Add a new clone3() flag CLONE_NNP that sets no_new_privs on the child
process at clone time. This is analogous to prctl(PR_SET_NO_NEW_PRIVS)
but applied at process creation rather than requiring a separate step
after the child starts running.

CLONE_NNP is rejected with CLONE_THREAD. It's conceptually a lot simpler
if the whole thread-group is forced into NNP and not have single threads
running around with NNP.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/uapi/linux/sched.h |  1 +
 kernel/fork.c              | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 8a22ea640817..7b1b87473ebb 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -37,6 +37,7 @@
 #define CLONE_CLEAR_SIGHAND 0x100000000ULL /* Clear any signal handler and reset to SIG_DFL. */
 #define CLONE_INTO_CGROUP 0x200000000ULL /* Clone into a specific cgroup given the right permissions. */
 #define CLONE_AUTOREAP 0x400000000ULL /* Auto-reap child on exit. */
+#define CLONE_NNP 0x1000000000ULL /* Set no_new_privs on child. */
 
 /*
  * cloning flags intersect with CSIGNAL so can be used with unshare and clone3
diff --git a/kernel/fork.c b/kernel/fork.c
index 0dedf2999f0c..a3202ee278d8 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2037,6 +2037,11 @@ __latent_entropy struct task_struct *copy_process(
 			return ERR_PTR(-EINVAL);
 	}
 
+	if (clone_flags & CLONE_NNP) {
+		if (clone_flags & CLONE_THREAD)
+			return ERR_PTR(-EINVAL);
+	}
+
 	/*
 	 * Force any signals received before this point to be delivered
 	 * before the fork happens.  Collect up signals sent to multiple
@@ -2421,6 +2426,9 @@ __latent_entropy struct task_struct *copy_process(
 	 */
 	copy_seccomp(p);
 
+	if (clone_flags & CLONE_NNP)
+		task_set_no_new_privs(p);
+
 	init_task_pid_links(p);
 	if (likely(p->pid)) {
 		ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace);
@@ -2909,7 +2917,7 @@ static bool clone3_args_valid(struct kernel_clone_args *kargs)
 	/* Verify that no unknown flags are passed along. */
 	if (kargs->flags &
 	    ~(CLONE_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP |
-	      CLONE_AUTOREAP))
+	      CLONE_AUTOREAP | CLONE_NNP))
 		return false;
 
 	/*

-- 
2.47.3