Patchwork [1/4] ext4: Fix fsync error handling after filesysteb abort.

login
register
mail settings
Submitter Dmitri Monakho
Date May 16, 2013, 12:28 p.m.
Message ID <1368707290-26185-1-git-send-email-dmonakhov@openvz.org>
Download mbox | patch
Permalink /patch/244298/
State Superseded
Headers show

Comments

Dmitri Monakho - May 16, 2013, 12:28 p.m.
If filesystem was aborted after inode's write back complete
but before it's metadata was updated we may return success
due to (sb->s_flags & MS_RDONLY) which is incorrect and
result in data loss.
In order to handle fs abort correctly we have to check
fs state once we discover that it is in MS_RDONLY state

Test case: http://patchwork.ozlabs.org/patch/244297/

Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
---
 fs/ext4/fsync.c |    8 ++++++--
 fs/ext4/super.c |   13 ++++++++++++-
 2 files changed, 18 insertions(+), 3 deletions(-)
Jan Kara - May 21, 2013, 4:18 p.m.
On Thu 16-05-13 16:28:07, Dmitry Monakhov wrote:
  The patch looks OK but I have some typo fixes below. But you can add
Reviewed-by: Jan Kara <jack@suse.cz>

> If filesystem was aborted after inode's write back complete
						    ^^ is
> but before it's metadata was updated we may return success
             ^^^ its

> due to (sb->s_flags & MS_RDONLY) which is incorrect and
> result in data loss.
   ^^^ results

> In order to handle fs abort correctly we have to check
> fs state once we discover that it is in MS_RDONLY state
> 
> Test case: http://patchwork.ozlabs.org/patch/244297/
> 
> Signed-off-by: Dmitry Monakhov <dmonakhov@openvz.org>
> ---
>  fs/ext4/fsync.c |    8 ++++++--
>  fs/ext4/super.c |   13 ++++++++++++-
>  2 files changed, 18 insertions(+), 3 deletions(-)
> 
> diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
> index e0ba8a4..d7df2f1 100644
> --- a/fs/ext4/fsync.c
> +++ b/fs/ext4/fsync.c
> @@ -129,9 +129,13 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
>  		return ret;
>  	mutex_lock(&inode->i_mutex);
>  
> -	if (inode->i_sb->s_flags & MS_RDONLY)
> +	if (inode->i_sb->s_flags & MS_RDONLY) {
> +		/* Make shure that we read updated s_mount_flags value */
                        ^^^ sure
> +		smp_rmb();
> +		if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
> +			ret = -EROFS;
>  		goto out;
> -
> +	}
>  	ret = ext4_flush_unwritten_io(inode);
>  	if (ret < 0)
>  		goto out;
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index dbc7c09..6c91c8e 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -398,6 +398,11 @@ static void ext4_handle_error(struct super_block *sb)
>  	}
>  	if (test_opt(sb, ERRORS_RO)) {
>  		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
> +		/*
> +		 * Make shure updated value of ->s_mount_flags will be visiable
                        ^^^ sure                                  visible ^^
> +		 * before ->s_flags update
> +		 */
> +		smp_wmb();
>  		sb->s_flags |= MS_RDONLY;
>  	}
>  	if (test_opt(sb, ERRORS_PANIC))
> @@ -552,6 +557,7 @@ void __ext4_std_error(struct super_block *sb, const char *function,
>   *
>   * We unconditionally force the filesystem into an ABORT|READONLY state,
>   * unless the error response on the fs has been set to panic in which
> +
  ^^ Stray empty line.

>   * case we take the easy way out and panic immediately.
>   */
>  
> @@ -570,8 +576,13 @@ void __ext4_abort(struct super_block *sb, const char *function,
>  
>  	if ((sb->s_flags & MS_RDONLY) == 0) {
>  		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
> -		sb->s_flags |= MS_RDONLY;
>  		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
> +		/*
> +		 * Make shure updated value of ->s_mount_flags will be visiable
                         ^^ sure                                 visible ^^
> +		 * before ->s_flags update
> +		 */
> +		smp_wmb();
> +		sb->s_flags |= MS_RDONLY;
>  		if (EXT4_SB(sb)->s_journal)
>  			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
>  		save_error_info(sb, function, line);

Patch

diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index e0ba8a4..d7df2f1 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -129,9 +129,13 @@  int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		return ret;
 	mutex_lock(&inode->i_mutex);
 
-	if (inode->i_sb->s_flags & MS_RDONLY)
+	if (inode->i_sb->s_flags & MS_RDONLY) {
+		/* Make shure that we read updated s_mount_flags value */
+		smp_rmb();
+		if (EXT4_SB(inode->i_sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			ret = -EROFS;
 		goto out;
-
+	}
 	ret = ext4_flush_unwritten_io(inode);
 	if (ret < 0)
 		goto out;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dbc7c09..6c91c8e 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -398,6 +398,11 @@  static void ext4_handle_error(struct super_block *sb)
 	}
 	if (test_opt(sb, ERRORS_RO)) {
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
+		/*
+		 * Make shure updated value of ->s_mount_flags will be visiable
+		 * before ->s_flags update
+		 */
+		smp_wmb();
 		sb->s_flags |= MS_RDONLY;
 	}
 	if (test_opt(sb, ERRORS_PANIC))
@@ -552,6 +557,7 @@  void __ext4_std_error(struct super_block *sb, const char *function,
  *
  * We unconditionally force the filesystem into an ABORT|READONLY state,
  * unless the error response on the fs has been set to panic in which
+
  * case we take the easy way out and panic immediately.
  */
 
@@ -570,8 +576,13 @@  void __ext4_abort(struct super_block *sb, const char *function,
 
 	if ((sb->s_flags & MS_RDONLY) == 0) {
 		ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
-		sb->s_flags |= MS_RDONLY;
 		EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+		/*
+		 * Make shure updated value of ->s_mount_flags will be visiable
+		 * before ->s_flags update
+		 */
+		smp_wmb();
+		sb->s_flags |= MS_RDONLY;
 		if (EXT4_SB(sb)->s_journal)
 			jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
 		save_error_info(sb, function, line);