> 在 2018年9月11日，上午8:29，Andreas Dilger <adilger@xxxxxxxxx> 写道： > > >> On Sep 10, 2018, at 5:55 PM, Wang Shilong <wangshilong1991@xxxxxxxxx> wrote: >> >> From: Wang Shilong <wshilong@xxxxxxx> >> >> We return most of failure of dquota_initialize() except >> inode evict, this could make a bit sense, for example >> we allow file removal even quota files are broken? >> >> But it dosen't make sense to allow setting project >> if quota files etc are broken. >> >> Signed-off-by: Wang Shilong <wshilong@xxxxxxx> >> --- >> This patch based on: >> https://patchwork.ozlabs.org/patch/967727/ You missed this part ^_^ >> --- >> fs/ext4/ioctl.c | 4 +++- >> 1 file changed, 3 insertions(+), 1 deletion(-) >> >> diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c >> index 6ef989a..2f0bb90 100644 >> --- a/fs/ext4/ioctl.c >> +++ b/fs/ext4/ioctl.c >> @@ -359,7 +359,9 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid) >> brelse(iloc.bh); >> } >> >> - dquot_initialize(inode); >> + err = dquot_initialize(inode); >> + if (err) >> + return err; > > (defect) this should use "goto out_unlock;" like the other error handling here. Hey Andreas, As I mentioned this patch is based on. https://patchwork.ozlabs.org/patch/967728/ Which removed out_unlock label. > > > Cheers, Andreas > > > > >
