Revert "ext4: Remove journal_checksum mount option and enable it by default"

This reverts commit d0646f7b636d067d715fab52a2ba9c6f0f46b0d7, as
requested by Eric Sandeen.

It can basically cause an ext4 filesystem to miss recovery (and thus get
mounted with errors) if the journal checksum does not match.

Quoth Eric:

   "My hand-wavy hunch about what is happening is that we're finding a
    bad checksum on the last partially-written transaction, which is
    not surprising, but if we have a wrapped log and we're doing the
    initial scan for head/tail, and we abort scanning on that bad
    checksum, then we are essentially running an unrecovered filesystem.

    But that's hand-wavy and I need to go look at the code.

    We lived without journal checksums on by default until now, and at
    this point they're doing more harm than good, so we should revert
    the default-changing commit until we can fix it and do some good
    power-fail testing with the fixes in place."

See

	http://bugzilla.kernel.org/show_bug.cgi?id=14354

for all the gory details.

Requested-by: Eric Sandeen <sandeen@redhat.com>
Cc: Theodore Tso <tytso@mit.edu>
Cc: Alexey Fisher <bug-track@fisher-privat.net>
Cc: Maxim Levitsky <maximlevitsky@gmail.com>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Mathias Burén <mathias.buren@gmail.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
index bf4f4b7..6d94e06 100644 (file)
--- a/Documentation/filesystems/ext4.txt
+++ b/Documentation/filesystems/ext4.txt
@@ -134,9 +134,15 @@ ro                         Mount filesystem read only. Note that ext4 will
                        mount options "ro,noload" can be used to prevent
                        writes to the filesystem.
 
+journal_checksum       Enable checksumming of the journal transactions.
+                       This will allow the recovery code in e2fsck and the
+                       kernel to detect corruption in the kernel.  It is a
+                       compatible change and will be ignored by older kernels.
+
 journal_async_commit   Commit block can be written to disk without waiting
                        for descriptor blocks. If enabled older kernels cannot
-                       mount the device.
+                       mount the device. This will enable 'journal_checksum'
+                       internally.
 
 journal=update         Update the ext4 file system's journal to the current
                        format.

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 984ca0c..00d153f 100644 (file)
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -743,6 +743,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_QUOTA               0x80000 /* Some quota option set */
 #define EXT4_MOUNT_USRQUOTA            0x100000 /* "old" user quota */
 #define EXT4_MOUNT_GRPQUOTA            0x200000 /* "old" group quota */
+#define EXT4_MOUNT_JOURNAL_CHECKSUM    0x800000 /* Journal checksums */
 #define EXT4_MOUNT_JOURNAL_ASYNC_COMMIT        0x1000000 /* Journal Async Commit */
 #define EXT4_MOUNT_I_VERSION            0x2000000 /* i_version support */
 #define EXT4_MOUNT_DELALLOC            0x8000000 /* Delalloc support */

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 312211e..d4ca92a 100644 (file)
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -1300,9 +1300,11 @@ static int parse_options(char *options, struct super_block *sb,
                        *journal_devnum = option;
                        break;
                case Opt_journal_checksum:
-                       break;  /* Kept for backwards compatibility */
+                       set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
+                       break;
                case Opt_journal_async_commit:
                        set_opt(sbi->s_mount_opt, JOURNAL_ASYNC_COMMIT);
+                       set_opt(sbi->s_mount_opt, JOURNAL_CHECKSUM);
                        break;
                case Opt_noload:
                        set_opt(sbi->s_mount_opt, NOLOAD);
@@ -2759,14 +2761,20 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
                goto failed_mount4;
        }
 
-       jbd2_journal_set_features(sbi->s_journal,
-                                 JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
-       if (test_opt(sb, JOURNAL_ASYNC_COMMIT))
-               jbd2_journal_set_features(sbi->s_journal, 0, 0,
+       if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
+               jbd2_journal_set_features(sbi->s_journal,
+                               JBD2_FEATURE_COMPAT_CHECKSUM, 0,
                                JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
-       else
+       } else if (test_opt(sb, JOURNAL_CHECKSUM)) {
+               jbd2_journal_set_features(sbi->s_journal,
+                               JBD2_FEATURE_COMPAT_CHECKSUM, 0, 0);
                jbd2_journal_clear_features(sbi->s_journal, 0, 0,
                                JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+       } else {
+               jbd2_journal_clear_features(sbi->s_journal,
+                               JBD2_FEATURE_COMPAT_CHECKSUM, 0,
+                               JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT);
+       }
 
        /* We have now updated the journal if required, so we can
         * validate the data journaling mode. */