backport NO_NEW_PRIVS

fs/exec.c

@@ -1227,6 +1227,9 @@ int check_unsafe_exec(struct linux_binprm *bprm)
 
 	bprm->unsafe = tracehook_unsafe_exec(p);
 
+	if (current->no_new_privs)
+		bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS;
+
 	n_fs = 1;
 	spin_lock(&p->fs->lock);
 	rcu_read_lock();
@@ -1270,7 +1273,8 @@ int prepare_binprm(struct linux_binprm *bprm)
 	bprm->cred->euid = current_euid();
 	bprm->cred->egid = current_egid();
 
-	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) {
+	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
+		!current->no_new_privs) {
 		/* Set-uid? */
 		if (mode & S_ISUID) {
 			bprm->per_clear |= PER_CLEAR_ON_SETID;

include/linux/prctl.h

@@ -102,4 +102,19 @@
 
 #define PR_MCE_KILL_GET 34
 
+/*
+ * If no_new_privs is set, then operations that grant new privileges (i.e.
+ * execve) will either fail or not grant them.  This affects suid/sgid,
+ * file capabilities, and LSMs.
+ *
+ * Operations that merely manipulate or drop existing privileges (setresuid,
+ * capset, etc.) will still work.  Drop those privileges if you want them gone.
+ *
+ * Changing LSM security domain is considered a new privilege.  So, for example,
+ * asking selinux for a specific new context (e.g. with runcon) will result
+ * in execve returning -EPERM.
+ */
+#define PR_SET_NO_NEW_PRIVS 38
+#define PR_GET_NO_NEW_PRIVS 39
+
 #endif /* _LINUX_PRCTL_H */

include/linux/sched.h

@@ -1300,6 +1300,8 @@ 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;

include/linux/security.h

@@ -129,6 +129,7 @@ struct request_sock;
 #define LSM_UNSAFE_SHARE	1
 #define LSM_UNSAFE_PTRACE	2
 #define LSM_UNSAFE_PTRACE_CAP	4
+#define LSM_UNSAFE_NO_NEW_PRIVS	8
 
 #ifdef CONFIG_MMU
 /*

kernel/sys.c

@@ -1800,6 +1800,16 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
 			else
 				error = PR_MCE_KILL_DEFAULT;
 			break;
+               case PR_SET_NO_NEW_PRIVS:
+                       if (arg2 != 1 || arg3 || arg4 || arg5)
+                               return -EINVAL;
+
+                       current->no_new_privs = 1;
+                       break;
+               case PR_GET_NO_NEW_PRIVS:
+                       if (arg2 || arg3 || arg4 || arg5)
+                               return -EINVAL;
+                       return current->no_new_privs ? 1 : 0;
 		default:
 			error = -EINVAL;
 			break;

security/apparmor/domain.c

@@ -360,6 +360,10 @@ int apparmor_bprm_set_creds(struct linux_binprm *bprm)
 	if (bprm->cred_prepared)
 		return 0;
 
+	/* XXX: no_new_privs is not usable with AppArmor yet */
+	if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)
+		return -EPERM;
+
 	cxt = bprm->cred->security;
 	BUG_ON(!cxt);
 

security/commoncap.c

@@ -526,14 +526,17 @@ int cap_bprm_set_creds(struct linux_binprm *bprm)
 
 
 	/* Don't let someone trace a set[ug]id/setpcap binary with the revised
-	 * credentials unless they have the appropriate permit
+	 * credentials unless they have the appropriate permit.
+	 *
+	 * In addition, if NO_NEW_PRIVS, then ensure we get no new privs.
 	 */
 	if ((new->euid != old->uid ||
 	     new->egid != old->gid ||
 	     !cap_issubset(new->cap_permitted, old->cap_permitted)) &&
 	    bprm->unsafe & ~LSM_UNSAFE_PTRACE_CAP) {
 		/* downgrade; they get no more than they had, and maybe less */
-		if (!capable(CAP_SETUID)) {
+		if (!capable(CAP_SETUID) ||
+		    (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)) {
 			new->euid = new->uid;
 			new->egid = new->gid;
 		}

security/selinux/hooks.c

@@ -2003,6 +2003,13 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 		new_tsec->sid = old_tsec->exec_sid;
 		/* Reset exec SID on execve. */
 		new_tsec->exec_sid = 0;
+
+		/*
+		 * Minimize confusion: if no_new_privs and a transition is
+		 * explicitly requested, then fail the exec.
+		 */
+		if (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS)
+			return -EPERM;
 	} else {
 		/* Check for a default transition on this program. */
 		rc = security_transition_sid(old_tsec->sid, isec->sid,
@@ -2015,7 +2022,8 @@ static int selinux_bprm_set_creds(struct linux_binprm *bprm)
 	COMMON_AUDIT_DATA_INIT(&ad, PATH);
 	ad.u.path = bprm->file->f_path;
 
-	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
+	if ((bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) ||
+	    (bprm->unsafe & LSM_UNSAFE_NO_NEW_PRIVS))
 		new_tsec->sid = old_tsec->sid;
 
 	if (new_tsec->sid == old_tsec->sid) {