From 12ae2c81b21cfaa193db2faf035d495807edc3a7 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 14:50:59 +0100 Subject: clone: add CLONE_AUTOREAP Add a new clone3() flag CLONE_AUTOREAP that makes a child process auto-reap on exit without ever becoming a zombie. This is a per-process property in contrast to the existing auto-reap mechanism via SA_NOCLDWAIT or SIG_IGN for SIGCHLD which applies to all children of a given parent. Currently the only way to automatically reap children is to set SA_NOCLDWAIT or SIG_IGN on SIGCHLD. This is a parent-scoped property affecting all children which makes it unsuitable for libraries or applications that need selective auto-reaping of specific children while still being able to wait() on others. CLONE_AUTOREAP stores an autoreap flag in the child's signal_struct. When the child exits do_notify_parent() checks this flag and causes exit_notify() to transition the task directly to EXIT_DEAD. Since the flag lives on the child it survives reparenting: if the original parent exits and the child is reparented to a subreaper or init the child still auto-reaps when it eventually exits. CLONE_AUTOREAP can be combined with CLONE_PIDFD to allow the parent to monitor the child's exit via poll() and retrieve exit status via PIDFD_GET_INFO. Without CLONE_PIDFD it provides a fire-and-forget pattern where the parent simply doesn't care about the child's exit status. No exit signal is delivered so exit_signal must be zero. CLONE_AUTOREAP is rejected in combination with CLONE_PARENT. If a CLONE_AUTOREAP child were to clone(CLONE_PARENT) the new grandchild would inherit exit_signal == 0 from the autoreap parent's group leader but without signal->autoreap. This grandchild would become a zombie that never sends a signal and is never autoreaped - confusing and arguably broken behavior. The flag is not inherited by the autoreap process's own children. Each child that should be autoreaped must be explicitly created with CLONE_AUTOREAP. Link: https://github.com/uapi-group/kernel-features/issues/45 Link: https://patch.msgid.link/20260226-work-pidfs-autoreap-v5-1-d148b984a989@kernel.org Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- kernel/fork.c | 17 ++++++++++++++++- kernel/ptrace.c | 3 ++- kernel/signal.c | 4 ++++ 3 files changed, 22 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index e832da9d15a4..10549574fda6 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2028,6 +2028,18 @@ __latent_entropy struct task_struct *copy_process( return ERR_PTR(-EINVAL); } + if (clone_flags & CLONE_AUTOREAP) { + if (clone_flags & CLONE_THREAD) + return ERR_PTR(-EINVAL); + if (clone_flags & CLONE_PARENT) + return ERR_PTR(-EINVAL); + if (args->exit_signal) + return ERR_PTR(-EINVAL); + } + + if ((clone_flags & CLONE_PARENT) && current->signal->autoreap) + return ERR_PTR(-EINVAL); + /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple @@ -2435,6 +2447,8 @@ __latent_entropy struct task_struct *copy_process( */ p->signal->has_child_subreaper = p->real_parent->signal->has_child_subreaper || p->real_parent->signal->is_child_subreaper; + if (clone_flags & CLONE_AUTOREAP) + p->signal->autoreap = 1; list_add_tail(&p->sibling, &p->real_parent->children); list_add_tail_rcu(&p->tasks, &init_task.tasks); attach_pid(p, PIDTYPE_TGID); @@ -2897,7 +2911,8 @@ 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_LEGACY_FLAGS | CLONE_CLEAR_SIGHAND | CLONE_INTO_CGROUP | + CLONE_AUTOREAP)) return false; /* diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 392ec2f75f01..68c17daef8d4 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -549,7 +549,8 @@ static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p) if (!dead && thread_group_empty(p)) { if (!same_thread_group(p->real_parent, tracer)) dead = do_notify_parent(p, p->exit_signal); - else if (ignoring_children(tracer->sighand)) { + else if (ignoring_children(tracer->sighand) || + p->signal->autoreap) { __wake_up_parent(p, tracer); dead = true; } diff --git a/kernel/signal.c b/kernel/signal.c index d65d0fe24bfb..e61f39fa8c8a 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -2251,6 +2251,10 @@ bool do_notify_parent(struct task_struct *tsk, int sig) if (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) sig = 0; } + if (!tsk->ptrace && tsk->signal->autoreap) { + autoreap = true; + sig = 0; + } /* * Send with __send_signal as si_pid and si_uid are in the * parent's namespaces. -- cgit v1.2.3 From 24baca56fafc33d4fb77cd9858a48c734183cb22 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 14:51:00 +0100 Subject: clone: add CLONE_NNP 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. Link: https://patch.msgid.link/20260226-work-pidfs-autoreap-v5-2-d148b984a989@kernel.org Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- kernel/fork.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 10549574fda6..736798e4005a 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2040,6 +2040,11 @@ __latent_entropy struct task_struct *copy_process( if ((clone_flags & CLONE_PARENT) && current->signal->autoreap) 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 @@ -2424,6 +2429,9 @@ __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); @@ -2912,7 +2920,7 @@ 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; /* -- cgit v1.2.3 From c8134b5f13ae959de2b3c8cc278e2602b0857345 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Thu, 26 Feb 2026 14:51:01 +0100 Subject: pidfd: add CLONE_PIDFD_AUTOKILL Add a new clone3() flag CLONE_PIDFD_AUTOKILL that ties a child's lifetime to the pidfd returned from clone3(). When the last reference to the struct file created by clone3() is closed the kernel sends SIGKILL to the child. A pidfd obtained via pidfd_open() for the same process does not keep the child alive and does not trigger autokill - only the specific struct file from clone3() has this property. This is useful for container runtimes, service managers, and sandboxed subprocess execution - any scenario where the child must die if the parent crashes or abandons the pidfd. CLONE_PIDFD_AUTOKILL requires both CLONE_PIDFD (the whole point is tying lifetime to the pidfd file) and CLONE_AUTOREAP (a killed child with no one to reap it would become a zombie). CLONE_THREAD is rejected because autokill targets a process not a thread. The clone3 pidfd is identified by the PIDFD_AUTOKILL file flag set on the struct file at clone3() time. The pidfs .release handler checks this flag and sends SIGKILL via do_send_sig_info(SIGKILL, SEND_SIG_PRIV, ...) only when it is set. Files from pidfd_open() or open_by_handle_at() are distinct struct files that do not carry this flag. dup()/fork() share the same struct file so they extend the child's lifetime until the last reference drops. CLONE_PIDFD_AUTOKILL uses a privilege model based on CLONE_NNP: without CLONE_NNP the child could escalate privileges via setuid/setgid exec after being spawned, so the caller must have CAP_SYS_ADMIN in its user namespace. With CLONE_NNP the child can never gain new privileges so unprivileged usage is allowed. This is a deliberate departure from the pdeath_signal model which is reset during secureexec and commit_creds() rendering it useless for container runtimes that need to deprivilege themselves. Link: https://patch.msgid.link/20260226-work-pidfs-autoreap-v5-3-d148b984a989@kernel.org Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- kernel/fork.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 736798e4005a..99a6cb4e7ab0 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2045,6 +2045,24 @@ __latent_entropy struct task_struct *copy_process( return ERR_PTR(-EINVAL); } + if (clone_flags & CLONE_PIDFD_AUTOKILL) { + if (!(clone_flags & CLONE_PIDFD)) + return ERR_PTR(-EINVAL); + if (!(clone_flags & CLONE_AUTOREAP)) + return ERR_PTR(-EINVAL); + if (clone_flags & CLONE_THREAD) + return ERR_PTR(-EINVAL); + /* + * Without CLONE_NNP the child could escalate privileges + * after being spawned, so require CAP_SYS_ADMIN. + * With CLONE_NNP the child can't gain new privileges, + * so allow unprivileged usage. + */ + if (!(clone_flags & CLONE_NNP) && + !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) + return ERR_PTR(-EPERM); + } + /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple @@ -2267,13 +2285,18 @@ __latent_entropy struct task_struct *copy_process( * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { - int flags = (clone_flags & CLONE_THREAD) ? PIDFD_THREAD : 0; + unsigned flags = PIDFD_STALE; + + if (clone_flags & CLONE_THREAD) + flags |= PIDFD_THREAD; + if (clone_flags & CLONE_PIDFD_AUTOKILL) + flags |= PIDFD_AUTOKILL; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ - retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile); + retval = pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; @@ -2920,7 +2943,7 @@ 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_NNP)) + CLONE_AUTOREAP | CLONE_NNP | CLONE_PIDFD_AUTOKILL)) return false; /* -- cgit v1.2.3