1 files changed, 87 insertions, 11 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index d6cd5849eb51..bfe73db1c26c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1961,6 +1961,91 @@ const struct file_operations pidfd_fops = {
 #endif
 };
 
+/**
+ * __pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
+ * @pid:   the struct pid for which to create a pidfd
+ * @flags: flags of the new @pidfd
+ * @pidfd: the pidfd to return
+ *
+ * Allocate a new file that stashes @pid and reserve a new pidfd number in the
+ * caller's file descriptor table. The pidfd is reserved but not installed yet.
+
+ * The helper doesn't perform checks on @pid which makes it useful for pidfds
+ * created via CLONE_PIDFD where @pid has no task attached when the pidfd and
+ * pidfd file are prepared.
+ *
+ * If this function returns successfully the caller is responsible to either
+ * call fd_install() passing the returned pidfd and pidfd file as arguments in
+ * order to install the pidfd into its file descriptor table or they must use
+ * put_unused_fd() and fput() on the returned pidfd and pidfd file
+ * respectively.
+ *
+ * This function is useful when a pidfd must already be reserved but there
+ * might still be points of failure afterwards and the caller wants to ensure
+ * that no pidfd is leaked into its file descriptor table.
+ *
+ * Return: On success, a reserved pidfd is returned from the function and a new
+ *         pidfd file is returned in the last argument to the function. On
+ *         error, a negative error code is returned from the function and the
+ *         last argument remains unchanged.
+ */
+static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
+{
+	int pidfd;
+	struct file *pidfd_file;
+
+	if (flags & ~(O_NONBLOCK | O_RDWR | O_CLOEXEC))
+		return -EINVAL;
+
+	pidfd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+	if (pidfd < 0)
+		return pidfd;
+
+	pidfd_file = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
+					flags | O_RDWR | O_CLOEXEC);
+	if (IS_ERR(pidfd_file)) {
+		put_unused_fd(pidfd);
+		return PTR_ERR(pidfd_file);
+	}
+	get_pid(pid); /* held by pidfd_file now */
+	*ret = pidfd_file;
+	return pidfd;
+}
+
+/**
+ * pidfd_prepare - allocate a new pidfd_file and reserve a pidfd
+ * @pid:   the struct pid for which to create a pidfd
+ * @flags: flags of the new @pidfd
+ * @pidfd: the pidfd to return
+ *
+ * Allocate a new file that stashes @pid and reserve a new pidfd number in the
+ * caller's file descriptor table. The pidfd is reserved but not installed yet.
+ *
+ * The helper verifies that @pid is used as a thread group leader.
+ *
+ * If this function returns successfully the caller is responsible to either
+ * call fd_install() passing the returned pidfd and pidfd file as arguments in
+ * order to install the pidfd into its file descriptor table or they must use
+ * put_unused_fd() and fput() on the returned pidfd and pidfd file
+ * respectively.
+ *
+ * This function is useful when a pidfd must already be reserved but there
+ * might still be points of failure afterwards and the caller wants to ensure
+ * that no pidfd is leaked into its file descriptor table.
+ *
+ * Return: On success, a reserved pidfd is returned from the function and a new
+ *         pidfd file is returned in the last argument to the function. On
+ *         error, a negative error code is returned from the function and the
+ *         last argument remains unchanged.
+ */
+int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
+{
+	if (!pid || !pid_has_task(pid, PIDTYPE_TGID))
+		return -EINVAL;
+
+	return __pidfd_prepare(pid, flags, ret);
+}
+
 static void __delayed_free_task(struct rcu_head *rhp)
 {
 	struct task_struct *tsk = container_of(rhp, struct task_struct, rcu);
@@ -2309,21 +2394,12 @@ __latent_entropy struct task_struct *copy_process(
 	 * if the fd table isn't shared).
 	 */
 	if (clone_flags & CLONE_PIDFD) {
-		retval = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+		/* Note that no task has been attached to @pid yet. */
+		retval = __pidfd_prepare(pid, O_RDWR | O_CLOEXEC, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
-
 		pidfd = retval;
 
-		pidfile = anon_inode_getfile("[pidfd]", &pidfd_fops, pid,
-					      O_RDWR | O_CLOEXEC);
-		if (IS_ERR(pidfile)) {
-			put_unused_fd(pidfd);
-			retval = PTR_ERR(pidfile);
-			goto bad_fork_free_pid;
-		}
-		get_pid(pid);	/* held by pidfile now */
-
 		retval = put_user(pidfd, args->pidfd);
 		if (retval)
 			goto bad_fork_put_pidfd;