summaryrefslogtreecommitdiff
path: root/fs/f2fs/node.c
blob: 51ef2789443322ea0e3a2d683d305b753997aeae (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
/*
 * fs/f2fs/node.c
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/mpage.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/pagevec.h>
#include <linux/swap.h>

#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include <trace/events/f2fs.h>

static struct kmem_cache *nat_entry_slab;
static struct kmem_cache *free_nid_slab;

static void clear_node_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
	unsigned int long flags;

	if (PageDirty(page)) {
		spin_lock_irqsave(&mapping->tree_lock, flags);
		radix_tree_tag_clear(&mapping->page_tree,
				page_index(page),
				PAGECACHE_TAG_DIRTY);
		spin_unlock_irqrestore(&mapping->tree_lock, flags);

		clear_page_dirty_for_io(page);
		dec_page_count(sbi, F2FS_DIRTY_NODES);
	}
	ClearPageUptodate(page);
}

static struct page *get_current_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
{
	pgoff_t index = current_nat_addr(sbi, nid);
	return get_meta_page(sbi, index);
}

static struct page *get_next_nat_page(struct f2fs_sb_info *sbi, nid_t nid)
{
	struct page *src_page;
	struct page *dst_page;
	pgoff_t src_off;
	pgoff_t dst_off;
	void *src_addr;
	void *dst_addr;
	struct f2fs_nm_info *nm_i = NM_I(sbi);

	src_off = current_nat_addr(sbi, nid);
	dst_off = next_nat_addr(sbi, src_off);

	/* get current nat block page with lock */
	src_page = get_meta_page(sbi, src_off);

	/* Dirty src_page means that it is already the new target NAT page. */
	if (PageDirty(src_page))
		return src_page;

	dst_page = grab_meta_page(sbi, dst_off);

	src_addr = page_address(src_page);
	dst_addr = page_address(dst_page);
	memcpy(dst_addr, src_addr, PAGE_CACHE_SIZE);
	set_page_dirty(dst_page);
	f2fs_put_page(src_page, 1);

	set_to_next_nat(nm_i, nid);

	return dst_page;
}

/*
 * Readahead NAT pages
 */
static void ra_nat_pages(struct f2fs_sb_info *sbi, int nid)
{
	struct address_space *mapping = sbi->meta_inode->i_mapping;
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct blk_plug plug;
	struct page *page;
	pgoff_t index;
	int i;

	blk_start_plug(&plug);

	for (i = 0; i < FREE_NID_PAGES; i++, nid += NAT_ENTRY_PER_BLOCK) {
		if (nid >= nm_i->max_nid)
			nid = 0;
		index = current_nat_addr(sbi, nid);

		page = grab_cache_page(mapping, index);
		if (!page)
			continue;
		if (PageUptodate(page)) {
			f2fs_put_page(page, 1);
			continue;
		}
		if (f2fs_readpage(sbi, page, index, READ))
			continue;

		f2fs_put_page(page, 0);
	}
	blk_finish_plug(&plug);
}

static struct nat_entry *__lookup_nat_cache(struct f2fs_nm_info *nm_i, nid_t n)
{
	return radix_tree_lookup(&nm_i->nat_root, n);
}

static unsigned int __gang_lookup_nat_cache(struct f2fs_nm_info *nm_i,
		nid_t start, unsigned int nr, struct nat_entry **ep)
{
	return radix_tree_gang_lookup(&nm_i->nat_root, (void **)ep, start, nr);
}

static void __del_from_nat_cache(struct f2fs_nm_info *nm_i, struct nat_entry *e)
{
	list_del(&e->list);
	radix_tree_delete(&nm_i->nat_root, nat_get_nid(e));
	nm_i->nat_cnt--;
	kmem_cache_free(nat_entry_slab, e);
}

int is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct nat_entry *e;
	int is_cp = 1;

	read_lock(&nm_i->nat_tree_lock);
	e = __lookup_nat_cache(nm_i, nid);
	if (e && !e->checkpointed)
		is_cp = 0;
	read_unlock(&nm_i->nat_tree_lock);
	return is_cp;
}

static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
{
	struct nat_entry *new;

	new = kmem_cache_alloc(nat_entry_slab, GFP_ATOMIC);
	if (!new)
		return NULL;
	if (radix_tree_insert(&nm_i->nat_root, nid, new)) {
		kmem_cache_free(nat_entry_slab, new);
		return NULL;
	}
	memset(new, 0, sizeof(struct nat_entry));
	nat_set_nid(new, nid);
	list_add_tail(&new->list, &nm_i->nat_entries);
	nm_i->nat_cnt++;
	return new;
}

static void cache_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
						struct f2fs_nat_entry *ne)
{
	struct nat_entry *e;
retry:
	write_lock(&nm_i->nat_tree_lock);
	e = __lookup_nat_cache(nm_i, nid);
	if (!e) {
		e = grab_nat_entry(nm_i, nid);
		if (!e) {
			write_unlock(&nm_i->nat_tree_lock);
			goto retry;
		}
		nat_set_blkaddr(e, le32_to_cpu(ne->block_addr));
		nat_set_ino(e, le32_to_cpu(ne->ino));
		nat_set_version(e, ne->version);
		e->checkpointed = true;
	}
	write_unlock(&nm_i->nat_tree_lock);
}

static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
			block_t new_blkaddr)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct nat_entry *e;
retry:
	write_lock(&nm_i->nat_tree_lock);
	e = __lookup_nat_cache(nm_i, ni->nid);
	if (!e) {
		e = grab_nat_entry(nm_i, ni->nid);
		if (!e) {
			write_unlock(&nm_i->nat_tree_lock);
			goto retry;
		}
		e->ni = *ni;
		e->checkpointed = true;
		BUG_ON(ni->blk_addr == NEW_ADDR);
	} else if (new_blkaddr == NEW_ADDR) {
		/*
		 * when nid is reallocated,
		 * previous nat entry can be remained in nat cache.
		 * So, reinitialize it with new information.
		 */
		e->ni = *ni;
		BUG_ON(ni->blk_addr != NULL_ADDR);
	}

	if (new_blkaddr == NEW_ADDR)
		e->checkpointed = false;

	/* sanity check */
	BUG_ON(nat_get_blkaddr(e) != ni->blk_addr);
	BUG_ON(nat_get_blkaddr(e) == NULL_ADDR &&
			new_blkaddr == NULL_ADDR);
	BUG_ON(nat_get_blkaddr(e) == NEW_ADDR &&
			new_blkaddr == NEW_ADDR);
	BUG_ON(nat_get_blkaddr(e) != NEW_ADDR &&
			nat_get_blkaddr(e) != NULL_ADDR &&
			new_blkaddr == NEW_ADDR);

	/* increament version no as node is removed */
	if (nat_get_blkaddr(e) != NEW_ADDR && new_blkaddr == NULL_ADDR) {
		unsigned char version = nat_get_version(e);
		nat_set_version(e, inc_node_version(version));
	}

	/* change address */
	nat_set_blkaddr(e, new_blkaddr);
	__set_nat_cache_dirty(nm_i, e);
	write_unlock(&nm_i->nat_tree_lock);
}

static int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);

	if (nm_i->nat_cnt <= NM_WOUT_THRESHOLD)
		return 0;

	write_lock(&nm_i->nat_tree_lock);
	while (nr_shrink && !list_empty(&nm_i->nat_entries)) {
		struct nat_entry *ne;
		ne = list_first_entry(&nm_i->nat_entries,
					struct nat_entry, list);
		__del_from_nat_cache(nm_i, ne);
		nr_shrink--;
	}
	write_unlock(&nm_i->nat_tree_lock);
	return nr_shrink;
}

/*
 * This function returns always success
 */
void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
	struct f2fs_summary_block *sum = curseg->sum_blk;
	nid_t start_nid = START_NID(nid);
	struct f2fs_nat_block *nat_blk;
	struct page *page = NULL;
	struct f2fs_nat_entry ne;
	struct nat_entry *e;
	int i;

	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
	ni->nid = nid;

	/* Check nat cache */
	read_lock(&nm_i->nat_tree_lock);
	e = __lookup_nat_cache(nm_i, nid);
	if (e) {
		ni->ino = nat_get_ino(e);
		ni->blk_addr = nat_get_blkaddr(e);
		ni->version = nat_get_version(e);
	}
	read_unlock(&nm_i->nat_tree_lock);
	if (e)
		return;

	/* Check current segment summary */
	mutex_lock(&curseg->curseg_mutex);
	i = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 0);
	if (i >= 0) {
		ne = nat_in_journal(sum, i);
		node_info_from_raw_nat(ni, &ne);
	}
	mutex_unlock(&curseg->curseg_mutex);
	if (i >= 0)
		goto cache;

	/* Fill node_info from nat page */
	page = get_current_nat_page(sbi, start_nid);
	nat_blk = (struct f2fs_nat_block *)page_address(page);
	ne = nat_blk->entries[nid - start_nid];
	node_info_from_raw_nat(ni, &ne);
	f2fs_put_page(page, 1);
cache:
	/* cache nat entry */
	cache_nat_entry(NM_I(sbi), nid, &ne);
}

/*
 * The maximum depth is four.
 * Offset[0] will have raw inode offset.
 */
static int get_node_path(struct f2fs_inode_info *fi, long block,
				int offset[4], unsigned int noffset[4])
{
	const long direct_index = ADDRS_PER_INODE(fi);
	const long direct_blks = ADDRS_PER_BLOCK;
	const long dptrs_per_blk = NIDS_PER_BLOCK;
	const long indirect_blks = ADDRS_PER_BLOCK * NIDS_PER_BLOCK;
	const long dindirect_blks = indirect_blks * NIDS_PER_BLOCK;
	int n = 0;
	int level = 0;

	noffset[0] = 0;

	if (block < direct_index) {
		offset[n] = block;
		goto got;
	}
	block -= direct_index;
	if (block < direct_blks) {
		offset[n++] = NODE_DIR1_BLOCK;
		noffset[n] = 1;
		offset[n] = block;
		level = 1;
		goto got;
	}
	block -= direct_blks;
	if (block < direct_blks) {
		offset[n++] = NODE_DIR2_BLOCK;
		noffset[n] = 2;
		offset[n] = block;
		level = 1;
		goto got;
	}
	block -= direct_blks;
	if (block < indirect_blks) {
		offset[n++] = NODE_IND1_BLOCK;
		noffset[n] = 3;
		offset[n++] = block / direct_blks;
		noffset[n] = 4 + offset[n - 1];
		offset[n] = block % direct_blks;
		level = 2;
		goto got;
	}
	block -= indirect_blks;
	if (block < indirect_blks) {
		offset[n++] = NODE_IND2_BLOCK;
		noffset[n] = 4 + dptrs_per_blk;
		offset[n++] = block / direct_blks;
		noffset[n] = 5 + dptrs_per_blk + offset[n - 1];
		offset[n] = block % direct_blks;
		level = 2;
		goto got;
	}
	block -= indirect_blks;
	if (block < dindirect_blks) {
		offset[n++] = NODE_DIND_BLOCK;
		noffset[n] = 5 + (dptrs_per_blk * 2);
		offset[n++] = block / indirect_blks;
		noffset[n] = 6 + (dptrs_per_blk * 2) +
			      offset[n - 1] * (dptrs_per_blk + 1);
		offset[n++] = (block / direct_blks) % dptrs_per_blk;
		noffset[n] = 7 + (dptrs_per_blk * 2) +
			      offset[n - 2] * (dptrs_per_blk + 1) +
			      offset[n - 1];
		offset[n] = block % direct_blks;
		level = 3;
		goto got;
	} else {
		BUG();
	}
got:
	return level;
}

/*
 * Caller should call f2fs_put_dnode(dn).
 * Also, it should grab and release a mutex by calling mutex_lock_op() and
 * mutex_unlock_op() only if ro is not set RDONLY_NODE.
 * In the case of RDONLY_NODE, we don't need to care about mutex.
 */
int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct page *npage[4];
	struct page *parent;
	int offset[4];
	unsigned int noffset[4];
	nid_t nids[4];
	int level, i;
	int err = 0;

	level = get_node_path(F2FS_I(dn->inode), index, offset, noffset);

	nids[0] = dn->inode->i_ino;
	npage[0] = dn->inode_page;

	if (!npage[0]) {
		npage[0] = get_node_page(sbi, nids[0]);
		if (IS_ERR(npage[0]))
			return PTR_ERR(npage[0]);
	}
	parent = npage[0];
	if (level != 0)
		nids[1] = get_nid(parent, offset[0], true);
	dn->inode_page = npage[0];
	dn->inode_page_locked = true;

	/* get indirect or direct nodes */
	for (i = 1; i <= level; i++) {
		bool done = false;

		if (!nids[i] && mode == ALLOC_NODE) {
			/* alloc new node */
			if (!alloc_nid(sbi, &(nids[i]))) {
				err = -ENOSPC;
				goto release_pages;
			}

			dn->nid = nids[i];
			npage[i] = new_node_page(dn, noffset[i], NULL);
			if (IS_ERR(npage[i])) {
				alloc_nid_failed(sbi, nids[i]);
				err = PTR_ERR(npage[i]);
				goto release_pages;
			}

			set_nid(parent, offset[i - 1], nids[i], i == 1);
			alloc_nid_done(sbi, nids[i]);
			done = true;
		} else if (mode == LOOKUP_NODE_RA && i == level && level > 1) {
			npage[i] = get_node_page_ra(parent, offset[i - 1]);
			if (IS_ERR(npage[i])) {
				err = PTR_ERR(npage[i]);
				goto release_pages;
			}
			done = true;
		}
		if (i == 1) {
			dn->inode_page_locked = false;
			unlock_page(parent);
		} else {
			f2fs_put_page(parent, 1);
		}

		if (!done) {
			npage[i] = get_node_page(sbi, nids[i]);
			if (IS_ERR(npage[i])) {
				err = PTR_ERR(npage[i]);
				f2fs_put_page(npage[0], 0);
				goto release_out;
			}
		}
		if (i < level) {
			parent = npage[i];
			nids[i + 1] = get_nid(parent, offset[i], false);
		}
	}
	dn->nid = nids[level];
	dn->ofs_in_node = offset[level];
	dn->node_page = npage[level];
	dn->data_blkaddr = datablock_addr(dn->node_page, dn->ofs_in_node);
	return 0;

release_pages:
	f2fs_put_page(parent, 1);
	if (i > 1)
		f2fs_put_page(npage[0], 0);
release_out:
	dn->inode_page = NULL;
	dn->node_page = NULL;
	return err;
}

static void truncate_node(struct dnode_of_data *dn)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct node_info ni;

	get_node_info(sbi, dn->nid, &ni);
	if (dn->inode->i_blocks == 0) {
		BUG_ON(ni.blk_addr != NULL_ADDR);
		goto invalidate;
	}
	BUG_ON(ni.blk_addr == NULL_ADDR);

	/* Deallocate node address */
	invalidate_blocks(sbi, ni.blk_addr);
	dec_valid_node_count(sbi, dn->inode, 1);
	set_node_addr(sbi, &ni, NULL_ADDR);

	if (dn->nid == dn->inode->i_ino) {
		remove_orphan_inode(sbi, dn->nid);
		dec_valid_inode_count(sbi);
	} else {
		sync_inode_page(dn);
	}
invalidate:
	clear_node_page_dirty(dn->node_page);
	F2FS_SET_SB_DIRT(sbi);

	f2fs_put_page(dn->node_page, 1);
	dn->node_page = NULL;
	trace_f2fs_truncate_node(dn->inode, dn->nid, ni.blk_addr);
}

static int truncate_dnode(struct dnode_of_data *dn)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct page *page;

	if (dn->nid == 0)
		return 1;

	/* get direct node */
	page = get_node_page(sbi, dn->nid);
	if (IS_ERR(page) && PTR_ERR(page) == -ENOENT)
		return 1;
	else if (IS_ERR(page))
		return PTR_ERR(page);

	/* Make dnode_of_data for parameter */
	dn->node_page = page;
	dn->ofs_in_node = 0;
	truncate_data_blocks(dn);
	truncate_node(dn);
	return 1;
}

static int truncate_nodes(struct dnode_of_data *dn, unsigned int nofs,
						int ofs, int depth)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct dnode_of_data rdn = *dn;
	struct page *page;
	struct f2fs_node *rn;
	nid_t child_nid;
	unsigned int child_nofs;
	int freed = 0;
	int i, ret;

	if (dn->nid == 0)
		return NIDS_PER_BLOCK + 1;

	trace_f2fs_truncate_nodes_enter(dn->inode, dn->nid, dn->data_blkaddr);

	page = get_node_page(sbi, dn->nid);
	if (IS_ERR(page)) {
		trace_f2fs_truncate_nodes_exit(dn->inode, PTR_ERR(page));
		return PTR_ERR(page);
	}

	rn = F2FS_NODE(page);
	if (depth < 3) {
		for (i = ofs; i < NIDS_PER_BLOCK; i++, freed++) {
			child_nid = le32_to_cpu(rn->in.nid[i]);
			if (child_nid == 0)
				continue;
			rdn.nid = child_nid;
			ret = truncate_dnode(&rdn);
			if (ret < 0)
				goto out_err;
			set_nid(page, i, 0, false);
		}
	} else {
		child_nofs = nofs + ofs * (NIDS_PER_BLOCK + 1) + 1;
		for (i = ofs; i < NIDS_PER_BLOCK; i++) {
			child_nid = le32_to_cpu(rn->in.nid[i]);
			if (child_nid == 0) {
				child_nofs += NIDS_PER_BLOCK + 1;
				continue;
			}
			rdn.nid = child_nid;
			ret = truncate_nodes(&rdn, child_nofs, 0, depth - 1);
			if (ret == (NIDS_PER_BLOCK + 1)) {
				set_nid(page, i, 0, false);
				child_nofs += ret;
			} else if (ret < 0 && ret != -ENOENT) {
				goto out_err;
			}
		}
		freed = child_nofs;
	}

	if (!ofs) {
		/* remove current indirect node */
		dn->node_page = page;
		truncate_node(dn);
		freed++;
	} else {
		f2fs_put_page(page, 1);
	}
	trace_f2fs_truncate_nodes_exit(dn->inode, freed);
	return freed;

out_err:
	f2fs_put_page(page, 1);
	trace_f2fs_truncate_nodes_exit(dn->inode, ret);
	return ret;
}

static int truncate_partial_nodes(struct dnode_of_data *dn,
			struct f2fs_inode *ri, int *offset, int depth)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct page *pages[2];
	nid_t nid[3];
	nid_t child_nid;
	int err = 0;
	int i;
	int idx = depth - 2;

	nid[0] = le32_to_cpu(ri->i_nid[offset[0] - NODE_DIR1_BLOCK]);
	if (!nid[0])
		return 0;

	/* get indirect nodes in the path */
	for (i = 0; i < depth - 1; i++) {
		/* refernece count'll be increased */
		pages[i] = get_node_page(sbi, nid[i]);
		if (IS_ERR(pages[i])) {
			depth = i + 1;
			err = PTR_ERR(pages[i]);
			goto fail;
		}
		nid[i + 1] = get_nid(pages[i], offset[i + 1], false);
	}

	/* free direct nodes linked to a partial indirect node */
	for (i = offset[depth - 1]; i < NIDS_PER_BLOCK; i++) {
		child_nid = get_nid(pages[idx], i, false);
		if (!child_nid)
			continue;
		dn->nid = child_nid;
		err = truncate_dnode(dn);
		if (err < 0)
			goto fail;
		set_nid(pages[idx], i, 0, false);
	}

	if (offset[depth - 1] == 0) {
		dn->node_page = pages[idx];
		dn->nid = nid[idx];
		truncate_node(dn);
	} else {
		f2fs_put_page(pages[idx], 1);
	}
	offset[idx]++;
	offset[depth - 1] = 0;
fail:
	for (i = depth - 3; i >= 0; i--)
		f2fs_put_page(pages[i], 1);

	trace_f2fs_truncate_partial_nodes(dn->inode, nid, depth, err);

	return err;
}

/*
 * All the block addresses of data and nodes should be nullified.
 */
int truncate_inode_blocks(struct inode *inode, pgoff_t from)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct address_space *node_mapping = sbi->node_inode->i_mapping;
	int err = 0, cont = 1;
	int level, offset[4], noffset[4];
	unsigned int nofs = 0;
	struct f2fs_node *rn;
	struct dnode_of_data dn;
	struct page *page;

	trace_f2fs_truncate_inode_blocks_enter(inode, from);

	level = get_node_path(F2FS_I(inode), from, offset, noffset);
restart:
	page = get_node_page(sbi, inode->i_ino);
	if (IS_ERR(page)) {
		trace_f2fs_truncate_inode_blocks_exit(inode, PTR_ERR(page));
		return PTR_ERR(page);
	}

	set_new_dnode(&dn, inode, page, NULL, 0);
	unlock_page(page);

	rn = F2FS_NODE(page);
	switch (level) {
	case 0:
	case 1:
		nofs = noffset[1];
		break;
	case 2:
		nofs = noffset[1];
		if (!offset[level - 1])
			goto skip_partial;
		err = truncate_partial_nodes(&dn, &rn->i, offset, level);
		if (err < 0 && err != -ENOENT)
			goto fail;
		nofs += 1 + NIDS_PER_BLOCK;
		break;
	case 3:
		nofs = 5 + 2 * NIDS_PER_BLOCK;
		if (!offset[level - 1])
			goto skip_partial;
		err = truncate_partial_nodes(&dn, &rn->i, offset, level);
		if (err < 0 && err != -ENOENT)
			goto fail;
		break;
	default:
		BUG();
	}

skip_partial:
	while (cont) {
		dn.nid = le32_to_cpu(rn->i.i_nid[offset[0] - NODE_DIR1_BLOCK]);
		switch (offset[0]) {
		case NODE_DIR1_BLOCK:
		case NODE_DIR2_BLOCK:
			err = truncate_dnode(&dn);
			break;

		case NODE_IND1_BLOCK:
		case NODE_IND2_BLOCK:
			err = truncate_nodes(&dn, nofs, offset[1], 2);
			break;

		case NODE_DIND_BLOCK:
			err = truncate_nodes(&dn, nofs, offset[1], 3);
			cont = 0;
			break;

		default:
			BUG();
		}
		if (err < 0 && err != -ENOENT)
			goto fail;
		if (offset[1] == 0 &&
				rn->i.i_nid[offset[0] - NODE_DIR1_BLOCK]) {
			lock_page(page);
			if (page->mapping != node_mapping) {
				f2fs_put_page(page, 1);
				goto restart;
			}
			wait_on_page_writeback(page);
			rn->i.i_nid[offset[0] - NODE_DIR1_BLOCK] = 0;
			set_page_dirty(page);
			unlock_page(page);
		}
		offset[1] = 0;
		offset[0]++;
		nofs += err;
	}
fail:
	f2fs_put_page(page, 0);
	trace_f2fs_truncate_inode_blocks_exit(inode, err);
	return err > 0 ? 0 : err;
}

int truncate_xattr_node(struct inode *inode, struct page *page)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	nid_t nid = F2FS_I(inode)->i_xattr_nid;
	struct dnode_of_data dn;
	struct page *npage;

	if (!nid)
		return 0;

	npage = get_node_page(sbi, nid);
	if (IS_ERR(npage))
		return PTR_ERR(npage);

	F2FS_I(inode)->i_xattr_nid = 0;

	/* need to do checkpoint during fsync */
	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));

	set_new_dnode(&dn, inode, page, npage, nid);

	if (page)
		dn.inode_page_locked = 1;
	truncate_node(&dn);
	return 0;
}

/*
 * Caller should grab and release a mutex by calling mutex_lock_op() and
 * mutex_unlock_op().
 */
int remove_inode_page(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct page *page;
	nid_t ino = inode->i_ino;
	struct dnode_of_data dn;
	int err;

	page = get_node_page(sbi, ino);
	if (IS_ERR(page))
		return PTR_ERR(page);

	err = truncate_xattr_node(inode, page);
	if (err) {
		f2fs_put_page(page, 1);
		return err;
	}

	/* 0 is possible, after f2fs_new_inode() is failed */
	BUG_ON(inode->i_blocks != 0 && inode->i_blocks != 1);
	set_new_dnode(&dn, inode, page, page, ino);
	truncate_node(&dn);
	return 0;
}

struct page *new_inode_page(struct inode *inode, const struct qstr *name)
{
	struct dnode_of_data dn;

	/* allocate inode page for new inode */
	set_new_dnode(&dn, inode, NULL, NULL, inode->i_ino);

	/* caller should f2fs_put_page(page, 1); */
	return new_node_page(&dn, 0, NULL);
}

struct page *new_node_page(struct dnode_of_data *dn,
				unsigned int ofs, struct page *ipage)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct address_space *mapping = sbi->node_inode->i_mapping;
	struct node_info old_ni, new_ni;
	struct page *page;
	int err;

	if (is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC))
		return ERR_PTR(-EPERM);

	page = grab_cache_page(mapping, dn->nid);
	if (!page)
		return ERR_PTR(-ENOMEM);

	if (!inc_valid_node_count(sbi, dn->inode, 1)) {
		err = -ENOSPC;
		goto fail;
	}

	get_node_info(sbi, dn->nid, &old_ni);

	/* Reinitialize old_ni with new node page */
	BUG_ON(old_ni.blk_addr != NULL_ADDR);
	new_ni = old_ni;
	new_ni.ino = dn->inode->i_ino;
	set_node_addr(sbi, &new_ni, NEW_ADDR);

	fill_node_footer(page, dn->nid, dn->inode->i_ino, ofs, true);
	set_cold_node(dn->inode, page);
	SetPageUptodate(page);
	set_page_dirty(page);

	if (ofs == XATTR_NODE_OFFSET)
		F2FS_I(dn->inode)->i_xattr_nid = dn->nid;

	dn->node_page = page;
	if (ipage)
		update_inode(dn->inode, ipage);
	else
		sync_inode_page(dn);
	if (ofs == 0)
		inc_valid_inode_count(sbi);

	return page;

fail:
	clear_node_page_dirty(page);
	f2fs_put_page(page, 1);
	return ERR_PTR(err);
}

/*
 * Caller should do after getting the following values.
 * 0: f2fs_put_page(page, 0)
 * LOCKED_PAGE: f2fs_put_page(page, 1)
 * error: nothing
 */
static int read_node_page(struct page *page, int type)
{
	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
	struct node_info ni;

	get_node_info(sbi, page->index, &ni);

	if (ni.blk_addr == NULL_ADDR) {
		f2fs_put_page(page, 1);
		return -ENOENT;
	}

	if (PageUptodate(page))
		return LOCKED_PAGE;

	return f2fs_readpage(sbi, page, ni.blk_addr, type);
}

/*
 * Readahead a node page
 */
void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid)
{
	struct address_space *mapping = sbi->node_inode->i_mapping;
	struct page *apage;
	int err;

	apage = find_get_page(mapping, nid);
	if (apage && PageUptodate(apage)) {
		f2fs_put_page(apage, 0);
		return;
	}
	f2fs_put_page(apage, 0);

	apage = grab_cache_page(mapping, nid);
	if (!apage)
		return;

	err = read_node_page(apage, READA);
	if (err == 0)
		f2fs_put_page(apage, 0);
	else if (err == LOCKED_PAGE)
		f2fs_put_page(apage, 1);
}

struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid)
{
	struct address_space *mapping = sbi->node_inode->i_mapping;
	struct page *page;
	int err;
repeat:
	page = grab_cache_page(mapping, nid);
	if (!page)
		return ERR_PTR(-ENOMEM);

	err = read_node_page(page, READ_SYNC);
	if (err < 0)
		return ERR_PTR(err);
	else if (err == LOCKED_PAGE)
		goto got_it;

	lock_page(page);
	if (!PageUptodate(page)) {
		f2fs_put_page(page, 1);
		return ERR_PTR(-EIO);
	}
	if (page->mapping != mapping) {
		f2fs_put_page(page, 1);
		goto repeat;
	}
got_it:
	BUG_ON(nid != nid_of_node(page));
	mark_page_accessed(page);
	return page;
}

/*
 * Return a locked page for the desired node page.
 * And, readahead MAX_RA_NODE number of node pages.
 */
struct page *get_node_page_ra(struct page *parent, int start)
{
	struct f2fs_sb_info *sbi = F2FS_SB(parent->mapping->host->i_sb);
	struct address_space *mapping = sbi->node_inode->i_mapping;
	struct blk_plug plug;
	struct page *page;
	int err, i, end;
	nid_t nid;

	/* First, try getting the desired direct node. */
	nid = get_nid(parent, start, false);
	if (!nid)
		return ERR_PTR(-ENOENT);
repeat:
	page = grab_cache_page(mapping, nid);
	if (!page)
		return ERR_PTR(-ENOMEM);

	err = read_node_page(page, READ_SYNC);
	if (err < 0)
		return ERR_PTR(err);
	else if (err == LOCKED_PAGE)
		goto page_hit;

	blk_start_plug(&plug);

	/* Then, try readahead for siblings of the desired node */
	end = start + MAX_RA_NODE;
	end = min(end, NIDS_PER_BLOCK);
	for (i = start + 1; i < end; i++) {
		nid = get_nid(parent, i, false);
		if (!nid)
			continue;
		ra_node_page(sbi, nid);
	}

	blk_finish_plug(&plug);

	lock_page(page);
	if (page->mapping != mapping) {
		f2fs_put_page(page, 1);
		goto repeat;
	}
page_hit:
	if (!PageUptodate(page)) {
		f2fs_put_page(page, 1);
		return ERR_PTR(-EIO);
	}
	mark_page_accessed(page);
	return page;
}

void sync_inode_page(struct dnode_of_data *dn)
{
	if (IS_INODE(dn->node_page) || dn->inode_page == dn->node_page) {
		update_inode(dn->inode, dn->node_page);
	} else if (dn->inode_page) {
		if (!dn->inode_page_locked)
			lock_page(dn->inode_page);
		update_inode(dn->inode, dn->inode_page);
		if (!dn->inode_page_locked)
			unlock_page(dn->inode_page);
	} else {
		update_inode_page(dn->inode);
	}
}

int sync_node_pages(struct f2fs_sb_info *sbi, nid_t ino,
					struct writeback_control *wbc)
{
	struct address_space *mapping = sbi->node_inode->i_mapping;
	pgoff_t index, end;
	struct pagevec pvec;
	int step = ino ? 2 : 0;
	int nwritten = 0, wrote = 0;

	pagevec_init(&pvec, 0);

next_step:
	index = 0;
	end = LONG_MAX;

	while (index <= end) {
		int i, nr_pages;
		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
				PAGECACHE_TAG_DIRTY,
				min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
		if (nr_pages == 0)
			break;

		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];

			/*
			 * flushing sequence with step:
			 * 0. indirect nodes
			 * 1. dentry dnodes
			 * 2. file dnodes
			 */
			if (step == 0 && IS_DNODE(page))
				continue;
			if (step == 1 && (!IS_DNODE(page) ||
						is_cold_node(page)))
				continue;
			if (step == 2 && (!IS_DNODE(page) ||
						!is_cold_node(page)))
				continue;

			/*
			 * If an fsync mode,
			 * we should not skip writing node pages.
			 */
			if (ino && ino_of_node(page) == ino)
				lock_page(page);
			else if (!trylock_page(page))
				continue;

			if (unlikely(page->mapping != mapping)) {
continue_unlock:
				unlock_page(page);
				continue;
			}
			if (ino && ino_of_node(page) != ino)
				goto continue_unlock;

			if (!PageDirty(page)) {
				/* someone wrote it for us */
				goto continue_unlock;
			}

			if (!clear_page_dirty_for_io(page))
				goto continue_unlock;

			/* called by fsync() */
			if (ino && IS_DNODE(page)) {
				int mark = !is_checkpointed_node(sbi, ino);
				set_fsync_mark(page, 1);
				if (IS_INODE(page))
					set_dentry_mark(page, mark);
				nwritten++;
			} else {
				set_fsync_mark(page, 0);
				set_dentry_mark(page, 0);
			}
			mapping->a_ops->writepage(page, wbc);
			wrote++;

			if (--wbc->nr_to_write == 0)
				break;
		}
		pagevec_release(&pvec);
		cond_resched();

		if (wbc->nr_to_write == 0) {
			step = 2;
			break;
		}
	}

	if (step < 2) {
		step++;
		goto next_step;
	}

	if (wrote)
		f2fs_submit_bio(sbi, NODE, wbc->sync_mode == WB_SYNC_ALL);

	return nwritten;
}

static int f2fs_write_node_page(struct page *page,
				struct writeback_control *wbc)
{
	struct f2fs_sb_info *sbi = F2FS_SB(page->mapping->host->i_sb);
	nid_t nid;
	block_t new_addr;
	struct node_info ni;

	wait_on_page_writeback(page);

	/* get old block addr of this node page */
	nid = nid_of_node(page);
	BUG_ON(page->index != nid);

	get_node_info(sbi, nid, &ni);

	/* This page is already truncated */
	if (ni.blk_addr == NULL_ADDR) {
		dec_page_count(sbi, F2FS_DIRTY_NODES);
		unlock_page(page);
		return 0;
	}

	if (wbc->for_reclaim) {
		dec_page_count(sbi, F2FS_DIRTY_NODES);
		wbc->pages_skipped++;
		set_page_dirty(page);
		return AOP_WRITEPAGE_ACTIVATE;
	}

	mutex_lock(&sbi->node_write);
	set_page_writeback(page);
	write_node_page(sbi, page, nid, ni.blk_addr, &new_addr);
	set_node_addr(sbi, &ni, new_addr);
	dec_page_count(sbi, F2FS_DIRTY_NODES);
	mutex_unlock(&sbi->node_write);
	unlock_page(page);
	return 0;
}

/*
 * It is very important to gather dirty pages and write at once, so that we can
 * submit a big bio without interfering other data writes.
 * Be default, 512 pages (2MB) * 3 node types, is more reasonable.
 */
#define COLLECT_DIRTY_NODES	1536
static int f2fs_write_node_pages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
	long nr_to_write = wbc->nr_to_write;

	/* First check balancing cached NAT entries */
	if (try_to_free_nats(sbi, NAT_ENTRY_PER_BLOCK)) {
		f2fs_sync_fs(sbi->sb, true);
		return 0;
	}

	/* collect a number of dirty node pages and write together */
	if (get_pages(sbi, F2FS_DIRTY_NODES) < COLLECT_DIRTY_NODES)
		return 0;

	/* if mounting is failed, skip writing node pages */
	wbc->nr_to_write = 3 * max_hw_blocks(sbi);
	sync_node_pages(sbi, 0, wbc);
	wbc->nr_to_write = nr_to_write - (3 * max_hw_blocks(sbi) -
						wbc->nr_to_write);
	return 0;
}

static int f2fs_set_node_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);

	SetPageUptodate(page);
	if (!PageDirty(page)) {
		__set_page_dirty_nobuffers(page);
		inc_page_count(sbi, F2FS_DIRTY_NODES);
		SetPagePrivate(page);
		return 1;
	}
	return 0;
}

static void f2fs_invalidate_node_page(struct page *page, unsigned int offset,
				      unsigned int length)
{
	struct inode *inode = page->mapping->host;
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	if (PageDirty(page))
		dec_page_count(sbi, F2FS_DIRTY_NODES);
	ClearPagePrivate(page);
}

static int f2fs_release_node_page(struct page *page, gfp_t wait)
{
	ClearPagePrivate(page);
	return 1;
}

/*
 * Structure of the f2fs node operations
 */
const struct address_space_operations f2fs_node_aops = {
	.writepage	= f2fs_write_node_page,
	.writepages	= f2fs_write_node_pages,
	.set_page_dirty	= f2fs_set_node_page_dirty,
	.invalidatepage	= f2fs_invalidate_node_page,
	.releasepage	= f2fs_release_node_page,
};

static struct free_nid *__lookup_free_nid_list(nid_t n, struct list_head *head)
{
	struct list_head *this;
	struct free_nid *i;
	list_for_each(this, head) {
		i = list_entry(this, struct free_nid, list);
		if (i->nid == n)
			return i;
	}
	return NULL;
}

static void __del_from_free_nid_list(struct free_nid *i)
{
	list_del(&i->list);
	kmem_cache_free(free_nid_slab, i);
}

static int add_free_nid(struct f2fs_nm_info *nm_i, nid_t nid, bool build)
{
	struct free_nid *i;
	struct nat_entry *ne;
	bool allocated = false;

	if (nm_i->fcnt > 2 * MAX_FREE_NIDS)
		return -1;

	/* 0 nid should not be used */
	if (nid == 0)
		return 0;

	if (!build)
		goto retry;

	/* do not add allocated nids */
	read_lock(&nm_i->nat_tree_lock);
	ne = __lookup_nat_cache(nm_i, nid);
	if (ne && nat_get_blkaddr(ne) != NULL_ADDR)
		allocated = true;
	read_unlock(&nm_i->nat_tree_lock);
	if (allocated)
		return 0;
retry:
	i = kmem_cache_alloc(free_nid_slab, GFP_NOFS);
	if (!i) {
		cond_resched();
		goto retry;
	}
	i->nid = nid;
	i->state = NID_NEW;

	spin_lock(&nm_i->free_nid_list_lock);
	if (__lookup_free_nid_list(nid, &nm_i->free_nid_list)) {
		spin_unlock(&nm_i->free_nid_list_lock);
		kmem_cache_free(free_nid_slab, i);
		return 0;
	}
	list_add_tail(&i->list, &nm_i->free_nid_list);
	nm_i->fcnt++;
	spin_unlock(&nm_i->free_nid_list_lock);
	return 1;
}

static void remove_free_nid(struct f2fs_nm_info *nm_i, nid_t nid)
{
	struct free_nid *i;
	spin_lock(&nm_i->free_nid_list_lock);
	i = __lookup_free_nid_list(nid, &nm_i->free_nid_list);
	if (i && i->state == NID_NEW) {
		__del_from_free_nid_list(i);
		nm_i->fcnt--;
	}
	spin_unlock(&nm_i->free_nid_list_lock);
}

static void scan_nat_page(struct f2fs_nm_info *nm_i,
			struct page *nat_page, nid_t start_nid)
{
	struct f2fs_nat_block *nat_blk = page_address(nat_page);
	block_t blk_addr;
	int i;

	i = start_nid % NAT_ENTRY_PER_BLOCK;

	for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) {

		if (start_nid >= nm_i->max_nid)
			break;

		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
		BUG_ON(blk_addr == NEW_ADDR);
		if (blk_addr == NULL_ADDR) {
			if (add_free_nid(nm_i, start_nid, true) < 0)
				break;
		}
	}
}

static void build_free_nids(struct f2fs_sb_info *sbi)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
	struct f2fs_summary_block *sum = curseg->sum_blk;
	int i = 0;
	nid_t nid = nm_i->next_scan_nid;

	/* Enough entries */
	if (nm_i->fcnt > NAT_ENTRY_PER_BLOCK)
		return;

	/* readahead nat pages to be scanned */
	ra_nat_pages(sbi, nid);

	while (1) {
		struct page *page = get_current_nat_page(sbi, nid);

		scan_nat_page(nm_i, page, nid);
		f2fs_put_page(page, 1);

		nid += (NAT_ENTRY_PER_BLOCK - (nid % NAT_ENTRY_PER_BLOCK));
		if (nid >= nm_i->max_nid)
			nid = 0;

		if (i++ == FREE_NID_PAGES)
			break;
	}

	/* go to the next free nat pages to find free nids abundantly */
	nm_i->next_scan_nid = nid;

	/* find free nids from current sum_pages */
	mutex_lock(&curseg->curseg_mutex);
	for (i = 0; i < nats_in_cursum(sum); i++) {
		block_t addr = le32_to_cpu(nat_in_journal(sum, i).block_addr);
		nid = le32_to_cpu(nid_in_journal(sum, i));
		if (addr == NULL_ADDR)
			add_free_nid(nm_i, nid, true);
		else
			remove_free_nid(nm_i, nid);
	}
	mutex_unlock(&curseg->curseg_mutex);
}

/*
 * If this function returns success, caller can obtain a new nid
 * from second parameter of this function.
 * The returned nid could be used ino as well as nid when inode is created.
 */
bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct free_nid *i = NULL;
	struct list_head *this;
retry:
	if (sbi->total_valid_node_count + 1 >= nm_i->max_nid)
		return false;

	spin_lock(&nm_i->free_nid_list_lock);

	/* We should not use stale free nids created by build_free_nids */
	if (nm_i->fcnt && !sbi->on_build_free_nids) {
		BUG_ON(list_empty(&nm_i->free_nid_list));
		list_for_each(this, &nm_i->free_nid_list) {
			i = list_entry(this, struct free_nid, list);
			if (i->state == NID_NEW)
				break;
		}

		BUG_ON(i->state != NID_NEW);
		*nid = i->nid;
		i->state = NID_ALLOC;
		nm_i->fcnt--;
		spin_unlock(&nm_i->free_nid_list_lock);
		return true;
	}
	spin_unlock(&nm_i->free_nid_list_lock);

	/* Let's scan nat pages and its caches to get free nids */
	mutex_lock(&nm_i->build_lock);
	sbi->on_build_free_nids = 1;
	build_free_nids(sbi);
	sbi->on_build_free_nids = 0;
	mutex_unlock(&nm_i->build_lock);
	goto retry;
}

/*
 * alloc_nid() should be called prior to this function.
 */
void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct free_nid *i;

	spin_lock(&nm_i->free_nid_list_lock);
	i = __lookup_free_nid_list(nid, &nm_i->free_nid_list);
	BUG_ON(!i || i->state != NID_ALLOC);
	__del_from_free_nid_list(i);
	spin_unlock(&nm_i->free_nid_list_lock);
}

/*
 * alloc_nid() should be called prior to this function.
 */
void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct free_nid *i;

	if (!nid)
		return;

	spin_lock(&nm_i->free_nid_list_lock);
	i = __lookup_free_nid_list(nid, &nm_i->free_nid_list);
	BUG_ON(!i || i->state != NID_ALLOC);
	if (nm_i->fcnt > 2 * MAX_FREE_NIDS) {
		__del_from_free_nid_list(i);
	} else {
		i->state = NID_NEW;
		nm_i->fcnt++;
	}
	spin_unlock(&nm_i->free_nid_list_lock);
}

void recover_node_page(struct f2fs_sb_info *sbi, struct page *page,
		struct f2fs_summary *sum, struct node_info *ni,
		block_t new_blkaddr)
{
	rewrite_node_page(sbi, page, sum, ni->blk_addr, new_blkaddr);
	set_node_addr(sbi, ni, new_blkaddr);
	clear_node_page_dirty(page);
}

int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
{
	struct address_space *mapping = sbi->node_inode->i_mapping;
	struct f2fs_node *src, *dst;
	nid_t ino = ino_of_node(page);
	struct node_info old_ni, new_ni;
	struct page *ipage;

	ipage = grab_cache_page(mapping, ino);
	if (!ipage)
		return -ENOMEM;

	/* Should not use this inode  from free nid list */
	remove_free_nid(NM_I(sbi), ino);

	get_node_info(sbi, ino, &old_ni);
	SetPageUptodate(ipage);
	fill_node_footer(ipage, ino, ino, 0, true);

	src = F2FS_NODE(page);
	dst = F2FS_NODE(ipage);

	memcpy(dst, src, (unsigned long)&src->i.i_ext - (unsigned long)&src->i);
	dst->i.i_size = 0;
	dst->i.i_blocks = cpu_to_le64(1);
	dst->i.i_links = cpu_to_le32(1);
	dst->i.i_xattr_nid = 0;

	new_ni = old_ni;
	new_ni.ino = ino;

	if (!inc_valid_node_count(sbi, NULL, 1))
		WARN_ON(1);
	set_node_addr(sbi, &new_ni, NEW_ADDR);
	inc_valid_inode_count(sbi);
	f2fs_put_page(ipage, 1);
	return 0;
}

int restore_node_summary(struct f2fs_sb_info *sbi,
			unsigned int segno, struct f2fs_summary_block *sum)
{
	struct f2fs_node *rn;
	struct f2fs_summary *sum_entry;
	struct page *page;
	block_t addr;
	int i, last_offset;

	/* alloc temporal page for read node */
	page = alloc_page(GFP_NOFS | __GFP_ZERO);
	if (!page)
		return -ENOMEM;
	lock_page(page);

	/* scan the node segment */
	last_offset = sbi->blocks_per_seg;
	addr = START_BLOCK(sbi, segno);
	sum_entry = &sum->entries[0];

	for (i = 0; i < last_offset; i++, sum_entry++) {
		/*
		 * In order to read next node page,
		 * we must clear PageUptodate flag.
		 */
		ClearPageUptodate(page);

		if (f2fs_readpage(sbi, page, addr, READ_SYNC))
			goto out;

		lock_page(page);
		rn = F2FS_NODE(page);
		sum_entry->nid = rn->footer.nid;
		sum_entry->version = 0;
		sum_entry->ofs_in_node = 0;
		addr++;
	}
	unlock_page(page);
out:
	__free_pages(page, 0);
	return 0;
}

static bool flush_nats_in_journal(struct f2fs_sb_info *sbi)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
	struct f2fs_summary_block *sum = curseg->sum_blk;
	int i;

	mutex_lock(&curseg->curseg_mutex);

	if (nats_in_cursum(sum) < NAT_JOURNAL_ENTRIES) {
		mutex_unlock(&curseg->curseg_mutex);
		return false;
	}

	for (i = 0; i < nats_in_cursum(sum); i++) {
		struct nat_entry *ne;
		struct f2fs_nat_entry raw_ne;
		nid_t nid = le32_to_cpu(nid_in_journal(sum, i));

		raw_ne = nat_in_journal(sum, i);
retry:
		write_lock(&nm_i->nat_tree_lock);
		ne = __lookup_nat_cache(nm_i, nid);
		if (ne) {
			__set_nat_cache_dirty(nm_i, ne);
			write_unlock(&nm_i->nat_tree_lock);
			continue;
		}
		ne = grab_nat_entry(nm_i, nid);
		if (!ne) {
			write_unlock(&nm_i->nat_tree_lock);
			goto retry;
		}
		nat_set_blkaddr(ne, le32_to_cpu(raw_ne.block_addr));
		nat_set_ino(ne, le32_to_cpu(raw_ne.ino));
		nat_set_version(ne, raw_ne.version);
		__set_nat_cache_dirty(nm_i, ne);
		write_unlock(&nm_i->nat_tree_lock);
	}
	update_nats_in_cursum(sum, -i);
	mutex_unlock(&curseg->curseg_mutex);
	return true;
}

/*
 * This function is called during the checkpointing process.
 */
void flush_nat_entries(struct f2fs_sb_info *sbi)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
	struct f2fs_summary_block *sum = curseg->sum_blk;
	struct list_head *cur, *n;
	struct page *page = NULL;
	struct f2fs_nat_block *nat_blk = NULL;
	nid_t start_nid = 0, end_nid = 0;
	bool flushed;

	flushed = flush_nats_in_journal(sbi);

	if (!flushed)
		mutex_lock(&curseg->curseg_mutex);

	/* 1) flush dirty nat caches */
	list_for_each_safe(cur, n, &nm_i->dirty_nat_entries) {
		struct nat_entry *ne;
		nid_t nid;
		struct f2fs_nat_entry raw_ne;
		int offset = -1;
		block_t new_blkaddr;

		ne = list_entry(cur, struct nat_entry, list);
		nid = nat_get_nid(ne);

		if (nat_get_blkaddr(ne) == NEW_ADDR)
			continue;
		if (flushed)
			goto to_nat_page;

		/* if there is room for nat enries in curseg->sumpage */
		offset = lookup_journal_in_cursum(sum, NAT_JOURNAL, nid, 1);
		if (offset >= 0) {
			raw_ne = nat_in_journal(sum, offset);
			goto flush_now;
		}
to_nat_page:
		if (!page || (start_nid > nid || nid > end_nid)) {
			if (page) {
				f2fs_put_page(page, 1);
				page = NULL;
			}
			start_nid = START_NID(nid);
			end_nid = start_nid + NAT_ENTRY_PER_BLOCK - 1;

			/*
			 * get nat block with dirty flag, increased reference
			 * count, mapped and lock
			 */
			page = get_next_nat_page(sbi, start_nid);
			nat_blk = page_address(page);
		}

		BUG_ON(!nat_blk);
		raw_ne = nat_blk->entries[nid - start_nid];
flush_now:
		new_blkaddr = nat_get_blkaddr(ne);

		raw_ne.ino = cpu_to_le32(nat_get_ino(ne));
		raw_ne.block_addr = cpu_to_le32(new_blkaddr);
		raw_ne.version = nat_get_version(ne);

		if (offset < 0) {
			nat_blk->entries[nid - start_nid] = raw_ne;
		} else {
			nat_in_journal(sum, offset) = raw_ne;
			nid_in_journal(sum, offset) = cpu_to_le32(nid);
		}

		if (nat_get_blkaddr(ne) == NULL_ADDR &&
				add_free_nid(NM_I(sbi), nid, false) <= 0) {
			write_lock(&nm_i->nat_tree_lock);
			__del_from_nat_cache(nm_i, ne);
			write_unlock(&nm_i->nat_tree_lock);
		} else {
			write_lock(&nm_i->nat_tree_lock);
			__clear_nat_cache_dirty(nm_i, ne);
			ne->checkpointed = true;
			write_unlock(&nm_i->nat_tree_lock);
		}
	}
	if (!flushed)
		mutex_unlock(&curseg->curseg_mutex);
	f2fs_put_page(page, 1);

	/* 2) shrink nat caches if necessary */
	try_to_free_nats(sbi, nm_i->nat_cnt - NM_WOUT_THRESHOLD);
}

static int init_node_manager(struct f2fs_sb_info *sbi)
{
	struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	unsigned char *version_bitmap;
	unsigned int nat_segs, nat_blocks;

	nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr);

	/* segment_count_nat includes pair segment so divide to 2. */
	nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
	nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
	nm_i->fcnt = 0;
	nm_i->nat_cnt = 0;

	INIT_LIST_HEAD(&nm_i->free_nid_list);
	INIT_RADIX_TREE(&nm_i->nat_root, GFP_ATOMIC);
	INIT_LIST_HEAD(&nm_i->nat_entries);
	INIT_LIST_HEAD(&nm_i->dirty_nat_entries);

	mutex_init(&nm_i->build_lock);
	spin_lock_init(&nm_i->free_nid_list_lock);
	rwlock_init(&nm_i->nat_tree_lock);

	nm_i->next_scan_nid = le32_to_cpu(sbi->ckpt->next_free_nid);
	nm_i->bitmap_size = __bitmap_size(sbi, NAT_BITMAP);
	version_bitmap = __bitmap_ptr(sbi, NAT_BITMAP);
	if (!version_bitmap)
		return -EFAULT;

	nm_i->nat_bitmap = kmemdup(version_bitmap, nm_i->bitmap_size,
					GFP_KERNEL);
	if (!nm_i->nat_bitmap)
		return -ENOMEM;
	return 0;
}

int build_node_manager(struct f2fs_sb_info *sbi)
{
	int err;

	sbi->nm_info = kzalloc(sizeof(struct f2fs_nm_info), GFP_KERNEL);
	if (!sbi->nm_info)
		return -ENOMEM;

	err = init_node_manager(sbi);
	if (err)
		return err;

	build_free_nids(sbi);
	return 0;
}

void destroy_node_manager(struct f2fs_sb_info *sbi)
{
	struct f2fs_nm_info *nm_i = NM_I(sbi);
	struct free_nid *i, *next_i;
	struct nat_entry *natvec[NATVEC_SIZE];
	nid_t nid = 0;
	unsigned int found;

	if (!nm_i)
		return;

	/* destroy free nid list */
	spin_lock(&nm_i->free_nid_list_lock);
	list_for_each_entry_safe(i, next_i, &nm_i->free_nid_list, list) {
		BUG_ON(i->state == NID_ALLOC);
		__del_from_free_nid_list(i);
		nm_i->fcnt--;
	}
	BUG_ON(nm_i->fcnt);
	spin_unlock(&nm_i->free_nid_list_lock);

	/* destroy nat cache */
	write_lock(&nm_i->nat_tree_lock);
	while ((found = __gang_lookup_nat_cache(nm_i,
					nid, NATVEC_SIZE, natvec))) {
		unsigned idx;
		for (idx = 0; idx < found; idx++) {
			struct nat_entry *e = natvec[idx];
			nid = nat_get_nid(e) + 1;
			__del_from_nat_cache(nm_i, e);
		}
	}
	BUG_ON(nm_i->nat_cnt);
	write_unlock(&nm_i->nat_tree_lock);

	kfree(nm_i->nat_bitmap);
	sbi->nm_info = NULL;
	kfree(nm_i);
}

int __init create_node_manager_caches(void)
{
	nat_entry_slab = f2fs_kmem_cache_create("nat_entry",
			sizeof(struct nat_entry), NULL);
	if (!nat_entry_slab)
		return -ENOMEM;

	free_nid_slab = f2fs_kmem_cache_create("free_nid",
			sizeof(struct free_nid), NULL);
	if (!free_nid_slab) {
		kmem_cache_destroy(nat_entry_slab);
		return -ENOMEM;
	}
	return 0;
}

void destroy_node_manager_caches(void)
{
	kmem_cache_destroy(free_nid_slab);
	kmem_cache_destroy(nat_entry_slab);
}