summaryrefslogtreecommitdiffstats
path: root/fs/nfs/write.c
blob: d09c9f878141a5c4213aef1faccb85b979bf4793 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
/*
 * linux/fs/nfs/write.c
 *
 * Write file data over NFS.
 *
 * Copyright (C) 1996, 1997, Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/types.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/migrate.h>

#include <linux/sunrpc/clnt.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/backing-dev.h>
#include <linux/export.h>
#include <linux/freezer.h>
#include <linux/wait.h>
#include <linux/iversion.h>

#include <linux/uaccess.h>

#include "delegation.h"
#include "internal.h"
#include "iostat.h"
#include "nfs4_fs.h"
#include "fscache.h"
#include "pnfs.h"

#include "nfstrace.h"

#define NFSDBG_FACILITY		NFSDBG_PAGECACHE

#define MIN_POOL_WRITE		(32)
#define MIN_POOL_COMMIT		(4)

struct nfs_io_completion {
	void (*complete)(void *data);
	void *data;
	struct kref refcount;
};

/*
 * Local function declarations
 */
static void nfs_redirty_request(struct nfs_page *req);
static const struct rpc_call_ops nfs_commit_ops;
static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops;
static const struct nfs_commit_completion_ops nfs_commit_completion_ops;
static const struct nfs_rw_ops nfs_rw_write_ops;
static void nfs_clear_request_commit(struct nfs_page *req);
static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
				      struct inode *inode);
static struct nfs_page *
nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
						struct page *page);

static struct kmem_cache *nfs_wdata_cachep;
static mempool_t *nfs_wdata_mempool;
static struct kmem_cache *nfs_cdata_cachep;
static mempool_t *nfs_commit_mempool;

struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail)
{
	struct nfs_commit_data *p;

	if (never_fail)
		p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
	else {
		/* It is OK to do some reclaim, not no safe to wait
		 * for anything to be returned to the pool.
		 * mempool_alloc() cannot handle that particular combination,
		 * so we need two separate attempts.
		 */
		p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT);
		if (!p)
			p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO |
					     __GFP_NOWARN | __GFP_NORETRY);
		if (!p)
			return NULL;
	}

	memset(p, 0, sizeof(*p));
	INIT_LIST_HEAD(&p->pages);
	return p;
}
EXPORT_SYMBOL_GPL(nfs_commitdata_alloc);

void nfs_commit_free(struct nfs_commit_data *p)
{
	mempool_free(p, nfs_commit_mempool);
}
EXPORT_SYMBOL_GPL(nfs_commit_free);

static struct nfs_pgio_header *nfs_writehdr_alloc(void)
{
	struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);

	memset(p, 0, sizeof(*p));
	p->rw_mode = FMODE_WRITE;
	return p;
}

static void nfs_writehdr_free(struct nfs_pgio_header *hdr)
{
	mempool_free(hdr, nfs_wdata_mempool);
}

static struct nfs_io_completion *nfs_io_completion_alloc(gfp_t gfp_flags)
{
	return kmalloc(sizeof(struct nfs_io_completion), gfp_flags);
}

static void nfs_io_completion_init(struct nfs_io_completion *ioc,
		void (*complete)(void *), void *data)
{
	ioc->complete = complete;
	ioc->data = data;
	kref_init(&ioc->refcount);
}

static void nfs_io_completion_release(struct kref *kref)
{
	struct nfs_io_completion *ioc = container_of(kref,
			struct nfs_io_completion, refcount);
	ioc->complete(ioc->data);
	kfree(ioc);
}

static void nfs_io_completion_get(struct nfs_io_completion *ioc)
{
	if (ioc != NULL)
		kref_get(&ioc->refcount);
}

static void nfs_io_completion_put(struct nfs_io_completion *ioc)
{
	if (ioc != NULL)
		kref_put(&ioc->refcount, nfs_io_completion_release);
}

static struct nfs_page *
nfs_page_private_request(struct page *page)
{
	if (!PagePrivate(page))
		return NULL;
	return (struct nfs_page *)page_private(page);
}

/*
 * nfs_page_find_head_request_locked - find head request associated with @page
 *
 * must be called while holding the inode lock.
 *
 * returns matching head request with reference held, or NULL if not found.
 */
static struct nfs_page *
nfs_page_find_private_request(struct page *page)
{
	struct address_space *mapping = page_file_mapping(page);
	struct nfs_page *req;

	if (!PagePrivate(page))
		return NULL;
	spin_lock(&mapping->private_lock);
	req = nfs_page_private_request(page);
	if (req) {
		WARN_ON_ONCE(req->wb_head != req);
		kref_get(&req->wb_kref);
	}
	spin_unlock(&mapping->private_lock);
	return req;
}

static struct nfs_page *
nfs_page_find_swap_request(struct page *page)
{
	struct inode *inode = page_file_mapping(page)->host;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_page *req = NULL;
	if (!PageSwapCache(page))
		return NULL;
	mutex_lock(&nfsi->commit_mutex);
	if (PageSwapCache(page)) {
		req = nfs_page_search_commits_for_head_request_locked(nfsi,
			page);
		if (req) {
			WARN_ON_ONCE(req->wb_head != req);
			kref_get(&req->wb_kref);
		}
	}
	mutex_unlock(&nfsi->commit_mutex);
	return req;
}

/*
 * nfs_page_find_head_request - find head request associated with @page
 *
 * returns matching head request with reference held, or NULL if not found.
 */
static struct nfs_page *nfs_page_find_head_request(struct page *page)
{
	struct nfs_page *req;

	req = nfs_page_find_private_request(page);
	if (!req)
		req = nfs_page_find_swap_request(page);
	return req;
}

/* Adjust the file length if we're writing beyond the end */
static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
{
	struct inode *inode = page_file_mapping(page)->host;
	loff_t end, i_size;
	pgoff_t end_index;

	spin_lock(&inode->i_lock);
	i_size = i_size_read(inode);
	end_index = (i_size - 1) >> PAGE_SHIFT;
	if (i_size > 0 && page_index(page) < end_index)
		goto out;
	end = page_file_offset(page) + ((loff_t)offset+count);
	if (i_size >= end)
		goto out;
	i_size_write(inode, end);
	NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
	nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
out:
	spin_unlock(&inode->i_lock);
}

/* A writeback failed: mark the page as bad, and invalidate the page cache */
static void nfs_set_pageerror(struct address_space *mapping)
{
	nfs_zap_mapping(mapping->host, mapping);
}

/*
 * nfs_page_group_search_locked
 * @head - head request of page group
 * @page_offset - offset into page
 *
 * Search page group with head @head to find a request that contains the
 * page offset @page_offset.
 *
 * Returns a pointer to the first matching nfs request, or NULL if no
 * match is found.
 *
 * Must be called with the page group lock held
 */
static struct nfs_page *
nfs_page_group_search_locked(struct nfs_page *head, unsigned int page_offset)
{
	struct nfs_page *req;

	req = head;
	do {
		if (page_offset >= req->wb_pgbase &&
		    page_offset < (req->wb_pgbase + req->wb_bytes))
			return req;

		req = req->wb_this_page;
	} while (req != head);

	return NULL;
}

/*
 * nfs_page_group_covers_page
 * @head - head request of page group
 *
 * Return true if the page group with head @head covers the whole page,
 * returns false otherwise
 */
static bool nfs_page_group_covers_page(struct nfs_page *req)
{
	struct nfs_page *tmp;
	unsigned int pos = 0;
	unsigned int len = nfs_page_length(req->wb_page);

	nfs_page_group_lock(req);

	for (;;) {
		tmp = nfs_page_group_search_locked(req->wb_head, pos);
		if (!tmp)
			break;
		pos = tmp->wb_pgbase + tmp->wb_bytes;
	}

	nfs_page_group_unlock(req);
	return pos >= len;
}

/* We can set the PG_uptodate flag if we see that a write request
 * covers the full page.
 */
static void nfs_mark_uptodate(struct nfs_page *req)
{
	if (PageUptodate(req->wb_page))
		return;
	if (!nfs_page_group_covers_page(req))
		return;
	SetPageUptodate(req->wb_page);
}

static int wb_priority(struct writeback_control *wbc)
{
	int ret = 0;

	if (wbc->sync_mode == WB_SYNC_ALL)
		ret = FLUSH_COND_STABLE;
	return ret;
}

/*
 * NFS congestion control
 */

int nfs_congestion_kb;

#define NFS_CONGESTION_ON_THRESH 	(nfs_congestion_kb >> (PAGE_SHIFT-10))
#define NFS_CONGESTION_OFF_THRESH	\
	(NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2))

static void nfs_set_page_writeback(struct page *page)
{
	struct inode *inode = page_file_mapping(page)->host;
	struct nfs_server *nfss = NFS_SERVER(inode);
	int ret = test_set_page_writeback(page);

	WARN_ON_ONCE(ret != 0);

	if (atomic_long_inc_return(&nfss->writeback) >
			NFS_CONGESTION_ON_THRESH)
		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
}

static void nfs_end_page_writeback(struct nfs_page *req)
{
	struct inode *inode = page_file_mapping(req->wb_page)->host;
	struct nfs_server *nfss = NFS_SERVER(inode);
	bool is_done;

	is_done = nfs_page_group_sync_on_bit(req, PG_WB_END);
	nfs_unlock_request(req);
	if (!is_done)
		return;

	end_page_writeback(req->wb_page);
	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
		clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
}

/*
 * nfs_unroll_locks_and_wait -  unlock all newly locked reqs and wait on @req
 *
 * this is a helper function for nfs_lock_and_join_requests
 *
 * @inode - inode associated with request page group, must be holding inode lock
 * @head  - head request of page group, must be holding head lock
 * @req   - request that couldn't lock and needs to wait on the req bit lock
 *
 * NOTE: this must be called holding page_group bit lock
 *       which will be released before returning.
 *
 * returns 0 on success, < 0 on error.
 */
static void
nfs_unroll_locks(struct inode *inode, struct nfs_page *head,
			  struct nfs_page *req)
{
	struct nfs_page *tmp;

	/* relinquish all the locks successfully grabbed this run */
	for (tmp = head->wb_this_page ; tmp != req; tmp = tmp->wb_this_page) {
		if (!kref_read(&tmp->wb_kref))
			continue;
		nfs_unlock_and_release_request(tmp);
	}
}

/*
 * nfs_destroy_unlinked_subrequests - destroy recently unlinked subrequests
 *
 * @destroy_list - request list (using wb_this_page) terminated by @old_head
 * @old_head - the old head of the list
 *
 * All subrequests must be locked and removed from all lists, so at this point
 * they are only "active" in this function, and possibly in nfs_wait_on_request
 * with a reference held by some other context.
 */
static void
nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list,
				 struct nfs_page *old_head,
				 struct inode *inode)
{
	while (destroy_list) {
		struct nfs_page *subreq = destroy_list;

		destroy_list = (subreq->wb_this_page == old_head) ?
				   NULL : subreq->wb_this_page;

		WARN_ON_ONCE(old_head != subreq->wb_head);

		/* make sure old group is not used */
		subreq->wb_this_page = subreq;

		clear_bit(PG_REMOVE, &subreq->wb_flags);

		/* Note: races with nfs_page_group_destroy() */
		if (!kref_read(&subreq->wb_kref)) {
			/* Check if we raced with nfs_page_group_destroy() */
			if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags))
				nfs_free_request(subreq);
			continue;
		}

		subreq->wb_head = subreq;

		if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) {
			nfs_release_request(subreq);
			atomic_long_dec(&NFS_I(inode)->nrequests);
		}

		/* subreq is now totally disconnected from page group or any
		 * write / commit lists. last chance to wake any waiters */
		nfs_unlock_and_release_request(subreq);
	}
}

/*
 * nfs_lock_and_join_requests - join all subreqs to the head req and return
 *                              a locked reference, cancelling any pending
 *                              operations for this page.
 *
 * @page - the page used to lookup the "page group" of nfs_page structures
 *
 * This function joins all sub requests to the head request by first
 * locking all requests in the group, cancelling any pending operations
 * and finally updating the head request to cover the whole range covered by
 * the (former) group.  All subrequests are removed from any write or commit
 * lists, unlinked from the group and destroyed.
 *
 * Returns a locked, referenced pointer to the head request - which after
 * this call is guaranteed to be the only request associated with the page.
 * Returns NULL if no requests are found for @page, or a ERR_PTR if an
 * error was encountered.
 */
static struct nfs_page *
nfs_lock_and_join_requests(struct page *page)
{
	struct inode *inode = page_file_mapping(page)->host;
	struct nfs_page *head, *subreq;
	struct nfs_page *destroy_list = NULL;
	unsigned int total_bytes;
	int ret;

try_again:
	/*
	 * A reference is taken only on the head request which acts as a
	 * reference to the whole page group - the group will not be destroyed
	 * until the head reference is released.
	 */
	head = nfs_page_find_head_request(page);
	if (!head)
		return NULL;

	/* lock the page head first in order to avoid an ABBA inefficiency */
	if (!nfs_lock_request(head)) {
		ret = nfs_wait_on_request(head);
		nfs_release_request(head);
		if (ret < 0)
			return ERR_PTR(ret);
		goto try_again;
	}

	/* Ensure that nobody removed the request before we locked it */
	if (head != nfs_page_private_request(page) && !PageSwapCache(page)) {
		nfs_unlock_and_release_request(head);
		goto try_again;
	}

	ret = nfs_page_group_lock(head);
	if (ret < 0)
		goto release_request;

	/* lock each request in the page group */
	total_bytes = head->wb_bytes;
	for (subreq = head->wb_this_page; subreq != head;
			subreq = subreq->wb_this_page) {

		if (!kref_get_unless_zero(&subreq->wb_kref)) {
			if (subreq->wb_offset == head->wb_offset + total_bytes)
				total_bytes += subreq->wb_bytes;
			continue;
		}

		while (!nfs_lock_request(subreq)) {
			/*
			 * Unlock page to allow nfs_page_group_sync_on_bit()
			 * to succeed
			 */
			nfs_page_group_unlock(head);
			ret = nfs_wait_on_request(subreq);
			if (!ret)
				ret = nfs_page_group_lock(head);
			if (ret < 0) {
				nfs_unroll_locks(inode, head, subreq);
				nfs_release_request(subreq);
				goto release_request;
			}
		}
		/*
		 * Subrequests are always contiguous, non overlapping
		 * and in order - but may be repeated (mirrored writes).
		 */
		if (subreq->wb_offset == (head->wb_offset + total_bytes)) {
			/* keep track of how many bytes this group covers */
			total_bytes += subreq->wb_bytes;
		} else if (WARN_ON_ONCE(subreq->wb_offset < head->wb_offset ||
			    ((subreq->wb_offset + subreq->wb_bytes) >
			     (head->wb_offset + total_bytes)))) {
			nfs_page_group_unlock(head);
			nfs_unroll_locks(inode, head, subreq);
			nfs_unlock_and_release_request(subreq);
			ret = -EIO;
			goto release_request;
		}
	}

	/* Now that all requests are locked, make sure they aren't on any list.
	 * Commit list removal accounting is done after locks are dropped */
	subreq = head;
	do {
		nfs_clear_request_commit(subreq);
		subreq = subreq->wb_this_page;
	} while (subreq != head);

	/* unlink subrequests from head, destroy them later */
	if (head->wb_this_page != head) {
		/* destroy list will be terminated by head */
		destroy_list = head->wb_this_page;
		head->wb_this_page = head;

		/* change head request to cover whole range that
		 * the former page group covered */
		head->wb_bytes = total_bytes;
	}

	/* Postpone destruction of this request */
	if (test_and_clear_bit(PG_REMOVE, &head->wb_flags)) {
		set_bit(PG_INODE_REF, &head->wb_flags);
		kref_get(&head->wb_kref);
		atomic_long_inc(&NFS_I(inode)->nrequests);
	}

	nfs_page_group_unlock(head);

	nfs_destroy_unlinked_subrequests(destroy_list, head, inode);

	/* Did we lose a race with nfs_inode_remove_request()? */
	if (!(PagePrivate(page) || PageSwapCache(page))) {
		nfs_unlock_and_release_request(head);
		return NULL;
	}

	/* still holds ref on head from nfs_page_find_head_request
	 * and still has lock on head from lock loop */
	return head;

release_request:
	nfs_unlock_and_release_request(head);
	return ERR_PTR(ret);
}

static void nfs_write_error_remove_page(struct nfs_page *req)
{
	nfs_end_page_writeback(req);
	generic_error_remove_page(page_file_mapping(req->wb_page),
				  req->wb_page);
	nfs_release_request(req);
}

static bool
nfs_error_is_fatal_on_server(int err)
{
	switch (err) {
	case 0:
	case -ERESTARTSYS:
	case -EINTR:
		return false;
	}
	return nfs_error_is_fatal(err);
}

/*
 * Find an associated nfs write request, and prepare to flush it out
 * May return an error if the user signalled nfs_wait_on_request().
 */
static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
				struct page *page)
{
	struct nfs_page *req;
	int ret = 0;

	req = nfs_lock_and_join_requests(page);
	if (!req)
		goto out;
	ret = PTR_ERR(req);
	if (IS_ERR(req))
		goto out;

	nfs_set_page_writeback(page);
	WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));

	ret = req->wb_context->error;
	/* If there is a fatal error that covers this write, just exit */
	if (nfs_error_is_fatal_on_server(ret))
		goto out_launder;

	ret = 0;
	if (!nfs_pageio_add_request(pgio, req)) {
		ret = pgio->pg_error;
		/*
		 * Remove the problematic req upon fatal errors on the server
		 */
		if (nfs_error_is_fatal(ret)) {
			nfs_context_set_write_error(req->wb_context, ret);
			if (nfs_error_is_fatal_on_server(ret))
				goto out_launder;
		} else
			ret = -EAGAIN;
		nfs_redirty_request(req);
	} else
		nfs_add_stats(page_file_mapping(page)->host,
				NFSIOS_WRITEPAGES, 1);
out:
	return ret;
out_launder:
	nfs_write_error_remove_page(req);
	return ret;
}

static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
			    struct nfs_pageio_descriptor *pgio)
{
	int ret;

	nfs_pageio_cond_complete(pgio, page_index(page));
	ret = nfs_page_async_flush(pgio, page);
	if (ret == -EAGAIN) {
		redirty_page_for_writepage(wbc, page);
		ret = 0;
	}
	return ret;
}

/*
 * Write an mmapped page to the server.
 */
static int nfs_writepage_locked(struct page *page,
				struct writeback_control *wbc)
{
	struct nfs_pageio_descriptor pgio;
	struct inode *inode = page_file_mapping(page)->host;
	int err;

	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
	nfs_pageio_init_write(&pgio, inode, 0,
				false, &nfs_async_write_completion_ops);
	err = nfs_do_writepage(page, wbc, &pgio);
	nfs_pageio_complete(&pgio);
	if (err < 0)
		return err;
	if (pgio.pg_error < 0)
		return pgio.pg_error;
	return 0;
}

int nfs_writepage(struct page *page, struct writeback_control *wbc)
{
	int ret;

	ret = nfs_writepage_locked(page, wbc);
	unlock_page(page);
	return ret;
}

static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data)
{
	int ret;

	ret = nfs_do_writepage(page, wbc, data);
	unlock_page(page);
	return ret;
}

static void nfs_io_completion_commit(void *inode)
{
	nfs_commit_inode(inode, 0);
}

int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct nfs_pageio_descriptor pgio;
	struct nfs_io_completion *ioc = nfs_io_completion_alloc(GFP_NOFS);
	int err;

	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);

	if (ioc)
		nfs_io_completion_init(ioc, nfs_io_completion_commit, inode);

	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false,
				&nfs_async_write_completion_ops);
	pgio.pg_io_completion = ioc;
	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
	nfs_pageio_complete(&pgio);
	nfs_io_completion_put(ioc);

	if (err < 0)
		goto out_err;
	err = pgio.pg_error;
	if (err < 0)
		goto out_err;
	return 0;
out_err:
	return err;
}

/*
 * Insert a write request into an inode
 */
static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
{
	struct address_space *mapping = page_file_mapping(req->wb_page);
	struct nfs_inode *nfsi = NFS_I(inode);

	WARN_ON_ONCE(req->wb_this_page != req);

	/* Lock the request! */
	nfs_lock_request(req);

	/*
	 * Swap-space should not get truncated. Hence no need to plug the race
	 * with invalidate/truncate.
	 */
	spin_lock(&mapping->private_lock);
	if (!nfs_have_writebacks(inode) &&
	    NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
		inode_inc_iversion_raw(inode);
	if (likely(!PageSwapCache(req->wb_page))) {
		set_bit(PG_MAPPED, &req->wb_flags);
		SetPagePrivate(req->wb_page);
		set_page_private(req->wb_page, (unsigned long)req);
	}
	spin_unlock(&mapping->private_lock);
	atomic_long_inc(&nfsi->nrequests);
	/* this a head request for a page group - mark it as having an
	 * extra reference so sub groups can follow suit.
	 * This flag also informs pgio layer when to bump nrequests when
	 * adding subrequests. */
	WARN_ON(test_and_set_bit(PG_INODE_REF, &req->wb_flags));
	kref_get(&req->wb_kref);
}

/*
 * Remove a write request from an inode
 */
static void nfs_inode_remove_request(struct nfs_page *req)
{
	struct address_space *mapping = page_file_mapping(req->wb_page);
	struct inode *inode = mapping->host;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_page *head;

	atomic_long_dec(&nfsi->nrequests);
	if (nfs_page_group_sync_on_bit(req, PG_REMOVE)) {
		head = req->wb_head;

		spin_lock(&mapping->private_lock);
		if (likely(head->wb_page && !PageSwapCache(head->wb_page))) {
			set_page_private(head->wb_page, 0);
			ClearPagePrivate(head->wb_page);
			clear_bit(PG_MAPPED, &head->wb_flags);
		}
		spin_unlock(&mapping->private_lock);
	}

	if (test_and_clear_bit(PG_INODE_REF, &req->wb_flags))
		nfs_release_request(req);
}

static void
nfs_mark_request_dirty(struct nfs_page *req)
{
	if (req->wb_page)
		__set_page_dirty_nobuffers(req->wb_page);
}

/*
 * nfs_page_search_commits_for_head_request_locked
 *
 * Search through commit lists on @inode for the head request for @page.
 * Must be called while holding the inode (which is cinfo) lock.
 *
 * Returns the head request if found, or NULL if not found.
 */
static struct nfs_page *
nfs_page_search_commits_for_head_request_locked(struct nfs_inode *nfsi,
						struct page *page)
{
	struct nfs_page *freq, *t;
	struct nfs_commit_info cinfo;
	struct inode *inode = &nfsi->vfs_inode;

	nfs_init_cinfo_from_inode(&cinfo, inode);

	/* search through pnfs commit lists */
	freq = pnfs_search_commit_reqs(inode, &cinfo, page);
	if (freq)
		return freq->wb_head;

	/* Linearly search the commit list for the correct request */
	list_for_each_entry_safe(freq, t, &cinfo.mds->list, wb_list) {
		if (freq->wb_page == page)
			return freq->wb_head;
	}

	return NULL;
}

/**
 * nfs_request_add_commit_list_locked - add request to a commit list
 * @req: pointer to a struct nfs_page
 * @dst: commit list head
 * @cinfo: holds list lock and accounting info
 *
 * This sets the PG_CLEAN bit, updates the cinfo count of
 * number of outstanding requests requiring a commit as well as
 * the MM page stats.
 *
 * The caller must hold NFS_I(cinfo->inode)->commit_mutex, and the
 * nfs_page lock.
 */
void
nfs_request_add_commit_list_locked(struct nfs_page *req, struct list_head *dst,
			    struct nfs_commit_info *cinfo)
{
	set_bit(PG_CLEAN, &req->wb_flags);
	nfs_list_add_request(req, dst);
	atomic_long_inc(&cinfo->mds->ncommit);
}
EXPORT_SYMBOL_GPL(nfs_request_add_commit_list_locked);

/**
 * nfs_request_add_commit_list - add request to a commit list
 * @req: pointer to a struct nfs_page
 * @dst: commit list head
 * @cinfo: holds list lock and accounting info
 *
 * This sets the PG_CLEAN bit, updates the cinfo count of
 * number of outstanding requests requiring a commit as well as
 * the MM page stats.
 *
 * The caller must _not_ hold the cinfo->lock, but must be
 * holding the nfs_page lock.
 */
void
nfs_request_add_commit_list(struct nfs_page *req, struct nfs_commit_info *cinfo)
{
	mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
	nfs_request_add_commit_list_locked(req, &cinfo->mds->list, cinfo);
	mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
	if (req->wb_page)
		nfs_mark_page_unstable(req->wb_page, cinfo);
}
EXPORT_SYMBOL_GPL(nfs_request_add_commit_list);

/**
 * nfs_request_remove_commit_list - Remove request from a commit list
 * @req: pointer to a nfs_page
 * @cinfo: holds list lock and accounting info
 *
 * This clears the PG_CLEAN bit, and updates the cinfo's count of
 * number of outstanding requests requiring a commit
 * It does not update the MM page stats.
 *
 * The caller _must_ hold the cinfo->lock and the nfs_page lock.
 */
void
nfs_request_remove_commit_list(struct nfs_page *req,
			       struct nfs_commit_info *cinfo)
{
	if (!test_and_clear_bit(PG_CLEAN, &(req)->wb_flags))
		return;
	nfs_list_remove_request(req);
	atomic_long_dec(&cinfo->mds->ncommit);
}
EXPORT_SYMBOL_GPL(nfs_request_remove_commit_list);

static void nfs_init_cinfo_from_inode(struct nfs_commit_info *cinfo,
				      struct inode *inode)
{
	cinfo->inode = inode;
	cinfo->mds = &NFS_I(inode)->commit_info;
	cinfo->ds = pnfs_get_ds_info(inode);
	cinfo->dreq = NULL;
	cinfo->completion_ops = &nfs_commit_completion_ops;
}

void nfs_init_cinfo(struct nfs_commit_info *cinfo,
		    struct inode *inode,
		    struct nfs_direct_req *dreq)
{
	if (dreq)
		nfs_init_cinfo_from_dreq(cinfo, dreq);
	else
		nfs_init_cinfo_from_inode(cinfo, inode);
}
EXPORT_SYMBOL_GPL(nfs_init_cinfo);

/*
 * Add a request to the inode's commit list.
 */
void
nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg,
			struct nfs_commit_info *cinfo, u32 ds_commit_idx)
{
	if (pnfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx))
		return;
	nfs_request_add_commit_list(req, cinfo);
}

static void
nfs_clear_page_commit(struct page *page)
{
	dec_node_page_state(page, NR_UNSTABLE_NFS);
	dec_wb_stat(&inode_to_bdi(page_file_mapping(page)->host)->wb,
		    WB_RECLAIMABLE);
}

/* Called holding the request lock on @req */
static void
nfs_clear_request_commit(struct nfs_page *req)
{
	if (test_bit(PG_CLEAN, &req->wb_flags)) {
		struct inode *inode = d_inode(req->wb_context->dentry);
		struct nfs_commit_info cinfo;

		nfs_init_cinfo_from_inode(&cinfo, inode);
		mutex_lock(&NFS_I(inode)->commit_mutex);
		if (!pnfs_clear_request_commit(req, &cinfo)) {
			nfs_request_remove_commit_list(req, &cinfo);
		}
		mutex_unlock(&NFS_I(inode)->commit_mutex);
		nfs_clear_page_commit(req->wb_page);
	}
}

int nfs_write_need_commit(struct nfs_pgio_header *hdr)
{
	if (hdr->verf.committed == NFS_DATA_SYNC)
		return hdr->lseg == NULL;
	return hdr->verf.committed != NFS_FILE_SYNC;
}

static void nfs_async_write_init(struct nfs_pgio_header *hdr)
{
	nfs_io_completion_get(hdr->io_completion);
}

static void nfs_write_completion(struct nfs_pgio_header *hdr)
{
	struct nfs_commit_info cinfo;
	unsigned long bytes = 0;

	if (test_bit(NFS_IOHDR_REDO, &hdr->flags))
		goto out;
	nfs_init_cinfo_from_inode(&cinfo, hdr->inode);
	while (!list_empty(&hdr->pages)) {
		struct nfs_page *req = nfs_list_entry(hdr->pages.next);

		bytes += req->wb_bytes;
		nfs_list_remove_request(req);
		if (test_bit(NFS_IOHDR_ERROR, &hdr->flags) &&
		    (hdr->good_bytes < bytes)) {
			nfs_set_pageerror(page_file_mapping(req->wb_page));
			nfs_context_set_write_error(req->wb_context, hdr->error);
			goto remove_req;
		}
		if (nfs_write_need_commit(hdr)) {
			memcpy(&req->wb_verf, &hdr->verf.verifier, sizeof(req->wb_verf));
			nfs_mark_request_commit(req, hdr->lseg, &cinfo,
				hdr->pgio_mirror_idx);
			goto next;
		}
remove_req:
		nfs_inode_remove_request(req);
next:
		nfs_end_page_writeback(req);
		nfs_release_request(req);
	}
out:
	nfs_io_completion_put(hdr->io_completion);
	hdr->release(hdr);
}

unsigned long
nfs_reqs_to_commit(struct nfs_commit_info *cinfo)
{
	return atomic_long_read(&cinfo->mds->ncommit);
}

/* NFS_I(cinfo->inode)->commit_mutex held by caller */
int
nfs_scan_commit_list(struct list_head *src, struct list_head *dst,
		     struct nfs_commit_info *cinfo, int max)
{
	struct nfs_page *req, *tmp;
	int ret = 0;

restart:
	list_for_each_entry_safe(req, tmp, src, wb_list) {
		kref_get(&req->wb_kref);
		if (!nfs_lock_request(req)) {
			int status;

			/* Prevent deadlock with nfs_lock_and_join_requests */
			if (!list_empty(dst)) {
				nfs_release_request(req);
				continue;
			}
			/* Ensure we make progress to prevent livelock */
			mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
			status = nfs_wait_on_request(req);
			nfs_release_request(req);
			mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
			if (status < 0)
				break;
			goto restart;
		}
		nfs_request_remove_commit_list(req, cinfo);
		clear_bit(PG_COMMIT_TO_DS, &req->wb_flags);
		nfs_list_add_request(req, dst);
		ret++;
		if ((ret == max) && !cinfo->dreq)
			break;
		cond_resched();
	}
	return ret;
}
EXPORT_SYMBOL_GPL(nfs_scan_commit_list);

/*
 * nfs_scan_commit - Scan an inode for commit requests
 * @inode: NFS inode to scan
 * @dst: mds destination list
 * @cinfo: mds and ds lists of reqs ready to commit
 *
 * Moves requests from the inode's 'commit' request list.
 * The requests are *not* checked to ensure that they form a contiguous set.
 */
int
nfs_scan_commit(struct inode *inode, struct list_head *dst,
		struct nfs_commit_info *cinfo)
{
	int ret = 0;

	if (!atomic_long_read(&cinfo->mds->ncommit))
		return 0;
	mutex_lock(&NFS_I(cinfo->inode)->commit_mutex);
	if (atomic_long_read(&cinfo->mds->ncommit) > 0) {
		const int max = INT_MAX;

		ret = nfs_scan_commit_list(&cinfo->mds->list, dst,
					   cinfo, max);
		ret += pnfs_scan_commit_lists(inode, cinfo, max - ret);
	}
	mutex_unlock(&NFS_I(cinfo->inode)->commit_mutex);
	return ret;
}

/*
 * Search for an existing write request, and attempt to update
 * it to reflect a new dirty region on a given page.
 *
 * If the attempt fails, then the existing request is flushed out
 * to disk.
 */
static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
		struct page *page,
		unsigned int offset,
		unsigned int bytes)
{
	struct nfs_page *req;
	unsigned int rqend;
	unsigned int end;
	int error;

	end = offset + bytes;

	req = nfs_lock_and_join_requests(page);
	if (IS_ERR_OR_NULL(req))
		return req;

	rqend = req->wb_offset + req->wb_bytes;
	/*
	 * Tell the caller to flush out the request if
	 * the offsets are non-contiguous.
	 * Note: nfs_flush_incompatible() will already
	 * have flushed out requests having wrong owners.
	 */
	if (offset > rqend || end < req->wb_offset)
		goto out_flushme;

	/* Okay, the request matches. Update the region */
	if (offset < req->wb_offset) {
		req->wb_offset = offset;
		req->wb_pgbase = offset;
	}
	if (end > rqend)
		req->wb_bytes = end - req->wb_offset;
	else
		req->wb_bytes = rqend - req->wb_offset;
	return req;
out_flushme:
	/*
	 * Note: we mark the request dirty here because
	 * nfs_lock_and_join_requests() cannot preserve
	 * commit flags, so we have to replay the write.
	 */
	nfs_mark_request_dirty(req);
	nfs_unlock_and_release_request(req);
	error = nfs_wb_page(inode, page);
	return (error < 0) ? ERR_PTR(error) : NULL;
}

/*
 * Try to update an existing write request, or create one if there is none.
 *
 * Note: Should always be called with the Page Lock held to prevent races
 * if we have to add a new request. Also assumes that the caller has
 * already called nfs_flush_incompatible() if necessary.
 */
static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
		struct page *page, unsigned int offset, unsigned int bytes)
{
	struct inode *inode = page_file_mapping(page)->host;
	struct nfs_page	*req;

	req = nfs_try_to_update_request(inode, page, offset, bytes);
	if (req != NULL)
		goto out;
	req = nfs_create_request(ctx, page, NULL, offset, bytes);
	if (IS_ERR(req))
		goto out;
	nfs_inode_add_request(inode, req);
out:
	return req;
}

static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
		unsigned int offset, unsigned int count)
{
	struct nfs_page	*req;

	req = nfs_setup_write_request(ctx, page, offset, count);
	if (IS_ERR(req))
		return PTR_ERR(req);
	/* Update file length */
	nfs_grow_file(page, offset, count);
	nfs_mark_uptodate(req);
	nfs_mark_request_dirty(req);
	nfs_unlock_and_release_request(req);
	return 0;
}

int nfs_flush_incompatible(struct file *file, struct page *page)
{
	struct nfs_open_context *ctx = nfs_file_open_context(file);
	struct nfs_lock_context *l_ctx;
	struct file_lock_context *flctx = file_inode(file)->i_flctx;
	struct nfs_page	*req;
	int do_flush, status;
	/*
	 * Look for a request corresponding to this page. If there
	 * is one, and it belongs to another file, we flush it out
	 * before we try to copy anything into the page. Do this
	 * due to the lack of an ACCESS-type call in NFSv2.
	 * Also do the same if we find a request from an existing
	 * dropped page.
	 */
	do {
		req = nfs_page_find_head_request(page);
		if (req == NULL)
			return 0;
		l_ctx = req->wb_lock_context;
		do_flush = req->wb_page != page ||
			!nfs_match_open_context(req->wb_context, ctx);
		if (l_ctx && flctx &&
		    !(list_empty_careful(&flctx->flc_posix) &&
		      list_empty_careful(&flctx->flc_flock))) {
			do_flush |= l_ctx->lockowner != current->files;
		}
		nfs_release_request(req);
		if (!do_flush)
			return 0;
		status = nfs_wb_page(page_file_mapping(page)->host, page);
	} while (status == 0);
	return status;
}

/*
 * Avoid buffered writes when a open context credential's key would
 * expire soon.
 *
 * Returns -EACCES if the key will expire within RPC_KEY_EXPIRE_FAIL.
 *
 * Return 0 and set a credential flag which triggers the inode to flush
 * and performs  NFS_FILE_SYNC writes if the key will expired within
 * RPC_KEY_EXPIRE_TIMEO.
 */
int
nfs_key_timeout_notify(struct file *filp, struct inode *inode)
{
	struct nfs_open_context *ctx = nfs_file_open_context(filp);

	if (nfs_ctx_key_to_expire(ctx, inode) &&
	    !ctx->ll_cred)
		/* Already expired! */
		return -EACCES;
	return 0;
}

/*
 * Test if the open context credential key is marked to expire soon.
 */
bool nfs_ctx_key_to_expire(struct nfs_open_context *ctx, struct inode *inode)
{
	struct rpc_auth *auth = NFS_SERVER(inode)->client->cl_auth;
	struct rpc_cred *cred = ctx->ll_cred;
	struct auth_cred acred = {
		.cred = ctx->cred,
	};

	if (cred && !cred->cr_ops->crmatch(&acred, cred, 0)) {
		put_rpccred(cred);
		ctx->ll_cred = NULL;
		cred = NULL;
	}
	if (!cred)
		cred = auth->au_ops->lookup_cred(auth, &acred, 0);
	if (!cred || IS_ERR(cred))
		return true;
	ctx->ll_cred = cred;
	return !!(cred->cr_ops->crkey_timeout &&
		  cred->cr_ops->crkey_timeout(cred));
}

/*
 * If the page cache is marked as unsafe or invalid, then we can't rely on
 * the PageUptodate() flag. In this case, we will need to turn off
 * write optimisations that depend on the page contents being correct.
 */
static bool nfs_write_pageuptodate(struct page *page, struct inode *inode)
{
	struct nfs_inode *nfsi = NFS_I(inode);

	if (nfs_have_delegated_attributes(inode))
		goto out;
	if (nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE)
		return false;
	smp_rmb();
	if (test_bit(NFS_INO_INVALIDATING, &nfsi->flags))
		return false;
out:
	if (nfsi->cache_validity & NFS_INO_INVALID_DATA)
		return false;
	return PageUptodate(page) != 0;
}

static bool
is_whole_file_wrlock(struct file_lock *fl)
{
	return fl->fl_start == 0 && fl->fl_end == OFFSET_MAX &&
			fl->fl_type == F_WRLCK;
}

/* If we know the page is up to date, and we're not using byte range locks (or
 * if we have the whole file locked for writing), it may be more efficient to
 * extend the write to cover the entire page in order to avoid fragmentation
 * inefficiencies.
 *
 * If the file is opened for synchronous writes then we can just skip the rest
 * of the checks.
 */
static int nfs_can_extend_write(struct file *file, struct page *page, struct inode *inode)
{
	int ret;
	struct file_lock_context *flctx = inode->i_flctx;
	struct file_lock *fl;

	if (file->f_flags & O_DSYNC)
		return 0;
	if (!nfs_write_pageuptodate(page, inode))
		return 0;
	if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE))
		return 1;
	if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
		       list_empty_careful(&flctx->flc_posix)))
		return 1;

	/* Check to see if there are whole file write locks */
	ret = 0;
	spin_lock(&flctx->flc_lock);
	if (!list_empty(&flctx->flc_posix)) {
		fl = list_first_entry(&flctx->flc_posix, struct file_lock,
					fl_list);
		if (is_whole_file_wrlock(fl))
			ret = 1;
	} else if (!list_empty(&flctx->flc_flock)) {
		fl = list_first_entry(&flctx->flc_flock, struct file_lock,
					fl_list);
		if (fl->fl_type == F_WRLCK)
			ret = 1;
	}
	spin_unlock(&flctx->flc_lock);
	return ret;
}

/*
 * Update and possibly write a cached page of an NFS file.
 *
 * XXX: Keep an eye on generic_file_read to make sure it doesn't do bad
 * things with a page scheduled for an RPC call (e.g. invalidate it).
 */
int nfs_updatepage(struct file *file, struct page *page,
		unsigned int offset, unsigned int count)
{
	struct nfs_open_context *ctx = nfs_file_open_context(file);
	struct address_space *mapping = page_file_mapping(page);
	struct inode	*inode = mapping->host;
	int		status = 0;

	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);

	dprintk("NFS:       nfs_updatepage(%pD2 %d@%lld)\n",
		file, count, (long long)(page_file_offset(page) + offset));

	if (!count)
		goto out;

	if (nfs_can_extend_write(file, page, inode)) {
		count = max(count + offset, nfs_page_length(page));
		offset = 0;
	}

	status = nfs_writepage_setup(ctx, page, offset, count);
	if (status < 0)
		nfs_set_pageerror(mapping);
	else
		__set_page_dirty_nobuffers(page);
out:
	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
			status, (long long)i_size_read(inode));
	return status;
}

static int flush_task_priority(int how)
{
	switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) {
		case FLUSH_HIGHPRI:
			return RPC_PRIORITY_HIGH;
		case FLUSH_LOWPRI:
			return RPC_PRIORITY_LOW;
	}
	return RPC_PRIORITY_NORMAL;
}

static void nfs_initiate_write(struct nfs_pgio_header *hdr,
			       struct rpc_message *msg,
			       const struct nfs_rpc_ops *rpc_ops,
			       struct rpc_task_setup *task_setup_data, int how)
{
	int priority = flush_task_priority(how);

	task_setup_data->priority = priority;
	rpc_ops->write_setup(hdr, msg, &task_setup_data->rpc_client);
	trace_nfs_initiate_write(hdr->inode, hdr->io_start, hdr->good_bytes,
				 hdr->args.stable);
}

/* If a nfs_flush_* function fails, it should remove reqs from @head and
 * call this on each, which will prepare them to be retried on next
 * writeback using standard nfs.
 */
static void nfs_redirty_request(struct nfs_page *req)
{
	nfs_mark_request_dirty(req);
	set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
	nfs_end_page_writeback(req);
	nfs_release_request(req);
}

static void nfs_async_write_error(struct list_head *head)
{
	struct nfs_page	*req;

	while (!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_redirty_request(req);
	}
}

static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr)
{
	nfs_async_write_error(&hdr->pages);
	filemap_fdatawrite_range(hdr->inode->i_mapping, hdr->args.offset,
			hdr->args.offset + hdr->args.count - 1);
}

static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = {
	.init_hdr = nfs_async_write_init,
	.error_cleanup = nfs_async_write_error,
	.completion = nfs_write_completion,
	.reschedule_io = nfs_async_write_reschedule_io,
};

void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
			       struct inode *inode, int ioflags, bool force_mds,
			       const struct nfs_pgio_completion_ops *compl_ops)
{
	struct nfs_server *server = NFS_SERVER(inode);
	const struct nfs_pageio_ops *pg_ops = &nfs_pgio_rw_ops;

#ifdef CONFIG_NFS_V4_1
	if (server->pnfs_curr_ld && !force_mds)
		pg_ops = server->pnfs_curr_ld->pg_write_ops;
#endif
	nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops,
			server->wsize, ioflags);
}
EXPORT_SYMBOL_GPL(nfs_pageio_init_write);

void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
{
	struct nfs_pgio_mirror *mirror;

	if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
		pgio->pg_ops->pg_cleanup(pgio);

	pgio->pg_ops = &nfs_pgio_rw_ops;

	nfs_pageio_stop_mirroring(pgio);

	mirror = &pgio->pg_mirrors[0];
	mirror->pg_bsize = NFS_SERVER(pgio->pg_inode)->wsize;
}
EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds);


void nfs_commit_prepare(struct rpc_task *task, void *calldata)
{
	struct nfs_commit_data *data = calldata;

	NFS_PROTO(data->inode)->commit_rpc_prepare(task, data);
}

/*
 * Special version of should_remove_suid() that ignores capabilities.
 */
static int nfs_should_remove_suid(const struct inode *inode)
{
	umode_t mode = inode->i_mode;
	int kill = 0;

	/* suid always must be killed */
	if (unlikely(mode & S_ISUID))
		kill = ATTR_KILL_SUID;

	/*
	 * sgid without any exec bits is just a mandatory locking mark; leave
	 * it alone.  If some exec bits are set, it's a real sgid; kill it.
	 */
	if (unlikely((mode & S_ISGID) && (mode & S_IXGRP)))
		kill |= ATTR_KILL_SGID;

	if (unlikely(kill && S_ISREG(mode)))
		return kill;

	return 0;
}

static void nfs_writeback_check_extend(struct nfs_pgio_header *hdr,
		struct nfs_fattr *fattr)
{
	struct nfs_pgio_args *argp = &hdr->args;
	struct nfs_pgio_res *resp = &hdr->res;
	u64 size = argp->offset + resp->count;

	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
		fattr->size = size;
	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) {
		fattr->valid &= ~NFS_ATTR_FATTR_SIZE;
		return;
	}
	if (size != fattr->size)
		return;
	/* Set attribute barrier */
	nfs_fattr_set_barrier(fattr);
	/* ...and update size */
	fattr->valid |= NFS_ATTR_FATTR_SIZE;
}

void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
{
	struct nfs_fattr *fattr = &hdr->fattr;
	struct inode *inode = hdr->inode;

	spin_lock(&inode->i_lock);
	nfs_writeback_check_extend(hdr, fattr);
	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL_GPL(nfs_writeback_update_inode);

/*
 * This function is called when the WRITE call is complete.
 */
static int nfs_writeback_done(struct rpc_task *task,
			      struct nfs_pgio_header *hdr,
			      struct inode *inode)
{
	int status;

	/*
	 * ->write_done will attempt to use post-op attributes to detect
	 * conflicting writes by other clients.  A strict interpretation
	 * of close-to-open would allow us to continue caching even if
	 * another writer had changed the file, but some applications
	 * depend on tighter cache coherency when writing.
	 */
	status = NFS_PROTO(inode)->write_done(task, hdr);
	if (status != 0)
		return status;

	nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, hdr->res.count);
	trace_nfs_writeback_done(inode, task->tk_status,
				 hdr->args.offset, hdr->res.verf);

	if (hdr->res.verf->committed < hdr->args.stable &&
	    task->tk_status >= 0) {
		/* We tried a write call, but the server did not
		 * commit data to stable storage even though we
		 * requested it.
		 * Note: There is a known bug in Tru64 < 5.0 in which
		 *	 the server reports NFS_DATA_SYNC, but performs
		 *	 NFS_FILE_SYNC. We therefore implement this checking
		 *	 as a dprintk() in order to avoid filling syslog.
		 */
		static unsigned long    complain;

		/* Note this will print the MDS for a DS write */
		if (time_before(complain, jiffies)) {
			dprintk("NFS:       faulty NFS server %s:"
				" (committed = %d) != (stable = %d)\n",
				NFS_SERVER(inode)->nfs_client->cl_hostname,
				hdr->res.verf->committed, hdr->args.stable);
			complain = jiffies + 300 * HZ;
		}
	}

	/* Deal with the suid/sgid bit corner case */
	if (nfs_should_remove_suid(inode)) {
		spin_lock(&inode->i_lock);
		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_OTHER;
		spin_unlock(&inode->i_lock);
	}
	return 0;
}

/*
 * This function is called when the WRITE call is complete.
 */
static void nfs_writeback_result(struct rpc_task *task,
				 struct nfs_pgio_header *hdr)
{
	struct nfs_pgio_args	*argp = &hdr->args;
	struct nfs_pgio_res	*resp = &hdr->res;

	if (resp->count < argp->count) {
		static unsigned long    complain;

		/* This a short write! */
		nfs_inc_stats(hdr->inode, NFSIOS_SHORTWRITE);

		/* Has the server at least made some progress? */
		if (resp->count == 0) {
			if (time_before(complain, jiffies)) {
				printk(KERN_WARNING
				       "NFS: Server wrote zero bytes, expected %u.\n",
				       argp->count);
				complain = jiffies + 300 * HZ;
			}
			nfs_set_pgio_error(hdr, -EIO, argp->offset);
			task->tk_status = -EIO;
			return;
		}

		/* For non rpc-based layout drivers, retry-through-MDS */
		if (!task->tk_ops) {
			hdr->pnfs_error = -EAGAIN;
			return;
		}

		/* Was this an NFSv2 write or an NFSv3 stable write? */
		if (resp->verf->committed != NFS_UNSTABLE) {
			/* Resend from where the server left off */
			hdr->mds_offset += resp->count;
			argp->offset += resp->count;
			argp->pgbase += resp->count;
			argp->count -= resp->count;
		} else {
			/* Resend as a stable write in order to avoid
			 * headaches in the case of a server crash.
			 */
			argp->stable = NFS_FILE_SYNC;
		}
		rpc_restart_call_prepare(task);
	}
}

static int wait_on_commit(struct nfs_mds_commit_info *cinfo)
{
	return wait_var_event_killable(&cinfo->rpcs_out,
				       !atomic_read(&cinfo->rpcs_out));
}

static void nfs_commit_begin(struct nfs_mds_commit_info *cinfo)
{
	atomic_inc(&cinfo->rpcs_out);
}

static void nfs_commit_end(struct nfs_mds_commit_info *cinfo)
{
	if (atomic_dec_and_test(&cinfo->rpcs_out))
		wake_up_var(&cinfo->rpcs_out);
}

void nfs_commitdata_release(struct nfs_commit_data *data)
{
	put_nfs_open_context(data->context);
	nfs_commit_free(data);
}
EXPORT_SYMBOL_GPL(nfs_commitdata_release);

int nfs_initiate_commit(struct rpc_clnt *clnt, struct nfs_commit_data *data,
			const struct nfs_rpc_ops *nfs_ops,
			const struct rpc_call_ops *call_ops,
			int how, int flags)
{
	struct rpc_task *task;
	int priority = flush_task_priority(how);
	struct rpc_message msg = {
		.rpc_argp = &data->args,
		.rpc_resp = &data->res,
		.rpc_cred = data->cred,
	};
	struct rpc_task_setup task_setup_data = {
		.task = &data->task,
		.rpc_client = clnt,
		.rpc_message = &msg,
		.callback_ops = call_ops,
		.callback_data = data,
		.workqueue = nfsiod_workqueue,
		.flags = RPC_TASK_ASYNC | flags,
		.priority = priority,
	};
	/* Set up the initial task struct.  */
	nfs_ops->commit_setup(data, &msg, &task_setup_data.rpc_client);
	trace_nfs_initiate_commit(data);

	dprintk("NFS: initiated commit call\n");

	task = rpc_run_task(&task_setup_data);
	if (IS_ERR(task))
		return PTR_ERR(task);
	if (how & FLUSH_SYNC)
		rpc_wait_for_completion_task(task);
	rpc_put_task(task);
	return 0;
}
EXPORT_SYMBOL_GPL(nfs_initiate_commit);

static loff_t nfs_get_lwb(struct list_head *head)
{
	loff_t lwb = 0;
	struct nfs_page *req;

	list_for_each_entry(req, head, wb_list)
		if (lwb < (req_offset(req) + req->wb_bytes))
			lwb = req_offset(req) + req->wb_bytes;

	return lwb;
}

/*
 * Set up the argument/result storage required for the RPC call.
 */
void nfs_init_commit(struct nfs_commit_data *data,
		     struct list_head *head,
		     struct pnfs_layout_segment *lseg,
		     struct nfs_commit_info *cinfo)
{
	struct nfs_page *first = nfs_list_entry(head->next);
	struct inode *inode = d_inode(first->wb_context->dentry);

	/* Set up the RPC argument and reply structs
	 * NB: take care not to mess about with data->commit et al. */

	list_splice_init(head, &data->pages);

	data->inode	  = inode;
	data->cred	  = first->wb_context->cred;
	data->lseg	  = lseg; /* reference transferred */
	/* only set lwb for pnfs commit */
	if (lseg)
		data->lwb = nfs_get_lwb(&data->pages);
	data->mds_ops     = &nfs_commit_ops;
	data->completion_ops = cinfo->completion_ops;
	data->dreq	  = cinfo->dreq;

	data->args.fh     = NFS_FH(data->inode);
	/* Note: we always request a commit of the entire inode */
	data->args.offset = 0;
	data->args.count  = 0;
	data->context     = get_nfs_open_context(first->wb_context);
	data->res.fattr   = &data->fattr;
	data->res.verf    = &data->verf;
	nfs_fattr_init(&data->fattr);
}
EXPORT_SYMBOL_GPL(nfs_init_commit);

void nfs_retry_commit(struct list_head *page_list,
		      struct pnfs_layout_segment *lseg,
		      struct nfs_commit_info *cinfo,
		      u32 ds_commit_idx)
{
	struct nfs_page *req;

	while (!list_empty(page_list)) {
		req = nfs_list_entry(page_list->next);
		nfs_list_remove_request(req);
		nfs_mark_request_commit(req, lseg, cinfo, ds_commit_idx);
		if (!cinfo->dreq)
			nfs_clear_page_commit(req->wb_page);
		nfs_unlock_and_release_request(req);
	}
}
EXPORT_SYMBOL_GPL(nfs_retry_commit);

static void
nfs_commit_resched_write(struct nfs_commit_info *cinfo,
		struct nfs_page *req)
{
	__set_page_dirty_nobuffers(req->wb_page);
}

/*
 * Commit dirty pages
 */
static int
nfs_commit_list(struct inode *inode, struct list_head *head, int how,
		struct nfs_commit_info *cinfo)
{
	struct nfs_commit_data	*data;

	/* another commit raced with us */
	if (list_empty(head))
		return 0;

	data = nfs_commitdata_alloc(true);

	/* Set up the argument struct */
	nfs_init_commit(data, head, NULL, cinfo);
	atomic_inc(&cinfo->mds->rpcs_out);
	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
				   data->mds_ops, how, 0);
}

/*
 * COMMIT call returned
 */
static void nfs_commit_done(struct rpc_task *task, void *calldata)
{
	struct nfs_commit_data	*data = calldata;

        dprintk("NFS: %5u nfs_commit_done (status %d)\n",
                                task->tk_pid, task->tk_status);

	/* Call the NFS version-specific code */
	NFS_PROTO(data->inode)->commit_done(task, data);
	trace_nfs_commit_done(data);
}

static void nfs_commit_release_pages(struct nfs_commit_data *data)
{
	struct nfs_page	*req;
	int status = data->task.tk_status;
	struct nfs_commit_info cinfo;
	struct nfs_server *nfss;

	while (!list_empty(&data->pages)) {
		req = nfs_list_entry(data->pages.next);
		nfs_list_remove_request(req);
		if (req->wb_page)
			nfs_clear_page_commit(req->wb_page);

		dprintk("NFS:       commit (%s/%llu %d@%lld)",
			req->wb_context->dentry->d_sb->s_id,
			(unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)),
			req->wb_bytes,
			(long long)req_offset(req));
		if (status < 0) {
			nfs_context_set_write_error(req->wb_context, status);
			if (req->wb_page)
				nfs_inode_remove_request(req);
			dprintk_cont(", error = %d\n", status);
			goto next;
		}

		/* Okay, COMMIT succeeded, apparently. Check the verifier
		 * returned by the server against all stored verfs. */
		if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) {
			/* We have a match */
			if (req->wb_page)
				nfs_inode_remove_request(req);
			dprintk_cont(" OK\n");
			goto next;
		}
		/* We have a mismatch. Write the page again */
		dprintk_cont(" mismatch\n");
		nfs_mark_request_dirty(req);
		set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
	next:
		nfs_unlock_and_release_request(req);
		/* Latency breaker */
		cond_resched();
	}
	nfss = NFS_SERVER(data->inode);
	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
		clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC);

	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
	nfs_commit_end(cinfo.mds);
}

static void nfs_commit_release(void *calldata)
{
	struct nfs_commit_data *data = calldata;

	data->completion_ops->completion(data);
	nfs_commitdata_release(calldata);
}

static const struct rpc_call_ops nfs_commit_ops = {
	.rpc_call_prepare = nfs_commit_prepare,
	.rpc_call_done = nfs_commit_done,
	.rpc_release = nfs_commit_release,
};

static const struct nfs_commit_completion_ops nfs_commit_completion_ops = {
	.completion = nfs_commit_release_pages,
	.resched_write = nfs_commit_resched_write,
};

int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
			    int how, struct nfs_commit_info *cinfo)
{
	int status;

	status = pnfs_commit_list(inode, head, how, cinfo);
	if (status == PNFS_NOT_ATTEMPTED)
		status = nfs_commit_list(inode, head, how, cinfo);
	return status;
}

static int __nfs_commit_inode(struct inode *inode, int how,
		struct writeback_control *wbc)
{
	LIST_HEAD(head);
	struct nfs_commit_info cinfo;
	int may_wait = how & FLUSH_SYNC;
	int ret, nscan;

	nfs_init_cinfo_from_inode(&cinfo, inode);
	nfs_commit_begin(cinfo.mds);
	for (;;) {
		ret = nscan = nfs_scan_commit(inode, &head, &cinfo);
		if (ret <= 0)
			break;
		ret = nfs_generic_commit_list(inode, &head, how, &cinfo);
		if (ret < 0)
			break;
		ret = 0;
		if (wbc && wbc->sync_mode == WB_SYNC_NONE) {
			if (nscan < wbc->nr_to_write)
				wbc->nr_to_write -= nscan;
			else
				wbc->nr_to_write = 0;
		}
		if (nscan < INT_MAX)
			break;
		cond_resched();
	}
	nfs_commit_end(cinfo.mds);
	if (ret || !may_wait)
		return ret;
	return wait_on_commit(cinfo.mds);
}

int nfs_commit_inode(struct inode *inode, int how)
{
	return __nfs_commit_inode(inode, how, NULL);
}
EXPORT_SYMBOL_GPL(nfs_commit_inode);

int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int flags = FLUSH_SYNC;
	int ret = 0;

	if (wbc->sync_mode == WB_SYNC_NONE) {
		/* no commits means nothing needs to be done */
		if (!atomic_long_read(&nfsi->commit_info.ncommit))
			goto check_requests_outstanding;

		/* Don't commit yet if this is a non-blocking flush and there
		 * are a lot of outstanding writes for this mapping.
		 */
		if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))
			goto out_mark_dirty;

		/* don't wait for the COMMIT response */
		flags = 0;
	}

	ret = __nfs_commit_inode(inode, flags, wbc);
	if (!ret) {
		if (flags & FLUSH_SYNC)
			return 0;
	} else if (atomic_long_read(&nfsi->commit_info.ncommit))
		goto out_mark_dirty;

check_requests_outstanding:
	if (!atomic_read(&nfsi->commit_info.rpcs_out))
		return ret;
out_mark_dirty:
	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
	return ret;
}
EXPORT_SYMBOL_GPL(nfs_write_inode);

/*
 * Wrapper for filemap_write_and_wait_range()
 *
 * Needed for pNFS in order to ensure data becomes visible to the
 * client.
 */
int nfs_filemap_write_and_wait_range(struct address_space *mapping,
		loff_t lstart, loff_t lend)
{
	int ret;

	ret = filemap_write_and_wait_range(mapping, lstart, lend);
	if (ret == 0)
		ret = pnfs_sync_inode(mapping->host, true);
	return ret;
}
EXPORT_SYMBOL_GPL(nfs_filemap_write_and_wait_range);

/*
 * flush the inode to disk.
 */
int nfs_wb_all(struct inode *inode)
{
	int ret;

	trace_nfs_writeback_inode_enter(inode);

	ret = filemap_write_and_wait(inode->i_mapping);
	if (ret)
		goto out;
	ret = nfs_commit_inode(inode, FLUSH_SYNC);
	if (ret < 0)
		goto out;
	pnfs_sync_inode(inode, true);
	ret = 0;

out:
	trace_nfs_writeback_inode_exit(inode, ret);
	return ret;
}
EXPORT_SYMBOL_GPL(nfs_wb_all);

int nfs_wb_page_cancel(struct inode *inode, struct page *page)
{
	struct nfs_page *req;
	int ret = 0;

	wait_on_page_writeback(page);

	/* blocking call to cancel all requests and join to a single (head)
	 * request */
	req = nfs_lock_and_join_requests(page);

	if (IS_ERR(req)) {
		ret = PTR_ERR(req);
	} else if (req) {
		/* all requests from this page have been cancelled by
		 * nfs_lock_and_join_requests, so just remove the head
		 * request from the inode / page_private pointer and
		 * release it */
		nfs_inode_remove_request(req);
		nfs_unlock_and_release_request(req);
	}

	return ret;
}

/*
 * Write back all requests on one page - we do this before reading it.
 */
int nfs_wb_page(struct inode *inode, struct page *page)
{
	loff_t range_start = page_file_offset(page);
	loff_t range_end = range_start + (loff_t)(PAGE_SIZE - 1);
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 0,
		.range_start = range_start,
		.range_end = range_end,
	};
	int ret;

	trace_nfs_writeback_page_enter(inode);

	for (;;) {
		wait_on_page_writeback(page);
		if (clear_page_dirty_for_io(page)) {
			ret = nfs_writepage_locked(page, &wbc);
			if (ret < 0)
				goto out_error;
			continue;
		}
		ret = 0;
		if (!PagePrivate(page))
			break;
		ret = nfs_commit_inode(inode, FLUSH_SYNC);
		if (ret < 0)
			goto out_error;
	}
out_error:
	trace_nfs_writeback_page_exit(inode, ret);
	return ret;
}

#ifdef CONFIG_MIGRATION
int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
		struct page *page, enum migrate_mode mode)
{
	/*
	 * If PagePrivate is set, then the page is currently associated with
	 * an in-progress read or write request. Don't try to migrate it.
	 *
	 * FIXME: we could do this in principle, but we'll need a way to ensure
	 *        that we can safely release the inode reference while holding
	 *        the page lock.
	 */
	if (PagePrivate(page))
		return -EBUSY;

	if (!nfs_fscache_release_page(page, GFP_KERNEL))
		return -EBUSY;

	return migrate_page(mapping, newpage, page, mode);
}
#endif

int __init nfs_init_writepagecache(void)
{
	nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
					     sizeof(struct nfs_pgio_header),
					     0, SLAB_HWCACHE_ALIGN,
					     NULL);
	if (nfs_wdata_cachep == NULL)
		return -ENOMEM;

	nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE,
						     nfs_wdata_cachep);
	if (nfs_wdata_mempool == NULL)
		goto out_destroy_write_cache;

	nfs_cdata_cachep = kmem_cache_create("nfs_commit_data",
					     sizeof(struct nfs_commit_data),
					     0, SLAB_HWCACHE_ALIGN,
					     NULL);
	if (nfs_cdata_cachep == NULL)
		goto out_destroy_write_mempool;

	nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
						      nfs_cdata_cachep);
	if (nfs_commit_mempool == NULL)
		goto out_destroy_commit_cache;

	/*
	 * NFS congestion size, scale with available memory.
	 *
	 *  64MB:    8192k
	 * 128MB:   11585k
	 * 256MB:   16384k
	 * 512MB:   23170k
	 *   1GB:   32768k
	 *   2GB:   46340k
	 *   4GB:   65536k
	 *   8GB:   92681k
	 *  16GB:  131072k
	 *
	 * This allows larger machines to have larger/more transfers.
	 * Limit the default to 256M
	 */
	nfs_congestion_kb = (16*int_sqrt(totalram_pages())) << (PAGE_SHIFT-10);
	if (nfs_congestion_kb > 256*1024)
		nfs_congestion_kb = 256*1024;

	return 0;

out_destroy_commit_cache:
	kmem_cache_destroy(nfs_cdata_cachep);
out_destroy_write_mempool:
	mempool_destroy(nfs_wdata_mempool);
out_destroy_write_cache:
	kmem_cache_destroy(nfs_wdata_cachep);
	return -ENOMEM;
}

void nfs_destroy_writepagecache(void)
{
	mempool_destroy(nfs_commit_mempool);
	kmem_cache_destroy(nfs_cdata_cachep);
	mempool_destroy(nfs_wdata_mempool);
	kmem_cache_destroy(nfs_wdata_cachep);
}

static const struct nfs_rw_ops nfs_rw_write_ops = {
	.rw_alloc_header	= nfs_writehdr_alloc,
	.rw_free_header		= nfs_writehdr_free,
	.rw_done		= nfs_writeback_done,
	.rw_result		= nfs_writeback_result,
	.rw_initiate		= nfs_initiate_write,
};