journal.c

linux 内核源代码

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

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

		ret = __jbd2_log_start_commit(journal, tid);
		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.
 */
int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
{
	int err = 0;

#ifdef CONFIG_JBD2_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:
 */

int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
{
	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);
	return jbd2_journal_bmap(journal, blocknr, retp);
}

/*
 * 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.
 */
int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
		 unsigned long long *retp)
{
	int err = 0;
	unsigned long long ret;

	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.
 *
 * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying
 * 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.
 */
struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
{
	struct buffer_head *bh;
	unsigned long long blocknr;
	int err;

	err = jbd2_journal_next_log_block(journal, &blocknr);

	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");
	return jbd2_journal_add_journal_head(bh);
}

/*
 * 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 = kzalloc(sizeof(*journal), GFP_KERNEL|__GFP_NOFAIL);
	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 * JBD2_DEFAULT_MAX_COMMIT_AGE);

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

	/* Set up a default-sized revoke table for the new mount. */
	err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
	if (err) {
		kfree(journal);
		goto fail;
	}
	return journal;
fail:
	return NULL;
}

/* jbd2_journal_init_dev and jbd2_journal_init_inode:
 *
 * 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.
 *
 */

/**
 *  journal_t * jbd2_journal_init_dev() - creates an initialises a journal structure
 *  @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 *
 *
 *  jbd2_journal_init_dev creates a journal which maps a fixed contiguous
 *  range of blocks on an arbitrary block device.
 *
 */
journal_t * jbd2_journal_init_dev(struct block_device *bdev,
			struct block_device *fs_dev,
			unsigned long long start, int len, int blocksize)
{
	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;
		goto out;
	}
	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;
out:
	return journal;
}

/**
 *  journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode.
 *  @inode: An inode to create the journal in
 *
 * jbd2_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 * jbd2_journal_init_inode (struct inode *inode)
{
	struct buffer_head *bh;
	journal_t *journal = journal_init_common();
	int err;
	int n;
	unsigned long 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,
		  (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;
	}

	err = jbd2_journal_bmap(journal, 0, &blocknr);
	/* 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;
	unsigned long 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;

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

	/* Add the dynamic fields and write it to disk. */
	jbd2_journal_update_superblock(journal, 1);
	return jbd2_journal_start_thread(journal);
}

/**
 * int jbd2_journal_create() - Initialise the new journal file
 * @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.
 **/
int jbd2_journal_create(journal_t *journal)
{
	unsigned long long blocknr;
	struct buffer_head *bh;
	journal_superblock_t *sb;
	int i, err;

	if (journal->j_maxlen < JBD2_MIN_JOURNAL_BLOCKS) {
		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
	   have any blocks on disk beginning with JBD2_MAGIC_NUMBER. */
	jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
	for (i = 0; i < journal->j_maxlen; i++) {
		err = jbd2_journal_bmap(journal, i, &blocknr);
		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;

	sb->s_header.h_magic	 = cpu_to_be32(JBD2_MAGIC_NUMBER);
	sb->s_header.h_blocktype = cpu_to_be32(JBD2_SUPERBLOCK_V2);

	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;

	journal->j_flags &= ~JBD2_ABORT;
	journal->j_format_version = 2;

	return journal_reset(journal);
}

/**
 * void jbd2_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 jbd2_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 JBD2_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 &= ~JBD2_FLUSHED;
	else
		journal->j_flags |= JBD2_FLUSHED;
	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;