sched: move no_new_privs into new atomic flags

Since seccomp transitions between threads requires updates to the
no_new_privs flag to be atomic, the flag must be part of an atomic flag
set. This moves the nnp flag into a separate task field, and introduces
accessors.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: Andy Lutomirski <luto@amacapital.net>

Conflicts
	include/linux/sched.h
	kernel/sys.c

EDIT: Sumsung/klte tree already had a few changes from the original
patch, so they are ommited/removed from here.

Change-Id: If83d4adaca8920efd278ff4e3d80a024dd079cde
Signed-off-by: Kevin F. Haggerty <haggertk@lineageos.org>

include/linux/sched.h

@@ -1367,9 +1367,6 @@ struct task_struct {
 				 * execve */
 	unsigned in_iowait:1;
 
-	/* task may not gain privileges */
-	unsigned no_new_privs:1;
-
 	/* Revert to default priority/policy when forking */
 	unsigned sched_reset_on_fork:1;
 	unsigned sched_contributes_to_load:1;
@@ -1898,6 +1895,7 @@ extern int task_free_unregister(struct notifier_block *n);
 /* Per-process atomic flags. */
 #define PFA_SPREAD_PAGE  1      /* Spread page cache over cpuset */
 #define PFA_SPREAD_SLAB  2      /* Spread some slab caches over cpuset */
+#define PFA_NO_NEW_PRIVS 0x00000001	/* May not gain new privileges. */
 
 #define TASK_PFA_TEST(name, func)					\
 	static inline bool task_##func(struct task_struct *p)		\
@@ -1909,6 +1907,16 @@ extern int task_free_unregister(struct notifier_block *n);
 	static inline void task_clear_##func(struct task_struct *p)	\
 	{ clear_bit(PFA_##name, &p->atomic_flags); }
 
+static inline bool task_no_new_privs(struct task_struct *p)
+{
+	return test_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
+static inline void task_set_no_new_privs(struct task_struct *p)
+{
+	set_bit(PFA_NO_NEW_PRIVS, &p->atomic_flags);
+}
+
 /*
  * task->jobctl flags
  */

kernel/seccomp.c

@@ -262,7 +262,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog)
 	 * This avoids scenarios where unprivileged tasks can affect the
 	 * behavior of privileged children.
 	 */
-	if (!current->no_new_privs &&
+	if (!task_no_new_privs(current) &&
 	    security_capable_noaudit(current_cred(), current_user_ns(),
 				     CAP_SYS_ADMIN) != 0)
 		return -EACCES;

security/apparmor/domain.c

@@ -398,6 +398,11 @@ int apparmor_bprm_set_creds(struct linux_binprm *bprm)
 			new_profile = find_attach(ns, &ns->base.profiles, name);
 		if (!new_profile)
 			goto cleanup;
+		/*
+		 * NOTE: Domain transitions from unconfined are allowed
+		 * even when no_new_privs is set because this aways results
+		 * in a further reduction of permissions.
+		 */
 		goto apply;
 	}
 
@@ -459,6 +464,16 @@ int apparmor_bprm_set_creds(struct linux_binprm *bprm)
 		/* fail exec */
 		error = -EACCES;
 
+	/*
+	 * Policy has specified a domain transition, if no_new_privs then
+	 * fail the exec.
+	 */
+	if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS) {
+		aa_put_profile(new_profile);
+		error = -EPERM;
+		goto cleanup;
+	}
+
 	if (!new_profile)
 		goto audit;
 
@@ -613,6 +628,14 @@ int aa_change_hat(const char *hats[], int count, u64 token, bool permtest)
 	const char *target = NULL, *info = NULL;
 	int error = 0;
 
+	/*
+	 * Fail explicitly requested domain transitions if no_new_privs.
+	 * There is no exception for unconfined as change_hat is not
+	 * available.
+	 */
+	if (task_no_new_privs(current))
+		return -EPERM;
+
 	/* released below */
 	cred = get_current_cred();
 	cxt = cred->security;
@@ -754,6 +777,18 @@ int aa_change_profile(const char *ns_name, const char *hname, bool onexec,
 	cxt = cred->security;
 	profile = aa_cred_profile(cred);
 
+	/*
+	 * Fail explicitly requested domain transitions if no_new_privs
+	 * and not unconfined.
+	 * Domain transitions from unconfined are allowed even when
+	 * no_new_privs is set because this aways results in a reduction
+	 * of permissions.
+	 */
+	if (task_no_new_privs(current) && !unconfined(profile)) {
+		put_cred(cred);
+		return -EPERM;
+	}
+
 	if (ns_name) {
 		/* released below */
 		ns = aa_find_namespace(profile->ns, ns_name);