summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_buf.c
blob: dcb70969ff1c75a9dda5c6c25afcc8dac8fc6270 (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
/*
 * Copyright (c) 2000-2006 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 <linux/stddef.h>
#include <linux/errno.h>
#include <linux/gfp.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/vmalloc.h>
#include <linux/bio.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/workqueue.h>
#include <linux/percpu.h>
#include <linux/blkdev.h>
#include <linux/hash.h>
#include <linux/kthread.h>
#include <linux/migrate.h>
#include <linux/backing-dev.h>
#include <linux/freezer.h>

#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_trace.h"
#include "xfs_log.h"

static kmem_zone_t *xfs_buf_zone;

#ifdef XFS_BUF_LOCK_TRACKING
# define XB_SET_OWNER(bp)	((bp)->b_last_holder = current->pid)
# define XB_CLEAR_OWNER(bp)	((bp)->b_last_holder = -1)
# define XB_GET_OWNER(bp)	((bp)->b_last_holder)
#else
# define XB_SET_OWNER(bp)	do { } while (0)
# define XB_CLEAR_OWNER(bp)	do { } while (0)
# define XB_GET_OWNER(bp)	do { } while (0)
#endif

#define xb_to_gfp(flags) \
	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN)


static inline int
xfs_buf_is_vmapped(
	struct xfs_buf	*bp)
{
	/*
	 * Return true if the buffer is vmapped.
	 *
	 * b_addr is null if the buffer is not mapped, but the code is clever
	 * enough to know it doesn't have to map a single page, so the check has
	 * to be both for b_addr and bp->b_page_count > 1.
	 */
	return bp->b_addr && bp->b_page_count > 1;
}

static inline int
xfs_buf_vmap_len(
	struct xfs_buf	*bp)
{
	return (bp->b_page_count * PAGE_SIZE) - bp->b_offset;
}

/*
 * When we mark a buffer stale, we remove the buffer from the LRU and clear the
 * b_lru_ref count so that the buffer is freed immediately when the buffer
 * reference count falls to zero. If the buffer is already on the LRU, we need
 * to remove the reference that LRU holds on the buffer.
 *
 * This prevents build-up of stale buffers on the LRU.
 */
void
xfs_buf_stale(
	struct xfs_buf	*bp)
{
	ASSERT(xfs_buf_islocked(bp));

	bp->b_flags |= XBF_STALE;

	/*
	 * Clear the delwri status so that a delwri queue walker will not
	 * flush this buffer to disk now that it is stale. The delwri queue has
	 * a reference to the buffer, so this is safe to do.
	 */
	bp->b_flags &= ~_XBF_DELWRI_Q;

	spin_lock(&bp->b_lock);
	atomic_set(&bp->b_lru_ref, 0);
	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
	    (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
		atomic_dec(&bp->b_hold);

	ASSERT(atomic_read(&bp->b_hold) >= 1);
	spin_unlock(&bp->b_lock);
}

static int
xfs_buf_get_maps(
	struct xfs_buf		*bp,
	int			map_count)
{
	ASSERT(bp->b_maps == NULL);
	bp->b_map_count = map_count;

	if (map_count == 1) {
		bp->b_maps = &bp->__b_map;
		return 0;
	}

	bp->b_maps = kmem_zalloc(map_count * sizeof(struct xfs_buf_map),
				KM_NOFS);
	if (!bp->b_maps)
		return -ENOMEM;
	return 0;
}

/*
 *	Frees b_pages if it was allocated.
 */
static void
xfs_buf_free_maps(
	struct xfs_buf	*bp)
{
	if (bp->b_maps != &bp->__b_map) {
		kmem_free(bp->b_maps);
		bp->b_maps = NULL;
	}
}

struct xfs_buf *
_xfs_buf_alloc(
	struct xfs_buftarg	*target,
	struct xfs_buf_map	*map,
	int			nmaps,
	xfs_buf_flags_t		flags)
{
	struct xfs_buf		*bp;
	int			error;
	int			i;

	bp = kmem_zone_zalloc(xfs_buf_zone, KM_NOFS);
	if (unlikely(!bp))
		return NULL;

	/*
	 * We don't want certain flags to appear in b_flags unless they are
	 * specifically set by later operations on the buffer.
	 */
	flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);

	atomic_set(&bp->b_hold, 1);
	atomic_set(&bp->b_lru_ref, 1);
	init_completion(&bp->b_iowait);
	INIT_LIST_HEAD(&bp->b_lru);
	INIT_LIST_HEAD(&bp->b_list);
	RB_CLEAR_NODE(&bp->b_rbnode);
	sema_init(&bp->b_sema, 0); /* held, no waiters */
	spin_lock_init(&bp->b_lock);
	XB_SET_OWNER(bp);
	bp->b_target = target;
	bp->b_flags = flags;

	/*
	 * Set length and io_length to the same value initially.
	 * I/O routines should use io_length, which will be the same in
	 * most cases but may be reset (e.g. XFS recovery).
	 */
	error = xfs_buf_get_maps(bp, nmaps);
	if (error)  {
		kmem_zone_free(xfs_buf_zone, bp);
		return NULL;
	}

	bp->b_bn = map[0].bm_bn;
	bp->b_length = 0;
	for (i = 0; i < nmaps; i++) {
		bp->b_maps[i].bm_bn = map[i].bm_bn;
		bp->b_maps[i].bm_len = map[i].bm_len;
		bp->b_length += map[i].bm_len;
	}
	bp->b_io_length = bp->b_length;

	atomic_set(&bp->b_pin_count, 0);
	init_waitqueue_head(&bp->b_waiters);

	XFS_STATS_INC(target->bt_mount, xb_create);
	trace_xfs_buf_init(bp, _RET_IP_);

	return bp;
}

/*
 *	Allocate a page array capable of holding a specified number
 *	of pages, and point the page buf at it.
 */
STATIC int
_xfs_buf_get_pages(
	xfs_buf_t		*bp,
	int			page_count)
{
	/* Make sure that we have a page list */
	if (bp->b_pages == NULL) {
		bp->b_page_count = page_count;
		if (page_count <= XB_PAGES) {
			bp->b_pages = bp->b_page_array;
		} else {
			bp->b_pages = kmem_alloc(sizeof(struct page *) *
						 page_count, KM_NOFS);
			if (bp->b_pages == NULL)
				return -ENOMEM;
		}
		memset(bp->b_pages, 0, sizeof(struct page *) * page_count);
	}
	return 0;
}

/*
 *	Frees b_pages if it was allocated.
 */
STATIC void
_xfs_buf_free_pages(
	xfs_buf_t	*bp)
{
	if (bp->b_pages != bp->b_page_array) {
		kmem_free(bp->b_pages);
		bp->b_pages = NULL;
	}
}

/*
 *	Releases the specified buffer.
 *
 * 	The modification state of any associated pages is left unchanged.
 * 	The buffer must not be on any hash - use xfs_buf_rele instead for
 * 	hashed and refcounted buffers
 */
void
xfs_buf_free(
	xfs_buf_t		*bp)
{
	trace_xfs_buf_free(bp, _RET_IP_);

	ASSERT(list_empty(&bp->b_lru));

	if (bp->b_flags & _XBF_PAGES) {
		uint		i;

		if (xfs_buf_is_vmapped(bp))
			vm_unmap_ram(bp->b_addr - bp->b_offset,
					bp->b_page_count);

		for (i = 0; i < bp->b_page_count; i++) {
			struct page	*page = bp->b_pages[i];

			__free_page(page);
		}
	} else if (bp->b_flags & _XBF_KMEM)
		kmem_free(bp->b_addr);
	_xfs_buf_free_pages(bp);
	xfs_buf_free_maps(bp);
	kmem_zone_free(xfs_buf_zone, bp);
}

/*
 * Allocates all the pages for buffer in question and builds it's page list.
 */
STATIC int
xfs_buf_allocate_memory(
	xfs_buf_t		*bp,
	uint			flags)
{
	size_t			size;
	size_t			nbytes, offset;
	gfp_t			gfp_mask = xb_to_gfp(flags);
	unsigned short		page_count, i;
	xfs_off_t		start, end;
	int			error;

	/*
	 * for buffers that are contained within a single page, just allocate
	 * the memory from the heap - there's no need for the complexity of
	 * page arrays to keep allocation down to order 0.
	 */
	size = BBTOB(bp->b_length);
	if (size < PAGE_SIZE) {
		bp->b_addr = kmem_alloc(size, KM_NOFS);
		if (!bp->b_addr) {
			/* low memory - use alloc_page loop instead */
			goto use_alloc_page;
		}

		if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) !=
		    ((unsigned long)bp->b_addr & PAGE_MASK)) {
			/* b_addr spans two pages - use alloc_page instead */
			kmem_free(bp->b_addr);
			bp->b_addr = NULL;
			goto use_alloc_page;
		}
		bp->b_offset = offset_in_page(bp->b_addr);
		bp->b_pages = bp->b_page_array;
		bp->b_pages[0] = virt_to_page(bp->b_addr);
		bp->b_page_count = 1;
		bp->b_flags |= _XBF_KMEM;
		return 0;
	}

use_alloc_page:
	start = BBTOB(bp->b_maps[0].bm_bn) >> PAGE_SHIFT;
	end = (BBTOB(bp->b_maps[0].bm_bn + bp->b_length) + PAGE_SIZE - 1)
								>> PAGE_SHIFT;
	page_count = end - start;
	error = _xfs_buf_get_pages(bp, page_count);
	if (unlikely(error))
		return error;

	offset = bp->b_offset;
	bp->b_flags |= _XBF_PAGES;

	for (i = 0; i < bp->b_page_count; i++) {
		struct page	*page;
		uint		retries = 0;
retry:
		page = alloc_page(gfp_mask);
		if (unlikely(page == NULL)) {
			if (flags & XBF_READ_AHEAD) {
				bp->b_page_count = i;
				error = -ENOMEM;
				goto out_free_pages;
			}

			/*
			 * This could deadlock.
			 *
			 * But until all the XFS lowlevel code is revamped to
			 * handle buffer allocation failures we can't do much.
			 */
			if (!(++retries % 100))
				xfs_err(NULL,
		"%s(%u) possible memory allocation deadlock in %s (mode:0x%x)",
					current->comm, current->pid,
					__func__, gfp_mask);

			XFS_STATS_INC(bp->b_target->bt_mount, xb_page_retries);
			congestion_wait(BLK_RW_ASYNC, HZ/50);
			goto retry;
		}

		XFS_STATS_INC(bp->b_target->bt_mount, xb_page_found);

		nbytes = min_t(size_t, size, PAGE_SIZE - offset);
		size -= nbytes;
		bp->b_pages[i] = page;
		offset = 0;
	}
	return 0;

out_free_pages:
	for (i = 0; i < bp->b_page_count; i++)
		__free_page(bp->b_pages[i]);
	bp->b_flags &= ~_XBF_PAGES;
	return error;
}

/*
 *	Map buffer into kernel address-space if necessary.
 */
STATIC int
_xfs_buf_map_pages(
	xfs_buf_t		*bp,
	uint			flags)
{
	ASSERT(bp->b_flags & _XBF_PAGES);
	if (bp->b_page_count == 1) {
		/* A single page buffer is always mappable */
		bp->b_addr = page_address(bp->b_pages[0]) + bp->b_offset;
	} else if (flags & XBF_UNMAPPED) {
		bp->b_addr = NULL;
	} else {
		int retried = 0;
		unsigned noio_flag;

		/*
		 * vm_map_ram() will allocate auxillary structures (e.g.
		 * pagetables) with GFP_KERNEL, yet we are likely to be under
		 * GFP_NOFS context here. Hence we need to tell memory reclaim
		 * that we are in such a context via PF_MEMALLOC_NOIO to prevent
		 * memory reclaim re-entering the filesystem here and
		 * potentially deadlocking.
		 */
		noio_flag = memalloc_noio_save();
		do {
			bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
						-1, PAGE_KERNEL);
			if (bp->b_addr)
				break;
			vm_unmap_aliases();
		} while (retried++ <= 1);
		memalloc_noio_restore(noio_flag);

		if (!bp->b_addr)
			return -ENOMEM;
		bp->b_addr += bp->b_offset;
	}

	return 0;
}

/*
 *	Finding and Reading Buffers
 */

/*
 *	Look up, and creates if absent, a lockable buffer for
 *	a given range of an inode.  The buffer is returned
 *	locked.	No I/O is implied by this call.
 */
xfs_buf_t *
_xfs_buf_find(
	struct xfs_buftarg	*btp,
	struct xfs_buf_map	*map,
	int			nmaps,
	xfs_buf_flags_t		flags,
	xfs_buf_t		*new_bp)
{
	struct xfs_perag	*pag;
	struct rb_node		**rbp;
	struct rb_node		*parent;
	xfs_buf_t		*bp;
	xfs_daddr_t		blkno = map[0].bm_bn;
	xfs_daddr_t		eofs;
	int			numblks = 0;
	int			i;

	for (i = 0; i < nmaps; i++)
		numblks += map[i].bm_len;

	/* Check for IOs smaller than the sector size / not sector aligned */
	ASSERT(!(BBTOB(numblks) < btp->bt_meta_sectorsize));
	ASSERT(!(BBTOB(blkno) & (xfs_off_t)btp->bt_meta_sectormask));

	/*
	 * Corrupted block numbers can get through to here, unfortunately, so we
	 * have to check that the buffer falls within the filesystem bounds.
	 */
	eofs = XFS_FSB_TO_BB(btp->bt_mount, btp->bt_mount->m_sb.sb_dblocks);
	if (blkno < 0 || blkno >= eofs) {
		/*
		 * XXX (dgc): we should really be returning -EFSCORRUPTED here,
		 * but none of the higher level infrastructure supports
		 * returning a specific error on buffer lookup failures.
		 */
		xfs_alert(btp->bt_mount,
			  "%s: Block out of range: block 0x%llx, EOFS 0x%llx ",
			  __func__, blkno, eofs);
		WARN_ON(1);
		return NULL;
	}

	/* get tree root */
	pag = xfs_perag_get(btp->bt_mount,
				xfs_daddr_to_agno(btp->bt_mount, blkno));

	/* walk tree */
	spin_lock(&pag->pag_buf_lock);
	rbp = &pag->pag_buf_tree.rb_node;
	parent = NULL;
	bp = NULL;
	while (*rbp) {
		parent = *rbp;
		bp = rb_entry(parent, struct xfs_buf, b_rbnode);

		if (blkno < bp->b_bn)
			rbp = &(*rbp)->rb_left;
		else if (blkno > bp->b_bn)
			rbp = &(*rbp)->rb_right;
		else {
			/*
			 * found a block number match. If the range doesn't
			 * match, the only way this is allowed is if the buffer
			 * in the cache is stale and the transaction that made
			 * it stale has not yet committed. i.e. we are
			 * reallocating a busy extent. Skip this buffer and
			 * continue searching to the right for an exact match.
			 */
			if (bp->b_length != numblks) {
				ASSERT(bp->b_flags & XBF_STALE);
				rbp = &(*rbp)->rb_right;
				continue;
			}
			atomic_inc(&bp->b_hold);
			goto found;
		}
	}

	/* No match found */
	if (new_bp) {
		rb_link_node(&new_bp->b_rbnode, parent, rbp);
		rb_insert_color(&new_bp->b_rbnode, &pag->pag_buf_tree);
		/* the buffer keeps the perag reference until it is freed */
		new_bp->b_pag = pag;
		spin_unlock(&pag->pag_buf_lock);
	} else {
		XFS_STATS_INC(btp->bt_mount, xb_miss_locked);
		spin_unlock(&pag->pag_buf_lock);
		xfs_perag_put(pag);
	}
	return new_bp;

found:
	spin_unlock(&pag->pag_buf_lock);
	xfs_perag_put(pag);

	if (!xfs_buf_trylock(bp)) {
		if (flags & XBF_TRYLOCK) {
			xfs_buf_rele(bp);
			XFS_STATS_INC(btp->bt_mount, xb_busy_locked);
			return NULL;
		}
		xfs_buf_lock(bp);
		XFS_STATS_INC(btp->bt_mount, xb_get_locked_waited);
	}

	/*
	 * if the buffer is stale, clear all the external state associated with
	 * it. We need to keep flags such as how we allocated the buffer memory
	 * intact here.
	 */
	if (bp->b_flags & XBF_STALE) {
		ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
		ASSERT(bp->b_iodone == NULL);
		bp->b_flags &= _XBF_KMEM | _XBF_PAGES;
		bp->b_ops = NULL;
	}

	trace_xfs_buf_find(bp, flags, _RET_IP_);
	XFS_STATS_INC(btp->bt_mount, xb_get_locked);
	return bp;
}

/*
 * Assembles a buffer covering the specified range. The code is optimised for
 * cache hits, as metadata intensive workloads will see 3 orders of magnitude
 * more hits than misses.
 */
struct xfs_buf *
xfs_buf_get_map(
	struct xfs_buftarg	*target,
	struct xfs_buf_map	*map,
	int			nmaps,
	xfs_buf_flags_t		flags)
{
	struct xfs_buf		*bp;
	struct xfs_buf		*new_bp;
	int			error = 0;

	bp = _xfs_buf_find(target, map, nmaps, flags, NULL);
	if (likely(bp))
		goto found;

	new_bp = _xfs_buf_alloc(target, map, nmaps, flags);
	if (unlikely(!new_bp))
		return NULL;

	error = xfs_buf_allocate_memory(new_bp, flags);
	if (error) {
		xfs_buf_free(new_bp);
		return NULL;
	}

	bp = _xfs_buf_find(target, map, nmaps, flags, new_bp);
	if (!bp) {
		xfs_buf_free(new_bp);
		return NULL;
	}

	if (bp != new_bp)
		xfs_buf_free(new_bp);

found:
	if (!bp->b_addr) {
		error = _xfs_buf_map_pages(bp, flags);
		if (unlikely(error)) {
			xfs_warn(target->bt_mount,
				"%s: failed to map pagesn", __func__);
			xfs_buf_relse(bp);
			return NULL;
		}
	}

	/*
	 * Clear b_error if this is a lookup from a caller that doesn't expect
	 * valid data to be found in the buffer.
	 */
	if (!(flags & XBF_READ))
		xfs_buf_ioerror(bp, 0);

	XFS_STATS_INC(target->bt_mount, xb_get);
	trace_xfs_buf_get(bp, flags, _RET_IP_);
	return bp;
}

STATIC int
_xfs_buf_read(
	xfs_buf_t		*bp,
	xfs_buf_flags_t		flags)
{
	ASSERT(!(flags & XBF_WRITE));
	ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL);

	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);

	if (flags & XBF_ASYNC) {
		xfs_buf_submit(bp);
		return 0;
	}
	return xfs_buf_submit_wait(bp);
}

xfs_buf_t *
xfs_buf_read_map(
	struct xfs_buftarg	*target,
	struct xfs_buf_map	*map,
	int			nmaps,
	xfs_buf_flags_t		flags,
	const struct xfs_buf_ops *ops)
{
	struct xfs_buf		*bp;

	flags |= XBF_READ;

	bp = xfs_buf_get_map(target, map, nmaps, flags);
	if (bp) {
		trace_xfs_buf_read(bp, flags, _RET_IP_);

		if (!XFS_BUF_ISDONE(bp)) {
			XFS_STATS_INC(target->bt_mount, xb_get_read);
			bp->b_ops = ops;
			_xfs_buf_read(bp, flags);
		} else if (flags & XBF_ASYNC) {
			/*
			 * Read ahead call which is already satisfied,
			 * drop the buffer
			 */
			xfs_buf_relse(bp);
			return NULL;
		} else {
			/* We do not want read in the flags */
			bp->b_flags &= ~XBF_READ;
		}
	}

	return bp;
}

/*
 *	If we are not low on memory then do the readahead in a deadlock
 *	safe manner.
 */
void
xfs_buf_readahead_map(
	struct xfs_buftarg	*target,
	struct xfs_buf_map	*map,
	int			nmaps,
	const struct xfs_buf_ops *ops)
{
	if (bdi_read_congested(target->bt_bdi))
		return;

	xfs_buf_read_map(target, map, nmaps,
		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD, ops);
}

/*
 * Read an uncached buffer from disk. Allocates and returns a locked
 * buffer containing the disk contents or nothing.
 */
int
xfs_buf_read_uncached(
	struct xfs_buftarg	*target,
	xfs_daddr_t		daddr,
	size_t			numblks,
	int			flags,
	struct xfs_buf		**bpp,
	const struct xfs_buf_ops *ops)
{
	struct xfs_buf		*bp;

	*bpp = NULL;

	bp = xfs_buf_get_uncached(target, numblks, flags);
	if (!bp)
		return -ENOMEM;

	/* set up the buffer for a read IO */
	ASSERT(bp->b_map_count == 1);
	bp->b_bn = XFS_BUF_DADDR_NULL;  /* always null for uncached buffers */
	bp->b_maps[0].bm_bn = daddr;
	bp->b_flags |= XBF_READ;
	bp->b_ops = ops;

	xfs_buf_submit_wait(bp);
	if (bp->b_error) {
		int	error = bp->b_error;
		xfs_buf_relse(bp);
		return error;
	}

	*bpp = bp;
	return 0;
}

/*
 * Return a buffer allocated as an empty buffer and associated to external
 * memory via xfs_buf_associate_memory() back to it's empty state.
 */
void
xfs_buf_set_empty(
	struct xfs_buf		*bp,
	size_t			numblks)
{
	if (bp->b_pages)
		_xfs_buf_free_pages(bp);

	bp->b_pages = NULL;
	bp->b_page_count = 0;
	bp->b_addr = NULL;
	bp->b_length = numblks;
	bp->b_io_length = numblks;

	ASSERT(bp->b_map_count == 1);
	bp->b_bn = XFS_BUF_DADDR_NULL;
	bp->b_maps[0].bm_bn = XFS_BUF_DADDR_NULL;
	bp->b_maps[0].bm_len = bp->b_length;
}

static inline struct page *
mem_to_page(
	void			*addr)
{
	if ((!is_vmalloc_addr(addr))) {
		return virt_to_page(addr);
	} else {
		return vmalloc_to_page(addr);
	}
}

int
xfs_buf_associate_memory(
	xfs_buf_t		*bp,
	void			*mem,
	size_t			len)
{
	int			rval;
	int			i = 0;
	unsigned long		pageaddr;
	unsigned long		offset;
	size_t			buflen;
	int			page_count;

	pageaddr = (unsigned long)mem & PAGE_MASK;
	offset = (unsigned long)mem - pageaddr;
	buflen = PAGE_ALIGN(len + offset);
	page_count = buflen >> PAGE_SHIFT;

	/* Free any previous set of page pointers */
	if (bp->b_pages)
		_xfs_buf_free_pages(bp);

	bp->b_pages = NULL;
	bp->b_addr = mem;

	rval = _xfs_buf_get_pages(bp, page_count);
	if (rval)
		return rval;

	bp->b_offset = offset;

	for (i = 0; i < bp->b_page_count; i++) {
		bp->b_pages[i] = mem_to_page((void *)pageaddr);
		pageaddr += PAGE_SIZE;
	}

	bp->b_io_length = BTOBB(len);
	bp->b_length = BTOBB(buflen);

	return 0;
}

xfs_buf_t *
xfs_buf_get_uncached(
	struct xfs_buftarg	*target,
	size_t			numblks,
	int			flags)
{
	unsigned long		page_count;
	int			error, i;
	struct xfs_buf		*bp;
	DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);

	bp = _xfs_buf_alloc(target, &map, 1, 0);
	if (unlikely(bp == NULL))
		goto fail;

	page_count = PAGE_ALIGN(numblks << BBSHIFT) >> PAGE_SHIFT;
	error = _xfs_buf_get_pages(bp, page_count);
	if (error)
		goto fail_free_buf;

	for (i = 0; i < page_count; i++) {
		bp->b_pages[i] = alloc_page(xb_to_gfp(flags));
		if (!bp->b_pages[i])
			goto fail_free_mem;
	}
	bp->b_flags |= _XBF_PAGES;

	error = _xfs_buf_map_pages(bp, 0);
	if (unlikely(error)) {
		xfs_warn(target->bt_mount,
			"%s: failed to map pages", __func__);
		goto fail_free_mem;
	}

	trace_xfs_buf_get_uncached(bp, _RET_IP_);
	return bp;

 fail_free_mem:
	while (--i >= 0)
		__free_page(bp->b_pages[i]);
	_xfs_buf_free_pages(bp);
 fail_free_buf:
	xfs_buf_free_maps(bp);
	kmem_zone_free(xfs_buf_zone, bp);
 fail:
	return NULL;
}

/*
 *	Increment reference count on buffer, to hold the buffer concurrently
 *	with another thread which may release (free) the buffer asynchronously.
 *	Must hold the buffer already to call this function.
 */
void
xfs_buf_hold(
	xfs_buf_t		*bp)
{
	trace_xfs_buf_hold(bp, _RET_IP_);
	atomic_inc(&bp->b_hold);
}

/*
 *	Releases a hold on the specified buffer.  If the
 *	the hold count is 1, calls xfs_buf_free.
 */
void
xfs_buf_rele(
	xfs_buf_t		*bp)
{
	struct xfs_perag	*pag = bp->b_pag;

	trace_xfs_buf_rele(bp, _RET_IP_);

	if (!pag) {
		ASSERT(list_empty(&bp->b_lru));
		ASSERT(RB_EMPTY_NODE(&bp->b_rbnode));
		if (atomic_dec_and_test(&bp->b_hold))
			xfs_buf_free(bp);
		return;
	}

	ASSERT(!RB_EMPTY_NODE(&bp->b_rbnode));

	ASSERT(atomic_read(&bp->b_hold) > 0);
	if (atomic_dec_and_lock(&bp->b_hold, &pag->pag_buf_lock)) {
		spin_lock(&bp->b_lock);
		if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
			/*
			 * If the buffer is added to the LRU take a new
			 * reference to the buffer for the LRU and clear the
			 * (now stale) dispose list state flag
			 */
			if (list_lru_add(&bp->b_target->bt_lru, &bp->b_lru)) {
				bp->b_state &= ~XFS_BSTATE_DISPOSE;
				atomic_inc(&bp->b_hold);
			}
			spin_unlock(&bp->b_lock);
			spin_unlock(&pag->pag_buf_lock);
		} else {
			/*
			 * most of the time buffers will already be removed from
			 * the LRU, so optimise that case by checking for the
			 * XFS_BSTATE_DISPOSE flag indicating the last list the
			 * buffer was on was the disposal list
			 */
			if (!(bp->b_state & XFS_BSTATE_DISPOSE)) {
				list_lru_del(&bp->b_target->bt_lru, &bp->b_lru);
			} else {
				ASSERT(list_empty(&bp->b_lru));
			}
			spin_unlock(&bp->b_lock);

			ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
			rb_erase(&bp->b_rbnode, &pag->pag_buf_tree);
			spin_unlock(&pag->pag_buf_lock);
			xfs_perag_put(pag);
			xfs_buf_free(bp);
		}
	}
}


/*
 *	Lock a buffer object, if it is not already locked.
 *
 *	If we come across a stale, pinned, locked buffer, we know that we are
 *	being asked to lock a buffer that has been reallocated. Because it is
 *	pinned, we know that the log has not been pushed to disk and hence it
 *	will still be locked.  Rather than continuing to have trylock attempts
 *	fail until someone else pushes the log, push it ourselves before
 *	returning.  This means that the xfsaild will not get stuck trying
 *	to push on stale inode buffers.
 */
int
xfs_buf_trylock(
	struct xfs_buf		*bp)
{
	int			locked;

	locked = down_trylock(&bp->b_sema) == 0;
	if (locked)
		XB_SET_OWNER(bp);

	trace_xfs_buf_trylock(bp, _RET_IP_);
	return locked;
}

/*
 *	Lock a buffer object.
 *
 *	If we come across a stale, pinned, locked buffer, we know that we
 *	are being asked to lock a buffer that has been reallocated. Because
 *	it is pinned, we know that the log has not been pushed to disk and
 *	hence it will still be locked. Rather than sleeping until someone
 *	else pushes the log, push it ourselves before trying to get the lock.
 */
void
xfs_buf_lock(
	struct xfs_buf		*bp)
{
	trace_xfs_buf_lock(bp, _RET_IP_);

	if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
		xfs_log_force(bp->b_target->bt_mount, 0);
	down(&bp->b_sema);
	XB_SET_OWNER(bp);

	trace_xfs_buf_lock_done(bp, _RET_IP_);
}

void
xfs_buf_unlock(
	struct xfs_buf		*bp)
{
	ASSERT(xfs_buf_islocked(bp));

	XB_CLEAR_OWNER(bp);
	up(&bp->b_sema);

	trace_xfs_buf_unlock(bp, _RET_IP_);
}

STATIC void
xfs_buf_wait_unpin(
	xfs_buf_t		*bp)
{
	DECLARE_WAITQUEUE	(wait, current);

	if (atomic_read(&bp->b_pin_count) == 0)
		return;

	add_wait_queue(&bp->b_waiters, &wait);
	for (;;) {
		set_current_state(TASK_UNINTERRUPTIBLE);
		if (atomic_read(&bp->b_pin_count) == 0)
			break;
		io_schedule();
	}
	remove_wait_queue(&bp->b_waiters, &wait);
	set_current_state(TASK_RUNNING);
}

/*
 *	Buffer Utility Routines
 */

void
xfs_buf_ioend(
	struct xfs_buf	*bp)
{
	bool		read = bp->b_flags & XBF_READ;

	trace_xfs_buf_iodone(bp, _RET_IP_);

	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD);

	/*
	 * Pull in IO completion errors now. We are guaranteed to be running
	 * single threaded, so we don't need the lock to read b_io_error.
	 */
	if (!bp->b_error && bp->b_io_error)
		xfs_buf_ioerror(bp, bp->b_io_error);

	/* Only validate buffers that were read without errors */
	if (read && !bp->b_error && bp->b_ops) {
		ASSERT(!bp->b_iodone);
		bp->b_ops->verify_read(bp);
	}

	if (!bp->b_error)
		bp->b_flags |= XBF_DONE;

	if (bp->b_iodone)
		(*(bp->b_iodone))(bp);
	else if (bp->b_flags & XBF_ASYNC)
		xfs_buf_relse(bp);
	else
		complete(&bp->b_iowait);
}

static void
xfs_buf_ioend_work(
	struct work_struct	*work)
{
	struct xfs_buf		*bp =
		container_of(work, xfs_buf_t, b_ioend_work);

	xfs_buf_ioend(bp);
}

void
xfs_buf_ioend_async(
	struct xfs_buf	*bp)
{
	INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work);
	queue_work(bp->b_ioend_wq, &bp->b_ioend_work);
}

void
xfs_buf_ioerror(
	xfs_buf_t		*bp,
	int			error)
{
	ASSERT(error <= 0 && error >= -1000);
	bp->b_error = error;
	trace_xfs_buf_ioerror(bp, error, _RET_IP_);
}

void
xfs_buf_ioerror_alert(
	struct xfs_buf		*bp,
	const char		*func)
{
	xfs_alert(bp->b_target->bt_mount,
"metadata I/O error: block 0x%llx (\"%s\") error %d numblks %d",
		(__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
}

int
xfs_bwrite(
	struct xfs_buf		*bp)
{
	int			error;

	ASSERT(xfs_buf_islocked(bp));

	bp->b_flags |= XBF_WRITE;
	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
			 XBF_WRITE_FAIL | XBF_DONE);

	error = xfs_buf_submit_wait(bp);
	if (error) {
		xfs_force_shutdown(bp->b_target->bt_mount,
				   SHUTDOWN_META_IO_ERROR);
	}
	return error;
}

STATIC void
xfs_buf_bio_end_io(
	struct bio		*bio)
{
	xfs_buf_t		*bp = (xfs_buf_t *)bio->bi_private;

	/*
	 * don't overwrite existing errors - otherwise we can lose errors on
	 * buffers that require multiple bios to complete.
	 */
	if (bio->bi_error) {
		spin_lock(&bp->b_lock);
		if (!bp->b_io_error)
			bp->b_io_error = bio->bi_error;
		spin_unlock(&bp->b_lock);
	}

	if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
		invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));

	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
		xfs_buf_ioend_async(bp);
	bio_put(bio);
}

static void
xfs_buf_ioapply_map(
	struct xfs_buf	*bp,
	int		map,
	int		*buf_offset,
	int		*count,
	int		rw)
{
	int		page_index;
	int		total_nr_pages = bp->b_page_count;
	int		nr_pages;
	struct bio	*bio;
	sector_t	sector =  bp->b_maps[map].bm_bn;
	int		size;
	int		offset;

	total_nr_pages = bp->b_page_count;

	/* skip the pages in the buffer before the start offset */
	page_index = 0;
	offset = *buf_offset;
	while (offset >= PAGE_SIZE) {
		page_index++;
		offset -= PAGE_SIZE;
	}

	/*
	 * Limit the IO size to the length of the current vector, and update the
	 * remaining IO count for the next time around.
	 */
	size = min_t(int, BBTOB(bp->b_maps[map].bm_len), *count);
	*count -= size;
	*buf_offset += size;

next_chunk:
	atomic_inc(&bp->b_io_remaining);
	nr_pages = BIO_MAX_SECTORS >> (PAGE_SHIFT - BBSHIFT);
	if (nr_pages > total_nr_pages)
		nr_pages = total_nr_pages;

	bio = bio_alloc(GFP_NOIO, nr_pages);
	bio->bi_bdev = bp->b_target->bt_bdev;
	bio->bi_iter.bi_sector = sector;
	bio->bi_end_io = xfs_buf_bio_end_io;
	bio->bi_private = bp;


	for (; size && nr_pages; nr_pages--, page_index++) {
		int	rbytes, nbytes = PAGE_SIZE - offset;

		if (nbytes > size)
			nbytes = size;

		rbytes = bio_add_page(bio, bp->b_pages[page_index], nbytes,
				      offset);
		if (rbytes < nbytes)
			break;

		offset = 0;
		sector += BTOBB(nbytes);
		size -= nbytes;
		total_nr_pages--;
	}

	if (likely(bio->bi_iter.bi_size)) {
		if (xfs_buf_is_vmapped(bp)) {
			flush_kernel_vmap_range(bp->b_addr,
						xfs_buf_vmap_len(bp));
		}
		submit_bio(rw, bio);
		if (size)
			goto next_chunk;
	} else {
		/*
		 * This is guaranteed not to be the last io reference count
		 * because the caller (xfs_buf_submit) holds a count itself.
		 */
		atomic_dec(&bp->b_io_remaining);
		xfs_buf_ioerror(bp, -EIO);
		bio_put(bio);
	}

}

STATIC void
_xfs_buf_ioapply(
	struct xfs_buf	*bp)
{
	struct blk_plug	plug;
	int		rw;
	int		offset;
	int		size;
	int		i;

	/*
	 * Make sure we capture only current IO errors rather than stale errors
	 * left over from previous use of the buffer (e.g. failed readahead).
	 */
	bp->b_error = 0;

	/*
	 * Initialize the I/O completion workqueue if we haven't yet or the
	 * submitter has not opted to specify a custom one.
	 */
	if (!bp->b_ioend_wq)
		bp->b_ioend_wq = bp->b_target->bt_mount->m_buf_workqueue;

	if (bp->b_flags & XBF_WRITE) {
		if (bp->b_flags & XBF_SYNCIO)
			rw = WRITE_SYNC;
		else
			rw = WRITE;
		if (bp->b_flags & XBF_FUA)
			rw |= REQ_FUA;
		if (bp->b_flags & XBF_FLUSH)
			rw |= REQ_FLUSH;

		/*
		 * Run the write verifier callback function if it exists. If
		 * this function fails it will mark the buffer with an error and
		 * the IO should not be dispatched.
		 */
		if (bp->b_ops) {
			bp->b_ops->verify_write(bp);
			if (bp->b_error) {
				xfs_force_shutdown(bp->b_target->bt_mount,
						   SHUTDOWN_CORRUPT_INCORE);
				return;
			}
		} else if (bp->b_bn != XFS_BUF_DADDR_NULL) {
			struct xfs_mount *mp = bp->b_target->bt_mount;

			/*
			 * non-crc filesystems don't attach verifiers during
			 * log recovery, so don't warn for such filesystems.
			 */
			if (xfs_sb_version_hascrc(&mp->m_sb)) {
				xfs_warn(mp,
					"%s: no ops on block 0x%llx/0x%x",
					__func__, bp->b_bn, bp->b_length);
				xfs_hex_dump(bp->b_addr, 64);
				dump_stack();
			}
		}
	} else if (bp->b_flags & XBF_READ_AHEAD) {
		rw = READA;
	} else {
		rw = READ;
	}

	/* we only use the buffer cache for meta-data */
	rw |= REQ_META;

	/*
	 * Walk all the vectors issuing IO on them. Set up the initial offset
	 * into the buffer and the desired IO size before we start -
	 * _xfs_buf_ioapply_vec() will modify them appropriately for each
	 * subsequent call.
	 */
	offset = bp->b_offset;
	size = BBTOB(bp->b_io_length);
	blk_start_plug(&plug);
	for (i = 0; i < bp->b_map_count; i++) {
		xfs_buf_ioapply_map(bp, i, &offset, &size, rw);
		if (bp->b_error)
			break;
		if (size <= 0)
			break;	/* all done */
	}
	blk_finish_plug(&plug);
}

/*
 * Asynchronous IO submission path. This transfers the buffer lock ownership and
 * the current reference to the IO. It is not safe to reference the buffer after
 * a call to this function unless the caller holds an additional reference
 * itself.
 */
void
xfs_buf_submit(
	struct xfs_buf	*bp)
{
	trace_xfs_buf_submit(bp, _RET_IP_);

	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
	ASSERT(bp->b_flags & XBF_ASYNC);

	/* on shutdown we stale and complete the buffer immediately */
	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
		xfs_buf_ioerror(bp, -EIO);
		bp->b_flags &= ~XBF_DONE;
		xfs_buf_stale(bp);
		xfs_buf_ioend(bp);
		return;
	}

	if (bp->b_flags & XBF_WRITE)
		xfs_buf_wait_unpin(bp);

	/* clear the internal error state to avoid spurious errors */
	bp->b_io_error = 0;

	/*
	 * The caller's reference is released during I/O completion.
	 * This occurs some time after the last b_io_remaining reference is
	 * released, so after we drop our Io reference we have to have some
	 * other reference to ensure the buffer doesn't go away from underneath
	 * us. Take a direct reference to ensure we have safe access to the
	 * buffer until we are finished with it.
	 */
	xfs_buf_hold(bp);

	/*
	 * Set the count to 1 initially, this will stop an I/O completion
	 * callout which happens before we have started all the I/O from calling
	 * xfs_buf_ioend too early.
	 */
	atomic_set(&bp->b_io_remaining, 1);
	_xfs_buf_ioapply(bp);

	/*
	 * If _xfs_buf_ioapply failed, we can get back here with only the IO
	 * reference we took above. If we drop it to zero, run completion so
	 * that we don't return to the caller with completion still pending.
	 */
	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
		if (bp->b_error)
			xfs_buf_ioend(bp);
		else
			xfs_buf_ioend_async(bp);
	}

	xfs_buf_rele(bp);
	/* Note: it is not safe to reference bp now we've dropped our ref */
}

/*
 * Synchronous buffer IO submission path, read or write.
 */
int
xfs_buf_submit_wait(
	struct xfs_buf	*bp)
{
	int		error;

	trace_xfs_buf_submit_wait(bp, _RET_IP_);

	ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC)));

	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
		xfs_buf_ioerror(bp, -EIO);
		xfs_buf_stale(bp);
		bp->b_flags &= ~XBF_DONE;
		return -EIO;
	}

	if (bp->b_flags & XBF_WRITE)
		xfs_buf_wait_unpin(bp);

	/* clear the internal error state to avoid spurious errors */
	bp->b_io_error = 0;

	/*
	 * For synchronous IO, the IO does not inherit the submitters reference
	 * count, nor the buffer lock. Hence we cannot release the reference we
	 * are about to take until we've waited for all IO completion to occur,
	 * including any xfs_buf_ioend_async() work that may be pending.
	 */
	xfs_buf_hold(bp);

	/*
	 * Set the count to 1 initially, this will stop an I/O completion
	 * callout which happens before we have started all the I/O from calling
	 * xfs_buf_ioend too early.
	 */
	atomic_set(&bp->b_io_remaining, 1);
	_xfs_buf_ioapply(bp);

	/*
	 * make sure we run completion synchronously if it raced with us and is
	 * already complete.
	 */
	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
		xfs_buf_ioend(bp);

	/* wait for completion before gathering the error from the buffer */
	trace_xfs_buf_iowait(bp, _RET_IP_);
	wait_for_completion(&bp->b_iowait);
	trace_xfs_buf_iowait_done(bp, _RET_IP_);
	error = bp->b_error;

	/*
	 * all done now, we can release the hold that keeps the buffer
	 * referenced for the entire IO.
	 */
	xfs_buf_rele(bp);
	return error;
}

void *
xfs_buf_offset(
	struct xfs_buf		*bp,
	size_t			offset)
{
	struct page		*page;

	if (bp->b_addr)
		return bp->b_addr + offset;

	offset += bp->b_offset;
	page = bp->b_pages[offset >> PAGE_SHIFT];
	return page_address(page) + (offset & (PAGE_SIZE-1));
}

/*
 *	Move data into or out of a buffer.
 */
void
xfs_buf_iomove(
	xfs_buf_t		*bp,	/* buffer to process		*/
	size_t			boff,	/* starting buffer offset	*/
	size_t			bsize,	/* length to copy		*/
	void			*data,	/* data address			*/
	xfs_buf_rw_t		mode)	/* read/write/zero flag		*/
{
	size_t			bend;

	bend = boff + bsize;
	while (boff < bend) {
		struct page	*page;
		int		page_index, page_offset, csize;

		page_index = (boff + bp->b_offset) >> PAGE_SHIFT;
		page_offset = (boff + bp->b_offset) & ~PAGE_MASK;
		page = bp->b_pages[page_index];
		csize = min_t(size_t, PAGE_SIZE - page_offset,
				      BBTOB(bp->b_io_length) - boff);

		ASSERT((csize + page_offset) <= PAGE_SIZE);

		switch (mode) {
		case XBRW_ZERO:
			memset(page_address(page) + page_offset, 0, csize);
			break;
		case XBRW_READ:
			memcpy(data, page_address(page) + page_offset, csize);
			break;
		case XBRW_WRITE:
			memcpy(page_address(page) + page_offset, data, csize);
		}

		boff += csize;
		data += csize;
	}
}

/*
 *	Handling of buffer targets (buftargs).
 */

/*
 * Wait for any bufs with callbacks that have been submitted but have not yet
 * returned. These buffers will have an elevated hold count, so wait on those
 * while freeing all the buffers only held by the LRU.
 */
static enum lru_status
xfs_buftarg_wait_rele(
	struct list_head	*item,
	struct list_lru_one	*lru,
	spinlock_t		*lru_lock,
	void			*arg)

{
	struct xfs_buf		*bp = container_of(item, struct xfs_buf, b_lru);
	struct list_head	*dispose = arg;

	if (atomic_read(&bp->b_hold) > 1) {
		/* need to wait, so skip it this pass */
		trace_xfs_buf_wait_buftarg(bp, _RET_IP_);
		return LRU_SKIP;
	}
	if (!spin_trylock(&bp->b_lock))
		return LRU_SKIP;

	/*
	 * clear the LRU reference count so the buffer doesn't get
	 * ignored in xfs_buf_rele().
	 */
	atomic_set(&bp->b_lru_ref, 0);
	bp->b_state |= XFS_BSTATE_DISPOSE;
	list_lru_isolate_move(lru, item, dispose);
	spin_unlock(&bp->b_lock);
	return LRU_REMOVED;
}

void
xfs_wait_buftarg(
	struct xfs_buftarg	*btp)
{
	LIST_HEAD(dispose);
	int loop = 0;

	/*
	 * We need to flush the buffer workqueue to ensure that all IO
	 * completion processing is 100% done. Just waiting on buffer locks is
	 * not sufficient for async IO as the reference count held over IO is
	 * not released until after the buffer lock is dropped. Hence we need to
	 * ensure here that all reference counts have been dropped before we
	 * start walking the LRU list.
	 */
	flush_workqueue(btp->bt_mount->m_buf_workqueue);

	/* loop until there is nothing left on the lru list. */
	while (list_lru_count(&btp->bt_lru)) {
		list_lru_walk(&btp->bt_lru, xfs_buftarg_wait_rele,
			      &dispose, LONG_MAX);

		while (!list_empty(&dispose)) {
			struct xfs_buf *bp;
			bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
			list_del_init(&bp->b_lru);
			if (bp->b_flags & XBF_WRITE_FAIL) {
				xfs_alert(btp->bt_mount,
"Corruption Alert: Buffer at block 0x%llx had permanent write failures!",
					(long long)bp->b_bn);
				xfs_alert(btp->bt_mount,
"Please run xfs_repair to determine the extent of the problem.");
			}
			xfs_buf_rele(bp);
		}
		if (loop++ != 0)
			delay(100);
	}
}

static enum lru_status
xfs_buftarg_isolate(
	struct list_head	*item,
	struct list_lru_one	*lru,
	spinlock_t		*lru_lock,
	void			*arg)
{
	struct xfs_buf		*bp = container_of(item, struct xfs_buf, b_lru);
	struct list_head	*dispose = arg;

	/*
	 * we are inverting the lru lock/bp->b_lock here, so use a trylock.
	 * If we fail to get the lock, just skip it.
	 */
	if (!spin_trylock(&bp->b_lock))
		return LRU_SKIP;
	/*
	 * Decrement the b_lru_ref count unless the value is already
	 * zero. If the value is already zero, we need to reclaim the
	 * buffer, otherwise it gets another trip through the LRU.
	 */
	if (!atomic_add_unless(&bp->b_lru_ref, -1, 0)) {
		spin_unlock(&bp->b_lock);
		return LRU_ROTATE;
	}

	bp->b_state |= XFS_BSTATE_DISPOSE;
	list_lru_isolate_move(lru, item, dispose);
	spin_unlock(&bp->b_lock);
	return LRU_REMOVED;
}

static unsigned long
xfs_buftarg_shrink_scan(
	struct shrinker		*shrink,
	struct shrink_control	*sc)
{
	struct xfs_buftarg	*btp = container_of(shrink,
					struct xfs_buftarg, bt_shrinker);
	LIST_HEAD(dispose);
	unsigned long		freed;

	freed = list_lru_shrink_walk(&btp->bt_lru, sc,
				     xfs_buftarg_isolate, &dispose);

	while (!list_empty(&dispose)) {
		struct xfs_buf *bp;
		bp = list_first_entry(&dispose, struct xfs_buf, b_lru);
		list_del_init(&bp->b_lru);
		xfs_buf_rele(bp);
	}

	return freed;
}

static unsigned long
xfs_buftarg_shrink_count(
	struct shrinker		*shrink,
	struct shrink_control	*sc)
{
	struct xfs_buftarg	*btp = container_of(shrink,
					struct xfs_buftarg, bt_shrinker);
	return list_lru_shrink_count(&btp->bt_lru, sc);
}

void
xfs_free_buftarg(
	struct xfs_mount	*mp,
	struct xfs_buftarg	*btp)
{
	unregister_shrinker(&btp->bt_shrinker);
	list_lru_destroy(&btp->bt_lru);

	if (mp->m_flags & XFS_MOUNT_BARRIER)
		xfs_blkdev_issue_flush(btp);

	kmem_free(btp);
}

int
xfs_setsize_buftarg(
	xfs_buftarg_t		*btp,
	unsigned int		sectorsize)
{
	/* Set up metadata sector size info */
	btp->bt_meta_sectorsize = sectorsize;
	btp->bt_meta_sectormask = sectorsize - 1;

	if (set_blocksize(btp->bt_bdev, sectorsize)) {
		char name[BDEVNAME_SIZE];

		bdevname(btp->bt_bdev, name);

		xfs_warn(btp->bt_mount,
			"Cannot set_blocksize to %u on device %s",
			sectorsize, name);
		return -EINVAL;
	}

	/* Set up device logical sector size mask */
	btp->bt_logical_sectorsize = bdev_logical_block_size(btp->bt_bdev);
	btp->bt_logical_sectormask = bdev_logical_block_size(btp->bt_bdev) - 1;

	return 0;
}

/*
 * When allocating the initial buffer target we have not yet
 * read in the superblock, so don't know what sized sectors
 * are being used at this early stage.  Play safe.
 */
STATIC int
xfs_setsize_buftarg_early(
	xfs_buftarg_t		*btp,
	struct block_device	*bdev)
{
	return xfs_setsize_buftarg(btp, bdev_logical_block_size(bdev));
}

xfs_buftarg_t *
xfs_alloc_buftarg(
	struct xfs_mount	*mp,
	struct block_device	*bdev)
{
	xfs_buftarg_t		*btp;

	btp = kmem_zalloc(sizeof(*btp), KM_SLEEP | KM_NOFS);

	btp->bt_mount = mp;
	btp->bt_dev =  bdev->bd_dev;
	btp->bt_bdev = bdev;
	btp->bt_bdi = blk_get_backing_dev_info(bdev);

	if (xfs_setsize_buftarg_early(btp, bdev))
		goto error;

	if (list_lru_init(&btp->bt_lru))
		goto error;

	btp->bt_shrinker.count_objects = xfs_buftarg_shrink_count;
	btp->bt_shrinker.scan_objects = xfs_buftarg_shrink_scan;
	btp->bt_shrinker.seeks = DEFAULT_SEEKS;
	btp->bt_shrinker.flags = SHRINKER_NUMA_AWARE;
	register_shrinker(&btp->bt_shrinker);
	return btp;

error:
	kmem_free(btp);
	return NULL;
}

/*
 * Cancel a delayed write list.
 *
 * Remove each buffer from the list, clear the delwri queue flag and drop the
 * associated buffer reference.
 */
void
xfs_buf_delwri_cancel(
	struct list_head	*list)
{
	struct xfs_buf		*bp;

	while (!list_empty(list)) {
		bp = list_first_entry(list, struct xfs_buf, b_list);

		xfs_buf_lock(bp);
		bp->b_flags &= ~_XBF_DELWRI_Q;
		list_del_init(&bp->b_list);
		xfs_buf_relse(bp);
	}
}

/*
 * Add a buffer to the delayed write list.
 *
 * This queues a buffer for writeout if it hasn't already been.  Note that
 * neither this routine nor the buffer list submission functions perform
 * any internal synchronization.  It is expected that the lists are thread-local
 * to the callers.
 *
 * Returns true if we queued up the buffer, or false if it already had
 * been on the buffer list.
 */
bool
xfs_buf_delwri_queue(
	struct xfs_buf		*bp,
	struct list_head	*list)
{
	ASSERT(xfs_buf_islocked(bp));
	ASSERT(!(bp->b_flags & XBF_READ));

	/*
	 * If the buffer is already marked delwri it already is queued up
	 * by someone else for imediate writeout.  Just ignore it in that
	 * case.
	 */
	if (bp->b_flags & _XBF_DELWRI_Q) {
		trace_xfs_buf_delwri_queued(bp, _RET_IP_);
		return false;
	}

	trace_xfs_buf_delwri_queue(bp, _RET_IP_);

	/*
	 * If a buffer gets written out synchronously or marked stale while it
	 * is on a delwri list we lazily remove it. To do this, the other party
	 * clears the  _XBF_DELWRI_Q flag but otherwise leaves the buffer alone.
	 * It remains referenced and on the list.  In a rare corner case it
	 * might get readded to a delwri list after the synchronous writeout, in
	 * which case we need just need to re-add the flag here.
	 */
	bp->b_flags |= _XBF_DELWRI_Q;
	if (list_empty(&bp->b_list)) {
		atomic_inc(&bp->b_hold);
		list_add_tail(&bp->b_list, list);
	}

	return true;
}

/*
 * Compare function is more complex than it needs to be because
 * the return value is only 32 bits and we are doing comparisons
 * on 64 bit values
 */
static int
xfs_buf_cmp(
	void		*priv,
	struct list_head *a,
	struct list_head *b)
{
	struct xfs_buf	*ap = container_of(a, struct xfs_buf, b_list);
	struct xfs_buf	*bp = container_of(b, struct xfs_buf, b_list);
	xfs_daddr_t		diff;

	diff = ap->b_maps[0].bm_bn - bp->b_maps[0].bm_bn;
	if (diff < 0)
		return -1;
	if (diff > 0)
		return 1;
	return 0;
}

static int
__xfs_buf_delwri_submit(
	struct list_head	*buffer_list,
	struct list_head	*io_list,
	bool			wait)
{
	struct blk_plug		plug;
	struct xfs_buf		*bp, *n;
	int			pinned = 0;

	list_for_each_entry_safe(bp, n, buffer_list, b_list) {
		if (!wait) {
			if (xfs_buf_ispinned(bp)) {
				pinned++;
				continue;
			}
			if (!xfs_buf_trylock(bp))
				continue;
		} else {
			xfs_buf_lock(bp);
		}

		/*
		 * Someone else might have written the buffer synchronously or
		 * marked it stale in the meantime.  In that case only the
		 * _XBF_DELWRI_Q flag got cleared, and we have to drop the
		 * reference and remove it from the list here.
		 */
		if (!(bp->b_flags & _XBF_DELWRI_Q)) {
			list_del_init(&bp->b_list);
			xfs_buf_relse(bp);
			continue;
		}

		list_move_tail(&bp->b_list, io_list);
		trace_xfs_buf_delwri_split(bp, _RET_IP_);
	}

	list_sort(NULL, io_list, xfs_buf_cmp);

	blk_start_plug(&plug);
	list_for_each_entry_safe(bp, n, io_list, b_list) {
		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_ASYNC | XBF_WRITE_FAIL);
		bp->b_flags |= XBF_WRITE | XBF_ASYNC;

		/*
		 * we do all Io submission async. This means if we need to wait
		 * for IO completion we need to take an extra reference so the
		 * buffer is still valid on the other side.
		 */
		if (wait)
			xfs_buf_hold(bp);
		else
			list_del_init(&bp->b_list);

		xfs_buf_submit(bp);
	}
	blk_finish_plug(&plug);

	return pinned;
}

/*
 * Write out a buffer list asynchronously.
 *
 * This will take the @buffer_list, write all non-locked and non-pinned buffers
 * out and not wait for I/O completion on any of the buffers.  This interface
 * is only safely useable for callers that can track I/O completion by higher
 * level means, e.g. AIL pushing as the @buffer_list is consumed in this
 * function.
 */
int
xfs_buf_delwri_submit_nowait(
	struct list_head	*buffer_list)
{
	LIST_HEAD		(io_list);
	return __xfs_buf_delwri_submit(buffer_list, &io_list, false);
}

/*
 * Write out a buffer list synchronously.
 *
 * This will take the @buffer_list, write all buffers out and wait for I/O
 * completion on all of the buffers. @buffer_list is consumed by the function,
 * so callers must have some other way of tracking buffers if they require such
 * functionality.
 */
int
xfs_buf_delwri_submit(
	struct list_head	*buffer_list)
{
	LIST_HEAD		(io_list);
	int			error = 0, error2;
	struct xfs_buf		*bp;

	__xfs_buf_delwri_submit(buffer_list, &io_list, true);

	/* Wait for IO to complete. */
	while (!list_empty(&io_list)) {
		bp = list_first_entry(&io_list, struct xfs_buf, b_list);

		list_del_init(&bp->b_list);

		/* locking the buffer will wait for async IO completion. */
		xfs_buf_lock(bp);
		error2 = bp->b_error;
		xfs_buf_relse(bp);
		if (!error)
			error = error2;
	}

	return error;
}

int __init
xfs_buf_init(void)
{
	xfs_buf_zone = kmem_zone_init_flags(sizeof(xfs_buf_t), "xfs_buf",
						KM_ZONE_HWALIGN, NULL);
	if (!xfs_buf_zone)
		goto out;

	return 0;

 out:
	return -ENOMEM;
}

void
xfs_buf_terminate(void)
{
	kmem_zone_destroy(xfs_buf_zone);
}