Re: [PATCH] ovl: do not ignore disk quota if current task is not privileged

[Konstantin Khlebnikov]

On 10.01.2017 19:06, Vivek Goyal wrote:
> On Tue, Jan 10, 2017 at 02:26:48PM +0300, Konstantin Khlebnikov wrote:
> > If overlay was mounted by root then quota set for upper layer does not work
> > because overlay now always use mounter's credentials for operations.
>
> Hi Konstantin,
>
> So CAP_SYS_RESOURCE bypasses the quota checks?

Yep. See in fs/quota/dquot.c

static int ignore_hardlimit(struct dquot *dquot)
{
	struct mem_dqinfo *info = &sb_dqopt(dquot->dq_sb)->info[dquot->dq_id.type];

	return capable(CAP_SYS_RESOURCE) &&
	       (info->dqi_format->qf_fmt_id != QFMT_VFS_OLD ||
		!(info->dqi_flags & DQF_ROOT_SQUASH));
}

Feature DQF_ROOT_SQUASH which disables this bypassing is obsoleted in modern quota formats.

> I just created dir upper on xfs filesystem and defined quota of 1G and
> as root user (with cap_sys_resoureces), I am not able to create file
> bigger than 1g in that dir. So looks like xfs quota took affect even
> for privileged user with CAP_SYS_RESOURCE set.
>
> What am I missing?

XFS has its own quota and I cannot find any capable(CAP_SYS_RESOURCE) here.
So, probably XFS ignores this capability and always limits root user.

> Vivek
>
> > This patch adds second copy of credentials without CAP_SYS_RESOURCE and
> > use it if current task doesn't have this capability in mounter's user-ns.
> > This affects creation new files, whiteouts, and copy-up operations.
> >
> > Now quota limits are ignored only if both mounter and current task have
> > capability CAP_SYS_RESOURCE in root user namespace.
> >
> > Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxxxxxx>
> > Fixes: 1175b6b8d963 ("ovl: do operations on underlying file system in mounter's context")
> > Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
> > Cc: Miklos Szeredi <mszeredi@xxxxxxxxxx>
> > ---
> >  fs/overlayfs/ovl_entry.h |    2 ++
> >  fs/overlayfs/super.c     |   13 ++++++++++++-
> >  fs/overlayfs/util.c      |   10 +++++++++-
> >  3 files changed, 23 insertions(+), 2 deletions(-)
> >
> > diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
> > index d14bca1850d9..55eb3b08e292 100644
> > --- a/fs/overlayfs/ovl_entry.h
> > +++ b/fs/overlayfs/ovl_entry.h
> > @@ -27,6 +27,8 @@ struct ovl_fs {
> >  	struct ovl_config config;
> >  	/* creds of process who forced instantiation of super block */
> >  	const struct cred *creator_cred;
> > +	/* the same credentials without CAP_SYS_RESOURCE */
> > +	const struct cred *creator_cred_unpriv;
> >  };
> >
> >  /* private information held for every overlayfs dentry */
> > diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
> > index 20f48abbb82f..6a15693641e0 100644
> > --- a/fs/overlayfs/super.c
> > +++ b/fs/overlayfs/super.c
> > @@ -157,6 +157,7 @@ static void ovl_put_super(struct super_block *sb)
> >  	kfree(ufs->config.upperdir);
> >  	kfree(ufs->config.workdir);
> >  	put_cred(ufs->creator_cred);
> > +	put_cred(ufs->creator_cred_unpriv);
> >  	kfree(ufs);
> >  }
> >
> > @@ -701,6 +702,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
> >  	unsigned int stacklen = 0;
> >  	unsigned int i;
> >  	bool remote = false;
> > +	struct cred *cred;
> >  	int err;
> >
> >  	err = -ENOMEM;
> > @@ -874,10 +876,17 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
> >  	if (!ufs->creator_cred)
> >  		goto out_put_lower_mnt;
> >
> > +	cred = prepare_creds();
> > +	if (!cred)
> > +		goto out_put_cred;
> > +
> > +	ufs->creator_cred_unpriv = cred;
> > +	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
> > +
> >  	err = -ENOMEM;
> >  	oe = ovl_alloc_entry(numlower);
> >  	if (!oe)
> > -		goto out_put_cred;
> > +		goto out_put_cred_unpriv;
> >
> >  	sb->s_magic = OVERLAYFS_SUPER_MAGIC;
> >  	sb->s_op = &ovl_super_operations;
> > @@ -914,6 +923,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
> >
> >  out_free_oe:
> >  	kfree(oe);
> > +out_put_cred_unpriv:
> > +	put_cred(ufs->creator_cred_unpriv);
> >  out_put_cred:
> >  	put_cred(ufs->creator_cred);
> >  out_put_lower_mnt:
> > diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
> > index 952286f4826c..92f60096c5da 100644
> > --- a/fs/overlayfs/util.c
> > +++ b/fs/overlayfs/util.c
> > @@ -35,8 +35,16 @@ struct dentry *ovl_workdir(struct dentry *dentry)
> >  const struct cred *ovl_override_creds(struct super_block *sb)
> >  {
> >  	struct ovl_fs *ofs = sb->s_fs_info;
> > +	const struct cred *cred = ofs->creator_cred;
> >
> > -	return override_creds(ofs->creator_cred);
> > +	/*
> > +	 * Do not override quota inode limit if current task is not
> > +	 * capable to do that in mounter's user namespace.
> > +	 */
> > +	if (!ns_capable_noaudit(cred->user_ns, CAP_SYS_RESOURCE))
> > +		cred = ofs->creator_cred_unpriv;
> > +
> > +	return override_creds(cred);
> >  }
> >
> >  struct ovl_entry *ovl_alloc_entry(unsigned int numlower)


--
Konstantin