replay.c

可以在不启动LINUX的情况下直接访问EXT2和EXT3格式的磁盘

	if (!journal)
		goto fail;

	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! */
	journal->j_flags = JFS_ABORT;

	/* Set up a default-sized revoke table for the new mount. */
	err = journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
	if (err) {
		kfree(journal);
		goto fail;
	}
	return journal;
fail:
	return NULL;
}

/**
 *  journal_t * journal_init_inode () - creates a journal which maps to a inode.
 *  @inode: An inode to create the journal in
 *
 * journal_init_inode creates a journal which maps an on-disk inode as
 * the journal.  The inode must exist already, must support bmap() and
 * must have all data blocks preallocated.
 */
journal_t * journal_init_inode (struct inode *inode)
{
	struct buffer_head *bh;
	journal_t *journal = journal_init_common();
	int err;
	int n;
	unsigned long blocknr;

	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,
		  (s64) inode->i_size,
		  inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize);

	journal->j_maxlen = (unsigned int)(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__);

        J_ASSERT(journal->j_revoke != NULL);
	    if (journal->j_revoke)
		    journal_destroy_revoke(journal);

		kfree(journal);
		return NULL;
	}

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

        J_ASSERT(journal->j_revoke != NULL);
	    if (journal->j_revoke)
		    journal_destroy_revoke(journal);
        J_ASSERT(journal->j_wbuf != NULL);
        kfree(journal->j_wbuf);
		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;
}

/**
 *
 *   wipe all journal data ...
 *
 */

void journal_wipe_recovery(journal_t *journal)
{
	/* We can now mark the journal as empty. */

	journal->j_tail = 0;
	if (journal->j_sb_buffer) {
		journal_update_superblock(journal, 0);
		brelse(journal->j_sb_buffer);
        journal->j_sb_buffer = NULL;
	}
}

/**
 * void journal_destroy() - Release a journal_t structure.
 * @journal: Journal to act on.
 *
 * Release a journal_t structure once it is no longer in use by the
 * journaled object.
 */
void journal_destroy(journal_t *journal)
{
#if 0
	/* Wait for the commit thread to wake up and die. */
	journal_kill_thread(journal);

	/* Force a final log commit */
	if (journal->j_running_transaction)
		journal_commit_transaction(journal);

	/* Force any old transactions to disk */

	/* Totally anal locking here... */
	spin_lock(&journal->j_list_lock);
	while (journal->j_checkpoint_transactions != NULL) {
		spin_unlock(&journal->j_list_lock);
		log_do_checkpoint(journal);
		spin_lock(&journal->j_list_lock);
	}

	J_ASSERT(journal->j_running_transaction == NULL);
	J_ASSERT(journal->j_committing_transaction == NULL);
	J_ASSERT(journal->j_checkpoint_transactions == NULL);
	spin_unlock(&journal->j_list_lock);

	/* We can now mark the journal as empty. */
	journal->j_tail = 0;
	journal->j_tail_sequence = ++journal->j_transaction_sequence;
	if (journal->j_sb_buffer) {
		journal_update_superblock(journal, 1);
		brelse(journal->j_sb_buffer);
	}
#endif

	if (journal->j_sb_buffer) {
		brelse(journal->j_sb_buffer);
	}
	if (journal->j_inode)
		iput(journal->j_inode);
	if (journal->j_revoke)
		journal_destroy_revoke(journal);
	kfree(journal->j_wbuf);
	kfree(journal);
}



/**
 *int journal_check_used_features () - Check if features specified are used.
 * @journal: Journal to check.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Check whether the journal uses all of a given set of
 * features.  Return true (non-zero) if it does.
 **/

int journal_check_used_features (journal_t *journal, unsigned long compat,
				 unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (!compat && !ro && !incompat)
		return 1;
	if (journal->j_format_version == 1)
		return 0;

	sb = journal->j_superblock;

	if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) &&
	    ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) &&
	    ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat))
		return 1;

	return 0;
}

/**
 * int journal_check_available_features() - Check feature set in journalling layer
 * @journal: Journal to check.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Check whether the journaling code supports the use of
 * all of a given set of features on this journal.  Return true
 * (non-zero) if it can. */

int journal_check_available_features (journal_t *journal, unsigned long compat,
				      unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (!compat && !ro && !incompat)
		return 1;

	sb = journal->j_superblock;

	/* We can support any known requested features iff the
	 * superblock is in version 2.  Otherwise we fail to support any
	 * extended sb features. */

	if (journal->j_format_version != 2)
		return 0;

	if ((compat   & JFS_KNOWN_COMPAT_FEATURES) == compat &&
	    (ro       & JFS_KNOWN_ROCOMPAT_FEATURES) == ro &&
	    (incompat & JFS_KNOWN_INCOMPAT_FEATURES) == incompat)
		return 1;

	return 0;
}

/**
 * int journal_set_features () - Mark a given journal feature in the superblock
 * @journal: Journal to act on.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Mark a given journal feature as present on the
 * superblock.  Returns true if the requested features could be set.
 *
 */

int journal_set_features (journal_t *journal, unsigned long compat,
			  unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (journal_check_used_features(journal, compat, ro, incompat))
		return 1;

	if (!journal_check_available_features(journal, compat, ro, incompat))
		return 0;

	jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n",
		  compat, ro, incompat);

	sb = journal->j_superblock;

	sb->s_feature_compat    |= cpu_to_be32(compat);
	sb->s_feature_ro_compat |= cpu_to_be32(ro);
	sb->s_feature_incompat  |= cpu_to_be32(incompat);

	return 1;
}

static int journal_convert_superblock_v1(journal_t *journal,
					 journal_superblock_t *sb)
{
	int offset, blocksize;
	struct buffer_head *bh;

	printk(KERN_WARNING
		"JBD: Converting superblock from version 1 to 2.\n");

	/* Pre-initialise new fields to zero */
	offset = (INT)(((INT_PTR) &(sb->s_feature_compat)) - ((INT_PTR) sb));
	blocksize = be32_to_cpu(sb->s_blocksize);
	memset(&sb->s_feature_compat, 0, blocksize-offset);

	sb->s_nr_users = cpu_to_be32(1);
	sb->s_header.h_blocktype = cpu_to_be32(JFS_SUPERBLOCK_V2);
	journal->j_format_version = 2;

	bh = journal->j_sb_buffer;
	BUFFER_TRACE(bh, "marking dirty");
	mark_buffer_dirty(bh);
	sync_dirty_buffer(bh);
	return 0;
}


/*
 * 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;
}


/*
 * 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;

	err = -EINVAL;

	if (sb->s_header.h_magic != cpu_to_be32(JFS_MAGIC_NUMBER) ||
	    sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
		printk(KERN_WARNING "JBD: no valid journal superblock found\n");
		goto out;
	}

	switch(be32_to_cpu(sb->s_header.h_blocktype)) {
	case JFS_SUPERBLOCK_V1:
		journal->j_format_version = 1;
		break;
	case JFS_SUPERBLOCK_V2:
		journal->j_format_version = 2;
		break;
	default:
		printk(KERN_WARNING "JBD: unrecognised superblock format ID\n");
		goto out;
	}

	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
		printk (KERN_WARNING "JBD: journal file too short\n");
		goto out;
	}

	return 0;

out:
	journal_fail_superblock(journal);
	return err;
}

/*
 * Load the on-disk journal superblock and read the key fields into the
 * journal_t.
 */

static int load_superblock(journal_t *journal)
{
	int err;
	journal_superblock_t *sb;

	err = journal_get_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;

	journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
	journal->j_tail = be32_to_cpu(sb->s_start);
	journal->j_first = be32_to_cpu(sb->s_first);
	journal->j_last = be32_to_cpu(sb->s_maxlen);
	journal->j_errno = be32_to_cpu(sb->s_errno);

	return 0;
}

/**
 * int journal_wipe() - Wipe journal contents
 * @journal: Journal to act on.
 * @write: flag (see below)
 *
 * Wipe out all of the contents of a journal, safely.  This will produce
 * a warning if the journal contains any valid recovery information.
 * Must be called between journal_init_*() and journal_load().
 *
 * If 'write' is non-zero, then we wipe out the journal on disk; otherwise
 * we merely suppress recovery.
 */

int journal_wipe(journal_t *journal, int write)
{
	journal_superblock_t *sb;
	int err = 0;

	J_ASSERT (!(journal->j_flags & JFS_LOADED));

	err = load_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;

	if (!journal->j_tail)
		goto no_recovery;

	printk (KERN_WARNING "JBD: %s recovery information on journal\n",
		write ? "Clearing" : "Ignoring");

	err = journal_skip_recovery(journal);
	if (write)
		journal_update_superblock(journal, 1);

 no_recovery:
	return err;
}


/**
 * int journal_update_format () - Update on-disk journal structure.
 * @journal: Journal to act on.
 *
 * Given an initialised but unloaded journal struct, poke about in the
 * on-disk structure to update it to the most recent supported version.
 */
int journal_update_format (journal_t *journal)
{
	journal_superblock_t *sb;
	int err;

	err = journal_get_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;

	switch (be32_to_cpu(sb->s_header.h_blocktype)) {
	case JFS_SUPERBLOCK_V2:
		return 0;
	case JFS_SUPERBLOCK_V1:
		return journal_convert_superblock_v1(journal, sb);
	default:
		break;
	}
	return -EINVAL;
}


/**
 * void journal_update_superblock() - Update journal sb on disk.
 * @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.
 */
void journal_update_superblock(journal_t *journal, int wait)
{
	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
	 * until the next commit by setting JFS_FLUSHED.  This avoids
	 * 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)
		journal->j_flags &= ~JFS_FLUSHED;
	else
		journal->j_flags |= JFS_FLUSHED;
	spin_unlock(&journal->j_state_lock);
}

/*
 * 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;
	unsigned long first, last;

	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;