Re: [PATCH resend 2/2] userns: control capabilities of some user namespaces

["Serge E. Hallyn" <serge@hallyn.com>]

Quoting Mahesh Bandewar (mahesh@bandewar.net):
> From: Mahesh Bandewar <maheshb@google.com>
> 
> With this new notion of "controlled" user-namespaces, the controlled
> user-namespaces are marked at the time of their creation while the
> capabilities of processes that belong to them are controlled using the
> global mask.
> 
> Init-user-ns is always uncontrolled and a process that has SYS_ADMIN
> that belongs to uncontrolled user-ns can create another (child) user-
> namespace that is uncontrolled. Any other process (that either does
> not have SYS_ADMIN or belongs to a controlled user-ns) can only
> create a user-ns that is controlled.
> 
> global-capability-whitelist (controlled_userns_caps_whitelist) is used
> at the capability check-time and keeps the semantics for the processes
> that belong to uncontrolled user-ns as it is. Processes that belong to
> controlled user-ns however are subjected to different checks-
> 
>    (a) if the capability in question is controlled and process belongs
>        to controlled user-ns, then it's always denied.
>    (b) if the capability in question is NOT controlled then fall back
>        to the traditional check.
> 
> Signed-off-by: Mahesh Bandewar <maheshb@google.com>
> ---
>  include/linux/capability.h     |  1 +
>  include/linux/user_namespace.h | 20 ++++++++++++++++++++
>  kernel/capability.c            |  5 +++++
>  kernel/user_namespace.c        |  3 +++
>  security/commoncap.c           |  8 ++++++++
>  5 files changed, 37 insertions(+)
> 
> diff --git a/include/linux/capability.h b/include/linux/capability.h
> index 6c0b9677c03f..b8c6cac18658 100644
> --- a/include/linux/capability.h
> +++ b/include/linux/capability.h
> @@ -250,6 +250,7 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns);
>  extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps);
>  int proc_douserns_caps_whitelist(struct ctl_table *table, int write,
>  				 void __user *buff, size_t *lenp, loff_t *ppos);
> +bool is_capability_controlled(int cap);
>  
>  extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size);
>  
> diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
> index c18e01252346..e890fe81b47e 100644
> --- a/include/linux/user_namespace.h
> +++ b/include/linux/user_namespace.h
> @@ -22,6 +22,7 @@ struct uid_gid_map {	/* 64 bytes -- 1 cache line */
>  };
>  
>  #define USERNS_SETGROUPS_ALLOWED 1UL
> +#define USERNS_CONTROLLED	 2UL
>  
>  #define USERNS_INIT_FLAGS USERNS_SETGROUPS_ALLOWED
>  
> @@ -102,6 +103,16 @@ static inline void put_user_ns(struct user_namespace *ns)
>  		__put_user_ns(ns);
>  }
>  
> +static inline bool is_user_ns_controlled(const struct user_namespace *ns)
> +{
> +	return ns->flags & USERNS_CONTROLLED;
> +}
> +
> +static inline void mark_user_ns_controlled(struct user_namespace *ns)
> +{
> +	ns->flags |= USERNS_CONTROLLED;
> +}
> +
>  struct seq_operations;
>  extern const struct seq_operations proc_uid_seq_operations;
>  extern const struct seq_operations proc_gid_seq_operations;
> @@ -160,6 +171,15 @@ static inline struct ns_common *ns_get_owner(struct ns_common *ns)
>  {
>  	return ERR_PTR(-EPERM);
>  }
> +
> +static inline bool is_user_ns_controlled(const struct user_namespace *ns)
> +{
> +	return false;
> +}
> +
> +static inline void mark_user_ns_controlled(struct user_namespace *ns)
> +{
> +}
>  #endif
>  
>  #endif /* _LINUX_USER_H */
> diff --git a/kernel/capability.c b/kernel/capability.c
> index 62dbe3350c1b..40a38cc4ff43 100644
> --- a/kernel/capability.c
> +++ b/kernel/capability.c
> @@ -510,6 +510,11 @@ bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns)
>  }
>  
>  /* Controlled-userns capabilities routines */
> +bool is_capability_controlled(int cap)
> +{
> +	return !cap_raised(controlled_userns_caps_whitelist, cap);
> +}
> +
>  #ifdef CONFIG_SYSCTL
>  int proc_douserns_caps_whitelist(struct ctl_table *table, int write,
>  				 void __user *buff, size_t *lenp, loff_t *ppos)
> diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
> index c490f1e4313b..f393ea5108f0 100644
> --- a/kernel/user_namespace.c
> +++ b/kernel/user_namespace.c
> @@ -53,6 +53,9 @@ static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns)
>  	cred->cap_effective = CAP_FULL_SET;
>  	cred->cap_ambient = CAP_EMPTY_SET;
>  	cred->cap_bset = CAP_FULL_SET;
> +	if (!ns_capable(user_ns->parent, CAP_SYS_ADMIN) ||
> +	    is_user_ns_controlled(user_ns->parent))
> +		mark_user_ns_controlled(user_ns);

Hm, why do this here, rather than at create_user_ns()?  It
shouldn't be recalculated when someone does setns() should it?