diff options
author | Lukas Czerner <lczerner@redhat.com> | 2012-02-20 17:53:00 -0500 |
---|---|---|
committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2012-04-02 09:27:19 -0700 |
commit | df3c660b5745e71665270141ced3fff82a4b0aa6 (patch) | |
tree | f5b9cbd8ef7eda5d9df565a7fe82960dc9858531 /fs/ext4 | |
parent | e4f7c341d6c6a78830dc918b23157ccfc399d397 (diff) | |
download | kernel_samsung_crespo-df3c660b5745e71665270141ced3fff82a4b0aa6.zip kernel_samsung_crespo-df3c660b5745e71665270141ced3fff82a4b0aa6.tar.gz kernel_samsung_crespo-df3c660b5745e71665270141ced3fff82a4b0aa6.tar.bz2 |
ext4: ignore EXT4_INODE_JOURNAL_DATA flag with delalloc
commit 3d2b158262826e8b75bbbfb7b97010838dd92ac7 upstream.
Ext4 does not support data journalling with delayed allocation enabled.
We even do not allow to mount the file system with delayed allocation
and data journalling enabled, however it can be set via FS_IOC_SETFLAGS
so we can hit the inode with EXT4_INODE_JOURNAL_DATA set even on file
system mounted with delayed allocation (default) and that's where
problem arises. The easies way to reproduce this problem is with the
following set of commands:
mkfs.ext4 /dev/sdd
mount /dev/sdd /mnt/test1
dd if=/dev/zero of=/mnt/test1/file bs=1M count=4
chattr +j /mnt/test1/file
dd if=/dev/zero of=/mnt/test1/file bs=1M count=4 conv=notrunc
chattr -j /mnt/test1/file
Additionally it can be reproduced quite reliably with xfstests 272 and
269. In fact the above reproducer is a part of test 272.
To fix this we should ignore the EXT4_INODE_JOURNAL_DATA inode flag if
the file system is mounted with delayed allocation. This can be easily
done by fixing ext4_should_*_data() functions do ignore data journal
flag when delalloc is set (suggested by Ted). We also have to set the
appropriate address space operations for the inode (again, ignoring data
journal flag if delalloc enabled).
Additionally this commit introduces ext4_inode_journal_mode() function
because ext4_should_*_data() has already had a lot of common code and
this change is putting it all into one function so it is easier to
read.
Successfully tested with xfstests in following configurations:
delalloc + data=ordered
delalloc + data=writeback
data=journal
nodelalloc + data=ordered
nodelalloc + data=writeback
nodelalloc + data=journal
Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/ext4_jbd2.h | 56 | ||||
-rw-r--r-- | fs/ext4/inode.c | 36 |
2 files changed, 51 insertions, 41 deletions
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index 5802fa1..95af6f8 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -261,43 +261,45 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle, /* super.c */ int ext4_force_commit(struct super_block *sb); -static inline int ext4_should_journal_data(struct inode *inode) +/* + * Ext4 inode journal modes + */ +#define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */ +#define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */ +#define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */ + +static inline int ext4_inode_journal_mode(struct inode *inode) { if (EXT4_JOURNAL(inode) == NULL) - return 0; - if (!S_ISREG(inode->i_mode)) - return 1; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) - return 1; - if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA)) - return 1; - return 0; + return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ + /* We do not support data journalling with delayed allocation */ + if (!S_ISREG(inode->i_mode) || + test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) + return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */ + if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) && + !test_opt(inode->i_sb, DELALLOC)) + return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */ + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) + return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */ + if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) + return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */ + else + BUG(); +} + +static inline int ext4_should_journal_data(struct inode *inode) +{ + return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE; } static inline int ext4_should_order_data(struct inode *inode) { - if (EXT4_JOURNAL(inode) == NULL) - return 0; - if (!S_ISREG(inode->i_mode)) - return 0; - if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA)) - return 0; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) - return 1; - return 0; + return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE; } static inline int ext4_should_writeback_data(struct inode *inode) { - if (EXT4_JOURNAL(inode) == NULL) - return 1; - if (!S_ISREG(inode->i_mode)) - return 0; - if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA)) - return 0; - if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) - return 1; - return 0; + return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE; } /* diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 792e6a9..c1e6a72 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -3212,13 +3212,14 @@ static int ext4_da_write_end(struct file *file, int write_mode = (int)(unsigned long)fsdata; if (write_mode == FALL_BACK_TO_NONDELALLOC) { - if (ext4_should_order_data(inode)) { + switch (ext4_inode_journal_mode(inode)) { + case EXT4_INODE_ORDERED_DATA_MODE: return ext4_ordered_write_end(file, mapping, pos, len, copied, page, fsdata); - } else if (ext4_should_writeback_data(inode)) { + case EXT4_INODE_WRITEBACK_DATA_MODE: return ext4_writeback_write_end(file, mapping, pos, len, copied, page, fsdata); - } else { + default: BUG(); } } @@ -3918,18 +3919,25 @@ static const struct address_space_operations ext4_da_aops = { void ext4_set_aops(struct inode *inode) { - if (ext4_should_order_data(inode) && - test_opt(inode->i_sb, DELALLOC)) - inode->i_mapping->a_ops = &ext4_da_aops; - else if (ext4_should_order_data(inode)) - inode->i_mapping->a_ops = &ext4_ordered_aops; - else if (ext4_should_writeback_data(inode) && - test_opt(inode->i_sb, DELALLOC)) - inode->i_mapping->a_ops = &ext4_da_aops; - else if (ext4_should_writeback_data(inode)) - inode->i_mapping->a_ops = &ext4_writeback_aops; - else + switch (ext4_inode_journal_mode(inode)) { + case EXT4_INODE_ORDERED_DATA_MODE: + if (test_opt(inode->i_sb, DELALLOC)) + inode->i_mapping->a_ops = &ext4_da_aops; + else + inode->i_mapping->a_ops = &ext4_ordered_aops; + break; + case EXT4_INODE_WRITEBACK_DATA_MODE: + if (test_opt(inode->i_sb, DELALLOC)) + inode->i_mapping->a_ops = &ext4_da_aops; + else + inode->i_mapping->a_ops = &ext4_writeback_aops; + break; + case EXT4_INODE_JOURNAL_DATA_MODE: inode->i_mapping->a_ops = &ext4_journalled_aops; + break; + default: + BUG(); + } } /* |