttle(trans);
		btrfs_btree_balance_dirty(fs_info);
	}

	if (!err) {
		ret = relocate_file_extent_cluster(rc->data_inode,
						   &rc->cluster);
		if (ret < 0)
			err = ret;
	}

	rc->create_reloc_tree = 0;
	set_reloc_control(rc);

	btrfs_backref_release_cache(&rc->backref_cache);
	btrfs_block_rsv_release(fs_info, rc->block_rsv, (u64)-1, NULL);

	/*
	 * Even in the case when the relocation is cancelled, we should all go
	 * through prepare_to_merge() and merge_reloc_roots().
	 *
	 * For error (including cancelled balance), prepare_to_merge() will
	 * mark all reloc trees orphan, then queue them for cleanup in
	 * merge_reloc_roots()
	 */
	err = prepare_to_merge(rc, err);

	merge_reloc_roots(rc);

	rc->merge_reloc_tree = 0;
	unset_reloc_control(rc);
	btrfs_block_rsv_release(fs_info, rc->block_rsv, (u64)-1, NULL);

	/* get rid of pinned extents */
	trans = btrfs_join_transaction(rc->extent_root);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_free;
	}
	btrfs_commit_transaction(trans);
out_free:
	ret = clean_dirty_subvols(rc);
	if (ret < 0 && !err)
		err = ret;
	btrfs_free_block_rsv(fs_info, rc->block_rsv);
	btrfs_free_path(path);
	return err;
}

static int __insert_orphan_inode(struct btrfs_trans_handle *trans,
				 struct btrfs_root *root, u64 objectid)
{
	struct btrfs_path *path;
	struct btrfs_inode_item *item;
	struct extent_buffer *leaf;
	u64 flags = BTRFS_INODE_NOCOMPRESS | BTRFS_INODE_PREALLOC;
	int ret;

	if (btrfs_is_zoned(trans->fs_info))
		flags &= ~BTRFS_INODE_PREALLOC;

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

	ret = btrfs_insert_empty_inode(trans, root, path, objectid);
	if (ret)
		goto out;

	leaf = path->nodes[0];
	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_inode_item);
	memzero_extent_buffer(leaf, (unsigned long)item, sizeof(*item));
	btrfs_set_inode_generation(leaf, item, 1);
	btrfs_set_inode_size(leaf, item, 0);
	btrfs_set_inode_mode(leaf, item, S_IFREG | 0600);
	btrfs_set_inode_flags(leaf, item, flags);
	btrfs_mark_buffer_dirty(leaf);
out:
	btrfs_free_path(path);
	return ret;
}

/*
 * helper to create inode for data relocation.
 * the inode is in data relocation tree and its link count is 0
 */
static noinline_for_stack
struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
				 struct btrfs_block_group *group)
{
	struct inode *inode = NULL;
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root;
	u64 objectid;
	int err = 0;

	root = btrfs_grab_root(fs_info->data_reloc_root);
	trans = btrfs_start_transaction(root, 6);
	if (IS_ERR(trans)) {
		btrfs_put_root(root);
		return ERR_CAST(trans);
	}

	err = btrfs_get_free_objectid(root, &objectid);
	if (err)
		goto out;

	err = __insert_orphan_inode(trans, root, objectid);
	BUG_ON(err);

	inode = btrfs_iget(fs_info->sb, objectid, root);
	BUG_ON(IS_ERR(inode));
	BTRFS_I(inode)->index_cnt = group->start;

	err = btrfs_orphan_add(trans, BTRFS_I(inode));
out:
	btrfs_put_root(root);
	btrfs_end_transaction(trans);
	btrfs_btree_balance_dirty(fs_info);
	if (err) {
		if (inode)
			iput(inode);
		inode = ERR_PTR(err);
	}
	return inode;
}

static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
{
	struct reloc_control *rc;

	rc = kzalloc(sizeof(*rc), GFP_NOFS);
	if (!rc)
		return NULL;

	INIT_LIST_HEAD(&rc->reloc_roots);
	INIT_LIST_HEAD(&rc->dirty_subvol_roots);
	btrfs_backref_init_cache(fs_info, &rc->backref_cache, 1);
	mapping_tree_init(&rc->reloc_root_tree);
	extent_io_tree_init(fs_info, &rc->processed_blocks,
			    IO_TREE_RELOC_BLOCKS, NULL);
	return rc;
}

static void free_reloc_control(struct reloc_control *rc)
{
	struct mapping_node *node, *tmp;

	free_reloc_roots(&rc->reloc_roots);
	rbtree_postorder_for_each_entry_safe(node, tmp,
			&rc->reloc_root_tree.rb_root, rb_node)
		kfree(node);

	kfree(rc);
}

/*
 * Print the block group being relocated
 */
static void describe_relocation(struct btrfs_fs_info *fs_info,
				struct btrfs_block_group *block_group)
{
	char buf[128] = {'\0'};

	btrfs_describe_block_groups(block_group->flags, buf, sizeof(buf));

	btrfs_info(fs_info,
		   "relocating block group %llu flags %s",
		   block_group->start, buf);
}

static const char *stage_to_string(int stage)
{
	if (stage == MOVE_DATA_EXTENTS)
		return "move data extents";
	if (stage == UPDATE_DATA_PTRS)
		return "update data pointers";
	return "unknown";
}

/*
 * function to relocate all extents in a block group.
 */
int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
{
	struct btrfs_block_group *bg;
	struct btrfs_root *extent_root = fs_info->extent_root;
	struct reloc_control *rc;
	struct inode *inode;
	struct btrfs_path *path;
	int ret;
	int rw = 0;
	int err = 0;

	bg = btrfs_lookup_block_group(fs_info, group_start);
	if (!bg)
		return -ENOENT;

	if (btrfs_pinned_by_swapfile(fs_info, bg)) {
		btrfs_put_block_group(bg);
		return -ETXTBSY;
	}

	rc = alloc_reloc_control(fs_info);
	if (!rc) {
		btrfs_put_block_group(bg);
		return -ENOMEM;
	}

	rc->extent_root = extent_root;
	rc->block_group = bg;

	ret = btrfs_inc_block_group_ro(rc->block_group, true);
	if (ret) {
		err = ret;
		goto out;
	}
	rw = 1;

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

	inode = lookup_free_space_inode(rc->block_group, path);
	btrfs_free_path(path);

	if (!IS_ERR(inode))
		ret = delete_block_group_cache(fs_info, rc->block_group, inode, 0);
	else
		ret = PTR_ERR(inode);

	if (ret && ret != -ENOENT) {
		err = ret;
		goto out;
	}

	rc->data_inode = create_reloc_inode(fs_info, rc->block_group);
	if (IS_ERR(rc->data_inode)) {
		err = PTR_ERR(rc->data_inode);
		rc->data_inode = NULL;
		goto out;
	}

	describe_relocation(fs_info, rc->block_group);

	btrfs_wait_block_group_reservations(rc->block_group);
	btrfs_wait_nocow_writers(rc->block_group);
	btrfs_wait_ordered_roots(fs_info, U64_MAX,
				 rc->block_group->start,
				 rc->block_group->length);

	while (1) {
		int finishes_stage;

		mutex_lock(&fs_info->cleaner_mutex);
		ret = relocate_block_group(rc);
		mutex_unlock(&fs_info->cleaner_mutex);
		if (ret < 0)
			err = ret;

		finishes_stage = rc->stage;
		/*
		 * We may have gotten ENOSPC after we already dirtied some
		 * extents.  If writeout happens while we're relocating a
		 * different block group we could end up hitting the
		 * BUG_ON(rc->stage == UPDATE_DATA_PTRS) in
		 * btrfs_reloc_cow_block.  Make sure we write everything out
		 * properly so we don't trip over this problem, and then break
		 * out of the loop if we hit an error.
		 */
		if (rc->stage == MOVE_DATA_EXTENTS && rc->found_file_extent) {
			ret = btrfs_wait_ordered_range(rc->data_inode, 0,
						       (u64)-1);
			if (ret)
				err = ret;
			invalidate_mapping_pages(rc->data_inode->i_mapping,
						 0, -1);
			rc->stage = UPDATE_DATA_PTRS;
		}

		if (err < 0)
			goto out;

		if (rc->extents_found == 0)
			break;

		btrfs_info(fs_info, "found %llu extents, stage: %s",
			   rc->extents_found, stage_to_string(finishes_stage));
	}

	WARN_ON(rc->block_group->pinned > 0);
	WARN_ON(rc->block_group->reserved > 0);
	WARN_ON(rc->block_group->used > 0);
out:
	if (err && rw)
		btrfs_dec_block_group_ro(rc->block_group);
	iput(rc->data_inode);
	btrfs_put_block_group(rc->block_group);
	free_reloc_control(rc);
	return err;
}

static noinline_for_stack int mark_garbage_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_trans_handle *trans;
	int ret, err;

	trans = btrfs_start_transaction(fs_info->tree_root, 0);
	if (IS_ERR(trans))
		return PTR_ERR(trans);

	memset(&root->root_item.drop_progress, 0,
		sizeof(root->root_item.drop_progress));
	btrfs_set_root_drop_level(&root->root_item, 0);
	btrfs_set_root_refs(&root->root_item, 0);
	ret = btrfs_update_root(trans, fs_info->tree_root,
				&root->root_key, &root->root_item);

	err = btrfs_end_transaction(trans);
	if (err)
		return err;
	return ret;
}

/*
 * recover relocation interrupted by system crash.
 *
 * this function resumes merging reloc trees with corresponding fs trees.
 * this is important for keeping the sharing of tree blocks
 */
int btrfs_recover_relocation(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	LIST_HEAD(reloc_roots);
	struct btrfs_key key;
	struct btrfs_root *fs_root;
	struct btrfs_root *reloc_root;
	struct btrfs_path *path;
	struct extent_buffer *leaf;
	struct reloc_control *rc = NULL;
	struct btrfs_trans_handle *trans;
	int ret;
	int err = 0;

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

	key.objectid = BTRFS_TREE_RELOC_OBJECTID;
	key.type = BTRFS_ROOT_ITEM_KEY;
	key.offset = (u64)-1;

	while (1) {
		ret = btrfs_search_slot(NULL, fs_info->tree_root, &key,
					path, 0, 0);
		if (ret < 0) {
			err = ret;
			goto out;
		}
		if (ret > 0) {
			if (path->slots[0] == 0)
				break;
			path->slots[0]--;
		}
		leaf = path->nodes[0];
		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
		btrfs_release_path(path);

		if (key.objectid != BTRFS_TREE_RELOC_OBJECTID ||
		    key.type != BTRFS_ROOT_ITEM_KEY)
			break;

		reloc_root = btrfs_read_tree_root(root, &key);
		if (IS_ERR(reloc_root)) {
			err = PTR_ERR(reloc_root);
			goto out;
		}

		set_bit(BTRFS_ROOT_SHAREABLE, &reloc_root->state);
		list_add(&reloc_root->root_list, &reloc_roots);

		if (btrfs_root_refs(&reloc_root->root_item) > 0) {
			fs_root = btrfs_get_fs_root(fs_info,
					reloc_root->root_key.offset, false);
			if (IS_ERR(fs_root)) {
				ret = PTR_ERR(fs_root);
				if (ret != -ENOENT) {
					err = ret;
					goto out;
				}
				ret = mark_garbage_root(reloc_root);
				if (ret < 0) {
					err = ret;
					goto out;
				}
			} else {
				btrfs_put_root(fs_root);
			}
		}

		if (key.offset == 0)
			break;

		key.offset--;
	}
	btrfs_release_path(path);

	if (list_empty(&reloc_roots))
		goto out;

	rc = alloc_reloc_control(fs_info);
	if (!rc) {
		err = -ENOMEM;
		goto out;
	}

	rc->extent_root = fs_info->extent_root;

	set_reloc_control(rc);

	trans = btrfs_join_transaction(rc->extent_root);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_unset;
	}

	rc->merge_reloc_tree = 1;

	while (!list_empty(&reloc_roots)) {
		reloc_root = list_entry(reloc_roots.next,
					struct btrfs_root, root_list);
		list_del(&reloc_root->root_list);

		if (btrfs_root_refs(&reloc_root->root_item) == 0) {
			list_add_tail(&reloc_root->root_list,
				      &rc->reloc_roots);
			continue;
		}

		fs_root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset,
					    false);
		if (IS_ERR(fs_root)) {
			err = PTR_ERR(fs_root);
			list_add_tail(&reloc_root->root_list, &reloc_roots);
			btrfs_end_transaction(trans);
			goto out_unset;
		}

		err = __add_reloc_root(reloc_root);
		BUG_ON(err < 0); /* -ENOMEM or logic error */
		fs_root->reloc_root = btrfs_grab_root(reloc_root);
		btrfs_put_root(fs_root);
	}

	err = btrfs_commit_transaction(trans);
	if (err)
		goto out_unset;

	merge_reloc_roots(rc);

	unset_reloc_control(rc);

	trans = btrfs_join_transaction(rc->extent_root);
	if (IS_ERR(trans)) {
		err = PTR_ERR(trans);
		goto out_clean;
	}
	err = btrfs_commit_transaction(trans);
out_clean:
	ret = clean_dirty_subvols(rc);
	if (ret < 0 && !err)
		err = ret;
out_unset:
	unset_reloc_control(rc);
	free_reloc_control(rc);
out:
	free_reloc_roots(&reloc_roots);

	btrfs_free_path(path);

	if (err == 0) {
		/* cleanup orphan inode in data relocation tree */
		fs_root = btrfs_grab_root(fs_info->data_reloc_root);
		ASSERT(fs_root);
		err = btrfs_orphan_cleanup(fs_root);
		btrfs_put_root(fs_root);
	}
	return err;
}

/*
 * helper to add ordered checksum for data relocation.
 *
 * cloning checksum properly handles the nodatasum extents.
 * it also saves CPU time to re-calculate the checksum.
 */
int btrfs_reloc_clone_csums(struct btrfs_inode *inode, u64 file_pos, u64 len)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct btrfs_ordered_sum *sums;
	struct btrfs_ordered_extent *ordered;
	int ret;
	u64 disk_bytenr;
	u64 new_bytenr;
	LIST_HEAD(list);

	ordered = btrfs_lookup_ordered_extent(inode, file_pos);
	BUG_ON(ordered->file_offset != file_pos || ordered->num_bytes != len);

	disk_bytenr = file_pos + inode->index_cnt;
	ret = btrfs_lookup_csums_range(fs_info->csum_root, disk_bytenr,
				       disk_bytenr + len - 1, &list, 0);
	if (ret)
		goto out;

	while (!list_empty(&list)) {
		sums = list_entry(list.next, struct btrfs_ordered_sum, list);
		list_del_init(&sums->list);

		/*
		 * We need to offset the new_bytenr based on where the csum is.
		 * We need to do this because we will read in entire prealloc
		 * extents but we may have written to say the middle of the
		 * prealloc extent, so we need to make sure the csum goes with
		 * the right disk offset.
		 *
		 * We can do this because the data reloc inode refers strictly
		 * to the on disk bytes, so we don't have to worry about
		 * disk_len vs real len like with real inodes since it's all
		 * disk length.
		 */
		new_bytenr = ordered->disk_bytenr + sums->bytenr - disk_bytenr;
		sums->bytenr = new_bytenr;

		btrfs_add_ordered_sum(ordered, sums);
	}
out:
	btrfs_put_ordered_extent(ordered);
	return ret;
}

int btrfs_reloc_cow_block(struct btrfs_trans_handle *trans,
			  struct btrfs_root *root, struct extent_buffer *buf,
			  struct extent_buffer *cow)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct reloc_control *rc;
	struct btrfs_backref_node *node;
	int first_cow = 0;
	int level;
	int ret = 0;

	rc = fs_info->reloc_ctl;
	if (!rc)
		return 0;

	BUG_ON(rc->stage == UPDATE_DATA_PTRS &&
	       root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID);

	level = btrfs_header_level(buf);
	if (btrfs_header_generation(buf) <=
	    btrfs_root_last_snapshot(&root->root_item))
		first_cow = 1;

	if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID &&
	    rc->create_reloc_tree) {
		WARN_ON(!first_cow && level == 0);

		node = rc->backref_cache.path[level];
		BUG_ON(node->bytenr != buf->start &&
		       node->new_bytenr != buf->start);

		btrfs_backref_drop_node_buffer(node);
		atomic_inc(&cow->refs);
		node->eb = cow;
		node->new_bytenr = cow->start;

		if (!node->pending) {
			list_move_tail(&node->list,
				       &rc->backref_cache.pending[level]);
			node->pending = 1;
		}

		if (first_cow)
			mark_block_processed(rc, node);

		if (first_cow && level > 0)
			rc->nodes_relocated += buf->len;
	}

	if (level == 0 && first_cow && rc->stage == UPDATE_DATA_PTRS)
		ret = replace_file_extents(trans, rc, root, cow);
	return ret;
}

/*
 * called before creating snapshot. it calculates metadata reservation
 * required for relocating tree blocks in the snapshot
 */
void btrfs_reloc_pre_snapshot(struct btrfs_pending_snapshot *pending,
			      u64 *bytes_to_reserve)
{
	struct btrfs_root *root = pending->root;
	struct reloc_control *rc = root->fs_info->reloc_ctl;

	if (!rc || !have_reloc_root(root))
		return;

	if (!rc->merge_reloc_tree)
		return;

	root = root->reloc_root;
	BUG_ON(btrfs_root_refs(&root->root_item) == 0);
	/*
	 * relocation is in the stage of merging trees. the space
	 * used by merging a reloc tree is twice the size of
	 * relocated tree nodes in the worst case. half for cowing
	 * the reloc tree, half for cowing the fs tree. the space
	 * used by cowing the reloc tree will be freed after the
	 * tree is dropped. if we create snapshot, cowing the fs
	 * tree may use more space than it frees. so we need
	 * reserve extra space.
	 */
	*bytes_to_reserve += rc->nodes_relocated;
}

/*
 * called after snapshot is created. migrate block reservation
 * and create reloc root for the newly created snapshot
 *
 * This is similar to btrfs_init_reloc_root(), we come out of here with two
 * references held on the reloc_root, one for root->reloc_root and one for
 * rc->reloc_roots.
 */
int btrfs_reloc_post_snapshot(struct btrfs_trans_handle *trans,
			       struct btrfs_pending_snapshot *pending)
{
	struct btrfs_root *root = pending->root;
	struct btrfs_root *reloc_root;
	struct btrfs_root *new_root;
	struct reloc_control *rc = root->fs_info->reloc_ctl;
	int ret;

	if (!rc || !have_reloc_root(root))
		return 0;

	rc = root->fs_info->reloc_ctl;
	rc->merging_rsv_size += rc->nodes_relocated;

	if (rc->merge_reloc_tree) {
		ret = btrfs_block_rsv_migrate(&pending->block_rsv,
					      rc->block_rsv,
					      rc->nodes_relocated, true);
		if (ret)
			return ret;
	}

	new_root = pending->snap;
	reloc_root = create_reloc_root(trans, root->reloc_root,
				       new_root->root_key.objectid);
	if (IS_ERR(reloc_root))
		return PTR_ERR(reloc_root);

	ret = __add_reloc_root(reloc_root);
	BUG_ON(ret < 0);
	new_root->reloc_root = btrfs_grab_root(reloc_root);

	if (rc->create_reloc_tree)
		ret = clone_backref_node(trans, rc, root, reloc_root);
	return ret;
}