ext4: allow specifying external journal by pathname mount option

It's always been a hassle that if an external journal's
device number changes, the filesystem won't mount.
And since boot-time enumeration can change, device number
changes aren't unusual.

The current mechanism to update the journal location is by
passing in a mount option w/ a new devnum, but that's a hassle;
it's a manual approach, fixing things after the fact.

Adding a mount option, "-o journal_path=/dev/$DEVICE" would
help, since then we can do i.e.

# mount -o journal_path=/dev/disk/by-label/$JOURNAL_LABEL ...

and it'll mount even if the devnum has changed, as shown here:

# losetup /dev/loop0 journalfile
# mke2fs -L mylabel-journal -O journal_dev /dev/loop0
# mkfs.ext4 -L mylabel -J device=/dev/loop0 /dev/sdb1

Change the journal device number:

# losetup -d /dev/loop0
# losetup /dev/loop1 journalfile

And today it will fail:

# mount /dev/sdb1 /mnt/test
mount: wrong fs type, bad option, bad superblock on /dev/sdb1,
       missing codepage or helper program, or other error
       In some cases useful info is found in syslog - try
       dmesg | tail  or so

# dmesg | tail -n 1
[17343.240702] EXT4-fs (sdb1): error: couldn't read superblock of external journal

But with this new mount option, we can specify the new path:

# mount -o journal_path=/dev/loop1 /dev/sdb1 /mnt/test
#

(which does update the encoded device number, incidentally):

# umount /dev/sdb1
# dumpe2fs -h /dev/sdb1 | grep "Journal device"
dumpe2fs 1.41.12 (17-May-2010)
Journal device:	          0x0701

But best of all we can just always mount by journal-path, and
it'll always work:

# mount -o journal_path=/dev/disk/by-label/mylabel-journal /dev/sdb1 /mnt/test
#

So the journal_path option can be specified in fstab, and as long as
the disk is available somewhere, and findable by label (or by UUID),
we can mount.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>

diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index f7cbf574a875271296d93bee53b290ca36c44a66..b91cfaaf6a0f459ef14a27098e993a2f6131fd34 100644 (file)
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -144,11 +144,12 @@ journal_async_commit      Commit block can be written to disk without waiting
                        mount the device. This will enable 'journal_checksum'
                        internally.
 
+journal_path=path
 journal_dev=devnum     When the external journal device's major/minor numbers
-                       have changed, this option allows the user to specify
+                       have changed, these options allow the user to specify
                        the new journal location.  The journal device is
-                       identified through its new major/minor numbers encoded
-                       in devnum.
+                       identified through either its new major/minor numbers
+                       encoded in devnum, or via a path to the device.
 
 norecovery             Don't load the journal on mounting.  Note that
 noload                 if the filesystem was not unmounted cleanly,

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b59373b625e9bcacaf3a63e409b21b1ef6212dfa..42337141e79fb90885678d9ea6a653d520437ffa 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1134,8 +1134,8 @@ enum {
        Opt_nouid32, Opt_debug, Opt_removed,
        Opt_user_xattr, Opt_nouser_xattr, Opt_acl, Opt_noacl,
        Opt_auto_da_alloc, Opt_noauto_da_alloc, Opt_noload,
-       Opt_commit, Opt_min_batch_time, Opt_max_batch_time,
-       Opt_journal_dev, Opt_journal_checksum, Opt_journal_async_commit,
+       Opt_commit, Opt_min_batch_time, Opt_max_batch_time, Opt_journal_dev,
+       Opt_journal_path, Opt_journal_checksum, Opt_journal_async_commit,
        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,
@@ -1179,6 +1179,7 @@ static const match_table_t tokens = {
        {Opt_min_batch_time, "min_batch_time=%u"},
        {Opt_max_batch_time, "max_batch_time=%u"},
        {Opt_journal_dev, "journal_dev=%u"},
+       {Opt_journal_path, "journal_path=%s"},
        {Opt_journal_checksum, "journal_checksum"},
        {Opt_journal_async_commit, "journal_async_commit"},
        {Opt_abort, "abort"},
@@ -1338,6 +1339,7 @@ static int clear_qf_name(struct super_block *sb, int qtype)
 #define MOPT_NO_EXT2   0x0100
 #define MOPT_NO_EXT3   0x0200
 #define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
+#define MOPT_STRING    0x0400
 
 static const struct mount_opts {
        int     token;
@@ -1387,6 +1389,7 @@ static const struct mount_opts {
        {Opt_resuid, 0, MOPT_GTE0},
        {Opt_resgid, 0, MOPT_GTE0},
        {Opt_journal_dev, 0, MOPT_GTE0},
+       {Opt_journal_path, 0, MOPT_STRING},
        {Opt_journal_ioprio, 0, MOPT_GTE0},
        {Opt_data_journal, EXT4_MOUNT_JOURNAL_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
        {Opt_data_ordered, EXT4_MOUNT_ORDERED_DATA, MOPT_NO_EXT2 | MOPT_DATAJ},
@@ -1480,7 +1483,7 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
                return -1;
        }
 
-       if (args->from && match_int(args, &arg))
+       if (args->from && !(m->flags & MOPT_STRING) && match_int(args, &arg))
                return -1;
        if (args->from && (m->flags & MOPT_GTE0) && (arg < 0))
                return -1;
@@ -1544,6 +1547,44 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
                        return -1;
                }
                *journal_devnum = arg;
+       } else if (token == Opt_journal_path) {
+               char *journal_path;
+               struct inode *journal_inode;
+               struct path path;
+               int error;
+
+               if (is_remount) {
+                       ext4_msg(sb, KERN_ERR,
+                                "Cannot specify journal on remount");
+                       return -1;
+               }
+               journal_path = match_strdup(&args[0]);
+               if (!journal_path) {
+                       ext4_msg(sb, KERN_ERR, "error: could not dup "
+                               "journal device string");
+                       return -1;
+               }
+
+               error = kern_path(journal_path, LOOKUP_FOLLOW, &path);
+               if (error) {
+                       ext4_msg(sb, KERN_ERR, "error: could not find "
+                               "journal device path: error %d", error);
+                       kfree(journal_path);
+                       return -1;
+               }
+
+               journal_inode = path.dentry->d_inode;
+               if (!S_ISBLK(journal_inode->i_mode)) {
+                       ext4_msg(sb, KERN_ERR, "error: journal path %s "
+                               "is not a block device", journal_path);
+                       path_put(&path);
+                       kfree(journal_path);
+                       return -1;
+               }
+
+               *journal_devnum = new_encode_dev(journal_inode->i_rdev);
+               path_put(&path);
+               kfree(journal_path);
        } else if (token == Opt_journal_ioprio) {
                if (arg > 7) {
                        ext4_msg(sb, KERN_ERR, "Invalid journal IO priority"