summaryrefslogtreecommitdiff
path: root/fs/ext4/inode.c
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2009-12-08 23:51:10 -0500
committerTheodore Ts'o <tytso@mit.edu>2009-12-08 23:51:10 -0500
commitb436b9bef84de6893e86346d8fbf7104bc520645 (patch)
tree50fb9ae167bcd622e9adf47646bcf3b4c7dd111d /fs/ext4/inode.c
parent194074acacebc169ded90a4657193f5180015051 (diff)
ext4: Wait for proper transaction commit on fsync
We cannot rely on buffer dirty bits during fsync because pdflush can come before fsync is called and clear dirty bits without forcing a transaction commit. What we do is that we track which transaction has last changed the inode and which transaction last changed allocation and force it to disk on fsync. Signed-off-by: Jan Kara <jack@suse.cz> Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Diffstat (limited to 'fs/ext4/inode.c')
-rw-r--r--fs/ext4/inode.c29
1 files changed, 29 insertions, 0 deletions
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 958c3ff800e9..f1bc1e338828 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -983,6 +983,8 @@ static int ext4_ind_get_blocks(handle_t *handle, struct inode *inode,
goto cleanup;
set_buffer_new(bh_result);
+
+ ext4_update_inode_fsync_trans(handle, inode, 1);
got_it:
map_bh(bh_result, inode->i_sb, le32_to_cpu(chain[depth-1].key));
if (count > blocks_to_boundary)
@@ -4738,6 +4740,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
struct ext4_inode *raw_inode;
struct ext4_inode_info *ei;
struct inode *inode;
+ journal_t *journal = EXT4_SB(sb)->s_journal;
long ret;
int block;
@@ -4802,6 +4805,31 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
ei->i_data[block] = raw_inode->i_block[block];
INIT_LIST_HEAD(&ei->i_orphan);
+ /*
+ * Set transaction id's of transactions that have to be committed
+ * to finish f[data]sync. We set them to currently running transaction
+ * as we cannot be sure that the inode or some of its metadata isn't
+ * part of the transaction - the inode could have been reclaimed and
+ * now it is reread from disk.
+ */
+ if (journal) {
+ transaction_t *transaction;
+ tid_t tid;
+
+ spin_lock(&journal->j_state_lock);
+ if (journal->j_running_transaction)
+ transaction = journal->j_running_transaction;
+ else
+ transaction = journal->j_committing_transaction;
+ if (transaction)
+ tid = transaction->t_tid;
+ else
+ tid = journal->j_commit_sequence;
+ spin_unlock(&journal->j_state_lock);
+ ei->i_sync_tid = tid;
+ ei->i_datasync_tid = tid;
+ }
+
if (EXT4_INODE_SIZE(inode->i_sb) > EXT4_GOOD_OLD_INODE_SIZE) {
ei->i_extra_isize = le16_to_cpu(raw_inode->i_extra_isize);
if (EXT4_GOOD_OLD_INODE_SIZE + ei->i_extra_isize >
@@ -5056,6 +5084,7 @@ static int ext4_do_update_inode(handle_t *handle,
err = rc;
ei->i_state &= ~EXT4_STATE_NEW;
+ ext4_update_inode_fsync_trans(handle, inode, 0);
out_brelse:
brelse(bh);
ext4_std_error(inode->i_sb, err);