[RFC PATCH v5 15/25] rootns: Add ROOTNS_KILL ioctl
From: Jarkko Sakkinen
Date: Fri Nov 20 2026 - 19:10:50 EST
Signaling every process inside a container from userspace via /proc is
racy against concurrent fork() calls.
Add the ROOTNS_KILL ioctl to require an ancestor active PID namespace,
walk the root namespace's PID namespace IDR under tasklist_lock, and
deliver a validated signal once to each thread group including in-flight
forks, aggregating per-process delivery results.
Signed-off-by: Jarkko Sakkinen <jarkko@xxxxxxxxxx>
---
include/uapi/linux/rootns.h | 13 ++++++++++
kernel/rootns.c | 52 +++++++++++++++++++++++++++++++++++++
2 files changed, 65 insertions(+)
diff --git a/include/uapi/linux/rootns.h b/include/uapi/linux/rootns.h
index 3fd215185398..acd91d895c63 100644
--- a/include/uapi/linux/rootns.h
+++ b/include/uapi/linux/rootns.h
@@ -67,4 +67,17 @@ struct rootns_wait_args {
*/
#define ROOTNS_WAIT _IOWR(ROOTNS_IOCTL_MAGIC, 0x02, struct rootns_wait_args)
+/**
+ * DOC: ROOTNS_KILL
+ *
+ * ``ioctl(rootnsfd, ROOTNS_KILL, sig)`` walks the target root namespace's PID
+ * namespace IDR under ``tasklist_lock`` and delivers ``sig`` (or ``0`` for a
+ * permission check) once to each member thread group.
+ *
+ * Returns ``0`` if at least one thread group was signaled, or ``-1`` with
+ * ``errno`` set to ``EXDEV`` if the caller's active PID namespace is not an
+ * ancestor or ``ESRCH`` if the ``rootns`` is not running or has no members.
+ */
+#define ROOTNS_KILL _IO(ROOTNS_IOCTL_MAGIC, 0x03)
+
#endif /* _UAPI_LINUX_ROOTNS_H */
diff --git a/kernel/rootns.c b/kernel/rootns.c
index cb74ddc8363c..5ae975604571 100644
--- a/kernel/rootns.c
+++ b/kernel/rootns.c
@@ -158,6 +158,53 @@ static long rootns_wait(struct rootns *rootns, void __user *uarg)
return ret;
}
+static int rootns_kill_members(struct rootns *rootns, int sig)
+{
+ struct pid_namespace *pid_ns = rootns->ns->pid_ns_for_children;
+ bool any_success = false;
+ bool any_other = false;
+ bool any_perm = false;
+ int other_err = 0;
+ struct pid *pid;
+ int nr;
+
+ if (!pidns_is_ancestor(pid_ns, task_active_pid_ns(current)))
+ return -EXDEV;
+ if (READ_ONCE(rootns->state) != ROOTNS_RUNNING)
+ return -ESRCH;
+
+ scoped_guard(rcu) {
+ read_lock(&tasklist_lock);
+ idr_for_each_entry(&pid_ns->idr, pid, nr) {
+ struct task_struct *task = pid_task(pid, PIDTYPE_TGID);
+ int err;
+
+ if (!task)
+ continue;
+
+ err = group_send_sig_info(sig, SEND_SIG_NOINFO, task,
+ PIDTYPE_MAX);
+ if (!err) {
+ any_success = true;
+ } else if (err == -EPERM) {
+ any_perm = true;
+ } else if (err != -ESRCH && !any_other) {
+ any_other = true;
+ other_err = err;
+ }
+ }
+ read_unlock(&tasklist_lock);
+ }
+
+ if (any_success)
+ return 0;
+ if (any_other)
+ return other_err;
+ if (any_perm)
+ return -EPERM;
+ return -ESRCH;
+}
+
static long rootns_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
struct rootns *rootns = file->private_data;
@@ -167,6 +214,10 @@ static long rootns_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
return rootns_get_nsfd(rootns, arg);
case ROOTNS_WAIT:
return rootns_wait(rootns, (void __user *)arg);
+ case ROOTNS_KILL:
+ if (arg > INT_MAX || !valid_signal(arg))
+ return -EINVAL;
+ return rootns_kill_members(rootns, arg);
default:
return -ENOIOCTLCMD;
}
@@ -180,6 +231,7 @@ static long rootns_compat_ioctl(struct file *file, unsigned int cmd,
case ROOTNS_WAIT:
return rootns_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
case ROOTNS_GET_NSFD:
+ case ROOTNS_KILL:
return rootns_ioctl(file, cmd, arg);
default:
return -ENOIOCTLCMD;
--
2.47.3