summaryrefslogtreecommitdiffstats
path: root/fs/ext4/extents_status.c
blob: ee018d5f397e6ba88ec0bf21196e1ad0612d4e53 (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
/*
 *  fs/ext4/extents_status.c
 *
 * Written by Yongqiang Yang <xiaoqiangnk@gmail.com>
 * Modified by
 *	Allison Henderson <achender@linux.vnet.ibm.com>
 *	Hugh Dickins <hughd@google.com>
 *	Zheng Liu <wenqing.lz@taobao.com>
 *
 * Ext4 extents status tree core functions.
 */
#include <linux/rbtree.h>
#include <linux/list_sort.h>
#include "ext4.h"
#include "extents_status.h"
#include "ext4_extents.h"

#include <trace/events/ext4.h>

/*
 * According to previous discussion in Ext4 Developer Workshop, we
 * will introduce a new structure called io tree to track all extent
 * status in order to solve some problems that we have met
 * (e.g. Reservation space warning), and provide extent-level locking.
 * Delay extent tree is the first step to achieve this goal.  It is
 * original built by Yongqiang Yang.  At that time it is called delay
 * extent tree, whose goal is only track delayed extents in memory to
 * simplify the implementation of fiemap and bigalloc, and introduce
 * lseek SEEK_DATA/SEEK_HOLE support.  That is why it is still called
 * delay extent tree at the first commit.  But for better understand
 * what it does, it has been rename to extent status tree.
 *
 * Step1:
 * Currently the first step has been done.  All delayed extents are
 * tracked in the tree.  It maintains the delayed extent when a delayed
 * allocation is issued, and the delayed extent is written out or
 * invalidated.  Therefore the implementation of fiemap and bigalloc
 * are simplified, and SEEK_DATA/SEEK_HOLE are introduced.
 *
 * The following comment describes the implemenmtation of extent
 * status tree and future works.
 *
 * Step2:
 * In this step all extent status are tracked by extent status tree.
 * Thus, we can first try to lookup a block mapping in this tree before
 * finding it in extent tree.  Hence, single extent cache can be removed
 * because extent status tree can do a better job.  Extents in status
 * tree are loaded on-demand.  Therefore, the extent status tree may not
 * contain all of the extents in a file.  Meanwhile we define a shrinker
 * to reclaim memory from extent status tree because fragmented extent
 * tree will make status tree cost too much memory.  written/unwritten/-
 * hole extents in the tree will be reclaimed by this shrinker when we
 * are under high memory pressure.  Delayed extents will not be
 * reclimed because fiemap, bigalloc, and seek_data/hole need it.
 */

/*
 * Extent status tree implementation for ext4.
 *
 *
 * ==========================================================================
 * Extent status tree tracks all extent status.
 *
 * 1. Why we need to implement extent status tree?
 *
 * Without extent status tree, ext4 identifies a delayed extent by looking
 * up page cache, this has several deficiencies - complicated, buggy,
 * and inefficient code.
 *
 * FIEMAP, SEEK_HOLE/DATA, bigalloc, and writeout all need to know if a
 * block or a range of blocks are belonged to a delayed extent.
 *
 * Let us have a look at how they do without extent status tree.
 *   --	FIEMAP
 *	FIEMAP looks up page cache to identify delayed allocations from holes.
 *
 *   --	SEEK_HOLE/DATA
 *	SEEK_HOLE/DATA has the same problem as FIEMAP.
 *
 *   --	bigalloc
 *	bigalloc looks up page cache to figure out if a block is
 *	already under delayed allocation or not to determine whether
 *	quota reserving is needed for the cluster.
 *
 *   --	writeout
 *	Writeout looks up whole page cache to see if a buffer is
 *	mapped, If there are not very many delayed buffers, then it is
 *	time comsuming.
 *
 * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA,
 * bigalloc and writeout can figure out if a block or a range of
 * blocks is under delayed allocation(belonged to a delayed extent) or
 * not by searching the extent tree.
 *
 *
 * ==========================================================================
 * 2. Ext4 extent status tree impelmentation
 *
 *   --	extent
 *	A extent is a range of blocks which are contiguous logically and
 *	physically.  Unlike extent in extent tree, this extent in ext4 is
 *	a in-memory struct, there is no corresponding on-disk data.  There
 *	is no limit on length of extent, so an extent can contain as many
 *	blocks as they are contiguous logically and physically.
 *
 *   --	extent status tree
 *	Every inode has an extent status tree and all allocation blocks
 *	are added to the tree with different status.  The extent in the
 *	tree are ordered by logical block no.
 *
 *   --	operations on a extent status tree
 *	There are three important operations on a delayed extent tree: find
 *	next extent, adding a extent(a range of blocks) and removing a extent.
 *
 *   --	race on a extent status tree
 *	Extent status tree is protected by inode->i_es_lock.
 *
 *   --	memory consumption
 *      Fragmented extent tree will make extent status tree cost too much
 *      memory.  Hence, we will reclaim written/unwritten/hole extents from
 *      the tree under a heavy memory pressure.
 *
 *
 * ==========================================================================
 * 3. Performance analysis
 *
 *   --	overhead
 *	1. There is a cache extent for write access, so if writes are
 *	not very random, adding space operaions are in O(1) time.
 *
 *   --	gain
 *	2. Code is much simpler, more readable, more maintainable and
 *	more efficient.
 *
 *
 * ==========================================================================
 * 4. TODO list
 *
 *   -- Refactor delayed space reservation
 *
 *   -- Extent-level locking
 */

static struct kmem_cache *ext4_es_cachep;

static int __es_insert_extent(struct inode *inode, struct extent_status *newes);
static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
			      ext4_lblk_t end);
static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
				       int nr_to_scan);

int __init ext4_init_es(void)
{
	ext4_es_cachep = kmem_cache_create("ext4_extent_status",
					   sizeof(struct extent_status),
					   0, (SLAB_RECLAIM_ACCOUNT), NULL);
	if (ext4_es_cachep == NULL)
		return -ENOMEM;
	return 0;
}

void ext4_exit_es(void)
{
	if (ext4_es_cachep)
		kmem_cache_destroy(ext4_es_cachep);
}

void ext4_es_init_tree(struct ext4_es_tree *tree)
{
	tree->root = RB_ROOT;
	tree->cache_es = NULL;
}

#ifdef ES_DEBUG__
static void ext4_es_print_tree(struct inode *inode)
{
	struct ext4_es_tree *tree;
	struct rb_node *node;

	printk(KERN_DEBUG "status extents for inode %lu:", inode->i_ino);
	tree = &EXT4_I(inode)->i_es_tree;
	node = rb_first(&tree->root);
	while (node) {
		struct extent_status *es;
		es = rb_entry(node, struct extent_status, rb_node);
		printk(KERN_DEBUG " [%u/%u) %llu %llx",
		       es->es_lblk, es->es_len,
		       ext4_es_pblock(es), ext4_es_status(es));
		node = rb_next(node);
	}
	printk(KERN_DEBUG "\n");
}
#else
#define ext4_es_print_tree(inode)
#endif

static inline ext4_lblk_t ext4_es_end(struct extent_status *es)
{
	BUG_ON(es->es_lblk + es->es_len < es->es_lblk);
	return es->es_lblk + es->es_len - 1;
}

/*
 * search through the tree for an delayed extent with a given offset.  If
 * it can't be found, try to find next extent.
 */
static struct extent_status *__es_tree_search(struct rb_root *root,
					      ext4_lblk_t lblk)
{
	struct rb_node *node = root->rb_node;
	struct extent_status *es = NULL;

	while (node) {
		es = rb_entry(node, struct extent_status, rb_node);
		if (lblk < es->es_lblk)
			node = node->rb_left;
		else if (lblk > ext4_es_end(es))
			node = node->rb_right;
		else
			return es;
	}

	if (es && lblk < es->es_lblk)
		return es;

	if (es && lblk > ext4_es_end(es)) {
		node = rb_next(&es->rb_node);
		return node ? rb_entry(node, struct extent_status, rb_node) :
			      NULL;
	}

	return NULL;
}

/*
 * ext4_es_find_delayed_extent_range: find the 1st delayed extent covering
 * @es->lblk if it exists, otherwise, the next extent after @es->lblk.
 *
 * @inode: the inode which owns delayed extents
 * @lblk: the offset where we start to search
 * @end: the offset where we stop to search
 * @es: delayed extent that we found
 */
void ext4_es_find_delayed_extent_range(struct inode *inode,
				 ext4_lblk_t lblk, ext4_lblk_t end,
				 struct extent_status *es)
{
	struct ext4_es_tree *tree = NULL;
	struct extent_status *es1 = NULL;
	struct rb_node *node;

	BUG_ON(es == NULL);
	BUG_ON(end < lblk);
	trace_ext4_es_find_delayed_extent_range_enter(inode, lblk);

	read_lock(&EXT4_I(inode)->i_es_lock);
	tree = &EXT4_I(inode)->i_es_tree;

	/* find extent in cache firstly */
	es->es_lblk = es->es_len = es->es_pblk = 0;
	if (tree->cache_es) {
		es1 = tree->cache_es;
		if (in_range(lblk, es1->es_lblk, es1->es_len)) {
			es_debug("%u cached by [%u/%u) %llu %llx\n",
				 lblk, es1->es_lblk, es1->es_len,
				 ext4_es_pblock(es1), ext4_es_status(es1));
			goto out;
		}
	}

	es1 = __es_tree_search(&tree->root, lblk);

out:
	if (es1 && !ext4_es_is_delayed(es1)) {
		while ((node = rb_next(&es1->rb_node)) != NULL) {
			es1 = rb_entry(node, struct extent_status, rb_node);
			if (es1->es_lblk > end) {
				es1 = NULL;
				break;
			}
			if (ext4_es_is_delayed(es1))
				break;
		}
	}

	if (es1 && ext4_es_is_delayed(es1)) {
		tree->cache_es = es1;
		es->es_lblk = es1->es_lblk;
		es->es_len = es1->es_len;
		es->es_pblk = es1->es_pblk;
	}

	read_unlock(&EXT4_I(inode)->i_es_lock);

	trace_ext4_es_find_delayed_extent_range_exit(inode, es);
}

static struct extent_status *
ext4_es_alloc_extent(struct inode *inode, ext4_lblk_t lblk, ext4_lblk_t len,
		     ext4_fsblk_t pblk)
{
	struct extent_status *es;
	es = kmem_cache_alloc(ext4_es_cachep, GFP_ATOMIC);
	if (es == NULL)
		return NULL;
	es->es_lblk = lblk;
	es->es_len = len;
	es->es_pblk = pblk;

	/*
	 * We don't count delayed extent because we never try to reclaim them
	 */
	if (!ext4_es_is_delayed(es)) {
		EXT4_I(inode)->i_es_lru_nr++;
		percpu_counter_inc(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
	}

	return es;
}

static void ext4_es_free_extent(struct inode *inode, struct extent_status *es)
{
	/* Decrease the lru counter when this es is not delayed */
	if (!ext4_es_is_delayed(es)) {
		BUG_ON(EXT4_I(inode)->i_es_lru_nr == 0);
		EXT4_I(inode)->i_es_lru_nr--;
		percpu_counter_dec(&EXT4_SB(inode->i_sb)->s_extent_cache_cnt);
	}

	kmem_cache_free(ext4_es_cachep, es);
}

/*
 * Check whether or not two extents can be merged
 * Condition:
 *  - logical block number is contiguous
 *  - physical block number is contiguous
 *  - status is equal
 */
static int ext4_es_can_be_merged(struct extent_status *es1,
				 struct extent_status *es2)
{
	if (ext4_es_status(es1) != ext4_es_status(es2))
		return 0;

	if (((__u64) es1->es_len) + es2->es_len > 0xFFFFFFFFULL)
		return 0;

	if (((__u64) es1->es_lblk) + es1->es_len != es2->es_lblk)
		return 0;

	if ((ext4_es_is_written(es1) || ext4_es_is_unwritten(es1)) &&
	    (ext4_es_pblock(es1) + es1->es_len == ext4_es_pblock(es2)))
		return 1;

	if (ext4_es_is_hole(es1))
		return 1;

	/* we need to check delayed extent is without unwritten status */
	if (ext4_es_is_delayed(es1) && !ext4_es_is_unwritten(es1))
		return 1;

	return 0;
}

static struct extent_status *
ext4_es_try_to_merge_left(struct inode *inode, struct extent_status *es)
{
	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
	struct extent_status *es1;
	struct rb_node *node;

	node = rb_prev(&es->rb_node);
	if (!node)
		return es;

	es1 = rb_entry(node, struct extent_status, rb_node);
	if (ext4_es_can_be_merged(es1, es)) {
		es1->es_len += es->es_len;
		rb_erase(&es->rb_node, &tree->root);
		ext4_es_free_extent(inode, es);
		es = es1;
	}

	return es;
}

static struct extent_status *
ext4_es_try_to_merge_right(struct inode *inode, struct extent_status *es)
{
	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
	struct extent_status *es1;
	struct rb_node *node;

	node = rb_next(&es->rb_node);
	if (!node)
		return es;

	es1 = rb_entry(node, struct extent_status, rb_node);
	if (ext4_es_can_be_merged(es, es1)) {
		es->es_len += es1->es_len;
		rb_erase(node, &tree->root);
		ext4_es_free_extent(inode, es1);
	}

	return es;
}

#ifdef ES_AGGRESSIVE_TEST
static void ext4_es_insert_extent_ext_check(struct inode *inode,
					    struct extent_status *es)
{
	struct ext4_ext_path *path = NULL;
	struct ext4_extent *ex;
	ext4_lblk_t ee_block;
	ext4_fsblk_t ee_start;
	unsigned short ee_len;
	int depth, ee_status, es_status;

	path = ext4_ext_find_extent(inode, es->es_lblk, NULL);
	if (IS_ERR(path))
		return;

	depth = ext_depth(inode);
	ex = path[depth].p_ext;

	if (ex) {

		ee_block = le32_to_cpu(ex->ee_block);
		ee_start = ext4_ext_pblock(ex);
		ee_len = ext4_ext_get_actual_len(ex);

		ee_status = ext4_ext_is_uninitialized(ex) ? 1 : 0;
		es_status = ext4_es_is_unwritten(es) ? 1 : 0;

		/*
		 * Make sure ex and es are not overlap when we try to insert
		 * a delayed/hole extent.
		 */
		if (!ext4_es_is_written(es) && !ext4_es_is_unwritten(es)) {
			if (in_range(es->es_lblk, ee_block, ee_len)) {
				pr_warn("ES insert assertation failed for "
					"inode: %lu we can find an extent "
					"at block [%d/%d/%llu/%c], but we "
					"want to add an delayed/hole extent "
					"[%d/%d/%llu/%llx]\n",
					inode->i_ino, ee_block, ee_len,
					ee_start, ee_status ? 'u' : 'w',
					es->es_lblk, es->es_len,
					ext4_es_pblock(es), ext4_es_status(es));
			}
			goto out;
		}

		/*
		 * We don't check ee_block == es->es_lblk, etc. because es
		 * might be a part of whole extent, vice versa.
		 */
		if (es->es_lblk < ee_block ||
		    ext4_es_pblock(es) != ee_start + es->es_lblk - ee_block) {
			pr_warn("ES insert assertation failed for inode: %lu "
				"ex_status [%d/%d/%llu/%c] != "
				"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
				ee_block, ee_len, ee_start,
				ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
				ext4_es_pblock(es), es_status ? 'u' : 'w');
			goto out;
		}

		if (ee_status ^ es_status) {
			pr_warn("ES insert assertation failed for inode: %lu "
				"ex_status [%d/%d/%llu/%c] != "
				"es_status [%d/%d/%llu/%c]\n", inode->i_ino,
				ee_block, ee_len, ee_start,
				ee_status ? 'u' : 'w', es->es_lblk, es->es_len,
				ext4_es_pblock(es), es_status ? 'u' : 'w');
		}
	} else {
		/*
		 * We can't find an extent on disk.  So we need to make sure
		 * that we don't want to add an written/unwritten extent.
		 */
		if (!ext4_es_is_delayed(es) && !ext4_es_is_hole(es)) {
			pr_warn("ES insert assertation failed for inode: %lu "
				"can't find an extent at block %d but we want "
				"to add an written/unwritten extent "
				"[%d/%d/%llu/%llx]\n", inode->i_ino,
				es->es_lblk, es->es_lblk, es->es_len,
				ext4_es_pblock(es), ext4_es_status(es));
		}
	}
out:
	if (path) {
		ext4_ext_drop_refs(path);
		kfree(path);
	}
}

static void ext4_es_insert_extent_ind_check(struct inode *inode,
					    struct extent_status *es)
{
	struct ext4_map_blocks map;
	int retval;

	/*
	 * Here we call ext4_ind_map_blocks to lookup a block mapping because
	 * 'Indirect' structure is defined in indirect.c.  So we couldn't
	 * access direct/indirect tree from outside.  It is too dirty to define
	 * this function in indirect.c file.
	 */

	map.m_lblk = es->es_lblk;
	map.m_len = es->es_len;

	retval = ext4_ind_map_blocks(NULL, inode, &map, 0);
	if (retval > 0) {
		if (ext4_es_is_delayed(es) || ext4_es_is_hole(es)) {
			/*
			 * We want to add a delayed/hole extent but this
			 * block has been allocated.
			 */
			pr_warn("ES insert assertation failed for inode: %lu "
				"We can find blocks but we want to add a "
				"delayed/hole extent [%d/%d/%llu/%llx]\n",
				inode->i_ino, es->es_lblk, es->es_len,
				ext4_es_pblock(es), ext4_es_status(es));
			return;
		} else if (ext4_es_is_written(es)) {
			if (retval != es->es_len) {
				pr_warn("ES insert assertation failed for "
					"inode: %lu retval %d != es_len %d\n",
					inode->i_ino, retval, es->es_len);
				return;
			}
			if (map.m_pblk != ext4_es_pblock(es)) {
				pr_warn("ES insert assertation failed for "
					"inode: %lu m_pblk %llu != "
					"es_pblk %llu\n",
					inode->i_ino, map.m_pblk,
					ext4_es_pblock(es));
				return;
			}
		} else {
			/*
			 * We don't need to check unwritten extent because
			 * indirect-based file doesn't have it.
			 */
			BUG_ON(1);
		}
	} else if (retval == 0) {
		if (ext4_es_is_written(es)) {
			pr_warn("ES insert assertation failed for inode: %lu "
				"We can't find the block but we want to add "
				"an written extent [%d/%d/%llu/%llx]\n",
				inode->i_ino, es->es_lblk, es->es_len,
				ext4_es_pblock(es), ext4_es_status(es));
			return;
		}
	}
}

static inline void ext4_es_insert_extent_check(struct inode *inode,
					       struct extent_status *es)
{
	/*
	 * We don't need to worry about the race condition because
	 * caller takes i_data_sem locking.
	 */
	BUG_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem));
	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
		ext4_es_insert_extent_ext_check(inode, es);
	else
		ext4_es_insert_extent_ind_check(inode, es);
}
#else
static inline void ext4_es_insert_extent_check(struct inode *inode,
					       struct extent_status *es)
{
}
#endif

static int __es_insert_extent(struct inode *inode, struct extent_status *newes)
{
	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
	struct rb_node **p = &tree->root.rb_node;
	struct rb_node *parent = NULL;
	struct extent_status *es;

	while (*p) {
		parent = *p;
		es = rb_entry(parent, struct extent_status, rb_node);

		if (newes->es_lblk < es->es_lblk) {
			if (ext4_es_can_be_merged(newes, es)) {
				/*
				 * Here we can modify es_lblk directly
				 * because it isn't overlapped.
				 */
				es->es_lblk = newes->es_lblk;
				es->es_len += newes->es_len;
				if (ext4_es_is_written(es) ||
				    ext4_es_is_unwritten(es))
					ext4_es_store_pblock(es,
							     newes->es_pblk);
				es = ext4_es_try_to_merge_left(inode, es);
				goto out;
			}
			p = &(*p)->rb_left;
		} else if (newes->es_lblk > ext4_es_end(es)) {
			if (ext4_es_can_be_merged(es, newes)) {
				es->es_len += newes->es_len;
				es = ext4_es_try_to_merge_right(inode, es);
				goto out;
			}
			p = &(*p)->rb_right;
		} else {
			BUG_ON(1);
			return -EINVAL;
		}
	}

	es = ext4_es_alloc_extent(inode, newes->es_lblk, newes->es_len,
				  newes->es_pblk);
	if (!es)
		return -ENOMEM;
	rb_link_node(&es->rb_node, parent, p);
	rb_insert_color(&es->rb_node, &tree->root);

out:
	tree->cache_es = es;
	return 0;
}

/*
 * ext4_es_insert_extent() adds a space to a extent status tree.
 *
 * ext4_es_insert_extent is called by ext4_da_write_begin and
 * ext4_es_remove_extent.
 *
 * Return 0 on success, error code on failure.
 */
int ext4_es_insert_extent(struct inode *inode, ext4_lblk_t lblk,
			  ext4_lblk_t len, ext4_fsblk_t pblk,
			  unsigned long long status)
{
	struct extent_status newes;
	ext4_lblk_t end = lblk + len - 1;
	int err = 0;

	es_debug("add [%u/%u) %llu %llx to extent status tree of inode %lu\n",
		 lblk, len, pblk, status, inode->i_ino);

	if (!len)
		return 0;

	BUG_ON(end < lblk);

	newes.es_lblk = lblk;
	newes.es_len = len;
	ext4_es_store_pblock(&newes, pblk);
	ext4_es_store_status(&newes, status);
	trace_ext4_es_insert_extent(inode, &newes);

	ext4_es_insert_extent_check(inode, &newes);

	write_lock(&EXT4_I(inode)->i_es_lock);
	err = __es_remove_extent(inode, lblk, end);
	if (err != 0)
		goto error;
	err = __es_insert_extent(inode, &newes);

error:
	write_unlock(&EXT4_I(inode)->i_es_lock);

	ext4_es_print_tree(inode);

	return err;
}

/*
 * ext4_es_lookup_extent() looks up an extent in extent status tree.
 *
 * ext4_es_lookup_extent is called by ext4_map_blocks/ext4_da_map_blocks.
 *
 * Return: 1 on found, 0 on not
 */
int ext4_es_lookup_extent(struct inode *inode, ext4_lblk_t lblk,
			  struct extent_status *es)
{
	struct ext4_es_tree *tree;
	struct extent_status *es1 = NULL;
	struct rb_node *node;
	int found = 0;

	trace_ext4_es_lookup_extent_enter(inode, lblk);
	es_debug("lookup extent in block %u\n", lblk);

	tree = &EXT4_I(inode)->i_es_tree;
	read_lock(&EXT4_I(inode)->i_es_lock);

	/* find extent in cache firstly */
	es->es_lblk = es->es_len = es->es_pblk = 0;
	if (tree->cache_es) {
		es1 = tree->cache_es;
		if (in_range(lblk, es1->es_lblk, es1->es_len)) {
			es_debug("%u cached by [%u/%u)\n",
				 lblk, es1->es_lblk, es1->es_len);
			found = 1;
			goto out;
		}
	}

	node = tree->root.rb_node;
	while (node) {
		es1 = rb_entry(node, struct extent_status, rb_node);
		if (lblk < es1->es_lblk)
			node = node->rb_left;
		else if (lblk > ext4_es_end(es1))
			node = node->rb_right;
		else {
			found = 1;
			break;
		}
	}

out:
	if (found) {
		BUG_ON(!es1);
		es->es_lblk = es1->es_lblk;
		es->es_len = es1->es_len;
		es->es_pblk = es1->es_pblk;
	}

	read_unlock(&EXT4_I(inode)->i_es_lock);

	trace_ext4_es_lookup_extent_exit(inode, es, found);
	return found;
}

static int __es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
			      ext4_lblk_t end)
{
	struct ext4_es_tree *tree = &EXT4_I(inode)->i_es_tree;
	struct rb_node *node;
	struct extent_status *es;
	struct extent_status orig_es;
	ext4_lblk_t len1, len2;
	ext4_fsblk_t block;
	int err = 0;

	es = __es_tree_search(&tree->root, lblk);
	if (!es)
		goto out;
	if (es->es_lblk > end)
		goto out;

	/* Simply invalidate cache_es. */
	tree->cache_es = NULL;

	orig_es.es_lblk = es->es_lblk;
	orig_es.es_len = es->es_len;
	orig_es.es_pblk = es->es_pblk;

	len1 = lblk > es->es_lblk ? lblk - es->es_lblk : 0;
	len2 = ext4_es_end(es) > end ? ext4_es_end(es) - end : 0;
	if (len1 > 0)
		es->es_len = len1;
	if (len2 > 0) {
		if (len1 > 0) {
			struct extent_status newes;

			newes.es_lblk = end + 1;
			newes.es_len = len2;
			if (ext4_es_is_written(&orig_es) ||
			    ext4_es_is_unwritten(&orig_es)) {
				block = ext4_es_pblock(&orig_es) +
					orig_es.es_len - len2;
				ext4_es_store_pblock(&newes, block);
			}
			ext4_es_store_status(&newes, ext4_es_status(&orig_es));
			err = __es_insert_extent(inode, &newes);
			if (err) {
				es->es_lblk = orig_es.es_lblk;
				es->es_len = orig_es.es_len;
				goto out;
			}
		} else {
			es->es_lblk = end + 1;
			es->es_len = len2;
			if (ext4_es_is_written(es) ||
			    ext4_es_is_unwritten(es)) {
				block = orig_es.es_pblk + orig_es.es_len - len2;
				ext4_es_store_pblock(es, block);
			}
		}
		goto out;
	}

	if (len1 > 0) {
		node = rb_next(&es->rb_node);
		if (node)
			es = rb_entry(node, struct extent_status, rb_node);
		else
			es = NULL;
	}

	while (es && ext4_es_end(es) <= end) {
		node = rb_next(&es->rb_node);
		rb_erase(&es->rb_node, &tree->root);
		ext4_es_free_extent(inode, es);
		if (!node) {
			es = NULL;
			break;
		}
		es = rb_entry(node, struct extent_status, rb_node);
	}

	if (es && es->es_lblk < end + 1) {
		ext4_lblk_t orig_len = es->es_len;

		len1 = ext4_es_end(es) - end;
		es->es_lblk = end + 1;
		es->es_len = len1;
		if (ext4_es_is_written(es) || ext4_es_is_unwritten(es)) {
			block = es->es_pblk + orig_len - len1;
			ext4_es_store_pblock(es, block);
		}
	}

out:
	return err;
}

/*
 * ext4_es_remove_extent() removes a space from a extent status tree.
 *
 * Return 0 on success, error code on failure.
 */
int ext4_es_remove_extent(struct inode *inode, ext4_lblk_t lblk,
			  ext4_lblk_t len)
{
	ext4_lblk_t end;
	int err = 0;

	trace_ext4_es_remove_extent(inode, lblk, len);
	es_debug("remove [%u/%u) from extent status tree of inode %lu\n",
		 lblk, len, inode->i_ino);

	if (!len)
		return err;

	end = lblk + len - 1;
	BUG_ON(end < lblk);

	write_lock(&EXT4_I(inode)->i_es_lock);
	err = __es_remove_extent(inode, lblk, end);
	write_unlock(&EXT4_I(inode)->i_es_lock);
	ext4_es_print_tree(inode);
	return err;
}

int ext4_es_zeroout(struct inode *inode, struct ext4_extent *ex)
{
	ext4_lblk_t  ee_block;
	ext4_fsblk_t ee_pblock;
	unsigned int ee_len;

	ee_block  = le32_to_cpu(ex->ee_block);
	ee_len    = ext4_ext_get_actual_len(ex);
	ee_pblock = ext4_ext_pblock(ex);

	if (ee_len == 0)
		return 0;

	return ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock,
				     EXTENT_STATUS_WRITTEN);
}

static int ext4_inode_touch_time_cmp(void *priv, struct list_head *a,
				     struct list_head *b)
{
	struct ext4_inode_info *eia, *eib;
	eia = list_entry(a, struct ext4_inode_info, i_es_lru);
	eib = list_entry(b, struct ext4_inode_info, i_es_lru);

	if (eia->i_touch_when == eib->i_touch_when)
		return 0;
	if (time_after(eia->i_touch_when, eib->i_touch_when))
		return 1;
	else
		return -1;
}

static int ext4_es_shrink(struct shrinker *shrink, struct shrink_control *sc)
{
	struct ext4_sb_info *sbi = container_of(shrink,
					struct ext4_sb_info, s_es_shrinker);
	struct ext4_inode_info *ei;
	struct list_head *cur, *tmp;
	LIST_HEAD(skiped);
	int nr_to_scan = sc->nr_to_scan;
	int ret, nr_shrunk = 0;

	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
	trace_ext4_es_shrink_enter(sbi->s_sb, nr_to_scan, ret);

	if (!nr_to_scan)
		return ret;

	spin_lock(&sbi->s_es_lru_lock);

	/*
	 * If the inode that is at the head of LRU list is newer than
	 * last_sorted time, that means that we need to sort this list.
	 */
	ei = list_first_entry(&sbi->s_es_lru, struct ext4_inode_info, i_es_lru);
	if (sbi->s_es_last_sorted < ei->i_touch_when) {
		list_sort(NULL, &sbi->s_es_lru, ext4_inode_touch_time_cmp);
		sbi->s_es_last_sorted = jiffies;
	}

	list_for_each_safe(cur, tmp, &sbi->s_es_lru) {
		/*
		 * If we have already reclaimed all extents from extent
		 * status tree, just stop the loop immediately.
		 */
		if (percpu_counter_read_positive(&sbi->s_extent_cache_cnt) == 0)
			break;

		ei = list_entry(cur, struct ext4_inode_info, i_es_lru);

		/* Skip the inode that is newer than the last_sorted time */
		if (sbi->s_es_last_sorted < ei->i_touch_when) {
			list_move_tail(cur, &skiped);
			continue;
		}

		if (ei->i_es_lru_nr == 0)
			continue;

		write_lock(&ei->i_es_lock);
		ret = __es_try_to_reclaim_extents(ei, nr_to_scan);
		if (ei->i_es_lru_nr == 0)
			list_del_init(&ei->i_es_lru);
		write_unlock(&ei->i_es_lock);

		nr_shrunk += ret;
		nr_to_scan -= ret;
		if (nr_to_scan == 0)
			break;
	}

	/* Move the newer inodes into the tail of the LRU list. */
	list_splice_tail(&skiped, &sbi->s_es_lru);
	spin_unlock(&sbi->s_es_lru_lock);

	ret = percpu_counter_read_positive(&sbi->s_extent_cache_cnt);
	trace_ext4_es_shrink_exit(sbi->s_sb, nr_shrunk, ret);
	return ret;
}

void ext4_es_register_shrinker(struct ext4_sb_info *sbi)
{
	INIT_LIST_HEAD(&sbi->s_es_lru);
	spin_lock_init(&sbi->s_es_lru_lock);
	sbi->s_es_last_sorted = 0;
	sbi->s_es_shrinker.shrink = ext4_es_shrink;
	sbi->s_es_shrinker.seeks = DEFAULT_SEEKS;
	register_shrinker(&sbi->s_es_shrinker);
}

void ext4_es_unregister_shrinker(struct ext4_sb_info *sbi)
{
	unregister_shrinker(&sbi->s_es_shrinker);
}

void ext4_es_lru_add(struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

	ei->i_touch_when = jiffies;

	if (!list_empty(&ei->i_es_lru))
		return;

	spin_lock(&sbi->s_es_lru_lock);
	if (list_empty(&ei->i_es_lru))
		list_add_tail(&ei->i_es_lru, &sbi->s_es_lru);
	spin_unlock(&sbi->s_es_lru_lock);
}

void ext4_es_lru_del(struct inode *inode)
{
	struct ext4_inode_info *ei = EXT4_I(inode);
	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);

	spin_lock(&sbi->s_es_lru_lock);
	if (!list_empty(&ei->i_es_lru))
		list_del_init(&ei->i_es_lru);
	spin_unlock(&sbi->s_es_lru_lock);
}

static int __es_try_to_reclaim_extents(struct ext4_inode_info *ei,
				       int nr_to_scan)
{
	struct inode *inode = &ei->vfs_inode;
	struct ext4_es_tree *tree = &ei->i_es_tree;
	struct rb_node *node;
	struct extent_status *es;
	int nr_shrunk = 0;

	if (ei->i_es_lru_nr == 0)
		return 0;

	node = rb_first(&tree->root);
	while (node != NULL) {
		es = rb_entry(node, struct extent_status, rb_node);
		node = rb_next(&es->rb_node);
		/*
		 * We can't reclaim delayed extent from status tree because
		 * fiemap, bigallic, and seek_data/hole need to use it.
		 */
		if (!ext4_es_is_delayed(es)) {
			rb_erase(&es->rb_node, &tree->root);
			ext4_es_free_extent(inode, es);
			nr_shrunk++;
			if (--nr_to_scan == 0)
				break;
		}
	}
	tree->cache_es = NULL;
	return nr_shrunk;
}
OpenPOWER on IntegriCloud