Re: [REVIEW][PATCH 1/2] userns: Better restrictions on when proc and sysfs can be mounted

[Gao feng <gaofeng-BthXqXjhjHXQFUHtdCDX3A@public.gmane.org>]

Hi Eric,

On 08/28/2013 05:44 AM, Eric W. Biederman wrote:
> 
> Rely on the fact that another flavor of the filesystem is already
> mounted and do not rely on state in the user namespace.
> 
> Verify that the mounted filesystem is not covered in any significant
> way.  I would love to verify that the previously mounted filesystem
> has no mounts on top but there are at least the directories
> /proc/sys/fs/binfmt_misc and /sys/fs/cgroup/ that exist explicitly
> for other filesystems to mount on top of.
> 
> Refactor the test into a function named fs_fully_visible and call that
> function from the mount routines of proc and sysfs.  This makes this
> test local to the filesystems involved and the results current of when
> the mounts take place, removing a weird threading of the user
> namespace, the mount namespace and the filesystems themselves.
> 
> Signed-off-by: "Eric W. Biederman" <ebiederm-aS9lmoZGLiVWk0Htik3J/w@public.gmane.org>
> ---
>  fs/namespace.c                 |   37 +++++++++++++++++++++++++------------
>  fs/proc/root.c                 |    7 +++++--
>  fs/sysfs/mount.c               |    3 ++-
>  include/linux/fs.h             |    1 +
>  include/linux/user_namespace.h |    4 ----
>  kernel/user.c                  |    2 --
>  kernel/user_namespace.c        |    2 --
>  7 files changed, 33 insertions(+), 23 deletions(-)
> 
> diff --git a/fs/namespace.c b/fs/namespace.c
> index 64627f8..877e427 100644
> --- a/fs/namespace.c
> +++ b/fs/namespace.c
> @@ -2867,25 +2867,38 @@ bool current_chrooted(void)
>  	return chrooted;
>  }
>  
> -void update_mnt_policy(struct user_namespace *userns)
> +bool fs_fully_visible(struct file_system_type *type)
>  {
>  	struct mnt_namespace *ns = current->nsproxy->mnt_ns;
>  	struct mount *mnt;
> +	bool visible = false;
>  
> -	down_read(&namespace_sem);
> +	if (unlikely(!ns))
> +		return false;
> +
> +	namespace_lock();
>  	list_for_each_entry(mnt, &ns->list, mnt_list) {
> -		switch (mnt->mnt.mnt_sb->s_magic) {
> -		case SYSFS_MAGIC:
> -			userns->may_mount_sysfs = true;
> -			break;
> -		case PROC_SUPER_MAGIC:
> -			userns->may_mount_proc = true;
> -			break;
> +		struct mount *child;
> +		if (mnt->mnt.mnt_sb->s_type != type)
> +			continue;
> +
> +		/* This mount is not fully visible if there are any child mounts
> +		 * that cover anything except for empty directories.
> +		 */
> +		list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
> +			struct inode *inode = child->mnt_mountpoint->d_inode;
> +			if (!S_ISDIR(inode->i_mode))
> +				goto next;
> +			if (inode->i_nlink != 2)
> +				goto next;


I met a problem that proc filesystem failed to mount in user namespace,
The problem is the i_nlink of sysctl entries under proc filesystem is not
2. it always is 1 even it's a directory, see proc_sys_make_inode. and for
btrfs, the i_nlink for an empty dir is 2 too. it seems like depends on the
filesystem itself,not depends on vfs. In my system binfmt_misc is mounted
on /proc/sys/fs/binfmt_misc, and the i_nlink of this directory's inode is
1.

btw, I'm not quite understand what's the inode->i_nlink != 2 here means?
is this directory empty? as I know, when we create a file(not dir) under
a dir, the i_nlink of this dir will not increase.

And another question, it looks like if we don't have proc/sys fs mounted,
then proc/sys will be failed to be mounted?

Thanks!

>  		}
> -		if (userns->may_mount_sysfs && userns->may_mount_proc)
> -			break;
> +		visible = true;
> +		goto found;
> +	next:	;
>  	}
> -	up_read(&namespace_sem);
> +found:
> +	namespace_unlock();
> +	return visible;
>  }
>  
>  static void *mntns_get(struct task_struct *task)
> diff --git a/fs/proc/root.c b/fs/proc/root.c
> index 38bd5d4..45e5fb7 100644
> --- a/fs/proc/root.c
> +++ b/fs/proc/root.c
> @@ -110,8 +110,11 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
>  		ns = task_active_pid_ns(current);
>  		options = data;
>  
> -		if (!current_user_ns()->may_mount_proc ||
> -		    !ns_capable(ns->user_ns, CAP_SYS_ADMIN))
> +		if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
> +			return ERR_PTR(-EPERM);
> +
> +		/* Does the mounter have privilege over the pid namespace? */
> +		if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
>  			return ERR_PTR(-EPERM);
>  	}
>  
> diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c
> index afd8327..4a2da3a 100644
> --- a/fs/sysfs/mount.c
> +++ b/fs/sysfs/mount.c
> @@ -112,7 +112,8 @@ static struct dentry *sysfs_mount(struct file_system_type *fs_type,
>  	struct super_block *sb;
>  	int error;
>  
> -	if (!(flags & MS_KERNMOUNT) && !current_user_ns()->may_mount_sysfs)
> +	if (!(flags & MS_KERNMOUNT) && !capable(CAP_SYS_ADMIN) &&
> +	    !fs_fully_visible(fs_type))
>  		return ERR_PTR(-EPERM);
>  
>  	info = kzalloc(sizeof(*info), GFP_KERNEL);
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index 9818747..3050c62 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1897,6 +1897,7 @@ extern int vfs_ustat(dev_t, struct kstatfs *);
>  extern int freeze_super(struct super_block *super);
>  extern int thaw_super(struct super_block *super);
>  extern bool our_mnt(struct vfsmount *mnt);
> +extern bool fs_fully_visible(struct file_system_type *);
>  
>  extern int current_umask(void);
>  
> diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
> index b6b215f..4ce0093 100644
> --- a/include/linux/user_namespace.h
> +++ b/include/linux/user_namespace.h
> @@ -26,8 +26,6 @@ struct user_namespace {
>  	kuid_t			owner;
>  	kgid_t			group;
>  	unsigned int		proc_inum;
> -	bool			may_mount_sysfs;
> -	bool			may_mount_proc;
>  };
>  
>  extern struct user_namespace init_user_ns;
> @@ -84,6 +82,4 @@ static inline void put_user_ns(struct user_namespace *ns)
>  
>  #endif
>  
> -void update_mnt_policy(struct user_namespace *userns);
> -
>  #endif /* _LINUX_USER_H */
> diff --git a/kernel/user.c b/kernel/user.c
> index 69b4c3d..5bbb919 100644
> --- a/kernel/user.c
> +++ b/kernel/user.c
> @@ -51,8 +51,6 @@ struct user_namespace init_user_ns = {
>  	.owner = GLOBAL_ROOT_UID,
>  	.group = GLOBAL_ROOT_GID,
>  	.proc_inum = PROC_USER_INIT_INO,
> -	.may_mount_sysfs = true,
> -	.may_mount_proc = true,
>  };
>  EXPORT_SYMBOL_GPL(init_user_ns);
>  
> diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
> index d8c30db..d58ad1e 100644
> --- a/kernel/user_namespace.c
> +++ b/kernel/user_namespace.c
> @@ -97,8 +97,6 @@ int create_user_ns(struct cred *new)
>  
>  	set_cred_user_ns(new, ns);
>  
> -	update_mnt_policy(ns);
> -
>  	return 0;
>  }
>  
>