summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_mount.c
blob: d3d38836f87fad07b3c815dd33ae234ddf785b03 (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
/*
 * Copyright (c) 2000-2005 Silicon Graphics, Inc.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_dir2.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_bmap.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_fsops.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_sysfs.h"


#ifdef HAVE_PERCPU_SB
STATIC void	xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
						int);
STATIC void	xfs_icsb_balance_counter_locked(xfs_mount_t *, xfs_sb_field_t,
						int);
STATIC void	xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
#else

#define xfs_icsb_balance_counter(mp, a, b)		do { } while (0)
#define xfs_icsb_balance_counter_locked(mp, a, b)	do { } while (0)
#endif

static DEFINE_MUTEX(xfs_uuid_table_mutex);
static int xfs_uuid_table_size;
static uuid_t *xfs_uuid_table;

/*
 * See if the UUID is unique among mounted XFS filesystems.
 * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
 */
STATIC int
xfs_uuid_mount(
	struct xfs_mount	*mp)
{
	uuid_t			*uuid = &mp->m_sb.sb_uuid;
	int			hole, i;

	if (mp->m_flags & XFS_MOUNT_NOUUID)
		return 0;

	if (uuid_is_nil(uuid)) {
		xfs_warn(mp, "Filesystem has nil UUID - can't mount");
		return -EINVAL;
	}

	mutex_lock(&xfs_uuid_table_mutex);
	for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) {
		if (uuid_is_nil(&xfs_uuid_table[i])) {
			hole = i;
			continue;
		}
		if (uuid_equal(uuid, &xfs_uuid_table[i]))
			goto out_duplicate;
	}

	if (hole < 0) {
		xfs_uuid_table = kmem_realloc(xfs_uuid_table,
			(xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table),
			xfs_uuid_table_size  * sizeof(*xfs_uuid_table),
			KM_SLEEP);
		hole = xfs_uuid_table_size++;
	}
	xfs_uuid_table[hole] = *uuid;
	mutex_unlock(&xfs_uuid_table_mutex);

	return 0;

 out_duplicate:
	mutex_unlock(&xfs_uuid_table_mutex);
	xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount", uuid);
	return -EINVAL;
}

STATIC void
xfs_uuid_unmount(
	struct xfs_mount	*mp)
{
	uuid_t			*uuid = &mp->m_sb.sb_uuid;
	int			i;

	if (mp->m_flags & XFS_MOUNT_NOUUID)
		return;

	mutex_lock(&xfs_uuid_table_mutex);
	for (i = 0; i < xfs_uuid_table_size; i++) {
		if (uuid_is_nil(&xfs_uuid_table[i]))
			continue;
		if (!uuid_equal(uuid, &xfs_uuid_table[i]))
			continue;
		memset(&xfs_uuid_table[i], 0, sizeof(uuid_t));
		break;
	}
	ASSERT(i < xfs_uuid_table_size);
	mutex_unlock(&xfs_uuid_table_mutex);
}


STATIC void
__xfs_free_perag(
	struct rcu_head	*head)
{
	struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);

	ASSERT(atomic_read(&pag->pag_ref) == 0);
	kmem_free(pag);
}

/*
 * Free up the per-ag resources associated with the mount structure.
 */
STATIC void
xfs_free_perag(
	xfs_mount_t	*mp)
{
	xfs_agnumber_t	agno;
	struct xfs_perag *pag;

	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
		spin_lock(&mp->m_perag_lock);
		pag = radix_tree_delete(&mp->m_perag_tree, agno);
		spin_unlock(&mp->m_perag_lock);
		ASSERT(pag);
		ASSERT(atomic_read(&pag->pag_ref) == 0);
		call_rcu(&pag->rcu_head, __xfs_free_perag);
	}
}

/*
 * Check size of device based on the (data/realtime) block count.
 * Note: this check is used by the growfs code as well as mount.
 */
int
xfs_sb_validate_fsb_count(
	xfs_sb_t	*sbp,
	__uint64_t	nblocks)
{
	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
	ASSERT(sbp->sb_blocklog >= BBSHIFT);

	/* Limited by ULONG_MAX of page cache index */
	if (nblocks >> (PAGE_CACHE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
		return -EFBIG;
	return 0;
}

int
xfs_initialize_perag(
	xfs_mount_t	*mp,
	xfs_agnumber_t	agcount,
	xfs_agnumber_t	*maxagi)
{
	xfs_agnumber_t	index;
	xfs_agnumber_t	first_initialised = 0;
	xfs_perag_t	*pag;
	xfs_agino_t	agino;
	xfs_ino_t	ino;
	xfs_sb_t	*sbp = &mp->m_sb;
	int		error = -ENOMEM;

	/*
	 * Walk the current per-ag tree so we don't try to initialise AGs
	 * that already exist (growfs case). Allocate and insert all the
	 * AGs we don't find ready for initialisation.
	 */
	for (index = 0; index < agcount; index++) {
		pag = xfs_perag_get(mp, index);
		if (pag) {
			xfs_perag_put(pag);
			continue;
		}
		if (!first_initialised)
			first_initialised = index;

		pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
		if (!pag)
			goto out_unwind;
		pag->pag_agno = index;
		pag->pag_mount = mp;
		spin_lock_init(&pag->pag_ici_lock);
		mutex_init(&pag->pag_ici_reclaim_lock);
		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
		spin_lock_init(&pag->pag_buf_lock);
		pag->pag_buf_tree = RB_ROOT;

		if (radix_tree_preload(GFP_NOFS))
			goto out_unwind;

		spin_lock(&mp->m_perag_lock);
		if (radix_tree_insert(&mp->m_perag_tree, index, pag)) {
			BUG();
			spin_unlock(&mp->m_perag_lock);
			radix_tree_preload_end();
			error = -EEXIST;
			goto out_unwind;
		}
		spin_unlock(&mp->m_perag_lock);
		radix_tree_preload_end();
	}

	/*
	 * If we mount with the inode64 option, or no inode overflows
	 * the legacy 32-bit address space clear the inode32 option.
	 */
	agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
	ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);

	if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
		mp->m_flags |= XFS_MOUNT_32BITINODES;
	else
		mp->m_flags &= ~XFS_MOUNT_32BITINODES;

	if (mp->m_flags & XFS_MOUNT_32BITINODES)
		index = xfs_set_inode32(mp, agcount);
	else
		index = xfs_set_inode64(mp, agcount);

	if (maxagi)
		*maxagi = index;
	return 0;

out_unwind:
	kmem_free(pag);
	for (; index > first_initialised; index--) {
		pag = radix_tree_delete(&mp->m_perag_tree, index);
		kmem_free(pag);
	}
	return error;
}

/*
 * xfs_readsb
 *
 * Does the initial read of the superblock.
 */
int
xfs_readsb(
	struct xfs_mount *mp,
	int		flags)
{
	unsigned int	sector_size;
	struct xfs_buf	*bp;
	struct xfs_sb	*sbp = &mp->m_sb;
	int		error;
	int		loud = !(flags & XFS_MFSI_QUIET);
	const struct xfs_buf_ops *buf_ops;

	ASSERT(mp->m_sb_bp == NULL);
	ASSERT(mp->m_ddev_targp != NULL);

	/*
	 * For the initial read, we must guess at the sector
	 * size based on the block device.  It's enough to
	 * get the sb_sectsize out of the superblock and
	 * then reread with the proper length.
	 * We don't verify it yet, because it may not be complete.
	 */
	sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
	buf_ops = NULL;

	/*
	 * Allocate a (locked) buffer to hold the superblock.
	 * This will be kept around at all times to optimize
	 * access to the superblock.
	 */
reread:
	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
				   BTOBB(sector_size), 0, &bp, buf_ops);
	if (error) {
		if (loud)
			xfs_warn(mp, "SB validate failed with error %d.", error);
		/* bad CRC means corrupted metadata */
		if (error == -EFSBADCRC)
			error = -EFSCORRUPTED;
		return error;
	}

	/*
	 * Initialize the mount structure from the superblock.
	 */
	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));

	/*
	 * If we haven't validated the superblock, do so now before we try
	 * to check the sector size and reread the superblock appropriately.
	 */
	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
		if (loud)
			xfs_warn(mp, "Invalid superblock magic number");
		error = -EINVAL;
		goto release_buf;
	}

	/*
	 * We must be able to do sector-sized and sector-aligned IO.
	 */
	if (sector_size > sbp->sb_sectsize) {
		if (loud)
			xfs_warn(mp, "device supports %u byte sectors (not %u)",
				sector_size, sbp->sb_sectsize);
		error = -ENOSYS;
		goto release_buf;
	}

	if (buf_ops == NULL) {
		/*
		 * Re-read the superblock so the buffer is correctly sized,
		 * and properly verified.
		 */
		xfs_buf_relse(bp);
		sector_size = sbp->sb_sectsize;
		buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
		goto reread;
	}

	/* Initialize per-cpu counters */
	xfs_icsb_reinit_counters(mp);

	/* no need to be quiet anymore, so reset the buf ops */
	bp->b_ops = &xfs_sb_buf_ops;

	mp->m_sb_bp = bp;
	xfs_buf_unlock(bp);
	return 0;

release_buf:
	xfs_buf_relse(bp);
	return error;
}

/*
 * Update alignment values based on mount options and sb values
 */
STATIC int
xfs_update_alignment(xfs_mount_t *mp)
{
	xfs_sb_t	*sbp = &(mp->m_sb);

	if (mp->m_dalign) {
		/*
		 * If stripe unit and stripe width are not multiples
		 * of the fs blocksize turn off alignment.
		 */
		if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
		    (BBTOB(mp->m_swidth) & mp->m_blockmask)) {
			xfs_warn(mp,
		"alignment check failed: sunit/swidth vs. blocksize(%d)",
				sbp->sb_blocksize);
			return -EINVAL;
		} else {
			/*
			 * Convert the stripe unit and width to FSBs.
			 */
			mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
			if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) {
				xfs_warn(mp,
			"alignment check failed: sunit/swidth vs. agsize(%d)",
					 sbp->sb_agblocks);
				return -EINVAL;
			} else if (mp->m_dalign) {
				mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
			} else {
				xfs_warn(mp,
			"alignment check failed: sunit(%d) less than bsize(%d)",
					 mp->m_dalign, sbp->sb_blocksize);
				return -EINVAL;
			}
		}

		/*
		 * Update superblock with new values
		 * and log changes
		 */
		if (xfs_sb_version_hasdalign(sbp)) {
			if (sbp->sb_unit != mp->m_dalign) {
				sbp->sb_unit = mp->m_dalign;
				mp->m_update_flags |= XFS_SB_UNIT;
			}
			if (sbp->sb_width != mp->m_swidth) {
				sbp->sb_width = mp->m_swidth;
				mp->m_update_flags |= XFS_SB_WIDTH;
			}
		} else {
			xfs_warn(mp,
	"cannot change alignment: superblock does not support data alignment");
			return -EINVAL;
		}
	} else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN &&
		    xfs_sb_version_hasdalign(&mp->m_sb)) {
			mp->m_dalign = sbp->sb_unit;
			mp->m_swidth = sbp->sb_width;
	}

	return 0;
}

/*
 * Set the maximum inode count for this filesystem
 */
STATIC void
xfs_set_maxicount(xfs_mount_t *mp)
{
	xfs_sb_t	*sbp = &(mp->m_sb);
	__uint64_t	icount;

	if (sbp->sb_imax_pct) {
		/*
		 * Make sure the maximum inode count is a multiple
		 * of the units we allocate inodes in.
		 */
		icount = sbp->sb_dblocks * sbp->sb_imax_pct;
		do_div(icount, 100);
		do_div(icount, mp->m_ialloc_blks);
		mp->m_maxicount = (icount * mp->m_ialloc_blks)  <<
				   sbp->sb_inopblog;
	} else {
		mp->m_maxicount = 0;
	}
}

/*
 * Set the default minimum read and write sizes unless
 * already specified in a mount option.
 * We use smaller I/O sizes when the file system
 * is being used for NFS service (wsync mount option).
 */
STATIC void
xfs_set_rw_sizes(xfs_mount_t *mp)
{
	xfs_sb_t	*sbp = &(mp->m_sb);
	int		readio_log, writeio_log;

	if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
		if (mp->m_flags & XFS_MOUNT_WSYNC) {
			readio_log = XFS_WSYNC_READIO_LOG;
			writeio_log = XFS_WSYNC_WRITEIO_LOG;
		} else {
			readio_log = XFS_READIO_LOG_LARGE;
			writeio_log = XFS_WRITEIO_LOG_LARGE;
		}
	} else {
		readio_log = mp->m_readio_log;
		writeio_log = mp->m_writeio_log;
	}

	if (sbp->sb_blocklog > readio_log) {
		mp->m_readio_log = sbp->sb_blocklog;
	} else {
		mp->m_readio_log = readio_log;
	}
	mp->m_readio_blocks = 1 << (mp->m_readio_log - sbp->sb_blocklog);
	if (sbp->sb_blocklog > writeio_log) {
		mp->m_writeio_log = sbp->sb_blocklog;
	} else {
		mp->m_writeio_log = writeio_log;
	}
	mp->m_writeio_blocks = 1 << (mp->m_writeio_log - sbp->sb_blocklog);
}

/*
 * precalculate the low space thresholds for dynamic speculative preallocation.
 */
void
xfs_set_low_space_thresholds(
	struct xfs_mount	*mp)
{
	int i;

	for (i = 0; i < XFS_LOWSP_MAX; i++) {
		__uint64_t space = mp->m_sb.sb_dblocks;

		do_div(space, 100);
		mp->m_low_space[i] = space * (i + 1);
	}
}


/*
 * Set whether we're using inode alignment.
 */
STATIC void
xfs_set_inoalignment(xfs_mount_t *mp)
{
	if (xfs_sb_version_hasalign(&mp->m_sb) &&
	    mp->m_sb.sb_inoalignmt >=
	    XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
		mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
	else
		mp->m_inoalign_mask = 0;
	/*
	 * If we are using stripe alignment, check whether
	 * the stripe unit is a multiple of the inode alignment
	 */
	if (mp->m_dalign && mp->m_inoalign_mask &&
	    !(mp->m_dalign & mp->m_inoalign_mask))
		mp->m_sinoalign = mp->m_dalign;
	else
		mp->m_sinoalign = 0;
}

/*
 * Check that the data (and log if separate) is an ok size.
 */
STATIC int
xfs_check_sizes(
	struct xfs_mount *mp)
{
	struct xfs_buf	*bp;
	xfs_daddr_t	d;
	int		error;

	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
		xfs_warn(mp, "filesystem size mismatch detected");
		return -EFBIG;
	}
	error = xfs_buf_read_uncached(mp->m_ddev_targp,
					d - XFS_FSS_TO_BB(mp, 1),
					XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
	if (error) {
		xfs_warn(mp, "last sector read failed");
		return error;
	}
	xfs_buf_relse(bp);

	if (mp->m_logdev_targp == mp->m_ddev_targp)
		return 0;

	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
		xfs_warn(mp, "log size mismatch detected");
		return -EFBIG;
	}
	error = xfs_buf_read_uncached(mp->m_logdev_targp,
					d - XFS_FSB_TO_BB(mp, 1),
					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
	if (error) {
		xfs_warn(mp, "log device read failed");
		return error;
	}
	xfs_buf_relse(bp);
	return 0;
}

/*
 * Clear the quotaflags in memory and in the superblock.
 */
int
xfs_mount_reset_sbqflags(
	struct xfs_mount	*mp)
{
	int			error;
	struct xfs_trans	*tp;

	mp->m_qflags = 0;

	/*
	 * It is OK to look at sb_qflags here in mount path,
	 * without m_sb_lock.
	 */
	if (mp->m_sb.sb_qflags == 0)
		return 0;
	spin_lock(&mp->m_sb_lock);
	mp->m_sb.sb_qflags = 0;
	spin_unlock(&mp->m_sb_lock);

	/*
	 * If the fs is readonly, let the incore superblock run
	 * with quotas off but don't flush the update out to disk
	 */
	if (mp->m_flags & XFS_MOUNT_RDONLY)
		return 0;

	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SBCHANGE);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_qm_sbchange, 0, 0);
	if (error) {
		xfs_trans_cancel(tp, 0);
		xfs_alert(mp, "%s: Superblock update failed!", __func__);
		return error;
	}

	xfs_mod_sb(tp, XFS_SB_QFLAGS);
	return xfs_trans_commit(tp, 0);
}

__uint64_t
xfs_default_resblks(xfs_mount_t *mp)
{
	__uint64_t resblks;

	/*
	 * We default to 5% or 8192 fsbs of space reserved, whichever is
	 * smaller.  This is intended to cover concurrent allocation
	 * transactions when we initially hit enospc. These each require a 4
	 * block reservation. Hence by default we cover roughly 2000 concurrent
	 * allocation reservations.
	 */
	resblks = mp->m_sb.sb_dblocks;
	do_div(resblks, 20);
	resblks = min_t(__uint64_t, resblks, 8192);
	return resblks;
}

/*
 * This function does the following on an initial mount of a file system:
 *	- reads the superblock from disk and init the mount struct
 *	- if we're a 32-bit kernel, do a size check on the superblock
 *		so we don't mount terabyte filesystems
 *	- init mount struct realtime fields
 *	- allocate inode hash table for fs
 *	- init directory manager
 *	- perform recovery and init the log manager
 */
int
xfs_mountfs(
	xfs_mount_t	*mp)
{
	xfs_sb_t	*sbp = &(mp->m_sb);
	xfs_inode_t	*rip;
	__uint64_t	resblks;
	uint		quotamount = 0;
	uint		quotaflags = 0;
	int		error = 0;

	xfs_sb_mount_common(mp, sbp);

	/*
	 * Check for a mismatched features2 values.  Older kernels
	 * read & wrote into the wrong sb offset for sb_features2
	 * on some platforms due to xfs_sb_t not being 64bit size aligned
	 * when sb_features2 was added, which made older superblock
	 * reading/writing routines swap it as a 64-bit value.
	 *
	 * For backwards compatibility, we make both slots equal.
	 *
	 * If we detect a mismatched field, we OR the set bits into the
	 * existing features2 field in case it has already been modified; we
	 * don't want to lose any features.  We then update the bad location
	 * with the ORed value so that older kernels will see any features2
	 * flags, and mark the two fields as needing updates once the
	 * transaction subsystem is online.
	 */
	if (xfs_sb_has_mismatched_features2(sbp)) {
		xfs_warn(mp, "correcting sb_features alignment problem");
		sbp->sb_features2 |= sbp->sb_bad_features2;
		sbp->sb_bad_features2 = sbp->sb_features2;
		mp->m_update_flags |= XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2;

		/*
		 * Re-check for ATTR2 in case it was found in bad_features2
		 * slot.
		 */
		if (xfs_sb_version_hasattr2(&mp->m_sb) &&
		   !(mp->m_flags & XFS_MOUNT_NOATTR2))
			mp->m_flags |= XFS_MOUNT_ATTR2;
	}

	if (xfs_sb_version_hasattr2(&mp->m_sb) &&
	   (mp->m_flags & XFS_MOUNT_NOATTR2)) {
		xfs_sb_version_removeattr2(&mp->m_sb);
		mp->m_update_flags |= XFS_SB_FEATURES2;

		/* update sb_versionnum for the clearing of the morebits */
		if (!sbp->sb_features2)
			mp->m_update_flags |= XFS_SB_VERSIONNUM;
	}

	/* always use v2 inodes by default now */
	if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {
		mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
		mp->m_update_flags |= XFS_SB_VERSIONNUM;
	}

	/*
	 * Check if sb_agblocks is aligned at stripe boundary
	 * If sb_agblocks is NOT aligned turn off m_dalign since
	 * allocator alignment is within an ag, therefore ag has
	 * to be aligned at stripe boundary.
	 */
	error = xfs_update_alignment(mp);
	if (error)
		goto out;

	xfs_alloc_compute_maxlevels(mp);
	xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
	xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
	xfs_ialloc_compute_maxlevels(mp);

	xfs_set_maxicount(mp);

	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype, NULL, mp->m_fsname);
	if (error)
		goto out;

	error = xfs_uuid_mount(mp);
	if (error)
		goto out_remove_sysfs;

	/*
	 * Set the minimum read and write sizes
	 */
	xfs_set_rw_sizes(mp);

	/* set the low space thresholds for dynamic preallocation */
	xfs_set_low_space_thresholds(mp);

	/*
	 * Set the inode cluster size.
	 * This may still be overridden by the file system
	 * block size if it is larger than the chosen cluster size.
	 *
	 * For v5 filesystems, scale the cluster size with the inode size to
	 * keep a constant ratio of inode per cluster buffer, but only if mkfs
	 * has set the inode alignment value appropriately for larger cluster
	 * sizes.
	 */
	mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;
	if (xfs_sb_version_hascrc(&mp->m_sb)) {
		int	new_size = mp->m_inode_cluster_size;

		new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE;
		if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size))
			mp->m_inode_cluster_size = new_size;
	}

	/*
	 * Set inode alignment fields
	 */
	xfs_set_inoalignment(mp);

	/*
	 * Check that the data (and log if separate) is an ok size.
	 */
	error = xfs_check_sizes(mp);
	if (error)
		goto out_remove_uuid;

	/*
	 * Initialize realtime fields in the mount structure
	 */
	error = xfs_rtmount_init(mp);
	if (error) {
		xfs_warn(mp, "RT mount failed");
		goto out_remove_uuid;
	}

	/*
	 *  Copies the low order bits of the timestamp and the randomly
	 *  set "sequence" number out of a UUID.
	 */
	uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid);

	mp->m_dmevmask = 0;	/* not persistent; set after each mount */

	error = xfs_da_mount(mp);
	if (error) {
		xfs_warn(mp, "Failed dir/attr init: %d", error);
		goto out_remove_uuid;
	}

	/*
	 * Initialize the precomputed transaction reservations values.
	 */
	xfs_trans_init(mp);

	/*
	 * Allocate and initialize the per-ag data.
	 */
	spin_lock_init(&mp->m_perag_lock);
	INIT_RADIX_TREE(&mp->m_perag_tree, GFP_ATOMIC);
	error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
	if (error) {
		xfs_warn(mp, "Failed per-ag init: %d", error);
		goto out_free_dir;
	}

	if (!sbp->sb_logblocks) {
		xfs_warn(mp, "no log defined");
		XFS_ERROR_REPORT("xfs_mountfs", XFS_ERRLEVEL_LOW, mp);
		error = -EFSCORRUPTED;
		goto out_free_perag;
	}

	/*
	 * log's mount-time initialization. Perform 1st part recovery if needed
	 */
	error = xfs_log_mount(mp, mp->m_logdev_targp,
			      XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
			      XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
	if (error) {
		xfs_warn(mp, "log mount failed");
		goto out_fail_wait;
	}

	/*
	 * Now the log is mounted, we know if it was an unclean shutdown or
	 * not. If it was, with the first phase of recovery has completed, we
	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
	 * but they are recovered transactionally in the second recovery phase
	 * later.
	 *
	 * Hence we can safely re-initialise incore superblock counters from
	 * the per-ag data. These may not be correct if the filesystem was not
	 * cleanly unmounted, so we need to wait for recovery to finish before
	 * doing this.
	 *
	 * If the filesystem was cleanly unmounted, then we can trust the
	 * values in the superblock to be correct and we don't need to do
	 * anything here.
	 *
	 * If we are currently making the filesystem, the initialisation will
	 * fail as the perag data is in an undefined state.
	 */
	if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
	    !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
	     !mp->m_sb.sb_inprogress) {
		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
		if (error)
			goto out_log_dealloc;
	}

	/*
	 * Get and sanity-check the root inode.
	 * Save the pointer to it in the mount structure.
	 */
	error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip);
	if (error) {
		xfs_warn(mp, "failed to read root inode");
		goto out_log_dealloc;
	}

	ASSERT(rip != NULL);

	if (unlikely(!S_ISDIR(rip->i_d.di_mode))) {
		xfs_warn(mp, "corrupted root inode %llu: not a directory",
			(unsigned long long)rip->i_ino);
		xfs_iunlock(rip, XFS_ILOCK_EXCL);
		XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW,
				 mp);
		error = -EFSCORRUPTED;
		goto out_rele_rip;
	}
	mp->m_rootip = rip;	/* save it */

	xfs_iunlock(rip, XFS_ILOCK_EXCL);

	/*
	 * Initialize realtime inode pointers in the mount structure
	 */
	error = xfs_rtmount_inodes(mp);
	if (error) {
		/*
		 * Free up the root inode.
		 */
		xfs_warn(mp, "failed to read RT inodes");
		goto out_rele_rip;
	}

	/*
	 * If this is a read-only mount defer the superblock updates until
	 * the next remount into writeable mode.  Otherwise we would never
	 * perform the update e.g. for the root filesystem.
	 */
	if (mp->m_update_flags && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
		error = xfs_mount_log_sb(mp, mp->m_update_flags);
		if (error) {
			xfs_warn(mp, "failed to write sb changes");
			goto out_rtunmount;
		}
	}

	/*
	 * Initialise the XFS quota management subsystem for this mount
	 */
	if (XFS_IS_QUOTA_RUNNING(mp)) {
		error = xfs_qm_newmount(mp, &quotamount, &quotaflags);
		if (error)
			goto out_rtunmount;
	} else {
		ASSERT(!XFS_IS_QUOTA_ON(mp));

		/*
		 * If a file system had quotas running earlier, but decided to
		 * mount without -o uquota/pquota/gquota options, revoke the
		 * quotachecked license.
		 */
		if (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_ACCT) {
			xfs_notice(mp, "resetting quota flags");
			error = xfs_mount_reset_sbqflags(mp);
			if (error)
				goto out_rtunmount;
		}
	}

	/*
	 * Finish recovering the file system.  This part needed to be
	 * delayed until after the root and real-time bitmap inodes
	 * were consistently read in.
	 */
	error = xfs_log_mount_finish(mp);
	if (error) {
		xfs_warn(mp, "log mount finish failed");
		goto out_rtunmount;
	}

	/*
	 * Complete the quota initialisation, post-log-replay component.
	 */
	if (quotamount) {
		ASSERT(mp->m_qflags == 0);
		mp->m_qflags = quotaflags;

		xfs_qm_mount_quotas(mp);
	}

	/*
	 * Now we are mounted, reserve a small amount of unused space for
	 * privileged transactions. This is needed so that transaction
	 * space required for critical operations can dip into this pool
	 * when at ENOSPC. This is needed for operations like create with
	 * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
	 * are not allowed to use this reserved space.
	 *
	 * This may drive us straight to ENOSPC on mount, but that implies
	 * we were already there on the last unmount. Warn if this occurs.
	 */
	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
		resblks = xfs_default_resblks(mp);
		error = xfs_reserve_blocks(mp, &resblks, NULL);
		if (error)
			xfs_warn(mp,
	"Unable to allocate reserve blocks. Continuing without reserve pool.");
	}

	return 0;

 out_rtunmount:
	xfs_rtunmount_inodes(mp);
 out_rele_rip:
	IRELE(rip);
 out_log_dealloc:
	xfs_log_unmount(mp);
 out_fail_wait:
	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
		xfs_wait_buftarg(mp->m_logdev_targp);
	xfs_wait_buftarg(mp->m_ddev_targp);
 out_free_perag:
	xfs_free_perag(mp);
 out_free_dir:
	xfs_da_unmount(mp);
 out_remove_uuid:
	xfs_uuid_unmount(mp);
 out_remove_sysfs:
	xfs_sysfs_del(&mp->m_kobj);
 out:
	return error;
}

/*
 * This flushes out the inodes,dquots and the superblock, unmounts the
 * log and makes sure that incore structures are freed.
 */
void
xfs_unmountfs(
	struct xfs_mount	*mp)
{
	__uint64_t		resblks;
	int			error;

	cancel_delayed_work_sync(&mp->m_eofblocks_work);

	xfs_qm_unmount_quotas(mp);
	xfs_rtunmount_inodes(mp);
	IRELE(mp->m_rootip);

	/*
	 * We can potentially deadlock here if we have an inode cluster
	 * that has been freed has its buffer still pinned in memory because
	 * the transaction is still sitting in a iclog. The stale inodes
	 * on that buffer will have their flush locks held until the
	 * transaction hits the disk and the callbacks run. the inode
	 * flush takes the flush lock unconditionally and with nothing to
	 * push out the iclog we will never get that unlocked. hence we
	 * need to force the log first.
	 */
	xfs_log_force(mp, XFS_LOG_SYNC);

	/*
	 * Flush all pending changes from the AIL.
	 */
	xfs_ail_push_all_sync(mp->m_ail);

	/*
	 * And reclaim all inodes.  At this point there should be no dirty
	 * inodes and none should be pinned or locked, but use synchronous
	 * reclaim just to be sure. We can stop background inode reclaim
	 * here as well if it is still running.
	 */
	cancel_delayed_work_sync(&mp->m_reclaim_work);
	xfs_reclaim_inodes(mp, SYNC_WAIT);

	xfs_qm_unmount(mp);

	/*
	 * Unreserve any blocks we have so that when we unmount we don't account
	 * the reserved free space as used. This is really only necessary for
	 * lazy superblock counting because it trusts the incore superblock
	 * counters to be absolutely correct on clean unmount.
	 *
	 * We don't bother correcting this elsewhere for lazy superblock
	 * counting because on mount of an unclean filesystem we reconstruct the
	 * correct counter value and this is irrelevant.
	 *
	 * For non-lazy counter filesystems, this doesn't matter at all because
	 * we only every apply deltas to the superblock and hence the incore
	 * value does not matter....
	 */
	resblks = 0;
	error = xfs_reserve_blocks(mp, &resblks, NULL);
	if (error)
		xfs_warn(mp, "Unable to free reserved block pool. "
				"Freespace may not be correct on next mount.");

	error = xfs_log_sbcount(mp);
	if (error)
		xfs_warn(mp, "Unable to update superblock counters. "
				"Freespace may not be correct on next mount.");

	xfs_log_unmount(mp);
	xfs_da_unmount(mp);
	xfs_uuid_unmount(mp);

#if defined(DEBUG)
	xfs_errortag_clearall(mp, 0);
#endif
	xfs_free_perag(mp);

	xfs_sysfs_del(&mp->m_kobj);
}

/*
 * Determine whether modifications can proceed. The caller specifies the minimum
 * freeze level for which modifications should not be allowed. This allows
 * certain operations to proceed while the freeze sequence is in progress, if
 * necessary.
 */
bool
xfs_fs_writable(
	struct xfs_mount	*mp,
	int			level)
{
	ASSERT(level > SB_UNFROZEN);
	if ((mp->m_super->s_writers.frozen >= level) ||
	    XFS_FORCED_SHUTDOWN(mp) || (mp->m_flags & XFS_MOUNT_RDONLY))
		return false;

	return true;
}

/*
 * xfs_log_sbcount
 *
 * Sync the superblock counters to disk.
 *
 * Note this code can be called during the process of freezing, so we use the
 * transaction allocator that does not block when the transaction subsystem is
 * in its frozen state.
 */
int
xfs_log_sbcount(xfs_mount_t *mp)
{
	xfs_trans_t	*tp;
	int		error;

	/* allow this to proceed during the freeze sequence... */
	if (!xfs_fs_writable(mp, SB_FREEZE_COMPLETE))
		return 0;

	xfs_icsb_sync_counters(mp, 0);

	/*
	 * we don't need to do this if we are updating the superblock
	 * counters on every modification.
	 */
	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
		return 0;

	tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_COUNT, KM_SLEEP);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
	if (error) {
		xfs_trans_cancel(tp, 0);
		return error;
	}

	xfs_mod_sb(tp, XFS_SB_IFREE | XFS_SB_ICOUNT | XFS_SB_FDBLOCKS);
	xfs_trans_set_sync(tp);
	error = xfs_trans_commit(tp, 0);
	return error;
}

/*
 * xfs_mod_incore_sb_unlocked() is a utility routine commonly used to apply
 * a delta to a specified field in the in-core superblock.  Simply
 * switch on the field indicated and apply the delta to that field.
 * Fields are not allowed to dip below zero, so if the delta would
 * do this do not apply it and return EINVAL.
 *
 * The m_sb_lock must be held when this routine is called.
 */
STATIC int
xfs_mod_incore_sb_unlocked(
	xfs_mount_t	*mp,
	xfs_sb_field_t	field,
	int64_t		delta,
	int		rsvd)
{
	int		scounter;	/* short counter for 32 bit fields */
	long long	lcounter;	/* long counter for 64 bit fields */
	long long	res_used, rem;

	/*
	 * With the in-core superblock spin lock held, switch
	 * on the indicated field.  Apply the delta to the
	 * proper field.  If the fields value would dip below
	 * 0, then do not apply the delta and return EINVAL.
	 */
	switch (field) {
	case XFS_SBS_ICOUNT:
		lcounter = (long long)mp->m_sb.sb_icount;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_icount = lcounter;
		return 0;
	case XFS_SBS_IFREE:
		lcounter = (long long)mp->m_sb.sb_ifree;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_ifree = lcounter;
		return 0;
	case XFS_SBS_FDBLOCKS:
		lcounter = (long long)
			mp->m_sb.sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
		res_used = (long long)(mp->m_resblks - mp->m_resblks_avail);

		if (delta > 0) {		/* Putting blocks back */
			if (res_used > delta) {
				mp->m_resblks_avail += delta;
			} else {
				rem = delta - res_used;
				mp->m_resblks_avail = mp->m_resblks;
				lcounter += rem;
			}
		} else {				/* Taking blocks away */
			lcounter += delta;
			if (lcounter >= 0) {
				mp->m_sb.sb_fdblocks = lcounter +
							XFS_ALLOC_SET_ASIDE(mp);
				return 0;
			}

			/*
			 * We are out of blocks, use any available reserved
			 * blocks if were allowed to.
			 */
			if (!rsvd)
				return -ENOSPC;

			lcounter = (long long)mp->m_resblks_avail + delta;
			if (lcounter >= 0) {
				mp->m_resblks_avail = lcounter;
				return 0;
			}
			printk_once(KERN_WARNING
				"Filesystem \"%s\": reserve blocks depleted! "
				"Consider increasing reserve pool size.",
				mp->m_fsname);
			return -ENOSPC;
		}

		mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
		return 0;
	case XFS_SBS_FREXTENTS:
		lcounter = (long long)mp->m_sb.sb_frextents;
		lcounter += delta;
		if (lcounter < 0) {
			return -ENOSPC;
		}
		mp->m_sb.sb_frextents = lcounter;
		return 0;
	case XFS_SBS_DBLOCKS:
		lcounter = (long long)mp->m_sb.sb_dblocks;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_dblocks = lcounter;
		return 0;
	case XFS_SBS_AGCOUNT:
		scounter = mp->m_sb.sb_agcount;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_agcount = scounter;
		return 0;
	case XFS_SBS_IMAX_PCT:
		scounter = mp->m_sb.sb_imax_pct;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_imax_pct = scounter;
		return 0;
	case XFS_SBS_REXTSIZE:
		scounter = mp->m_sb.sb_rextsize;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_rextsize = scounter;
		return 0;
	case XFS_SBS_RBMBLOCKS:
		scounter = mp->m_sb.sb_rbmblocks;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_rbmblocks = scounter;
		return 0;
	case XFS_SBS_RBLOCKS:
		lcounter = (long long)mp->m_sb.sb_rblocks;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_rblocks = lcounter;
		return 0;
	case XFS_SBS_REXTENTS:
		lcounter = (long long)mp->m_sb.sb_rextents;
		lcounter += delta;
		if (lcounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_rextents = lcounter;
		return 0;
	case XFS_SBS_REXTSLOG:
		scounter = mp->m_sb.sb_rextslog;
		scounter += delta;
		if (scounter < 0) {
			ASSERT(0);
			return -EINVAL;
		}
		mp->m_sb.sb_rextslog = scounter;
		return 0;
	default:
		ASSERT(0);
		return -EINVAL;
	}
}

/*
 * xfs_mod_incore_sb() is used to change a field in the in-core
 * superblock structure by the specified delta.  This modification
 * is protected by the m_sb_lock.  Just use the xfs_mod_incore_sb_unlocked()
 * routine to do the work.
 */
int
xfs_mod_incore_sb(
	struct xfs_mount	*mp,
	xfs_sb_field_t		field,
	int64_t			delta,
	int			rsvd)
{
	int			status;

#ifdef HAVE_PERCPU_SB
	ASSERT(field < XFS_SBS_ICOUNT || field > XFS_SBS_FDBLOCKS);
#endif
	spin_lock(&mp->m_sb_lock);
	status = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
	spin_unlock(&mp->m_sb_lock);

	return status;
}

/*
 * Change more than one field in the in-core superblock structure at a time.
 *
 * The fields and changes to those fields are specified in the array of
 * xfs_mod_sb structures passed in.  Either all of the specified deltas
 * will be applied or none of them will.  If any modified field dips below 0,
 * then all modifications will be backed out and EINVAL will be returned.
 *
 * Note that this function may not be used for the superblock values that
 * are tracked with the in-memory per-cpu counters - a direct call to
 * xfs_icsb_modify_counters is required for these.
 */
int
xfs_mod_incore_sb_batch(
	struct xfs_mount	*mp,
	xfs_mod_sb_t		*msb,
	uint			nmsb,
	int			rsvd)
{
	xfs_mod_sb_t		*msbp;
	int			error = 0;

	/*
	 * Loop through the array of mod structures and apply each individually.
	 * If any fail, then back out all those which have already been applied.
	 * Do all of this within the scope of the m_sb_lock so that all of the
	 * changes will be atomic.
	 */
	spin_lock(&mp->m_sb_lock);
	for (msbp = msb; msbp < (msb + nmsb); msbp++) {
		ASSERT(msbp->msb_field < XFS_SBS_ICOUNT ||
		       msbp->msb_field > XFS_SBS_FDBLOCKS);

		error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field,
						   msbp->msb_delta, rsvd);
		if (error)
			goto unwind;
	}
	spin_unlock(&mp->m_sb_lock);
	return 0;

unwind:
	while (--msbp >= msb) {
		error = xfs_mod_incore_sb_unlocked(mp, msbp->msb_field,
						   -msbp->msb_delta, rsvd);
		ASSERT(error == 0);
	}
	spin_unlock(&mp->m_sb_lock);
	return error;
}

/*
 * xfs_getsb() is called to obtain the buffer for the superblock.
 * The buffer is returned locked and read in from disk.
 * The buffer should be released with a call to xfs_brelse().
 *
 * If the flags parameter is BUF_TRYLOCK, then we'll only return
 * the superblock buffer if it can be locked without sleeping.
 * If it can't then we'll return NULL.
 */
struct xfs_buf *
xfs_getsb(
	struct xfs_mount	*mp,
	int			flags)
{
	struct xfs_buf		*bp = mp->m_sb_bp;

	if (!xfs_buf_trylock(bp)) {
		if (flags & XBF_TRYLOCK)
			return NULL;
		xfs_buf_lock(bp);
	}

	xfs_buf_hold(bp);
	ASSERT(XFS_BUF_ISDONE(bp));
	return bp;
}

/*
 * Used to free the superblock along various error paths.
 */
void
xfs_freesb(
	struct xfs_mount	*mp)
{
	struct xfs_buf		*bp = mp->m_sb_bp;

	xfs_buf_lock(bp);
	mp->m_sb_bp = NULL;
	xfs_buf_relse(bp);
}

/*
 * Used to log changes to the superblock unit and width fields which could
 * be altered by the mount options, as well as any potential sb_features2
 * fixup. Only the first superblock is updated.
 */
int
xfs_mount_log_sb(
	xfs_mount_t	*mp,
	__int64_t	fields)
{
	xfs_trans_t	*tp;
	int		error;

	ASSERT(fields & (XFS_SB_UNIT | XFS_SB_WIDTH | XFS_SB_UUID |
			 XFS_SB_FEATURES2 | XFS_SB_BAD_FEATURES2 |
			 XFS_SB_VERSIONNUM));

	tp = xfs_trans_alloc(mp, XFS_TRANS_SB_UNIT);
	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
	if (error) {
		xfs_trans_cancel(tp, 0);
		return error;
	}
	xfs_mod_sb(tp, fields);
	error = xfs_trans_commit(tp, 0);
	return error;
}

/*
 * If the underlying (data/log/rt) device is readonly, there are some
 * operations that cannot proceed.
 */
int
xfs_dev_is_read_only(
	struct xfs_mount	*mp,
	char			*message)
{
	if (xfs_readonly_buftarg(mp->m_ddev_targp) ||
	    xfs_readonly_buftarg(mp->m_logdev_targp) ||
	    (mp->m_rtdev_targp && xfs_readonly_buftarg(mp->m_rtdev_targp))) {
		xfs_notice(mp, "%s required on read-only device.", message);
		xfs_notice(mp, "write access unavailable, cannot proceed.");
		return -EROFS;
	}
	return 0;
}

#ifdef HAVE_PERCPU_SB
/*
 * Per-cpu incore superblock counters
 *
 * Simple concept, difficult implementation
 *
 * Basically, replace the incore superblock counters with a distributed per cpu
 * counter for contended fields (e.g.  free block count).
 *
 * Difficulties arise in that the incore sb is used for ENOSPC checking, and
 * hence needs to be accurately read when we are running low on space. Hence
 * there is a method to enable and disable the per-cpu counters based on how
 * much "stuff" is available in them.
 *
 * Basically, a counter is enabled if there is enough free resource to justify
 * running a per-cpu fast-path. If the per-cpu counter runs out (i.e. a local
 * ENOSPC), then we disable the counters to synchronise all callers and
 * re-distribute the available resources.
 *
 * If, once we redistributed the available resources, we still get a failure,
 * we disable the per-cpu counter and go through the slow path.
 *
 * The slow path is the current xfs_mod_incore_sb() function.  This means that
 * when we disable a per-cpu counter, we need to drain its resources back to
 * the global superblock. We do this after disabling the counter to prevent
 * more threads from queueing up on the counter.
 *
 * Essentially, this means that we still need a lock in the fast path to enable
 * synchronisation between the global counters and the per-cpu counters. This
 * is not a problem because the lock will be local to a CPU almost all the time
 * and have little contention except when we get to ENOSPC conditions.
 *
 * Basically, this lock becomes a barrier that enables us to lock out the fast
 * path while we do things like enabling and disabling counters and
 * synchronising the counters.
 *
 * Locking rules:
 *
 * 	1. m_sb_lock before picking up per-cpu locks
 * 	2. per-cpu locks always picked up via for_each_online_cpu() order
 * 	3. accurate counter sync requires m_sb_lock + per cpu locks
 * 	4. modifying per-cpu counters requires holding per-cpu lock
 * 	5. modifying global counters requires holding m_sb_lock
 *	6. enabling or disabling a counter requires holding the m_sb_lock 
 *	   and _none_ of the per-cpu locks.
 *
 * Disabled counters are only ever re-enabled by a balance operation
 * that results in more free resources per CPU than a given threshold.
 * To ensure counters don't remain disabled, they are rebalanced when
 * the global resource goes above a higher threshold (i.e. some hysteresis
 * is present to prevent thrashing).
 */

#ifdef CONFIG_HOTPLUG_CPU
/*
 * hot-plug CPU notifier support.
 *
 * We need a notifier per filesystem as we need to be able to identify
 * the filesystem to balance the counters out. This is achieved by
 * having a notifier block embedded in the xfs_mount_t and doing pointer
 * magic to get the mount pointer from the notifier block address.
 */
STATIC int
xfs_icsb_cpu_notify(
	struct notifier_block *nfb,
	unsigned long action,
	void *hcpu)
{
	xfs_icsb_cnts_t *cntp;
	xfs_mount_t	*mp;

	mp = (xfs_mount_t *)container_of(nfb, xfs_mount_t, m_icsb_notifier);
	cntp = (xfs_icsb_cnts_t *)
			per_cpu_ptr(mp->m_sb_cnts, (unsigned long)hcpu);
	switch (action) {
	case CPU_UP_PREPARE:
	case CPU_UP_PREPARE_FROZEN:
		/* Easy Case - initialize the area and locks, and
		 * then rebalance when online does everything else for us. */
		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
		break;
	case CPU_ONLINE:
	case CPU_ONLINE_FROZEN:
		xfs_icsb_lock(mp);
		xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
		xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
		xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
		xfs_icsb_unlock(mp);
		break;
	case CPU_DEAD:
	case CPU_DEAD_FROZEN:
		/* Disable all the counters, then fold the dead cpu's
		 * count into the total on the global superblock and
		 * re-enable the counters. */
		xfs_icsb_lock(mp);
		spin_lock(&mp->m_sb_lock);
		xfs_icsb_disable_counter(mp, XFS_SBS_ICOUNT);
		xfs_icsb_disable_counter(mp, XFS_SBS_IFREE);
		xfs_icsb_disable_counter(mp, XFS_SBS_FDBLOCKS);

		mp->m_sb.sb_icount += cntp->icsb_icount;
		mp->m_sb.sb_ifree += cntp->icsb_ifree;
		mp->m_sb.sb_fdblocks += cntp->icsb_fdblocks;

		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));

		xfs_icsb_balance_counter_locked(mp, XFS_SBS_ICOUNT, 0);
		xfs_icsb_balance_counter_locked(mp, XFS_SBS_IFREE, 0);
		xfs_icsb_balance_counter_locked(mp, XFS_SBS_FDBLOCKS, 0);
		spin_unlock(&mp->m_sb_lock);
		xfs_icsb_unlock(mp);
		break;
	}

	return NOTIFY_OK;
}
#endif /* CONFIG_HOTPLUG_CPU */

int
xfs_icsb_init_counters(
	xfs_mount_t	*mp)
{
	xfs_icsb_cnts_t *cntp;
	int		i;

	mp->m_sb_cnts = alloc_percpu(xfs_icsb_cnts_t);
	if (mp->m_sb_cnts == NULL)
		return -ENOMEM;

	for_each_online_cpu(i) {
		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
		memset(cntp, 0, sizeof(xfs_icsb_cnts_t));
	}

	mutex_init(&mp->m_icsb_mutex);

	/*
	 * start with all counters disabled so that the
	 * initial balance kicks us off correctly
	 */
	mp->m_icsb_counters = -1;

#ifdef CONFIG_HOTPLUG_CPU
	mp->m_icsb_notifier.notifier_call = xfs_icsb_cpu_notify;
	mp->m_icsb_notifier.priority = 0;
	register_hotcpu_notifier(&mp->m_icsb_notifier);
#endif /* CONFIG_HOTPLUG_CPU */

	return 0;
}

void
xfs_icsb_reinit_counters(
	xfs_mount_t	*mp)
{
	xfs_icsb_lock(mp);
	/*
	 * start with all counters disabled so that the
	 * initial balance kicks us off correctly
	 */
	mp->m_icsb_counters = -1;
	xfs_icsb_balance_counter(mp, XFS_SBS_ICOUNT, 0);
	xfs_icsb_balance_counter(mp, XFS_SBS_IFREE, 0);
	xfs_icsb_balance_counter(mp, XFS_SBS_FDBLOCKS, 0);
	xfs_icsb_unlock(mp);
}

void
xfs_icsb_destroy_counters(
	xfs_mount_t	*mp)
{
	if (mp->m_sb_cnts) {
		unregister_hotcpu_notifier(&mp->m_icsb_notifier);
		free_percpu(mp->m_sb_cnts);
	}
	mutex_destroy(&mp->m_icsb_mutex);
}

STATIC void
xfs_icsb_lock_cntr(
	xfs_icsb_cnts_t	*icsbp)
{
	while (test_and_set_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags)) {
		ndelay(1000);
	}
}

STATIC void
xfs_icsb_unlock_cntr(
	xfs_icsb_cnts_t	*icsbp)
{
	clear_bit(XFS_ICSB_FLAG_LOCK, &icsbp->icsb_flags);
}


STATIC void
xfs_icsb_lock_all_counters(
	xfs_mount_t	*mp)
{
	xfs_icsb_cnts_t *cntp;
	int		i;

	for_each_online_cpu(i) {
		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
		xfs_icsb_lock_cntr(cntp);
	}
}

STATIC void
xfs_icsb_unlock_all_counters(
	xfs_mount_t	*mp)
{
	xfs_icsb_cnts_t *cntp;
	int		i;

	for_each_online_cpu(i) {
		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
		xfs_icsb_unlock_cntr(cntp);
	}
}

STATIC void
xfs_icsb_count(
	xfs_mount_t	*mp,
	xfs_icsb_cnts_t	*cnt,
	int		flags)
{
	xfs_icsb_cnts_t *cntp;
	int		i;

	memset(cnt, 0, sizeof(xfs_icsb_cnts_t));

	if (!(flags & XFS_ICSB_LAZY_COUNT))
		xfs_icsb_lock_all_counters(mp);

	for_each_online_cpu(i) {
		cntp = (xfs_icsb_cnts_t *)per_cpu_ptr(mp->m_sb_cnts, i);
		cnt->icsb_icount += cntp->icsb_icount;
		cnt->icsb_ifree += cntp->icsb_ifree;
		cnt->icsb_fdblocks += cntp->icsb_fdblocks;
	}

	if (!(flags & XFS_ICSB_LAZY_COUNT))
		xfs_icsb_unlock_all_counters(mp);
}

STATIC int
xfs_icsb_counter_disabled(
	xfs_mount_t	*mp,
	xfs_sb_field_t	field)
{
	ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));
	return test_bit(field, &mp->m_icsb_counters);
}

STATIC void
xfs_icsb_disable_counter(
	xfs_mount_t	*mp,
	xfs_sb_field_t	field)
{
	xfs_icsb_cnts_t	cnt;

	ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));

	/*
	 * If we are already disabled, then there is nothing to do
	 * here. We check before locking all the counters to avoid
	 * the expensive lock operation when being called in the
	 * slow path and the counter is already disabled. This is
	 * safe because the only time we set or clear this state is under
	 * the m_icsb_mutex.
	 */
	if (xfs_icsb_counter_disabled(mp, field))
		return;

	xfs_icsb_lock_all_counters(mp);
	if (!test_and_set_bit(field, &mp->m_icsb_counters)) {
		/* drain back to superblock */

		xfs_icsb_count(mp, &cnt, XFS_ICSB_LAZY_COUNT);
		switch(field) {
		case XFS_SBS_ICOUNT:
			mp->m_sb.sb_icount = cnt.icsb_icount;
			break;
		case XFS_SBS_IFREE:
			mp->m_sb.sb_ifree = cnt.icsb_ifree;
			break;
		case XFS_SBS_FDBLOCKS:
			mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
			break;
		default:
			BUG();
		}
	}

	xfs_icsb_unlock_all_counters(mp);
}

STATIC void
xfs_icsb_enable_counter(
	xfs_mount_t	*mp,
	xfs_sb_field_t	field,
	uint64_t	count,
	uint64_t	resid)
{
	xfs_icsb_cnts_t	*cntp;
	int		i;

	ASSERT((field >= XFS_SBS_ICOUNT) && (field <= XFS_SBS_FDBLOCKS));

	xfs_icsb_lock_all_counters(mp);
	for_each_online_cpu(i) {
		cntp = per_cpu_ptr(mp->m_sb_cnts, i);
		switch (field) {
		case XFS_SBS_ICOUNT:
			cntp->icsb_icount = count + resid;
			break;
		case XFS_SBS_IFREE:
			cntp->icsb_ifree = count + resid;
			break;
		case XFS_SBS_FDBLOCKS:
			cntp->icsb_fdblocks = count + resid;
			break;
		default:
			BUG();
			break;
		}
		resid = 0;
	}
	clear_bit(field, &mp->m_icsb_counters);
	xfs_icsb_unlock_all_counters(mp);
}

void
xfs_icsb_sync_counters_locked(
	xfs_mount_t	*mp,
	int		flags)
{
	xfs_icsb_cnts_t	cnt;

	xfs_icsb_count(mp, &cnt, flags);

	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_ICOUNT))
		mp->m_sb.sb_icount = cnt.icsb_icount;
	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_IFREE))
		mp->m_sb.sb_ifree = cnt.icsb_ifree;
	if (!xfs_icsb_counter_disabled(mp, XFS_SBS_FDBLOCKS))
		mp->m_sb.sb_fdblocks = cnt.icsb_fdblocks;
}

/*
 * Accurate update of per-cpu counters to incore superblock
 */
void
xfs_icsb_sync_counters(
	xfs_mount_t	*mp,
	int		flags)
{
	spin_lock(&mp->m_sb_lock);
	xfs_icsb_sync_counters_locked(mp, flags);
	spin_unlock(&mp->m_sb_lock);
}

/*
 * Balance and enable/disable counters as necessary.
 *
 * Thresholds for re-enabling counters are somewhat magic.  inode counts are
 * chosen to be the same number as single on disk allocation chunk per CPU, and
 * free blocks is something far enough zero that we aren't going thrash when we
 * get near ENOSPC. We also need to supply a minimum we require per cpu to
 * prevent looping endlessly when xfs_alloc_space asks for more than will
 * be distributed to a single CPU but each CPU has enough blocks to be
 * reenabled.
 *
 * Note that we can be called when counters are already disabled.
 * xfs_icsb_disable_counter() optimises the counter locking in this case to
 * prevent locking every per-cpu counter needlessly.
 */

#define XFS_ICSB_INO_CNTR_REENABLE	(uint64_t)64
#define XFS_ICSB_FDBLK_CNTR_REENABLE(mp) \
		(uint64_t)(512 + XFS_ALLOC_SET_ASIDE(mp))
STATIC void
xfs_icsb_balance_counter_locked(
	xfs_mount_t	*mp,
	xfs_sb_field_t  field,
	int		min_per_cpu)
{
	uint64_t	count, resid;
	int		weight = num_online_cpus();
	uint64_t	min = (uint64_t)min_per_cpu;

	/* disable counter and sync counter */
	xfs_icsb_disable_counter(mp, field);

	/* update counters  - first CPU gets residual*/
	switch (field) {
	case XFS_SBS_ICOUNT:
		count = mp->m_sb.sb_icount;
		resid = do_div(count, weight);
		if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
			return;
		break;
	case XFS_SBS_IFREE:
		count = mp->m_sb.sb_ifree;
		resid = do_div(count, weight);
		if (count < max(min, XFS_ICSB_INO_CNTR_REENABLE))
			return;
		break;
	case XFS_SBS_FDBLOCKS:
		count = mp->m_sb.sb_fdblocks;
		resid = do_div(count, weight);
		if (count < max(min, XFS_ICSB_FDBLK_CNTR_REENABLE(mp)))
			return;
		break;
	default:
		BUG();
		count = resid = 0;	/* quiet, gcc */
		break;
	}

	xfs_icsb_enable_counter(mp, field, count, resid);
}

STATIC void
xfs_icsb_balance_counter(
	xfs_mount_t	*mp,
	xfs_sb_field_t  fields,
	int		min_per_cpu)
{
	spin_lock(&mp->m_sb_lock);
	xfs_icsb_balance_counter_locked(mp, fields, min_per_cpu);
	spin_unlock(&mp->m_sb_lock);
}

int
xfs_icsb_modify_counters(
	xfs_mount_t	*mp,
	xfs_sb_field_t	field,
	int64_t		delta,
	int		rsvd)
{
	xfs_icsb_cnts_t	*icsbp;
	long long	lcounter;	/* long counter for 64 bit fields */
	int		ret = 0;

	might_sleep();
again:
	preempt_disable();
	icsbp = this_cpu_ptr(mp->m_sb_cnts);

	/*
	 * if the counter is disabled, go to slow path
	 */
	if (unlikely(xfs_icsb_counter_disabled(mp, field)))
		goto slow_path;
	xfs_icsb_lock_cntr(icsbp);
	if (unlikely(xfs_icsb_counter_disabled(mp, field))) {
		xfs_icsb_unlock_cntr(icsbp);
		goto slow_path;
	}

	switch (field) {
	case XFS_SBS_ICOUNT:
		lcounter = icsbp->icsb_icount;
		lcounter += delta;
		if (unlikely(lcounter < 0))
			goto balance_counter;
		icsbp->icsb_icount = lcounter;
		break;

	case XFS_SBS_IFREE:
		lcounter = icsbp->icsb_ifree;
		lcounter += delta;
		if (unlikely(lcounter < 0))
			goto balance_counter;
		icsbp->icsb_ifree = lcounter;
		break;

	case XFS_SBS_FDBLOCKS:
		BUG_ON((mp->m_resblks - mp->m_resblks_avail) != 0);

		lcounter = icsbp->icsb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
		lcounter += delta;
		if (unlikely(lcounter < 0))
			goto balance_counter;
		icsbp->icsb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);
		break;
	default:
		BUG();
		break;
	}
	xfs_icsb_unlock_cntr(icsbp);
	preempt_enable();
	return 0;

slow_path:
	preempt_enable();

	/*
	 * serialise with a mutex so we don't burn lots of cpu on
	 * the superblock lock. We still need to hold the superblock
	 * lock, however, when we modify the global structures.
	 */
	xfs_icsb_lock(mp);

	/*
	 * Now running atomically.
	 *
	 * If the counter is enabled, someone has beaten us to rebalancing.
	 * Drop the lock and try again in the fast path....
	 */
	if (!(xfs_icsb_counter_disabled(mp, field))) {
		xfs_icsb_unlock(mp);
		goto again;
	}

	/*
	 * The counter is currently disabled. Because we are
	 * running atomically here, we know a rebalance cannot
	 * be in progress. Hence we can go straight to operating
	 * on the global superblock. We do not call xfs_mod_incore_sb()
	 * here even though we need to get the m_sb_lock. Doing so
	 * will cause us to re-enter this function and deadlock.
	 * Hence we get the m_sb_lock ourselves and then call
	 * xfs_mod_incore_sb_unlocked() as the unlocked path operates
	 * directly on the global counters.
	 */
	spin_lock(&mp->m_sb_lock);
	ret = xfs_mod_incore_sb_unlocked(mp, field, delta, rsvd);
	spin_unlock(&mp->m_sb_lock);

	/*
	 * Now that we've modified the global superblock, we
	 * may be able to re-enable the distributed counters
	 * (e.g. lots of space just got freed). After that
	 * we are done.
	 */
	if (ret != -ENOSPC)
		xfs_icsb_balance_counter(mp, field, 0);
	xfs_icsb_unlock(mp);
	return ret;

balance_counter:
	xfs_icsb_unlock_cntr(icsbp);
	preempt_enable();

	/*
	 * We may have multiple threads here if multiple per-cpu
	 * counters run dry at the same time. This will mean we can
	 * do more balances than strictly necessary but it is not
	 * the common slowpath case.
	 */
	xfs_icsb_lock(mp);

	/*
	 * running atomically.
	 *
	 * This will leave the counter in the correct state for future
	 * accesses. After the rebalance, we simply try again and our retry
	 * will either succeed through the fast path or slow path without
	 * another balance operation being required.
	 */
	xfs_icsb_balance_counter(mp, field, delta);
	xfs_icsb_unlock(mp);
	goto again;
}

#endif