summaryrefslogtreecommitdiffstats
path: root/fs/gfs2/rgrp.c
blob: 17a8d3b4399057e18cf8e3ba071187a81390a49c (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
/*
 * Copyright (C) Sistina Software, Inc.  1997-2003 All rights reserved.
 * Copyright (C) 2004-2008 Red Hat, Inc.  All rights reserved.
 *
 * This copyrighted material is made available to anyone wishing to use,
 * modify, copy, or redistribute it subject to the terms and conditions
 * of the GNU General Public License version 2.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
#include <linux/fs.h>
#include <linux/gfs2_ondisk.h>
#include <linux/prefetch.h>
#include <linux/blkdev.h>
#include <linux/rbtree.h>
#include <linux/random.h>

#include "gfs2.h"
#include "incore.h"
#include "glock.h"
#include "glops.h"
#include "lops.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "super.h"
#include "trans.h"
#include "util.h"
#include "log.h"
#include "inode.h"
#include "trace_gfs2.h"
#include "dir.h"

#define BFITNOENT ((u32)~0)
#define NO_BLOCK ((u64)~0)

#if BITS_PER_LONG == 32
#define LBITMASK   (0x55555555UL)
#define LBITSKIP55 (0x55555555UL)
#define LBITSKIP00 (0x00000000UL)
#else
#define LBITMASK   (0x5555555555555555UL)
#define LBITSKIP55 (0x5555555555555555UL)
#define LBITSKIP00 (0x0000000000000000UL)
#endif

/*
 * These routines are used by the resource group routines (rgrp.c)
 * to keep track of block allocation.  Each block is represented by two
 * bits.  So, each byte represents GFS2_NBBY (i.e. 4) blocks.
 *
 * 0 = Free
 * 1 = Used (not metadata)
 * 2 = Unlinked (still in use) inode
 * 3 = Used (metadata)
 */

struct gfs2_extent {
	struct gfs2_rbm rbm;
	u32 len;
};

static const char valid_change[16] = {
	        /* current */
	/* n */ 0, 1, 1, 1,
	/* e */ 1, 0, 0, 0,
	/* w */ 0, 0, 0, 1,
	        1, 0, 0, 0
};

static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
			 const struct gfs2_inode *ip, bool nowrap);


/**
 * gfs2_setbit - Set a bit in the bitmaps
 * @rbm: The position of the bit to set
 * @do_clone: Also set the clone bitmap, if it exists
 * @new_state: the new state of the block
 *
 */

static inline void gfs2_setbit(const struct gfs2_rbm *rbm, bool do_clone,
			       unsigned char new_state)
{
	unsigned char *byte1, *byte2, *end, cur_state;
	struct gfs2_bitmap *bi = rbm_bi(rbm);
	unsigned int buflen = bi->bi_bytes;
	const unsigned int bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE;

	byte1 = bi->bi_bh->b_data + bi->bi_offset + (rbm->offset / GFS2_NBBY);
	end = bi->bi_bh->b_data + bi->bi_offset + buflen;

	BUG_ON(byte1 >= end);

	cur_state = (*byte1 >> bit) & GFS2_BIT_MASK;

	if (unlikely(!valid_change[new_state * 4 + cur_state])) {
		struct gfs2_sbd *sdp = rbm->rgd->rd_sbd;

		fs_warn(sdp, "buf_blk = 0x%x old_state=%d, new_state=%d\n",
			rbm->offset, cur_state, new_state);
		fs_warn(sdp, "rgrp=0x%llx bi_start=0x%x biblk: 0x%llx\n",
			(unsigned long long)rbm->rgd->rd_addr, bi->bi_start,
			(unsigned long long)bi->bi_bh->b_blocknr);
		fs_warn(sdp, "bi_offset=0x%x bi_bytes=0x%x block=0x%llx\n",
			bi->bi_offset, bi->bi_bytes,
			(unsigned long long)gfs2_rbm_to_block(rbm));
		dump_stack();
		gfs2_consist_rgrpd(rbm->rgd);
		return;
	}
	*byte1 ^= (cur_state ^ new_state) << bit;

	if (do_clone && bi->bi_clone) {
		byte2 = bi->bi_clone + bi->bi_offset + (rbm->offset / GFS2_NBBY);
		cur_state = (*byte2 >> bit) & GFS2_BIT_MASK;
		*byte2 ^= (cur_state ^ new_state) << bit;
	}
}

/**
 * gfs2_testbit - test a bit in the bitmaps
 * @rbm: The bit to test
 * @use_clone: If true, test the clone bitmap, not the official bitmap.
 *
 * Some callers like gfs2_unaligned_extlen need to test the clone bitmaps,
 * not the "real" bitmaps, to avoid allocating recently freed blocks.
 *
 * Returns: The two bit block state of the requested bit
 */

static inline u8 gfs2_testbit(const struct gfs2_rbm *rbm, bool use_clone)
{
	struct gfs2_bitmap *bi = rbm_bi(rbm);
	const u8 *buffer;
	const u8 *byte;
	unsigned int bit;

	if (use_clone && bi->bi_clone)
		buffer = bi->bi_clone;
	else
		buffer = bi->bi_bh->b_data;
	buffer += bi->bi_offset;
	byte = buffer + (rbm->offset / GFS2_NBBY);
	bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE;

	return (*byte >> bit) & GFS2_BIT_MASK;
}

/**
 * gfs2_bit_search
 * @ptr: Pointer to bitmap data
 * @mask: Mask to use (normally 0x55555.... but adjusted for search start)
 * @state: The state we are searching for
 *
 * We xor the bitmap data with a patter which is the bitwise opposite
 * of what we are looking for, this gives rise to a pattern of ones
 * wherever there is a match. Since we have two bits per entry, we
 * take this pattern, shift it down by one place and then and it with
 * the original. All the even bit positions (0,2,4, etc) then represent
 * successful matches, so we mask with 0x55555..... to remove the unwanted
 * odd bit positions.
 *
 * This allows searching of a whole u64 at once (32 blocks) with a
 * single test (on 64 bit arches).
 */

static inline u64 gfs2_bit_search(const __le64 *ptr, u64 mask, u8 state)
{
	u64 tmp;
	static const u64 search[] = {
		[0] = 0xffffffffffffffffULL,
		[1] = 0xaaaaaaaaaaaaaaaaULL,
		[2] = 0x5555555555555555ULL,
		[3] = 0x0000000000000000ULL,
	};
	tmp = le64_to_cpu(*ptr) ^ search[state];
	tmp &= (tmp >> 1);
	tmp &= mask;
	return tmp;
}

/**
 * rs_cmp - multi-block reservation range compare
 * @blk: absolute file system block number of the new reservation
 * @len: number of blocks in the new reservation
 * @rs: existing reservation to compare against
 *
 * returns: 1 if the block range is beyond the reach of the reservation
 *         -1 if the block range is before the start of the reservation
 *          0 if the block range overlaps with the reservation
 */
static inline int rs_cmp(u64 blk, u32 len, struct gfs2_blkreserv *rs)
{
	u64 startblk = gfs2_rbm_to_block(&rs->rs_rbm);

	if (blk >= startblk + rs->rs_free)
		return 1;
	if (blk + len - 1 < startblk)
		return -1;
	return 0;
}

/**
 * gfs2_bitfit - Search an rgrp's bitmap buffer to find a bit-pair representing
 *       a block in a given allocation state.
 * @buf: the buffer that holds the bitmaps
 * @len: the length (in bytes) of the buffer
 * @goal: start search at this block's bit-pair (within @buffer)
 * @state: GFS2_BLKST_XXX the state of the block we're looking for.
 *
 * Scope of @goal and returned block number is only within this bitmap buffer,
 * not entire rgrp or filesystem.  @buffer will be offset from the actual
 * beginning of a bitmap block buffer, skipping any header structures, but
 * headers are always a multiple of 64 bits long so that the buffer is
 * always aligned to a 64 bit boundary.
 *
 * The size of the buffer is in bytes, but is it assumed that it is
 * always ok to read a complete multiple of 64 bits at the end
 * of the block in case the end is no aligned to a natural boundary.
 *
 * Return: the block number (bitmap buffer scope) that was found
 */

static u32 gfs2_bitfit(const u8 *buf, const unsigned int len,
		       u32 goal, u8 state)
{
	u32 spoint = (goal << 1) & ((8*sizeof(u64)) - 1);
	const __le64 *ptr = ((__le64 *)buf) + (goal >> 5);
	const __le64 *end = (__le64 *)(buf + ALIGN(len, sizeof(u64)));
	u64 tmp;
	u64 mask = 0x5555555555555555ULL;
	u32 bit;

	/* Mask off bits we don't care about at the start of the search */
	mask <<= spoint;
	tmp = gfs2_bit_search(ptr, mask, state);
	ptr++;
	while(tmp == 0 && ptr < end) {
		tmp = gfs2_bit_search(ptr, 0x5555555555555555ULL, state);
		ptr++;
	}
	/* Mask off any bits which are more than len bytes from the start */
	if (ptr == end && (len & (sizeof(u64) - 1)))
		tmp &= (((u64)~0) >> (64 - 8*(len & (sizeof(u64) - 1))));
	/* Didn't find anything, so return */
	if (tmp == 0)
		return BFITNOENT;
	ptr--;
	bit = __ffs64(tmp);
	bit /= 2;	/* two bits per entry in the bitmap */
	return (((const unsigned char *)ptr - buf) * GFS2_NBBY) + bit;
}

/**
 * gfs2_rbm_from_block - Set the rbm based upon rgd and block number
 * @rbm: The rbm with rgd already set correctly
 * @block: The block number (filesystem relative)
 *
 * This sets the bi and offset members of an rbm based on a
 * resource group and a filesystem relative block number. The
 * resource group must be set in the rbm on entry, the bi and
 * offset members will be set by this function.
 *
 * Returns: 0 on success, or an error code
 */

static int gfs2_rbm_from_block(struct gfs2_rbm *rbm, u64 block)
{
	if (!rgrp_contains_block(rbm->rgd, block))
		return -E2BIG;
	rbm->bii = 0;
	rbm->offset = block - rbm->rgd->rd_data0;
	/* Check if the block is within the first block */
	if (rbm->offset < rbm_bi(rbm)->bi_blocks)
		return 0;

	/* Adjust for the size diff between gfs2_meta_header and gfs2_rgrp */
	rbm->offset += (sizeof(struct gfs2_rgrp) -
			sizeof(struct gfs2_meta_header)) * GFS2_NBBY;
	rbm->bii = rbm->offset / rbm->rgd->rd_sbd->sd_blocks_per_bitmap;
	rbm->offset -= rbm->bii * rbm->rgd->rd_sbd->sd_blocks_per_bitmap;
	return 0;
}

/**
 * gfs2_rbm_incr - increment an rbm structure
 * @rbm: The rbm with rgd already set correctly
 *
 * This function takes an existing rbm structure and increments it to the next
 * viable block offset.
 *
 * Returns: If incrementing the offset would cause the rbm to go past the
 *          end of the rgrp, true is returned, otherwise false.
 *
 */

static bool gfs2_rbm_incr(struct gfs2_rbm *rbm)
{
	if (rbm->offset + 1 < rbm_bi(rbm)->bi_blocks) { /* in the same bitmap */
		rbm->offset++;
		return false;
	}
	if (rbm->bii == rbm->rgd->rd_length - 1) /* at the last bitmap */
		return true;

	rbm->offset = 0;
	rbm->bii++;
	return false;
}

/**
 * gfs2_unaligned_extlen - Look for free blocks which are not byte aligned
 * @rbm: Position to search (value/result)
 * @n_unaligned: Number of unaligned blocks to check
 * @len: Decremented for each block found (terminate on zero)
 *
 * Returns: true if a non-free block is encountered
 */

static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *len)
{
	u32 n;
	u8 res;

	for (n = 0; n < n_unaligned; n++) {
		res = gfs2_testbit(rbm, true);
		if (res != GFS2_BLKST_FREE)
			return true;
		(*len)--;
		if (*len == 0)
			return true;
		if (gfs2_rbm_incr(rbm))
			return true;
	}

	return false;
}

/**
 * gfs2_free_extlen - Return extent length of free blocks
 * @rrbm: Starting position
 * @len: Max length to check
 *
 * Starting at the block specified by the rbm, see how many free blocks
 * there are, not reading more than len blocks ahead. This can be done
 * using memchr_inv when the blocks are byte aligned, but has to be done
 * on a block by block basis in case of unaligned blocks. Also this
 * function can cope with bitmap boundaries (although it must stop on
 * a resource group boundary)
 *
 * Returns: Number of free blocks in the extent
 */

static u32 gfs2_free_extlen(const struct gfs2_rbm *rrbm, u32 len)
{
	struct gfs2_rbm rbm = *rrbm;
	u32 n_unaligned = rbm.offset & 3;
	u32 size = len;
	u32 bytes;
	u32 chunk_size;
	u8 *ptr, *start, *end;
	u64 block;
	struct gfs2_bitmap *bi;

	if (n_unaligned &&
	    gfs2_unaligned_extlen(&rbm, 4 - n_unaligned, &len))
		goto out;

	n_unaligned = len & 3;
	/* Start is now byte aligned */
	while (len > 3) {
		bi = rbm_bi(&rbm);
		start = bi->bi_bh->b_data;
		if (bi->bi_clone)
			start = bi->bi_clone;
		start += bi->bi_offset;
		end = start + bi->bi_bytes;
		BUG_ON(rbm.offset & 3);
		start += (rbm.offset / GFS2_NBBY);
		bytes = min_t(u32, len / GFS2_NBBY, (end - start));
		ptr = memchr_inv(start, 0, bytes);
		chunk_size = ((ptr == NULL) ? bytes : (ptr - start));
		chunk_size *= GFS2_NBBY;
		BUG_ON(len < chunk_size);
		len -= chunk_size;
		block = gfs2_rbm_to_block(&rbm);
		if (gfs2_rbm_from_block(&rbm, block + chunk_size)) {
			n_unaligned = 0;
			break;
		}
		if (ptr) {
			n_unaligned = 3;
			break;
		}
		n_unaligned = len & 3;
	}

	/* Deal with any bits left over at the end */
	if (n_unaligned)
		gfs2_unaligned_extlen(&rbm, n_unaligned, &len);
out:
	return size - len;
}

/**
 * gfs2_bitcount - count the number of bits in a certain state
 * @rgd: the resource group descriptor
 * @buffer: the buffer that holds the bitmaps
 * @buflen: the length (in bytes) of the buffer
 * @state: the state of the block we're looking for
 *
 * Returns: The number of bits
 */

static u32 gfs2_bitcount(struct gfs2_rgrpd *rgd, const u8 *buffer,
			 unsigned int buflen, u8 state)
{
	const u8 *byte = buffer;
	const u8 *end = buffer + buflen;
	const u8 state1 = state << 2;
	const u8 state2 = state << 4;
	const u8 state3 = state << 6;
	u32 count = 0;

	for (; byte < end; byte++) {
		if (((*byte) & 0x03) == state)
			count++;
		if (((*byte) & 0x0C) == state1)
			count++;
		if (((*byte) & 0x30) == state2)
			count++;
		if (((*byte) & 0xC0) == state3)
			count++;
	}

	return count;
}

/**
 * gfs2_rgrp_verify - Verify that a resource group is consistent
 * @rgd: the rgrp
 *
 */

void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_bitmap *bi = NULL;
	u32 length = rgd->rd_length;
	u32 count[4], tmp;
	int buf, x;

	memset(count, 0, 4 * sizeof(u32));

	/* Count # blocks in each of 4 possible allocation states */
	for (buf = 0; buf < length; buf++) {
		bi = rgd->rd_bits + buf;
		for (x = 0; x < 4; x++)
			count[x] += gfs2_bitcount(rgd,
						  bi->bi_bh->b_data +
						  bi->bi_offset,
						  bi->bi_bytes, x);
	}

	if (count[0] != rgd->rd_free) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "free data mismatch:  %u != %u\n",
			       count[0], rgd->rd_free);
		return;
	}

	tmp = rgd->rd_data - rgd->rd_free - rgd->rd_dinodes;
	if (count[1] != tmp) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "used data mismatch:  %u != %u\n",
			       count[1], tmp);
		return;
	}

	if (count[2] + count[3] != rgd->rd_dinodes) {
		if (gfs2_consist_rgrpd(rgd))
			fs_err(sdp, "used metadata mismatch:  %u != %u\n",
			       count[2] + count[3], rgd->rd_dinodes);
		return;
	}
}

/**
 * gfs2_blk2rgrpd - Find resource group for a given data/meta block number
 * @sdp: The GFS2 superblock
 * @blk: The data block number
 * @exact: True if this needs to be an exact match
 *
 * The @exact argument should be set to true by most callers. The exception
 * is when we need to match blocks which are not represented by the rgrp
 * bitmap, but which are part of the rgrp (i.e. padding blocks) which are
 * there for alignment purposes. Another way of looking at it is that @exact
 * matches only valid data/metadata blocks, but with @exact false, it will
 * match any block within the extent of the rgrp.
 *
 * Returns: The resource group, or NULL if not found
 */

struct gfs2_rgrpd *gfs2_blk2rgrpd(struct gfs2_sbd *sdp, u64 blk, bool exact)
{
	struct rb_node *n, *next;
	struct gfs2_rgrpd *cur;

	spin_lock(&sdp->sd_rindex_spin);
	n = sdp->sd_rindex_tree.rb_node;
	while (n) {
		cur = rb_entry(n, struct gfs2_rgrpd, rd_node);
		next = NULL;
		if (blk < cur->rd_addr)
			next = n->rb_left;
		else if (blk >= cur->rd_data0 + cur->rd_data)
			next = n->rb_right;
		if (next == NULL) {
			spin_unlock(&sdp->sd_rindex_spin);
			if (exact) {
				if (blk < cur->rd_addr)
					return NULL;
				if (blk >= cur->rd_data0 + cur->rd_data)
					return NULL;
			}
			return cur;
		}
		n = next;
	}
	spin_unlock(&sdp->sd_rindex_spin);

	return NULL;
}

/**
 * gfs2_rgrpd_get_first - get the first Resource Group in the filesystem
 * @sdp: The GFS2 superblock
 *
 * Returns: The first rgrp in the filesystem
 */

struct gfs2_rgrpd *gfs2_rgrpd_get_first(struct gfs2_sbd *sdp)
{
	const struct rb_node *n;
	struct gfs2_rgrpd *rgd;

	spin_lock(&sdp->sd_rindex_spin);
	n = rb_first(&sdp->sd_rindex_tree);
	rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
	spin_unlock(&sdp->sd_rindex_spin);

	return rgd;
}

/**
 * gfs2_rgrpd_get_next - get the next RG
 * @rgd: the resource group descriptor
 *
 * Returns: The next rgrp
 */

struct gfs2_rgrpd *gfs2_rgrpd_get_next(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	const struct rb_node *n;

	spin_lock(&sdp->sd_rindex_spin);
	n = rb_next(&rgd->rd_node);
	if (n == NULL)
		n = rb_first(&sdp->sd_rindex_tree);

	if (unlikely(&rgd->rd_node == n)) {
		spin_unlock(&sdp->sd_rindex_spin);
		return NULL;
	}
	rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
	spin_unlock(&sdp->sd_rindex_spin);
	return rgd;
}

void check_and_update_goal(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	if (!ip->i_goal || gfs2_blk2rgrpd(sdp, ip->i_goal, 1) == NULL)
		ip->i_goal = ip->i_no_addr;
}

void gfs2_free_clones(struct gfs2_rgrpd *rgd)
{
	int x;

	for (x = 0; x < rgd->rd_length; x++) {
		struct gfs2_bitmap *bi = rgd->rd_bits + x;
		kfree(bi->bi_clone);
		bi->bi_clone = NULL;
	}
}

/**
 * gfs2_rsqa_alloc - make sure we have a reservation assigned to the inode
 *                 plus a quota allocations data structure, if necessary
 * @ip: the inode for this reservation
 */
int gfs2_rsqa_alloc(struct gfs2_inode *ip)
{
	return gfs2_qa_alloc(ip);
}

static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
{
	struct gfs2_inode *ip = container_of(rs, struct gfs2_inode, i_res);

	gfs2_print_dbg(seq, "  B: n:%llu s:%llu b:%u f:%u\n",
		       (unsigned long long)ip->i_no_addr,
		       (unsigned long long)gfs2_rbm_to_block(&rs->rs_rbm),
		       rs->rs_rbm.offset, rs->rs_free);
}

/**
 * __rs_deltree - remove a multi-block reservation from the rgd tree
 * @rs: The reservation to remove
 *
 */
static void __rs_deltree(struct gfs2_blkreserv *rs)
{
	struct gfs2_rgrpd *rgd;

	if (!gfs2_rs_active(rs))
		return;

	rgd = rs->rs_rbm.rgd;
	trace_gfs2_rs(rs, TRACE_RS_TREEDEL);
	rb_erase(&rs->rs_node, &rgd->rd_rstree);
	RB_CLEAR_NODE(&rs->rs_node);

	if (rs->rs_free) {
		u64 last_block = gfs2_rbm_to_block(&rs->rs_rbm) +
				 rs->rs_free - 1;
		struct gfs2_rbm last_rbm = { .rgd = rs->rs_rbm.rgd, };
		struct gfs2_bitmap *start, *last;

		/* return reserved blocks to the rgrp */
		BUG_ON(rs->rs_rbm.rgd->rd_reserved < rs->rs_free);
		rs->rs_rbm.rgd->rd_reserved -= rs->rs_free;
		/* The rgrp extent failure point is likely not to increase;
		   it will only do so if the freed blocks are somehow
		   contiguous with a span of free blocks that follows. Still,
		   it will force the number to be recalculated later. */
		rgd->rd_extfail_pt += rs->rs_free;
		rs->rs_free = 0;
		if (gfs2_rbm_from_block(&last_rbm, last_block))
			return;
		start = rbm_bi(&rs->rs_rbm);
		last = rbm_bi(&last_rbm);
		do
			clear_bit(GBF_FULL, &start->bi_flags);
		while (start++ != last);
	}
}

/**
 * gfs2_rs_deltree - remove a multi-block reservation from the rgd tree
 * @rs: The reservation to remove
 *
 */
void gfs2_rs_deltree(struct gfs2_blkreserv *rs)
{
	struct gfs2_rgrpd *rgd;

	rgd = rs->rs_rbm.rgd;
	if (rgd) {
		spin_lock(&rgd->rd_rsspin);
		__rs_deltree(rs);
		BUG_ON(rs->rs_free);
		spin_unlock(&rgd->rd_rsspin);
	}
}

/**
 * gfs2_rsqa_delete - delete a multi-block reservation and quota allocation
 * @ip: The inode for this reservation
 * @wcount: The inode's write count, or NULL
 *
 */
void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount)
{
	down_write(&ip->i_rw_mutex);
	if ((wcount == NULL) || (atomic_read(wcount) <= 1))
		gfs2_rs_deltree(&ip->i_res);
	up_write(&ip->i_rw_mutex);
	gfs2_qa_delete(ip, wcount);
}

/**
 * return_all_reservations - return all reserved blocks back to the rgrp.
 * @rgd: the rgrp that needs its space back
 *
 * We previously reserved a bunch of blocks for allocation. Now we need to
 * give them back. This leave the reservation structures in tact, but removes
 * all of their corresponding "no-fly zones".
 */
static void return_all_reservations(struct gfs2_rgrpd *rgd)
{
	struct rb_node *n;
	struct gfs2_blkreserv *rs;

	spin_lock(&rgd->rd_rsspin);
	while ((n = rb_first(&rgd->rd_rstree))) {
		rs = rb_entry(n, struct gfs2_blkreserv, rs_node);
		__rs_deltree(rs);
	}
	spin_unlock(&rgd->rd_rsspin);
}

void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
{
	struct rb_node *n;
	struct gfs2_rgrpd *rgd;
	struct gfs2_glock *gl;

	while ((n = rb_first(&sdp->sd_rindex_tree))) {
		rgd = rb_entry(n, struct gfs2_rgrpd, rd_node);
		gl = rgd->rd_gl;

		rb_erase(n, &sdp->sd_rindex_tree);

		if (gl) {
			glock_clear_object(gl, rgd);
			gfs2_rgrp_brelse(rgd);
			gfs2_glock_put(gl);
		}

		gfs2_free_clones(rgd);
		kfree(rgd->rd_bits);
		rgd->rd_bits = NULL;
		return_all_reservations(rgd);
		kmem_cache_free(gfs2_rgrpd_cachep, rgd);
	}
}

static void gfs2_rindex_print(const struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;

	fs_info(sdp, "ri_addr = %llu\n", (unsigned long long)rgd->rd_addr);
	fs_info(sdp, "ri_length = %u\n", rgd->rd_length);
	fs_info(sdp, "ri_data0 = %llu\n", (unsigned long long)rgd->rd_data0);
	fs_info(sdp, "ri_data = %u\n", rgd->rd_data);
	fs_info(sdp, "ri_bitbytes = %u\n", rgd->rd_bitbytes);
}

/**
 * gfs2_compute_bitstructs - Compute the bitmap sizes
 * @rgd: The resource group descriptor
 *
 * Calculates bitmap descriptors, one for each block that contains bitmap data
 *
 * Returns: errno
 */

static int compute_bitstructs(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_bitmap *bi;
	u32 length = rgd->rd_length; /* # blocks in hdr & bitmap */
	u32 bytes_left, bytes;
	int x;

	if (!length)
		return -EINVAL;

	rgd->rd_bits = kcalloc(length, sizeof(struct gfs2_bitmap), GFP_NOFS);
	if (!rgd->rd_bits)
		return -ENOMEM;

	bytes_left = rgd->rd_bitbytes;

	for (x = 0; x < length; x++) {
		bi = rgd->rd_bits + x;

		bi->bi_flags = 0;
		/* small rgrp; bitmap stored completely in header block */
		if (length == 1) {
			bytes = bytes_left;
			bi->bi_offset = sizeof(struct gfs2_rgrp);
			bi->bi_start = 0;
			bi->bi_bytes = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		/* header block */
		} else if (x == 0) {
			bytes = sdp->sd_sb.sb_bsize - sizeof(struct gfs2_rgrp);
			bi->bi_offset = sizeof(struct gfs2_rgrp);
			bi->bi_start = 0;
			bi->bi_bytes = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		/* last block */
		} else if (x + 1 == length) {
			bytes = bytes_left;
			bi->bi_offset = sizeof(struct gfs2_meta_header);
			bi->bi_start = rgd->rd_bitbytes - bytes_left;
			bi->bi_bytes = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		/* other blocks */
		} else {
			bytes = sdp->sd_sb.sb_bsize -
				sizeof(struct gfs2_meta_header);
			bi->bi_offset = sizeof(struct gfs2_meta_header);
			bi->bi_start = rgd->rd_bitbytes - bytes_left;
			bi->bi_bytes = bytes;
			bi->bi_blocks = bytes * GFS2_NBBY;
		}

		bytes_left -= bytes;
	}

	if (bytes_left) {
		gfs2_consist_rgrpd(rgd);
		return -EIO;
	}
	bi = rgd->rd_bits + (length - 1);
	if ((bi->bi_start + bi->bi_bytes) * GFS2_NBBY != rgd->rd_data) {
		if (gfs2_consist_rgrpd(rgd)) {
			gfs2_rindex_print(rgd);
			fs_err(sdp, "start=%u len=%u offset=%u\n",
			       bi->bi_start, bi->bi_bytes, bi->bi_offset);
		}
		return -EIO;
	}

	return 0;
}

/**
 * gfs2_ri_total - Total up the file system space, according to the rindex.
 * @sdp: the filesystem
 *
 */
u64 gfs2_ri_total(struct gfs2_sbd *sdp)
{
	u64 total_data = 0;	
	struct inode *inode = sdp->sd_rindex;
	struct gfs2_inode *ip = GFS2_I(inode);
	char buf[sizeof(struct gfs2_rindex)];
	int error, rgrps;

	for (rgrps = 0;; rgrps++) {
		loff_t pos = rgrps * sizeof(struct gfs2_rindex);

		if (pos + sizeof(struct gfs2_rindex) > i_size_read(inode))
			break;
		error = gfs2_internal_read(ip, buf, &pos,
					   sizeof(struct gfs2_rindex));
		if (error != sizeof(struct gfs2_rindex))
			break;
		total_data += be32_to_cpu(((struct gfs2_rindex *)buf)->ri_data);
	}
	return total_data;
}

static int rgd_insert(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct rb_node **newn = &sdp->sd_rindex_tree.rb_node, *parent = NULL;

	/* Figure out where to put new node */
	while (*newn) {
		struct gfs2_rgrpd *cur = rb_entry(*newn, struct gfs2_rgrpd,
						  rd_node);

		parent = *newn;
		if (rgd->rd_addr < cur->rd_addr)
			newn = &((*newn)->rb_left);
		else if (rgd->rd_addr > cur->rd_addr)
			newn = &((*newn)->rb_right);
		else
			return -EEXIST;
	}

	rb_link_node(&rgd->rd_node, parent, newn);
	rb_insert_color(&rgd->rd_node, &sdp->sd_rindex_tree);
	sdp->sd_rgrps++;
	return 0;
}

/**
 * read_rindex_entry - Pull in a new resource index entry from the disk
 * @ip: Pointer to the rindex inode
 *
 * Returns: 0 on success, > 0 on EOF, error code otherwise
 */

static int read_rindex_entry(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	const unsigned bsize = sdp->sd_sb.sb_bsize;
	loff_t pos = sdp->sd_rgrps * sizeof(struct gfs2_rindex);
	struct gfs2_rindex buf;
	int error;
	struct gfs2_rgrpd *rgd;

	if (pos >= i_size_read(&ip->i_inode))
		return 1;

	error = gfs2_internal_read(ip, (char *)&buf, &pos,
				   sizeof(struct gfs2_rindex));

	if (error != sizeof(struct gfs2_rindex))
		return (error == 0) ? 1 : error;

	rgd = kmem_cache_zalloc(gfs2_rgrpd_cachep, GFP_NOFS);
	error = -ENOMEM;
	if (!rgd)
		return error;

	rgd->rd_sbd = sdp;
	rgd->rd_addr = be64_to_cpu(buf.ri_addr);
	rgd->rd_length = be32_to_cpu(buf.ri_length);
	rgd->rd_data0 = be64_to_cpu(buf.ri_data0);
	rgd->rd_data = be32_to_cpu(buf.ri_data);
	rgd->rd_bitbytes = be32_to_cpu(buf.ri_bitbytes);
	spin_lock_init(&rgd->rd_rsspin);

	error = compute_bitstructs(rgd);
	if (error)
		goto fail;

	error = gfs2_glock_get(sdp, rgd->rd_addr,
			       &gfs2_rgrp_glops, CREATE, &rgd->rd_gl);
	if (error)
		goto fail;

	rgd->rd_rgl = (struct gfs2_rgrp_lvb *)rgd->rd_gl->gl_lksb.sb_lvbptr;
	rgd->rd_flags &= ~(GFS2_RDF_UPTODATE | GFS2_RDF_PREFERRED);
	if (rgd->rd_data > sdp->sd_max_rg_data)
		sdp->sd_max_rg_data = rgd->rd_data;
	spin_lock(&sdp->sd_rindex_spin);
	error = rgd_insert(rgd);
	spin_unlock(&sdp->sd_rindex_spin);
	if (!error) {
		glock_set_object(rgd->rd_gl, rgd);
		rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_MASK;
		rgd->rd_gl->gl_vm.end = PAGE_ALIGN((rgd->rd_addr +
						    rgd->rd_length) * bsize) - 1;
		return 0;
	}

	error = 0; /* someone else read in the rgrp; free it and ignore it */
	gfs2_glock_put(rgd->rd_gl);

fail:
	kfree(rgd->rd_bits);
	rgd->rd_bits = NULL;
	kmem_cache_free(gfs2_rgrpd_cachep, rgd);
	return error;
}

/**
 * set_rgrp_preferences - Run all the rgrps, selecting some we prefer to use
 * @sdp: the GFS2 superblock
 *
 * The purpose of this function is to select a subset of the resource groups
 * and mark them as PREFERRED. We do it in such a way that each node prefers
 * to use a unique set of rgrps to minimize glock contention.
 */
static void set_rgrp_preferences(struct gfs2_sbd *sdp)
{
	struct gfs2_rgrpd *rgd, *first;
	int i;

	/* Skip an initial number of rgrps, based on this node's journal ID.
	   That should start each node out on its own set. */
	rgd = gfs2_rgrpd_get_first(sdp);
	for (i = 0; i < sdp->sd_lockstruct.ls_jid; i++)
		rgd = gfs2_rgrpd_get_next(rgd);
	first = rgd;

	do {
		rgd->rd_flags |= GFS2_RDF_PREFERRED;
		for (i = 0; i < sdp->sd_journals; i++) {
			rgd = gfs2_rgrpd_get_next(rgd);
			if (!rgd || rgd == first)
				break;
		}
	} while (rgd && rgd != first);
}

/**
 * gfs2_ri_update - Pull in a new resource index from the disk
 * @ip: pointer to the rindex inode
 *
 * Returns: 0 on successful update, error code otherwise
 */

static int gfs2_ri_update(struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	int error;

	do {
		error = read_rindex_entry(ip);
	} while (error == 0);

	if (error < 0)
		return error;

	set_rgrp_preferences(sdp);

	sdp->sd_rindex_uptodate = 1;
	return 0;
}

/**
 * gfs2_rindex_update - Update the rindex if required
 * @sdp: The GFS2 superblock
 *
 * We grab a lock on the rindex inode to make sure that it doesn't
 * change whilst we are performing an operation. We keep this lock
 * for quite long periods of time compared to other locks. This
 * doesn't matter, since it is shared and it is very, very rarely
 * accessed in the exclusive mode (i.e. only when expanding the filesystem).
 *
 * This makes sure that we're using the latest copy of the resource index
 * special file, which might have been updated if someone expanded the
 * filesystem (via gfs2_grow utility), which adds new resource groups.
 *
 * Returns: 0 on succeess, error code otherwise
 */

int gfs2_rindex_update(struct gfs2_sbd *sdp)
{
	struct gfs2_inode *ip = GFS2_I(sdp->sd_rindex);
	struct gfs2_glock *gl = ip->i_gl;
	struct gfs2_holder ri_gh;
	int error = 0;
	int unlock_required = 0;

	/* Read new copy from disk if we don't have the latest */
	if (!sdp->sd_rindex_uptodate) {
		if (!gfs2_glock_is_locked_by_me(gl)) {
			error = gfs2_glock_nq_init(gl, LM_ST_SHARED, 0, &ri_gh);
			if (error)
				return error;
			unlock_required = 1;
		}
		if (!sdp->sd_rindex_uptodate)
			error = gfs2_ri_update(ip);
		if (unlock_required)
			gfs2_glock_dq_uninit(&ri_gh);
	}

	return error;
}

static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
{
	const struct gfs2_rgrp *str = buf;
	u32 rg_flags;

	rg_flags = be32_to_cpu(str->rg_flags);
	rg_flags &= ~GFS2_RDF_MASK;
	rgd->rd_flags &= GFS2_RDF_MASK;
	rgd->rd_flags |= rg_flags;
	rgd->rd_free = be32_to_cpu(str->rg_free);
	rgd->rd_dinodes = be32_to_cpu(str->rg_dinodes);
	rgd->rd_igeneration = be64_to_cpu(str->rg_igeneration);
	/* rd_data0, rd_data and rd_bitbytes already set from rindex */
}

static void gfs2_rgrp_ondisk2lvb(struct gfs2_rgrp_lvb *rgl, const void *buf)
{
	const struct gfs2_rgrp *str = buf;

	rgl->rl_magic = cpu_to_be32(GFS2_MAGIC);
	rgl->rl_flags = str->rg_flags;
	rgl->rl_free = str->rg_free;
	rgl->rl_dinodes = str->rg_dinodes;
	rgl->rl_igeneration = str->rg_igeneration;
	rgl->__pad = 0UL;
}

static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
{
	struct gfs2_rgrpd *next = gfs2_rgrpd_get_next(rgd);
	struct gfs2_rgrp *str = buf;
	u32 crc;

	str->rg_flags = cpu_to_be32(rgd->rd_flags & ~GFS2_RDF_MASK);
	str->rg_free = cpu_to_be32(rgd->rd_free);
	str->rg_dinodes = cpu_to_be32(rgd->rd_dinodes);
	if (next == NULL)
		str->rg_skip = 0;
	else if (next->rd_addr > rgd->rd_addr)
		str->rg_skip = cpu_to_be32(next->rd_addr - rgd->rd_addr);
	str->rg_igeneration = cpu_to_be64(rgd->rd_igeneration);
	str->rg_data0 = cpu_to_be64(rgd->rd_data0);
	str->rg_data = cpu_to_be32(rgd->rd_data);
	str->rg_bitbytes = cpu_to_be32(rgd->rd_bitbytes);
	str->rg_crc = 0;
	crc = gfs2_disk_hash(buf, sizeof(struct gfs2_rgrp));
	str->rg_crc = cpu_to_be32(crc);

	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, buf);
}

static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd)
{
	struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
	struct gfs2_rgrp *str = (struct gfs2_rgrp *)rgd->rd_bits[0].bi_bh->b_data;
	int valid = 1;

	if (rgl->rl_flags != str->rg_flags) {
		printk(KERN_WARNING "GFS2: rgd: %llu lvb flag mismatch %u/%u",
		       (unsigned long long)rgd->rd_addr,
		       be32_to_cpu(rgl->rl_flags), be32_to_cpu(str->rg_flags));
		valid = 0;
	}
	if (rgl->rl_free != str->rg_free) {
		printk(KERN_WARNING "GFS2: rgd: %llu lvb free mismatch %u/%u",
		       (unsigned long long)rgd->rd_addr,
		       be32_to_cpu(rgl->rl_free), be32_to_cpu(str->rg_free));
		valid = 0;
	}
	if (rgl->rl_dinodes != str->rg_dinodes) {
		printk(KERN_WARNING "GFS2: rgd: %llu lvb dinode mismatch %u/%u",
		       (unsigned long long)rgd->rd_addr,
		       be32_to_cpu(rgl->rl_dinodes),
		       be32_to_cpu(str->rg_dinodes));
		valid = 0;
	}
	if (rgl->rl_igeneration != str->rg_igeneration) {
		printk(KERN_WARNING "GFS2: rgd: %llu lvb igen mismatch "
		       "%llu/%llu", (unsigned long long)rgd->rd_addr,
		       (unsigned long long)be64_to_cpu(rgl->rl_igeneration),
		       (unsigned long long)be64_to_cpu(str->rg_igeneration));
		valid = 0;
	}
	return valid;
}

static u32 count_unlinked(struct gfs2_rgrpd *rgd)
{
	struct gfs2_bitmap *bi;
	const u32 length = rgd->rd_length;
	const u8 *buffer = NULL;
	u32 i, goal, count = 0;

	for (i = 0, bi = rgd->rd_bits; i < length; i++, bi++) {
		goal = 0;
		buffer = bi->bi_bh->b_data + bi->bi_offset;
		WARN_ON(!buffer_uptodate(bi->bi_bh));
		while (goal < bi->bi_blocks) {
			goal = gfs2_bitfit(buffer, bi->bi_bytes, goal,
					   GFS2_BLKST_UNLINKED);
			if (goal == BFITNOENT)
				break;
			count++;
			goal++;
		}
	}

	return count;
}


/**
 * gfs2_rgrp_bh_get - Read in a RG's header and bitmaps
 * @rgd: the struct gfs2_rgrpd describing the RG to read in
 *
 * Read in all of a Resource Group's header and bitmap blocks.
 * Caller must eventually call gfs2_rgrp_brelse() to free the bitmaps.
 *
 * Returns: errno
 */

static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_glock *gl = rgd->rd_gl;
	unsigned int length = rgd->rd_length;
	struct gfs2_bitmap *bi;
	unsigned int x, y;
	int error;

	if (rgd->rd_bits[0].bi_bh != NULL)
		return 0;

	for (x = 0; x < length; x++) {
		bi = rgd->rd_bits + x;
		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, 0, &bi->bi_bh);
		if (error)
			goto fail;
	}

	for (y = length; y--;) {
		bi = rgd->rd_bits + y;
		error = gfs2_meta_wait(sdp, bi->bi_bh);
		if (error)
			goto fail;
		if (gfs2_metatype_check(sdp, bi->bi_bh, y ? GFS2_METATYPE_RB :
					      GFS2_METATYPE_RG)) {
			error = -EIO;
			goto fail;
		}
	}

	if (!(rgd->rd_flags & GFS2_RDF_UPTODATE)) {
		for (x = 0; x < length; x++)
			clear_bit(GBF_FULL, &rgd->rd_bits[x].bi_flags);
		gfs2_rgrp_in(rgd, (rgd->rd_bits[0].bi_bh)->b_data);
		rgd->rd_flags |= (GFS2_RDF_UPTODATE | GFS2_RDF_CHECK);
		rgd->rd_free_clone = rgd->rd_free;
		/* max out the rgrp allocation failure point */
		rgd->rd_extfail_pt = rgd->rd_free;
	}
	if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic) {
		rgd->rd_rgl->rl_unlinked = cpu_to_be32(count_unlinked(rgd));
		gfs2_rgrp_ondisk2lvb(rgd->rd_rgl,
				     rgd->rd_bits[0].bi_bh->b_data);
	}
	else if (sdp->sd_args.ar_rgrplvb) {
		if (!gfs2_rgrp_lvb_valid(rgd)){
			gfs2_consist_rgrpd(rgd);
			error = -EIO;
			goto fail;
		}
		if (rgd->rd_rgl->rl_unlinked == 0)
			rgd->rd_flags &= ~GFS2_RDF_CHECK;
	}
	return 0;

fail:
	while (x--) {
		bi = rgd->rd_bits + x;
		brelse(bi->bi_bh);
		bi->bi_bh = NULL;
		gfs2_assert_warn(sdp, !bi->bi_clone);
	}

	return error;
}

static int update_rgrp_lvb(struct gfs2_rgrpd *rgd)
{
	u32 rl_flags;

	if (rgd->rd_flags & GFS2_RDF_UPTODATE)
		return 0;

	if (cpu_to_be32(GFS2_MAGIC) != rgd->rd_rgl->rl_magic)
		return gfs2_rgrp_bh_get(rgd);

	rl_flags = be32_to_cpu(rgd->rd_rgl->rl_flags);
	rl_flags &= ~GFS2_RDF_MASK;
	rgd->rd_flags &= GFS2_RDF_MASK;
	rgd->rd_flags |= (rl_flags | GFS2_RDF_CHECK);
	if (rgd->rd_rgl->rl_unlinked == 0)
		rgd->rd_flags &= ~GFS2_RDF_CHECK;
	rgd->rd_free = be32_to_cpu(rgd->rd_rgl->rl_free);
	rgd->rd_free_clone = rgd->rd_free;
	rgd->rd_dinodes = be32_to_cpu(rgd->rd_rgl->rl_dinodes);
	rgd->rd_igeneration = be64_to_cpu(rgd->rd_rgl->rl_igeneration);
	return 0;
}

int gfs2_rgrp_go_lock(struct gfs2_holder *gh)
{
	struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
	struct gfs2_sbd *sdp = rgd->rd_sbd;

	if (gh->gh_flags & GL_SKIP && sdp->sd_args.ar_rgrplvb)
		return 0;
	return gfs2_rgrp_bh_get(rgd);
}

/**
 * gfs2_rgrp_brelse - Release RG bitmaps read in with gfs2_rgrp_bh_get()
 * @rgd: The resource group
 *
 */

void gfs2_rgrp_brelse(struct gfs2_rgrpd *rgd)
{
	int x, length = rgd->rd_length;

	for (x = 0; x < length; x++) {
		struct gfs2_bitmap *bi = rgd->rd_bits + x;
		if (bi->bi_bh) {
			brelse(bi->bi_bh);
			bi->bi_bh = NULL;
		}
	}

}

/**
 * gfs2_rgrp_go_unlock - Unlock a rgrp glock
 * @gh: The glock holder for the resource group
 *
 */

void gfs2_rgrp_go_unlock(struct gfs2_holder *gh)
{
	struct gfs2_rgrpd *rgd = gh->gh_gl->gl_object;
	int demote_requested = test_bit(GLF_DEMOTE, &gh->gh_gl->gl_flags) |
		test_bit(GLF_PENDING_DEMOTE, &gh->gh_gl->gl_flags);

	if (rgd && demote_requested)
		gfs2_rgrp_brelse(rgd);
}

int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
			     struct buffer_head *bh,
			     const struct gfs2_bitmap *bi, unsigned minlen, u64 *ptrimmed)
{
	struct super_block *sb = sdp->sd_vfs;
	u64 blk;
	sector_t start = 0;
	sector_t nr_blks = 0;
	int rv;
	unsigned int x;
	u32 trimmed = 0;
	u8 diff;

	for (x = 0; x < bi->bi_bytes; x++) {
		const u8 *clone = bi->bi_clone ? bi->bi_clone : bi->bi_bh->b_data;
		clone += bi->bi_offset;
		clone += x;
		if (bh) {
			const u8 *orig = bh->b_data + bi->bi_offset + x;
			diff = ~(*orig | (*orig >> 1)) & (*clone | (*clone >> 1));
		} else {
			diff = ~(*clone | (*clone >> 1));
		}
		diff &= 0x55;
		if (diff == 0)
			continue;
		blk = offset + ((bi->bi_start + x) * GFS2_NBBY);
		while(diff) {
			if (diff & 1) {
				if (nr_blks == 0)
					goto start_new_extent;
				if ((start + nr_blks) != blk) {
					if (nr_blks >= minlen) {
						rv = sb_issue_discard(sb,
							start, nr_blks,
							GFP_NOFS, 0);
						if (rv)
							goto fail;
						trimmed += nr_blks;
					}
					nr_blks = 0;
start_new_extent:
					start = blk;
				}
				nr_blks++;
			}
			diff >>= 2;
			blk++;
		}
	}
	if (nr_blks >= minlen) {
		rv = sb_issue_discard(sb, start, nr_blks, GFP_NOFS, 0);
		if (rv)
			goto fail;
		trimmed += nr_blks;
	}
	if (ptrimmed)
		*ptrimmed = trimmed;
	return 0;

fail:
	if (sdp->sd_args.ar_discard)
		fs_warn(sdp, "error %d on discard request, turning discards off for this filesystem\n", rv);
	sdp->sd_args.ar_discard = 0;
	return -EIO;
}

/**
 * gfs2_fitrim - Generate discard requests for unused bits of the filesystem
 * @filp: Any file on the filesystem
 * @argp: Pointer to the arguments (also used to pass result)
 *
 * Returns: 0 on success, otherwise error code
 */

int gfs2_fitrim(struct file *filp, void __user *argp)
{
	struct inode *inode = file_inode(filp);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct request_queue *q = bdev_get_queue(sdp->sd_vfs->s_bdev);
	struct buffer_head *bh;
	struct gfs2_rgrpd *rgd;
	struct gfs2_rgrpd *rgd_end;
	struct gfs2_holder gh;
	struct fstrim_range r;
	int ret = 0;
	u64 amt;
	u64 trimmed = 0;
	u64 start, end, minlen;
	unsigned int x;
	unsigned bs_shift = sdp->sd_sb.sb_bsize_shift;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!blk_queue_discard(q))
		return -EOPNOTSUPP;

	if (copy_from_user(&r, argp, sizeof(r)))
		return -EFAULT;

	ret = gfs2_rindex_update(sdp);
	if (ret)
		return ret;

	start = r.start >> bs_shift;
	end = start + (r.len >> bs_shift);
	minlen = max_t(u64, r.minlen,
		       q->limits.discard_granularity) >> bs_shift;

	if (end <= start || minlen > sdp->sd_max_rg_data)
		return -EINVAL;

	rgd = gfs2_blk2rgrpd(sdp, start, 0);
	rgd_end = gfs2_blk2rgrpd(sdp, end, 0);

	if ((gfs2_rgrpd_get_first(sdp) == gfs2_rgrpd_get_next(rgd_end))
	    && (start > rgd_end->rd_data0 + rgd_end->rd_data))
		return -EINVAL; /* start is beyond the end of the fs */

	while (1) {

		ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, &gh);
		if (ret)
			goto out;

		if (!(rgd->rd_flags & GFS2_RGF_TRIMMED)) {
			/* Trim each bitmap in the rgrp */
			for (x = 0; x < rgd->rd_length; x++) {
				struct gfs2_bitmap *bi = rgd->rd_bits + x;
				ret = gfs2_rgrp_send_discards(sdp,
						rgd->rd_data0, NULL, bi, minlen,
						&amt);
				if (ret) {
					gfs2_glock_dq_uninit(&gh);
					goto out;
				}
				trimmed += amt;
			}

			/* Mark rgrp as having been trimmed */
			ret = gfs2_trans_begin(sdp, RES_RG_HDR, 0);
			if (ret == 0) {
				bh = rgd->rd_bits[0].bi_bh;
				rgd->rd_flags |= GFS2_RGF_TRIMMED;
				gfs2_trans_add_meta(rgd->rd_gl, bh);
				gfs2_rgrp_out(rgd, bh->b_data);
				gfs2_trans_end(sdp);
			}
		}
		gfs2_glock_dq_uninit(&gh);

		if (rgd == rgd_end)
			break;

		rgd = gfs2_rgrpd_get_next(rgd);
	}

out:
	r.len = trimmed << bs_shift;
	if (copy_to_user(argp, &r, sizeof(r)))
		return -EFAULT;

	return ret;
}

/**
 * rs_insert - insert a new multi-block reservation into the rgrp's rb_tree
 * @ip: the inode structure
 *
 */
static void rs_insert(struct gfs2_inode *ip)
{
	struct rb_node **newn, *parent = NULL;
	int rc;
	struct gfs2_blkreserv *rs = &ip->i_res;
	struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd;
	u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm);

	BUG_ON(gfs2_rs_active(rs));

	spin_lock(&rgd->rd_rsspin);
	newn = &rgd->rd_rstree.rb_node;
	while (*newn) {
		struct gfs2_blkreserv *cur =
			rb_entry(*newn, struct gfs2_blkreserv, rs_node);

		parent = *newn;
		rc = rs_cmp(fsblock, rs->rs_free, cur);
		if (rc > 0)
			newn = &((*newn)->rb_right);
		else if (rc < 0)
			newn = &((*newn)->rb_left);
		else {
			spin_unlock(&rgd->rd_rsspin);
			WARN_ON(1);
			return;
		}
	}

	rb_link_node(&rs->rs_node, parent, newn);
	rb_insert_color(&rs->rs_node, &rgd->rd_rstree);

	/* Do our rgrp accounting for the reservation */
	rgd->rd_reserved += rs->rs_free; /* blocks reserved */
	spin_unlock(&rgd->rd_rsspin);
	trace_gfs2_rs(rs, TRACE_RS_INSERT);
}

/**
 * rgd_free - return the number of free blocks we can allocate.
 * @rgd: the resource group
 *
 * This function returns the number of free blocks for an rgrp.
 * That's the clone-free blocks (blocks that are free, not including those
 * still being used for unlinked files that haven't been deleted.)
 *
 * It also subtracts any blocks reserved by someone else, but does not
 * include free blocks that are still part of our current reservation,
 * because obviously we can (and will) allocate them.
 */
static inline u32 rgd_free(struct gfs2_rgrpd *rgd, struct gfs2_blkreserv *rs)
{
	u32 tot_reserved, tot_free;

	if (WARN_ON_ONCE(rgd->rd_reserved < rs->rs_free))
		return 0;
	tot_reserved = rgd->rd_reserved - rs->rs_free;

	if (rgd->rd_free_clone < tot_reserved)
		tot_reserved = 0;

	tot_free = rgd->rd_free_clone - tot_reserved;

	return tot_free;
}

/**
 * rg_mblk_search - find a group of multiple free blocks to form a reservation
 * @rgd: the resource group descriptor
 * @ip: pointer to the inode for which we're reserving blocks
 * @ap: the allocation parameters
 *
 */

static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
			   const struct gfs2_alloc_parms *ap)
{
	struct gfs2_rbm rbm = { .rgd = rgd, };
	u64 goal;
	struct gfs2_blkreserv *rs = &ip->i_res;
	u32 extlen;
	u32 free_blocks = rgd_free(rgd, rs);
	int ret;
	struct inode *inode = &ip->i_inode;

	if (S_ISDIR(inode->i_mode))
		extlen = 1;
	else {
		extlen = max_t(u32, atomic_read(&ip->i_sizehint), ap->target);
		extlen = clamp(extlen, (u32)RGRP_RSRV_MINBLKS, free_blocks);
	}
	if ((rgd->rd_free_clone < rgd->rd_reserved) || (free_blocks < extlen))
		return;

	/* Find bitmap block that contains bits for goal block */
	if (rgrp_contains_block(rgd, ip->i_goal))
		goal = ip->i_goal;
	else
		goal = rgd->rd_last_alloc + rgd->rd_data0;

	if (WARN_ON(gfs2_rbm_from_block(&rbm, goal)))
		return;

	ret = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, &extlen, ip, true);
	if (ret == 0) {
		rs->rs_rbm = rbm;
		rs->rs_free = extlen;
		rs_insert(ip);
	} else {
		if (goal == rgd->rd_last_alloc + rgd->rd_data0)
			rgd->rd_last_alloc = 0;
	}
}

/**
 * gfs2_next_unreserved_block - Return next block that is not reserved
 * @rgd: The resource group
 * @block: The starting block
 * @length: The required length
 * @ip: Ignore any reservations for this inode
 *
 * If the block does not appear in any reservation, then return the
 * block number unchanged. If it does appear in the reservation, then
 * keep looking through the tree of reservations in order to find the
 * first block number which is not reserved.
 */

static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block,
				      u32 length,
				      const struct gfs2_inode *ip)
{
	struct gfs2_blkreserv *rs;
	struct rb_node *n;
	int rc;

	spin_lock(&rgd->rd_rsspin);
	n = rgd->rd_rstree.rb_node;
	while (n) {
		rs = rb_entry(n, struct gfs2_blkreserv, rs_node);
		rc = rs_cmp(block, length, rs);
		if (rc < 0)
			n = n->rb_left;
		else if (rc > 0)
			n = n->rb_right;
		else
			break;
	}

	if (n) {
		while ((rs_cmp(block, length, rs) == 0) && (&ip->i_res != rs)) {
			block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free;
			n = n->rb_right;
			if (n == NULL)
				break;
			rs = rb_entry(n, struct gfs2_blkreserv, rs_node);
		}
	}

	spin_unlock(&rgd->rd_rsspin);
	return block;
}

/**
 * gfs2_reservation_check_and_update - Check for reservations during block alloc
 * @rbm: The current position in the resource group
 * @ip: The inode for which we are searching for blocks
 * @minext: The minimum extent length
 * @maxext: A pointer to the maximum extent structure
 *
 * This checks the current position in the rgrp to see whether there is
 * a reservation covering this block. If not then this function is a
 * no-op. If there is, then the position is moved to the end of the
 * contiguous reservation(s) so that we are pointing at the first
 * non-reserved block.
 *
 * Returns: 0 if no reservation, 1 if @rbm has changed, otherwise an error
 */

static int gfs2_reservation_check_and_update(struct gfs2_rbm *rbm,
					     const struct gfs2_inode *ip,
					     u32 minext,
					     struct gfs2_extent *maxext)
{
	u64 block = gfs2_rbm_to_block(rbm);
	u32 extlen = 1;
	u64 nblock;
	int ret;

	/*
	 * If we have a minimum extent length, then skip over any extent
	 * which is less than the min extent length in size.
	 */
	if (minext) {
		extlen = gfs2_free_extlen(rbm, minext);
		if (extlen <= maxext->len)
			goto fail;
	}

	/*
	 * Check the extent which has been found against the reservations
	 * and skip if parts of it are already reserved
	 */
	nblock = gfs2_next_unreserved_block(rbm->rgd, block, extlen, ip);
	if (nblock == block) {
		if (!minext || extlen >= minext)
			return 0;

		if (extlen > maxext->len) {
			maxext->len = extlen;
			maxext->rbm = *rbm;
		}
fail:
		nblock = block + extlen;
	}
	ret = gfs2_rbm_from_block(rbm, nblock);
	if (ret < 0)
		return ret;
	return 1;
}

/**
 * gfs2_rbm_find - Look for blocks of a particular state
 * @rbm: Value/result starting position and final position
 * @state: The state which we want to find
 * @minext: Pointer to the requested extent length (NULL for a single block)
 *          This is updated to be the actual reservation size.
 * @ip: If set, check for reservations
 * @nowrap: Stop looking at the end of the rgrp, rather than wrapping
 *          around until we've reached the starting point.
 *
 * Side effects:
 * - If looking for free blocks, we set GBF_FULL on each bitmap which
 *   has no free blocks in it.
 * - If looking for free blocks, we set rd_extfail_pt on each rgrp which
 *   has come up short on a free block search.
 *
 * Returns: 0 on success, -ENOSPC if there is no block of the requested state
 */

static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
			 const struct gfs2_inode *ip, bool nowrap)
{
	struct buffer_head *bh;
	int initial_bii;
	u32 initial_offset;
	int first_bii = rbm->bii;
	u32 first_offset = rbm->offset;
	u32 offset;
	u8 *buffer;
	int n = 0;
	int iters = rbm->rgd->rd_length;
	int ret;
	struct gfs2_bitmap *bi;
	struct gfs2_extent maxext = { .rbm.rgd = rbm->rgd, };

	/* If we are not starting at the beginning of a bitmap, then we
	 * need to add one to the bitmap count to ensure that we search
	 * the starting bitmap twice.
	 */
	if (rbm->offset != 0)
		iters++;

	while(1) {
		bi = rbm_bi(rbm);
		if ((ip == NULL || !gfs2_rs_active(&ip->i_res)) &&
		    test_bit(GBF_FULL, &bi->bi_flags) &&
		    (state == GFS2_BLKST_FREE))
			goto next_bitmap;

		bh = bi->bi_bh;
		buffer = bh->b_data + bi->bi_offset;
		WARN_ON(!buffer_uptodate(bh));
		if (state != GFS2_BLKST_UNLINKED && bi->bi_clone)
			buffer = bi->bi_clone + bi->bi_offset;
		initial_offset = rbm->offset;
		offset = gfs2_bitfit(buffer, bi->bi_bytes, rbm->offset, state);
		if (offset == BFITNOENT)
			goto bitmap_full;
		rbm->offset = offset;
		if (ip == NULL)
			return 0;

		initial_bii = rbm->bii;
		ret = gfs2_reservation_check_and_update(rbm, ip,
							minext ? *minext : 0,
							&maxext);
		if (ret == 0)
			return 0;
		if (ret > 0) {
			n += (rbm->bii - initial_bii);
			goto next_iter;
		}
		if (ret == -E2BIG) {
			rbm->bii = 0;
			rbm->offset = 0;
			n += (rbm->bii - initial_bii);
			goto res_covered_end_of_rgrp;
		}
		return ret;

bitmap_full:	/* Mark bitmap as full and fall through */
		if ((state == GFS2_BLKST_FREE) && initial_offset == 0)
			set_bit(GBF_FULL, &bi->bi_flags);

next_bitmap:	/* Find next bitmap in the rgrp */
		rbm->offset = 0;
		rbm->bii++;
		if (rbm->bii == rbm->rgd->rd_length)
			rbm->bii = 0;
res_covered_end_of_rgrp:
		if ((rbm->bii == 0) && nowrap)
			break;
		n++;
next_iter:
		if (n >= iters)
			break;
	}

	if (minext == NULL || state != GFS2_BLKST_FREE)
		return -ENOSPC;

	/* If the extent was too small, and it's smaller than the smallest
	   to have failed before, remember for future reference that it's
	   useless to search this rgrp again for this amount or more. */
	if ((first_offset == 0) && (first_bii == 0) &&
	    (*minext < rbm->rgd->rd_extfail_pt))
		rbm->rgd->rd_extfail_pt = *minext;

	/* If the maximum extent we found is big enough to fulfill the
	   minimum requirements, use it anyway. */
	if (maxext.len) {
		*rbm = maxext.rbm;
		*minext = maxext.len;
		return 0;
	}

	return -ENOSPC;
}

/**
 * try_rgrp_unlink - Look for any unlinked, allocated, but unused inodes
 * @rgd: The rgrp
 * @last_unlinked: block address of the last dinode we unlinked
 * @skip: block address we should explicitly not unlink
 *
 * Returns: 0 if no error
 *          The inode, if one has been found, in inode.
 */

static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip)
{
	u64 block;
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	struct gfs2_glock *gl;
	struct gfs2_inode *ip;
	int error;
	int found = 0;
	struct gfs2_rbm rbm = { .rgd = rgd, .bii = 0, .offset = 0 };

	while (1) {
		down_write(&sdp->sd_log_flush_lock);
		error = gfs2_rbm_find(&rbm, GFS2_BLKST_UNLINKED, NULL, NULL,
				      true);
		up_write(&sdp->sd_log_flush_lock);
		if (error == -ENOSPC)
			break;
		if (WARN_ON_ONCE(error))
			break;

		block = gfs2_rbm_to_block(&rbm);
		if (gfs2_rbm_from_block(&rbm, block + 1))
			break;
		if (*last_unlinked != NO_BLOCK && block <= *last_unlinked)
			continue;
		if (block == skip)
			continue;
		*last_unlinked = block;

		error = gfs2_glock_get(sdp, block, &gfs2_iopen_glops, CREATE, &gl);
		if (error)
			continue;

		/* If the inode is already in cache, we can ignore it here
		 * because the existing inode disposal code will deal with
		 * it when all refs have gone away. Accessing gl_object like
		 * this is not safe in general. Here it is ok because we do
		 * not dereference the pointer, and we only need an approx
		 * answer to whether it is NULL or not.
		 */
		ip = gl->gl_object;

		if (ip || queue_work(gfs2_delete_workqueue, &gl->gl_delete) == 0)
			gfs2_glock_put(gl);
		else
			found++;

		/* Limit reclaim to sensible number of tasks */
		if (found > NR_CPUS)
			return;
	}

	rgd->rd_flags &= ~GFS2_RDF_CHECK;
	return;
}

/**
 * gfs2_rgrp_congested - Use stats to figure out whether an rgrp is congested
 * @rgd: The rgrp in question
 * @loops: An indication of how picky we can be (0=very, 1=less so)
 *
 * This function uses the recently added glock statistics in order to
 * figure out whether a parciular resource group is suffering from
 * contention from multiple nodes. This is done purely on the basis
 * of timings, since this is the only data we have to work with and
 * our aim here is to reject a resource group which is highly contended
 * but (very important) not to do this too often in order to ensure that
 * we do not land up introducing fragmentation by changing resource
 * groups when not actually required.
 *
 * The calculation is fairly simple, we want to know whether the SRTTB
 * (i.e. smoothed round trip time for blocking operations) to acquire
 * the lock for this rgrp's glock is significantly greater than the
 * time taken for resource groups on average. We introduce a margin in
 * the form of the variable @var which is computed as the sum of the two
 * respective variences, and multiplied by a factor depending on @loops
 * and whether we have a lot of data to base the decision on. This is
 * then tested against the square difference of the means in order to
 * decide whether the result is statistically significant or not.
 *
 * Returns: A boolean verdict on the congestion status
 */

static bool gfs2_rgrp_congested(const struct gfs2_rgrpd *rgd, int loops)
{
	const struct gfs2_glock *gl = rgd->rd_gl;
	const struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
	struct gfs2_lkstats *st;
	u64 r_dcount, l_dcount;
	u64 l_srttb, a_srttb = 0;
	s64 srttb_diff;
	u64 sqr_diff;
	u64 var;
	int cpu, nonzero = 0;

	preempt_disable();
	for_each_present_cpu(cpu) {
		st = &per_cpu_ptr(sdp->sd_lkstats, cpu)->lkstats[LM_TYPE_RGRP];
		if (st->stats[GFS2_LKS_SRTTB]) {
			a_srttb += st->stats[GFS2_LKS_SRTTB];
			nonzero++;
		}
	}
	st = &this_cpu_ptr(sdp->sd_lkstats)->lkstats[LM_TYPE_RGRP];
	if (nonzero)
		do_div(a_srttb, nonzero);
	r_dcount = st->stats[GFS2_LKS_DCOUNT];
	var = st->stats[GFS2_LKS_SRTTVARB] +
	      gl->gl_stats.stats[GFS2_LKS_SRTTVARB];
	preempt_enable();

	l_srttb = gl->gl_stats.stats[GFS2_LKS_SRTTB];
	l_dcount = gl->gl_stats.stats[GFS2_LKS_DCOUNT];

	if ((l_dcount < 1) || (r_dcount < 1) || (a_srttb == 0))
		return false;

	srttb_diff = a_srttb - l_srttb;
	sqr_diff = srttb_diff * srttb_diff;

	var *= 2;
	if (l_dcount < 8 || r_dcount < 8)
		var *= 2;
	if (loops == 1)
		var *= 2;

	return ((srttb_diff < 0) && (sqr_diff > var));
}

/**
 * gfs2_rgrp_used_recently
 * @rs: The block reservation with the rgrp to test
 * @msecs: The time limit in milliseconds
 *
 * Returns: True if the rgrp glock has been used within the time limit
 */
static bool gfs2_rgrp_used_recently(const struct gfs2_blkreserv *rs,
				    u64 msecs)
{
	u64 tdiff;

	tdiff = ktime_to_ns(ktime_sub(ktime_get_real(),
                            rs->rs_rbm.rgd->rd_gl->gl_dstamp));

	return tdiff > (msecs * 1000 * 1000);
}

static u32 gfs2_orlov_skip(const struct gfs2_inode *ip)
{
	const struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	u32 skip;

	get_random_bytes(&skip, sizeof(skip));
	return skip % sdp->sd_rgrps;
}

static bool gfs2_select_rgrp(struct gfs2_rgrpd **pos, const struct gfs2_rgrpd *begin)
{
	struct gfs2_rgrpd *rgd = *pos;
	struct gfs2_sbd *sdp = rgd->rd_sbd;

	rgd = gfs2_rgrpd_get_next(rgd);
	if (rgd == NULL)
		rgd = gfs2_rgrpd_get_first(sdp);
	*pos = rgd;
	if (rgd != begin) /* If we didn't wrap */
		return true;
	return false;
}

/**
 * fast_to_acquire - determine if a resource group will be fast to acquire
 *
 * If this is one of our preferred rgrps, it should be quicker to acquire,
 * because we tried to set ourselves up as dlm lock master.
 */
static inline int fast_to_acquire(struct gfs2_rgrpd *rgd)
{
	struct gfs2_glock *gl = rgd->rd_gl;

	if (gl->gl_state != LM_ST_UNLOCKED && list_empty(&gl->gl_holders) &&
	    !test_bit(GLF_DEMOTE_IN_PROGRESS, &gl->gl_flags) &&
	    !test_bit(GLF_DEMOTE, &gl->gl_flags))
		return 1;
	if (rgd->rd_flags & GFS2_RDF_PREFERRED)
		return 1;
	return 0;
}

/**
 * gfs2_inplace_reserve - Reserve space in the filesystem
 * @ip: the inode to reserve space for
 * @ap: the allocation parameters
 *
 * We try our best to find an rgrp that has at least ap->target blocks
 * available. After a couple of passes (loops == 2), the prospects of finding
 * such an rgrp diminish. At this stage, we return the first rgrp that has
 * at least ap->min_target blocks available. Either way, we set ap->allowed to
 * the number of blocks available in the chosen rgrp.
 *
 * Returns: 0 on success,
 *          -ENOMEM if a suitable rgrp can't be found
 *          errno otherwise
 */

int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_rgrpd *begin = NULL;
	struct gfs2_blkreserv *rs = &ip->i_res;
	int error = 0, rg_locked, flags = 0;
	u64 last_unlinked = NO_BLOCK;
	int loops = 0;
	u32 free_blocks, skip = 0;

	if (sdp->sd_args.ar_rgrplvb)
		flags |= GL_SKIP;
	if (gfs2_assert_warn(sdp, ap->target))
		return -EINVAL;
	if (gfs2_rs_active(rs)) {
		begin = rs->rs_rbm.rgd;
	} else if (rs->rs_rbm.rgd &&
		   rgrp_contains_block(rs->rs_rbm.rgd, ip->i_goal)) {
		begin = rs->rs_rbm.rgd;
	} else {
		check_and_update_goal(ip);
		rs->rs_rbm.rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1);
	}
	if (S_ISDIR(ip->i_inode.i_mode) && (ap->aflags & GFS2_AF_ORLOV))
		skip = gfs2_orlov_skip(ip);
	if (rs->rs_rbm.rgd == NULL)
		return -EBADSLT;

	while (loops < 3) {
		rg_locked = 1;

		if (!gfs2_glock_is_locked_by_me(rs->rs_rbm.rgd->rd_gl)) {
			rg_locked = 0;
			if (skip && skip--)
				goto next_rgrp;
			if (!gfs2_rs_active(rs)) {
				if (loops == 0 &&
				    !fast_to_acquire(rs->rs_rbm.rgd))
					goto next_rgrp;
				if ((loops < 2) &&
				    gfs2_rgrp_used_recently(rs, 1000) &&
				    gfs2_rgrp_congested(rs->rs_rbm.rgd, loops))
					goto next_rgrp;
			}
			error = gfs2_glock_nq_init(rs->rs_rbm.rgd->rd_gl,
						   LM_ST_EXCLUSIVE, flags,
						   &ip->i_rgd_gh);
			if (unlikely(error))
				return error;
			if (!gfs2_rs_active(rs) && (loops < 2) &&
			    gfs2_rgrp_congested(rs->rs_rbm.rgd, loops))
				goto skip_rgrp;
			if (sdp->sd_args.ar_rgrplvb) {
				error = update_rgrp_lvb(rs->rs_rbm.rgd);
				if (unlikely(error)) {
					gfs2_glock_dq_uninit(&ip->i_rgd_gh);
					return error;
				}
			}
		}

		/* Skip unusable resource groups */
		if ((rs->rs_rbm.rgd->rd_flags & (GFS2_RGF_NOALLOC |
						 GFS2_RDF_ERROR)) ||
		    (loops == 0 && ap->target > rs->rs_rbm.rgd->rd_extfail_pt))
			goto skip_rgrp;

		if (sdp->sd_args.ar_rgrplvb)
			gfs2_rgrp_bh_get(rs->rs_rbm.rgd);

		/* Get a reservation if we don't already have one */
		if (!gfs2_rs_active(rs))
			rg_mblk_search(rs->rs_rbm.rgd, ip, ap);

		/* Skip rgrps when we can't get a reservation on first pass */
		if (!gfs2_rs_active(rs) && (loops < 1))
			goto check_rgrp;

		/* If rgrp has enough free space, use it */
		free_blocks = rgd_free(rs->rs_rbm.rgd, rs);
		if (free_blocks >= ap->target ||
		    (loops == 2 && ap->min_target &&
		     free_blocks >= ap->min_target)) {
			ap->allowed = free_blocks;
			return 0;
		}
check_rgrp:
		/* Check for unlinked inodes which can be reclaimed */
		if (rs->rs_rbm.rgd->rd_flags & GFS2_RDF_CHECK)
			try_rgrp_unlink(rs->rs_rbm.rgd, &last_unlinked,
					ip->i_no_addr);
skip_rgrp:
		/* Drop reservation, if we couldn't use reserved rgrp */
		if (gfs2_rs_active(rs))
			gfs2_rs_deltree(rs);

		/* Unlock rgrp if required */
		if (!rg_locked)
			gfs2_glock_dq_uninit(&ip->i_rgd_gh);
next_rgrp:
		/* Find the next rgrp, and continue looking */
		if (gfs2_select_rgrp(&rs->rs_rbm.rgd, begin))
			continue;
		if (skip)
			continue;

		/* If we've scanned all the rgrps, but found no free blocks
		 * then this checks for some less likely conditions before
		 * trying again.
		 */
		loops++;
		/* Check that fs hasn't grown if writing to rindex */
		if (ip == GFS2_I(sdp->sd_rindex) && !sdp->sd_rindex_uptodate) {
			error = gfs2_ri_update(ip);
			if (error)
				return error;
		}
		/* Flushing the log may release space */
		if (loops == 2)
			gfs2_log_flush(sdp, NULL, GFS2_LOG_HEAD_FLUSH_NORMAL |
				       GFS2_LFC_INPLACE_RESERVE);
	}

	return -ENOSPC;
}

/**
 * gfs2_inplace_release - release an inplace reservation
 * @ip: the inode the reservation was taken out on
 *
 * Release a reservation made by gfs2_inplace_reserve().
 */

void gfs2_inplace_release(struct gfs2_inode *ip)
{
	if (gfs2_holder_initialized(&ip->i_rgd_gh))
		gfs2_glock_dq_uninit(&ip->i_rgd_gh);
}

/**
 * gfs2_alloc_extent - allocate an extent from a given bitmap
 * @rbm: the resource group information
 * @dinode: TRUE if the first block we allocate is for a dinode
 * @n: The extent length (value/result)
 *
 * Add the bitmap buffer to the transaction.
 * Set the found bits to @new_state to change block's allocation state.
 */
static void gfs2_alloc_extent(const struct gfs2_rbm *rbm, bool dinode,
			     unsigned int *n)
{
	struct gfs2_rbm pos = { .rgd = rbm->rgd, };
	const unsigned int elen = *n;
	u64 block;
	int ret;

	*n = 1;
	block = gfs2_rbm_to_block(rbm);
	gfs2_trans_add_meta(rbm->rgd->rd_gl, rbm_bi(rbm)->bi_bh);
	gfs2_setbit(rbm, true, dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED);
	block++;
	while (*n < elen) {
		ret = gfs2_rbm_from_block(&pos, block);
		if (ret || gfs2_testbit(&pos, true) != GFS2_BLKST_FREE)
			break;
		gfs2_trans_add_meta(pos.rgd->rd_gl, rbm_bi(&pos)->bi_bh);
		gfs2_setbit(&pos, true, GFS2_BLKST_USED);
		(*n)++;
		block++;
	}
}

/**
 * rgblk_free - Change alloc state of given block(s)
 * @sdp: the filesystem
 * @rgd: the resource group the blocks are in
 * @bstart: the start of a run of blocks to free
 * @blen: the length of the block run (all must lie within ONE RG!)
 * @new_state: GFS2_BLKST_XXX the after-allocation block state
 */

static void rgblk_free(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd,
		       u64 bstart, u32 blen, unsigned char new_state)
{
	struct gfs2_rbm rbm;
	struct gfs2_bitmap *bi, *bi_prev = NULL;

	rbm.rgd = rgd;
	if (WARN_ON_ONCE(gfs2_rbm_from_block(&rbm, bstart)))
		return;
	while (blen--) {
		bi = rbm_bi(&rbm);
		if (bi != bi_prev) {
			if (!bi->bi_clone) {
				bi->bi_clone = kmalloc(bi->bi_bh->b_size,
						      GFP_NOFS | __GFP_NOFAIL);
				memcpy(bi->bi_clone + bi->bi_offset,
				       bi->bi_bh->b_data + bi->bi_offset,
				       bi->bi_bytes);
			}
			gfs2_trans_add_meta(rbm.rgd->rd_gl, bi->bi_bh);
			bi_prev = bi;
		}
		gfs2_setbit(&rbm, false, new_state);
		gfs2_rbm_incr(&rbm);
	}
}

/**
 * gfs2_rgrp_dump - print out an rgrp
 * @seq: The iterator
 * @gl: The glock in question
 *
 */

void gfs2_rgrp_dump(struct seq_file *seq, struct gfs2_glock *gl)
{
	struct gfs2_rgrpd *rgd = gl->gl_object;
	struct gfs2_blkreserv *trs;
	const struct rb_node *n;

	if (rgd == NULL)
		return;
	gfs2_print_dbg(seq, " R: n:%llu f:%02x b:%u/%u i:%u r:%u e:%u\n",
		       (unsigned long long)rgd->rd_addr, rgd->rd_flags,
		       rgd->rd_free, rgd->rd_free_clone, rgd->rd_dinodes,
		       rgd->rd_reserved, rgd->rd_extfail_pt);
	if (rgd->rd_sbd->sd_args.ar_rgrplvb) {
		struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;

		gfs2_print_dbg(seq, "  L: f:%02x b:%u i:%u\n",
			       be32_to_cpu(rgl->rl_flags),
			       be32_to_cpu(rgl->rl_free),
			       be32_to_cpu(rgl->rl_dinodes));
	}
	spin_lock(&rgd->rd_rsspin);
	for (n = rb_first(&rgd->rd_rstree); n; n = rb_next(&trs->rs_node)) {
		trs = rb_entry(n, struct gfs2_blkreserv, rs_node);
		dump_rs(seq, trs);
	}
	spin_unlock(&rgd->rd_rsspin);
}

static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;
	fs_warn(sdp, "rgrp %llu has an error, marking it readonly until umount\n",
		(unsigned long long)rgd->rd_addr);
	fs_warn(sdp, "umount on all nodes and run fsck.gfs2 to fix the error\n");
	gfs2_rgrp_dump(NULL, rgd->rd_gl);
	rgd->rd_flags |= GFS2_RDF_ERROR;
}

/**
 * gfs2_adjust_reservation - Adjust (or remove) a reservation after allocation
 * @ip: The inode we have just allocated blocks for
 * @rbm: The start of the allocated blocks
 * @len: The extent length
 *
 * Adjusts a reservation after an allocation has taken place. If the
 * reservation does not match the allocation, or if it is now empty
 * then it is removed.
 */

static void gfs2_adjust_reservation(struct gfs2_inode *ip,
				    const struct gfs2_rbm *rbm, unsigned len)
{
	struct gfs2_blkreserv *rs = &ip->i_res;
	struct gfs2_rgrpd *rgd = rbm->rgd;
	unsigned rlen;
	u64 block;
	int ret;

	spin_lock(&rgd->rd_rsspin);
	if (gfs2_rs_active(rs)) {
		if (gfs2_rbm_eq(&rs->rs_rbm, rbm)) {
			block = gfs2_rbm_to_block(rbm);
			ret = gfs2_rbm_from_block(&rs->rs_rbm, block + len);
			rlen = min(rs->rs_free, len);
			rs->rs_free -= rlen;
			rgd->rd_reserved -= rlen;
			trace_gfs2_rs(rs, TRACE_RS_CLAIM);
			if (rs->rs_free && !ret)
				goto out;
			/* We used up our block reservation, so we should
			   reserve more blocks next time. */
			atomic_add(RGRP_RSRV_ADDBLKS, &ip->i_sizehint);
		}
		__rs_deltree(rs);
	}
out:
	spin_unlock(&rgd->rd_rsspin);
}

/**
 * gfs2_set_alloc_start - Set starting point for block allocation
 * @rbm: The rbm which will be set to the required location
 * @ip: The gfs2 inode
 * @dinode: Flag to say if allocation includes a new inode
 *
 * This sets the starting point from the reservation if one is active
 * otherwise it falls back to guessing a start point based on the
 * inode's goal block or the last allocation point in the rgrp.
 */

static void gfs2_set_alloc_start(struct gfs2_rbm *rbm,
				 const struct gfs2_inode *ip, bool dinode)
{
	u64 goal;

	if (gfs2_rs_active(&ip->i_res)) {
		*rbm = ip->i_res.rs_rbm;
		return;
	}

	if (!dinode && rgrp_contains_block(rbm->rgd, ip->i_goal))
		goal = ip->i_goal;
	else
		goal = rbm->rgd->rd_last_alloc + rbm->rgd->rd_data0;

	if (WARN_ON_ONCE(gfs2_rbm_from_block(rbm, goal))) {
		rbm->bii = 0;
		rbm->offset = 0;
	}
}

/**
 * gfs2_alloc_blocks - Allocate one or more blocks of data and/or a dinode
 * @ip: the inode to allocate the block for
 * @bn: Used to return the starting block number
 * @nblocks: requested number of blocks/extent length (value/result)
 * @dinode: 1 if we're allocating a dinode block, else 0
 * @generation: the generation number of the inode
 *
 * Returns: 0 or error
 */

int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
		      bool dinode, u64 *generation)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct buffer_head *dibh;
	struct gfs2_rbm rbm = { .rgd = ip->i_res.rs_rbm.rgd, };
	unsigned int ndata;
	u64 block; /* block, within the file system scope */
	int error;

	gfs2_set_alloc_start(&rbm, ip, dinode);
	error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, ip, false);

	if (error == -ENOSPC) {
		gfs2_set_alloc_start(&rbm, ip, dinode);
		error = gfs2_rbm_find(&rbm, GFS2_BLKST_FREE, NULL, NULL, false);
	}

	/* Since all blocks are reserved in advance, this shouldn't happen */
	if (error) {
		fs_warn(sdp, "inum=%llu error=%d, nblocks=%u, full=%d fail_pt=%d\n",
			(unsigned long long)ip->i_no_addr, error, *nblocks,
			test_bit(GBF_FULL, &rbm.rgd->rd_bits->bi_flags),
			rbm.rgd->rd_extfail_pt);
		goto rgrp_error;
	}

	gfs2_alloc_extent(&rbm, dinode, nblocks);
	block = gfs2_rbm_to_block(&rbm);
	rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0;
	if (gfs2_rs_active(&ip->i_res))
		gfs2_adjust_reservation(ip, &rbm, *nblocks);
	ndata = *nblocks;
	if (dinode)
		ndata--;

	if (!dinode) {
		ip->i_goal = block + ndata - 1;
		error = gfs2_meta_inode_buffer(ip, &dibh);
		if (error == 0) {
			struct gfs2_dinode *di =
				(struct gfs2_dinode *)dibh->b_data;
			gfs2_trans_add_meta(ip->i_gl, dibh);
			di->di_goal_meta = di->di_goal_data =
				cpu_to_be64(ip->i_goal);
			brelse(dibh);
		}
	}
	if (rbm.rgd->rd_free < *nblocks) {
		fs_warn(sdp, "nblocks=%u\n", *nblocks);
		goto rgrp_error;
	}

	rbm.rgd->rd_free -= *nblocks;
	if (dinode) {
		rbm.rgd->rd_dinodes++;
		*generation = rbm.rgd->rd_igeneration++;
		if (*generation == 0)
			*generation = rbm.rgd->rd_igeneration++;
	}

	gfs2_trans_add_meta(rbm.rgd->rd_gl, rbm.rgd->rd_bits[0].bi_bh);
	gfs2_rgrp_out(rbm.rgd, rbm.rgd->rd_bits[0].bi_bh->b_data);

	gfs2_statfs_change(sdp, 0, -(s64)*nblocks, dinode ? 1 : 0);
	if (dinode)
		gfs2_trans_add_unrevoke(sdp, block, *nblocks);

	gfs2_quota_change(ip, *nblocks, ip->i_inode.i_uid, ip->i_inode.i_gid);

	rbm.rgd->rd_free_clone -= *nblocks;
	trace_gfs2_block_alloc(ip, rbm.rgd, block, *nblocks,
			       dinode ? GFS2_BLKST_DINODE : GFS2_BLKST_USED);
	*bn = block;
	return 0;

rgrp_error:
	gfs2_rgrp_error(rbm.rgd);
	return -EIO;
}

/**
 * __gfs2_free_blocks - free a contiguous run of block(s)
 * @ip: the inode these blocks are being freed from
 * @rgd: the resource group the blocks are in
 * @bstart: first block of a run of contiguous blocks
 * @blen: the length of the block run
 * @meta: 1 if the blocks represent metadata
 *
 */

void __gfs2_free_blocks(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd,
			u64 bstart, u32 blen, int meta)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);

	rgblk_free(sdp, rgd, bstart, blen, GFS2_BLKST_FREE);
	trace_gfs2_block_alloc(ip, rgd, bstart, blen, GFS2_BLKST_FREE);
	rgd->rd_free += blen;
	rgd->rd_flags &= ~GFS2_RGF_TRIMMED;
	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);

	/* Directories keep their data in the metadata address space */
	if (meta || ip->i_depth)
		gfs2_meta_wipe(ip, bstart, blen);
}

/**
 * gfs2_free_meta - free a contiguous run of data block(s)
 * @ip: the inode these blocks are being freed from
 * @rgd: the resource group the blocks are in
 * @bstart: first block of a run of contiguous blocks
 * @blen: the length of the block run
 *
 */

void gfs2_free_meta(struct gfs2_inode *ip, struct gfs2_rgrpd *rgd,
		    u64 bstart, u32 blen)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);

	__gfs2_free_blocks(ip, rgd, bstart, blen, 1);
	gfs2_statfs_change(sdp, 0, +blen, 0);
	gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid);
}

void gfs2_unlink_di(struct inode *inode)
{
	struct gfs2_inode *ip = GFS2_I(inode);
	struct gfs2_sbd *sdp = GFS2_SB(inode);
	struct gfs2_rgrpd *rgd;
	u64 blkno = ip->i_no_addr;

	rgd = gfs2_blk2rgrpd(sdp, blkno, true);
	if (!rgd)
		return;
	rgblk_free(sdp, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
	trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
	be32_add_cpu(&rgd->rd_rgl->rl_unlinked, 1);
}

void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
{
	struct gfs2_sbd *sdp = rgd->rd_sbd;

	rgblk_free(sdp, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE);
	if (!rgd->rd_dinodes)
		gfs2_consist_rgrpd(rgd);
	rgd->rd_dinodes--;
	rgd->rd_free++;

	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
	be32_add_cpu(&rgd->rd_rgl->rl_unlinked, -1);

	gfs2_statfs_change(sdp, 0, +1, -1);
	trace_gfs2_block_alloc(ip, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE);
	gfs2_quota_change(ip, -1, ip->i_inode.i_uid, ip->i_inode.i_gid);
	gfs2_meta_wipe(ip, ip->i_no_addr, 1);
}

/**
 * gfs2_check_blk_type - Check the type of a block
 * @sdp: The superblock
 * @no_addr: The block number to check
 * @type: The block type we are looking for
 *
 * Returns: 0 if the block type matches the expected type
 *          -ESTALE if it doesn't match
 *          or -ve errno if something went wrong while checking
 */

int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
{
	struct gfs2_rgrpd *rgd;
	struct gfs2_holder rgd_gh;
	struct gfs2_rbm rbm;
	int error = -EINVAL;

	rgd = gfs2_blk2rgrpd(sdp, no_addr, 1);
	if (!rgd)
		goto fail;

	error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_SHARED, 0, &rgd_gh);
	if (error)
		goto fail;

	rbm.rgd = rgd;
	error = gfs2_rbm_from_block(&rbm, no_addr);
	if (WARN_ON_ONCE(error))
		goto fail;

	if (gfs2_testbit(&rbm, false) != type)
		error = -ESTALE;

	gfs2_glock_dq_uninit(&rgd_gh);
fail:
	return error;
}

/**
 * gfs2_rlist_add - add a RG to a list of RGs
 * @ip: the inode
 * @rlist: the list of resource groups
 * @block: the block
 *
 * Figure out what RG a block belongs to and add that RG to the list
 *
 * FIXME: Don't use NOFAIL
 *
 */

void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
		    u64 block)
{
	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
	struct gfs2_rgrpd *rgd;
	struct gfs2_rgrpd **tmp;
	unsigned int new_space;
	unsigned int x;

	if (gfs2_assert_warn(sdp, !rlist->rl_ghs))
		return;

	/*
	 * The resource group last accessed is kept in the last position.
	 */

	if (rlist->rl_rgrps) {
		rgd = rlist->rl_rgd[rlist->rl_rgrps - 1];
		if (rgrp_contains_block(rgd, block))
			return;
		rgd = gfs2_blk2rgrpd(sdp, block, 1);
	} else {
		rgd = ip->i_res.rs_rbm.rgd;
		if (!rgd || !rgrp_contains_block(rgd, block))
			rgd = gfs2_blk2rgrpd(sdp, block, 1);
	}

	if (!rgd) {
		fs_err(sdp, "rlist_add: no rgrp for block %llu\n",
		       (unsigned long long)block);
		return;
	}

	for (x = 0; x < rlist->rl_rgrps; x++) {
		if (rlist->rl_rgd[x] == rgd) {
			swap(rlist->rl_rgd[x],
			     rlist->rl_rgd[rlist->rl_rgrps - 1]);
			return;
		}
	}

	if (rlist->rl_rgrps == rlist->rl_space) {
		new_space = rlist->rl_space + 10;

		tmp = kcalloc(new_space, sizeof(struct gfs2_rgrpd *),
			      GFP_NOFS | __GFP_NOFAIL);

		if (rlist->rl_rgd) {
			memcpy(tmp, rlist->rl_rgd,
			       rlist->rl_space * sizeof(struct gfs2_rgrpd *));
			kfree(rlist->rl_rgd);
		}

		rlist->rl_space = new_space;
		rlist->rl_rgd = tmp;
	}

	rlist->rl_rgd[rlist->rl_rgrps++] = rgd;
}

/**
 * gfs2_rlist_alloc - all RGs have been added to the rlist, now allocate
 *      and initialize an array of glock holders for them
 * @rlist: the list of resource groups
 *
 * FIXME: Don't use NOFAIL
 *
 */

void gfs2_rlist_alloc(struct gfs2_rgrp_list *rlist)
{
	unsigned int x;

	rlist->rl_ghs = kmalloc_array(rlist->rl_rgrps,
				      sizeof(struct gfs2_holder),
				      GFP_NOFS | __GFP_NOFAIL);
	for (x = 0; x < rlist->rl_rgrps; x++)
		gfs2_holder_init(rlist->rl_rgd[x]->rd_gl,
				LM_ST_EXCLUSIVE, 0,
				&rlist->rl_ghs[x]);
}

/**
 * gfs2_rlist_free - free a resource group list
 * @rlist: the list of resource groups
 *
 */

void gfs2_rlist_free(struct gfs2_rgrp_list *rlist)
{
	unsigned int x;

	kfree(rlist->rl_rgd);

	if (rlist->rl_ghs) {
		for (x = 0; x < rlist->rl_rgrps; x++)
			gfs2_holder_uninit(&rlist->rl_ghs[x]);
		kfree(rlist->rl_ghs);
		rlist->rl_ghs = NULL;
	}
}