ovl: do not ignore disk quota if current task is not privileged
diff mbox

Message ID 148404760886.4400.14907571208759802396.stgit@buzz
State New
Headers show

Commit Message

Konstantin Khlebnikov Jan. 10, 2017, 11:26 a.m. UTC
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.

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@yandex-team.ru>
Fixes: 1175b6b8d963 ("ovl: do operations on underlying file system in mounter's context")
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/overlayfs/ovl_entry.h |    2 ++
 fs/overlayfs/super.c     |   13 ++++++++++++-
 fs/overlayfs/util.c      |   10 +++++++++-
 3 files changed, 23 insertions(+), 2 deletions(-)


--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Vivek Goyal Jan. 10, 2017, 2:46 p.m. UTC | #1
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.
> 
> 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.

This makes sense to me. I too would like quota to take effect for
containers on overlay.

I will test it. 

Vivek

> 
> Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
> Fixes: 1175b6b8d963 ("ovl: do operations on underlying file system in mounter's context")
> Cc: Vivek Goyal <vgoyal@redhat.com>
> Cc: Miklos Szeredi <mszeredi@redhat.com>
> ---
>  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)
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Miklos Szeredi Jan. 10, 2017, 3:57 p.m. UTC | #2
On Tue, Jan 10, 2017 at 3:46 PM, Vivek Goyal <vgoyal@redhat.com> 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.
>>
>> 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.
>
> This makes sense to me. I too would like quota to take effect for
> containers on overlay.

At first sight I hated this patch.  It breaks the nice concept that
underlying filesystems are just storage for the overlay and don't care
about caller's privileges (as a block device wouldn't care about
caller's privileges when allocating space).

However I don't see a good way around this, so...

Looks like this also has effect on reserving space in ext4, not sure
what that entails.

Thanks,
Miklos
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Vivek Goyal Jan. 10, 2017, 4:06 p.m. UTC | #3
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?

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?

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@yandex-team.ru>
> Fixes: 1175b6b8d963 ("ovl: do operations on underlying file system in mounter's context")
> Cc: Vivek Goyal <vgoyal@redhat.com>
> Cc: Miklos Szeredi <mszeredi@redhat.com>
> ---
>  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)
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Konstantin Khlebnikov Jan. 10, 2017, 4:30 p.m. UTC | #4
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@yandex-team.ru>
>> Fixes: 1175b6b8d963 ("ovl: do operations on underlying file system in mounter's context")
>> Cc: Vivek Goyal <vgoyal@redhat.com>
>> Cc: Miklos Szeredi <mszeredi@redhat.com>
>> ---
>>  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 Khlebnikov Jan. 10, 2017, 4:34 p.m. UTC | #5
On 10.01.2017 18:57, Miklos Szeredi wrote:
> On Tue, Jan 10, 2017 at 3:46 PM, Vivek Goyal <vgoyal@redhat.com> 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.
>>>
>>> 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.
>>
>> This makes sense to me. I too would like quota to take effect for
>> containers on overlay.
>
> At first sight I hated this patch.  It breaks the nice concept that
> underlying filesystems are just storage for the overlay and don't care
> about caller's privileges (as a block device wouldn't care about
> caller's privileges when allocating space).
>
> However I don't see a good way around this, so...

Another solution: just always drop CAP_SYS_RESOURCE from capabilities.

> Looks like this also has effect on reserving space in ext4, not sure
> what that entails.

Yes, CAP_SYS_RESOURCE allows to use reserved space and inodes.
Vivek Goyal Jan. 10, 2017, 4:35 p.m. UTC | #6
On Tue, Jan 10, 2017 at 11:06:47AM -0500, 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?
> 
> 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?

As root user, I set limit of 1G on work/ and upper/ dir and created
a file of 4G in lower/ dir and mounted overlay on "merged" dir and
did "touch zerofile", and go error message.

touch: cannot touch 'zerofile': No space left on device

So looks like I am doing something wrong and not be able to reproduce
the issue to begin with.

Vivek
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Konstantin Khlebnikov Jan. 10, 2017, 4:44 p.m. UTC | #7
On 10.01.2017 19:35, Vivek Goyal wrote:
> On Tue, Jan 10, 2017 at 11:06:47AM -0500, 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?
>>
>> 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?
>
> As root user, I set limit of 1G on work/ and upper/ dir and created
> a file of 4G in lower/ dir and mounted overlay on "merged" dir and
> did "touch zerofile", and go error message.
>
> touch: cannot touch 'zerofile': No space left on device
>
> So looks like I am doing something wrong and not be able to reproduce
> the issue to begin with.
>

I'm using ext4 project quota around upper/work directories.
ext4 use generic quota implementation: it ignores hard limits if CAP_SYS_RESOURCE is set.

It seems XFS ignores CAP_SYS_RESOURCE for any kind of quota.
But I've found special meaning for CAP_FOWNER - chown() can ignore user/group
quota if caller have this capability.
Amir Goldstein Jan. 10, 2017, 6:11 p.m. UTC | #8
On Tue, Jan 10, 2017 at 6:34 PM, Konstantin Khlebnikov
<khlebnikov@yandex-team.ru> wrote:
>
> On 10.01.2017 18:57, Miklos Szeredi wrote:
>>
>> On Tue, Jan 10, 2017 at 3:46 PM, Vivek Goyal <vgoyal@redhat.com> 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.
>>>>
>>>> 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.
>>>
>>>
>>> This makes sense to me. I too would like quota to take effect for
>>> containers on overlay.
>>
>>
>> At first sight I hated this patch.  It breaks the nice concept that
>> underlying filesystems are just storage for the overlay and don't care
>> about caller's privileges (as a block device wouldn't care about
>> caller's privileges when allocating space).
>>
>> However I don't see a good way around this, so...
>
>
> Another solution: just always drop CAP_SYS_RESOURCE from capabilities.
>

That sounds like a better (and simpler) solution.

Let overlayfs support mount options noquota|quota (default configurable
from Kconfig and module param) and 'quota' means drop CAP_SYS_RESOURCE.


>> Looks like this also has effect on reserving space in ext4, not sure
>> what that entails.
>
>
> Yes, CAP_SYS_RESOURCE allows to use reserved space and inodes.
>

That's really not good. It's beyond disobeying user quotas, because
file system may get to unrecoverable state when corruption is detected
and already filled the root reserved space.

Amir.
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Konstantin Khlebnikov Jan. 10, 2017, 6:30 p.m. UTC | #9
On 10.01.2017 21:11, Amir Goldstein wrote:
> On Tue, Jan 10, 2017 at 6:34 PM, Konstantin Khlebnikov
> <khlebnikov@yandex-team.ru> wrote:
>>
>> On 10.01.2017 18:57, Miklos Szeredi wrote:
>>>
>>> On Tue, Jan 10, 2017 at 3:46 PM, Vivek Goyal <vgoyal@redhat.com> 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.
>>>>>
>>>>> 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.
>>>>
>>>>
>>>> This makes sense to me. I too would like quota to take effect for
>>>> containers on overlay.
>>>
>>>
>>> At first sight I hated this patch.  It breaks the nice concept that
>>> underlying filesystems are just storage for the overlay and don't care
>>> about caller's privileges (as a block device wouldn't care about
>>> caller's privileges when allocating space).
>>>
>>> However I don't see a good way around this, so...
>>
>>
>> Another solution: just always drop CAP_SYS_RESOURCE from capabilities.
>>
>
> That sounds like a better (and simpler) solution.
>
> Let overlayfs support mount options noquota|quota (default configurable
> from Kconfig and module param) and 'quota' means drop CAP_SYS_RESOURCE.

Too complicated for me. Let's drop it unconditionally. See v2 patch.

>
>
>>> Looks like this also has effect on reserving space in ext4, not sure
>>> what that entails.
>>
>>
>> Yes, CAP_SYS_RESOURCE allows to use reserved space and inodes.
>>
>
> That's really not good. It's beyond disobeying user quotas, because
> file system may get to unrecoverable state when corruption is detected
> and already filled the root reserved space.
>
> Amir.
>

Patch
diff mbox

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)