summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs/xfs_alloc.c
blob: 100ab5931b3132e8b3de4daab94de0dc16f10e07 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_shared.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_btree.h"
#include "xfs_rmap.h"
#include "xfs_alloc_btree.h"
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
#include "xfs_errortag.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_ag.h"
#include "xfs_ag_resv.h"
#include "xfs_bmap.h"

struct kmem_cache	*xfs_extfree_item_cache;

struct workqueue_struct *xfs_alloc_wq;

#define XFS_ABSDIFF(a,b)	(((a) <= (b)) ? ((b) - (a)) : ((a) - (b)))

#define	XFSA_FIXUP_BNO_OK	1
#define	XFSA_FIXUP_CNT_OK	2

/*
 * Size of the AGFL.  For CRC-enabled filesystes we steal a couple of slots in
 * the beginning of the block for a proper header with the location information
 * and CRC.
 */
unsigned int
xfs_agfl_size(
	struct xfs_mount	*mp)
{
	unsigned int		size = mp->m_sb.sb_sectsize;

	if (xfs_has_crc(mp))
		size -= sizeof(struct xfs_agfl);

	return size / sizeof(xfs_agblock_t);
}

unsigned int
xfs_refc_block(
	struct xfs_mount	*mp)
{
	if (xfs_has_rmapbt(mp))
		return XFS_RMAP_BLOCK(mp) + 1;
	if (xfs_has_finobt(mp))
		return XFS_FIBT_BLOCK(mp) + 1;
	return XFS_IBT_BLOCK(mp) + 1;
}

xfs_extlen_t
xfs_prealloc_blocks(
	struct xfs_mount	*mp)
{
	if (xfs_has_reflink(mp))
		return xfs_refc_block(mp) + 1;
	if (xfs_has_rmapbt(mp))
		return XFS_RMAP_BLOCK(mp) + 1;
	if (xfs_has_finobt(mp))
		return XFS_FIBT_BLOCK(mp) + 1;
	return XFS_IBT_BLOCK(mp) + 1;
}

/*
 * The number of blocks per AG that we withhold from xfs_mod_fdblocks to
 * guarantee that we can refill the AGFL prior to allocating space in a nearly
 * full AG.  Although the space described by the free space btrees, the
 * blocks used by the freesp btrees themselves, and the blocks owned by the
 * AGFL are counted in the ondisk fdblocks, it's a mistake to let the ondisk
 * free space in the AG drop so low that the free space btrees cannot refill an
 * empty AGFL up to the minimum level.  Rather than grind through empty AGs
 * until the fs goes down, we subtract this many AG blocks from the incore
 * fdblocks to ensure user allocation does not overcommit the space the
 * filesystem needs for the AGFLs.  The rmap btree uses a per-AG reservation to
 * withhold space from xfs_mod_fdblocks, so we do not account for that here.
 */
#define XFS_ALLOCBT_AGFL_RESERVE	4

/*
 * Compute the number of blocks that we set aside to guarantee the ability to
 * refill the AGFL and handle a full bmap btree split.
 *
 * In order to avoid ENOSPC-related deadlock caused by out-of-order locking of
 * AGF buffer (PV 947395), we place constraints on the relationship among
 * actual allocations for data blocks, freelist blocks, and potential file data
 * bmap btree blocks. However, these restrictions may result in no actual space
 * allocated for a delayed extent, for example, a data block in a certain AG is
 * allocated but there is no additional block for the additional bmap btree
 * block due to a split of the bmap btree of the file. The result of this may
 * lead to an infinite loop when the file gets flushed to disk and all delayed
 * extents need to be actually allocated. To get around this, we explicitly set
 * aside a few blocks which will not be reserved in delayed allocation.
 *
 * For each AG, we need to reserve enough blocks to replenish a totally empty
 * AGFL and 4 more to handle a potential split of the file's bmap btree.
 */
unsigned int
xfs_alloc_set_aside(
	struct xfs_mount	*mp)
{
	return mp->m_sb.sb_agcount * (XFS_ALLOCBT_AGFL_RESERVE + 4);
}

/*
 * When deciding how much space to allocate out of an AG, we limit the
 * allocation maximum size to the size the AG. However, we cannot use all the
 * blocks in the AG - some are permanently used by metadata. These
 * blocks are generally:
 *	- the AG superblock, AGF, AGI and AGFL
 *	- the AGF (bno and cnt) and AGI btree root blocks, and optionally
 *	  the AGI free inode and rmap btree root blocks.
 *	- blocks on the AGFL according to xfs_alloc_set_aside() limits
 *	- the rmapbt root block
 *
 * The AG headers are sector sized, so the amount of space they take up is
 * dependent on filesystem geometry. The others are all single blocks.
 */
unsigned int
xfs_alloc_ag_max_usable(
	struct xfs_mount	*mp)
{
	unsigned int		blocks;

	blocks = XFS_BB_TO_FSB(mp, XFS_FSS_TO_BB(mp, 4)); /* ag headers */
	blocks += XFS_ALLOCBT_AGFL_RESERVE;
	blocks += 3;			/* AGF, AGI btree root blocks */
	if (xfs_has_finobt(mp))
		blocks++;		/* finobt root block */
	if (xfs_has_rmapbt(mp))
		blocks++;		/* rmap root block */
	if (xfs_has_reflink(mp))
		blocks++;		/* refcount root block */

	return mp->m_sb.sb_agblocks - blocks;
}

/*
 * Lookup the record equal to [bno, len] in the btree given by cur.
 */
STATIC int				/* error */
xfs_alloc_lookup_eq(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_agblock_t		bno,	/* starting block of extent */
	xfs_extlen_t		len,	/* length of extent */
	int			*stat)	/* success/failure */
{
	int			error;

	cur->bc_rec.a.ar_startblock = bno;
	cur->bc_rec.a.ar_blockcount = len;
	error = xfs_btree_lookup(cur, XFS_LOOKUP_EQ, stat);
	cur->bc_ag.abt.active = (*stat == 1);
	return error;
}

/*
 * Lookup the first record greater than or equal to [bno, len]
 * in the btree given by cur.
 */
int				/* error */
xfs_alloc_lookup_ge(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_agblock_t		bno,	/* starting block of extent */
	xfs_extlen_t		len,	/* length of extent */
	int			*stat)	/* success/failure */
{
	int			error;

	cur->bc_rec.a.ar_startblock = bno;
	cur->bc_rec.a.ar_blockcount = len;
	error = xfs_btree_lookup(cur, XFS_LOOKUP_GE, stat);
	cur->bc_ag.abt.active = (*stat == 1);
	return error;
}

/*
 * Lookup the first record less than or equal to [bno, len]
 * in the btree given by cur.
 */
int					/* error */
xfs_alloc_lookup_le(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_agblock_t		bno,	/* starting block of extent */
	xfs_extlen_t		len,	/* length of extent */
	int			*stat)	/* success/failure */
{
	int			error;
	cur->bc_rec.a.ar_startblock = bno;
	cur->bc_rec.a.ar_blockcount = len;
	error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, stat);
	cur->bc_ag.abt.active = (*stat == 1);
	return error;
}

static inline bool
xfs_alloc_cur_active(
	struct xfs_btree_cur	*cur)
{
	return cur && cur->bc_ag.abt.active;
}

/*
 * Update the record referred to by cur to the value given
 * by [bno, len].
 * This either works (return 0) or gets an EFSCORRUPTED error.
 */
STATIC int				/* error */
xfs_alloc_update(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_agblock_t		bno,	/* starting block of extent */
	xfs_extlen_t		len)	/* length of extent */
{
	union xfs_btree_rec	rec;

	rec.alloc.ar_startblock = cpu_to_be32(bno);
	rec.alloc.ar_blockcount = cpu_to_be32(len);
	return xfs_btree_update(cur, &rec);
}

/* Convert the ondisk btree record to its incore representation. */
void
xfs_alloc_btrec_to_irec(
	const union xfs_btree_rec	*rec,
	struct xfs_alloc_rec_incore	*irec)
{
	irec->ar_startblock = be32_to_cpu(rec->alloc.ar_startblock);
	irec->ar_blockcount = be32_to_cpu(rec->alloc.ar_blockcount);
}

/* Simple checks for free space records. */
xfs_failaddr_t
xfs_alloc_check_irec(
	struct xfs_btree_cur		*cur,
	const struct xfs_alloc_rec_incore *irec)
{
	struct xfs_perag		*pag = cur->bc_ag.pag;

	if (irec->ar_blockcount == 0)
		return __this_address;

	/* check for valid extent range, including overflow */
	if (!xfs_verify_agbext(pag, irec->ar_startblock, irec->ar_blockcount))
		return __this_address;

	return NULL;
}

static inline int
xfs_alloc_complain_bad_rec(
	struct xfs_btree_cur		*cur,
	xfs_failaddr_t			fa,
	const struct xfs_alloc_rec_incore *irec)
{
	struct xfs_mount		*mp = cur->bc_mp;

	xfs_warn(mp,
		"%s Freespace BTree record corruption in AG %d detected at %pS!",
		cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size",
		cur->bc_ag.pag->pag_agno, fa);
	xfs_warn(mp,
		"start block 0x%x block count 0x%x", irec->ar_startblock,
		irec->ar_blockcount);
	return -EFSCORRUPTED;
}

/*
 * Get the data from the pointed-to record.
 */
int					/* error */
xfs_alloc_get_rec(
	struct xfs_btree_cur	*cur,	/* btree cursor */
	xfs_agblock_t		*bno,	/* output: starting block of extent */
	xfs_extlen_t		*len,	/* output: length of extent */
	int			*stat)	/* output: success/failure */
{
	struct xfs_alloc_rec_incore irec;
	union xfs_btree_rec	*rec;
	xfs_failaddr_t		fa;
	int			error;

	error = xfs_btree_get_rec(cur, &rec, stat);
	if (error || !(*stat))
		return error;

	xfs_alloc_btrec_to_irec(rec, &irec);
	fa = xfs_alloc_check_irec(cur, &irec);
	if (fa)
		return xfs_alloc_complain_bad_rec(cur, fa, &irec);

	*bno = irec.ar_startblock;
	*len = irec.ar_blockcount;
	return 0;
}

/*
 * Compute aligned version of the found extent.
 * Takes alignment and min length into account.
 */
STATIC bool
xfs_alloc_compute_aligned(
	xfs_alloc_arg_t	*args,		/* allocation argument structure */
	xfs_agblock_t	foundbno,	/* starting block in found extent */
	xfs_extlen_t	foundlen,	/* length in found extent */
	xfs_agblock_t	*resbno,	/* result block number */
	xfs_extlen_t	*reslen,	/* result length */
	unsigned	*busy_gen)
{
	xfs_agblock_t	bno = foundbno;
	xfs_extlen_t	len = foundlen;
	xfs_extlen_t	diff;
	bool		busy;

	/* Trim busy sections out of found extent */
	busy = xfs_extent_busy_trim(args, &bno, &len, busy_gen);

	/*
	 * If we have a largish extent that happens to start before min_agbno,
	 * see if we can shift it into range...
	 */
	if (bno < args->min_agbno && bno + len > args->min_agbno) {
		diff = args->min_agbno - bno;
		if (len > diff) {
			bno += diff;
			len -= diff;
		}
	}

	if (args->alignment > 1 && len >= args->minlen) {
		xfs_agblock_t	aligned_bno = roundup(bno, args->alignment);

		diff = aligned_bno - bno;

		*resbno = aligned_bno;
		*reslen = diff >= len ? 0 : len - diff;
	} else {
		*resbno = bno;
		*reslen = len;
	}

	return busy;
}

/*
 * Compute best start block and diff for "near" allocations.
 * freelen >= wantlen already checked by caller.
 */
STATIC xfs_extlen_t			/* difference value (absolute) */
xfs_alloc_compute_diff(
	xfs_agblock_t	wantbno,	/* target starting block */
	xfs_extlen_t	wantlen,	/* target length */
	xfs_extlen_t	alignment,	/* target alignment */
	int		datatype,	/* are we allocating data? */
	xfs_agblock_t	freebno,	/* freespace's starting block */
	xfs_extlen_t	freelen,	/* freespace's length */
	xfs_agblock_t	*newbnop)	/* result: best start block from free */
{
	xfs_agblock_t	freeend;	/* end of freespace extent */
	xfs_agblock_t	newbno1;	/* return block number */
	xfs_agblock_t	newbno2;	/* other new block number */
	xfs_extlen_t	newlen1=0;	/* length with newbno1 */
	xfs_extlen_t	newlen2=0;	/* length with newbno2 */
	xfs_agblock_t	wantend;	/* end of target extent */
	bool		userdata = datatype & XFS_ALLOC_USERDATA;

	ASSERT(freelen >= wantlen);
	freeend = freebno + freelen;
	wantend = wantbno + wantlen;
	/*
	 * We want to allocate from the start of a free extent if it is past
	 * the desired block or if we are allocating user data and the free
	 * extent is before desired block. The second case is there to allow
	 * for contiguous allocation from the remaining free space if the file
	 * grows in the short term.
	 */
	if (freebno >= wantbno || (userdata && freeend < wantend)) {
		if ((newbno1 = roundup(freebno, alignment)) >= freeend)
			newbno1 = NULLAGBLOCK;
	} else if (freeend >= wantend && alignment > 1) {
		newbno1 = roundup(wantbno, alignment);
		newbno2 = newbno1 - alignment;
		if (newbno1 >= freeend)
			newbno1 = NULLAGBLOCK;
		else
			newlen1 = XFS_EXTLEN_MIN(wantlen, freeend - newbno1);
		if (newbno2 < freebno)
			newbno2 = NULLAGBLOCK;
		else
			newlen2 = XFS_EXTLEN_MIN(wantlen, freeend - newbno2);
		if (newbno1 != NULLAGBLOCK && newbno2 != NULLAGBLOCK) {
			if (newlen1 < newlen2 ||
			    (newlen1 == newlen2 &&
			     XFS_ABSDIFF(newbno1, wantbno) >
			     XFS_ABSDIFF(newbno2, wantbno)))
				newbno1 = newbno2;
		} else if (newbno2 != NULLAGBLOCK)
			newbno1 = newbno2;
	} else if (freeend >= wantend) {
		newbno1 = wantbno;
	} else if (alignment > 1) {
		newbno1 = roundup(freeend - wantlen, alignment);
		if (newbno1 > freeend - wantlen &&
		    newbno1 - alignment >= freebno)
			newbno1 -= alignment;
		else if (newbno1 >= freeend)
			newbno1 = NULLAGBLOCK;
	} else
		newbno1 = freeend - wantlen;
	*newbnop = newbno1;
	return newbno1 == NULLAGBLOCK ? 0 : XFS_ABSDIFF(newbno1, wantbno);
}

/*
 * Fix up the length, based on mod and prod.
 * len should be k * prod + mod for some k.
 * If len is too small it is returned unchanged.
 * If len hits maxlen it is left alone.
 */
STATIC void
xfs_alloc_fix_len(
	xfs_alloc_arg_t	*args)		/* allocation argument structure */
{
	xfs_extlen_t	k;
	xfs_extlen_t	rlen;

	ASSERT(args->mod < args->prod);
	rlen = args->len;
	ASSERT(rlen >= args->minlen);
	ASSERT(rlen <= args->maxlen);
	if (args->prod <= 1 || rlen < args->mod || rlen == args->maxlen ||
	    (args->mod == 0 && rlen < args->prod))
		return;
	k = rlen % args->prod;
	if (k == args->mod)
		return;
	if (k > args->mod)
		rlen = rlen - (k - args->mod);
	else
		rlen = rlen - args->prod + (args->mod - k);
	/* casts to (int) catch length underflows */
	if ((int)rlen < (int)args->minlen)
		return;
	ASSERT(rlen >= args->minlen && rlen <= args->maxlen);
	ASSERT(rlen % args->prod == args->mod);
	ASSERT(args->pag->pagf_freeblks + args->pag->pagf_flcount >=
		rlen + args->minleft);
	args->len = rlen;
}

/*
 * Update the two btrees, logically removing from freespace the extent
 * starting at rbno, rlen blocks.  The extent is contained within the
 * actual (current) free extent fbno for flen blocks.
 * Flags are passed in indicating whether the cursors are set to the
 * relevant records.
 */
STATIC int				/* error code */
xfs_alloc_fixup_trees(
	struct xfs_btree_cur *cnt_cur,	/* cursor for by-size btree */
	struct xfs_btree_cur *bno_cur,	/* cursor for by-block btree */
	xfs_agblock_t	fbno,		/* starting block of free extent */
	xfs_extlen_t	flen,		/* length of free extent */
	xfs_agblock_t	rbno,		/* starting block of returned extent */
	xfs_extlen_t	rlen,		/* length of returned extent */
	int		flags)		/* flags, XFSA_FIXUP_... */
{
	int		error;		/* error code */
	int		i;		/* operation results */
	xfs_agblock_t	nfbno1;		/* first new free startblock */
	xfs_agblock_t	nfbno2;		/* second new free startblock */
	xfs_extlen_t	nflen1=0;	/* first new free length */
	xfs_extlen_t	nflen2=0;	/* second new free length */
	struct xfs_mount *mp;

	mp = cnt_cur->bc_mp;

	/*
	 * Look up the record in the by-size tree if necessary.
	 */
	if (flags & XFSA_FIXUP_CNT_OK) {
#ifdef DEBUG
		if ((error = xfs_alloc_get_rec(cnt_cur, &nfbno1, &nflen1, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp,
				   i != 1 ||
				   nfbno1 != fbno ||
				   nflen1 != flen))
			return -EFSCORRUPTED;
#endif
	} else {
		if ((error = xfs_alloc_lookup_eq(cnt_cur, fbno, flen, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 1))
			return -EFSCORRUPTED;
	}
	/*
	 * Look up the record in the by-block tree if necessary.
	 */
	if (flags & XFSA_FIXUP_BNO_OK) {
#ifdef DEBUG
		if ((error = xfs_alloc_get_rec(bno_cur, &nfbno1, &nflen1, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp,
				   i != 1 ||
				   nfbno1 != fbno ||
				   nflen1 != flen))
			return -EFSCORRUPTED;
#endif
	} else {
		if ((error = xfs_alloc_lookup_eq(bno_cur, fbno, flen, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 1))
			return -EFSCORRUPTED;
	}

#ifdef DEBUG
	if (bno_cur->bc_nlevels == 1 && cnt_cur->bc_nlevels == 1) {
		struct xfs_btree_block	*bnoblock;
		struct xfs_btree_block	*cntblock;

		bnoblock = XFS_BUF_TO_BLOCK(bno_cur->bc_levels[0].bp);
		cntblock = XFS_BUF_TO_BLOCK(cnt_cur->bc_levels[0].bp);

		if (XFS_IS_CORRUPT(mp,
				   bnoblock->bb_numrecs !=
				   cntblock->bb_numrecs))
			return -EFSCORRUPTED;
	}
#endif

	/*
	 * Deal with all four cases: the allocated record is contained
	 * within the freespace record, so we can have new freespace
	 * at either (or both) end, or no freespace remaining.
	 */
	if (rbno == fbno && rlen == flen)
		nfbno1 = nfbno2 = NULLAGBLOCK;
	else if (rbno == fbno) {
		nfbno1 = rbno + rlen;
		nflen1 = flen - rlen;
		nfbno2 = NULLAGBLOCK;
	} else if (rbno + rlen == fbno + flen) {
		nfbno1 = fbno;
		nflen1 = flen - rlen;
		nfbno2 = NULLAGBLOCK;
	} else {
		nfbno1 = fbno;
		nflen1 = rbno - fbno;
		nfbno2 = rbno + rlen;
		nflen2 = (fbno + flen) - nfbno2;
	}
	/*
	 * Delete the entry from the by-size btree.
	 */
	if ((error = xfs_btree_delete(cnt_cur, &i)))
		return error;
	if (XFS_IS_CORRUPT(mp, i != 1))
		return -EFSCORRUPTED;
	/*
	 * Add new by-size btree entry(s).
	 */
	if (nfbno1 != NULLAGBLOCK) {
		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno1, nflen1, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 0))
			return -EFSCORRUPTED;
		if ((error = xfs_btree_insert(cnt_cur, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 1))
			return -EFSCORRUPTED;
	}
	if (nfbno2 != NULLAGBLOCK) {
		if ((error = xfs_alloc_lookup_eq(cnt_cur, nfbno2, nflen2, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 0))
			return -EFSCORRUPTED;
		if ((error = xfs_btree_insert(cnt_cur, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 1))
			return -EFSCORRUPTED;
	}
	/*
	 * Fix up the by-block btree entry(s).
	 */
	if (nfbno1 == NULLAGBLOCK) {
		/*
		 * No remaining freespace, just delete the by-block tree entry.
		 */
		if ((error = xfs_btree_delete(bno_cur, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 1))
			return -EFSCORRUPTED;
	} else {
		/*
		 * Update the by-block entry to start later|be shorter.
		 */
		if ((error = xfs_alloc_update(bno_cur, nfbno1, nflen1)))
			return error;
	}
	if (nfbno2 != NULLAGBLOCK) {
		/*
		 * 2 resulting free entries, need to add one.
		 */
		if ((error = xfs_alloc_lookup_eq(bno_cur, nfbno2, nflen2, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 0))
			return -EFSCORRUPTED;
		if ((error = xfs_btree_insert(bno_cur, &i)))
			return error;
		if (XFS_IS_CORRUPT(mp, i != 1))
			return -EFSCORRUPTED;
	}
	return 0;
}

/*
 * We do not verify the AGFL contents against AGF-based index counters here,
 * even though we may have access to the perag that contains shadow copies. We
 * don't know if the AGF based counters have been checked, and if they have they
 * still may be inconsistent because they haven't yet been reset on the first
 * allocation after the AGF has been read in.
 *
 * This means we can only check that all agfl entries contain valid or null
 * values because we can't reliably determine the active range to exclude
 * NULLAGBNO as a valid value.
 *
 * However, we can't even do that for v4 format filesystems because there are
 * old versions of mkfs out there that does not initialise the AGFL to known,
 * verifiable values. HEnce we can't tell the difference between a AGFL block
 * allocated by mkfs and a corrupted AGFL block here on v4 filesystems.
 *
 * As a result, we can only fully validate AGFL block numbers when we pull them
 * from the freelist in xfs_alloc_get_freelist().
 */
static xfs_failaddr_t
xfs_agfl_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount *mp = bp->b_mount;
	struct xfs_agfl	*agfl = XFS_BUF_TO_AGFL(bp);
	__be32		*agfl_bno = xfs_buf_to_agfl_bno(bp);
	int		i;

	if (!xfs_has_crc(mp))
		return NULL;

	if (!xfs_verify_magic(bp, agfl->agfl_magicnum))
		return __this_address;
	if (!uuid_equal(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid))
		return __this_address;
	/*
	 * during growfs operations, the perag is not fully initialised,
	 * so we can't use it for any useful checking. growfs ensures we can't
	 * use it by using uncached buffers that don't have the perag attached
	 * so we can detect and avoid this problem.
	 */
	if (bp->b_pag && be32_to_cpu(agfl->agfl_seqno) != bp->b_pag->pag_agno)
		return __this_address;

	for (i = 0; i < xfs_agfl_size(mp); i++) {
		if (be32_to_cpu(agfl_bno[i]) != NULLAGBLOCK &&
		    be32_to_cpu(agfl_bno[i]) >= mp->m_sb.sb_agblocks)
			return __this_address;
	}

	if (!xfs_log_check_lsn(mp, be64_to_cpu(XFS_BUF_TO_AGFL(bp)->agfl_lsn)))
		return __this_address;
	return NULL;
}

static void
xfs_agfl_read_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount *mp = bp->b_mount;
	xfs_failaddr_t	fa;

	/*
	 * There is no verification of non-crc AGFLs because mkfs does not
	 * initialise the AGFL to zero or NULL. Hence the only valid part of the
	 * AGFL is what the AGF says is active. We can't get to the AGF, so we
	 * can't verify just those entries are valid.
	 */
	if (!xfs_has_crc(mp))
		return;

	if (!xfs_buf_verify_cksum(bp, XFS_AGFL_CRC_OFF))
		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
	else {
		fa = xfs_agfl_verify(bp);
		if (fa)
			xfs_verifier_error(bp, -EFSCORRUPTED, fa);
	}
}

static void
xfs_agfl_write_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount	*mp = bp->b_mount;
	struct xfs_buf_log_item	*bip = bp->b_log_item;
	xfs_failaddr_t		fa;

	/* no verification of non-crc AGFLs */
	if (!xfs_has_crc(mp))
		return;

	fa = xfs_agfl_verify(bp);
	if (fa) {
		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
		return;
	}

	if (bip)
		XFS_BUF_TO_AGFL(bp)->agfl_lsn = cpu_to_be64(bip->bli_item.li_lsn);

	xfs_buf_update_cksum(bp, XFS_AGFL_CRC_OFF);
}

const struct xfs_buf_ops xfs_agfl_buf_ops = {
	.name = "xfs_agfl",
	.magic = { cpu_to_be32(XFS_AGFL_MAGIC), cpu_to_be32(XFS_AGFL_MAGIC) },
	.verify_read = xfs_agfl_read_verify,
	.verify_write = xfs_agfl_write_verify,
	.verify_struct = xfs_agfl_verify,
};

/*
 * Read in the allocation group free block array.
 */
int
xfs_alloc_read_agfl(
	struct xfs_perag	*pag,
	struct xfs_trans	*tp,
	struct xfs_buf		**bpp)
{
	struct xfs_mount	*mp = pag->pag_mount;
	struct xfs_buf		*bp;
	int			error;

	error = xfs_trans_read_buf(
			mp, tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGFL_DADDR(mp)),
			XFS_FSS_TO_BB(mp, 1), 0, &bp, &xfs_agfl_buf_ops);
	if (error)
		return error;
	xfs_buf_set_ref(bp, XFS_AGFL_REF);
	*bpp = bp;
	return 0;
}

STATIC int
xfs_alloc_update_counters(
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	long			len)
{
	struct xfs_agf		*agf = agbp->b_addr;

	agbp->b_pag->pagf_freeblks += len;
	be32_add_cpu(&agf->agf_freeblks, len);

	if (unlikely(be32_to_cpu(agf->agf_freeblks) >
		     be32_to_cpu(agf->agf_length))) {
		xfs_buf_mark_corrupt(agbp);
		return -EFSCORRUPTED;
	}

	xfs_alloc_log_agf(tp, agbp, XFS_AGF_FREEBLKS);
	return 0;
}

/*
 * Block allocation algorithm and data structures.
 */
struct xfs_alloc_cur {
	struct xfs_btree_cur		*cnt;	/* btree cursors */
	struct xfs_btree_cur		*bnolt;
	struct xfs_btree_cur		*bnogt;
	xfs_extlen_t			cur_len;/* current search length */
	xfs_agblock_t			rec_bno;/* extent startblock */
	xfs_extlen_t			rec_len;/* extent length */
	xfs_agblock_t			bno;	/* alloc bno */
	xfs_extlen_t			len;	/* alloc len */
	xfs_extlen_t			diff;	/* diff from search bno */
	unsigned int			busy_gen;/* busy state */
	bool				busy;
};

/*
 * Set up cursors, etc. in the extent allocation cursor. This function can be
 * called multiple times to reset an initialized structure without having to
 * reallocate cursors.
 */
static int
xfs_alloc_cur_setup(
	struct xfs_alloc_arg	*args,
	struct xfs_alloc_cur	*acur)
{
	int			error;
	int			i;

	acur->cur_len = args->maxlen;
	acur->rec_bno = 0;
	acur->rec_len = 0;
	acur->bno = 0;
	acur->len = 0;
	acur->diff = -1;
	acur->busy = false;
	acur->busy_gen = 0;

	/*
	 * Perform an initial cntbt lookup to check for availability of maxlen
	 * extents. If this fails, we'll return -ENOSPC to signal the caller to
	 * attempt a small allocation.
	 */
	if (!acur->cnt)
		acur->cnt = xfs_allocbt_init_cursor(args->mp, args->tp,
					args->agbp, args->pag, XFS_BTNUM_CNT);
	error = xfs_alloc_lookup_ge(acur->cnt, 0, args->maxlen, &i);
	if (error)
		return error;

	/*
	 * Allocate the bnobt left and right search cursors.
	 */
	if (!acur->bnolt)
		acur->bnolt = xfs_allocbt_init_cursor(args->mp, args->tp,
					args->agbp, args->pag, XFS_BTNUM_BNO);
	if (!acur->bnogt)
		acur->bnogt = xfs_allocbt_init_cursor(args->mp, args->tp,
					args->agbp, args->pag, XFS_BTNUM_BNO);
	return i == 1 ? 0 : -ENOSPC;
}

static void
xfs_alloc_cur_close(
	struct xfs_alloc_cur	*acur,
	bool			error)
{
	int			cur_error = XFS_BTREE_NOERROR;

	if (error)
		cur_error = XFS_BTREE_ERROR;

	if (acur->cnt)
		xfs_btree_del_cursor(acur->cnt, cur_error);
	if (acur->bnolt)
		xfs_btree_del_cursor(acur->bnolt, cur_error);
	if (acur->bnogt)
		xfs_btree_del_cursor(acur->bnogt, cur_error);
	acur->cnt = acur->bnolt = acur->bnogt = NULL;
}

/*
 * Check an extent for allocation and track the best available candidate in the
 * allocation structure. The cursor is deactivated if it has entered an out of
 * range state based on allocation arguments. Optionally return the extent
 * extent geometry and allocation status if requested by the caller.
 */
static int
xfs_alloc_cur_check(
	struct xfs_alloc_arg	*args,
	struct xfs_alloc_cur	*acur,
	struct xfs_btree_cur	*cur,
	int			*new)
{
	int			error, i;
	xfs_agblock_t		bno, bnoa, bnew;
	xfs_extlen_t		len, lena, diff = -1;
	bool			busy;
	unsigned		busy_gen = 0;
	bool			deactivate = false;
	bool			isbnobt = cur->bc_btnum == XFS_BTNUM_BNO;

	*new = 0;

	error = xfs_alloc_get_rec(cur, &bno, &len, &i);
	if (error)
		return error;
	if (XFS_IS_CORRUPT(args->mp, i != 1))
		return -EFSCORRUPTED;

	/*
	 * Check minlen and deactivate a cntbt cursor if out of acceptable size
	 * range (i.e., walking backwards looking for a minlen extent).
	 */
	if (len < args->minlen) {
		deactivate = !isbnobt;
		goto out;
	}

	busy = xfs_alloc_compute_aligned(args, bno, len, &bnoa, &lena,
					 &busy_gen);
	acur->busy |= busy;
	if (busy)
		acur->busy_gen = busy_gen;
	/* deactivate a bnobt cursor outside of locality range */
	if (bnoa < args->min_agbno || bnoa > args->max_agbno) {
		deactivate = isbnobt;
		goto out;
	}
	if (lena < args->minlen)
		goto out;

	args->len = XFS_EXTLEN_MIN(lena, args->maxlen);
	xfs_alloc_fix_len(args);
	ASSERT(args->len >= args->minlen);
	if (args->len < acur->len)
		goto out;

	/*
	 * We have an aligned record that satisfies minlen and beats or matches
	 * the candidate extent size. Compare locality for near allocation mode.
	 */
	diff = xfs_alloc_compute_diff(args->agbno, args->len,
				      args->alignment, args->datatype,
				      bnoa, lena, &bnew);
	if (bnew == NULLAGBLOCK)
		goto out;

	/*
	 * Deactivate a bnobt cursor with worse locality than the current best.
	 */
	if (diff > acur->diff) {
		deactivate = isbnobt;
		goto out;
	}

	ASSERT(args->len > acur->len ||
	       (args->len == acur->len && diff <= acur->diff));
	acur->rec_bno = bno;
	acur->rec_len = len;
	acur->bno = bnew;
	acur->len = args->len;
	acur->diff = diff;
	*new = 1;

	/*
	 * We're done if we found a perfect allocation. This only deactivates
	 * the current cursor, but this is just an optimization to terminate a
	 * cntbt search that otherwise runs to the edge of the tree.
	 */
	if (acur->diff == 0 && acur->len == args->maxlen)
		deactivate = true;
out:
	if (deactivate)
		cur->bc_ag.abt.active = false;
	trace_xfs_alloc_cur_check(args->mp, cur->bc_btnum, bno, len, diff,
				  *new);
	return 0;
}

/*
 * Complete an allocation of a candidate extent. Remove the extent from both
 * trees and update the args structure.
 */
STATIC int
xfs_alloc_cur_finish(
	struct xfs_alloc_arg	*args,
	struct xfs_alloc_cur	*acur)
{
	struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
	int			error;

	ASSERT(acur->cnt && acur->bnolt);
	ASSERT(acur->bno >= acur->rec_bno);
	ASSERT(acur->bno + acur->len <= acur->rec_bno + acur->rec_len);
	ASSERT(acur->rec_bno + acur->rec_len <= be32_to_cpu(agf->agf_length));

	error = xfs_alloc_fixup_trees(acur->cnt, acur->bnolt, acur->rec_bno,
				      acur->rec_len, acur->bno, acur->len, 0);
	if (error)
		return error;

	args->agbno = acur->bno;
	args->len = acur->len;
	args->wasfromfl = 0;

	trace_xfs_alloc_cur(args);
	return 0;
}

/*
 * Locality allocation lookup algorithm. This expects a cntbt cursor and uses
 * bno optimized lookup to search for extents with ideal size and locality.
 */
STATIC int
xfs_alloc_cntbt_iter(
	struct xfs_alloc_arg		*args,
	struct xfs_alloc_cur		*acur)
{
	struct xfs_btree_cur	*cur = acur->cnt;
	xfs_agblock_t		bno;
	xfs_extlen_t		len, cur_len;
	int			error;
	int			i;

	if (!xfs_alloc_cur_active(cur))
		return 0;

	/* locality optimized lookup */
	cur_len = acur->cur_len;
	error = xfs_alloc_lookup_ge(cur, args->agbno, cur_len, &i);
	if (error)
		return error;
	if (i == 0)
		return 0;
	error = xfs_alloc_get_rec(cur, &bno, &len, &i);
	if (error)
		return error;

	/* check the current record and update search length from it */
	error = xfs_alloc_cur_check(args, acur, cur, &i);
	if (error)
		return error;
	ASSERT(len >= acur->cur_len);
	acur->cur_len = len;

	/*
	 * We looked up the first record >= [agbno, len] above. The agbno is a
	 * secondary key and so the current record may lie just before or after
	 * agbno. If it is past agbno, check the previous record too so long as
	 * the length matches as it may be closer. Don't check a smaller record
	 * because that could deactivate our cursor.
	 */
	if (bno > args->agbno) {
		error = xfs_btree_decrement(cur, 0, &i);
		if (!error && i) {
			error = xfs_alloc_get_rec(cur, &bno, &len, &i);
			if (!error && i && len == acur->cur_len)
				error = xfs_alloc_cur_check(args, acur, cur,
							    &i);
		}
		if (error)
			return error;
	}

	/*
	 * Increment the search key until we find at least one allocation
	 * candidate or if the extent we found was larger. Otherwise, double the
	 * search key to optimize the search. Efficiency is more important here
	 * than absolute best locality.
	 */
	cur_len <<= 1;
	if (!acur->len || acur->cur_len >= cur_len)
		acur->cur_len++;
	else
		acur->cur_len = cur_len;

	return error;
}

/*
 * Deal with the case where only small freespaces remain. Either return the
 * contents of the last freespace record, or allocate space from the freelist if
 * there is nothing in the tree.
 */
STATIC int			/* error */
xfs_alloc_ag_vextent_small(
	struct xfs_alloc_arg	*args,	/* allocation argument structure */
	struct xfs_btree_cur	*ccur,	/* optional by-size cursor */
	xfs_agblock_t		*fbnop,	/* result block number */
	xfs_extlen_t		*flenp,	/* result length */
	int			*stat)	/* status: 0-freelist, 1-normal/none */
{
	struct xfs_agf		*agf = args->agbp->b_addr;
	int			error = 0;
	xfs_agblock_t		fbno = NULLAGBLOCK;
	xfs_extlen_t		flen = 0;
	int			i = 0;

	/*
	 * If a cntbt cursor is provided, try to allocate the largest record in
	 * the tree. Try the AGFL if the cntbt is empty, otherwise fail the
	 * allocation. Make sure to respect minleft even when pulling from the
	 * freelist.
	 */
	if (ccur)
		error = xfs_btree_decrement(ccur, 0, &i);
	if (error)
		goto error;
	if (i) {
		error = xfs_alloc_get_rec(ccur, &fbno, &flen, &i);
		if (error)
			goto error;
		if (XFS_IS_CORRUPT(args->mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error;
		}
		goto out;
	}

	if (args->minlen != 1 || args->alignment != 1 ||
	    args->resv == XFS_AG_RESV_AGFL ||
	    be32_to_cpu(agf->agf_flcount) <= args->minleft)
		goto out;

	error = xfs_alloc_get_freelist(args->pag, args->tp, args->agbp,
			&fbno, 0);
	if (error)
		goto error;
	if (fbno == NULLAGBLOCK)
		goto out;

	xfs_extent_busy_reuse(args->mp, args->pag, fbno, 1,
			      (args->datatype & XFS_ALLOC_NOBUSY));

	if (args->datatype & XFS_ALLOC_USERDATA) {
		struct xfs_buf	*bp;

		error = xfs_trans_get_buf(args->tp, args->mp->m_ddev_targp,
				XFS_AGB_TO_DADDR(args->mp, args->agno, fbno),
				args->mp->m_bsize, 0, &bp);
		if (error)
			goto error;
		xfs_trans_binval(args->tp, bp);
	}
	*fbnop = args->agbno = fbno;
	*flenp = args->len = 1;
	if (XFS_IS_CORRUPT(args->mp, fbno >= be32_to_cpu(agf->agf_length))) {
		error = -EFSCORRUPTED;
		goto error;
	}
	args->wasfromfl = 1;
	trace_xfs_alloc_small_freelist(args);

	/*
	 * If we're feeding an AGFL block to something that doesn't live in the
	 * free space, we need to clear out the OWN_AG rmap.
	 */
	error = xfs_rmap_free(args->tp, args->agbp, args->pag, fbno, 1,
			      &XFS_RMAP_OINFO_AG);
	if (error)
		goto error;

	*stat = 0;
	return 0;

out:
	/*
	 * Can't do the allocation, give up.
	 */
	if (flen < args->minlen) {
		args->agbno = NULLAGBLOCK;
		trace_xfs_alloc_small_notenough(args);
		flen = 0;
	}
	*fbnop = fbno;
	*flenp = flen;
	*stat = 1;
	trace_xfs_alloc_small_done(args);
	return 0;

error:
	trace_xfs_alloc_small_error(args);
	return error;
}

/*
 * Allocate a variable extent at exactly agno/bno.
 * Extent's length (returned in *len) will be between minlen and maxlen,
 * and of the form k * prod + mod unless there's nothing that large.
 * Return the starting a.g. block (bno), or NULLAGBLOCK if we can't do it.
 */
STATIC int			/* error */
xfs_alloc_ag_vextent_exact(
	xfs_alloc_arg_t	*args)	/* allocation argument structure */
{
	struct xfs_agf __maybe_unused *agf = args->agbp->b_addr;
	struct xfs_btree_cur *bno_cur;/* by block-number btree cursor */
	struct xfs_btree_cur *cnt_cur;/* by count btree cursor */
	int		error;
	xfs_agblock_t	fbno;	/* start block of found extent */
	xfs_extlen_t	flen;	/* length of found extent */
	xfs_agblock_t	tbno;	/* start block of busy extent */
	xfs_extlen_t	tlen;	/* length of busy extent */
	xfs_agblock_t	tend;	/* end block of busy extent */
	int		i;	/* success/failure of operation */
	unsigned	busy_gen;

	ASSERT(args->alignment == 1);

	/*
	 * Allocate/initialize a cursor for the by-number freespace btree.
	 */
	bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
					  args->pag, XFS_BTNUM_BNO);

	/*
	 * Lookup bno and minlen in the btree (minlen is irrelevant, really).
	 * Look for the closest free block <= bno, it must contain bno
	 * if any free block does.
	 */
	error = xfs_alloc_lookup_le(bno_cur, args->agbno, args->minlen, &i);
	if (error)
		goto error0;
	if (!i)
		goto not_found;

	/*
	 * Grab the freespace record.
	 */
	error = xfs_alloc_get_rec(bno_cur, &fbno, &flen, &i);
	if (error)
		goto error0;
	if (XFS_IS_CORRUPT(args->mp, i != 1)) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	ASSERT(fbno <= args->agbno);

	/*
	 * Check for overlapping busy extents.
	 */
	tbno = fbno;
	tlen = flen;
	xfs_extent_busy_trim(args, &tbno, &tlen, &busy_gen);

	/*
	 * Give up if the start of the extent is busy, or the freespace isn't
	 * long enough for the minimum request.
	 */
	if (tbno > args->agbno)
		goto not_found;
	if (tlen < args->minlen)
		goto not_found;
	tend = tbno + tlen;
	if (tend < args->agbno + args->minlen)
		goto not_found;

	/*
	 * End of extent will be smaller of the freespace end and the
	 * maximal requested end.
	 *
	 * Fix the length according to mod and prod if given.
	 */
	args->len = XFS_AGBLOCK_MIN(tend, args->agbno + args->maxlen)
						- args->agbno;
	xfs_alloc_fix_len(args);
	ASSERT(args->agbno + args->len <= tend);

	/*
	 * We are allocating agbno for args->len
	 * Allocate/initialize a cursor for the by-size btree.
	 */
	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
					args->pag, XFS_BTNUM_CNT);
	ASSERT(args->agbno + args->len <= be32_to_cpu(agf->agf_length));
	error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen, args->agbno,
				      args->len, XFSA_FIXUP_BNO_OK);
	if (error) {
		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_ERROR);
		goto error0;
	}

	xfs_btree_del_cursor(bno_cur, XFS_BTREE_NOERROR);
	xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);

	args->wasfromfl = 0;
	trace_xfs_alloc_exact_done(args);
	return 0;

not_found:
	/* Didn't find it, return null. */
	xfs_btree_del_cursor(bno_cur, XFS_BTREE_NOERROR);
	args->agbno = NULLAGBLOCK;
	trace_xfs_alloc_exact_notfound(args);
	return 0;

error0:
	xfs_btree_del_cursor(bno_cur, XFS_BTREE_ERROR);
	trace_xfs_alloc_exact_error(args);
	return error;
}

/*
 * Search a given number of btree records in a given direction. Check each
 * record against the good extent we've already found.
 */
STATIC int
xfs_alloc_walk_iter(
	struct xfs_alloc_arg	*args,
	struct xfs_alloc_cur	*acur,
	struct xfs_btree_cur	*cur,
	bool			increment,
	bool			find_one, /* quit on first candidate */
	int			count,    /* rec count (-1 for infinite) */
	int			*stat)
{
	int			error;
	int			i;

	*stat = 0;

	/*
	 * Search so long as the cursor is active or we find a better extent.
	 * The cursor is deactivated if it extends beyond the range of the
	 * current allocation candidate.
	 */
	while (xfs_alloc_cur_active(cur) && count) {
		error = xfs_alloc_cur_check(args, acur, cur, &i);
		if (error)
			return error;
		if (i == 1) {
			*stat = 1;
			if (find_one)
				break;
		}
		if (!xfs_alloc_cur_active(cur))
			break;

		if (increment)
			error = xfs_btree_increment(cur, 0, &i);
		else
			error = xfs_btree_decrement(cur, 0, &i);
		if (error)
			return error;
		if (i == 0)
			cur->bc_ag.abt.active = false;

		if (count > 0)
			count--;
	}

	return 0;
}

/*
 * Search the by-bno and by-size btrees in parallel in search of an extent with
 * ideal locality based on the NEAR mode ->agbno locality hint.
 */
STATIC int
xfs_alloc_ag_vextent_locality(
	struct xfs_alloc_arg	*args,
	struct xfs_alloc_cur	*acur,
	int			*stat)
{
	struct xfs_btree_cur	*fbcur = NULL;
	int			error;
	int			i;
	bool			fbinc;

	ASSERT(acur->len == 0);

	*stat = 0;

	error = xfs_alloc_lookup_ge(acur->cnt, args->agbno, acur->cur_len, &i);
	if (error)
		return error;
	error = xfs_alloc_lookup_le(acur->bnolt, args->agbno, 0, &i);
	if (error)
		return error;
	error = xfs_alloc_lookup_ge(acur->bnogt, args->agbno, 0, &i);
	if (error)
		return error;

	/*
	 * Search the bnobt and cntbt in parallel. Search the bnobt left and
	 * right and lookup the closest extent to the locality hint for each
	 * extent size key in the cntbt. The entire search terminates
	 * immediately on a bnobt hit because that means we've found best case
	 * locality. Otherwise the search continues until the cntbt cursor runs
	 * off the end of the tree. If no allocation candidate is found at this
	 * point, give up on locality, walk backwards from the end of the cntbt
	 * and take the first available extent.
	 *
	 * The parallel tree searches balance each other out to provide fairly
	 * consistent performance for various situations. The bnobt search can
	 * have pathological behavior in the worst case scenario of larger
	 * allocation requests and fragmented free space. On the other hand, the
	 * bnobt is able to satisfy most smaller allocation requests much more
	 * quickly than the cntbt. The cntbt search can sift through fragmented
	 * free space and sets of free extents for larger allocation requests
	 * more quickly than the bnobt. Since the locality hint is just a hint
	 * and we don't want to scan the entire bnobt for perfect locality, the
	 * cntbt search essentially bounds the bnobt search such that we can
	 * find good enough locality at reasonable performance in most cases.
	 */
	while (xfs_alloc_cur_active(acur->bnolt) ||
	       xfs_alloc_cur_active(acur->bnogt) ||
	       xfs_alloc_cur_active(acur->cnt)) {

		trace_xfs_alloc_cur_lookup(args);

		/*
		 * Search the bnobt left and right. In the case of a hit, finish
		 * the search in the opposite direction and we're done.
		 */
		error = xfs_alloc_walk_iter(args, acur, acur->bnolt, false,
					    true, 1, &i);
		if (error)
			return error;
		if (i == 1) {
			trace_xfs_alloc_cur_left(args);
			fbcur = acur->bnogt;
			fbinc = true;
			break;
		}
		error = xfs_alloc_walk_iter(args, acur, acur->bnogt, true, true,
					    1, &i);
		if (error)
			return error;
		if (i == 1) {
			trace_xfs_alloc_cur_right(args);
			fbcur = acur->bnolt;
			fbinc = false;
			break;
		}

		/*
		 * Check the extent with best locality based on the current
		 * extent size search key and keep track of the best candidate.
		 */
		error = xfs_alloc_cntbt_iter(args, acur);
		if (error)
			return error;
		if (!xfs_alloc_cur_active(acur->cnt)) {
			trace_xfs_alloc_cur_lookup_done(args);
			break;
		}
	}

	/*
	 * If we failed to find anything due to busy extents, return empty
	 * handed so the caller can flush and retry. If no busy extents were
	 * found, walk backwards from the end of the cntbt as a last resort.
	 */
	if (!xfs_alloc_cur_active(acur->cnt) && !acur->len && !acur->busy) {
		error = xfs_btree_decrement(acur->cnt, 0, &i);
		if (error)
			return error;
		if (i) {
			acur->cnt->bc_ag.abt.active = true;
			fbcur = acur->cnt;
			fbinc = false;
		}
	}

	/*
	 * Search in the opposite direction for a better entry in the case of
	 * a bnobt hit or walk backwards from the end of the cntbt.
	 */
	if (fbcur) {
		error = xfs_alloc_walk_iter(args, acur, fbcur, fbinc, true, -1,
					    &i);
		if (error)
			return error;
	}

	if (acur->len)
		*stat = 1;

	return 0;
}

/* Check the last block of the cnt btree for allocations. */
static int
xfs_alloc_ag_vextent_lastblock(
	struct xfs_alloc_arg	*args,
	struct xfs_alloc_cur	*acur,
	xfs_agblock_t		*bno,
	xfs_extlen_t		*len,
	bool			*allocated)
{
	int			error;
	int			i;

#ifdef DEBUG
	/* Randomly don't execute the first algorithm. */
	if (get_random_u32_below(2))
		return 0;
#endif

	/*
	 * Start from the entry that lookup found, sequence through all larger
	 * free blocks.  If we're actually pointing at a record smaller than
	 * maxlen, go to the start of this block, and skip all those smaller
	 * than minlen.
	 */
	if (*len || args->alignment > 1) {
		acur->cnt->bc_levels[0].ptr = 1;
		do {
			error = xfs_alloc_get_rec(acur->cnt, bno, len, &i);
			if (error)
				return error;
			if (XFS_IS_CORRUPT(args->mp, i != 1))
				return -EFSCORRUPTED;
			if (*len >= args->minlen)
				break;
			error = xfs_btree_increment(acur->cnt, 0, &i);
			if (error)
				return error;
		} while (i);
		ASSERT(*len >= args->minlen);
		if (!i)
			return 0;
	}

	error = xfs_alloc_walk_iter(args, acur, acur->cnt, true, false, -1, &i);
	if (error)
		return error;

	/*
	 * It didn't work.  We COULD be in a case where there's a good record
	 * somewhere, so try again.
	 */
	if (acur->len == 0)
		return 0;

	trace_xfs_alloc_near_first(args);
	*allocated = true;
	return 0;
}

/*
 * Allocate a variable extent near bno in the allocation group agno.
 * Extent's length (returned in len) will be between minlen and maxlen,
 * and of the form k * prod + mod unless there's nothing that large.
 * Return the starting a.g. block, or NULLAGBLOCK if we can't do it.
 */
STATIC int
xfs_alloc_ag_vextent_near(
	struct xfs_alloc_arg	*args,
	uint32_t		alloc_flags)
{
	struct xfs_alloc_cur	acur = {};
	int			error;		/* error code */
	int			i;		/* result code, temporary */
	xfs_agblock_t		bno;
	xfs_extlen_t		len;

	/* handle uninitialized agbno range so caller doesn't have to */
	if (!args->min_agbno && !args->max_agbno)
		args->max_agbno = args->mp->m_sb.sb_agblocks - 1;
	ASSERT(args->min_agbno <= args->max_agbno);

	/* clamp agbno to the range if it's outside */
	if (args->agbno < args->min_agbno)
		args->agbno = args->min_agbno;
	if (args->agbno > args->max_agbno)
		args->agbno = args->max_agbno;

	/* Retry once quickly if we find busy extents before blocking. */
	alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH;
restart:
	len = 0;

	/*
	 * Set up cursors and see if there are any free extents as big as
	 * maxlen. If not, pick the last entry in the tree unless the tree is
	 * empty.
	 */
	error = xfs_alloc_cur_setup(args, &acur);
	if (error == -ENOSPC) {
		error = xfs_alloc_ag_vextent_small(args, acur.cnt, &bno,
				&len, &i);
		if (error)
			goto out;
		if (i == 0 || len == 0) {
			trace_xfs_alloc_near_noentry(args);
			goto out;
		}
		ASSERT(i == 1);
	} else if (error) {
		goto out;
	}

	/*
	 * First algorithm.
	 * If the requested extent is large wrt the freespaces available
	 * in this a.g., then the cursor will be pointing to a btree entry
	 * near the right edge of the tree.  If it's in the last btree leaf
	 * block, then we just examine all the entries in that block
	 * that are big enough, and pick the best one.
	 */
	if (xfs_btree_islastblock(acur.cnt, 0)) {
		bool		allocated = false;

		error = xfs_alloc_ag_vextent_lastblock(args, &acur, &bno, &len,
				&allocated);
		if (error)
			goto out;
		if (allocated)
			goto alloc_finish;
	}

	/*
	 * Second algorithm. Combined cntbt and bnobt search to find ideal
	 * locality.
	 */
	error = xfs_alloc_ag_vextent_locality(args, &acur, &i);
	if (error)
		goto out;

	/*
	 * If we couldn't get anything, give up.
	 */
	if (!acur.len) {
		if (acur.busy) {
			/*
			 * Our only valid extents must have been busy. Flush and
			 * retry the allocation again. If we get an -EAGAIN
			 * error, we're being told that a deadlock was avoided
			 * and the current transaction needs committing before
			 * the allocation can be retried.
			 */
			trace_xfs_alloc_near_busy(args);
			error = xfs_extent_busy_flush(args->tp, args->pag,
					acur.busy_gen, alloc_flags);
			if (error)
				goto out;

			alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
			goto restart;
		}
		trace_xfs_alloc_size_neither(args);
		args->agbno = NULLAGBLOCK;
		goto out;
	}

alloc_finish:
	/* fix up btrees on a successful allocation */
	error = xfs_alloc_cur_finish(args, &acur);

out:
	xfs_alloc_cur_close(&acur, error);
	return error;
}

/*
 * Allocate a variable extent anywhere in the allocation group agno.
 * Extent's length (returned in len) will be between minlen and maxlen,
 * and of the form k * prod + mod unless there's nothing that large.
 * Return the starting a.g. block, or NULLAGBLOCK if we can't do it.
 */
static int
xfs_alloc_ag_vextent_size(
	struct xfs_alloc_arg	*args,
	uint32_t		alloc_flags)
{
	struct xfs_agf		*agf = args->agbp->b_addr;
	struct xfs_btree_cur	*bno_cur;
	struct xfs_btree_cur	*cnt_cur;
	xfs_agblock_t		fbno;		/* start of found freespace */
	xfs_extlen_t		flen;		/* length of found freespace */
	xfs_agblock_t		rbno;		/* returned block number */
	xfs_extlen_t		rlen;		/* length of returned extent */
	bool			busy;
	unsigned		busy_gen;
	int			error;
	int			i;

	/* Retry once quickly if we find busy extents before blocking. */
	alloc_flags |= XFS_ALLOC_FLAG_TRYFLUSH;
restart:
	/*
	 * Allocate and initialize a cursor for the by-size btree.
	 */
	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
					args->pag, XFS_BTNUM_CNT);
	bno_cur = NULL;

	/*
	 * Look for an entry >= maxlen+alignment-1 blocks.
	 */
	if ((error = xfs_alloc_lookup_ge(cnt_cur, 0,
			args->maxlen + args->alignment - 1, &i)))
		goto error0;

	/*
	 * If none then we have to settle for a smaller extent. In the case that
	 * there are no large extents, this will return the last entry in the
	 * tree unless the tree is empty. In the case that there are only busy
	 * large extents, this will return the largest small extent unless there
	 * are no smaller extents available.
	 */
	if (!i) {
		error = xfs_alloc_ag_vextent_small(args, cnt_cur,
						   &fbno, &flen, &i);
		if (error)
			goto error0;
		if (i == 0 || flen == 0) {
			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
			trace_xfs_alloc_size_noentry(args);
			return 0;
		}
		ASSERT(i == 1);
		busy = xfs_alloc_compute_aligned(args, fbno, flen, &rbno,
				&rlen, &busy_gen);
	} else {
		/*
		 * Search for a non-busy extent that is large enough.
		 */
		for (;;) {
			error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i);
			if (error)
				goto error0;
			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
				error = -EFSCORRUPTED;
				goto error0;
			}

			busy = xfs_alloc_compute_aligned(args, fbno, flen,
					&rbno, &rlen, &busy_gen);

			if (rlen >= args->maxlen)
				break;

			error = xfs_btree_increment(cnt_cur, 0, &i);
			if (error)
				goto error0;
			if (i)
				continue;

			/*
			 * Our only valid extents must have been busy. Flush and
			 * retry the allocation again. If we get an -EAGAIN
			 * error, we're being told that a deadlock was avoided
			 * and the current transaction needs committing before
			 * the allocation can be retried.
			 */
			trace_xfs_alloc_size_busy(args);
			error = xfs_extent_busy_flush(args->tp, args->pag,
					busy_gen, alloc_flags);
			if (error)
				goto error0;

			alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
			goto restart;
		}
	}

	/*
	 * In the first case above, we got the last entry in the
	 * by-size btree.  Now we check to see if the space hits maxlen
	 * once aligned; if not, we search left for something better.
	 * This can't happen in the second case above.
	 */
	rlen = XFS_EXTLEN_MIN(args->maxlen, rlen);
	if (XFS_IS_CORRUPT(args->mp,
			   rlen != 0 &&
			   (rlen > flen ||
			    rbno + rlen > fbno + flen))) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	if (rlen < args->maxlen) {
		xfs_agblock_t	bestfbno;
		xfs_extlen_t	bestflen;
		xfs_agblock_t	bestrbno;
		xfs_extlen_t	bestrlen;

		bestrlen = rlen;
		bestrbno = rbno;
		bestflen = flen;
		bestfbno = fbno;
		for (;;) {
			if ((error = xfs_btree_decrement(cnt_cur, 0, &i)))
				goto error0;
			if (i == 0)
				break;
			if ((error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen,
					&i)))
				goto error0;
			if (XFS_IS_CORRUPT(args->mp, i != 1)) {
				error = -EFSCORRUPTED;
				goto error0;
			}
			if (flen < bestrlen)
				break;
			busy = xfs_alloc_compute_aligned(args, fbno, flen,
					&rbno, &rlen, &busy_gen);
			rlen = XFS_EXTLEN_MIN(args->maxlen, rlen);
			if (XFS_IS_CORRUPT(args->mp,
					   rlen != 0 &&
					   (rlen > flen ||
					    rbno + rlen > fbno + flen))) {
				error = -EFSCORRUPTED;
				goto error0;
			}
			if (rlen > bestrlen) {
				bestrlen = rlen;
				bestrbno = rbno;
				bestflen = flen;
				bestfbno = fbno;
				if (rlen == args->maxlen)
					break;
			}
		}
		if ((error = xfs_alloc_lookup_eq(cnt_cur, bestfbno, bestflen,
				&i)))
			goto error0;
		if (XFS_IS_CORRUPT(args->mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		rlen = bestrlen;
		rbno = bestrbno;
		flen = bestflen;
		fbno = bestfbno;
	}
	args->wasfromfl = 0;
	/*
	 * Fix up the length.
	 */
	args->len = rlen;
	if (rlen < args->minlen) {
		if (busy) {
			/*
			 * Our only valid extents must have been busy. Flush and
			 * retry the allocation again. If we get an -EAGAIN
			 * error, we're being told that a deadlock was avoided
			 * and the current transaction needs committing before
			 * the allocation can be retried.
			 */
			trace_xfs_alloc_size_busy(args);
			error = xfs_extent_busy_flush(args->tp, args->pag,
					busy_gen, alloc_flags);
			if (error)
				goto error0;

			alloc_flags &= ~XFS_ALLOC_FLAG_TRYFLUSH;
			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
			goto restart;
		}
		goto out_nominleft;
	}
	xfs_alloc_fix_len(args);

	rlen = args->len;
	if (XFS_IS_CORRUPT(args->mp, rlen > flen)) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	/*
	 * Allocate and initialize a cursor for the by-block tree.
	 */
	bno_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
					args->pag, XFS_BTNUM_BNO);
	if ((error = xfs_alloc_fixup_trees(cnt_cur, bno_cur, fbno, flen,
			rbno, rlen, XFSA_FIXUP_CNT_OK)))
		goto error0;
	xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
	xfs_btree_del_cursor(bno_cur, XFS_BTREE_NOERROR);
	cnt_cur = bno_cur = NULL;
	args->len = rlen;
	args->agbno = rbno;
	if (XFS_IS_CORRUPT(args->mp,
			   args->agbno + args->len >
			   be32_to_cpu(agf->agf_length))) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	trace_xfs_alloc_size_done(args);
	return 0;

error0:
	trace_xfs_alloc_size_error(args);
	if (cnt_cur)
		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_ERROR);
	if (bno_cur)
		xfs_btree_del_cursor(bno_cur, XFS_BTREE_ERROR);
	return error;

out_nominleft:
	xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
	trace_xfs_alloc_size_nominleft(args);
	args->agbno = NULLAGBLOCK;
	return 0;
}

/*
 * Free the extent starting at agno/bno for length.
 */
STATIC int
xfs_free_ag_extent(
	struct xfs_trans		*tp,
	struct xfs_buf			*agbp,
	xfs_agnumber_t			agno,
	xfs_agblock_t			bno,
	xfs_extlen_t			len,
	const struct xfs_owner_info	*oinfo,
	enum xfs_ag_resv_type		type)
{
	struct xfs_mount		*mp;
	struct xfs_btree_cur		*bno_cur;
	struct xfs_btree_cur		*cnt_cur;
	xfs_agblock_t			gtbno; /* start of right neighbor */
	xfs_extlen_t			gtlen; /* length of right neighbor */
	xfs_agblock_t			ltbno; /* start of left neighbor */
	xfs_extlen_t			ltlen; /* length of left neighbor */
	xfs_agblock_t			nbno; /* new starting block of freesp */
	xfs_extlen_t			nlen; /* new length of freespace */
	int				haveleft; /* have a left neighbor */
	int				haveright; /* have a right neighbor */
	int				i;
	int				error;
	struct xfs_perag		*pag = agbp->b_pag;

	bno_cur = cnt_cur = NULL;
	mp = tp->t_mountp;

	if (!xfs_rmap_should_skip_owner_update(oinfo)) {
		error = xfs_rmap_free(tp, agbp, pag, bno, len, oinfo);
		if (error)
			goto error0;
	}

	/*
	 * Allocate and initialize a cursor for the by-block btree.
	 */
	bno_cur = xfs_allocbt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_BNO);
	/*
	 * Look for a neighboring block on the left (lower block numbers)
	 * that is contiguous with this space.
	 */
	if ((error = xfs_alloc_lookup_le(bno_cur, bno, len, &haveleft)))
		goto error0;
	if (haveleft) {
		/*
		 * There is a block to our left.
		 */
		if ((error = xfs_alloc_get_rec(bno_cur, &ltbno, &ltlen, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		/*
		 * It's not contiguous, though.
		 */
		if (ltbno + ltlen < bno)
			haveleft = 0;
		else {
			/*
			 * If this failure happens the request to free this
			 * space was invalid, it's (partly) already free.
			 * Very bad.
			 */
			if (XFS_IS_CORRUPT(mp, ltbno + ltlen > bno)) {
				error = -EFSCORRUPTED;
				goto error0;
			}
		}
	}
	/*
	 * Look for a neighboring block on the right (higher block numbers)
	 * that is contiguous with this space.
	 */
	if ((error = xfs_btree_increment(bno_cur, 0, &haveright)))
		goto error0;
	if (haveright) {
		/*
		 * There is a block to our right.
		 */
		if ((error = xfs_alloc_get_rec(bno_cur, &gtbno, &gtlen, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		/*
		 * It's not contiguous, though.
		 */
		if (bno + len < gtbno)
			haveright = 0;
		else {
			/*
			 * If this failure happens the request to free this
			 * space was invalid, it's (partly) already free.
			 * Very bad.
			 */
			if (XFS_IS_CORRUPT(mp, bno + len > gtbno)) {
				error = -EFSCORRUPTED;
				goto error0;
			}
		}
	}
	/*
	 * Now allocate and initialize a cursor for the by-size tree.
	 */
	cnt_cur = xfs_allocbt_init_cursor(mp, tp, agbp, pag, XFS_BTNUM_CNT);
	/*
	 * Have both left and right contiguous neighbors.
	 * Merge all three into a single free block.
	 */
	if (haveleft && haveright) {
		/*
		 * Delete the old by-size entry on the left.
		 */
		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		if ((error = xfs_btree_delete(cnt_cur, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		/*
		 * Delete the old by-size entry on the right.
		 */
		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		if ((error = xfs_btree_delete(cnt_cur, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		/*
		 * Delete the old by-block entry for the right block.
		 */
		if ((error = xfs_btree_delete(bno_cur, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		/*
		 * Move the by-block cursor back to the left neighbor.
		 */
		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
#ifdef DEBUG
		/*
		 * Check that this is the right record: delete didn't
		 * mangle the cursor.
		 */
		{
			xfs_agblock_t	xxbno;
			xfs_extlen_t	xxlen;

			if ((error = xfs_alloc_get_rec(bno_cur, &xxbno, &xxlen,
					&i)))
				goto error0;
			if (XFS_IS_CORRUPT(mp,
					   i != 1 ||
					   xxbno != ltbno ||
					   xxlen != ltlen)) {
				error = -EFSCORRUPTED;
				goto error0;
			}
		}
#endif
		/*
		 * Update remaining by-block entry to the new, joined block.
		 */
		nbno = ltbno;
		nlen = len + ltlen + gtlen;
		if ((error = xfs_alloc_update(bno_cur, nbno, nlen)))
			goto error0;
	}
	/*
	 * Have only a left contiguous neighbor.
	 * Merge it together with the new freespace.
	 */
	else if (haveleft) {
		/*
		 * Delete the old by-size entry on the left.
		 */
		if ((error = xfs_alloc_lookup_eq(cnt_cur, ltbno, ltlen, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		if ((error = xfs_btree_delete(cnt_cur, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		/*
		 * Back up the by-block cursor to the left neighbor, and
		 * update its length.
		 */
		if ((error = xfs_btree_decrement(bno_cur, 0, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		nbno = ltbno;
		nlen = len + ltlen;
		if ((error = xfs_alloc_update(bno_cur, nbno, nlen)))
			goto error0;
	}
	/*
	 * Have only a right contiguous neighbor.
	 * Merge it together with the new freespace.
	 */
	else if (haveright) {
		/*
		 * Delete the old by-size entry on the right.
		 */
		if ((error = xfs_alloc_lookup_eq(cnt_cur, gtbno, gtlen, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		if ((error = xfs_btree_delete(cnt_cur, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
		/*
		 * Update the starting block and length of the right
		 * neighbor in the by-block tree.
		 */
		nbno = bno;
		nlen = len + gtlen;
		if ((error = xfs_alloc_update(bno_cur, nbno, nlen)))
			goto error0;
	}
	/*
	 * No contiguous neighbors.
	 * Insert the new freespace into the by-block tree.
	 */
	else {
		nbno = bno;
		nlen = len;
		if ((error = xfs_btree_insert(bno_cur, &i)))
			goto error0;
		if (XFS_IS_CORRUPT(mp, i != 1)) {
			error = -EFSCORRUPTED;
			goto error0;
		}
	}
	xfs_btree_del_cursor(bno_cur, XFS_BTREE_NOERROR);
	bno_cur = NULL;
	/*
	 * In all cases we need to insert the new freespace in the by-size tree.
	 */
	if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i)))
		goto error0;
	if (XFS_IS_CORRUPT(mp, i != 0)) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	if ((error = xfs_btree_insert(cnt_cur, &i)))
		goto error0;
	if (XFS_IS_CORRUPT(mp, i != 1)) {
		error = -EFSCORRUPTED;
		goto error0;
	}
	xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
	cnt_cur = NULL;

	/*
	 * Update the freespace totals in the ag and superblock.
	 */
	error = xfs_alloc_update_counters(tp, agbp, len);
	xfs_ag_resv_free_extent(agbp->b_pag, type, tp, len);
	if (error)
		goto error0;

	XFS_STATS_INC(mp, xs_freex);
	XFS_STATS_ADD(mp, xs_freeb, len);

	trace_xfs_free_extent(mp, agno, bno, len, type, haveleft, haveright);

	return 0;

 error0:
	trace_xfs_free_extent(mp, agno, bno, len, type, -1, -1);
	if (bno_cur)
		xfs_btree_del_cursor(bno_cur, XFS_BTREE_ERROR);
	if (cnt_cur)
		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_ERROR);
	return error;
}

/*
 * Visible (exported) allocation/free functions.
 * Some of these are used just by xfs_alloc_btree.c and this file.
 */

/*
 * Compute and fill in value of m_alloc_maxlevels.
 */
void
xfs_alloc_compute_maxlevels(
	xfs_mount_t	*mp)	/* file system mount structure */
{
	mp->m_alloc_maxlevels = xfs_btree_compute_maxlevels(mp->m_alloc_mnr,
			(mp->m_sb.sb_agblocks + 1) / 2);
	ASSERT(mp->m_alloc_maxlevels <= xfs_allocbt_maxlevels_ondisk());
}

/*
 * Find the length of the longest extent in an AG.  The 'need' parameter
 * specifies how much space we're going to need for the AGFL and the
 * 'reserved' parameter tells us how many blocks in this AG are reserved for
 * other callers.
 */
xfs_extlen_t
xfs_alloc_longest_free_extent(
	struct xfs_perag	*pag,
	xfs_extlen_t		need,
	xfs_extlen_t		reserved)
{
	xfs_extlen_t		delta = 0;

	/*
	 * If the AGFL needs a recharge, we'll have to subtract that from the
	 * longest extent.
	 */
	if (need > pag->pagf_flcount)
		delta = need - pag->pagf_flcount;

	/*
	 * If we cannot maintain others' reservations with space from the
	 * not-longest freesp extents, we'll have to subtract /that/ from
	 * the longest extent too.
	 */
	if (pag->pagf_freeblks - pag->pagf_longest < reserved)
		delta += reserved - (pag->pagf_freeblks - pag->pagf_longest);

	/*
	 * If the longest extent is long enough to satisfy all the
	 * reservations and AGFL rules in place, we can return this extent.
	 */
	if (pag->pagf_longest > delta)
		return min_t(xfs_extlen_t, pag->pag_mount->m_ag_max_usable,
				pag->pagf_longest - delta);

	/* Otherwise, let the caller try for 1 block if there's space. */
	return pag->pagf_flcount > 0 || pag->pagf_longest > 0;
}

/*
 * Compute the minimum length of the AGFL in the given AG.  If @pag is NULL,
 * return the largest possible minimum length.
 */
unsigned int
xfs_alloc_min_freelist(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag)
{
	/* AG btrees have at least 1 level. */
	static const uint8_t	fake_levels[XFS_BTNUM_AGF] = {1, 1, 1};
	const uint8_t		*levels = pag ? pag->pagf_levels : fake_levels;
	unsigned int		min_free;

	ASSERT(mp->m_alloc_maxlevels > 0);

	/*
	 * For a btree shorter than the maximum height, the worst case is that
	 * every level gets split and a new level is added, then while inserting
	 * another entry to refill the AGFL, every level under the old root gets
	 * split again. This is:
	 *
	 *   (full height split reservation) + (AGFL refill split height)
	 * = (current height + 1) + (current height - 1)
	 * = (new height) + (new height - 2)
	 * = 2 * new height - 2
	 *
	 * For a btree of maximum height, the worst case is that every level
	 * under the root gets split, then while inserting another entry to
	 * refill the AGFL, every level under the root gets split again. This is
	 * also:
	 *
	 *   2 * (current height - 1)
	 * = 2 * (new height - 1)
	 * = 2 * new height - 2
	 */

	/* space needed by-bno freespace btree */
	min_free = min_t(unsigned int, levels[XFS_BTNUM_BNOi] + 1,
				       mp->m_alloc_maxlevels) * 2 - 2;
	/* space needed by-size freespace btree */
	min_free += min_t(unsigned int, levels[XFS_BTNUM_CNTi] + 1,
				       mp->m_alloc_maxlevels) * 2 - 2;
	/* space needed reverse mapping used space btree */
	if (xfs_has_rmapbt(mp))
		min_free += min_t(unsigned int, levels[XFS_BTNUM_RMAPi] + 1,
						mp->m_rmap_maxlevels) * 2 - 2;

	return min_free;
}

/*
 * Check if the operation we are fixing up the freelist for should go ahead or
 * not. If we are freeing blocks, we always allow it, otherwise the allocation
 * is dependent on whether the size and shape of free space available will
 * permit the requested allocation to take place.
 */
static bool
xfs_alloc_space_available(
	struct xfs_alloc_arg	*args,
	xfs_extlen_t		min_free,
	int			flags)
{
	struct xfs_perag	*pag = args->pag;
	xfs_extlen_t		alloc_len, longest;
	xfs_extlen_t		reservation; /* blocks that are still reserved */
	int			available;
	xfs_extlen_t		agflcount;

	if (flags & XFS_ALLOC_FLAG_FREEING)
		return true;

	reservation = xfs_ag_resv_needed(pag, args->resv);

	/* do we have enough contiguous free space for the allocation? */
	alloc_len = args->minlen + (args->alignment - 1) + args->minalignslop;
	longest = xfs_alloc_longest_free_extent(pag, min_free, reservation);
	if (longest < alloc_len)
		return false;

	/*
	 * Do we have enough free space remaining for the allocation? Don't
	 * account extra agfl blocks because we are about to defer free them,
	 * making them unavailable until the current transaction commits.
	 */
	agflcount = min_t(xfs_extlen_t, pag->pagf_flcount, min_free);
	available = (int)(pag->pagf_freeblks + agflcount -
			  reservation - min_free - args->minleft);
	if (available < (int)max(args->total, alloc_len))
		return false;

	/*
	 * Clamp maxlen to the amount of free space available for the actual
	 * extent allocation.
	 */
	if (available < (int)args->maxlen && !(flags & XFS_ALLOC_FLAG_CHECK)) {
		args->maxlen = available;
		ASSERT(args->maxlen > 0);
		ASSERT(args->maxlen >= args->minlen);
	}

	return true;
}

int
xfs_free_agfl_block(
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		agbno,
	struct xfs_buf		*agbp,
	struct xfs_owner_info	*oinfo)
{
	int			error;
	struct xfs_buf		*bp;

	error = xfs_free_ag_extent(tp, agbp, agno, agbno, 1, oinfo,
				   XFS_AG_RESV_AGFL);
	if (error)
		return error;

	error = xfs_trans_get_buf(tp, tp->t_mountp->m_ddev_targp,
			XFS_AGB_TO_DADDR(tp->t_mountp, agno, agbno),
			tp->t_mountp->m_bsize, 0, &bp);
	if (error)
		return error;
	xfs_trans_binval(tp, bp);

	return 0;
}

/*
 * Check the agfl fields of the agf for inconsistency or corruption.
 *
 * The original purpose was to detect an agfl header padding mismatch between
 * current and early v5 kernels. This problem manifests as a 1-slot size
 * difference between the on-disk flcount and the active [first, last] range of
 * a wrapped agfl.
 *
 * However, we need to use these same checks to catch agfl count corruptions
 * unrelated to padding. This could occur on any v4 or v5 filesystem, so either
 * way, we need to reset the agfl and warn the user.
 *
 * Return true if a reset is required before the agfl can be used, false
 * otherwise.
 */
static bool
xfs_agfl_needs_reset(
	struct xfs_mount	*mp,
	struct xfs_agf		*agf)
{
	uint32_t		f = be32_to_cpu(agf->agf_flfirst);
	uint32_t		l = be32_to_cpu(agf->agf_fllast);
	uint32_t		c = be32_to_cpu(agf->agf_flcount);
	int			agfl_size = xfs_agfl_size(mp);
	int			active;

	/*
	 * The agf read verifier catches severe corruption of these fields.
	 * Repeat some sanity checks to cover a packed -> unpacked mismatch if
	 * the verifier allows it.
	 */
	if (f >= agfl_size || l >= agfl_size)
		return true;
	if (c > agfl_size)
		return true;

	/*
	 * Check consistency between the on-disk count and the active range. An
	 * agfl padding mismatch manifests as an inconsistent flcount.
	 */
	if (c && l >= f)
		active = l - f + 1;
	else if (c)
		active = agfl_size - f + l + 1;
	else
		active = 0;

	return active != c;
}

/*
 * Reset the agfl to an empty state. Ignore/drop any existing blocks since the
 * agfl content cannot be trusted. Warn the user that a repair is required to
 * recover leaked blocks.
 *
 * The purpose of this mechanism is to handle filesystems affected by the agfl
 * header padding mismatch problem. A reset keeps the filesystem online with a
 * relatively minor free space accounting inconsistency rather than suffer the
 * inevitable crash from use of an invalid agfl block.
 */
static void
xfs_agfl_reset(
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	struct xfs_perag	*pag)
{
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_agf		*agf = agbp->b_addr;

	ASSERT(xfs_perag_agfl_needs_reset(pag));
	trace_xfs_agfl_reset(mp, agf, 0, _RET_IP_);

	xfs_warn(mp,
	       "WARNING: Reset corrupted AGFL on AG %u. %d blocks leaked. "
	       "Please unmount and run xfs_repair.",
	         pag->pag_agno, pag->pagf_flcount);

	agf->agf_flfirst = 0;
	agf->agf_fllast = cpu_to_be32(xfs_agfl_size(mp) - 1);
	agf->agf_flcount = 0;
	xfs_alloc_log_agf(tp, agbp, XFS_AGF_FLFIRST | XFS_AGF_FLLAST |
				    XFS_AGF_FLCOUNT);

	pag->pagf_flcount = 0;
	clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
}

/*
 * Defer an AGFL block free. This is effectively equivalent to
 * xfs_free_extent_later() with some special handling particular to AGFL blocks.
 *
 * Deferring AGFL frees helps prevent log reservation overruns due to too many
 * allocation operations in a transaction. AGFL frees are prone to this problem
 * because for one they are always freed one at a time. Further, an immediate
 * AGFL block free can cause a btree join and require another block free before
 * the real allocation can proceed. Deferring the free disconnects freeing up
 * the AGFL slot from freeing the block.
 */
static int
xfs_defer_agfl_block(
	struct xfs_trans		*tp,
	xfs_agnumber_t			agno,
	xfs_agblock_t			agbno,
	struct xfs_owner_info		*oinfo)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_extent_free_item	*xefi;
	xfs_fsblock_t			fsbno = XFS_AGB_TO_FSB(mp, agno, agbno);

	ASSERT(xfs_extfree_item_cache != NULL);
	ASSERT(oinfo != NULL);

	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, fsbno)))
		return -EFSCORRUPTED;

	xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
			       GFP_KERNEL | __GFP_NOFAIL);
	xefi->xefi_startblock = fsbno;
	xefi->xefi_blockcount = 1;
	xefi->xefi_owner = oinfo->oi_owner;
	xefi->xefi_agresv = XFS_AG_RESV_AGFL;

	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);

	xfs_extent_free_get_group(mp, xefi);
	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list);
	return 0;
}

/*
 * Add the extent to the list of extents to be free at transaction end.
 * The list is maintained sorted (by block number).
 */
int
__xfs_free_extent_later(
	struct xfs_trans		*tp,
	xfs_fsblock_t			bno,
	xfs_filblks_t			len,
	const struct xfs_owner_info	*oinfo,
	enum xfs_ag_resv_type		type,
	bool				skip_discard)
{
	struct xfs_extent_free_item	*xefi;
	struct xfs_mount		*mp = tp->t_mountp;
#ifdef DEBUG
	xfs_agnumber_t			agno;
	xfs_agblock_t			agbno;

	ASSERT(bno != NULLFSBLOCK);
	ASSERT(len > 0);
	ASSERT(len <= XFS_MAX_BMBT_EXTLEN);
	ASSERT(!isnullstartblock(bno));
	agno = XFS_FSB_TO_AGNO(mp, bno);
	agbno = XFS_FSB_TO_AGBNO(mp, bno);
	ASSERT(agno < mp->m_sb.sb_agcount);
	ASSERT(agbno < mp->m_sb.sb_agblocks);
	ASSERT(len < mp->m_sb.sb_agblocks);
	ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
#endif
	ASSERT(xfs_extfree_item_cache != NULL);
	ASSERT(type != XFS_AG_RESV_AGFL);

	if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
		return -EFSCORRUPTED;

	xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
			       GFP_KERNEL | __GFP_NOFAIL);
	xefi->xefi_startblock = bno;
	xefi->xefi_blockcount = (xfs_extlen_t)len;
	xefi->xefi_agresv = type;
	if (skip_discard)
		xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD;
	if (oinfo) {
		ASSERT(oinfo->oi_offset == 0);

		if (oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK)
			xefi->xefi_flags |= XFS_EFI_ATTR_FORK;
		if (oinfo->oi_flags & XFS_OWNER_INFO_BMBT_BLOCK)
			xefi->xefi_flags |= XFS_EFI_BMBT_BLOCK;
		xefi->xefi_owner = oinfo->oi_owner;
	} else {
		xefi->xefi_owner = XFS_RMAP_OWN_NULL;
	}
	trace_xfs_bmap_free_defer(mp,
			XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);

	xfs_extent_free_get_group(mp, xefi);
	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list);
	return 0;
}

#ifdef DEBUG
/*
 * Check if an AGF has a free extent record whose length is equal to
 * args->minlen.
 */
STATIC int
xfs_exact_minlen_extent_available(
	struct xfs_alloc_arg	*args,
	struct xfs_buf		*agbp,
	int			*stat)
{
	struct xfs_btree_cur	*cnt_cur;
	xfs_agblock_t		fbno;
	xfs_extlen_t		flen;
	int			error = 0;

	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, agbp,
					args->pag, XFS_BTNUM_CNT);
	error = xfs_alloc_lookup_ge(cnt_cur, 0, args->minlen, stat);
	if (error)
		goto out;

	if (*stat == 0) {
		error = -EFSCORRUPTED;
		goto out;
	}

	error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, stat);
	if (error)
		goto out;

	if (*stat == 1 && flen != args->minlen)
		*stat = 0;

out:
	xfs_btree_del_cursor(cnt_cur, error);

	return error;
}
#endif

/*
 * Decide whether to use this allocation group for this allocation.
 * If so, fix up the btree freelist's size.
 */
int			/* error */
xfs_alloc_fix_freelist(
	struct xfs_alloc_arg	*args,	/* allocation argument structure */
	uint32_t		alloc_flags)
{
	struct xfs_mount	*mp = args->mp;
	struct xfs_perag	*pag = args->pag;
	struct xfs_trans	*tp = args->tp;
	struct xfs_buf		*agbp = NULL;
	struct xfs_buf		*agflbp = NULL;
	struct xfs_alloc_arg	targs;	/* local allocation arguments */
	xfs_agblock_t		bno;	/* freelist block */
	xfs_extlen_t		need;	/* total blocks needed in freelist */
	int			error = 0;

	/* deferred ops (AGFL block frees) require permanent transactions */
	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);

	if (!xfs_perag_initialised_agf(pag)) {
		error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp);
		if (error) {
			/* Couldn't lock the AGF so skip this AG. */
			if (error == -EAGAIN)
				error = 0;
			goto out_no_agbp;
		}
	}

	/*
	 * If this is a metadata preferred pag and we are user data then try
	 * somewhere else if we are not being asked to try harder at this
	 * point
	 */
	if (xfs_perag_prefers_metadata(pag) &&
	    (args->datatype & XFS_ALLOC_USERDATA) &&
	    (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)) {
		ASSERT(!(alloc_flags & XFS_ALLOC_FLAG_FREEING));
		goto out_agbp_relse;
	}

	need = xfs_alloc_min_freelist(mp, pag);
	if (!xfs_alloc_space_available(args, need, alloc_flags |
			XFS_ALLOC_FLAG_CHECK))
		goto out_agbp_relse;

	/*
	 * Get the a.g. freespace buffer.
	 * Can fail if we're not blocking on locks, and it's held.
	 */
	if (!agbp) {
		error = xfs_alloc_read_agf(pag, tp, alloc_flags, &agbp);
		if (error) {
			/* Couldn't lock the AGF so skip this AG. */
			if (error == -EAGAIN)
				error = 0;
			goto out_no_agbp;
		}
	}

	/* reset a padding mismatched agfl before final free space check */
	if (xfs_perag_agfl_needs_reset(pag))
		xfs_agfl_reset(tp, agbp, pag);

	/* If there isn't enough total space or single-extent, reject it. */
	need = xfs_alloc_min_freelist(mp, pag);
	if (!xfs_alloc_space_available(args, need, alloc_flags))
		goto out_agbp_relse;

#ifdef DEBUG
	if (args->alloc_minlen_only) {
		int stat;

		error = xfs_exact_minlen_extent_available(args, agbp, &stat);
		if (error || !stat)
			goto out_agbp_relse;
	}
#endif
	/*
	 * Make the freelist shorter if it's too long.
	 *
	 * Note that from this point onwards, we will always release the agf and
	 * agfl buffers on error. This handles the case where we error out and
	 * the buffers are clean or may not have been joined to the transaction
	 * and hence need to be released manually. If they have been joined to
	 * the transaction, then xfs_trans_brelse() will handle them
	 * appropriately based on the recursion count and dirty state of the
	 * buffer.
	 *
	 * XXX (dgc): When we have lots of free space, does this buy us
	 * anything other than extra overhead when we need to put more blocks
	 * back on the free list? Maybe we should only do this when space is
	 * getting low or the AGFL is more than half full?
	 *
	 * The NOSHRINK flag prevents the AGFL from being shrunk if it's too
	 * big; the NORMAP flag prevents AGFL expand/shrink operations from
	 * updating the rmapbt.  Both flags are used in xfs_repair while we're
	 * rebuilding the rmapbt, and neither are used by the kernel.  They're
	 * both required to ensure that rmaps are correctly recorded for the
	 * regenerated AGFL, bnobt, and cntbt.  See repair/phase5.c and
	 * repair/rmap.c in xfsprogs for details.
	 */
	memset(&targs, 0, sizeof(targs));
	/* struct copy below */
	if (alloc_flags & XFS_ALLOC_FLAG_NORMAP)
		targs.oinfo = XFS_RMAP_OINFO_SKIP_UPDATE;
	else
		targs.oinfo = XFS_RMAP_OINFO_AG;
	while (!(alloc_flags & XFS_ALLOC_FLAG_NOSHRINK) &&
			pag->pagf_flcount > need) {
		error = xfs_alloc_get_freelist(pag, tp, agbp, &bno, 0);
		if (error)
			goto out_agbp_relse;

		/* defer agfl frees */
		error = xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
		if (error)
			goto out_agbp_relse;
	}

	targs.tp = tp;
	targs.mp = mp;
	targs.agbp = agbp;
	targs.agno = args->agno;
	targs.alignment = targs.minlen = targs.prod = 1;
	targs.pag = pag;
	error = xfs_alloc_read_agfl(pag, tp, &agflbp);
	if (error)
		goto out_agbp_relse;

	/* Make the freelist longer if it's too short. */
	while (pag->pagf_flcount < need) {
		targs.agbno = 0;
		targs.maxlen = need - pag->pagf_flcount;
		targs.resv = XFS_AG_RESV_AGFL;

		/* Allocate as many blocks as possible at once. */
		error = xfs_alloc_ag_vextent_size(&targs, alloc_flags);
		if (error)
			goto out_agflbp_relse;

		/*
		 * Stop if we run out.  Won't happen if callers are obeying
		 * the restrictions correctly.  Can happen for free calls
		 * on a completely full ag.
		 */
		if (targs.agbno == NULLAGBLOCK) {
			if (alloc_flags & XFS_ALLOC_FLAG_FREEING)
				break;
			goto out_agflbp_relse;
		}

		if (!xfs_rmap_should_skip_owner_update(&targs.oinfo)) {
			error = xfs_rmap_alloc(tp, agbp, pag,
				       targs.agbno, targs.len, &targs.oinfo);
			if (error)
				goto out_agflbp_relse;
		}
		error = xfs_alloc_update_counters(tp, agbp,
						  -((long)(targs.len)));
		if (error)
			goto out_agflbp_relse;

		/*
		 * Put each allocated block on the list.
		 */
		for (bno = targs.agbno; bno < targs.agbno + targs.len; bno++) {
			error = xfs_alloc_put_freelist(pag, tp, agbp,
							agflbp, bno, 0);
			if (error)
				goto out_agflbp_relse;
		}
	}
	xfs_trans_brelse(tp, agflbp);
	args->agbp = agbp;
	return 0;

out_agflbp_relse:
	xfs_trans_brelse(tp, agflbp);
out_agbp_relse:
	if (agbp)
		xfs_trans_brelse(tp, agbp);
out_no_agbp:
	args->agbp = NULL;
	return error;
}

/*
 * Get a block from the freelist.
 * Returns with the buffer for the block gotten.
 */
int
xfs_alloc_get_freelist(
	struct xfs_perag	*pag,
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	xfs_agblock_t		*bnop,
	int			btreeblk)
{
	struct xfs_agf		*agf = agbp->b_addr;
	struct xfs_buf		*agflbp;
	xfs_agblock_t		bno;
	__be32			*agfl_bno;
	int			error;
	uint32_t		logflags;
	struct xfs_mount	*mp = tp->t_mountp;

	/*
	 * Freelist is empty, give up.
	 */
	if (!agf->agf_flcount) {
		*bnop = NULLAGBLOCK;
		return 0;
	}
	/*
	 * Read the array of free blocks.
	 */
	error = xfs_alloc_read_agfl(pag, tp, &agflbp);
	if (error)
		return error;


	/*
	 * Get the block number and update the data structures.
	 */
	agfl_bno = xfs_buf_to_agfl_bno(agflbp);
	bno = be32_to_cpu(agfl_bno[be32_to_cpu(agf->agf_flfirst)]);
	if (XFS_IS_CORRUPT(tp->t_mountp, !xfs_verify_agbno(pag, bno)))
		return -EFSCORRUPTED;

	be32_add_cpu(&agf->agf_flfirst, 1);
	xfs_trans_brelse(tp, agflbp);
	if (be32_to_cpu(agf->agf_flfirst) == xfs_agfl_size(mp))
		agf->agf_flfirst = 0;

	ASSERT(!xfs_perag_agfl_needs_reset(pag));
	be32_add_cpu(&agf->agf_flcount, -1);
	pag->pagf_flcount--;

	logflags = XFS_AGF_FLFIRST | XFS_AGF_FLCOUNT;
	if (btreeblk) {
		be32_add_cpu(&agf->agf_btreeblks, 1);
		pag->pagf_btreeblks++;
		logflags |= XFS_AGF_BTREEBLKS;
	}

	xfs_alloc_log_agf(tp, agbp, logflags);
	*bnop = bno;

	return 0;
}

/*
 * Log the given fields from the agf structure.
 */
void
xfs_alloc_log_agf(
	struct xfs_trans	*tp,
	struct xfs_buf		*bp,
	uint32_t		fields)
{
	int	first;		/* first byte offset */
	int	last;		/* last byte offset */
	static const short	offsets[] = {
		offsetof(xfs_agf_t, agf_magicnum),
		offsetof(xfs_agf_t, agf_versionnum),
		offsetof(xfs_agf_t, agf_seqno),
		offsetof(xfs_agf_t, agf_length),
		offsetof(xfs_agf_t, agf_roots[0]),
		offsetof(xfs_agf_t, agf_levels[0]),
		offsetof(xfs_agf_t, agf_flfirst),
		offsetof(xfs_agf_t, agf_fllast),
		offsetof(xfs_agf_t, agf_flcount),
		offsetof(xfs_agf_t, agf_freeblks),
		offsetof(xfs_agf_t, agf_longest),
		offsetof(xfs_agf_t, agf_btreeblks),
		offsetof(xfs_agf_t, agf_uuid),
		offsetof(xfs_agf_t, agf_rmap_blocks),
		offsetof(xfs_agf_t, agf_refcount_blocks),
		offsetof(xfs_agf_t, agf_refcount_root),
		offsetof(xfs_agf_t, agf_refcount_level),
		/* needed so that we don't log the whole rest of the structure: */
		offsetof(xfs_agf_t, agf_spare64),
		sizeof(xfs_agf_t)
	};

	trace_xfs_agf(tp->t_mountp, bp->b_addr, fields, _RET_IP_);

	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_AGF_BUF);

	xfs_btree_offsets(fields, offsets, XFS_AGF_NUM_BITS, &first, &last);
	xfs_trans_log_buf(tp, bp, (uint)first, (uint)last);
}

/*
 * Put the block on the freelist for the allocation group.
 */
int
xfs_alloc_put_freelist(
	struct xfs_perag	*pag,
	struct xfs_trans	*tp,
	struct xfs_buf		*agbp,
	struct xfs_buf		*agflbp,
	xfs_agblock_t		bno,
	int			btreeblk)
{
	struct xfs_mount	*mp = tp->t_mountp;
	struct xfs_agf		*agf = agbp->b_addr;
	__be32			*blockp;
	int			error;
	uint32_t		logflags;
	__be32			*agfl_bno;
	int			startoff;

	if (!agflbp) {
		error = xfs_alloc_read_agfl(pag, tp, &agflbp);
		if (error)
			return error;
	}

	be32_add_cpu(&agf->agf_fllast, 1);
	if (be32_to_cpu(agf->agf_fllast) == xfs_agfl_size(mp))
		agf->agf_fllast = 0;

	ASSERT(!xfs_perag_agfl_needs_reset(pag));
	be32_add_cpu(&agf->agf_flcount, 1);
	pag->pagf_flcount++;

	logflags = XFS_AGF_FLLAST | XFS_AGF_FLCOUNT;
	if (btreeblk) {
		be32_add_cpu(&agf->agf_btreeblks, -1);
		pag->pagf_btreeblks--;
		logflags |= XFS_AGF_BTREEBLKS;
	}

	xfs_alloc_log_agf(tp, agbp, logflags);

	ASSERT(be32_to_cpu(agf->agf_flcount) <= xfs_agfl_size(mp));

	agfl_bno = xfs_buf_to_agfl_bno(agflbp);
	blockp = &agfl_bno[be32_to_cpu(agf->agf_fllast)];
	*blockp = cpu_to_be32(bno);
	startoff = (char *)blockp - (char *)agflbp->b_addr;

	xfs_alloc_log_agf(tp, agbp, logflags);

	xfs_trans_buf_set_type(tp, agflbp, XFS_BLFT_AGFL_BUF);
	xfs_trans_log_buf(tp, agflbp, startoff,
			  startoff + sizeof(xfs_agblock_t) - 1);
	return 0;
}

/*
 * Check that this AGF/AGI header's sequence number and length matches the AG
 * number and size in fsblocks.
 */
xfs_failaddr_t
xfs_validate_ag_length(
	struct xfs_buf		*bp,
	uint32_t		seqno,
	uint32_t		length)
{
	struct xfs_mount	*mp = bp->b_mount;
	/*
	 * During growfs operations, the perag is not fully initialised,
	 * so we can't use it for any useful checking. growfs ensures we can't
	 * use it by using uncached buffers that don't have the perag attached
	 * so we can detect and avoid this problem.
	 */
	if (bp->b_pag && seqno != bp->b_pag->pag_agno)
		return __this_address;

	/*
	 * Only the last AG in the filesystem is allowed to be shorter
	 * than the AG size recorded in the superblock.
	 */
	if (length != mp->m_sb.sb_agblocks) {
		/*
		 * During growfs, the new last AG can get here before we
		 * have updated the superblock. Give it a pass on the seqno
		 * check.
		 */
		if (bp->b_pag && seqno != mp->m_sb.sb_agcount - 1)
			return __this_address;
		if (length < XFS_MIN_AG_BLOCKS)
			return __this_address;
		if (length > mp->m_sb.sb_agblocks)
			return __this_address;
	}

	return NULL;
}

/*
 * Verify the AGF is consistent.
 *
 * We do not verify the AGFL indexes in the AGF are fully consistent here
 * because of issues with variable on-disk structure sizes. Instead, we check
 * the agfl indexes for consistency when we initialise the perag from the AGF
 * information after a read completes.
 *
 * If the index is inconsistent, then we mark the perag as needing an AGFL
 * reset. The first AGFL update performed then resets the AGFL indexes and
 * refills the AGFL with known good free blocks, allowing the filesystem to
 * continue operating normally at the cost of a few leaked free space blocks.
 */
static xfs_failaddr_t
xfs_agf_verify(
	struct xfs_buf		*bp)
{
	struct xfs_mount	*mp = bp->b_mount;
	struct xfs_agf		*agf = bp->b_addr;
	xfs_failaddr_t		fa;
	uint32_t		agf_seqno = be32_to_cpu(agf->agf_seqno);
	uint32_t		agf_length = be32_to_cpu(agf->agf_length);

	if (xfs_has_crc(mp)) {
		if (!uuid_equal(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid))
			return __this_address;
		if (!xfs_log_check_lsn(mp, be64_to_cpu(agf->agf_lsn)))
			return __this_address;
	}

	if (!xfs_verify_magic(bp, agf->agf_magicnum))
		return __this_address;

	if (!XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)))
		return __this_address;

	/*
	 * Both agf_seqno and agf_length need to validated before anything else
	 * block number related in the AGF or AGFL can be checked.
	 */
	fa = xfs_validate_ag_length(bp, agf_seqno, agf_length);
	if (fa)
		return fa;

	if (be32_to_cpu(agf->agf_flfirst) >= xfs_agfl_size(mp))
		return __this_address;
	if (be32_to_cpu(agf->agf_fllast) >= xfs_agfl_size(mp))
		return __this_address;
	if (be32_to_cpu(agf->agf_flcount) > xfs_agfl_size(mp))
		return __this_address;

	if (be32_to_cpu(agf->agf_freeblks) < be32_to_cpu(agf->agf_longest) ||
	    be32_to_cpu(agf->agf_freeblks) > agf_length)
		return __this_address;

	if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) < 1 ||
	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) < 1 ||
	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]) >
						mp->m_alloc_maxlevels ||
	    be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]) >
						mp->m_alloc_maxlevels)
		return __this_address;

	if (xfs_has_lazysbcount(mp) &&
	    be32_to_cpu(agf->agf_btreeblks) > agf_length)
		return __this_address;

	if (xfs_has_rmapbt(mp)) {
		if (be32_to_cpu(agf->agf_rmap_blocks) > agf_length)
			return __this_address;

		if (be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) < 1 ||
		    be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]) >
							mp->m_rmap_maxlevels)
			return __this_address;
	}

	if (xfs_has_reflink(mp)) {
		if (be32_to_cpu(agf->agf_refcount_blocks) > agf_length)
			return __this_address;

		if (be32_to_cpu(agf->agf_refcount_level) < 1 ||
		    be32_to_cpu(agf->agf_refcount_level) > mp->m_refc_maxlevels)
			return __this_address;
	}

	return NULL;
}

static void
xfs_agf_read_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount *mp = bp->b_mount;
	xfs_failaddr_t	fa;

	if (xfs_has_crc(mp) &&
	    !xfs_buf_verify_cksum(bp, XFS_AGF_CRC_OFF))
		xfs_verifier_error(bp, -EFSBADCRC, __this_address);
	else {
		fa = xfs_agf_verify(bp);
		if (XFS_TEST_ERROR(fa, mp, XFS_ERRTAG_ALLOC_READ_AGF))
			xfs_verifier_error(bp, -EFSCORRUPTED, fa);
	}
}

static void
xfs_agf_write_verify(
	struct xfs_buf	*bp)
{
	struct xfs_mount	*mp = bp->b_mount;
	struct xfs_buf_log_item	*bip = bp->b_log_item;
	struct xfs_agf		*agf = bp->b_addr;
	xfs_failaddr_t		fa;

	fa = xfs_agf_verify(bp);
	if (fa) {
		xfs_verifier_error(bp, -EFSCORRUPTED, fa);
		return;
	}

	if (!xfs_has_crc(mp))
		return;

	if (bip)
		agf->agf_lsn = cpu_to_be64(bip->bli_item.li_lsn);

	xfs_buf_update_cksum(bp, XFS_AGF_CRC_OFF);
}

const struct xfs_buf_ops xfs_agf_buf_ops = {
	.name = "xfs_agf",
	.magic = { cpu_to_be32(XFS_AGF_MAGIC), cpu_to_be32(XFS_AGF_MAGIC) },
	.verify_read = xfs_agf_read_verify,
	.verify_write = xfs_agf_write_verify,
	.verify_struct = xfs_agf_verify,
};

/*
 * Read in the allocation group header (free/alloc section).
 */
int
xfs_read_agf(
	struct xfs_perag	*pag,
	struct xfs_trans	*tp,
	int			flags,
	struct xfs_buf		**agfbpp)
{
	struct xfs_mount	*mp = pag->pag_mount;
	int			error;

	trace_xfs_read_agf(pag->pag_mount, pag->pag_agno);

	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
			XFS_AG_DADDR(mp, pag->pag_agno, XFS_AGF_DADDR(mp)),
			XFS_FSS_TO_BB(mp, 1), flags, agfbpp, &xfs_agf_buf_ops);
	if (error)
		return error;

	xfs_buf_set_ref(*agfbpp, XFS_AGF_REF);
	return 0;
}

/*
 * Read in the allocation group header (free/alloc section) and initialise the
 * perag structure if necessary. If the caller provides @agfbpp, then return the
 * locked buffer to the caller, otherwise free it.
 */
int
xfs_alloc_read_agf(
	struct xfs_perag	*pag,
	struct xfs_trans	*tp,
	int			flags,
	struct xfs_buf		**agfbpp)
{
	struct xfs_buf		*agfbp;
	struct xfs_agf		*agf;
	int			error;
	int			allocbt_blks;

	trace_xfs_alloc_read_agf(pag->pag_mount, pag->pag_agno);

	/* We don't support trylock when freeing. */
	ASSERT((flags & (XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK)) !=
			(XFS_ALLOC_FLAG_FREEING | XFS_ALLOC_FLAG_TRYLOCK));
	error = xfs_read_agf(pag, tp,
			(flags & XFS_ALLOC_FLAG_TRYLOCK) ? XBF_TRYLOCK : 0,
			&agfbp);
	if (error)
		return error;

	agf = agfbp->b_addr;
	if (!xfs_perag_initialised_agf(pag)) {
		pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
		pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
		pag->pagf_flcount = be32_to_cpu(agf->agf_flcount);
		pag->pagf_longest = be32_to_cpu(agf->agf_longest);
		pag->pagf_levels[XFS_BTNUM_BNOi] =
			be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]);
		pag->pagf_levels[XFS_BTNUM_CNTi] =
			be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]);
		pag->pagf_levels[XFS_BTNUM_RMAPi] =
			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
		pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
		if (xfs_agfl_needs_reset(pag->pag_mount, agf))
			set_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);
		else
			clear_bit(XFS_AGSTATE_AGFL_NEEDS_RESET, &pag->pag_opstate);

		/*
		 * Update the in-core allocbt counter. Filter out the rmapbt
		 * subset of the btreeblks counter because the rmapbt is managed
		 * by perag reservation. Subtract one for the rmapbt root block
		 * because the rmap counter includes it while the btreeblks
		 * counter only tracks non-root blocks.
		 */
		allocbt_blks = pag->pagf_btreeblks;
		if (xfs_has_rmapbt(pag->pag_mount))
			allocbt_blks -= be32_to_cpu(agf->agf_rmap_blocks) - 1;
		if (allocbt_blks > 0)
			atomic64_add(allocbt_blks,
					&pag->pag_mount->m_allocbt_blks);

		set_bit(XFS_AGSTATE_AGF_INIT, &pag->pag_opstate);
	}
#ifdef DEBUG
	else if (!xfs_is_shutdown(pag->pag_mount)) {
		ASSERT(pag->pagf_freeblks == be32_to_cpu(agf->agf_freeblks));
		ASSERT(pag->pagf_btreeblks == be32_to_cpu(agf->agf_btreeblks));
		ASSERT(pag->pagf_flcount == be32_to_cpu(agf->agf_flcount));
		ASSERT(pag->pagf_longest == be32_to_cpu(agf->agf_longest));
		ASSERT(pag->pagf_levels[XFS_BTNUM_BNOi] ==
		       be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]));
		ASSERT(pag->pagf_levels[XFS_BTNUM_CNTi] ==
		       be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]));
	}
#endif
	if (agfbpp)
		*agfbpp = agfbp;
	else
		xfs_trans_brelse(tp, agfbp);
	return 0;
}

/*
 * Pre-proces allocation arguments to set initial state that we don't require
 * callers to set up correctly, as well as bounds check the allocation args
 * that are set up.
 */
static int
xfs_alloc_vextent_check_args(
	struct xfs_alloc_arg	*args,
	xfs_fsblock_t		target,
	xfs_agnumber_t		*minimum_agno)
{
	struct xfs_mount	*mp = args->mp;
	xfs_agblock_t		agsize;

	args->fsbno = NULLFSBLOCK;

	*minimum_agno = 0;
	if (args->tp->t_highest_agno != NULLAGNUMBER)
		*minimum_agno = args->tp->t_highest_agno;

	/*
	 * Just fix this up, for the case where the last a.g. is shorter
	 * (or there's only one a.g.) and the caller couldn't easily figure
	 * that out (xfs_bmap_alloc).
	 */
	agsize = mp->m_sb.sb_agblocks;
	if (args->maxlen > agsize)
		args->maxlen = agsize;
	if (args->alignment == 0)
		args->alignment = 1;

	ASSERT(args->minlen > 0);
	ASSERT(args->maxlen > 0);
	ASSERT(args->alignment > 0);
	ASSERT(args->resv != XFS_AG_RESV_AGFL);

	ASSERT(XFS_FSB_TO_AGNO(mp, target) < mp->m_sb.sb_agcount);
	ASSERT(XFS_FSB_TO_AGBNO(mp, target) < agsize);
	ASSERT(args->minlen <= args->maxlen);
	ASSERT(args->minlen <= agsize);
	ASSERT(args->mod < args->prod);

	if (XFS_FSB_TO_AGNO(mp, target) >= mp->m_sb.sb_agcount ||
	    XFS_FSB_TO_AGBNO(mp, target) >= agsize ||
	    args->minlen > args->maxlen || args->minlen > agsize ||
	    args->mod >= args->prod) {
		trace_xfs_alloc_vextent_badargs(args);
		return -ENOSPC;
	}

	if (args->agno != NULLAGNUMBER && *minimum_agno > args->agno) {
		trace_xfs_alloc_vextent_skip_deadlock(args);
		return -ENOSPC;
	}
	return 0;

}

/*
 * Prepare an AG for allocation. If the AG is not prepared to accept the
 * allocation, return failure.
 *
 * XXX(dgc): The complexity of "need_pag" will go away as all caller paths are
 * modified to hold their own perag references.
 */
static int
xfs_alloc_vextent_prepare_ag(
	struct xfs_alloc_arg	*args,
	uint32_t		alloc_flags)
{
	bool			need_pag = !args->pag;
	int			error;

	if (need_pag)
		args->pag = xfs_perag_get(args->mp, args->agno);

	args->agbp = NULL;
	error = xfs_alloc_fix_freelist(args, alloc_flags);
	if (error) {
		trace_xfs_alloc_vextent_nofix(args);
		if (need_pag)
			xfs_perag_put(args->pag);
		args->agbno = NULLAGBLOCK;
		return error;
	}
	if (!args->agbp) {
		/* cannot allocate in this AG at all */
		trace_xfs_alloc_vextent_noagbp(args);
		args->agbno = NULLAGBLOCK;
		return 0;
	}
	args->wasfromfl = 0;
	return 0;
}

/*
 * Post-process allocation results to account for the allocation if it succeed
 * and set the allocated block number correctly for the caller.
 *
 * XXX: we should really be returning ENOSPC for ENOSPC, not
 * hiding it behind a "successful" NULLFSBLOCK allocation.
 */
static int
xfs_alloc_vextent_finish(
	struct xfs_alloc_arg	*args,
	xfs_agnumber_t		minimum_agno,
	int			alloc_error,
	bool			drop_perag)
{
	struct xfs_mount	*mp = args->mp;
	int			error = 0;

	/*
	 * We can end up here with a locked AGF. If we failed, the caller is
	 * likely going to try to allocate again with different parameters, and
	 * that can widen the AGs that are searched for free space. If we have
	 * to do BMBT block allocation, we have to do a new allocation.
	 *
	 * Hence leaving this function with the AGF locked opens up potential
	 * ABBA AGF deadlocks because a future allocation attempt in this
	 * transaction may attempt to lock a lower number AGF.
	 *
	 * We can't release the AGF until the transaction is commited, so at
	 * this point we must update the "first allocation" tracker to point at
	 * this AG if the tracker is empty or points to a lower AG. This allows
	 * the next allocation attempt to be modified appropriately to avoid
	 * deadlocks.
	 */
	if (args->agbp &&
	    (args->tp->t_highest_agno == NULLAGNUMBER ||
	     args->agno > minimum_agno))
		args->tp->t_highest_agno = args->agno;

	/*
	 * If the allocation failed with an error or we had an ENOSPC result,
	 * preserve the returned error whilst also marking the allocation result
	 * as "no extent allocated". This ensures that callers that fail to
	 * capture the error will still treat it as a failed allocation.
	 */
	if (alloc_error || args->agbno == NULLAGBLOCK) {
		args->fsbno = NULLFSBLOCK;
		error = alloc_error;
		goto out_drop_perag;
	}

	args->fsbno = XFS_AGB_TO_FSB(mp, args->agno, args->agbno);

	ASSERT(args->len >= args->minlen);
	ASSERT(args->len <= args->maxlen);
	ASSERT(args->agbno % args->alignment == 0);
	XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno), args->len);

	/* if not file data, insert new block into the reverse map btree */
	if (!xfs_rmap_should_skip_owner_update(&args->oinfo)) {
		error = xfs_rmap_alloc(args->tp, args->agbp, args->pag,
				       args->agbno, args->len, &args->oinfo);
		if (error)
			goto out_drop_perag;
	}

	if (!args->wasfromfl) {
		error = xfs_alloc_update_counters(args->tp, args->agbp,
						  -((long)(args->len)));
		if (error)
			goto out_drop_perag;

		ASSERT(!xfs_extent_busy_search(mp, args->pag, args->agbno,
				args->len));
	}

	xfs_ag_resv_alloc_extent(args->pag, args->resv, args);

	XFS_STATS_INC(mp, xs_allocx);
	XFS_STATS_ADD(mp, xs_allocb, args->len);

	trace_xfs_alloc_vextent_finish(args);

out_drop_perag:
	if (drop_perag && args->pag) {
		xfs_perag_rele(args->pag);
		args->pag = NULL;
	}
	return error;
}

/*
 * Allocate within a single AG only. This uses a best-fit length algorithm so if
 * you need an exact sized allocation without locality constraints, this is the
 * fastest way to do it.
 *
 * Caller is expected to hold a perag reference in args->pag.
 */
int
xfs_alloc_vextent_this_ag(
	struct xfs_alloc_arg	*args,
	xfs_agnumber_t		agno)
{
	struct xfs_mount	*mp = args->mp;
	xfs_agnumber_t		minimum_agno;
	uint32_t		alloc_flags = 0;
	int			error;

	ASSERT(args->pag != NULL);
	ASSERT(args->pag->pag_agno == agno);

	args->agno = agno;
	args->agbno = 0;

	trace_xfs_alloc_vextent_this_ag(args);

	error = xfs_alloc_vextent_check_args(args, XFS_AGB_TO_FSB(mp, agno, 0),
			&minimum_agno);
	if (error) {
		if (error == -ENOSPC)
			return 0;
		return error;
	}

	error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
	if (!error && args->agbp)
		error = xfs_alloc_ag_vextent_size(args, alloc_flags);

	return xfs_alloc_vextent_finish(args, minimum_agno, error, false);
}

/*
 * Iterate all AGs trying to allocate an extent starting from @start_ag.
 *
 * If the incoming allocation type is XFS_ALLOCTYPE_NEAR_BNO, it means the
 * allocation attempts in @start_agno have locality information. If we fail to
 * allocate in that AG, then we revert to anywhere-in-AG for all the other AGs
 * we attempt to allocation in as there is no locality optimisation possible for
 * those allocations.
 *
 * On return, args->pag may be left referenced if we finish before the "all
 * failed" return point. The allocation finish still needs the perag, and
 * so the caller will release it once they've finished the allocation.
 *
 * When we wrap the AG iteration at the end of the filesystem, we have to be
 * careful not to wrap into AGs below ones we already have locked in the
 * transaction if we are doing a blocking iteration. This will result in an
 * out-of-order locking of AGFs and hence can cause deadlocks.
 */
static int
xfs_alloc_vextent_iterate_ags(
	struct xfs_alloc_arg	*args,
	xfs_agnumber_t		minimum_agno,
	xfs_agnumber_t		start_agno,
	xfs_agblock_t		target_agbno,
	uint32_t		alloc_flags)
{
	struct xfs_mount	*mp = args->mp;
	xfs_agnumber_t		restart_agno = minimum_agno;
	xfs_agnumber_t		agno;
	int			error = 0;

	if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK)
		restart_agno = 0;
restart:
	for_each_perag_wrap_range(mp, start_agno, restart_agno,
			mp->m_sb.sb_agcount, agno, args->pag) {
		args->agno = agno;
		error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
		if (error)
			break;
		if (!args->agbp) {
			trace_xfs_alloc_vextent_loopfailed(args);
			continue;
		}

		/*
		 * Allocation is supposed to succeed now, so break out of the
		 * loop regardless of whether we succeed or not.
		 */
		if (args->agno == start_agno && target_agbno) {
			args->agbno = target_agbno;
			error = xfs_alloc_ag_vextent_near(args, alloc_flags);
		} else {
			args->agbno = 0;
			error = xfs_alloc_ag_vextent_size(args, alloc_flags);
		}
		break;
	}
	if (error) {
		xfs_perag_rele(args->pag);
		args->pag = NULL;
		return error;
	}
	if (args->agbp)
		return 0;

	/*
	 * We didn't find an AG we can alloation from. If we were given
	 * constraining flags by the caller, drop them and retry the allocation
	 * without any constraints being set.
	 */
	if (alloc_flags & XFS_ALLOC_FLAG_TRYLOCK) {
		alloc_flags &= ~XFS_ALLOC_FLAG_TRYLOCK;
		restart_agno = minimum_agno;
		goto restart;
	}

	ASSERT(args->pag == NULL);
	trace_xfs_alloc_vextent_allfailed(args);
	return 0;
}

/*
 * Iterate from the AGs from the start AG to the end of the filesystem, trying
 * to allocate blocks. It starts with a near allocation attempt in the initial
 * AG, then falls back to anywhere-in-ag after the first AG fails. It will wrap
 * back to zero if allowed by previous allocations in this transaction,
 * otherwise will wrap back to the start AG and run a second blocking pass to
 * the end of the filesystem.
 */
int
xfs_alloc_vextent_start_ag(
	struct xfs_alloc_arg	*args,
	xfs_fsblock_t		target)
{
	struct xfs_mount	*mp = args->mp;
	xfs_agnumber_t		minimum_agno;
	xfs_agnumber_t		start_agno;
	xfs_agnumber_t		rotorstep = xfs_rotorstep;
	bool			bump_rotor = false;
	uint32_t		alloc_flags = XFS_ALLOC_FLAG_TRYLOCK;
	int			error;

	ASSERT(args->pag == NULL);

	args->agno = NULLAGNUMBER;
	args->agbno = NULLAGBLOCK;

	trace_xfs_alloc_vextent_start_ag(args);

	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
	if (error) {
		if (error == -ENOSPC)
			return 0;
		return error;
	}

	if ((args->datatype & XFS_ALLOC_INITIAL_USER_DATA) &&
	    xfs_is_inode32(mp)) {
		target = XFS_AGB_TO_FSB(mp,
				((mp->m_agfrotor / rotorstep) %
				mp->m_sb.sb_agcount), 0);
		bump_rotor = 1;
	}

	start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
	error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
			XFS_FSB_TO_AGBNO(mp, target), alloc_flags);

	if (bump_rotor) {
		if (args->agno == start_agno)
			mp->m_agfrotor = (mp->m_agfrotor + 1) %
				(mp->m_sb.sb_agcount * rotorstep);
		else
			mp->m_agfrotor = (args->agno * rotorstep + 1) %
				(mp->m_sb.sb_agcount * rotorstep);
	}

	return xfs_alloc_vextent_finish(args, minimum_agno, error, true);
}

/*
 * Iterate from the agno indicated via @target through to the end of the
 * filesystem attempting blocking allocation. This does not wrap or try a second
 * pass, so will not recurse into AGs lower than indicated by the target.
 */
int
xfs_alloc_vextent_first_ag(
	struct xfs_alloc_arg	*args,
	xfs_fsblock_t		target)
 {
	struct xfs_mount	*mp = args->mp;
	xfs_agnumber_t		minimum_agno;
	xfs_agnumber_t		start_agno;
	uint32_t		alloc_flags = XFS_ALLOC_FLAG_TRYLOCK;
	int			error;

	ASSERT(args->pag == NULL);

	args->agno = NULLAGNUMBER;
	args->agbno = NULLAGBLOCK;

	trace_xfs_alloc_vextent_first_ag(args);

	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
	if (error) {
		if (error == -ENOSPC)
			return 0;
		return error;
	}

	start_agno = max(minimum_agno, XFS_FSB_TO_AGNO(mp, target));
	error = xfs_alloc_vextent_iterate_ags(args, minimum_agno, start_agno,
			XFS_FSB_TO_AGBNO(mp, target), alloc_flags);
	return xfs_alloc_vextent_finish(args, minimum_agno, error, true);
}

/*
 * Allocate at the exact block target or fail. Caller is expected to hold a
 * perag reference in args->pag.
 */
int
xfs_alloc_vextent_exact_bno(
	struct xfs_alloc_arg	*args,
	xfs_fsblock_t		target)
{
	struct xfs_mount	*mp = args->mp;
	xfs_agnumber_t		minimum_agno;
	int			error;

	ASSERT(args->pag != NULL);
	ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target));

	args->agno = XFS_FSB_TO_AGNO(mp, target);
	args->agbno = XFS_FSB_TO_AGBNO(mp, target);

	trace_xfs_alloc_vextent_exact_bno(args);

	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
	if (error) {
		if (error == -ENOSPC)
			return 0;
		return error;
	}

	error = xfs_alloc_vextent_prepare_ag(args, 0);
	if (!error && args->agbp)
		error = xfs_alloc_ag_vextent_exact(args);

	return xfs_alloc_vextent_finish(args, minimum_agno, error, false);
}

/*
 * Allocate an extent as close to the target as possible. If there are not
 * viable candidates in the AG, then fail the allocation.
 *
 * Caller may or may not have a per-ag reference in args->pag.
 */
int
xfs_alloc_vextent_near_bno(
	struct xfs_alloc_arg	*args,
	xfs_fsblock_t		target)
{
	struct xfs_mount	*mp = args->mp;
	xfs_agnumber_t		minimum_agno;
	bool			needs_perag = args->pag == NULL;
	uint32_t		alloc_flags = 0;
	int			error;

	if (!needs_perag)
		ASSERT(args->pag->pag_agno == XFS_FSB_TO_AGNO(mp, target));

	args->agno = XFS_FSB_TO_AGNO(mp, target);
	args->agbno = XFS_FSB_TO_AGBNO(mp, target);

	trace_xfs_alloc_vextent_near_bno(args);

	error = xfs_alloc_vextent_check_args(args, target, &minimum_agno);
	if (error) {
		if (error == -ENOSPC)
			return 0;
		return error;
	}

	if (needs_perag)
		args->pag = xfs_perag_grab(mp, args->agno);

	error = xfs_alloc_vextent_prepare_ag(args, alloc_flags);
	if (!error && args->agbp)
		error = xfs_alloc_ag_vextent_near(args, alloc_flags);

	return xfs_alloc_vextent_finish(args, minimum_agno, error, needs_perag);
}

/* Ensure that the freelist is at full capacity. */
int
xfs_free_extent_fix_freelist(
	struct xfs_trans	*tp,
	struct xfs_perag	*pag,
	struct xfs_buf		**agbp)
{
	struct xfs_alloc_arg	args;
	int			error;

	memset(&args, 0, sizeof(struct xfs_alloc_arg));
	args.tp = tp;
	args.mp = tp->t_mountp;
	args.agno = pag->pag_agno;
	args.pag = pag;

	/*
	 * validate that the block number is legal - the enables us to detect
	 * and handle a silent filesystem corruption rather than crashing.
	 */
	if (args.agno >= args.mp->m_sb.sb_agcount)
		return -EFSCORRUPTED;

	error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
	if (error)
		return error;

	*agbp = args.agbp;
	return 0;
}

/*
 * Free an extent.
 * Just break up the extent address and hand off to xfs_free_ag_extent
 * after fixing up the freelist.
 */
int
__xfs_free_extent(
	struct xfs_trans		*tp,
	struct xfs_perag		*pag,
	xfs_agblock_t			agbno,
	xfs_extlen_t			len,
	const struct xfs_owner_info	*oinfo,
	enum xfs_ag_resv_type		type,
	bool				skip_discard)
{
	struct xfs_mount		*mp = tp->t_mountp;
	struct xfs_buf			*agbp;
	struct xfs_agf			*agf;
	int				error;
	unsigned int			busy_flags = 0;

	ASSERT(len != 0);
	ASSERT(type != XFS_AG_RESV_AGFL);

	if (XFS_TEST_ERROR(false, mp,
			XFS_ERRTAG_FREE_EXTENT))
		return -EIO;

	error = xfs_free_extent_fix_freelist(tp, pag, &agbp);
	if (error)
		return error;
	agf = agbp->b_addr;

	if (XFS_IS_CORRUPT(mp, agbno >= mp->m_sb.sb_agblocks)) {
		error = -EFSCORRUPTED;
		goto err_release;
	}

	/* validate the extent size is legal now we have the agf locked */
	if (XFS_IS_CORRUPT(mp, agbno + len > be32_to_cpu(agf->agf_length))) {
		error = -EFSCORRUPTED;
		goto err_release;
	}

	error = xfs_free_ag_extent(tp, agbp, pag->pag_agno, agbno, len, oinfo,
			type);
	if (error)
		goto err_release;

	if (skip_discard)
		busy_flags |= XFS_EXTENT_BUSY_SKIP_DISCARD;
	xfs_extent_busy_insert(tp, pag, agbno, len, busy_flags);
	return 0;

err_release:
	xfs_trans_brelse(tp, agbp);
	return error;
}

struct xfs_alloc_query_range_info {
	xfs_alloc_query_range_fn	fn;
	void				*priv;
};

/* Format btree record and pass to our callback. */
STATIC int
xfs_alloc_query_range_helper(
	struct xfs_btree_cur		*cur,
	const union xfs_btree_rec	*rec,
	void				*priv)
{
	struct xfs_alloc_query_range_info	*query = priv;
	struct xfs_alloc_rec_incore		irec;
	xfs_failaddr_t				fa;

	xfs_alloc_btrec_to_irec(rec, &irec);
	fa = xfs_alloc_check_irec(cur, &irec);
	if (fa)
		return xfs_alloc_complain_bad_rec(cur, fa, &irec);

	return query->fn(cur, &irec, query->priv);
}

/* Find all free space within a given range of blocks. */
int
xfs_alloc_query_range(
	struct xfs_btree_cur			*cur,
	const struct xfs_alloc_rec_incore	*low_rec,
	const struct xfs_alloc_rec_incore	*high_rec,
	xfs_alloc_query_range_fn		fn,
	void					*priv)
{
	union xfs_btree_irec			low_brec = { .a = *low_rec };
	union xfs_btree_irec			high_brec = { .a = *high_rec };
	struct xfs_alloc_query_range_info	query = { .priv = priv, .fn = fn };

	ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
	return xfs_btree_query_range(cur, &low_brec, &high_brec,
			xfs_alloc_query_range_helper, &query);
}

/* Find all free space records. */
int
xfs_alloc_query_all(
	struct xfs_btree_cur			*cur,
	xfs_alloc_query_range_fn		fn,
	void					*priv)
{
	struct xfs_alloc_query_range_info	query;

	ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
	query.priv = priv;
	query.fn = fn;
	return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query);
}

/*
 * Scan part of the keyspace of the free space and tell us if the area has no
 * records, is fully mapped by records, or is partially filled.
 */
int
xfs_alloc_has_records(
	struct xfs_btree_cur	*cur,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	enum xbtree_recpacking	*outcome)
{
	union xfs_btree_irec	low;
	union xfs_btree_irec	high;

	memset(&low, 0, sizeof(low));
	low.a.ar_startblock = bno;
	memset(&high, 0xFF, sizeof(high));
	high.a.ar_startblock = bno + len - 1;

	return xfs_btree_has_records(cur, &low, &high, NULL, outcome);
}

/*
 * Walk all the blocks in the AGFL.  The @walk_fn can return any negative
 * error code or XFS_ITER_*.
 */
int
xfs_agfl_walk(
	struct xfs_mount	*mp,
	struct xfs_agf		*agf,
	struct xfs_buf		*agflbp,
	xfs_agfl_walk_fn	walk_fn,
	void			*priv)
{
	__be32			*agfl_bno;
	unsigned int		i;
	int			error;

	agfl_bno = xfs_buf_to_agfl_bno(agflbp);
	i = be32_to_cpu(agf->agf_flfirst);

	/* Nothing to walk in an empty AGFL. */
	if (agf->agf_flcount == cpu_to_be32(0))
		return 0;

	/* Otherwise, walk from first to last, wrapping as needed. */
	for (;;) {
		error = walk_fn(mp, be32_to_cpu(agfl_bno[i]), priv);
		if (error)
			return error;
		if (i == be32_to_cpu(agf->agf_fllast))
			break;
		if (++i == xfs_agfl_size(mp))
			i = 0;
	}

	return 0;
}

int __init
xfs_extfree_intent_init_cache(void)
{
	xfs_extfree_item_cache = kmem_cache_create("xfs_extfree_intent",
			sizeof(struct xfs_extent_free_item),
			0, 0, NULL);

	return xfs_extfree_item_cache != NULL ? 0 : -ENOMEM;
}

void
xfs_extfree_intent_destroy_cache(void)
{
	kmem_cache_destroy(xfs_extfree_item_cache);
	xfs_extfree_item_cache = NULL;
}