aboutsummaryrefslogtreecommitdiff
path: root/fs/nfs/write.c
blob: 8593965a35ef29bc997de57a396a343d3708439c (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
/*
 * 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/sunrpc/clnt.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/backing-dev.h>

#include <asm/uaccess.h>
#include <linux/smp_lock.h>

#include "delegation.h"
#include "internal.h"
#include "iostat.h"

#define NFSDBG_FACILITY		NFSDBG_PAGECACHE

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

/*
 * Local function declarations
 */
static struct nfs_page * nfs_update_request(struct nfs_open_context*,
					    struct page *,
					    unsigned int, unsigned int);
static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how);
static const struct rpc_call_ops nfs_write_partial_ops;
static const struct rpc_call_ops nfs_write_full_ops;
static const struct rpc_call_ops nfs_commit_ops;

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

struct nfs_write_data *nfs_commit_alloc(void)
{
	struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);

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

void nfs_commit_rcu_free(struct rcu_head *head)
{
	struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
	if (p && (p->pagevec != &p->page_array[0]))
		kfree(p->pagevec);
	mempool_free(p, nfs_commit_mempool);
}

void nfs_commit_free(struct nfs_write_data *wdata)
{
	call_rcu_bh(&wdata->task.u.tk_rcu, nfs_commit_rcu_free);
}

struct nfs_write_data *nfs_writedata_alloc(size_t len)
{
	unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
	struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);

	if (p) {
		memset(p, 0, sizeof(*p));
		INIT_LIST_HEAD(&p->pages);
		p->npages = pagecount;
		if (pagecount <= ARRAY_SIZE(p->page_array))
			p->pagevec = p->page_array;
		else {
			p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
			if (!p->pagevec) {
				mempool_free(p, nfs_wdata_mempool);
				p = NULL;
			}
		}
	}
	return p;
}

static void nfs_writedata_rcu_free(struct rcu_head *head)
{
	struct nfs_write_data *p = container_of(head, struct nfs_write_data, task.u.tk_rcu);
	if (p && (p->pagevec != &p->page_array[0]))
		kfree(p->pagevec);
	mempool_free(p, nfs_wdata_mempool);
}

static void nfs_writedata_free(struct nfs_write_data *wdata)
{
	call_rcu_bh(&wdata->task.u.tk_rcu, nfs_writedata_rcu_free);
}

void nfs_writedata_release(void *wdata)
{
	nfs_writedata_free(wdata);
}

static struct nfs_page *nfs_page_find_request_locked(struct page *page)
{
	struct nfs_page *req = NULL;

	if (PagePrivate(page)) {
		req = (struct nfs_page *)page_private(page);
		if (req != NULL)
			atomic_inc(&req->wb_count);
	}
	return req;
}

static struct nfs_page *nfs_page_find_request(struct page *page)
{
	struct nfs_page *req = NULL;
	spinlock_t *req_lock = &NFS_I(page->mapping->host)->req_lock;

	spin_lock(req_lock);
	req = nfs_page_find_request_locked(page);
	spin_unlock(req_lock);
	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->mapping->host;
	loff_t end, i_size = i_size_read(inode);
	unsigned long end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;

	if (i_size > 0 && page->index < end_index)
		return;
	end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
	if (i_size >= end)
		return;
	nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
	i_size_write(inode, end);
}

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

/* We can set the PG_uptodate flag if we see that a write request
 * covers the full page.
 */
static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int count)
{
	if (PageUptodate(page))
		return;
	if (base != 0)
		return;
	if (count != nfs_page_length(page))
		return;
	if (count != PAGE_CACHE_SIZE)
		memclear_highpage_flush(page, count, PAGE_CACHE_SIZE - count);
	SetPageUptodate(page);
}

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

	for (;;) {
		req = nfs_update_request(ctx, page, offset, count);
		if (!IS_ERR(req))
			break;
		ret = PTR_ERR(req);
		if (ret != -EBUSY)
			return ret;
		ret = nfs_wb_page(page->mapping->host, page);
		if (ret != 0)
			return ret;
	}
	/* Update file length */
	nfs_grow_file(page, offset, count);
	/* Set the PG_uptodate flag? */
	nfs_mark_uptodate(page, offset, count);
	nfs_unlock_request(req);
	return 0;
}

static int wb_priority(struct writeback_control *wbc)
{
	if (wbc->for_reclaim)
		return FLUSH_HIGHPRI;
	if (wbc->for_kupdate)
		return FLUSH_LOWPRI;
	return 0;
}

/*
 * 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 int nfs_set_page_writeback(struct page *page)
{
	int ret = test_set_page_writeback(page);

	if (!ret) {
		struct inode *inode = page->mapping->host;
		struct nfs_server *nfss = NFS_SERVER(inode);

		if (atomic_inc_return(&nfss->writeback) >
				NFS_CONGESTION_ON_THRESH)
			set_bdi_congested(&nfss->backing_dev_info, WRITE);
	}
	return ret;
}

static void nfs_end_page_writeback(struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct nfs_server *nfss = NFS_SERVER(inode);

	end_page_writeback(page);
	if (atomic_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH) {
		clear_bdi_congested(&nfss->backing_dev_info, WRITE);
		congestion_end(WRITE);
	}
}

/*
 * Find an associated nfs write request, and prepare to flush it out
 * Returns 1 if there was no write request, or if the request was
 * already tagged by nfs_set_page_dirty.Returns 0 if the request
 * was not tagged.
 * May also return an error if the user signalled nfs_wait_on_request().
 */
static int nfs_page_mark_flush(struct page *page)
{
	struct nfs_page *req;
	struct nfs_inode *nfsi = NFS_I(page->mapping->host);
	spinlock_t *req_lock = &nfsi->req_lock;
	int ret;

	spin_lock(req_lock);
	for(;;) {
		req = nfs_page_find_request_locked(page);
		if (req == NULL) {
			spin_unlock(req_lock);
			return 1;
		}
		if (nfs_lock_request_dontget(req))
			break;
		/* Note: If we hold the page lock, as is the case in nfs_writepage,
		 *	 then the call to nfs_lock_request_dontget() will always
		 *	 succeed provided that someone hasn't already marked the
		 *	 request as dirty (in which case we don't care).
		 */
		spin_unlock(req_lock);
		ret = nfs_wait_on_request(req);
		nfs_release_request(req);
		if (ret != 0)
			return ret;
		spin_lock(req_lock);
	}
	if (test_bit(PG_NEED_COMMIT, &req->wb_flags)) {
		/* This request is marked for commit */
		spin_unlock(req_lock);
		nfs_unlock_request(req);
		return 1;
	}
	if (nfs_set_page_writeback(page) == 0) {
		nfs_list_remove_request(req);
		/* add the request to the inode's dirty list. */
		radix_tree_tag_set(&nfsi->nfs_page_tree,
				req->wb_index, NFS_PAGE_TAG_DIRTY);
		nfs_list_add_request(req, &nfsi->dirty);
		nfsi->ndirty++;
		spin_unlock(req_lock);
		__mark_inode_dirty(page->mapping->host, I_DIRTY_PAGES);
	} else
		spin_unlock(req_lock);
	ret = test_bit(PG_NEED_FLUSH, &req->wb_flags);
	nfs_unlock_request(req);
	return ret;
}

/*
 * Write an mmapped page to the server.
 */
static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc)
{
	struct nfs_open_context *ctx;
	struct inode *inode = page->mapping->host;
	unsigned offset;
	int err;

	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);

	err = nfs_page_mark_flush(page);
	if (err <= 0)
		goto out;
	err = 0;
	offset = nfs_page_length(page);
	if (!offset)
		goto out;

	ctx = nfs_find_open_context(inode, NULL, FMODE_WRITE);
	if (ctx == NULL) {
		err = -EBADF;
		goto out;
	}
	err = nfs_writepage_setup(ctx, page, 0, offset);
	put_nfs_open_context(ctx);
	if (err != 0)
		goto out;
	err = nfs_page_mark_flush(page);
	if (err > 0)
		err = 0;
out:
	if (!wbc->for_writepages)
		nfs_flush_mapping(page->mapping, wbc, FLUSH_STABLE|wb_priority(wbc));
	return err;
}

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

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

int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	int err;

	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);

	err = generic_writepages(mapping, wbc);
	if (err)
		return err;
	err = nfs_flush_mapping(mapping, wbc, wb_priority(wbc));
	if (err < 0)
		goto out;
	nfs_add_stats(inode, NFSIOS_WRITEPAGES, err);
	err = 0;
out:
	return err;
}

/*
 * Insert a write request into an inode
 */
static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int error;

	error = radix_tree_insert(&nfsi->nfs_page_tree, req->wb_index, req);
	BUG_ON(error == -EEXIST);
	if (error)
		return error;
	if (!nfsi->npages) {
		igrab(inode);
		nfs_begin_data_update(inode);
		if (nfs_have_delegation(inode, FMODE_WRITE))
			nfsi->change_attr++;
	}
	SetPagePrivate(req->wb_page);
	set_page_private(req->wb_page, (unsigned long)req);
	if (PageDirty(req->wb_page))
		set_bit(PG_NEED_FLUSH, &req->wb_flags);
	nfsi->npages++;
	atomic_inc(&req->wb_count);
	return 0;
}

/*
 * Remove a write request from an inode
 */
static void nfs_inode_remove_request(struct nfs_page *req)
{
	struct inode *inode = req->wb_context->dentry->d_inode;
	struct nfs_inode *nfsi = NFS_I(inode);

	BUG_ON (!NFS_WBACK_BUSY(req));

	spin_lock(&nfsi->req_lock);
	set_page_private(req->wb_page, 0);
	ClearPagePrivate(req->wb_page);
	radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
	if (test_and_clear_bit(PG_NEED_FLUSH, &req->wb_flags))
		__set_page_dirty_nobuffers(req->wb_page);
	nfsi->npages--;
	if (!nfsi->npages) {
		spin_unlock(&nfsi->req_lock);
		nfs_end_data_update(inode);
		iput(inode);
	} else
		spin_unlock(&nfsi->req_lock);
	nfs_clear_request(req);
	nfs_release_request(req);
}

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

/*
 * Check if a request is dirty
 */
static inline int
nfs_dirty_request(struct nfs_page *req)
{
	struct page *page = req->wb_page;

	if (page == NULL || test_bit(PG_NEED_COMMIT, &req->wb_flags))
		return 0;
	return !PageWriteback(req->wb_page);
}

#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
/*
 * Add a request to the inode's commit list.
 */
static void
nfs_mark_request_commit(struct nfs_page *req)
{
	struct inode *inode = req->wb_context->dentry->d_inode;
	struct nfs_inode *nfsi = NFS_I(inode);

	spin_lock(&nfsi->req_lock);
	nfs_list_add_request(req, &nfsi->commit);
	nfsi->ncommit++;
	set_bit(PG_NEED_COMMIT, &(req)->wb_flags);
	spin_unlock(&nfsi->req_lock);
	inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}

static inline
int nfs_write_need_commit(struct nfs_write_data *data)
{
	return data->verf.committed != NFS_FILE_SYNC;
}

static inline
int nfs_reschedule_unstable_write(struct nfs_page *req)
{
	if (test_bit(PG_NEED_COMMIT, &req->wb_flags)) {
		nfs_mark_request_commit(req);
		return 1;
	}
	if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) {
		nfs_redirty_request(req);
		return 1;
	}
	return 0;
}
#else
static inline void
nfs_mark_request_commit(struct nfs_page *req)
{
}

static inline
int nfs_write_need_commit(struct nfs_write_data *data)
{
	return 0;
}

static inline
int nfs_reschedule_unstable_write(struct nfs_page *req)
{
	return 0;
}
#endif

/*
 * Wait for a request to complete.
 *
 * Interruptible by signals only if mounted with intr flag.
 */
static int nfs_wait_on_requests_locked(struct inode *inode, unsigned long idx_start, unsigned int npages)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_page *req;
	unsigned long		idx_end, next;
	unsigned int		res = 0;
	int			error;

	if (npages == 0)
		idx_end = ~0;
	else
		idx_end = idx_start + npages - 1;

	next = idx_start;
	while (radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree, (void **)&req, next, 1, NFS_PAGE_TAG_WRITEBACK)) {
		if (req->wb_index > idx_end)
			break;

		next = req->wb_index + 1;
		BUG_ON(!NFS_WBACK_BUSY(req));

		atomic_inc(&req->wb_count);
		spin_unlock(&nfsi->req_lock);
		error = nfs_wait_on_request(req);
		nfs_release_request(req);
		spin_lock(&nfsi->req_lock);
		if (error < 0)
			return error;
		res++;
	}
	return res;
}

static void nfs_cancel_dirty_list(struct list_head *head)
{
	struct nfs_page *req;
	while(!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_end_page_writeback(req->wb_page);
		nfs_inode_remove_request(req);
		nfs_clear_page_writeback(req);
	}
}

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

	while(!list_empty(head)) {
		req = nfs_list_entry(head->next);
		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
		nfs_list_remove_request(req);
		clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
		nfs_inode_remove_request(req);
		nfs_unlock_request(req);
	}
}

#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
/*
 * nfs_scan_commit - Scan an inode for commit requests
 * @inode: NFS inode to scan
 * @dst: destination list
 * @idx_start: lower bound of page->index to scan.
 * @npages: idx_start + npages sets the upper bound to scan.
 *
 * Moves requests from the inode's 'commit' request list.
 * The requests are *not* checked to ensure that they form a contiguous set.
 */
static int
nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_start, unsigned int npages)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	int res = 0;

	if (nfsi->ncommit != 0) {
		res = nfs_scan_list(nfsi, &nfsi->commit, dst, idx_start, npages);
		nfsi->ncommit -= res;
		if ((nfsi->ncommit == 0) != list_empty(&nfsi->commit))
			printk(KERN_ERR "NFS: desynchronized value of nfs_i.ncommit.\n");
	}
	return res;
}
#else
static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_start, unsigned int npages)
{
	return 0;
}
#endif

static int nfs_wait_on_write_congestion(struct address_space *mapping)
{
	struct inode *inode = mapping->host;
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	int ret = 0;

	might_sleep();

	if (!bdi_write_congested(bdi))
		return 0;

	nfs_inc_stats(inode, NFSIOS_CONGESTIONWAIT);

	do {
		struct rpc_clnt *clnt = NFS_CLIENT(inode);
		sigset_t oldset;

		rpc_clnt_sigmask(clnt, &oldset);
		ret = congestion_wait_interruptible(WRITE, HZ/10);
		rpc_clnt_sigunmask(clnt, &oldset);
		if (ret == -ERESTARTSYS)
			break;
		ret = 0;
	} while (bdi_write_congested(bdi));

	return ret;
}

/*
 * Try to update any existing write request, or create one if there is none.
 * In order to match, the request's credentials must match those of
 * the calling process.
 *
 * Note: Should always be called with the Page Lock held!
 */
static struct nfs_page * nfs_update_request(struct nfs_open_context* ctx,
		struct page *page, unsigned int offset, unsigned int bytes)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode = mapping->host;
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_page		*req, *new = NULL;
	unsigned long		rqend, end;

	end = offset + bytes;

	if (nfs_wait_on_write_congestion(mapping))
		return ERR_PTR(-ERESTARTSYS);
	for (;;) {
		/* Loop over all inode entries and see if we find
		 * A request for the page we wish to update
		 */
		spin_lock(&nfsi->req_lock);
		req = nfs_page_find_request_locked(page);
		if (req) {
			if (!nfs_lock_request_dontget(req)) {
				int error;

				spin_unlock(&nfsi->req_lock);
				error = nfs_wait_on_request(req);
				nfs_release_request(req);
				if (error < 0) {
					if (new)
						nfs_release_request(new);
					return ERR_PTR(error);
				}
				continue;
			}
			spin_unlock(&nfsi->req_lock);
			if (new)
				nfs_release_request(new);
			break;
		}

		if (new) {
			int error;
			nfs_lock_request_dontget(new);
			error = nfs_inode_add_request(inode, new);
			if (error) {
				spin_unlock(&nfsi->req_lock);
				nfs_unlock_request(new);
				return ERR_PTR(error);
			}
			spin_unlock(&nfsi->req_lock);
			return new;
		}
		spin_unlock(&nfsi->req_lock);

		new = nfs_create_request(ctx, inode, page, offset, bytes);
		if (IS_ERR(new))
			return new;
	}

	/* We have a request for our page.
	 * If the creds don't match, or the
	 * page addresses don't match,
	 * tell the caller to wait on the conflicting
	 * request.
	 */
	rqend = req->wb_offset + req->wb_bytes;
	if (req->wb_context != ctx
	    || req->wb_page != page
	    || !nfs_dirty_request(req)
	    || offset > rqend || end < req->wb_offset) {
		nfs_unlock_request(req);
		return ERR_PTR(-EBUSY);
	}

	/* Okay, the request matches. Update the region */
	if (offset < req->wb_offset) {
		req->wb_offset = offset;
		req->wb_pgbase = offset;
		req->wb_bytes = rqend - req->wb_offset;
	}

	if (end > rqend)
		req->wb_bytes = end - req->wb_offset;

	return req;
}

int nfs_flush_incompatible(struct file *file, struct page *page)
{
	struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data;
	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_request(page);
		if (req == NULL)
			return 0;
		do_flush = req->wb_page != page || req->wb_context != ctx
			|| !nfs_dirty_request(req);
		nfs_release_request(req);
		if (!do_flush)
			return 0;
		status = nfs_wb_page(page->mapping->host, page);
	} while (status == 0);
	return status;
}

/*
 * 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 = (struct nfs_open_context *)file->private_data;
	struct inode	*inode = page->mapping->host;
	int		status = 0;

	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);

	dprintk("NFS:      nfs_updatepage(%s/%s %d@%Ld)\n",
		file->f_path.dentry->d_parent->d_name.name,
		file->f_path.dentry->d_name.name, count,
		(long long)(page_offset(page) +offset));

	/* If we're not using byte range locks, and we know the page
	 * is entirely in cache, it may be more efficient to avoid
	 * fragmenting write requests.
	 */
	if (PageUptodate(page) && inode->i_flock == NULL && !(file->f_mode & O_SYNC)) {
		count = max(count + offset, nfs_page_length(page));
		offset = 0;
	}

	status = nfs_writepage_setup(ctx, page, offset, count);
	__set_page_dirty_nobuffers(page);

        dprintk("NFS:      nfs_updatepage returns %d (isize %Ld)\n",
			status, (long long)i_size_read(inode));
	if (status < 0)
		nfs_set_pageerror(page);
	return status;
}

static void nfs_writepage_release(struct nfs_page *req)
{

	if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) {
		nfs_end_page_writeback(req->wb_page);
		nfs_inode_remove_request(req);
	} else
		nfs_end_page_writeback(req->wb_page);
	nfs_clear_page_writeback(req);
}

static inline 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;
}

/*
 * Set up the argument/result storage required for the RPC call.
 */
static void nfs_write_rpcsetup(struct nfs_page *req,
		struct nfs_write_data *data,
		const struct rpc_call_ops *call_ops,
		unsigned int count, unsigned int offset,
		int how)
{
	struct inode		*inode;
	int flags;

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

	data->req = req;
	data->inode = inode = req->wb_context->dentry->d_inode;
	data->cred = req->wb_context->cred;

	data->args.fh     = NFS_FH(inode);
	data->args.offset = req_offset(req) + offset;
	data->args.pgbase = req->wb_pgbase + offset;
	data->args.pages  = data->pagevec;
	data->args.count  = count;
	data->args.context = req->wb_context;

	data->res.fattr   = &data->fattr;
	data->res.count   = count;
	data->res.verf    = &data->verf;
	nfs_fattr_init(&data->fattr);

	/* Set up the initial task struct.  */
	flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
	rpc_init_task(&data->task, NFS_CLIENT(inode), flags, call_ops, data);
	NFS_PROTO(inode)->write_setup(data, how);

	data->task.tk_priority = flush_task_priority(how);
	data->task.tk_cookie = (unsigned long)inode;

	dprintk("NFS: %5u initiated write call "
		"(req %s/%Ld, %u bytes @ offset %Lu)\n",
		data->task.tk_pid,
		inode->i_sb->s_id,
		(long long)NFS_FILEID(inode),
		count,
		(unsigned long long)data->args.offset);
}

static void nfs_execute_write(struct nfs_write_data *data)
{
	struct rpc_clnt *clnt = NFS_CLIENT(data->inode);
	sigset_t oldset;

	rpc_clnt_sigmask(clnt, &oldset);
	rpc_execute(&data->task);
	rpc_clnt_sigunmask(clnt, &oldset);
}

/*
 * Generate multiple small requests to write out a single
 * contiguous dirty area on one page.
 */
static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how)
{
	struct nfs_page *req = nfs_list_entry(head->next);
	struct page *page = req->wb_page;
	struct nfs_write_data *data;
	size_t wsize = NFS_SERVER(inode)->wsize, nbytes;
	unsigned int offset;
	int requests = 0;
	LIST_HEAD(list);

	nfs_list_remove_request(req);

	nbytes = req->wb_bytes;
	do {
		size_t len = min(nbytes, wsize);

		data = nfs_writedata_alloc(len);
		if (!data)
			goto out_bad;
		list_add(&data->pages, &list);
		requests++;
		nbytes -= len;
	} while (nbytes != 0);
	atomic_set(&req->wb_complete, requests);

	ClearPageError(page);
	offset = 0;
	nbytes = req->wb_bytes;
	do {
		data = list_entry(list.next, struct nfs_write_data, pages);
		list_del_init(&data->pages);

		data->pagevec[0] = page;

		if (nbytes > wsize) {
			nfs_write_rpcsetup(req, data, &nfs_write_partial_ops,
					wsize, offset, how);
			offset += wsize;
			nbytes -= wsize;
		} else {
			nfs_write_rpcsetup(req, data, &nfs_write_partial_ops,
					nbytes, offset, how);
			nbytes = 0;
		}
		nfs_execute_write(data);
	} while (nbytes != 0);

	return 0;

out_bad:
	while (!list_empty(&list)) {
		data = list_entry(list.next, struct nfs_write_data, pages);
		list_del(&data->pages);
		nfs_writedata_release(data);
	}
	nfs_redirty_request(req);
	nfs_end_page_writeback(req->wb_page);
	nfs_clear_page_writeback(req);
	return -ENOMEM;
}

/*
 * Create an RPC task for the given write request and kick it.
 * The page must have been locked by the caller.
 *
 * It may happen that the page we're passed is not marked dirty.
 * This is the case if nfs_updatepage detects a conflicting request
 * that has been written but not committed.
 */
static int nfs_flush_one(struct inode *inode, struct list_head *head, int how)
{
	struct nfs_page		*req;
	struct page		**pages;
	struct nfs_write_data	*data;
	unsigned int		count;

	data = nfs_writedata_alloc(NFS_SERVER(inode)->wsize);
	if (!data)
		goto out_bad;

	pages = data->pagevec;
	count = 0;
	while (!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_list_add_request(req, &data->pages);
		ClearPageError(req->wb_page);
		*pages++ = req->wb_page;
		count += req->wb_bytes;
	}
	req = nfs_list_entry(data->pages.next);

	/* Set up the argument struct */
	nfs_write_rpcsetup(req, data, &nfs_write_full_ops, count, 0, how);

	nfs_execute_write(data);
	return 0;
 out_bad:
	while (!list_empty(head)) {
		struct nfs_page *req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_redirty_request(req);
		nfs_end_page_writeback(req->wb_page);
		nfs_clear_page_writeback(req);
	}
	return -ENOMEM;
}

static int nfs_flush_list(struct inode *inode, struct list_head *head, int npages, int how)
{
	LIST_HEAD(one_request);
	int (*flush_one)(struct inode *, struct list_head *, int);
	struct nfs_page	*req;
	int wpages = NFS_SERVER(inode)->wpages;
	int wsize = NFS_SERVER(inode)->wsize;
	int error;

	flush_one = nfs_flush_one;
	if (wsize < PAGE_CACHE_SIZE)
		flush_one = nfs_flush_multi;
	/* For single writes, FLUSH_STABLE is more efficient */
	if (npages <= wpages && npages == NFS_I(inode)->npages
			&& nfs_list_entry(head->next)->wb_bytes <= wsize)
		how |= FLUSH_STABLE;

	do {
		nfs_coalesce_requests(head, &one_request, wpages);
		req = nfs_list_entry(one_request.next);
		error = flush_one(inode, &one_request, how);
		if (error < 0)
			goto out_err;
	} while (!list_empty(head));
	return 0;
out_err:
	while (!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_redirty_request(req);
		nfs_end_page_writeback(req->wb_page);
		nfs_clear_page_writeback(req);
	}
	return error;
}

/*
 * Handle a write reply that flushed part of a page.
 */
static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata)
{
	struct nfs_write_data	*data = calldata;
	struct nfs_page		*req = data->req;
	struct page		*page = req->wb_page;

	dprintk("NFS: write (%s/%Ld %d@%Ld)",
		req->wb_context->dentry->d_inode->i_sb->s_id,
		(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
		req->wb_bytes,
		(long long)req_offset(req));

	if (nfs_writeback_done(task, data) != 0)
		return;

	if (task->tk_status < 0) {
		nfs_set_pageerror(page);
		req->wb_context->error = task->tk_status;
		dprintk(", error = %d\n", task->tk_status);
		goto out;
	}

	if (nfs_write_need_commit(data)) {
		spinlock_t *req_lock = &NFS_I(page->mapping->host)->req_lock;

		spin_lock(req_lock);
		if (test_bit(PG_NEED_RESCHED, &req->wb_flags)) {
			/* Do nothing we need to resend the writes */
		} else if (!test_and_set_bit(PG_NEED_COMMIT, &req->wb_flags)) {
			memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
			dprintk(" defer commit\n");
		} else if (memcmp(&req->wb_verf, &data->verf, sizeof(req->wb_verf))) {
			set_bit(PG_NEED_RESCHED, &req->wb_flags);
			clear_bit(PG_NEED_COMMIT, &req->wb_flags);
			dprintk(" server reboot detected\n");
		}
		spin_unlock(req_lock);
	} else
		dprintk(" OK\n");

out:
	if (atomic_dec_and_test(&req->wb_complete))
		nfs_writepage_release(req);
}

static const struct rpc_call_ops nfs_write_partial_ops = {
	.rpc_call_done = nfs_writeback_done_partial,
	.rpc_release = nfs_writedata_release,
};

/*
 * Handle a write reply that flushes a whole page.
 *
 * FIXME: There is an inherent race with invalidate_inode_pages and
 *	  writebacks since the page->count is kept > 1 for as long
 *	  as the page has a write request pending.
 */
static void nfs_writeback_done_full(struct rpc_task *task, void *calldata)
{
	struct nfs_write_data	*data = calldata;
	struct nfs_page		*req;
	struct page		*page;

	if (nfs_writeback_done(task, data) != 0)
		return;

	/* Update attributes as result of writeback. */
	while (!list_empty(&data->pages)) {
		req = nfs_list_entry(data->pages.next);
		nfs_list_remove_request(req);
		page = req->wb_page;

		dprintk("NFS: write (%s/%Ld %d@%Ld)",
			req->wb_context->dentry->d_inode->i_sb->s_id,
			(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
			req->wb_bytes,
			(long long)req_offset(req));

		if (task->tk_status < 0) {
			nfs_set_pageerror(page);
			req->wb_context->error = task->tk_status;
			dprintk(", error = %d\n", task->tk_status);
			goto remove_request;
		}

		if (nfs_write_need_commit(data)) {
			memcpy(&req->wb_verf, &data->verf, sizeof(req->wb_verf));
			nfs_mark_request_commit(req);
			nfs_end_page_writeback(page);
			dprintk(" marked for commit\n");
			goto next;
		}
		dprintk(" OK\n");
remove_request:
		nfs_end_page_writeback(page);
		nfs_inode_remove_request(req);
	next:
		nfs_clear_page_writeback(req);
	}
}

static const struct rpc_call_ops nfs_write_full_ops = {
	.rpc_call_done = nfs_writeback_done_full,
	.rpc_release = nfs_writedata_release,
};


/*
 * This function is called when the WRITE call is complete.
 */
int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
{
	struct nfs_writeargs	*argp = &data->args;
	struct nfs_writeres	*resp = &data->res;
	int status;

	dprintk("NFS: %5u nfs_writeback_done (status %d)\n",
		task->tk_pid, task->tk_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(data->inode)->write_done(task, data);
	if (status != 0)
		return status;
	nfs_add_stats(data->inode, NFSIOS_SERVERWRITTENBYTES, resp->count);

#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
	if (resp->verf->committed < argp->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;

		if (time_before(complain, jiffies)) {
			dprintk("NFS: faulty NFS server %s:"
				" (committed = %d) != (stable = %d)\n",
				NFS_SERVER(data->inode)->nfs_client->cl_hostname,
				resp->verf->committed, argp->stable);
			complain = jiffies + 300 * HZ;
		}
	}
#endif
	/* Is this a short write? */
	if (task->tk_status >= 0 && resp->count < argp->count) {
		static unsigned long    complain;

		nfs_inc_stats(data->inode, NFSIOS_SHORTWRITE);

		/* Has the server at least made some progress? */
		if (resp->count != 0) {
			/* Was this an NFSv2 write or an NFSv3 stable write? */
			if (resp->verf->committed != NFS_UNSTABLE) {
				/* Resend from where the server left off */
				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(task);
			return -EAGAIN;
		}
		if (time_before(complain, jiffies)) {
			printk(KERN_WARNING
			       "NFS: Server wrote zero bytes, expected %u.\n",
					argp->count);
			complain = jiffies + 300 * HZ;
		}
		/* Can't do anything about it except throw an error. */
		task->tk_status = -EIO;
	}
	return 0;
}


#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
void nfs_commit_release(void *wdata)
{
	nfs_commit_free(wdata);
}

/*
 * Set up the argument/result storage required for the RPC call.
 */
static void nfs_commit_rpcsetup(struct list_head *head,
		struct nfs_write_data *data,
		int how)
{
	struct nfs_page		*first;
	struct inode		*inode;
	int flags;

	/* 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);
	first = nfs_list_entry(data->pages.next);
	inode = first->wb_context->dentry->d_inode;

	data->inode	  = inode;
	data->cred	  = first->wb_context->cred;

	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->res.count   = 0;
	data->res.fattr   = &data->fattr;
	data->res.verf    = &data->verf;
	nfs_fattr_init(&data->fattr);

	/* Set up the initial task struct.  */
	flags = (how & FLUSH_SYNC) ? 0 : RPC_TASK_ASYNC;
	rpc_init_task(&data->task, NFS_CLIENT(inode), flags, &nfs_commit_ops, data);
	NFS_PROTO(inode)->commit_setup(data, how);

	data->task.tk_priority = flush_task_priority(how);
	data->task.tk_cookie = (unsigned long)inode;
	
	dprintk("NFS: %5u initiated commit call\n", data->task.tk_pid);
}

/*
 * Commit dirty pages
 */
static int
nfs_commit_list(struct inode *inode, struct list_head *head, int how)
{
	struct nfs_write_data	*data;
	struct nfs_page         *req;

	data = nfs_commit_alloc();

	if (!data)
		goto out_bad;

	/* Set up the argument struct */
	nfs_commit_rpcsetup(head, data, how);

	nfs_execute_write(data);
	return 0;
 out_bad:
	while (!list_empty(head)) {
		req = nfs_list_entry(head->next);
		nfs_list_remove_request(req);
		nfs_mark_request_commit(req);
		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
		nfs_clear_page_writeback(req);
	}
	return -ENOMEM;
}

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

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

	/* Call the NFS version-specific code */
	if (NFS_PROTO(data->inode)->commit_done(task, data) != 0)
		return;

	while (!list_empty(&data->pages)) {
		req = nfs_list_entry(data->pages.next);
		nfs_list_remove_request(req);
		clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);

		dprintk("NFS: commit (%s/%Ld %d@%Ld)",
			req->wb_context->dentry->d_inode->i_sb->s_id,
			(long long)NFS_FILEID(req->wb_context->dentry->d_inode),
			req->wb_bytes,
			(long long)req_offset(req));
		if (task->tk_status < 0) {
			req->wb_context->error = task->tk_status;
			nfs_inode_remove_request(req);
			dprintk(", error = %d\n", task->tk_status);
			goto next;
		}

		/* Okay, COMMIT succeeded, apparently. Check the verifier
		 * returned by the server against all stored verfs. */
		if (!memcmp(req->wb_verf.verifier, data->verf.verifier, sizeof(data->verf.verifier))) {
			/* We have a match */
			nfs_inode_remove_request(req);
			dprintk(" OK\n");
			goto next;
		}
		/* We have a mismatch. Write the page again */
		dprintk(" mismatch\n");
		nfs_redirty_request(req);
	next:
		nfs_clear_page_writeback(req);
	}
}

static const struct rpc_call_ops nfs_commit_ops = {
	.rpc_call_done = nfs_commit_done,
	.rpc_release = nfs_commit_release,
};
#else
static inline int nfs_commit_list(struct inode *inode, struct list_head *head, int how)
{
	return 0;
}
#endif

static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how)
{
	struct nfs_inode *nfsi = NFS_I(mapping->host);
	LIST_HEAD(head);
	long res;

	spin_lock(&nfsi->req_lock);
	res = nfs_scan_dirty(mapping, wbc, &head);
	spin_unlock(&nfsi->req_lock);
	if (res) {
		int error = nfs_flush_list(mapping->host, &head, res, how);
		if (error < 0)
			return error;
	}
	return res;
}

#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
int nfs_commit_inode(struct inode *inode, int how)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	LIST_HEAD(head);
	int res;

	spin_lock(&nfsi->req_lock);
	res = nfs_scan_commit(inode, &head, 0, 0);
	spin_unlock(&nfsi->req_lock);
	if (res) {
		int error = nfs_commit_list(inode, &head, how);
		if (error < 0)
			return error;
	}
	return res;
}
#endif

long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_control *wbc, int how)
{
	struct inode *inode = mapping->host;
	struct nfs_inode *nfsi = NFS_I(inode);
	unsigned long idx_start, idx_end;
	unsigned int npages = 0;
	LIST_HEAD(head);
	int nocommit = how & FLUSH_NOCOMMIT;
	long pages, ret;

	/* FIXME */
	if (wbc->range_cyclic)
		idx_start = 0;
	else {
		idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
		idx_end = wbc->range_end >> PAGE_CACHE_SHIFT;
		if (idx_end > idx_start) {
			unsigned long l_npages = 1 + idx_end - idx_start;
			npages = l_npages;
			if (sizeof(npages) != sizeof(l_npages) &&
					(unsigned long)npages != l_npages)
				npages = 0;
		}
	}
	how &= ~FLUSH_NOCOMMIT;
	spin_lock(&nfsi->req_lock);
	do {
		wbc->pages_skipped = 0;
		ret = nfs_wait_on_requests_locked(inode, idx_start, npages);
		if (ret != 0)
			continue;
		pages = nfs_scan_dirty(mapping, wbc, &head);
		if (pages != 0) {
			spin_unlock(&nfsi->req_lock);
			if (how & FLUSH_INVALIDATE) {
				nfs_cancel_dirty_list(&head);
				ret = pages;
			} else
				ret = nfs_flush_list(inode, &head, pages, how);
			spin_lock(&nfsi->req_lock);
			continue;
		}
		if (wbc->pages_skipped != 0)
			continue;
		if (nocommit)
			break;
		pages = nfs_scan_commit(inode, &head, idx_start, npages);
		if (pages == 0) {
			if (wbc->pages_skipped != 0)
				continue;
			break;
		}
		if (how & FLUSH_INVALIDATE) {
			spin_unlock(&nfsi->req_lock);
			nfs_cancel_commit_list(&head);
			ret = pages;
			spin_lock(&nfsi->req_lock);
			continue;
		}
		pages += nfs_scan_commit(inode, &head, 0, 0);
		spin_unlock(&nfsi->req_lock);
		ret = nfs_commit_list(inode, &head, how);
		spin_lock(&nfsi->req_lock);
	} while (ret >= 0);
	spin_unlock(&nfsi->req_lock);
	return ret;
}

/*
 * flush the inode to disk.
 */
int nfs_wb_all(struct inode *inode)
{
	struct address_space *mapping = inode->i_mapping;
	struct writeback_control wbc = {
		.bdi = mapping->backing_dev_info,
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.for_writepages = 1,
		.range_cyclic = 1,
	};
	int ret;

	ret = generic_writepages(mapping, &wbc);
	if (ret < 0)
		goto out;
	ret = nfs_sync_mapping_wait(mapping, &wbc, 0);
	if (ret >= 0)
		return 0;
out:
	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
	return ret;
}

int nfs_sync_mapping_range(struct address_space *mapping, loff_t range_start, loff_t range_end, int how)
{
	struct writeback_control wbc = {
		.bdi = mapping->backing_dev_info,
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.range_start = range_start,
		.range_end = range_end,
		.for_writepages = 1,
	};
	int ret;

	if (!(how & FLUSH_NOWRITEPAGE)) {
		ret = generic_writepages(mapping, &wbc);
		if (ret < 0)
			goto out;
	}
	ret = nfs_sync_mapping_wait(mapping, &wbc, how);
	if (ret >= 0)
		return 0;
out:
	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
	return ret;
}

int nfs_wb_page_priority(struct inode *inode, struct page *page, int how)
{
	loff_t range_start = page_offset(page);
	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
	struct writeback_control wbc = {
		.bdi = page->mapping->backing_dev_info,
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.range_start = range_start,
		.range_end = range_end,
	};
	int ret;

	BUG_ON(!PageLocked(page));
	if (!(how & FLUSH_NOWRITEPAGE) && clear_page_dirty_for_io(page)) {
		ret = nfs_writepage_locked(page, &wbc);
		if (ret < 0)
			goto out;
	}
	if (!PagePrivate(page))
		return 0;
	ret = nfs_sync_mapping_wait(page->mapping, &wbc, how);
	if (ret >= 0)
		return 0;
out:
	__mark_inode_dirty(inode, I_DIRTY_PAGES);
	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)
{
	return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
}

int nfs_set_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode;
	spinlock_t *req_lock;
	struct nfs_page *req;
	int ret;

	if (!mapping)
		goto out_raced;
	inode = mapping->host;
	if (!inode)
		goto out_raced;
	req_lock = &NFS_I(inode)->req_lock;
	spin_lock(req_lock);
	req = nfs_page_find_request_locked(page);
	if (req != NULL) {
		/* Mark any existing write requests for flushing */
		ret = !test_and_set_bit(PG_NEED_FLUSH, &req->wb_flags);
		spin_unlock(req_lock);
		nfs_release_request(req);
		return ret;
	}
	ret = __set_page_dirty_nobuffers(page);
	spin_unlock(req_lock);
	return ret;
out_raced:
	return !TestSetPageDirty(page);
}


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

	nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT,
						      nfs_wdata_cachep);
	if (nfs_commit_mempool == NULL)
		return -ENOMEM;

	/*
	 * 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;
}

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