summaryrefslogtreecommitdiff
path: root/fs/btrfs/defrag.c
blob: 5244561e201682a3c69a3fc077aa9e11847fd958 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/sched.h>
#include "ctree.h"
#include "disk-io.h"
#include "print-tree.h"
#include "transaction.h"
#include "locking.h"
#include "accessors.h"
#include "messages.h"
#include "delalloc-space.h"
#include "subpage.h"
#include "defrag.h"
#include "file-item.h"
#include "super.h"

static struct kmem_cache *btrfs_inode_defrag_cachep;

/*
 * When auto defrag is enabled we queue up these defrag structs to remember
 * which inodes need defragging passes.
 */
struct inode_defrag {
	struct rb_node rb_node;
	/* Inode number */
	u64 ino;
	/*
	 * Transid where the defrag was added, we search for extents newer than
	 * this.
	 */
	u64 transid;

	/* Root objectid */
	u64 root;

	/*
	 * The extent size threshold for autodefrag.
	 *
	 * This value is different for compressed/non-compressed extents, thus
	 * needs to be passed from higher layer.
	 * (aka, inode_should_defrag())
	 */
	u32 extent_thresh;
};

static int __compare_inode_defrag(struct inode_defrag *defrag1,
				  struct inode_defrag *defrag2)
{
	if (defrag1->root > defrag2->root)
		return 1;
	else if (defrag1->root < defrag2->root)
		return -1;
	else if (defrag1->ino > defrag2->ino)
		return 1;
	else if (defrag1->ino < defrag2->ino)
		return -1;
	else
		return 0;
}

/*
 * Pop a record for an inode into the defrag tree.  The lock must be held
 * already.
 *
 * If you're inserting a record for an older transid than an existing record,
 * the transid already in the tree is lowered.
 *
 * If an existing record is found the defrag item you pass in is freed.
 */
static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
				    struct inode_defrag *defrag)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct inode_defrag *entry;
	struct rb_node **p;
	struct rb_node *parent = NULL;
	int ret;

	p = &fs_info->defrag_inodes.rb_node;
	while (*p) {
		parent = *p;
		entry = rb_entry(parent, struct inode_defrag, rb_node);

		ret = __compare_inode_defrag(defrag, entry);
		if (ret < 0)
			p = &parent->rb_left;
		else if (ret > 0)
			p = &parent->rb_right;
		else {
			/*
			 * If we're reinserting an entry for an old defrag run,
			 * make sure to lower the transid of our existing
			 * record.
			 */
			if (defrag->transid < entry->transid)
				entry->transid = defrag->transid;
			entry->extent_thresh = min(defrag->extent_thresh,
						   entry->extent_thresh);
			return -EEXIST;
		}
	}
	set_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags);
	rb_link_node(&defrag->rb_node, parent, p);
	rb_insert_color(&defrag->rb_node, &fs_info->defrag_inodes);
	return 0;
}

static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
{
	if (!btrfs_test_opt(fs_info, AUTO_DEFRAG))
		return 0;

	if (btrfs_fs_closing(fs_info))
		return 0;

	return 1;
}

/*
 * Insert a defrag record for this inode if auto defrag is enabled.
 */
int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
			   struct btrfs_inode *inode, u32 extent_thresh)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct inode_defrag *defrag;
	u64 transid;
	int ret;

	if (!__need_auto_defrag(fs_info))
		return 0;

	if (test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags))
		return 0;

	if (trans)
		transid = trans->transid;
	else
		transid = inode->root->last_trans;

	defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS);
	if (!defrag)
		return -ENOMEM;

	defrag->ino = btrfs_ino(inode);
	defrag->transid = transid;
	defrag->root = root->root_key.objectid;
	defrag->extent_thresh = extent_thresh;

	spin_lock(&fs_info->defrag_inodes_lock);
	if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) {
		/*
		 * If we set IN_DEFRAG flag and evict the inode from memory,
		 * and then re-read this inode, this new inode doesn't have
		 * IN_DEFRAG flag. At the case, we may find the existed defrag.
		 */
		ret = __btrfs_add_inode_defrag(inode, defrag);
		if (ret)
			kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
	} else {
		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
	}
	spin_unlock(&fs_info->defrag_inodes_lock);
	return 0;
}

/*
 * Pick the defragable inode that we want, if it doesn't exist, we will get the
 * next one.
 */
static struct inode_defrag *btrfs_pick_defrag_inode(
			struct btrfs_fs_info *fs_info, u64 root, u64 ino)
{
	struct inode_defrag *entry = NULL;
	struct inode_defrag tmp;
	struct rb_node *p;
	struct rb_node *parent = NULL;
	int ret;

	tmp.ino = ino;
	tmp.root = root;

	spin_lock(&fs_info->defrag_inodes_lock);
	p = fs_info->defrag_inodes.rb_node;
	while (p) {
		parent = p;
		entry = rb_entry(parent, struct inode_defrag, rb_node);

		ret = __compare_inode_defrag(&tmp, entry);
		if (ret < 0)
			p = parent->rb_left;
		else if (ret > 0)
			p = parent->rb_right;
		else
			goto out;
	}

	if (parent && __compare_inode_defrag(&tmp, entry) > 0) {
		parent = rb_next(parent);
		if (parent)
			entry = rb_entry(parent, struct inode_defrag, rb_node);
		else
			entry = NULL;
	}
out:
	if (entry)
		rb_erase(parent, &fs_info->defrag_inodes);
	spin_unlock(&fs_info->defrag_inodes_lock);
	return entry;
}

void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info)
{
	struct inode_defrag *defrag;
	struct rb_node *node;

	spin_lock(&fs_info->defrag_inodes_lock);
	node = rb_first(&fs_info->defrag_inodes);
	while (node) {
		rb_erase(node, &fs_info->defrag_inodes);
		defrag = rb_entry(node, struct inode_defrag, rb_node);
		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);

		cond_resched_lock(&fs_info->defrag_inodes_lock);

		node = rb_first(&fs_info->defrag_inodes);
	}
	spin_unlock(&fs_info->defrag_inodes_lock);
}

#define BTRFS_DEFRAG_BATCH	1024

static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
				    struct inode_defrag *defrag)
{
	struct btrfs_root *inode_root;
	struct inode *inode;
	struct btrfs_ioctl_defrag_range_args range;
	int ret = 0;
	u64 cur = 0;

again:
	if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state))
		goto cleanup;
	if (!__need_auto_defrag(fs_info))
		goto cleanup;

	/* Get the inode */
	inode_root = btrfs_get_fs_root(fs_info, defrag->root, true);
	if (IS_ERR(inode_root)) {
		ret = PTR_ERR(inode_root);
		goto cleanup;
	}

	inode = btrfs_iget(fs_info->sb, defrag->ino, inode_root);
	btrfs_put_root(inode_root);
	if (IS_ERR(inode)) {
		ret = PTR_ERR(inode);
		goto cleanup;
	}

	if (cur >= i_size_read(inode)) {
		iput(inode);
		goto cleanup;
	}

	/* Do a chunk of defrag */
	clear_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
	memset(&range, 0, sizeof(range));
	range.len = (u64)-1;
	range.start = cur;
	range.extent_thresh = defrag->extent_thresh;

	sb_start_write(fs_info->sb);
	ret = btrfs_defrag_file(inode, NULL, &range, defrag->transid,
				       BTRFS_DEFRAG_BATCH);
	sb_end_write(fs_info->sb);
	iput(inode);

	if (ret < 0)
		goto cleanup;

	cur = max(cur + fs_info->sectorsize, range.start);
	goto again;

cleanup:
	kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
	return ret;
}

/*
 * Run through the list of inodes in the FS that need defragging.
 */
int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
{
	struct inode_defrag *defrag;
	u64 first_ino = 0;
	u64 root_objectid = 0;

	atomic_inc(&fs_info->defrag_running);
	while (1) {
		/* Pause the auto defragger. */
		if (test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state))
			break;

		if (!__need_auto_defrag(fs_info))
			break;

		/* find an inode to defrag */
		defrag = btrfs_pick_defrag_inode(fs_info, root_objectid, first_ino);
		if (!defrag) {
			if (root_objectid || first_ino) {
				root_objectid = 0;
				first_ino = 0;
				continue;
			} else {
				break;
			}
		}

		first_ino = defrag->ino + 1;
		root_objectid = defrag->root;

		__btrfs_run_defrag_inode(fs_info, defrag);
	}
	atomic_dec(&fs_info->defrag_running);

	/*
	 * During unmount, we use the transaction_wait queue to wait for the
	 * defragger to stop.
	 */
	wake_up(&fs_info->transaction_wait);
	return 0;
}

/*
 * Check if two blocks addresses are close, used by defrag.
 */
static bool close_blocks(u64 blocknr, u64 other, u32 blocksize)
{
	if (blocknr < other && other - (blocknr + blocksize) < SZ_32K)
		return true;
	if (blocknr > other && blocknr - (other + blocksize) < SZ_32K)
		return true;
	return false;
}

/*
 * Go through all the leaves pointed to by a node and reallocate them so that
 * disk order is close to key order.
 */
static int btrfs_realloc_node(struct btrfs_trans_handle *trans,
			      struct btrfs_root *root,
			      struct extent_buffer *parent,
			      int start_slot, u64 *last_ret,
			      struct btrfs_key *progress)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	const u32 blocksize = fs_info->nodesize;
	const int end_slot = btrfs_header_nritems(parent) - 1;
	u64 search_start = *last_ret;
	u64 last_block = 0;
	int ret = 0;
	bool progress_passed = false;

	/*
	 * COWing must happen through a running transaction, which always
	 * matches the current fs generation (it's a transaction with a state
	 * less than TRANS_STATE_UNBLOCKED). If it doesn't, then turn the fs
	 * into error state to prevent the commit of any transaction.
	 */
	if (unlikely(trans->transaction != fs_info->running_transaction ||
		     trans->transid != fs_info->generation)) {
		btrfs_abort_transaction(trans, -EUCLEAN);
		btrfs_crit(fs_info,
"unexpected transaction when attempting to reallocate parent %llu for root %llu, transaction %llu running transaction %llu fs generation %llu",
			   parent->start, btrfs_root_id(root), trans->transid,
			   fs_info->running_transaction->transid,
			   fs_info->generation);
		return -EUCLEAN;
	}

	if (btrfs_header_nritems(parent) <= 1)
		return 0;

	for (int i = start_slot; i <= end_slot; i++) {
		struct extent_buffer *cur;
		struct btrfs_disk_key disk_key;
		u64 blocknr;
		u64 other;
		bool close = true;

		btrfs_node_key(parent, &disk_key, i);
		if (!progress_passed && btrfs_comp_keys(&disk_key, progress) < 0)
			continue;

		progress_passed = true;
		blocknr = btrfs_node_blockptr(parent, i);
		if (last_block == 0)
			last_block = blocknr;

		if (i > 0) {
			other = btrfs_node_blockptr(parent, i - 1);
			close = close_blocks(blocknr, other, blocksize);
		}
		if (!close && i < end_slot) {
			other = btrfs_node_blockptr(parent, i + 1);
			close = close_blocks(blocknr, other, blocksize);
		}
		if (close) {
			last_block = blocknr;
			continue;
		}

		cur = btrfs_read_node_slot(parent, i);
		if (IS_ERR(cur))
			return PTR_ERR(cur);
		if (search_start == 0)
			search_start = last_block;

		btrfs_tree_lock(cur);
		ret = btrfs_force_cow_block(trans, root, cur, parent, i,
					    &cur, search_start,
					    min(16 * blocksize,
						(end_slot - i) * blocksize),
					    BTRFS_NESTING_COW);
		if (ret) {
			btrfs_tree_unlock(cur);
			free_extent_buffer(cur);
			break;
		}
		search_start = cur->start;
		last_block = cur->start;
		*last_ret = search_start;
		btrfs_tree_unlock(cur);
		free_extent_buffer(cur);
	}
	return ret;
}

/*
 * Defrag all the leaves in a given btree.
 * Read all the leaves and try to get key order to
 * better reflect disk order
 */

static int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root)
{
	struct btrfs_path *path = NULL;
	struct btrfs_key key;
	int ret = 0;
	int wret;
	int level;
	int next_key_ret = 0;
	u64 last_ret = 0;

	if (!test_bit(BTRFS_ROOT_SHAREABLE, &root->state))
		goto out;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	level = btrfs_header_level(root->node);

	if (level == 0)
		goto out;

	if (root->defrag_progress.objectid == 0) {
		struct extent_buffer *root_node;
		u32 nritems;

		root_node = btrfs_lock_root_node(root);
		nritems = btrfs_header_nritems(root_node);
		root->defrag_max.objectid = 0;
		/* from above we know this is not a leaf */
		btrfs_node_key_to_cpu(root_node, &root->defrag_max,
				      nritems - 1);
		btrfs_tree_unlock(root_node);
		free_extent_buffer(root_node);
		memset(&key, 0, sizeof(key));
	} else {
		memcpy(&key, &root->defrag_progress, sizeof(key));
	}

	path->keep_locks = 1;

	ret = btrfs_search_forward(root, &key, path, BTRFS_OLDEST_GENERATION);
	if (ret < 0)
		goto out;
	if (ret > 0) {
		ret = 0;
		goto out;
	}
	btrfs_release_path(path);
	/*
	 * We don't need a lock on a leaf. btrfs_realloc_node() will lock all
	 * leafs from path->nodes[1], so set lowest_level to 1 to avoid later
	 * a deadlock (attempting to write lock an already write locked leaf).
	 */
	path->lowest_level = 1;
	wret = btrfs_search_slot(trans, root, &key, path, 0, 1);

	if (wret < 0) {
		ret = wret;
		goto out;
	}
	if (!path->nodes[1]) {
		ret = 0;
		goto out;
	}
	/*
	 * The node at level 1 must always be locked when our path has
	 * keep_locks set and lowest_level is 1, regardless of the value of
	 * path->slots[1].
	 */
	BUG_ON(path->locks[1] == 0);
	ret = btrfs_realloc_node(trans, root,
				 path->nodes[1], 0,
				 &last_ret,
				 &root->defrag_progress);
	if (ret) {
		WARN_ON(ret == -EAGAIN);
		goto out;
	}
	/*
	 * Now that we reallocated the node we can find the next key. Note that
	 * btrfs_find_next_key() can release our path and do another search
	 * without COWing, this is because even with path->keep_locks = 1,
	 * btrfs_search_slot() / ctree.c:unlock_up() does not keeps a lock on a
	 * node when path->slots[node_level - 1] does not point to the last
	 * item or a slot beyond the last item (ctree.c:unlock_up()). Therefore
	 * we search for the next key after reallocating our node.
	 */
	path->slots[1] = btrfs_header_nritems(path->nodes[1]);
	next_key_ret = btrfs_find_next_key(root, path, &key, 1,
					   BTRFS_OLDEST_GENERATION);
	if (next_key_ret == 0) {
		memcpy(&root->defrag_progress, &key, sizeof(key));
		ret = -EAGAIN;
	}
out:
	btrfs_free_path(path);
	if (ret == -EAGAIN) {
		if (root->defrag_max.objectid > root->defrag_progress.objectid)
			goto done;
		if (root->defrag_max.type > root->defrag_progress.type)
			goto done;
		if (root->defrag_max.offset > root->defrag_progress.offset)
			goto done;
		ret = 0;
	}
done:
	if (ret != -EAGAIN)
		memset(&root->defrag_progress, 0,
		       sizeof(root->defrag_progress));

	return ret;
}

/*
 * Defrag a given btree.  Every leaf in the btree is read and defragmented.
 */
int btrfs_defrag_root(struct btrfs_root *root)
{
	struct btrfs_fs_info *fs_info = root->fs_info;
	int ret;

	if (test_and_set_bit(BTRFS_ROOT_DEFRAG_RUNNING, &root->state))
		return 0;

	while (1) {
		struct btrfs_trans_handle *trans;

		trans = btrfs_start_transaction(root, 0);
		if (IS_ERR(trans)) {
			ret = PTR_ERR(trans);
			break;
		}

		ret = btrfs_defrag_leaves(trans, root);

		btrfs_end_transaction(trans);
		btrfs_btree_balance_dirty(fs_info);
		cond_resched();

		if (btrfs_fs_closing(fs_info) || ret != -EAGAIN)
			break;

		if (btrfs_defrag_cancelled(fs_info)) {
			btrfs_debug(fs_info, "defrag_root cancelled");
			ret = -EAGAIN;
			break;
		}
	}
	clear_bit(BTRFS_ROOT_DEFRAG_RUNNING, &root->state);
	return ret;
}

/*
 * Defrag specific helper to get an extent map.
 *
 * Differences between this and btrfs_get_extent() are:
 *
 * - No extent_map will be added to inode->extent_tree
 *   To reduce memory usage in the long run.
 *
 * - Extra optimization to skip file extents older than @newer_than
 *   By using btrfs_search_forward() we can skip entire file ranges that
 *   have extents created in past transactions, because btrfs_search_forward()
 *   will not visit leaves and nodes with a generation smaller than given
 *   minimal generation threshold (@newer_than).
 *
 * Return valid em if we find a file extent matching the requirement.
 * Return NULL if we can not find a file extent matching the requirement.
 *
 * Return ERR_PTR() for error.
 */
static struct extent_map *defrag_get_extent(struct btrfs_inode *inode,
					    u64 start, u64 newer_than)
{
	struct btrfs_root *root = inode->root;
	struct btrfs_file_extent_item *fi;
	struct btrfs_path path = { 0 };
	struct extent_map *em;
	struct btrfs_key key;
	u64 ino = btrfs_ino(inode);
	int ret;

	em = alloc_extent_map();
	if (!em) {
		ret = -ENOMEM;
		goto err;
	}

	key.objectid = ino;
	key.type = BTRFS_EXTENT_DATA_KEY;
	key.offset = start;

	if (newer_than) {
		ret = btrfs_search_forward(root, &key, &path, newer_than);
		if (ret < 0)
			goto err;
		/* Can't find anything newer */
		if (ret > 0)
			goto not_found;
	} else {
		ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
		if (ret < 0)
			goto err;
	}
	if (path.slots[0] >= btrfs_header_nritems(path.nodes[0])) {
		/*
		 * If btrfs_search_slot() makes path to point beyond nritems,
		 * we should not have an empty leaf, as this inode must at
		 * least have its INODE_ITEM.
		 */
		ASSERT(btrfs_header_nritems(path.nodes[0]));
		path.slots[0] = btrfs_header_nritems(path.nodes[0]) - 1;
	}
	btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
	/* Perfect match, no need to go one slot back */
	if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY &&
	    key.offset == start)
		goto iterate;

	/* We didn't find a perfect match, needs to go one slot back */
	if (path.slots[0] > 0) {
		btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);
		if (key.objectid == ino && key.type == BTRFS_EXTENT_DATA_KEY)
			path.slots[0]--;
	}

iterate:
	/* Iterate through the path to find a file extent covering @start */
	while (true) {
		u64 extent_end;

		if (path.slots[0] >= btrfs_header_nritems(path.nodes[0]))
			goto next;

		btrfs_item_key_to_cpu(path.nodes[0], &key, path.slots[0]);

		/*
		 * We may go one slot back to INODE_REF/XATTR item, then
		 * need to go forward until we reach an EXTENT_DATA.
		 * But we should still has the correct ino as key.objectid.
		 */
		if (WARN_ON(key.objectid < ino) || key.type < BTRFS_EXTENT_DATA_KEY)
			goto next;

		/* It's beyond our target range, definitely not extent found */
		if (key.objectid > ino || key.type > BTRFS_EXTENT_DATA_KEY)
			goto not_found;

		/*
		 *	|	|<- File extent ->|
		 *	\- start
		 *
		 * This means there is a hole between start and key.offset.
		 */
		if (key.offset > start) {
			em->start = start;
			em->orig_start = start;
			em->block_start = EXTENT_MAP_HOLE;
			em->len = key.offset - start;
			break;
		}

		fi = btrfs_item_ptr(path.nodes[0], path.slots[0],
				    struct btrfs_file_extent_item);
		extent_end = btrfs_file_extent_end(&path);

		/*
		 *	|<- file extent ->|	|
		 *				\- start
		 *
		 * We haven't reached start, search next slot.
		 */
		if (extent_end <= start)
			goto next;

		/* Now this extent covers @start, convert it to em */
		btrfs_extent_item_to_extent_map(inode, &path, fi, em);
		break;
next:
		ret = btrfs_next_item(root, &path);
		if (ret < 0)
			goto err;
		if (ret > 0)
			goto not_found;
	}
	btrfs_release_path(&path);
	return em;

not_found:
	btrfs_release_path(&path);
	free_extent_map(em);
	return NULL;

err:
	btrfs_release_path(&path);
	free_extent_map(em);
	return ERR_PTR(ret);
}

static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start,
					       u64 newer_than, bool locked)
{
	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
	struct extent_map *em;
	const u32 sectorsize = BTRFS_I(inode)->root->fs_info->sectorsize;

	/*
	 * Hopefully we have this extent in the tree already, try without the
	 * full extent lock.
	 */
	read_lock(&em_tree->lock);
	em = lookup_extent_mapping(em_tree, start, sectorsize);
	read_unlock(&em_tree->lock);

	/*
	 * We can get a merged extent, in that case, we need to re-search
	 * tree to get the original em for defrag.
	 *
	 * If @newer_than is 0 or em::generation < newer_than, we can trust
	 * this em, as either we don't care about the generation, or the
	 * merged extent map will be rejected anyway.
	 */
	if (em && test_bit(EXTENT_FLAG_MERGED, &em->flags) &&
	    newer_than && em->generation >= newer_than) {
		free_extent_map(em);
		em = NULL;
	}

	if (!em) {
		struct extent_state *cached = NULL;
		u64 end = start + sectorsize - 1;

		/* Get the big lock and read metadata off disk. */
		if (!locked)
			lock_extent(io_tree, start, end, &cached);
		em = defrag_get_extent(BTRFS_I(inode), start, newer_than);
		if (!locked)
			unlock_extent(io_tree, start, end, &cached);

		if (IS_ERR(em))
			return NULL;
	}

	return em;
}

static u32 get_extent_max_capacity(const struct btrfs_fs_info *fs_info,
				   const struct extent_map *em)
{
	if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
		return BTRFS_MAX_COMPRESSED;
	return fs_info->max_extent_size;
}

static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em,
				     u32 extent_thresh, u64 newer_than, bool locked)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	struct extent_map *next;
	bool ret = false;

	/* This is the last extent */
	if (em->start + em->len >= i_size_read(inode))
		return false;

	/*
	 * Here we need to pass @newer_then when checking the next extent, or
	 * we will hit a case we mark current extent for defrag, but the next
	 * one will not be a target.
	 * This will just cause extra IO without really reducing the fragments.
	 */
	next = defrag_lookup_extent(inode, em->start + em->len, newer_than, locked);
	/* No more em or hole */
	if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
		goto out;
	if (test_bit(EXTENT_FLAG_PREALLOC, &next->flags))
		goto out;
	/*
	 * If the next extent is at its max capacity, defragging current extent
	 * makes no sense, as the total number of extents won't change.
	 */
	if (next->len >= get_extent_max_capacity(fs_info, em))
		goto out;
	/* Skip older extent */
	if (next->generation < newer_than)
		goto out;
	/* Also check extent size */
	if (next->len >= extent_thresh)
		goto out;

	ret = true;
out:
	free_extent_map(next);
	return ret;
}

/*
 * Prepare one page to be defragged.
 *
 * This will ensure:
 *
 * - Returned page is locked and has been set up properly.
 * - No ordered extent exists in the page.
 * - The page is uptodate.
 *
 * NOTE: Caller should also wait for page writeback after the cluster is
 * prepared, here we don't do writeback wait for each page.
 */
static struct page *defrag_prepare_one_page(struct btrfs_inode *inode, pgoff_t index)
{
	struct address_space *mapping = inode->vfs_inode.i_mapping;
	gfp_t mask = btrfs_alloc_write_mask(mapping);
	u64 page_start = (u64)index << PAGE_SHIFT;
	u64 page_end = page_start + PAGE_SIZE - 1;
	struct extent_state *cached_state = NULL;
	struct page *page;
	int ret;

again:
	page = find_or_create_page(mapping, index, mask);
	if (!page)
		return ERR_PTR(-ENOMEM);

	/*
	 * Since we can defragment files opened read-only, we can encounter
	 * transparent huge pages here (see CONFIG_READ_ONLY_THP_FOR_FS). We
	 * can't do I/O using huge pages yet, so return an error for now.
	 * Filesystem transparent huge pages are typically only used for
	 * executables that explicitly enable them, so this isn't very
	 * restrictive.
	 */
	if (PageCompound(page)) {
		unlock_page(page);
		put_page(page);
		return ERR_PTR(-ETXTBSY);
	}

	ret = set_page_extent_mapped(page);
	if (ret < 0) {
		unlock_page(page);
		put_page(page);
		return ERR_PTR(ret);
	}

	/* Wait for any existing ordered extent in the range */
	while (1) {
		struct btrfs_ordered_extent *ordered;

		lock_extent(&inode->io_tree, page_start, page_end, &cached_state);
		ordered = btrfs_lookup_ordered_range(inode, page_start, PAGE_SIZE);
		unlock_extent(&inode->io_tree, page_start, page_end,
			      &cached_state);
		if (!ordered)
			break;

		unlock_page(page);
		btrfs_start_ordered_extent(ordered);
		btrfs_put_ordered_extent(ordered);
		lock_page(page);
		/*
		 * We unlocked the page above, so we need check if it was
		 * released or not.
		 */
		if (page->mapping != mapping || !PagePrivate(page)) {
			unlock_page(page);
			put_page(page);
			goto again;
		}
	}

	/*
	 * Now the page range has no ordered extent any more.  Read the page to
	 * make it uptodate.
	 */
	if (!PageUptodate(page)) {
		btrfs_read_folio(NULL, page_folio(page));
		lock_page(page);
		if (page->mapping != mapping || !PagePrivate(page)) {
			unlock_page(page);
			put_page(page);
			goto again;
		}
		if (!PageUptodate(page)) {
			unlock_page(page);
			put_page(page);
			return ERR_PTR(-EIO);
		}
	}
	return page;
}

struct defrag_target_range {
	struct list_head list;
	u64 start;
	u64 len;
};

/*
 * Collect all valid target extents.
 *
 * @start:	   file offset to lookup
 * @len:	   length to lookup
 * @extent_thresh: file extent size threshold, any extent size >= this value
 *		   will be ignored
 * @newer_than:    only defrag extents newer than this value
 * @do_compress:   whether the defrag is doing compression
 *		   if true, @extent_thresh will be ignored and all regular
 *		   file extents meeting @newer_than will be targets.
 * @locked:	   if the range has already held extent lock
 * @target_list:   list of targets file extents
 */
static int defrag_collect_targets(struct btrfs_inode *inode,
				  u64 start, u64 len, u32 extent_thresh,
				  u64 newer_than, bool do_compress,
				  bool locked, struct list_head *target_list,
				  u64 *last_scanned_ret)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	bool last_is_target = false;
	u64 cur = start;
	int ret = 0;

	while (cur < start + len) {
		struct extent_map *em;
		struct defrag_target_range *new;
		bool next_mergeable = true;
		u64 range_len;

		last_is_target = false;
		em = defrag_lookup_extent(&inode->vfs_inode, cur, newer_than, locked);
		if (!em)
			break;

		/*
		 * If the file extent is an inlined one, we may still want to
		 * defrag it (fallthrough) if it will cause a regular extent.
		 * This is for users who want to convert inline extents to
		 * regular ones through max_inline= mount option.
		 */
		if (em->block_start == EXTENT_MAP_INLINE &&
		    em->len <= inode->root->fs_info->max_inline)
			goto next;

		/* Skip hole/delalloc/preallocated extents */
		if (em->block_start == EXTENT_MAP_HOLE ||
		    em->block_start == EXTENT_MAP_DELALLOC ||
		    test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
			goto next;

		/* Skip older extent */
		if (em->generation < newer_than)
			goto next;

		/* This em is under writeback, no need to defrag */
		if (em->generation == (u64)-1)
			goto next;

		/*
		 * Our start offset might be in the middle of an existing extent
		 * map, so take that into account.
		 */
		range_len = em->len - (cur - em->start);
		/*
		 * If this range of the extent map is already flagged for delalloc,
		 * skip it, because:
		 *
		 * 1) We could deadlock later, when trying to reserve space for
		 *    delalloc, because in case we can't immediately reserve space
		 *    the flusher can start delalloc and wait for the respective
		 *    ordered extents to complete. The deadlock would happen
		 *    because we do the space reservation while holding the range
		 *    locked, and starting writeback, or finishing an ordered
		 *    extent, requires locking the range;
		 *
		 * 2) If there's delalloc there, it means there's dirty pages for
		 *    which writeback has not started yet (we clean the delalloc
		 *    flag when starting writeback and after creating an ordered
		 *    extent). If we mark pages in an adjacent range for defrag,
		 *    then we will have a larger contiguous range for delalloc,
		 *    very likely resulting in a larger extent after writeback is
		 *    triggered (except in a case of free space fragmentation).
		 */
		if (test_range_bit_exists(&inode->io_tree, cur, cur + range_len - 1,
					  EXTENT_DELALLOC))
			goto next;

		/*
		 * For do_compress case, we want to compress all valid file
		 * extents, thus no @extent_thresh or mergeable check.
		 */
		if (do_compress)
			goto add;

		/* Skip too large extent */
		if (range_len >= extent_thresh)
			goto next;

		/*
		 * Skip extents already at its max capacity, this is mostly for
		 * compressed extents, which max cap is only 128K.
		 */
		if (em->len >= get_extent_max_capacity(fs_info, em))
			goto next;

		/*
		 * Normally there are no more extents after an inline one, thus
		 * @next_mergeable will normally be false and not defragged.
		 * So if an inline extent passed all above checks, just add it
		 * for defrag, and be converted to regular extents.
		 */
		if (em->block_start == EXTENT_MAP_INLINE)
			goto add;

		next_mergeable = defrag_check_next_extent(&inode->vfs_inode, em,
						extent_thresh, newer_than, locked);
		if (!next_mergeable) {
			struct defrag_target_range *last;

			/* Empty target list, no way to merge with last entry */
			if (list_empty(target_list))
				goto next;
			last = list_entry(target_list->prev,
					  struct defrag_target_range, list);
			/* Not mergeable with last entry */
			if (last->start + last->len != cur)
				goto next;

			/* Mergeable, fall through to add it to @target_list. */
		}

add:
		last_is_target = true;
		range_len = min(extent_map_end(em), start + len) - cur;
		/*
		 * This one is a good target, check if it can be merged into
		 * last range of the target list.
		 */
		if (!list_empty(target_list)) {
			struct defrag_target_range *last;

			last = list_entry(target_list->prev,
					  struct defrag_target_range, list);
			ASSERT(last->start + last->len <= cur);
			if (last->start + last->len == cur) {
				/* Mergeable, enlarge the last entry */
				last->len += range_len;
				goto next;
			}
			/* Fall through to allocate a new entry */
		}

		/* Allocate new defrag_target_range */
		new = kmalloc(sizeof(*new), GFP_NOFS);
		if (!new) {
			free_extent_map(em);
			ret = -ENOMEM;
			break;
		}
		new->start = cur;
		new->len = range_len;
		list_add_tail(&new->list, target_list);

next:
		cur = extent_map_end(em);
		free_extent_map(em);
	}
	if (ret < 0) {
		struct defrag_target_range *entry;
		struct defrag_target_range *tmp;

		list_for_each_entry_safe(entry, tmp, target_list, list) {
			list_del_init(&entry->list);
			kfree(entry);
		}
	}
	if (!ret && last_scanned_ret) {
		/*
		 * If the last extent is not a target, the caller can skip to
		 * the end of that extent.
		 * Otherwise, we can only go the end of the specified range.
		 */
		if (!last_is_target)
			*last_scanned_ret = max(cur, *last_scanned_ret);
		else
			*last_scanned_ret = max(start + len, *last_scanned_ret);
	}
	return ret;
}

#define CLUSTER_SIZE	(SZ_256K)
static_assert(PAGE_ALIGNED(CLUSTER_SIZE));

/*
 * Defrag one contiguous target range.
 *
 * @inode:	target inode
 * @target:	target range to defrag
 * @pages:	locked pages covering the defrag range
 * @nr_pages:	number of locked pages
 *
 * Caller should ensure:
 *
 * - Pages are prepared
 *   Pages should be locked, no ordered extent in the pages range,
 *   no writeback.
 *
 * - Extent bits are locked
 */
static int defrag_one_locked_target(struct btrfs_inode *inode,
				    struct defrag_target_range *target,
				    struct page **pages, int nr_pages,
				    struct extent_state **cached_state)
{
	struct btrfs_fs_info *fs_info = inode->root->fs_info;
	struct extent_changeset *data_reserved = NULL;
	const u64 start = target->start;
	const u64 len = target->len;
	unsigned long last_index = (start + len - 1) >> PAGE_SHIFT;
	unsigned long start_index = start >> PAGE_SHIFT;
	unsigned long first_index = page_index(pages[0]);
	int ret = 0;
	int i;

	ASSERT(last_index - first_index + 1 <= nr_pages);

	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, start, len);
	if (ret < 0)
		return ret;
	clear_extent_bit(&inode->io_tree, start, start + len - 1,
			 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
			 EXTENT_DEFRAG, cached_state);
	set_extent_bit(&inode->io_tree, start, start + len - 1,
		       EXTENT_DELALLOC | EXTENT_DEFRAG, cached_state);

	/* Update the page status */
	for (i = start_index - first_index; i <= last_index - first_index; i++) {
		ClearPageChecked(pages[i]);
		btrfs_page_clamp_set_dirty(fs_info, pages[i], start, len);
	}
	btrfs_delalloc_release_extents(inode, len);
	extent_changeset_free(data_reserved);

	return ret;
}

static int defrag_one_range(struct btrfs_inode *inode, u64 start, u32 len,
			    u32 extent_thresh, u64 newer_than, bool do_compress,
			    u64 *last_scanned_ret)
{
	struct extent_state *cached_state = NULL;
	struct defrag_target_range *entry;
	struct defrag_target_range *tmp;
	LIST_HEAD(target_list);
	struct page **pages;
	const u32 sectorsize = inode->root->fs_info->sectorsize;
	u64 last_index = (start + len - 1) >> PAGE_SHIFT;
	u64 start_index = start >> PAGE_SHIFT;
	unsigned int nr_pages = last_index - start_index + 1;
	int ret = 0;
	int i;

	ASSERT(nr_pages <= CLUSTER_SIZE / PAGE_SIZE);
	ASSERT(IS_ALIGNED(start, sectorsize) && IS_ALIGNED(len, sectorsize));

	pages = kcalloc(nr_pages, sizeof(struct page *), GFP_NOFS);
	if (!pages)
		return -ENOMEM;

	/* Prepare all pages */
	for (i = 0; i < nr_pages; i++) {
		pages[i] = defrag_prepare_one_page(inode, start_index + i);
		if (IS_ERR(pages[i])) {
			ret = PTR_ERR(pages[i]);
			pages[i] = NULL;
			goto free_pages;
		}
	}
	for (i = 0; i < nr_pages; i++)
		wait_on_page_writeback(pages[i]);

	/* Lock the pages range */
	lock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
		    (last_index << PAGE_SHIFT) + PAGE_SIZE - 1,
		    &cached_state);
	/*
	 * Now we have a consistent view about the extent map, re-check
	 * which range really needs to be defragged.
	 *
	 * And this time we have extent locked already, pass @locked = true
	 * so that we won't relock the extent range and cause deadlock.
	 */
	ret = defrag_collect_targets(inode, start, len, extent_thresh,
				     newer_than, do_compress, true,
				     &target_list, last_scanned_ret);
	if (ret < 0)
		goto unlock_extent;

	list_for_each_entry(entry, &target_list, list) {
		ret = defrag_one_locked_target(inode, entry, pages, nr_pages,
					       &cached_state);
		if (ret < 0)
			break;
	}

	list_for_each_entry_safe(entry, tmp, &target_list, list) {
		list_del_init(&entry->list);
		kfree(entry);
	}
unlock_extent:
	unlock_extent(&inode->io_tree, start_index << PAGE_SHIFT,
		      (last_index << PAGE_SHIFT) + PAGE_SIZE - 1,
		      &cached_state);
free_pages:
	for (i = 0; i < nr_pages; i++) {
		if (pages[i]) {
			unlock_page(pages[i]);
			put_page(pages[i]);
		}
	}
	kfree(pages);
	return ret;
}

static int defrag_one_cluster(struct btrfs_inode *inode,
			      struct file_ra_state *ra,
			      u64 start, u32 len, u32 extent_thresh,
			      u64 newer_than, bool do_compress,
			      unsigned long *sectors_defragged,
			      unsigned long max_sectors,
			      u64 *last_scanned_ret)
{
	const u32 sectorsize = inode->root->fs_info->sectorsize;
	struct defrag_target_range *entry;
	struct defrag_target_range *tmp;
	LIST_HEAD(target_list);
	int ret;

	ret = defrag_collect_targets(inode, start, len, extent_thresh,
				     newer_than, do_compress, false,
				     &target_list, NULL);
	if (ret < 0)
		goto out;

	list_for_each_entry(entry, &target_list, list) {
		u32 range_len = entry->len;

		/* Reached or beyond the limit */
		if (max_sectors && *sectors_defragged >= max_sectors) {
			ret = 1;
			break;
		}

		if (max_sectors)
			range_len = min_t(u32, range_len,
				(max_sectors - *sectors_defragged) * sectorsize);

		/*
		 * If defrag_one_range() has updated last_scanned_ret,
		 * our range may already be invalid (e.g. hole punched).
		 * Skip if our range is before last_scanned_ret, as there is
		 * no need to defrag the range anymore.
		 */
		if (entry->start + range_len <= *last_scanned_ret)
			continue;

		if (ra)
			page_cache_sync_readahead(inode->vfs_inode.i_mapping,
				ra, NULL, entry->start >> PAGE_SHIFT,
				((entry->start + range_len - 1) >> PAGE_SHIFT) -
				(entry->start >> PAGE_SHIFT) + 1);
		/*
		 * Here we may not defrag any range if holes are punched before
		 * we locked the pages.
		 * But that's fine, it only affects the @sectors_defragged
		 * accounting.
		 */
		ret = defrag_one_range(inode, entry->start, range_len,
				       extent_thresh, newer_than, do_compress,
				       last_scanned_ret);
		if (ret < 0)
			break;
		*sectors_defragged += range_len >>
				      inode->root->fs_info->sectorsize_bits;
	}
out:
	list_for_each_entry_safe(entry, tmp, &target_list, list) {
		list_del_init(&entry->list);
		kfree(entry);
	}
	if (ret >= 0)
		*last_scanned_ret = max(*last_scanned_ret, start + len);
	return ret;
}

/*
 * Entry point to file defragmentation.
 *
 * @inode:	   inode to be defragged
 * @ra:		   readahead state (can be NUL)
 * @range:	   defrag options including range and flags
 * @newer_than:	   minimum transid to defrag
 * @max_to_defrag: max number of sectors to be defragged, if 0, the whole inode
 *		   will be defragged.
 *
 * Return <0 for error.
 * Return >=0 for the number of sectors defragged, and range->start will be updated
 * to indicate the file offset where next defrag should be started at.
 * (Mostly for autodefrag, which sets @max_to_defrag thus we may exit early without
 *  defragging all the range).
 */
int btrfs_defrag_file(struct inode *inode, struct file_ra_state *ra,
		      struct btrfs_ioctl_defrag_range_args *range,
		      u64 newer_than, unsigned long max_to_defrag)
{
	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
	unsigned long sectors_defragged = 0;
	u64 isize = i_size_read(inode);
	u64 cur;
	u64 last_byte;
	bool do_compress = (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS);
	bool ra_allocated = false;
	int compress_type = BTRFS_COMPRESS_ZLIB;
	int ret = 0;
	u32 extent_thresh = range->extent_thresh;
	pgoff_t start_index;

	if (isize == 0)
		return 0;

	if (range->start >= isize)
		return -EINVAL;

	if (do_compress) {
		if (range->compress_type >= BTRFS_NR_COMPRESS_TYPES)
			return -EINVAL;
		if (range->compress_type)
			compress_type = range->compress_type;
	}

	if (extent_thresh == 0)
		extent_thresh = SZ_256K;

	if (range->start + range->len > range->start) {
		/* Got a specific range */
		last_byte = min(isize, range->start + range->len);
	} else {
		/* Defrag until file end */
		last_byte = isize;
	}

	/* Align the range */
	cur = round_down(range->start, fs_info->sectorsize);
	last_byte = round_up(last_byte, fs_info->sectorsize) - 1;

	/*
	 * If we were not given a ra, allocate a readahead context. As
	 * readahead is just an optimization, defrag will work without it so
	 * we don't error out.
	 */
	if (!ra) {
		ra_allocated = true;
		ra = kzalloc(sizeof(*ra), GFP_KERNEL);
		if (ra)
			file_ra_state_init(ra, inode->i_mapping);
	}

	/*
	 * Make writeback start from the beginning of the range, so that the
	 * defrag range can be written sequentially.
	 */
	start_index = cur >> PAGE_SHIFT;
	if (start_index < inode->i_mapping->writeback_index)
		inode->i_mapping->writeback_index = start_index;

	while (cur < last_byte) {
		const unsigned long prev_sectors_defragged = sectors_defragged;
		u64 last_scanned = cur;
		u64 cluster_end;

		if (btrfs_defrag_cancelled(fs_info)) {
			ret = -EAGAIN;
			break;
		}

		/* We want the cluster end at page boundary when possible */
		cluster_end = (((cur >> PAGE_SHIFT) +
			       (SZ_256K >> PAGE_SHIFT)) << PAGE_SHIFT) - 1;
		cluster_end = min(cluster_end, last_byte);

		btrfs_inode_lock(BTRFS_I(inode), 0);
		if (IS_SWAPFILE(inode)) {
			ret = -ETXTBSY;
			btrfs_inode_unlock(BTRFS_I(inode), 0);
			break;
		}
		if (!(inode->i_sb->s_flags & SB_ACTIVE)) {
			btrfs_inode_unlock(BTRFS_I(inode), 0);
			break;
		}
		if (do_compress)
			BTRFS_I(inode)->defrag_compress = compress_type;
		ret = defrag_one_cluster(BTRFS_I(inode), ra, cur,
				cluster_end + 1 - cur, extent_thresh,
				newer_than, do_compress, &sectors_defragged,
				max_to_defrag, &last_scanned);

		if (sectors_defragged > prev_sectors_defragged)
			balance_dirty_pages_ratelimited(inode->i_mapping);

		btrfs_inode_unlock(BTRFS_I(inode), 0);
		if (ret < 0)
			break;
		cur = max(cluster_end + 1, last_scanned);
		if (ret > 0) {
			ret = 0;
			break;
		}
		cond_resched();
	}

	if (ra_allocated)
		kfree(ra);
	/*
	 * Update range.start for autodefrag, this will indicate where to start
	 * in next run.
	 */
	range->start = cur;
	if (sectors_defragged) {
		/*
		 * We have defragged some sectors, for compression case they
		 * need to be written back immediately.
		 */
		if (range->flags & BTRFS_DEFRAG_RANGE_START_IO) {
			filemap_flush(inode->i_mapping);
			if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
				     &BTRFS_I(inode)->runtime_flags))
				filemap_flush(inode->i_mapping);
		}
		if (range->compress_type == BTRFS_COMPRESS_LZO)
			btrfs_set_fs_incompat(fs_info, COMPRESS_LZO);
		else if (range->compress_type == BTRFS_COMPRESS_ZSTD)
			btrfs_set_fs_incompat(fs_info, COMPRESS_ZSTD);
		ret = sectors_defragged;
	}
	if (do_compress) {
		btrfs_inode_lock(BTRFS_I(inode), 0);
		BTRFS_I(inode)->defrag_compress = BTRFS_COMPRESS_NONE;
		btrfs_inode_unlock(BTRFS_I(inode), 0);
	}
	return ret;
}

void __cold btrfs_auto_defrag_exit(void)
{
	kmem_cache_destroy(btrfs_inode_defrag_cachep);
}

int __init btrfs_auto_defrag_init(void)
{
	btrfs_inode_defrag_cachep = kmem_cache_create("btrfs_inode_defrag",
					sizeof(struct inode_defrag), 0,
					SLAB_MEM_SPREAD,
					NULL);
	if (!btrfs_inode_defrag_cachep)
		return -ENOMEM;

	return 0;
}