mm: Add a user_ns owner to mm_struct and fix ptrace permission checks

During exec dumpable is cleared if the file that is being executed is
not readable by the user executing the file.  A bug in
ptrace_may_access allows reading the file if the executable happens to
enter into a subordinate user namespace (aka clone(CLONE_NEWUSER),
unshare(CLONE_NEWUSER), or setns(fd, CLONE_NEWUSER).

This problem is fixed with only necessary userspace breakage by adding
a user namespace owner to mm_struct, captured at the time of exec, so
it is clear in which user namespace CAP_SYS_PTRACE must be present in
to be able to safely give read permission to the executable.

The function ptrace_may_access is modified to verify that the ptracer
has CAP_SYS_ADMIN in task->mm->user_ns instead of task->cred->user_ns.
This ensures that if the task changes it's cred into a subordinate
user namespace it does not become ptraceable.

The function ptrace_attach is modified to only set PT_PTRACE_CAP when
CAP_SYS_PTRACE is held over task->mm->user_ns.  The intent of
PT_PTRACE_CAP is to be a flag to note that whatever permission changes
the task might go through the tracer has sufficient permissions for
it not to be an issue.  task->cred->user_ns is always the same
as or descendent of mm->user_ns.  Which guarantees that having
CAP_SYS_PTRACE over mm->user_ns is the worst case for the tasks
credentials.

To prevent regressions mm->dumpable and mm->user_ns are not considered
when a task has no mm.  As simply failing ptrace_may_attach causes
regressions in privileged applications attempting to read things
such as /proc/<pid>/stat

Cc: stable@vger.kernel.org
Acked-by: Kees Cook <keescook@chromium.org>
Tested-by: Cyrill Gorcunov <gorcunov@openvz.org>
Fixes: 8409cca70561 ("userns: allow ptrace from non-init user namespaces")
Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>

1 files changed, 11 insertions, 15 deletions

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index e6474f7272ec..282821557183 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -220,7 +220,7 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode)
 static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 {
 	const struct cred *cred = current_cred(), *tcred;
-	int dumpable = 0;
+	struct mm_struct *mm;
 	kuid_t caller_uid;
 	kgid_t caller_gid;
 
@@ -271,16 +271,11 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	return -EPERM;
 ok:
 	rcu_read_unlock();
-	smp_rmb();
-	if (task->mm)
-		dumpable = get_dumpable(task->mm);
-	rcu_read_lock();
-	if (dumpable != SUID_DUMP_USER &&
-	    !ptrace_has_cap(__task_cred(task)->user_ns, mode)) {
-		rcu_read_unlock();
-		return -EPERM;
-	}
-	rcu_read_unlock();
+	mm = task->mm;
+	if (mm &&
+	    ((get_dumpable(mm) != SUID_DUMP_USER) &&
+	     !ptrace_has_cap(mm->user_ns, mode)))
+	    return -EPERM;
 
 	return security_ptrace_access_check(task, mode);
 }
@@ -331,6 +326,11 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	task_lock(task);
 	retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
+	if (!retval) {
+		struct mm_struct *mm = task->mm;
+		if (mm && ns_capable(mm->user_ns, CAP_SYS_PTRACE))
+			flags |= PT_PTRACE_CAP;
+	}
 	task_unlock(task);
 	if (retval)
 		goto unlock_creds;
@@ -344,10 +344,6 @@ static int ptrace_attach(struct task_struct *task, long request,
 
 	if (seize)
 		flags |= PT_SEIZED;
-	rcu_read_lock();
-	if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE))
-		flags |= PT_PTRACE_CAP;
-	rcu_read_unlock();
 	task->ptrace = flags;
 
 	__ptrace_link(task, current);