ext3: add an option to control error handling on file data

If the journal doesn't abort when it gets an IO error in file data blocks,
the file data corruption will spread silently.  Because most of
applications and commands do buffered writes without fsync(), they don't
notice the IO error.  It's scary for mission critical systems.  On the
other hand, if the journal aborts whenever it gets an IO error in file
data blocks, the system will easily become inoperable.  So this patch
introduces a filesystem option to determine whether it aborts the journal
or just call printk() when it gets an IO error in file data.

If you mount a ext3 fs with data_err=abort option, it aborts on file data
write error.  If you mount it with data_err=ignore, it doesn't abort, just
call printk().  data_err=ignore is the default.

Signed-off-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
Cc: Jan Kara <jack@ucw.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

5 files changed, 28 insertions, 0 deletions

diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index 295f26cd895a..9dd2a3bb2acc 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -96,6 +96,11 @@ errors=remount-ro(*)	Remount the filesystem read-only on an error.
 errors=continue         Keep going on a filesystem error.
 errors=panic            Panic and halt the machine if an error occurs.
 
+data_err=ignore(*)      Just print an error message if an error occurs
+                        in a file data buffer in ordered mode.
+data_err=abort          Abort the journal if an error occurs in a file
+                        data buffer in ordered mode.
+
 grpid                   Give objects the same group ID as their creator.
 bsdgroups
 
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 399a96a6c556..3a260af5544d 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -625,6 +625,9 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
         else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
                 seq_puts(seq, ",data=writeback");
 
+        if (test_opt(sb, DATA_ERR_ABORT))
+                seq_puts(seq, ",data_err=abort");
+
         ext3_show_quota_options(seq, sb);
 
         return 0;
@@ -754,6 +757,7 @@ enum {
         Opt_reservation, Opt_noreservation, Opt_noload, Opt_nobh, Opt_bh,
         Opt_commit, Opt_journal_update, Opt_journal_inum, Opt_journal_dev,
         Opt_abort, Opt_data_journal, Opt_data_ordered, Opt_data_writeback,
+        Opt_data_err_abort, Opt_data_err_ignore,
         Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
         Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_quota, Opt_noquota,
         Opt_ignore, Opt_barrier, Opt_err, Opt_resize, Opt_usrquota,
@@ -796,6 +800,8 @@ static const match_table_t tokens = {
         {Opt_data_journal, "data=journal"},
         {Opt_data_ordered, "data=ordered"},
         {Opt_data_writeback, "data=writeback"},
+        {Opt_data_err_abort, "data_err=abort"},
+        {Opt_data_err_ignore, "data_err=ignore"},
         {Opt_offusrjquota, "usrjquota="},
         {Opt_usrjquota, "usrjquota=%s"},
         {Opt_offgrpjquota, "grpjquota="},
@@ -1011,6 +1017,12 @@ static int parse_options (char *options, struct super_block *sb,
                                 sbi->s_mount_opt |= data_opt;
                         }
                         break;
+                case Opt_data_err_abort:
+                        set_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+                        break;
+                case Opt_data_err_ignore:
+                        clear_opt(sbi->s_mount_opt, DATA_ERR_ABORT);
+                        break;
 #ifdef CONFIG_QUOTA
                 case Opt_usrjquota:
                         qtype = USRQUOTA;
@@ -1986,6 +1998,10 @@ static void ext3_init_journal_params(struct super_block *sb, journal_t *journal)
                 journal->j_flags |= JFS_BARRIER;
         else
                 journal->j_flags &= ~JFS_BARRIER;
+        if (test_opt(sb, DATA_ERR_ABORT))
+                journal->j_flags |= JFS_ABORT_ON_SYNCDATA_ERR;
+        else
+                journal->j_flags &= ~JFS_ABORT_ON_SYNCDATA_ERR;
         spin_unlock(&journal->j_state_lock);
 }
 
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index d6a6659f3e46..25719d902c51 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -482,6 +482,8 @@ void journal_commit_transaction(journal_t *journal)
                 printk(KERN_WARNING
                         "JBD: Detected IO errors while flushing file data "
                         "on %s\n", bdevname(journal->j_fs_dev, b));
+                if (journal->j_flags & JFS_ABORT_ON_SYNCDATA_ERR)
+                        journal_abort(journal, err);
                 err = 0;
         }
 
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 159d9b476cd7..d14f02918483 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -380,6 +380,8 @@ struct ext3_inode {
 #define EXT3_MOUNT_QUOTA                0x80000 /* Some quota option set */
 #define EXT3_MOUNT_USRQUOTA             0x100000 /* "old" user quota */
 #define EXT3_MOUNT_GRPQUOTA             0x200000 /* "old" group quota */
+#define EXT3_MOUNT_DATA_ERR_ABORT       0x400000 /* Abort on file data write
+                                                  * error in ordered mode */
 
 /* Compatibility, for having both ext2_fs.h and ext3_fs.h included at once */
 #ifndef _LINUX_EXT2_FS_H
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 7ebbcb1c9ba4..35d4f6342fac 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -816,6 +816,9 @@ struct journal_s
 #define JFS_FLUSHED     0x008   /* The journal superblock has been flushed */
 #define JFS_LOADED      0x010   /* The journal superblock has been loaded */
 #define JFS_BARRIER     0x020   /* Use IDE barriers */
+#define JFS_ABORT_ON_SYNCDATA_ERR       0x040  /* Abort the journal on file
+                                                * data write error in ordered
+                                                * mode */
 
 /*
  * Function declarations for the journaling transaction and buffer