summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs/xfs_trans_resv.c
blob: 2c4ad6e4bb1498be85d66998ec01e4c7ddb61a69 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
 * Copyright (C) 2010 Red Hat, Inc.
 * All Rights Reserved.
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_da_btree.h"
#include "xfs_inode.h"
#include "xfs_bmap_btree.h"
#include "xfs_quota.h"
#include "xfs_trans.h"
#include "xfs_qm.h"
#include "xfs_trans_space.h"

#define _ALLOC	true
#define _FREE	false

/*
 * A buffer has a format structure overhead in the log in addition
 * to the data, so we need to take this into account when reserving
 * space in a transaction for a buffer.  Round the space required up
 * to a multiple of 128 bytes so that we don't change the historical
 * reservation that has been used for this overhead.
 */
STATIC uint
xfs_buf_log_overhead(void)
{
	return round_up(sizeof(struct xlog_op_header) +
			sizeof(struct xfs_buf_log_format), 128);
}

/*
 * Calculate out transaction log reservation per item in bytes.
 *
 * The nbufs argument is used to indicate the number of items that
 * will be changed in a transaction.  size is used to tell how many
 * bytes should be reserved per item.
 */
STATIC uint
xfs_calc_buf_res(
	uint		nbufs,
	uint		size)
{
	return nbufs * (size + xfs_buf_log_overhead());
}

/*
 * Per-extent log reservation for the btree changes involved in freeing or
 * allocating an extent.  In classic XFS there were two trees that will be
 * modified (bnobt + cntbt).  With rmap enabled, there are three trees
 * (rmapbt).  The number of blocks reserved is based on the formula:
 *
 * num trees * ((2 blocks/level * max depth) - 1)
 *
 * Keep in mind that max depth is calculated separately for each type of tree.
 */
uint
xfs_allocfree_block_count(
	struct xfs_mount *mp,
	uint		num_ops)
{
	uint		blocks;

	blocks = num_ops * 2 * (2 * mp->m_alloc_maxlevels - 1);
	if (xfs_has_rmapbt(mp))
		blocks += num_ops * (2 * mp->m_rmap_maxlevels - 1);

	return blocks;
}

/*
 * Per-extent log reservation for refcount btree changes.  These are never done
 * in the same transaction as an allocation or a free, so we compute them
 * separately.
 */
static unsigned int
xfs_refcountbt_block_count(
	struct xfs_mount	*mp,
	unsigned int		num_ops)
{
	return num_ops * (2 * mp->m_refc_maxlevels - 1);
}

/*
 * Logging inodes is really tricksy. They are logged in memory format,
 * which means that what we write into the log doesn't directly translate into
 * the amount of space they use on disk.
 *
 * Case in point - btree format forks in memory format use more space than the
 * on-disk format. In memory, the buffer contains a normal btree block header so
 * the btree code can treat it as though it is just another generic buffer.
 * However, when we write it to the inode fork, we don't write all of this
 * header as it isn't needed. e.g. the root is only ever in the inode, so
 * there's no need for sibling pointers which would waste 16 bytes of space.
 *
 * Hence when we have an inode with a maximally sized btree format fork, then
 * amount of information we actually log is greater than the size of the inode
 * on disk. Hence we need an inode reservation function that calculates all this
 * correctly. So, we log:
 *
 * - 4 log op headers for object
 *	- for the ilf, the inode core and 2 forks
 * - inode log format object
 * - the inode core
 * - two inode forks containing bmap btree root blocks.
 *	- the btree data contained by both forks will fit into the inode size,
 *	  hence when combined with the inode core above, we have a total of the
 *	  actual inode size.
 *	- the BMBT headers need to be accounted separately, as they are
 *	  additional to the records and pointers that fit inside the inode
 *	  forks.
 */
STATIC uint
xfs_calc_inode_res(
	struct xfs_mount	*mp,
	uint			ninodes)
{
	return ninodes *
		(4 * sizeof(struct xlog_op_header) +
		 sizeof(struct xfs_inode_log_format) +
		 mp->m_sb.sb_inodesize +
		 2 * XFS_BMBT_BLOCK_LEN(mp));
}

/*
 * Inode btree record insertion/removal modifies the inode btree and free space
 * btrees (since the inobt does not use the agfl). This requires the following
 * reservation:
 *
 * the inode btree: max depth * blocksize
 * the allocation btrees: 2 trees * (max depth - 1) * block size
 *
 * The caller must account for SB and AG header modifications, etc.
 */
STATIC uint
xfs_calc_inobt_res(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(M_IGEO(mp)->inobt_maxlevels,
			XFS_FSB_TO_B(mp, 1)) +
				xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
			XFS_FSB_TO_B(mp, 1));
}

/*
 * The free inode btree is a conditional feature. The behavior differs slightly
 * from that of the traditional inode btree in that the finobt tracks records
 * for inode chunks with at least one free inode. A record can be removed from
 * the tree during individual inode allocation. Therefore the finobt
 * reservation is unconditional for both the inode chunk allocation and
 * individual inode allocation (modify) cases.
 *
 * Behavior aside, the reservation for finobt modification is equivalent to the
 * traditional inobt: cover a full finobt shape change plus block allocation.
 */
STATIC uint
xfs_calc_finobt_res(
	struct xfs_mount	*mp)
{
	if (!xfs_has_finobt(mp))
		return 0;

	return xfs_calc_inobt_res(mp);
}

/*
 * Calculate the reservation required to allocate or free an inode chunk. This
 * includes:
 *
 * the allocation btrees: 2 trees * (max depth - 1) * block size
 * the inode chunk: m_ino_geo.ialloc_blks * N
 *
 * The size N of the inode chunk reservation depends on whether it is for
 * allocation or free and which type of create transaction is in use. An inode
 * chunk free always invalidates the buffers and only requires reservation for
 * headers (N == 0). An inode chunk allocation requires a chunk sized
 * reservation on v4 and older superblocks to initialize the chunk. No chunk
 * reservation is required for allocation on v5 supers, which use ordered
 * buffers to initialize.
 */
STATIC uint
xfs_calc_inode_chunk_res(
	struct xfs_mount	*mp,
	bool			alloc)
{
	uint			res, size = 0;

	res = xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
			       XFS_FSB_TO_B(mp, 1));
	if (alloc) {
		/* icreate tx uses ordered buffers */
		if (xfs_has_v3inodes(mp))
			return res;
		size = XFS_FSB_TO_B(mp, 1);
	}

	res += xfs_calc_buf_res(M_IGEO(mp)->ialloc_blks, size);
	return res;
}

/*
 * Per-extent log reservation for the btree changes involved in freeing or
 * allocating a realtime extent.  We have to be able to log as many rtbitmap
 * blocks as needed to mark inuse XFS_BMBT_MAX_EXTLEN blocks' worth of realtime
 * extents, as well as the realtime summary block.
 */
static unsigned int
xfs_rtalloc_block_count(
	struct xfs_mount	*mp,
	unsigned int		num_ops)
{
	unsigned int		blksz = XFS_FSB_TO_B(mp, 1);
	unsigned int		rtbmp_bytes;

	rtbmp_bytes = (XFS_MAX_BMBT_EXTLEN / mp->m_sb.sb_rextsize) / NBBY;
	return (howmany(rtbmp_bytes, blksz) + 1) * num_ops;
}

/*
 * Various log reservation values.
 *
 * These are based on the size of the file system block because that is what
 * most transactions manipulate.  Each adds in an additional 128 bytes per
 * item logged to try to account for the overhead of the transaction mechanism.
 *
 * Note:  Most of the reservations underestimate the number of allocation
 * groups into which they could free extents in the xfs_defer_finish() call.
 * This is because the number in the worst case is quite high and quite
 * unusual.  In order to fix this we need to change xfs_defer_finish() to free
 * extents in only a single AG at a time.  This will require changes to the
 * EFI code as well, however, so that the EFI for the extents not freed is
 * logged again in each transaction.  See SGI PV #261917.
 *
 * Reservation functions here avoid a huge stack in xfs_trans_init due to
 * register overflow from temporaries in the calculations.
 */

/*
 * Compute the log reservation required to handle the refcount update
 * transaction.  Refcount updates are always done via deferred log items.
 *
 * This is calculated as:
 * Data device refcount updates (t1):
 *    the agfs of the ags containing the blocks: nr_ops * sector size
 *    the refcount btrees: nr_ops * 1 trees * (2 * max depth - 1) * block size
 */
static unsigned int
xfs_calc_refcountbt_reservation(
	struct xfs_mount	*mp,
	unsigned int		nr_ops)
{
	unsigned int		blksz = XFS_FSB_TO_B(mp, 1);

	if (!xfs_has_reflink(mp))
		return 0;

	return xfs_calc_buf_res(nr_ops, mp->m_sb.sb_sectsize) +
	       xfs_calc_buf_res(xfs_refcountbt_block_count(mp, nr_ops), blksz);
}

/*
 * In a write transaction we can allocate a maximum of 2
 * extents.  This gives (t1):
 *    the inode getting the new extents: inode size
 *    the inode's bmap btree: max depth * block size
 *    the agfs of the ags from which the extents are allocated: 2 * sector
 *    the superblock free block counter: sector size
 *    the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
 * Or, if we're writing to a realtime file (t2):
 *    the inode getting the new extents: inode size
 *    the inode's bmap btree: max depth * block size
 *    the agfs of the ags from which the extents are allocated: 2 * sector
 *    the superblock free block counter: sector size
 *    the realtime bitmap: ((XFS_BMBT_MAX_EXTLEN / rtextsize) / NBBY) bytes
 *    the realtime summary: 1 block
 *    the allocation btrees: 2 trees * (2 * max depth - 1) * block size
 * And the bmap_finish transaction can free bmap blocks in a join (t3):
 *    the agfs of the ags containing the blocks: 2 * sector size
 *    the agfls of the ags containing the blocks: 2 * sector size
 *    the super block free block counter: sector size
 *    the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
 * And any refcount updates that happen in a separate transaction (t4).
 */
STATIC uint
xfs_calc_write_reservation(
	struct xfs_mount	*mp,
	bool			for_minlogsize)
{
	unsigned int		t1, t2, t3, t4;
	unsigned int		blksz = XFS_FSB_TO_B(mp, 1);

	t1 = xfs_calc_inode_res(mp, 1) +
	     xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), blksz) +
	     xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
	     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz);

	if (xfs_has_realtime(mp)) {
		t2 = xfs_calc_inode_res(mp, 1) +
		     xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
				     blksz) +
		     xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
		     xfs_calc_buf_res(xfs_rtalloc_block_count(mp, 1), blksz) +
		     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1), blksz);
	} else {
		t2 = 0;
	}

	t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
	     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz);

	/*
	 * In the early days of reflink, we included enough reservation to log
	 * two refcountbt splits for each transaction.  The codebase runs
	 * refcountbt updates in separate transactions now, so to compute the
	 * minimum log size, add the refcountbtree splits back to t1 and t3 and
	 * do not account them separately as t4.  Reflink did not support
	 * realtime when the reservations were established, so no adjustment to
	 * t2 is needed.
	 */
	if (for_minlogsize) {
		unsigned int	adj = 0;

		if (xfs_has_reflink(mp))
			adj = xfs_calc_buf_res(
					xfs_refcountbt_block_count(mp, 2),
					blksz);
		t1 += adj;
		t3 += adj;
		return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
	}

	t4 = xfs_calc_refcountbt_reservation(mp, 1);
	return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
}

unsigned int
xfs_calc_write_reservation_minlogsize(
	struct xfs_mount	*mp)
{
	return xfs_calc_write_reservation(mp, true);
}

/*
 * In truncating a file we free up to two extents at once.  We can modify (t1):
 *    the inode being truncated: inode size
 *    the inode's bmap btree: (max depth + 1) * block size
 * And the bmap_finish transaction can free the blocks and bmap blocks (t2):
 *    the agf for each of the ags: 4 * sector size
 *    the agfl for each of the ags: 4 * sector size
 *    the super block to reflect the freed blocks: sector size
 *    worst case split in allocation btrees per extent assuming 4 extents:
 *		4 exts * 2 trees * (2 * max depth - 1) * block size
 * Or, if it's a realtime file (t3):
 *    the agf for each of the ags: 2 * sector size
 *    the agfl for each of the ags: 2 * sector size
 *    the super block to reflect the freed blocks: sector size
 *    the realtime bitmap:
 *		2 exts * ((XFS_BMBT_MAX_EXTLEN / rtextsize) / NBBY) bytes
 *    the realtime summary: 2 exts * 1 block
 *    worst case split in allocation btrees per extent assuming 2 extents:
 *		2 exts * 2 trees * (2 * max depth - 1) * block size
 * And any refcount updates that happen in a separate transaction (t4).
 */
STATIC uint
xfs_calc_itruncate_reservation(
	struct xfs_mount	*mp,
	bool			for_minlogsize)
{
	unsigned int		t1, t2, t3, t4;
	unsigned int		blksz = XFS_FSB_TO_B(mp, 1);

	t1 = xfs_calc_inode_res(mp, 1) +
	     xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz);

	t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
	     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 4), blksz);

	if (xfs_has_realtime(mp)) {
		t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
		     xfs_calc_buf_res(xfs_rtalloc_block_count(mp, 2), blksz) +
		     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2), blksz);
	} else {
		t3 = 0;
	}

	/*
	 * In the early days of reflink, we included enough reservation to log
	 * four refcountbt splits in the same transaction as bnobt/cntbt
	 * updates.  The codebase runs refcountbt updates in separate
	 * transactions now, so to compute the minimum log size, add the
	 * refcount btree splits back here and do not compute them separately
	 * as t4.  Reflink did not support realtime when the reservations were
	 * established, so do not adjust t3.
	 */
	if (for_minlogsize) {
		if (xfs_has_reflink(mp))
			t2 += xfs_calc_buf_res(
					xfs_refcountbt_block_count(mp, 4),
					blksz);

		return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3);
	}

	t4 = xfs_calc_refcountbt_reservation(mp, 2);
	return XFS_DQUOT_LOGRES(mp) + max(t4, max3(t1, t2, t3));
}

unsigned int
xfs_calc_itruncate_reservation_minlogsize(
	struct xfs_mount	*mp)
{
	return xfs_calc_itruncate_reservation(mp, true);
}

/*
 * In renaming a files we can modify:
 *    the four inodes involved: 4 * inode size
 *    the two directory btrees: 2 * (max depth + v2) * dir block size
 *    the two directory bmap btrees: 2 * max depth * block size
 * And the bmap_finish transaction can free dir and bmap blocks (two sets
 *	of bmap blocks) giving:
 *    the agf for the ags in which the blocks live: 3 * sector size
 *    the agfl for the ags in which the blocks live: 3 * sector size
 *    the superblock for the free block count: sector size
 *    the allocation btrees: 3 exts * 2 trees * (2 * max depth - 1) * block size
 */
STATIC uint
xfs_calc_rename_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		max((xfs_calc_inode_res(mp, 4) +
		     xfs_calc_buf_res(2 * XFS_DIROP_LOG_COUNT(mp),
				      XFS_FSB_TO_B(mp, 1))),
		    (xfs_calc_buf_res(7, mp->m_sb.sb_sectsize) +
		     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 3),
				      XFS_FSB_TO_B(mp, 1))));
}

/*
 * For removing an inode from unlinked list at first, we can modify:
 *    the agi hash list and counters: sector size
 *    the on disk inode before ours in the agi hash list: inode cluster size
 *    the on disk inode in the agi hash list: inode cluster size
 */
STATIC uint
xfs_calc_iunlink_remove_reservation(
	struct xfs_mount        *mp)
{
	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
	       2 * M_IGEO(mp)->inode_cluster_size;
}

/*
 * For creating a link to an inode:
 *    the parent directory inode: inode size
 *    the linked inode: inode size
 *    the directory btree could split: (max depth + v2) * dir block size
 *    the directory bmap btree could join or split: (max depth + v2) * blocksize
 * And the bmap_finish transaction can free some bmap blocks giving:
 *    the agf for the ag in which the blocks live: sector size
 *    the agfl for the ag in which the blocks live: sector size
 *    the superblock for the free block count: sector size
 *    the allocation btrees: 2 trees * (2 * max depth - 1) * block size
 */
STATIC uint
xfs_calc_link_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		xfs_calc_iunlink_remove_reservation(mp) +
		max((xfs_calc_inode_res(mp, 2) +
		     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
				      XFS_FSB_TO_B(mp, 1))),
		    (xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
		     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
				      XFS_FSB_TO_B(mp, 1))));
}

/*
 * For adding an inode to unlinked list we can modify:
 *    the agi hash list: sector size
 *    the on disk inode: inode cluster size
 */
STATIC uint
xfs_calc_iunlink_add_reservation(xfs_mount_t *mp)
{
	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
			M_IGEO(mp)->inode_cluster_size;
}

/*
 * For removing a directory entry we can modify:
 *    the parent directory inode: inode size
 *    the removed inode: inode size
 *    the directory btree could join: (max depth + v2) * dir block size
 *    the directory bmap btree could join or split: (max depth + v2) * blocksize
 * And the bmap_finish transaction can free the dir and bmap blocks giving:
 *    the agf for the ag in which the blocks live: 2 * sector size
 *    the agfl for the ag in which the blocks live: 2 * sector size
 *    the superblock for the free block count: sector size
 *    the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
 */
STATIC uint
xfs_calc_remove_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		xfs_calc_iunlink_add_reservation(mp) +
		max((xfs_calc_inode_res(mp, 2) +
		     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
				      XFS_FSB_TO_B(mp, 1))),
		    (xfs_calc_buf_res(4, mp->m_sb.sb_sectsize) +
		     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2),
				      XFS_FSB_TO_B(mp, 1))));
}

/*
 * For create, break it in to the two cases that the transaction
 * covers. We start with the modify case - allocation done by modification
 * of the state of existing inodes - and the allocation case.
 */

/*
 * For create we can modify:
 *    the parent directory inode: inode size
 *    the new inode: inode size
 *    the inode btree entry: block size
 *    the superblock for the nlink flag: sector size
 *    the directory btree: (max depth + v2) * dir block size
 *    the directory inode's bmap btree: (max depth + v2) * block size
 *    the finobt (record modification and allocation btrees)
 */
STATIC uint
xfs_calc_create_resv_modify(
	struct xfs_mount	*mp)
{
	return xfs_calc_inode_res(mp, 2) +
		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
		(uint)XFS_FSB_TO_B(mp, 1) +
		xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1)) +
		xfs_calc_finobt_res(mp);
}

/*
 * For icreate we can allocate some inodes giving:
 *    the agi and agf of the ag getting the new inodes: 2 * sectorsize
 *    the superblock for the nlink flag: sector size
 *    the inode chunk (allocation, optional init)
 *    the inobt (record insertion)
 *    the finobt (optional, record insertion)
 */
STATIC uint
xfs_calc_icreate_resv_alloc(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
		mp->m_sb.sb_sectsize +
		xfs_calc_inode_chunk_res(mp, _ALLOC) +
		xfs_calc_inobt_res(mp) +
		xfs_calc_finobt_res(mp);
}

STATIC uint
xfs_calc_icreate_reservation(xfs_mount_t *mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		max(xfs_calc_icreate_resv_alloc(mp),
		    xfs_calc_create_resv_modify(mp));
}

STATIC uint
xfs_calc_create_tmpfile_reservation(
	struct xfs_mount        *mp)
{
	uint	res = XFS_DQUOT_LOGRES(mp);

	res += xfs_calc_icreate_resv_alloc(mp);
	return res + xfs_calc_iunlink_add_reservation(mp);
}

/*
 * Making a new directory is the same as creating a new file.
 */
STATIC uint
xfs_calc_mkdir_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_icreate_reservation(mp);
}


/*
 * Making a new symplink is the same as creating a new file, but
 * with the added blocks for remote symlink data which can be up to 1kB in
 * length (XFS_SYMLINK_MAXLEN).
 */
STATIC uint
xfs_calc_symlink_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_icreate_reservation(mp) +
	       xfs_calc_buf_res(1, XFS_SYMLINK_MAXLEN);
}

/*
 * In freeing an inode we can modify:
 *    the inode being freed: inode size
 *    the super block free inode counter, AGF and AGFL: sector size
 *    the on disk inode (agi unlinked list removal)
 *    the inode chunk (invalidated, headers only)
 *    the inode btree
 *    the finobt (record insertion, removal or modification)
 *
 * Note that the inode chunk res. includes an allocfree res. for freeing of the
 * inode chunk. This is technically extraneous because the inode chunk free is
 * deferred (it occurs after a transaction roll). Include the extra reservation
 * anyways since we've had reports of ifree transaction overruns due to too many
 * agfl fixups during inode chunk frees.
 */
STATIC uint
xfs_calc_ifree_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		xfs_calc_inode_res(mp, 1) +
		xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
		xfs_calc_iunlink_remove_reservation(mp) +
		xfs_calc_inode_chunk_res(mp, _FREE) +
		xfs_calc_inobt_res(mp) +
		xfs_calc_finobt_res(mp);
}

/*
 * When only changing the inode we log the inode and possibly the superblock
 * We also add a bit of slop for the transaction stuff.
 */
STATIC uint
xfs_calc_ichange_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		xfs_calc_inode_res(mp, 1) +
		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);

}

/*
 * Growing the data section of the filesystem.
 *	superblock
 *	agi and agf
 *	allocation btrees
 */
STATIC uint
xfs_calc_growdata_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) +
		xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
				 XFS_FSB_TO_B(mp, 1));
}

/*
 * Growing the rt section of the filesystem.
 * In the first set of transactions (ALLOC) we allocate space to the
 * bitmap or summary files.
 *	superblock: sector size
 *	agf of the ag from which the extent is allocated: sector size
 *	bmap btree for bitmap/summary inode: max depth * blocksize
 *	bitmap/summary inode: inode size
 *	allocation btrees for 1 block alloc: 2 * (2 * maxdepth - 1) * blocksize
 */
STATIC uint
xfs_calc_growrtalloc_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
		xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK),
				 XFS_FSB_TO_B(mp, 1)) +
		xfs_calc_inode_res(mp, 1) +
		xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
				 XFS_FSB_TO_B(mp, 1));
}

/*
 * Growing the rt section of the filesystem.
 * In the second set of transactions (ZERO) we zero the new metadata blocks.
 *	one bitmap/summary block: blocksize
 */
STATIC uint
xfs_calc_growrtzero_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(1, mp->m_sb.sb_blocksize);
}

/*
 * Growing the rt section of the filesystem.
 * In the third set of transactions (FREE) we update metadata without
 * allocating any new blocks.
 *	superblock: sector size
 *	bitmap inode: inode size
 *	summary inode: inode size
 *	one bitmap block: blocksize
 *	summary blocks: new summary size
 */
STATIC uint
xfs_calc_growrtfree_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
		xfs_calc_inode_res(mp, 2) +
		xfs_calc_buf_res(1, mp->m_sb.sb_blocksize) +
		xfs_calc_buf_res(1, mp->m_rsumsize);
}

/*
 * Logging the inode modification timestamp on a synchronous write.
 *	inode
 */
STATIC uint
xfs_calc_swrite_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_inode_res(mp, 1);
}

/*
 * Logging the inode mode bits when writing a setuid/setgid file
 *	inode
 */
STATIC uint
xfs_calc_writeid_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_inode_res(mp, 1);
}

/*
 * Converting the inode from non-attributed to attributed.
 *	the inode being converted: inode size
 *	agf block and superblock (for block allocation)
 *	the new block (directory sized)
 *	bmap blocks for the new directory block
 *	allocation btrees
 */
STATIC uint
xfs_calc_addafork_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		xfs_calc_inode_res(mp, 1) +
		xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
		xfs_calc_buf_res(1, mp->m_dir_geo->blksize) +
		xfs_calc_buf_res(XFS_DAENTER_BMAP1B(mp, XFS_DATA_FORK) + 1,
				 XFS_FSB_TO_B(mp, 1)) +
		xfs_calc_buf_res(xfs_allocfree_block_count(mp, 1),
				 XFS_FSB_TO_B(mp, 1));
}

/*
 * Removing the attribute fork of a file
 *    the inode being truncated: inode size
 *    the inode's bmap btree: max depth * block size
 * And the bmap_finish transaction can free the blocks and bmap blocks:
 *    the agf for each of the ags: 4 * sector size
 *    the agfl for each of the ags: 4 * sector size
 *    the super block to reflect the freed blocks: sector size
 *    worst case split in allocation btrees per extent assuming 4 extents:
 *		4 exts * 2 trees * (2 * max depth - 1) * block size
 */
STATIC uint
xfs_calc_attrinval_reservation(
	struct xfs_mount	*mp)
{
	return max((xfs_calc_inode_res(mp, 1) +
		    xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
				     XFS_FSB_TO_B(mp, 1))),
		   (xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) +
		    xfs_calc_buf_res(xfs_allocfree_block_count(mp, 4),
				     XFS_FSB_TO_B(mp, 1))));
}

/*
 * Setting an attribute at mount time.
 *	the inode getting the attribute
 *	the superblock for allocations
 *	the agfs extents are allocated from
 *	the attribute btree * max depth
 *	the inode allocation btree
 * Since attribute transaction space is dependent on the size of the attribute,
 * the calculation is done partially at mount time and partially at runtime(see
 * below).
 */
STATIC uint
xfs_calc_attrsetm_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		xfs_calc_inode_res(mp, 1) +
		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
		xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH, XFS_FSB_TO_B(mp, 1));
}

/*
 * Setting an attribute at runtime, transaction space unit per block.
 * 	the superblock for allocations: sector size
 *	the inode bmap btree could join or split: max depth * block size
 * Since the runtime attribute transaction space is dependent on the total
 * blocks needed for the 1st bmap, here we calculate out the space unit for
 * one block so that the caller could figure out the total space according
 * to the attibute extent length in blocks by:
 *	ext * M_RES(mp)->tr_attrsetrt.tr_logres
 */
STATIC uint
xfs_calc_attrsetrt_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
		xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK),
				 XFS_FSB_TO_B(mp, 1));
}

/*
 * Removing an attribute.
 *    the inode: inode size
 *    the attribute btree could join: max depth * block size
 *    the inode bmap btree could join or split: max depth * block size
 * And the bmap_finish transaction can free the attr blocks freed giving:
 *    the agf for the ag in which the blocks live: 2 * sector size
 *    the agfl for the ag in which the blocks live: 2 * sector size
 *    the superblock for the free block count: sector size
 *    the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
 */
STATIC uint
xfs_calc_attrrm_reservation(
	struct xfs_mount	*mp)
{
	return XFS_DQUOT_LOGRES(mp) +
		max((xfs_calc_inode_res(mp, 1) +
		     xfs_calc_buf_res(XFS_DA_NODE_MAXDEPTH,
				      XFS_FSB_TO_B(mp, 1)) +
		     (uint)XFS_FSB_TO_B(mp,
					XFS_BM_MAXLEVELS(mp, XFS_ATTR_FORK)) +
		     xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), 0)),
		    (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) +
		     xfs_calc_buf_res(xfs_allocfree_block_count(mp, 2),
				      XFS_FSB_TO_B(mp, 1))));
}

/*
 * Clearing a bad agino number in an agi hash bucket.
 */
STATIC uint
xfs_calc_clear_agi_bucket_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}

/*
 * Adjusting quota limits.
 *    the disk quota buffer: sizeof(struct xfs_disk_dquot)
 */
STATIC uint
xfs_calc_qm_setqlim_reservation(void)
{
	return xfs_calc_buf_res(1, sizeof(struct xfs_disk_dquot));
}

/*
 * Allocating quota on disk if needed.
 *	the write transaction log space for quota file extent allocation
 *	the unit of quota allocation: one system block size
 */
STATIC uint
xfs_calc_qm_dqalloc_reservation(
	struct xfs_mount	*mp,
	bool			for_minlogsize)
{
	return xfs_calc_write_reservation(mp, for_minlogsize) +
		xfs_calc_buf_res(1,
			XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) - 1);
}

unsigned int
xfs_calc_qm_dqalloc_reservation_minlogsize(
	struct xfs_mount	*mp)
{
	return xfs_calc_qm_dqalloc_reservation(mp, true);
}

/*
 * Syncing the incore super block changes to disk.
 *     the super block to reflect the changes: sector size
 */
STATIC uint
xfs_calc_sb_reservation(
	struct xfs_mount	*mp)
{
	return xfs_calc_buf_res(1, mp->m_sb.sb_sectsize);
}

void
xfs_trans_resv_calc(
	struct xfs_mount	*mp,
	struct xfs_trans_resv	*resp)
{
	int			logcount_adj = 0;

	/*
	 * The following transactions are logged in physical format and
	 * require a permanent reservation on space.
	 */
	resp->tr_write.tr_logres = xfs_calc_write_reservation(mp, false);
	resp->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
	resp->tr_write.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_itruncate.tr_logres = xfs_calc_itruncate_reservation(mp, false);
	resp->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
	resp->tr_itruncate.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_rename.tr_logres = xfs_calc_rename_reservation(mp);
	resp->tr_rename.tr_logcount = XFS_RENAME_LOG_COUNT;
	resp->tr_rename.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_link.tr_logres = xfs_calc_link_reservation(mp);
	resp->tr_link.tr_logcount = XFS_LINK_LOG_COUNT;
	resp->tr_link.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_remove.tr_logres = xfs_calc_remove_reservation(mp);
	resp->tr_remove.tr_logcount = XFS_REMOVE_LOG_COUNT;
	resp->tr_remove.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_symlink.tr_logres = xfs_calc_symlink_reservation(mp);
	resp->tr_symlink.tr_logcount = XFS_SYMLINK_LOG_COUNT;
	resp->tr_symlink.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_create.tr_logres = xfs_calc_icreate_reservation(mp);
	resp->tr_create.tr_logcount = XFS_CREATE_LOG_COUNT;
	resp->tr_create.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_create_tmpfile.tr_logres =
			xfs_calc_create_tmpfile_reservation(mp);
	resp->tr_create_tmpfile.tr_logcount = XFS_CREATE_TMPFILE_LOG_COUNT;
	resp->tr_create_tmpfile.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_mkdir.tr_logres = xfs_calc_mkdir_reservation(mp);
	resp->tr_mkdir.tr_logcount = XFS_MKDIR_LOG_COUNT;
	resp->tr_mkdir.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_ifree.tr_logres = xfs_calc_ifree_reservation(mp);
	resp->tr_ifree.tr_logcount = XFS_INACTIVE_LOG_COUNT;
	resp->tr_ifree.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_addafork.tr_logres = xfs_calc_addafork_reservation(mp);
	resp->tr_addafork.tr_logcount = XFS_ADDAFORK_LOG_COUNT;
	resp->tr_addafork.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_attrinval.tr_logres = xfs_calc_attrinval_reservation(mp);
	resp->tr_attrinval.tr_logcount = XFS_ATTRINVAL_LOG_COUNT;
	resp->tr_attrinval.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_attrsetm.tr_logres = xfs_calc_attrsetm_reservation(mp);
	resp->tr_attrsetm.tr_logcount = XFS_ATTRSET_LOG_COUNT;
	resp->tr_attrsetm.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_attrrm.tr_logres = xfs_calc_attrrm_reservation(mp);
	resp->tr_attrrm.tr_logcount = XFS_ATTRRM_LOG_COUNT;
	resp->tr_attrrm.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_growrtalloc.tr_logres = xfs_calc_growrtalloc_reservation(mp);
	resp->tr_growrtalloc.tr_logcount = XFS_DEFAULT_PERM_LOG_COUNT;
	resp->tr_growrtalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	resp->tr_qm_dqalloc.tr_logres = xfs_calc_qm_dqalloc_reservation(mp,
			false);
	resp->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT;
	resp->tr_qm_dqalloc.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	/*
	 * The following transactions are logged in logical format with
	 * a default log count.
	 */
	resp->tr_qm_setqlim.tr_logres = xfs_calc_qm_setqlim_reservation();
	resp->tr_qm_setqlim.tr_logcount = XFS_DEFAULT_LOG_COUNT;

	resp->tr_sb.tr_logres = xfs_calc_sb_reservation(mp);
	resp->tr_sb.tr_logcount = XFS_DEFAULT_LOG_COUNT;

	/* growdata requires permanent res; it can free space to the last AG */
	resp->tr_growdata.tr_logres = xfs_calc_growdata_reservation(mp);
	resp->tr_growdata.tr_logcount = XFS_DEFAULT_PERM_LOG_COUNT;
	resp->tr_growdata.tr_logflags |= XFS_TRANS_PERM_LOG_RES;

	/* The following transaction are logged in logical format */
	resp->tr_ichange.tr_logres = xfs_calc_ichange_reservation(mp);
	resp->tr_fsyncts.tr_logres = xfs_calc_swrite_reservation(mp);
	resp->tr_writeid.tr_logres = xfs_calc_writeid_reservation(mp);
	resp->tr_attrsetrt.tr_logres = xfs_calc_attrsetrt_reservation(mp);
	resp->tr_clearagi.tr_logres = xfs_calc_clear_agi_bucket_reservation(mp);
	resp->tr_growrtzero.tr_logres = xfs_calc_growrtzero_reservation(mp);
	resp->tr_growrtfree.tr_logres = xfs_calc_growrtfree_reservation(mp);

	/*
	 * Add one logcount for BUI items that appear with rmap or reflink,
	 * one logcount for refcount intent items, and one logcount for rmap
	 * intent items.
	 */
	if (xfs_has_reflink(mp) || xfs_has_rmapbt(mp))
		logcount_adj++;
	if (xfs_has_reflink(mp))
		logcount_adj++;
	if (xfs_has_rmapbt(mp))
		logcount_adj++;

	resp->tr_itruncate.tr_logcount += logcount_adj;
	resp->tr_write.tr_logcount += logcount_adj;
	resp->tr_qm_dqalloc.tr_logcount += logcount_adj;
}