journal.c 56.4 KB
Newer Older
1
/*
2
 * linux/fs/jbd2/journal.c
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
 *
 * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
 *
 * Copyright 1998 Red Hat corp --- All Rights Reserved
 *
 * This file is part of the Linux kernel and is made available under
 * the terms of the GNU General Public License, version 2, or at your
 * option, any later version, incorporated herein by reference.
 *
 * Generic filesystem journal-writing code; part of the ext2fs
 * journaling system.
 *
 * This file manages journals: areas of disk reserved for logging
 * transactional updates.  This includes the kernel journaling thread
 * which is responsible for scheduling updates to the log.
 *
 * We do not actually manage the physical storage of the journal in this
 * file: that is left to a per-journal policy function, which allows us
 * to store the journal within a filesystem-specified area for ext2
 * journaling (ext2 can use a reserved inode for storing the log).
 */

#include <linux/module.h>
#include <linux/time.h>
#include <linux/fs.h>
28
#include <linux/jbd2.h>
29
30
31
32
33
34
35
36
37
38
39
40
41
42
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/suspend.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/poison.h>
#include <linux/proc_fs.h>

#include <asm/uaccess.h>
#include <asm/page.h>

43
44
45
46
47
48
49
50
51
52
53
54
55
EXPORT_SYMBOL(jbd2_journal_start);
EXPORT_SYMBOL(jbd2_journal_restart);
EXPORT_SYMBOL(jbd2_journal_extend);
EXPORT_SYMBOL(jbd2_journal_stop);
EXPORT_SYMBOL(jbd2_journal_lock_updates);
EXPORT_SYMBOL(jbd2_journal_unlock_updates);
EXPORT_SYMBOL(jbd2_journal_get_write_access);
EXPORT_SYMBOL(jbd2_journal_get_create_access);
EXPORT_SYMBOL(jbd2_journal_get_undo_access);
EXPORT_SYMBOL(jbd2_journal_dirty_data);
EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
EXPORT_SYMBOL(jbd2_journal_release_buffer);
EXPORT_SYMBOL(jbd2_journal_forget);
56
57
58
#if 0
EXPORT_SYMBOL(journal_sync_buffer);
#endif
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
EXPORT_SYMBOL(jbd2_journal_flush);
EXPORT_SYMBOL(jbd2_journal_revoke);

EXPORT_SYMBOL(jbd2_journal_init_dev);
EXPORT_SYMBOL(jbd2_journal_init_inode);
EXPORT_SYMBOL(jbd2_journal_update_format);
EXPORT_SYMBOL(jbd2_journal_check_used_features);
EXPORT_SYMBOL(jbd2_journal_check_available_features);
EXPORT_SYMBOL(jbd2_journal_set_features);
EXPORT_SYMBOL(jbd2_journal_create);
EXPORT_SYMBOL(jbd2_journal_load);
EXPORT_SYMBOL(jbd2_journal_destroy);
EXPORT_SYMBOL(jbd2_journal_update_superblock);
EXPORT_SYMBOL(jbd2_journal_abort);
EXPORT_SYMBOL(jbd2_journal_errno);
EXPORT_SYMBOL(jbd2_journal_ack_err);
EXPORT_SYMBOL(jbd2_journal_clear_err);
EXPORT_SYMBOL(jbd2_log_wait_commit);
EXPORT_SYMBOL(jbd2_journal_start_commit);
EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
EXPORT_SYMBOL(jbd2_journal_wipe);
EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
EXPORT_SYMBOL(jbd2_journal_invalidatepage);
EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
EXPORT_SYMBOL(jbd2_journal_force_commit);
84
85
86

static int journal_convert_superblock_v1(journal_t *, journal_superblock_t *);
static void __journal_abort_soft (journal_t *journal, int errno);
87
static int jbd2_journal_create_jbd_slab(size_t slab_size);
88
89
90
91
92
93
94
95
96
97
98
99
100

/*
 * Helper function used to manage commit timeouts
 */

static void commit_timeout(unsigned long __data)
{
	struct task_struct * p = (struct task_struct *) __data;

	wake_up_process(p);
}

/*
101
 * kjournald2: The main thread function used to manage a logging device
102
103
104
105
106
107
108
109
110
111
112
113
114
115
 * journal.
 *
 * This kernel thread is responsible for two things:
 *
 * 1) COMMIT:  Every so often we need to commit the current state of the
 *    filesystem to disk.  The journal thread is responsible for writing
 *    all of the metadata buffers to disk.
 *
 * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
 *    of the data in that part of the log has been rewritten elsewhere on
 *    the disk.  Flushing these old buffers to reclaim space in the log is
 *    known as checkpointing, and this thread is responsible for that job.
 */

116
static int kjournald2(void *arg)
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
{
	journal_t *journal = arg;
	transaction_t *transaction;

	/*
	 * Set up an interval timer which can be used to trigger a commit wakeup
	 * after the commit interval expires
	 */
	setup_timer(&journal->j_commit_timer, commit_timeout,
			(unsigned long)current);

	/* Record that the journal thread is running */
	journal->j_task = current;
	wake_up(&journal->j_wait_done_commit);

132
	printk(KERN_INFO "kjournald2 starting.  Commit interval %ld seconds\n",
133
134
135
136
137
138
139
140
			journal->j_commit_interval / HZ);

	/*
	 * And now, wait forever for commit wakeup events.
	 */
	spin_lock(&journal->j_state_lock);

loop:
141
	if (journal->j_flags & JBD2_UNMOUNT)
142
143
144
145
146
147
148
149
150
		goto end_loop;

	jbd_debug(1, "commit_sequence=%d, commit_request=%d\n",
		journal->j_commit_sequence, journal->j_commit_request);

	if (journal->j_commit_sequence != journal->j_commit_request) {
		jbd_debug(1, "OK, requests differ\n");
		spin_unlock(&journal->j_state_lock);
		del_timer_sync(&journal->j_commit_timer);
151
		jbd2_journal_commit_transaction(journal);
152
153
154
155
156
157
158
159
160
161
162
		spin_lock(&journal->j_state_lock);
		goto loop;
	}

	wake_up(&journal->j_wait_done_commit);
	if (freezing(current)) {
		/*
		 * The simpler the better. Flushing journal isn't a
		 * good idea, because that depends on threads that may
		 * be already stopped.
		 */
163
		jbd_debug(1, "Now suspending kjournald2\n");
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
		spin_unlock(&journal->j_state_lock);
		refrigerator();
		spin_lock(&journal->j_state_lock);
	} else {
		/*
		 * We assume on resume that commits are already there,
		 * so we don't sleep
		 */
		DEFINE_WAIT(wait);
		int should_sleep = 1;

		prepare_to_wait(&journal->j_wait_commit, &wait,
				TASK_INTERRUPTIBLE);
		if (journal->j_commit_sequence != journal->j_commit_request)
			should_sleep = 0;
		transaction = journal->j_running_transaction;
		if (transaction && time_after_eq(jiffies,
						transaction->t_expires))
			should_sleep = 0;
183
		if (journal->j_flags & JBD2_UNMOUNT)
184
185
186
187
188
189
190
191
192
			should_sleep = 0;
		if (should_sleep) {
			spin_unlock(&journal->j_state_lock);
			schedule();
			spin_lock(&journal->j_state_lock);
		}
		finish_wait(&journal->j_wait_commit, &wait);
	}

193
	jbd_debug(1, "kjournald2 wakes\n");
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213

	/*
	 * Were we woken up by a commit wakeup event?
	 */
	transaction = journal->j_running_transaction;
	if (transaction && time_after_eq(jiffies, transaction->t_expires)) {
		journal->j_commit_request = transaction->t_tid;
		jbd_debug(1, "woke because of timeout\n");
	}
	goto loop;

end_loop:
	spin_unlock(&journal->j_state_lock);
	del_timer_sync(&journal->j_commit_timer);
	journal->j_task = NULL;
	wake_up(&journal->j_wait_done_commit);
	jbd_debug(1, "Journal thread exiting.\n");
	return 0;
}

214
static void jbd2_journal_start_thread(journal_t *journal)
215
{
216
	kthread_run(kjournald2, journal, "kjournald2");
217
218
219
220
221
222
	wait_event(journal->j_wait_done_commit, journal->j_task != 0);
}

static void journal_kill_thread(journal_t *journal)
{
	spin_lock(&journal->j_state_lock);
223
	journal->j_flags |= JBD2_UNMOUNT;
224
225
226
227
228
229
230
231
232
233
234

	while (journal->j_task) {
		wake_up(&journal->j_wait_commit);
		spin_unlock(&journal->j_state_lock);
		wait_event(journal->j_wait_done_commit, journal->j_task == 0);
		spin_lock(&journal->j_state_lock);
	}
	spin_unlock(&journal->j_state_lock);
}

/*
235
 * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal.
236
237
238
239
240
241
242
 *
 * Writes a metadata buffer to a given disk block.  The actual IO is not
 * performed but a new buffer_head is constructed which labels the data
 * to be written with the correct destination disk block.
 *
 * Any magic-number escaping which needs to be done will cause a
 * copy-out here.  If the buffer happens to start with the
243
 * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the
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
 * magic number is only written to the log for descripter blocks.  In
 * this case, we copy the data and replace the first word with 0, and we
 * return a result code which indicates that this buffer needs to be
 * marked as an escaped buffer in the corresponding log descriptor
 * block.  The missing word can then be restored when the block is read
 * during recovery.
 *
 * If the source buffer has already been modified by a new transaction
 * since we took the last commit snapshot, we use the frozen copy of
 * that data for IO.  If we end up using the existing buffer_head's data
 * for the write, then we *have* to lock the buffer to prevent anyone
 * else from using and possibly modifying it while the IO is in
 * progress.
 *
 * The function returns a pointer to the buffer_heads to be used for IO.
 *
 * We assume that the journal has already been locked in this function.
 *
 * Return value:
 *  <0: Error
 * >=0: Finished OK
 *
 * On success:
 * Bit 0 set == escape performed on the data
 * Bit 1 set == buffer copy-out performed (kfree the data after IO)
 */

271
int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
272
273
				  struct journal_head  *jh_in,
				  struct journal_head **jh_out,
274
				  unsigned long long blocknr)
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
{
	int need_copy_out = 0;
	int done_copy_out = 0;
	int do_escape = 0;
	char *mapped_data;
	struct buffer_head *new_bh;
	struct journal_head *new_jh;
	struct page *new_page;
	unsigned int new_offset;
	struct buffer_head *bh_in = jh2bh(jh_in);

	/*
	 * The buffer really shouldn't be locked: only the current committing
	 * transaction is allowed to write it, so nobody else is allowed
	 * to do any IO.
	 *
	 * akpm: except if we're journalling data, and write() output is
	 * also part of a shared mapping, and another thread has
	 * decided to launch a writepage() against this buffer.
	 */
	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));

	new_bh = alloc_buffer_head(GFP_NOFS|__GFP_NOFAIL);

	/*
	 * If a new transaction has already done a buffer copy-out, then
	 * we use that version of the data for the commit.
	 */
	jbd_lock_bh_state(bh_in);
repeat:
	if (jh_in->b_frozen_data) {
		done_copy_out = 1;
		new_page = virt_to_page(jh_in->b_frozen_data);
		new_offset = offset_in_page(jh_in->b_frozen_data);
	} else {
		new_page = jh2bh(jh_in)->b_page;
		new_offset = offset_in_page(jh2bh(jh_in)->b_data);
	}

	mapped_data = kmap_atomic(new_page, KM_USER0);
	/*
	 * Check for escaping
	 */
	if (*((__be32 *)(mapped_data + new_offset)) ==
319
				cpu_to_be32(JBD2_MAGIC_NUMBER)) {
320
321
322
323
324
325
326
327
328
329
330
331
		need_copy_out = 1;
		do_escape = 1;
	}
	kunmap_atomic(mapped_data, KM_USER0);

	/*
	 * Do we need to do a data copy?
	 */
	if (need_copy_out && !done_copy_out) {
		char *tmp;

		jbd_unlock_bh_state(bh_in);
332
		tmp = jbd2_slab_alloc(bh_in->b_size, GFP_NOFS);
333
334
		jbd_lock_bh_state(bh_in);
		if (jh_in->b_frozen_data) {
335
			jbd2_slab_free(tmp, bh_in->b_size);
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
			goto repeat;
		}

		jh_in->b_frozen_data = tmp;
		mapped_data = kmap_atomic(new_page, KM_USER0);
		memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
		kunmap_atomic(mapped_data, KM_USER0);

		new_page = virt_to_page(tmp);
		new_offset = offset_in_page(tmp);
		done_copy_out = 1;
	}

	/*
	 * Did we need to do an escaping?  Now we've done all the
	 * copying, we can finally do so.
	 */
	if (do_escape) {
		mapped_data = kmap_atomic(new_page, KM_USER0);
		*((unsigned int *)(mapped_data + new_offset)) = 0;
		kunmap_atomic(mapped_data, KM_USER0);
	}

	/* keep subsequent assertions sane */
	new_bh->b_state = 0;
	init_buffer(new_bh, NULL, NULL);
	atomic_set(&new_bh->b_count, 1);
	jbd_unlock_bh_state(bh_in);

365
	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382

	set_bh_page(new_bh, new_page, new_offset);
	new_jh->b_transaction = NULL;
	new_bh->b_size = jh2bh(jh_in)->b_size;
	new_bh->b_bdev = transaction->t_journal->j_dev;
	new_bh->b_blocknr = blocknr;
	set_buffer_mapped(new_bh);
	set_buffer_dirty(new_bh);

	*jh_out = new_jh;

	/*
	 * The to-be-written buffer needs to get moved to the io queue,
	 * and the original buffer whose contents we are shadowing or
	 * copying is moved to the transaction's shadow queue.
	 */
	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
383
	jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
384
	JBUFFER_TRACE(new_jh, "file as BJ_IO");
385
	jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);
386
387
388
389
390
391
392
393
394
395

	return do_escape | (done_copy_out << 1);
}

/*
 * Allocation code for the journal file.  Manage the space left in the
 * journal, so that we can begin checkpointing when appropriate.
 */

/*
396
 * __jbd2_log_space_left: Return the number of free blocks left in the journal.
397
398
399
400
401
402
 *
 * Called with the journal already locked.
 *
 * Called under j_state_lock
 */

403
int __jbd2_log_space_left(journal_t *journal)
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
{
	int left = journal->j_free;

	assert_spin_locked(&journal->j_state_lock);

	/*
	 * Be pessimistic here about the number of those free blocks which
	 * might be required for log descriptor control blocks.
	 */

#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */

	left -= MIN_LOG_RESERVED_BLOCKS;

	if (left <= 0)
		return 0;
	left -= (left >> 3);
	return left;
}

/*
 * Called under j_state_lock.  Returns true if a transaction was started.
 */
427
int __jbd2_log_start_commit(journal_t *journal, tid_t target)
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
{
	/*
	 * Are we already doing a recent enough commit?
	 */
	if (!tid_geq(journal->j_commit_request, target)) {
		/*
		 * We want a new commit: OK, mark the request and wakup the
		 * commit thread.  We do _not_ do the commit ourselves.
		 */

		journal->j_commit_request = target;
		jbd_debug(1, "JBD: requesting commit %d/%d\n",
			  journal->j_commit_request,
			  journal->j_commit_sequence);
		wake_up(&journal->j_wait_commit);
		return 1;
	}
	return 0;
}

448
int jbd2_log_start_commit(journal_t *journal, tid_t tid)
449
450
451
452
{
	int ret;

	spin_lock(&journal->j_state_lock);
453
	ret = __jbd2_log_start_commit(journal, tid);
454
455
456
457
458
459
460
461
462
463
464
465
466
467
	spin_unlock(&journal->j_state_lock);
	return ret;
}

/*
 * Force and wait upon a commit if the calling process is not within
 * transaction.  This is used for forcing out undo-protected data which contains
 * bitmaps, when the fs is running out of space.
 *
 * We can only force the running transaction if we don't have an active handle;
 * otherwise, we will deadlock.
 *
 * Returns true if a transaction was started.
 */
468
int jbd2_journal_force_commit_nested(journal_t *journal)
469
470
471
472
473
474
475
{
	transaction_t *transaction = NULL;
	tid_t tid;

	spin_lock(&journal->j_state_lock);
	if (journal->j_running_transaction && !current->journal_info) {
		transaction = journal->j_running_transaction;
476
		__jbd2_log_start_commit(journal, transaction->t_tid);
477
478
479
480
481
482
483
484
485
486
	} else if (journal->j_committing_transaction)
		transaction = journal->j_committing_transaction;

	if (!transaction) {
		spin_unlock(&journal->j_state_lock);
		return 0;	/* Nothing to retry */
	}

	tid = transaction->t_tid;
	spin_unlock(&journal->j_state_lock);
487
	jbd2_log_wait_commit(journal, tid);
488
489
490
491
492
493
494
	return 1;
}

/*
 * Start a commit of the current running transaction (if any).  Returns true
 * if a transaction was started, and fills its tid in at *ptid
 */
495
int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
496
497
498
499
500
501
502
{
	int ret = 0;

	spin_lock(&journal->j_state_lock);
	if (journal->j_running_transaction) {
		tid_t tid = journal->j_running_transaction->t_tid;

503
		ret = __jbd2_log_start_commit(journal, tid);
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
		if (ret && ptid)
			*ptid = tid;
	} else if (journal->j_committing_transaction && ptid) {
		/*
		 * If ext3_write_super() recently started a commit, then we
		 * have to wait for completion of that transaction
		 */
		*ptid = journal->j_committing_transaction->t_tid;
		ret = 1;
	}
	spin_unlock(&journal->j_state_lock);
	return ret;
}

/*
 * Wait for a specified commit to complete.
 * The caller may not hold the journal lock.
 */
522
int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
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
{
	int err = 0;

#ifdef CONFIG_JBD_DEBUG
	spin_lock(&journal->j_state_lock);
	if (!tid_geq(journal->j_commit_request, tid)) {
		printk(KERN_EMERG
		       "%s: error: j_commit_request=%d, tid=%d\n",
		       __FUNCTION__, journal->j_commit_request, tid);
	}
	spin_unlock(&journal->j_state_lock);
#endif
	spin_lock(&journal->j_state_lock);
	while (tid_gt(tid, journal->j_commit_sequence)) {
		jbd_debug(1, "JBD: want %d, j_commit_sequence=%d\n",
				  tid, journal->j_commit_sequence);
		wake_up(&journal->j_wait_commit);
		spin_unlock(&journal->j_state_lock);
		wait_event(journal->j_wait_done_commit,
				!tid_gt(tid, journal->j_commit_sequence));
		spin_lock(&journal->j_state_lock);
	}
	spin_unlock(&journal->j_state_lock);

	if (unlikely(is_journal_aborted(journal))) {
		printk(KERN_EMERG "journal commit I/O error\n");
		err = -EIO;
	}
	return err;
}

/*
 * Log buffer allocation routines:
 */

558
int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
559
560
561
562
563
564
565
566
567
568
569
570
{
	unsigned long blocknr;

	spin_lock(&journal->j_state_lock);
	J_ASSERT(journal->j_free > 1);

	blocknr = journal->j_head;
	journal->j_head++;
	journal->j_free--;
	if (journal->j_head == journal->j_last)
		journal->j_head = journal->j_first;
	spin_unlock(&journal->j_state_lock);
571
	return jbd2_journal_bmap(journal, blocknr, retp);
572
573
574
575
576
577
578
579
580
}

/*
 * Conversion of logical to physical block numbers for the journal
 *
 * On external journals the journal blocks are identity-mapped, so
 * this is a no-op.  If needed, we can use j_blk_offset - everything is
 * ready.
 */
581
int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
582
		 unsigned long long *retp)
583
584
{
	int err = 0;
585
	unsigned long long ret;
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

	if (journal->j_inode) {
		ret = bmap(journal->j_inode, blocknr);
		if (ret)
			*retp = ret;
		else {
			char b[BDEVNAME_SIZE];

			printk(KERN_ALERT "%s: journal block not found "
					"at offset %lu on %s\n",
				__FUNCTION__,
				blocknr,
				bdevname(journal->j_dev, b));
			err = -EIO;
			__journal_abort_soft(journal, err);
		}
	} else {
		*retp = blocknr; /* +journal->j_blk_offset */
	}
	return err;
}

/*
 * We play buffer_head aliasing tricks to write data/metadata blocks to
 * the journal without copying their contents, but for journal
 * descriptor blocks we do need to generate bona fide buffers.
 *
613
 * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying
614
615
616
617
 * the buffer's contents they really should run flush_dcache_page(bh->b_page).
 * But we don't bother doing that, so there will be coherency problems with
 * mmaps of blockdevs which hold live JBD-controlled filesystems.
 */
618
struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
619
620
{
	struct buffer_head *bh;
621
	unsigned long long blocknr;
622
623
	int err;

624
	err = jbd2_journal_next_log_block(journal, &blocknr);
625
626
627
628
629
630
631
632
633
634

	if (err)
		return NULL;

	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
	lock_buffer(bh);
	memset(bh->b_data, 0, journal->j_blocksize);
	set_buffer_uptodate(bh);
	unlock_buffer(bh);
	BUFFER_TRACE(bh, "return this buffer");
635
	return jbd2_journal_add_journal_head(bh);
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
}

/*
 * Management for journal control blocks: functions to create and
 * destroy journal_t structures, and to initialise and read existing
 * journal blocks from disk.  */

/* First: create and setup a journal_t object in memory.  We initialise
 * very few fields yet: that has to wait until we have created the
 * journal structures from from scratch, or loaded them from disk. */

static journal_t * journal_init_common (void)
{
	journal_t *journal;
	int err;

	journal = jbd_kmalloc(sizeof(*journal), GFP_KERNEL);
	if (!journal)
		goto fail;
	memset(journal, 0, sizeof(*journal));

	init_waitqueue_head(&journal->j_wait_transaction_locked);
	init_waitqueue_head(&journal->j_wait_logspace);
	init_waitqueue_head(&journal->j_wait_done_commit);
	init_waitqueue_head(&journal->j_wait_checkpoint);
	init_waitqueue_head(&journal->j_wait_commit);
	init_waitqueue_head(&journal->j_wait_updates);
	mutex_init(&journal->j_barrier);
	mutex_init(&journal->j_checkpoint_mutex);
	spin_lock_init(&journal->j_revoke_lock);
	spin_lock_init(&journal->j_list_lock);
	spin_lock_init(&journal->j_state_lock);

	journal->j_commit_interval = (HZ * JBD_DEFAULT_MAX_COMMIT_AGE);

	/* The journal is marked for error until we succeed with recovery! */
672
	journal->j_flags = JBD2_ABORT;
673
674

	/* Set up a default-sized revoke table for the new mount. */
675
	err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
676
677
678
679
680
681
682
683
684
	if (err) {
		kfree(journal);
		goto fail;
	}
	return journal;
fail:
	return NULL;
}

685
/* jbd2_journal_init_dev and jbd2_journal_init_inode:
686
687
688
689
690
691
692
693
694
 *
 * Create a journal structure assigned some fixed set of disk blocks to
 * the journal.  We don't actually touch those disk blocks yet, but we
 * need to set up all of the mapping information to tell the journaling
 * system where the journal blocks are.
 *
 */

/**
695
 *  journal_t * jbd2_journal_init_dev() - creates an initialises a journal structure
696
697
698
699
700
701
702
 *  @bdev: Block device on which to create the journal
 *  @fs_dev: Device which hold journalled filesystem for this journal.
 *  @start: Block nr Start of journal.
 *  @len:  Length of the journal in blocks.
 *  @blocksize: blocksize of journalling device
 *  @returns: a newly created journal_t *
 *
703
 *  jbd2_journal_init_dev creates a journal which maps a fixed contiguous
704
705
706
 *  range of blocks on an arbitrary block device.
 *
 */
707
journal_t * jbd2_journal_init_dev(struct block_device *bdev,
708
			struct block_device *fs_dev,
709
			unsigned long long start, int len, int blocksize)
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
{
	journal_t *journal = journal_init_common();
	struct buffer_head *bh;
	int n;

	if (!journal)
		return NULL;

	/* journal descriptor can store up to n blocks -bzzz */
	journal->j_blocksize = blocksize;
	n = journal->j_blocksize / sizeof(journal_block_tag_t);
	journal->j_wbufsize = n;
	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
	if (!journal->j_wbuf) {
		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
			__FUNCTION__);
		kfree(journal);
		journal = NULL;
728
		goto out;
729
730
731
732
733
734
735
736
737
738
	}
	journal->j_dev = bdev;
	journal->j_fs_dev = fs_dev;
	journal->j_blk_offset = start;
	journal->j_maxlen = len;

	bh = __getblk(journal->j_dev, start, journal->j_blocksize);
	J_ASSERT(bh != NULL);
	journal->j_sb_buffer = bh;
	journal->j_superblock = (journal_superblock_t *)bh->b_data;
739
out:
740
741
742
743
	return journal;
}

/**
744
 *  journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode.
745
746
 *  @inode: An inode to create the journal in
 *
747
 * jbd2_journal_init_inode creates a journal which maps an on-disk inode as
748
749
750
 * the journal.  The inode must exist already, must support bmap() and
 * must have all data blocks preallocated.
 */
751
journal_t * jbd2_journal_init_inode (struct inode *inode)
752
753
754
755
756
{
	struct buffer_head *bh;
	journal_t *journal = journal_init_common();
	int err;
	int n;
757
	unsigned long long blocknr;
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

	if (!journal)
		return NULL;

	journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
	journal->j_inode = inode;
	jbd_debug(1,
		  "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
		  journal, inode->i_sb->s_id, inode->i_ino,
		  (long long) inode->i_size,
		  inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize);

	journal->j_maxlen = inode->i_size >> inode->i_sb->s_blocksize_bits;
	journal->j_blocksize = inode->i_sb->s_blocksize;

	/* journal descriptor can store up to n blocks -bzzz */
	n = journal->j_blocksize / sizeof(journal_block_tag_t);
	journal->j_wbufsize = n;
	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
	if (!journal->j_wbuf) {
		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
			__FUNCTION__);
		kfree(journal);
		return NULL;
	}

784
	err = jbd2_journal_bmap(journal, 0, &blocknr);
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
	/* If that failed, give up */
	if (err) {
		printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
		       __FUNCTION__);
		kfree(journal);
		return NULL;
	}

	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
	J_ASSERT(bh != NULL);
	journal->j_sb_buffer = bh;
	journal->j_superblock = (journal_superblock_t *)bh->b_data;

	return journal;
}

/*
 * If the journal init or create aborts, we need to mark the journal
 * superblock as being NULL to prevent the journal destroy from writing
 * back a bogus superblock.
 */
static void journal_fail_superblock (journal_t *journal)
{
	struct buffer_head *bh = journal->j_sb_buffer;
	brelse(bh);
	journal->j_sb_buffer = NULL;
}

/*
 * Given a journal_t structure, initialise the various fields for
 * startup of a new journaling session.  We use this both when creating
 * a journal, and after recovering an old journal to reset it for
 * subsequent use.
 */

static int journal_reset(journal_t *journal)
{
	journal_superblock_t *sb = journal->j_superblock;
823
	unsigned long long first, last;
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841

	first = be32_to_cpu(sb->s_first);
	last = be32_to_cpu(sb->s_maxlen);

	journal->j_first = first;
	journal->j_last = last;

	journal->j_head = first;
	journal->j_tail = first;
	journal->j_free = last - first;

	journal->j_tail_sequence = journal->j_transaction_sequence;
	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
	journal->j_commit_request = journal->j_commit_sequence;

	journal->j_max_transaction_buffers = journal->j_maxlen / 4;

	/* Add the dynamic fields and write it to disk. */
842
843
	jbd2_journal_update_superblock(journal, 1);
	jbd2_journal_start_thread(journal);
844
845
846
847
	return 0;
}

/**
848
 * int jbd2_journal_create() - Initialise the new journal file
849
850
851
852
853
854
 * @journal: Journal to create. This structure must have been initialised
 *
 * Given a journal_t structure which tells us which disk blocks we can
 * use, create a new journal superblock and initialise all of the
 * journal fields from scratch.
 **/
855
int jbd2_journal_create(journal_t *journal)
856
{
857
	unsigned long long blocknr;
858
859
860
861
	struct buffer_head *bh;
	journal_superblock_t *sb;
	int i, err;

862
	if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) {
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
		printk (KERN_ERR "Journal length (%d blocks) too short.\n",
			journal->j_maxlen);
		journal_fail_superblock(journal);
		return -EINVAL;
	}

	if (journal->j_inode == NULL) {
		/*
		 * We don't know what block to start at!
		 */
		printk(KERN_EMERG
		       "%s: creation of journal on external device!\n",
		       __FUNCTION__);
		BUG();
	}

	/* Zero out the entire journal on disk.  We cannot afford to
880
	   have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */
881
882
	jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
	for (i = 0; i < journal->j_maxlen; i++) {
883
		err = jbd2_journal_bmap(journal, i, &blocknr);
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
		if (err)
			return err;
		bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
		lock_buffer(bh);
		memset (bh->b_data, 0, journal->j_blocksize);
		BUFFER_TRACE(bh, "marking dirty");
		mark_buffer_dirty(bh);
		BUFFER_TRACE(bh, "marking uptodate");
		set_buffer_uptodate(bh);
		unlock_buffer(bh);
		__brelse(bh);
	}

	sync_blockdev(journal->j_dev);
	jbd_debug(1, "JBD: journal cleared.\n");

	/* OK, fill in the initial static fields in the new superblock */
	sb = journal->j_superblock;

903
904
	sb->s_header.h_magic	 = cpu_to_be32(JBD2_MAGIC_NUMBER);
	sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);
905
906
907
908
909
910
911

	sb->s_blocksize	= cpu_to_be32(journal->j_blocksize);
	sb->s_maxlen	= cpu_to_be32(journal->j_maxlen);
	sb->s_first	= cpu_to_be32(1);

	journal->j_transaction_sequence = 1;

912
	journal->j_flags &= ~JBD2_ABORT;
913
914
915
916
917
918
	journal->j_format_version = 2;

	return journal_reset(journal);
}

/**
919
 * void jbd2_journal_update_superblock() - Update journal sb on disk.
920
921
922
923
924
925
 * @journal: The journal to update.
 * @wait: Set to '0' if you don't want to wait for IO completion.
 *
 * Update a journal's dynamic superblock fields and write it to disk,
 * optionally waiting for the IO to complete.
 */
926
void jbd2_journal_update_superblock(journal_t *journal, int wait)
927
928
929
930
931
932
933
934
{
	journal_superblock_t *sb = journal->j_superblock;
	struct buffer_head *bh = journal->j_sb_buffer;

	/*
	 * As a special case, if the on-disk copy is already marked as needing
	 * no recovery (s_start == 0) and there are no outstanding transactions
	 * in the filesystem, then we can safely defer the superblock update
935
	 * until the next commit by setting JBD2_FLUSHED.  This avoids
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
	 * attempting a write to a potential-readonly device.
	 */
	if (sb->s_start == 0 && journal->j_tail_sequence ==
				journal->j_transaction_sequence) {
		jbd_debug(1,"JBD: Skipping superblock update on recovered sb "
			"(start %ld, seq %d, errno %d)\n",
			journal->j_tail, journal->j_tail_sequence,
			journal->j_errno);
		goto out;
	}

	spin_lock(&journal->j_state_lock);
	jbd_debug(1,"JBD: updating superblock (start %ld, seq %d, errno %d)\n",
		  journal->j_tail, journal->j_tail_sequence, journal->j_errno);

	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
	sb->s_start    = cpu_to_be32(journal->j_tail);
	sb->s_errno    = cpu_to_be32(journal->j_errno);
	spin_unlock(&journal->j_state_lock);

	BUFFER_TRACE(bh, "marking dirty");
	mark_buffer_dirty(bh);
	if (wait)
		sync_dirty_buffer(bh);
	else
		ll_rw_block(SWRITE, 1, &bh);

out:
	/* If we have just flushed the log (by marking s_start==0), then
	 * any future commit will have to be careful to update the
	 * superblock again to re-record the true start of the log. */

	spin_lock(&journal->j_state_lock);
	if (sb->s_start)
970
		journal->j_flags &= ~JBD2_FLUSHED;
971
	else
972
		journal->j_flags |= JBD2_FLUSHED;
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
	spin_unlock(&journal->j_state_lock);
}

/*
 * Read the superblock for a given journal, performing initial
 * validation of the format.
 */

static int journal_get_superblock(journal_t *journal)
{
	struct buffer_head *bh;
	journal_superblock_t *sb;
	int err = -EIO;

	bh = journal->j_sb_buffer;

	J_ASSERT(bh != NULL);
	if (!buffer_uptodate(bh)) {
		ll_rw_block(READ, 1, &bh);
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh)) {
			printk (KERN_ERR
				"JBD: IO error reading journal superblock\n");
			goto out;
		}
	}

	sb = journal->j_superblock;
For faster browsing, not all history is shown. View entire blame