aboutsummaryrefslogtreecommitdiff
path: root/fs/ocfs2/journal.h
blob: 9ff4e8cf9d972857a79e07a628116084bc6ba506 (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
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * journal.h
 *
 * Defines journalling api and structures.
 *
 * Copyright (C) 2003, 2005 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#ifndef OCFS2_JOURNAL_H
#define OCFS2_JOURNAL_H

#include <linux/fs.h>
#include <linux/jbd2.h>

enum ocfs2_journal_state {
	OCFS2_JOURNAL_FREE = 0,
	OCFS2_JOURNAL_LOADED,
	OCFS2_JOURNAL_IN_SHUTDOWN,
};

struct ocfs2_super;
struct ocfs2_dinode;

/*
 * The recovery_list is a simple linked list of node numbers to recover.
 * It is protected by the recovery_lock.
 */

struct ocfs2_recovery_map {
	unsigned int rm_used;
	unsigned int *rm_entries;
};


struct ocfs2_journal {
	enum ocfs2_journal_state   j_state;    /* Journals current state   */

	journal_t                 *j_journal; /* The kernels journal type */
	struct inode              *j_inode;   /* Kernel inode pointing to
					       * this journal             */
	struct ocfs2_super        *j_osb;     /* pointer to the super
					       * block for the node
					       * we're currently
					       * running on -- not
					       * necessarily the super
					       * block from the node
					       * which we usually run
					       * from (recovery,
					       * etc)                     */
	struct buffer_head        *j_bh;      /* Journal disk inode block */
	atomic_t                  j_num_trans; /* Number of transactions
					        * currently in the system. */
	spinlock_t                j_lock;
	unsigned long             j_trans_id;
	struct rw_semaphore       j_trans_barrier;
	wait_queue_head_t         j_checkpointed;

	/* both fields protected by j_lock*/
	struct list_head          j_la_cleanups;
	struct work_struct        j_recovery_work;
};

extern spinlock_t trans_inc_lock;

/* wrap j_trans_id so we never have it equal to zero. */
static inline unsigned long ocfs2_inc_trans_id(struct ocfs2_journal *j)
{
	unsigned long old_id;
	spin_lock(&trans_inc_lock);
	old_id = j->j_trans_id++;
	if (unlikely(!j->j_trans_id))
		j->j_trans_id = 1;
	spin_unlock(&trans_inc_lock);
	return old_id;
}

static inline void ocfs2_set_ci_lock_trans(struct ocfs2_journal *journal,
					   struct ocfs2_caching_info *ci)
{
	spin_lock(&trans_inc_lock);
	ci->ci_last_trans = journal->j_trans_id;
	spin_unlock(&trans_inc_lock);
}

/* Used to figure out whether it's safe to drop a metadata lock on an
 * cached object. Returns true if all the object's changes have been
 * checkpointed to disk. You should be holding the spinlock on the
 * metadata lock while calling this to be sure that nobody can take
 * the lock and put it on another transaction. */
static inline int ocfs2_ci_fully_checkpointed(struct ocfs2_caching_info *ci)
{
	int ret;
	struct ocfs2_journal *journal =
		OCFS2_SB(ocfs2_metadata_cache_get_super(ci))->journal;

	spin_lock(&trans_inc_lock);
	ret = time_after(journal->j_trans_id, ci->ci_last_trans);
	spin_unlock(&trans_inc_lock);
	return ret;
}

/* convenience function to check if an object backed by struct
 * ocfs2_caching_info  is still new (has never hit disk) Will do you a
 * favor and set created_trans = 0 when you've
 * been checkpointed.  returns '1' if the ci is still new. */
static inline int ocfs2_ci_is_new(struct ocfs2_caching_info *ci)
{
	int ret;
	struct ocfs2_journal *journal =
		OCFS2_SB(ocfs2_metadata_cache_get_super(ci))->journal;

	spin_lock(&trans_inc_lock);
	ret = !(time_after(journal->j_trans_id, ci->ci_created_trans));
	if (!ret)
		ci->ci_created_trans = 0;
	spin_unlock(&trans_inc_lock);
	return ret;
}

/* Wrapper for inodes so we can check system files */
static inline int ocfs2_inode_is_new(struct inode *inode)
{
	/* System files are never "new" as they're written out by
	 * mkfs. This helps us early during mount, before we have the
	 * journal open and j_trans_id could be junk. */
	if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE)
		return 0;

	return ocfs2_ci_is_new(INODE_CACHE(inode));
}

static inline void ocfs2_ci_set_new(struct ocfs2_super *osb,
				    struct ocfs2_caching_info *ci)
{
	spin_lock(&trans_inc_lock);
	ci->ci_created_trans = osb->journal->j_trans_id;
	spin_unlock(&trans_inc_lock);
}

/* Exported only for the journal struct init code in super.c. Do not call. */
void ocfs2_orphan_scan_init(struct ocfs2_super *osb);
void ocfs2_orphan_scan_start(struct ocfs2_super *osb);
void ocfs2_orphan_scan_stop(struct ocfs2_super *osb);
void ocfs2_orphan_scan_exit(struct ocfs2_super *osb);

void ocfs2_complete_recovery(struct work_struct *work);
void ocfs2_wait_for_recovery(struct ocfs2_super *osb);

int ocfs2_recovery_init(struct ocfs2_super *osb);
void ocfs2_recovery_exit(struct ocfs2_super *osb);

int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
/*
 *  Journal Control:
 *  Initialize, Load, Shutdown, Wipe a journal.
 *
 *  ocfs2_journal_init     - Initialize journal structures in the OSB.
 *  ocfs2_journal_load     - Load the given journal off disk. Replay it if
 *                          there's transactions still in there.
 *  ocfs2_journal_shutdown - Shutdown a journal, this will flush all
 *                          uncommitted, uncheckpointed transactions.
 *  ocfs2_journal_wipe     - Wipe transactions from a journal. Optionally
 *                          zero out each block.
 *  ocfs2_recovery_thread  - Perform recovery on a node. osb is our own osb.
 *  ocfs2_mark_dead_nodes - Start recovery on nodes we won't get a heartbeat
 *                          event on.
 *  ocfs2_start_checkpoint - Kick the commit thread to do a checkpoint.
 */
void   ocfs2_set_journal_params(struct ocfs2_super *osb);
int    ocfs2_journal_init(struct ocfs2_journal *journal,
			  int *dirty);
void   ocfs2_journal_shutdown(struct ocfs2_super *osb);
int    ocfs2_journal_wipe(struct ocfs2_journal *journal,
			  int full);
int    ocfs2_journal_load(struct ocfs2_journal *journal, int local,
			  int replayed);
int    ocfs2_check_journals_nolocks(struct ocfs2_super *osb);
void   ocfs2_recovery_thread(struct ocfs2_super *osb,
			     int node_num);
int    ocfs2_mark_dead_nodes(struct ocfs2_super *osb);
void   ocfs2_complete_mount_recovery(struct ocfs2_super *osb);
void ocfs2_complete_quota_recovery(struct ocfs2_super *osb);

static inline void ocfs2_start_checkpoint(struct ocfs2_super *osb)
{
	wake_up(&osb->checkpoint_event);
}

static inline void ocfs2_checkpoint_inode(struct inode *inode)
{
	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);

	if (ocfs2_mount_local(osb))
		return;

	if (!ocfs2_ci_fully_checkpointed(INODE_CACHE(inode))) {
		/* WARNING: This only kicks off a single
		 * checkpoint. If someone races you and adds more
		 * metadata to the journal, you won't know, and will
		 * wind up waiting *a lot* longer than necessary. Right
		 * now we only use this in clear_inode so that's
		 * OK. */
		ocfs2_start_checkpoint(osb);

		wait_event(osb->journal->j_checkpointed,
			   ocfs2_ci_fully_checkpointed(INODE_CACHE(inode)));
	}
}

/*
 *  Transaction Handling:
 *  Manage the lifetime of a transaction handle.
 *
 *  ocfs2_start_trans      - Begin a transaction. Give it an upper estimate of
 *                          the number of blocks that will be changed during
 *                          this handle.
 *  ocfs2_commit_trans - Complete a handle. It might return -EIO if
 *                       the journal was aborted. The majority of paths don't
 *                       check the return value as an error there comes too
 *                       late to do anything (and will be picked up in a
 *                       later transaction).
 *  ocfs2_extend_trans     - Extend a handle by nblocks credits. This may
 *                          commit the handle to disk in the process, but will
 *                          not release any locks taken during the transaction.
 *  ocfs2_journal_access* - Notify the handle that we want to journal this
 *                          buffer. Will have to call ocfs2_journal_dirty once
 *                          we've actually dirtied it. Type is one of . or .
 *                          Always call the specific flavor of
 *                          ocfs2_journal_access_*() unless you intend to
 *                          manage the checksum by hand.
 *  ocfs2_journal_dirty    - Mark a journalled buffer as having dirty data.
 *  ocfs2_jbd2_file_inode  - Mark an inode so that its data goes out before
 *                           the current handle commits.
 */

/* You must always start_trans with a number of buffs > 0, but it's
 * perfectly legal to go through an entire transaction without having
 * dirtied any buffers. */
handle_t		    *ocfs2_start_trans(struct ocfs2_super *osb,
					       int max_buffs);
int			     ocfs2_commit_trans(struct ocfs2_super *osb,
						handle_t *handle);
int			     ocfs2_extend_trans(handle_t *handle, int nblocks);
int			     ocfs2_allocate_extend_trans(handle_t *handle,
						int thresh);

/*
 * Define an arbitrary limit for the amount of data we will anticipate
 * writing to any given transaction.  For unbounded transactions such as
 * fallocate(2) we can write more than this, but we always
 * start off at the maximum transaction size and grow the transaction
 * optimistically as we go.
 */
#define OCFS2_MAX_TRANS_DATA	64U

/*
 * Create access is for when we get a newly created buffer and we're
 * not gonna read it off disk, but rather fill it ourselves.  Right
 * now, we don't do anything special with this (it turns into a write
 * request), but this is a good placeholder in case we do...
 *
 * Write access is for when we read a block off disk and are going to
 * modify it. This way the journalling layer knows it may need to make
 * a copy of that block (if it's part of another, uncommitted
 * transaction) before we do so.
 */
#define OCFS2_JOURNAL_ACCESS_CREATE 0
#define OCFS2_JOURNAL_ACCESS_WRITE  1
#define OCFS2_JOURNAL_ACCESS_UNDO   2


/* ocfs2_inode */
int ocfs2_journal_access_di(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* ocfs2_extent_block */
int ocfs2_journal_access_eb(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* ocfs2_refcount_block */
int ocfs2_journal_access_rb(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* ocfs2_group_desc */
int ocfs2_journal_access_gd(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* ocfs2_xattr_block */
int ocfs2_journal_access_xb(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* quota blocks */
int ocfs2_journal_access_dq(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* dirblock */
int ocfs2_journal_access_db(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* ocfs2_dx_root_block */
int ocfs2_journal_access_dr(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* ocfs2_dx_leaf */
int ocfs2_journal_access_dl(handle_t *handle, struct ocfs2_caching_info *ci,
			    struct buffer_head *bh, int type);
/* Anything that has no ecc */
int ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci,
			 struct buffer_head *bh, int type);

/*
 * A word about the journal_access/journal_dirty "dance". It is
 * entirely legal to journal_access a buffer more than once (as long
 * as the access type is the same -- I'm not sure what will happen if
 * access type is different but this should never happen anyway) It is
 * also legal to journal_dirty a buffer more than once. In fact, you
 * can even journal_access a buffer after you've done a
 * journal_access/journal_dirty pair. The only thing you cannot do
 * however, is journal_dirty a buffer which you haven't yet passed to
 * journal_access at least once.
 *
 * That said, 99% of the time this doesn't matter and this is what the
 * path looks like:
 *
 *	<read a bh>
 *	ocfs2_journal_access(handle, bh,	OCFS2_JOURNAL_ACCESS_WRITE);
 *	<modify the bh>
 * 	ocfs2_journal_dirty(handle, bh);
 */
void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh);

/*
 *  Credit Macros:
 *  Convenience macros to calculate number of credits needed.
 *
 *  For convenience sake, I have a set of macros here which calculate
 *  the *maximum* number of sectors which will be changed for various
 *  metadata updates.
 */

/* simple file updates like chmod, etc. */
#define OCFS2_INODE_UPDATE_CREDITS 1

/* extended attribute block update */
#define OCFS2_XATTR_BLOCK_UPDATE_CREDITS 1

/* Update of a single quota block */
#define OCFS2_QUOTA_BLOCK_UPDATE_CREDITS 1

/* global quotafile inode update, data block */
#define OCFS2_QINFO_WRITE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + \
				   OCFS2_QUOTA_BLOCK_UPDATE_CREDITS)

#define OCFS2_LOCAL_QINFO_WRITE_CREDITS OCFS2_QUOTA_BLOCK_UPDATE_CREDITS
/*
 * The two writes below can accidentally see global info dirty due
 * to set_info() quotactl so make them prepared for the writes.
 */
/* quota data block, global info */
/* Write to local quota file */
#define OCFS2_QWRITE_CREDITS (OCFS2_QINFO_WRITE_CREDITS + \
			      OCFS2_QUOTA_BLOCK_UPDATE_CREDITS)

/* global quota data block, local quota data block, global quota inode,
 * global quota info */
#define OCFS2_QSYNC_CREDITS (OCFS2_QINFO_WRITE_CREDITS + \
			     2 * OCFS2_QUOTA_BLOCK_UPDATE_CREDITS)

static inline int ocfs2_quota_trans_credits(struct super_block *sb)
{
	int credits = 0;

	if (OCFS2_HAS_RO_COMPAT_FEATURE(sb, OCFS2_FEATURE_RO_COMPAT_USRQUOTA))
		credits += OCFS2_QWRITE_CREDITS;
	if (OCFS2_HAS_RO_COMPAT_FEATURE(sb, OCFS2_FEATURE_RO_COMPAT_GRPQUOTA))
		credits += OCFS2_QWRITE_CREDITS;
	return credits;
}

/* group extend. inode update and last group update. */
#define OCFS2_GROUP_EXTEND_CREDITS	(OCFS2_INODE_UPDATE_CREDITS + 1)

/* group add. inode update and the new group update. */
#define OCFS2_GROUP_ADD_CREDITS	(OCFS2_INODE_UPDATE_CREDITS + 1)

/* get one bit out of a suballocator: dinode + group descriptor +
 * prev. group desc. if we relink. */
#define OCFS2_SUBALLOC_ALLOC (3)

static inline int ocfs2_inline_to_extents_credits(struct super_block *sb)
{
	return OCFS2_SUBALLOC_ALLOC + OCFS2_INODE_UPDATE_CREDITS +
	       ocfs2_quota_trans_credits(sb);
}

/* dinode + group descriptor update. We don't relink on free yet. */
#define OCFS2_SUBALLOC_FREE  (2)

#define OCFS2_TRUNCATE_LOG_UPDATE OCFS2_INODE_UPDATE_CREDITS
#define OCFS2_TRUNCATE_LOG_FLUSH_ONE_REC (OCFS2_SUBALLOC_FREE 		      \
					 + OCFS2_TRUNCATE_LOG_UPDATE)

static inline int ocfs2_remove_extent_credits(struct super_block *sb)
{
	return OCFS2_TRUNCATE_LOG_UPDATE + OCFS2_INODE_UPDATE_CREDITS +
	       ocfs2_quota_trans_credits(sb);
}

/* data block for new dir/symlink, allocation of directory block, dx_root
 * update for free list */
#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + OCFS2_SUBALLOC_ALLOC + 1)

static inline int ocfs2_add_dir_index_credits(struct super_block *sb)
{
	/* 1 block for index, 2 allocs (data, metadata), 1 clusters
	 * worth of blocks for initial extent. */
	return 1 + 2 * OCFS2_SUBALLOC_ALLOC +
		ocfs2_clusters_to_blocks(sb, 1);
}

/* parent fe, parent block, new file entry, index leaf, inode alloc fe, inode
 * alloc group descriptor + mkdir/symlink blocks + dir blocks + xattr
 * blocks + quota update */
static inline int ocfs2_mknod_credits(struct super_block *sb, int is_dir,
				      int xattr_credits)
{
	int dir_credits = OCFS2_DIR_LINK_ADDITIONAL_CREDITS;

	if (is_dir)
		dir_credits += ocfs2_add_dir_index_credits(sb);

	return 4 + OCFS2_SUBALLOC_ALLOC + dir_credits + xattr_credits +
	       ocfs2_quota_trans_credits(sb);
}

/* local alloc metadata change + main bitmap updates */
#define OCFS2_WINDOW_MOVE_CREDITS (OCFS2_INODE_UPDATE_CREDITS                 \
				  + OCFS2_SUBALLOC_ALLOC + OCFS2_SUBALLOC_FREE)

/* used when we don't need an allocation change for a dir extend. One
 * for the dinode, one for the new block. */
#define OCFS2_SIMPLE_DIR_EXTEND_CREDITS (2)

/* file update (nlink, etc) + directory mtime/ctime + dir entry block + quota
 * update on dir + index leaf + dx root update for free list +
 * previous dirblock update in the free list */
static inline int ocfs2_link_credits(struct super_block *sb)
{
	return 2*OCFS2_INODE_UPDATE_CREDITS + 4 +
	       ocfs2_quota_trans_credits(sb);
}

/* inode + dir inode (if we unlink a dir), + dir entry block + orphan
 * dir inode link + dir inode index leaf + dir index root */
static inline int ocfs2_unlink_credits(struct super_block *sb)
{
	/* The quota update from ocfs2_link_credits is unused here... */
	return 2 * OCFS2_INODE_UPDATE_CREDITS + 3 + ocfs2_link_credits(sb);
}

/* dinode + orphan dir dinode + inode alloc dinode + orphan dir entry +
 * inode alloc group descriptor + orphan dir index root +
 * orphan dir index leaf */
#define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 4)

/* dinode update, old dir dinode update, new dir dinode update, old
 * dir dir entry, new dir dir entry, dir entry update for renaming
 * directory + target unlink + 3 x dir index leaves */
static inline int ocfs2_rename_credits(struct super_block *sb)
{
	return 3 * OCFS2_INODE_UPDATE_CREDITS + 6 + ocfs2_unlink_credits(sb);
}

/* global bitmap dinode, group desc., relinked group,
 * suballocator dinode, group desc., relinked group,
 * dinode, xattr block */
#define OCFS2_XATTR_BLOCK_CREATE_CREDITS (OCFS2_SUBALLOC_ALLOC * 2 + \
					  + OCFS2_INODE_UPDATE_CREDITS \
					  + OCFS2_XATTR_BLOCK_UPDATE_CREDITS)

/* inode update, removal of dx root block from allocator */
#define OCFS2_DX_ROOT_REMOVE_CREDITS (OCFS2_INODE_UPDATE_CREDITS +	\
				      OCFS2_SUBALLOC_FREE)

static inline int ocfs2_calc_dxi_expand_credits(struct super_block *sb)
{
	int credits = 1 + OCFS2_SUBALLOC_ALLOC;

	credits += ocfs2_clusters_to_blocks(sb, 1);
	credits += ocfs2_quota_trans_credits(sb);

	return credits;
}

/* inode update, new refcount block and its allocation credits. */
#define OCFS2_REFCOUNT_TREE_CREATE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1 \
					    + OCFS2_SUBALLOC_ALLOC)

/* inode and the refcount block update. */
#define OCFS2_REFCOUNT_TREE_SET_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1)

/*
 * inode and the refcount block update.
 * It doesn't include the credits for sub alloc change.
 * So if we need to free the bit, OCFS2_SUBALLOC_FREE needs to be added.
 */
#define OCFS2_REFCOUNT_TREE_REMOVE_CREDITS (OCFS2_INODE_UPDATE_CREDITS + 1)

/* 2 metadata alloc, 2 new blocks and root refcount block */
#define OCFS2_EXPAND_REFCOUNT_TREE_CREDITS (OCFS2_SUBALLOC_ALLOC * 2 + 3)

/*
 * Please note that the caller must make sure that root_el is the root
 * of extent tree. So for an inode, it should be &fe->id2.i_list. Otherwise
 * the result may be wrong.
 */
static inline int ocfs2_calc_extend_credits(struct super_block *sb,
					    struct ocfs2_extent_list *root_el)
{
	int bitmap_blocks, sysfile_bitmap_blocks, extent_blocks;

	/* bitmap dinode, group desc. + relinked group. */
	bitmap_blocks = OCFS2_SUBALLOC_ALLOC;

	/* we might need to shift tree depth so lets assume an
	 * absolute worst case of complete fragmentation.  Even with
	 * that, we only need one update for the dinode, and then
	 * however many metadata chunks needed * a remaining suballoc
	 * alloc. */
	sysfile_bitmap_blocks = 1 +
		(OCFS2_SUBALLOC_ALLOC - 1) * ocfs2_extend_meta_needed(root_el);

	/* this does not include *new* metadata blocks, which are
	 * accounted for in sysfile_bitmap_blocks. root_el +
	 * prev. last_eb_blk + blocks along edge of tree.
	 * calc_symlink_credits passes because we just need 1
	 * credit for the dinode there. */
	extent_blocks = 1 + 1 + le16_to_cpu(root_el->l_tree_depth);

	return bitmap_blocks + sysfile_bitmap_blocks + extent_blocks +
	       ocfs2_quota_trans_credits(sb);
}

static inline int ocfs2_calc_symlink_credits(struct super_block *sb)
{
	int blocks = ocfs2_mknod_credits(sb, 0, 0);

	/* links can be longer than one block so we may update many
	 * within our single allocated extent. */
	blocks += ocfs2_clusters_to_blocks(sb, 1);

	return blocks + ocfs2_quota_trans_credits(sb);
}

static inline int ocfs2_calc_group_alloc_credits(struct super_block *sb,
						 unsigned int cpg)
{
	int blocks;
	int bitmap_blocks = OCFS2_SUBALLOC_ALLOC + 1;
	/* parent inode update + new block group header + bitmap inode update
	   + bitmap blocks affected */
	blocks = 1 + 1 + 1 + bitmap_blocks;
	return blocks;
}

/*
 * Allocating a discontiguous block group requires the credits from
 * ocfs2_calc_group_alloc_credits() as well as enough credits to fill
 * the group descriptor's extent list.  The caller already has started
 * the transaction with ocfs2_calc_group_alloc_credits().  They extend
 * it with these credits.
 */
static inline int ocfs2_calc_bg_discontig_credits(struct super_block *sb)
{
	return ocfs2_extent_recs_per_gd(sb);
}

static inline int ocfs2_calc_tree_trunc_credits(struct super_block *sb,
						unsigned int clusters_to_del,
						struct ocfs2_dinode *fe,
						struct ocfs2_extent_list *last_el)
{
 	/* for dinode + all headers in this pass + update to next leaf */
	u16 next_free = le16_to_cpu(last_el->l_next_free_rec);
	u16 tree_depth = le16_to_cpu(fe->id2.i_list.l_tree_depth);
	int credits = 1 + tree_depth + 1;
	int i;

	i = next_free - 1;
	BUG_ON(i < 0);

	/* We may be deleting metadata blocks, so metadata alloc dinode +
	   one desc. block for each possible delete. */
	if (tree_depth && next_free == 1 &&
	    ocfs2_rec_clusters(last_el, &last_el->l_recs[i]) == clusters_to_del)
		credits += 1 + tree_depth;

	/* update to the truncate log. */
	credits += OCFS2_TRUNCATE_LOG_UPDATE;

	credits += ocfs2_quota_trans_credits(sb);

	return credits;
}

static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
{
	return jbd2_journal_file_inode(handle, &OCFS2_I(inode)->ip_jinode);
}

static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
					       loff_t new_size)
{
	return jbd2_journal_begin_ordered_truncate(
				OCFS2_SB(inode->i_sb)->journal->j_journal,
				&OCFS2_I(inode)->ip_jinode,
				new_size);
}

#endif /* OCFS2_JOURNAL_H */