Re: [PATCH] ptrace: being capable wrt a process requires mapped uids/gids

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

On Sat, Dec 26, 2015 at 03:52:31AM +0100, Jann Horn wrote:
> ptrace_has_cap() checks whether the current process should be
> treated as having a certain capability for ptrace checks
> against another process. Until now, this was equivalent to
> has_ns_capability(current, target_ns, CAP_SYS_PTRACE).
> 
> However, if a root-owned process wants to enter a user
> namespace for some reason without knowing who owns it and
> therefore can't change to the namespace owner's uid and gid
> before entering, as soon as it has entered the namespace,
> the namespace owner can attach to it via ptrace and thereby
> gain access to its uid and gid.
> 
> While it is possible for the entering process to switch to
> the uid of a claimed namespace owner before entering,
> causing the attempt to enter to fail if the claimed uid is
> wrong, this doesn't solve the problem of determining an
> appropriate gid.
> 
> With this change, the entering process can first enter the
> namespace and then safely inspect the namespace's
> properties, e.g. through /proc/self/{uid_map,gid_map},
> assuming that the namespace owner doesn't have access to
> uid 0.
> 
> Changed in v2: The caller needs to be capable in the
> namespace into which tcred's uids/gids can be mapped.
> 
> Signed-off-by: Jann Horn <jann@thejh.net>
> ---
>  kernel/ptrace.c | 33 ++++++++++++++++++++++++++++-----
>  1 file changed, 28 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/ptrace.c b/kernel/ptrace.c
> index b760bae..260a08d 100644
> --- a/kernel/ptrace.c
> +++ b/kernel/ptrace.c
> @@ -20,6 +20,7 @@
>  #include <linux/uio.h>
>  #include <linux/audit.h>
>  #include <linux/pid_namespace.h>
> +#include <linux/user_namespace.h>
>  #include <linux/syscalls.h>
>  #include <linux/uaccess.h>
>  #include <linux/regset.h>
> @@ -207,12 +208,34 @@ static int ptrace_check_attach(struct task_struct *child, bool ignore_state)
>  	return ret;
>  }
>  
> -static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
> +static bool ptrace_has_cap(const struct cred *tcred, unsigned int mode)
>  {
> +	struct user_namespace *tns = tcred->user_ns;
> +
> +	/* When a root-owned process enters a user namespace created by a
> +	 * malicious user, the user shouldn't be able to execute code under
> +	 * uid 0 by attaching to the root-owned process via ptrace.
> +	 * Therefore, similar to the capable_wrt_inode_uidgid() check,
> +	 * verify that all the uids and gids of the target process are
> +	 * mapped into a namespace below the current one in which the caller
> +	 * is capable.
> +	 * No fsuid/fsgid check because __ptrace_may_access doesn't do it
> +	 * either.
> +	 */
> +	while (
> +	    !kuid_has_mapping(tns, tcred->euid) ||
> +	    !kuid_has_mapping(tns, tcred->suid) ||
> +	    !kuid_has_mapping(tns, tcred->uid)  ||
> +	    !kgid_has_mapping(tns, tcred->egid) ||
> +	    !kgid_has_mapping(tns, tcred->sgid) ||
> +	    !kgid_has_mapping(tns, tcred->gid)) {
> +		tns = tns->parent;

Sorry, i can't quite remember - is there a way for a task in init_user_ns to have
INVALID_UID | INVALID_GID ?  I.e. any point in breaking here if tns == &init_user_n?

> +	}
> +
>  	if (mode & PTRACE_MODE_NOAUDIT)
> -		return has_ns_capability_noaudit(current, ns, CAP_SYS_PTRACE);
> +		return has_ns_capability_noaudit(current, tns, CAP_SYS_PTRACE);
>  	else
> -		return has_ns_capability(current, ns, CAP_SYS_PTRACE);
> +		return has_ns_capability(current, tns, CAP_SYS_PTRACE);
>  }
>  
>  /* Returns 0 on success, -errno on denial. */
> @@ -241,7 +264,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
>  	    gid_eq(cred->gid, tcred->sgid) &&
>  	    gid_eq(cred->gid, tcred->gid))
>  		goto ok;
> -	if (ptrace_has_cap(tcred->user_ns, mode))
> +	if (ptrace_has_cap(tcred, mode))
>  		goto ok;
>  	rcu_read_unlock();
>  	return -EPERM;
> @@ -252,7 +275,7 @@ ok:
>  		dumpable = get_dumpable(task->mm);
>  	rcu_read_lock();
>  	if (dumpable != SUID_DUMP_USER &&
> -	    !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
> +	    !ptrace_has_cap(__task_cred(task), mode)) {
>  		rcu_read_unlock();
>  		return -EPERM;
>  	}
> -- 
> 2.1.4
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/