ext4: fix races in ext4_sync_parent()

[pandora-kernel.git] / fs / ext4 / fsync.c

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index e9473cb..f9dbe33 100644 (file)
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -36,7 +36,7 @@
 
 static void dump_completed_IO(struct inode * inode)
 {
-#ifdef EXT4_DEBUG
+#ifdef EXT4FS_DEBUG
        struct list_head *cur, *before, *after;
        ext4_io_end_t *io, *io0, *io1;
        unsigned long flags;
@@ -129,15 +129,30 @@ static int ext4_sync_parent(struct inode *inode)
 {
        struct writeback_control wbc;
        struct dentry *dentry = NULL;
+       struct inode *next;
        int ret = 0;
 
-       while (inode && ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
+       if (!ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY))
+               return 0;
+       inode = igrab(inode);
+       while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
                ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
-               dentry = list_entry(inode->i_dentry.next,
-                                   struct dentry, d_alias);
-               if (!dentry || !dentry->d_parent || !dentry->d_parent->d_inode)
+               dentry = NULL;
+               spin_lock(&inode->i_lock);
+               if (!list_empty(&inode->i_dentry)) {
+                       dentry = list_first_entry(&inode->i_dentry,
+                                                 struct dentry, d_alias);
+                       dget(dentry);
+               }
+               spin_unlock(&inode->i_lock);
+               if (!dentry)
+                       break;
+               next = igrab(dentry->d_parent->d_inode);
+               dput(dentry);
+               if (!next)
                        break;
-               inode = dentry->d_parent->d_inode;
+               iput(inode);
+               inode = next;
                ret = sync_mapping_buffers(inode->i_mapping);
                if (ret)
                        break;
@@ -148,6 +163,7 @@ static int ext4_sync_parent(struct inode *inode)
                if (ret)
                        break;
        }
+       iput(inode);
        return ret;
 }
 
@@ -172,6 +188,7 @@ int ext4_sync_file(struct file *file, int datasync)
        journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
        int ret;
        tid_t commit_tid;
+       bool needs_barrier = false;
 
        J_ASSERT(ext4_journal_current_handle() == NULL);
 
@@ -211,22 +228,12 @@ int ext4_sync_file(struct file *file, int datasync)
        }
 
        commit_tid = datasync ? ei->i_datasync_tid : ei->i_sync_tid;
-       if (jbd2_log_start_commit(journal, commit_tid)) {
-               /*
-                * When the journal is on a different device than the
-                * fs data disk, we need to issue the barrier in
-                * writeback mode.  (In ordered mode, the jbd2 layer
-                * will take care of issuing the barrier.  In
-                * data=journal, all of the data blocks are written to
-                * the journal device.)
-                */
-               if (ext4_should_writeback_data(inode) &&
-                   (journal->j_fs_dev != journal->j_dev) &&
-                   (journal->j_flags & JBD2_BARRIER))
-                       blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL,
-                                       NULL);
-               ret = jbd2_log_wait_commit(journal, commit_tid);
-       } else if (journal->j_flags & JBD2_BARRIER)
+       if (journal->j_flags & JBD2_BARRIER &&
+           !jbd2_trans_will_send_data_barrier(journal, commit_tid))
+               needs_barrier = true;
+       jbd2_log_start_commit(journal, commit_tid);
+       ret = jbd2_log_wait_commit(journal, commit_tid);
+       if (needs_barrier)
                blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
  out:
        trace_ext4_sync_file_exit(inode, ret);