[RFC PATCH v3 06/13] rootns: Add rootns_kill() system call

From: Jarkko Sakkinen

Date: Wed Nov 18 2026 - 14:40:46 EST


Signaling every process inside a container from userspace via /proc is
racy against concurrent fork() calls.

Add the rootns_kill() system call 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/linux/syscalls.h | 1 +
kernel/rootns.c | 71 ++++++++++++++++++++++++++++++++++++++++
kernel/sys_ni.c | 1 +
3 files changed, 73 insertions(+)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 60e9c4ff71e7..a854d248c8a3 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -1009,6 +1009,7 @@ asmlinkage long sys_lsm_list_modules(u64 __user *ids, u32 __user *size, u32 flag
asmlinkage long sys_rootns_create(unsigned int flags);
asmlinkage long sys_rootns_wait(int rootnsfd, int __user *status,
unsigned int options, struct rusage __user *ru);
+asmlinkage long sys_rootns_kill(int rootnsfd, int sig);

/*
* Architecture-specific system calls
diff --git a/kernel/rootns.c b/kernel/rootns.c
index 5582ff010ca5..32bb8ef5ed58 100644
--- a/kernel/rootns.c
+++ b/kernel/rootns.c
@@ -408,3 +408,74 @@ COMPAT_SYSCALL_DEFINE4(rootns_wait, int, rootnsfd,
return ret;
}
#endif
+
+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;
+}
+
+/**
+ * sys_rootns_kill - Send a signal to all thread groups in a root namespace
+ * @rootnsfd: Root namespace control file descriptor
+ * @sig: Signal number to deliver (or 0 for permission check)
+ *
+ * Walk the target root namespace's PID namespace IDR under ``tasklist_lock``
+ * and deliver @sig once to each member thread group.
+ *
+ * Return: 0 if at least one thread group was signaled, %-EXDEV if the caller's
+ * active PID namespace is not an ancestor, %-ESRCH if the rootns is not
+ * running or has no members, or negative error code on failure.
+ */
+SYSCALL_DEFINE2(rootns_kill, int, rootnsfd, int, sig)
+{
+ CLASS(fd, f)(rootnsfd);
+
+ if (fd_empty(f))
+ return -EBADF;
+ if (!is_rootns_file(fd_file(f)) || !valid_signal(sig))
+ return -EINVAL;
+
+ return rootns_kill_members(fd_file(f)->private_data, sig);
+}
diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c
index f9918d38107b..fba44c49ddbb 100644
--- a/kernel/sys_ni.c
+++ b/kernel/sys_ni.c
@@ -403,3 +403,4 @@ COND_SYSCALL(uprobe);
COND_SYSCALL(rootns_create);
COND_SYSCALL(rootns_wait);
COND_SYSCALL_COMPAT(rootns_wait);
+COND_SYSCALL(rootns_kill);
--
2.47.3