On Sat 12-04-14 19:20:14, Ted Tso wrote:
> To avoid potential data races, use a spinlock which protects the raw
> (on-disk) inode.
>
> Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
The patch looks good. You can add:
Reviewed-by: Jan Kara <jack@xxxxxxx>
Honza
> ---
> fs/ext4/ext4.h | 2 ++
> fs/ext4/inode.c | 41 ++++++++++++++++++++++-------------------
> fs/ext4/super.c | 1 +
> 3 files changed, 25 insertions(+), 19 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index 86c2cda..1d08a1b 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -875,6 +875,8 @@ struct ext4_inode_info {
> struct inode vfs_inode;
> struct jbd2_inode *jinode;
>
> + spinlock_t i_raw_lock; /* protects updates to the raw inode */
> +
> /*
> * File creation time. Its function is same as that of
> * struct timespec i_{a,c,m}time in the generic inode.
> diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
> index 2eb5fad..7ae10f0 100644
> --- a/fs/ext4/inode.c
> +++ b/fs/ext4/inode.c
> @@ -4306,12 +4306,15 @@ static int ext4_do_update_inode(handle_t *handle,
> struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
> struct ext4_inode_info *ei = EXT4_I(inode);
> struct buffer_head *bh = iloc->bh;
> + struct super_block *sb = inode->i_sb;
> int err = 0, rc, block;
> - int need_datasync = 0;
> + int need_datasync = 0, set_large_file = 0;
> uid_t i_uid;
> gid_t i_gid;
>
> - /* For fields not not tracking in the in-memory inode,
> + spin_lock(&ei->i_raw_lock);
> +
> + /* For fields not tracked in the in-memory inode,
> * initialise them to zero for new inodes. */
> if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
> memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
> @@ -4349,8 +4352,10 @@ static int ext4_do_update_inode(handle_t *handle,
> EXT4_INODE_SET_XTIME(i_atime, inode, raw_inode);
> EXT4_EINODE_SET_XTIME(i_crtime, ei, raw_inode);
>
> - if (ext4_inode_blocks_set(handle, raw_inode, ei))
> + if (ext4_inode_blocks_set(handle, raw_inode, ei)) {
> + spin_unlock(&ei->i_raw_lock);
> goto out_brelse;
> + }
> raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
> raw_inode->i_flags = cpu_to_le32(ei->i_flags & 0xFFFFFFFF);
> if (likely(!test_opt2(inode->i_sb, HURD_COMPAT)))
> @@ -4362,24 +4367,11 @@ static int ext4_do_update_inode(handle_t *handle,
> need_datasync = 1;
> }
> if (ei->i_disksize > 0x7fffffffULL) {
> - struct super_block *sb = inode->i_sb;
> if (!EXT4_HAS_RO_COMPAT_FEATURE(sb,
> EXT4_FEATURE_RO_COMPAT_LARGE_FILE) ||
> EXT4_SB(sb)->s_es->s_rev_level ==
> - cpu_to_le32(EXT4_GOOD_OLD_REV)) {
> - /* If this is the first large file
> - * created, add a flag to the superblock.
> - */
> - err = ext4_journal_get_write_access(handle,
> - EXT4_SB(sb)->s_sbh);
> - if (err)
> - goto out_brelse;
> - ext4_update_dynamic_rev(sb);
> - EXT4_SET_RO_COMPAT_FEATURE(sb,
> - EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
> - ext4_handle_sync(handle);
> - err = ext4_handle_dirty_super(handle, sb);
> - }
> + cpu_to_le32(EXT4_GOOD_OLD_REV))
> + set_large_file = 1;
> }
> raw_inode->i_generation = cpu_to_le32(inode->i_generation);
> if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
> @@ -4411,12 +4403,23 @@ static int ext4_do_update_inode(handle_t *handle,
>
> ext4_inode_csum_set(inode, raw_inode, ei);
>
> + spin_unlock(&ei->i_raw_lock);
> +
> BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
> rc = ext4_handle_dirty_metadata(handle, NULL, bh);
> if (!err)
> err = rc;
> ext4_clear_inode_state(inode, EXT4_STATE_NEW);
> -
> + if (set_large_file) {
> + err = ext4_journal_get_write_access(handle, EXT4_SB(sb)->s_sbh);
> + if (err)
> + goto out_brelse;
> + ext4_update_dynamic_rev(sb);
> + EXT4_SET_RO_COMPAT_FEATURE(sb,
> + EXT4_FEATURE_RO_COMPAT_LARGE_FILE);
> + ext4_handle_sync(handle);
> + err = ext4_handle_dirty_super(handle, sb);
> + }
> ext4_update_inode_fsync_trans(handle, inode, need_datasync);
> out_brelse:
> brelse(bh);
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index c4895c1..1f8cb18 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -879,6 +879,7 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
> return NULL;
>
> ei->vfs_inode.i_version = 1;
> + spin_lock_init(&ei->i_raw_lock);
> INIT_LIST_HEAD(&ei->i_prealloc_list);
> spin_lock_init(&ei->i_prealloc_lock);
> ext4_es_init_tree(&ei->i_es_tree);
> --
> 1.9.0
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
Jan Kara <jack@xxxxxxx>
SUSE Labs, CR
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
