1 files changed, 69 insertions, 0 deletions
diff --git a/kernel/pid.c b/kernel/pid.c
index 6ce3a95968f7..8e6f50053364 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -37,6 +37,8 @@
 #include <linux/syscalls.h>
 #include <linux/proc_ns.h>
 #include <linux/proc_fs.h>
+#include <linux/anon_inodes.h>
+#include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/idr.h>
 
@@ -452,6 +454,73 @@ struct pid *find_ge_pid(int nr, struct pid_namespace *ns)
 	return idr_get_next(&ns->idr, &nr);
 }
 
+/**
+ * pidfd_create() - Create a new pid file descriptor.
+ *
+ * @pid:  struct pid that the pidfd will reference
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set.
+ *
+ * Note, that this function can only be called after the fd table has
+ * been unshared to avoid leaking the pidfd to the new process.
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ *         On error, a negative errno number will be returned.
+ */
+static int pidfd_create(struct pid *pid)
+{
+	int fd;
+
+	fd = anon_inode_getfd("[pidfd]", &pidfd_fops, get_pid(pid),
+			      O_RDWR | O_CLOEXEC);
+	if (fd < 0)
+		put_pid(pid);
+
+	return fd;
+}
+
+/**
+ * pidfd_open() - Open new pid file descriptor.
+ *
+ * @pid:   pid for which to retrieve a pidfd
+ * @flags: flags to pass
+ *
+ * This creates a new pid file descriptor with the O_CLOEXEC flag set for
+ * the process identified by @pid. Currently, the process identified by
+ * @pid must be a thread-group leader. This restriction currently exists
+ * for all aspects of pidfds including pidfd creation (CLONE_PIDFD cannot
+ * be used with CLONE_THREAD) and pidfd polling (only supports thread group
+ * leaders).
+ *
+ * Return: On success, a cloexec pidfd is returned.
+ *         On error, a negative errno number will be returned.
+ */
+SYSCALL_DEFINE2(pidfd_open, pid_t, pid, unsigned int, flags)
+{
+	int fd, ret;
+	struct pid *p;
+
+	if (flags)
+		return -EINVAL;
+
+	if (pid <= 0)
+		return -EINVAL;
+
+	p = find_get_pid(pid);
+	if (!p)
+		return -ESRCH;
+
+	ret = 0;
+	rcu_read_lock();
+	if (!pid_task(p, PIDTYPE_TGID))
+		ret = -EINVAL;
+	rcu_read_unlock();
+
+	fd = ret ?: pidfd_create(p);
+	put_pid(p);
+	return fd;
+}
+
 void __init pid_idr_init(void)
 {
 	/* Verify no one has done anything silly: */