jbd2: fix sending of data flush on journal commit

In data=ordered mode, it's theoretically possible (however rare) that
an inode is filed to transaction's t_inode_list and a flusher thread
writes all the data and inode is reclaimed before the transaction
starts to commit.  In such a case, we could erroneously omit sending a
flush to file system device when it is different from the journal
device (because data can still be in disk cache only).

Fix the problem by setting a flag in a transaction when some inode is added
to it and then send disk flush in the commit code when the flag is set.

Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 78c299218681ad03ec3dd246800694bd773f98c5..2d5095ecc25fa9922d6225800f13dbbabb7ccf26 100644 (file)
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -219,7 +219,6 @@ static int journal_submit_data_buffers(journal_t *journal,
                        ret = err;
                spin_lock(&journal->j_list_lock);
                J_ASSERT(jinode->i_transaction == commit_transaction);
-               commit_transaction->t_flushed_data_blocks = 1;
                clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
                smp_mb__after_clear_bit();
                wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
@@ -683,7 +682,7 @@ start_journal_io:
         * then we must flush the file system device before we issue
         * the commit record
         */
-       if (commit_transaction->t_flushed_data_blocks &&
+       if (commit_transaction->t_need_data_flush &&
            (journal->j_fs_dev != journal->j_dev) &&
            (journal->j_flags & JBD2_BARRIER))
                blkdev_issue_flush(journal->j_fs_dev, GFP_KERNEL, NULL);

diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 85a055ef93fedb138e44918227426abd3f34eb46..20065c9f2479253a23a865ed9dd80569c8236535 100644 (file)
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2147,6 +2147,13 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
            jinode->i_next_transaction == transaction)
                goto done;
 
+       /*
+        * We only ever set this variable to 1 so the test is safe. Since
+        * t_need_data_flush is likely to be set, we do the test to save some
+        * cacheline bouncing
+        */
+       if (!transaction->t_need_data_flush)
+               transaction->t_need_data_flush = 1;
        /* On some different transaction's list - should be
         * the committing one */
        if (jinode->i_transaction) {

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index a32dcaec04e147917a3e085a5e83146189782336..4d57955061f48b12412a55991e005a265d204b3c 100644 (file)
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -658,7 +658,9 @@ struct transaction_s
         * waiting for it to finish.
         */
        unsigned int t_synchronous_commit:1;
-       unsigned int t_flushed_data_blocks:1;
+
+       /* Disk flush needs to be sent to fs partition [no locking] */
+       int                     t_need_data_flush;
 
        /*
         * For use by the filesystem to store fs-specific data