journal.c

《嵌入式系统设计与实例开发实验教材二源码》Linux内核移植与编译实验

	new_bh->b_state = 0;
	init_buffer(new_bh, NULL, NULL);
	atomic_set(&new_bh->b_count, 1);
	new_jh = journal_add_journal_head(new_bh);

	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_dev = transaction->t_journal->j_dev;
	new_bh->b_blocknr = blocknr;
	new_bh->b_state |= (1 << BH_Mapped) | (1 << BH_Dirty);

	*jh_out = new_jh;

	/*
	 * Did we need to do an escaping?  Now we've done all the
	 * copying, we can finally do so.
	 */

	if (do_escape)
		* ((unsigned int *) mapped_data) = 0;
	kunmap(new_page);
	
	/*
	 * 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");
	journal_file_buffer(jh_in, transaction, BJ_Shadow);
	JBUFFER_TRACE(new_jh, "file as BJ_IO");
	journal_file_buffer(new_jh, transaction, BJ_IO);

	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.
 */

/*
 * log_space_left: Return the number of free blocks left in the journal.
 *
 * Called with the journal already locked.
 */

int log_space_left (journal_t *journal)
{
	int left = journal->j_free;

	/* 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;
}

/*
 * This function must be non-allocating for PF_MEMALLOC tasks
 */
tid_t log_start_commit (journal_t *journal, transaction_t *transaction)
{
	tid_t target = journal->j_commit_request;

	lock_kernel(); /* Protect journal->j_running_transaction */
	
	/*
	 * A NULL transaction asks us to commit the currently running
	 * transaction, if there is one.  
	 */
	if (transaction)
		target = transaction->t_tid;
	else {
		transaction = journal->j_running_transaction;
		if (!transaction)
			goto out;
		target = transaction->t_tid;
	}
		
	/*
	 * Are we already doing a recent enough commit?
	 */
	if (tid_geq(journal->j_commit_request, target))
		goto out;

	/*
	 * 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);

out:
	unlock_kernel();
	return target;
}

/*
 * Wait for a specified commit to complete.
 * The caller may not hold the journal lock.
 */
void log_wait_commit (journal_t *journal, tid_t tid)
{
	lock_kernel();
#ifdef CONFIG_JBD_DEBUG
	lock_journal(journal);
	if (!tid_geq(journal->j_commit_request, tid)) {
		printk(KERN_EMERG __FUNCTION__
			": error: j_commit_request=%d, tid=%d\n",
			journal->j_commit_request, tid);
	}
	unlock_journal(journal);
#endif
	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);
		sleep_on(&journal->j_wait_done_commit);
	}
	unlock_kernel();
}

/*
 * Log buffer allocation routines:
 */

int journal_next_log_block(journal_t *journal, unsigned long *retp)
{
	unsigned long blocknr;

	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;
	return 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 journal_bmap(journal_t *journal, unsigned long blocknr, 
		 unsigned long *retp)
{
	int err = 0;
	unsigned long ret;

	if (journal->j_inode) {
		ret = bmap(journal->j_inode, blocknr);
		if (ret)
			*retp = ret;
		else {
			printk (KERN_ALERT __FUNCTION__ 
				": journal block not found "
				"at offset %lu on %s\n",
				blocknr, bdevname(journal->j_dev));
			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.
 *
 * We return a jh whose bh is locked and ready to be populated.
 */

struct journal_head * journal_get_descriptor_buffer(journal_t *journal)
{
	struct buffer_head *bh;
	unsigned long blocknr;
	int err;

	err = journal_next_log_block(journal, &blocknr);

	if (err)
		return NULL;

	bh = getblk(journal->j_dev, blocknr, journal->j_blocksize);
	lock_buffer(bh);
	BUFFER_TRACE(bh, "return this buffer");
	return 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;

	MOD_INC_USE_COUNT;

	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);
	init_MUTEX(&journal->j_barrier);
	init_MUTEX(&journal->j_checkpoint_sem);
	init_MUTEX(&journal->j_sem);

	journal->j_commit_interval = (HZ * 5);

	/* 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:
	MOD_DEC_USE_COUNT;
	return NULL;
}

/* journal_init_dev and 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_init_dev creates a journal which maps a fixed contiguous
 * range of blocks on an arbitrary block device.
 *
 * 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_dev(kdev_t dev, kdev_t fs_dev,
			int start, int len, int blocksize)
{
	journal_t *journal = journal_init_common();
	struct buffer_head *bh;

	if (!journal)
		return NULL;

	journal->j_dev = dev;
	journal->j_fs_dev = fs_dev;
	journal->j_blk_offset = start;
	journal->j_maxlen = len;
	journal->j_blocksize = blocksize;

	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;

	return journal;
}

journal_t * journal_init_inode (struct inode *inode)
{
	struct buffer_head *bh;
	journal_t *journal = journal_init_common();
	int err;
	unsigned long blocknr;

	if (!journal)
		return NULL;

	journal->j_dev = inode->i_dev;
	journal->j_fs_dev = inode->i_dev;
	journal->j_inode = inode;
	jbd_debug(1,
		  "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
		  journal, bdevname(inode->i_dev), 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;

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

	first = ntohl(sb->s_first);
	last = ntohl(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. */
	journal_update_superblock(journal, 1);

	lock_journal(journal);
	journal_start_thread(journal);
	unlock_journal(journal);

	return 0;
}

/*
 * 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 journal_create (journal_t *journal)
{
	unsigned long blocknr;
	struct buffer_head *bh;
	journal_superblock_t *sb;
	int i, err;

	if (journal->j_maxlen < JFS_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 __FUNCTION__
			": creation of journal on external device!\n");
		BUG();
	}

	/* Zero out the entire journal on disk.  We cannot afford to
	   have any blocks on disk beginning with JFS_MAGIC_NUMBER. */
	jbd_debug(1, "JBD: Zeroing out journal blocks...\n");
	for (i = 0; i < journal->j_maxlen; i++) {
		err = journal_bmap(journal, i, &blocknr);
		if (err)
			return err;
		bh = getblk(journal->j_dev, blocknr, journal->j_blocksize);
		wait_on_buffer(bh);
		memset (bh->b_data, 0, journal->j_blocksize);
		BUFFER_TRACE(bh, "marking dirty");
		mark_buffer_dirty(bh);
		BUFFER_TRACE(bh, "marking uptodate");
		mark_buffer_uptodate(bh, 1);
		__brelse(bh);
	}

	sync_dev(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	 = htonl(JFS_MAGIC_NUMBER);
	sb->s_header.h_blocktype = htonl(JFS_SUPERBLOCK_V2);

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

	journal->j_transaction_sequence = 1;

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

	return journal_reset(journal);
}

/*
 * 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;

	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 = htonl(journal->j_tail_sequence);
	sb->s_start    = htonl(journal->j_tail);
	sb->s_errno    = htonl(journal->j_errno);

	BUFFER_TRACE(bh, "marking dirty");
	mark_buffer_dirty(bh);
	ll_rw_block(WRITE, 1, &bh);