pidfs: get rid of __pidfd_prepare()

Fold it into pidfd_prepare() and rename PIDFD_CLONE to PIDFD_STALE to
indicate that the passed pid might not have task linkage and no explicit
check for that should be performed.

Link: https://lore.kernel.org/20250425-work-pidfs-net-v2-3-450a19461e75@kernel.org
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Reviewed-by: David Rheinsberg <david@readahead.eu>
Signed-off-by: Christian Brauner <brauner@kernel.org>

1 files changed, 29 insertions, 54 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index f7403e1fb0d4..1d95f4dae327 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2036,54 +2036,10 @@ static inline void rcu_copy_process(struct task_struct *p)
 }
 
 /**
- * __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
- * @ret: Where to return the file for the pidfd.
- *
- * 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)
-{
-	struct file *pidfd_file;
-
-	CLASS(get_unused_fd, pidfd)(O_CLOEXEC);
-	if (pidfd < 0)
-		return pidfd;
-
-	pidfd_file = pidfs_alloc_file(pid, flags | O_RDWR);
-	if (IS_ERR(pidfd_file))
-		return PTR_ERR(pidfd_file);
-
-	*ret = pidfd_file;
-	return take_fd(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
- * @ret: Where to return the pidfd.
+ * @ret_file: return the new pidfs file
  *
  * 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.
@@ -2106,16 +2062,26 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re
  *         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)
+int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret_file)
 {
+	struct file *pidfs_file;
+
 	/*
-	 * While holding the pidfd waitqueue lock removing the task
-	 * linkage for the thread-group leader pid (PIDTYPE_TGID) isn't
-	 * possible. Thus, if there's still task linkage for PIDTYPE_PID
-	 * not having thread-group leader linkage for the pid means it
-	 * wasn't a thread-group leader in the first place.
+	 * PIDFD_STALE is only allowed to be passed if the caller knows
+	 * that @pid is already registered in pidfs and thus
+	 * PIDFD_INFO_EXIT information is guaranteed to be available.
 	 */
-	scoped_guard(spinlock_irq, &pid->wait_pidfd.lock) {
+	if (!(flags & PIDFD_STALE)) {
+		/*
+		 * While holding the pidfd waitqueue lock removing the
+		 * task linkage for the thread-group leader pid
+		 * (PIDTYPE_TGID) isn't possible. Thus, if there's still
+		 * task linkage for PIDTYPE_PID not having thread-group
+		 * leader linkage for the pid means it wasn't a
+		 * thread-group leader in the first place.
+		 */
+		guard(spinlock_irq)(&pid->wait_pidfd.lock);
+
 		/* Task has already been reaped. */
 		if (!pid_has_task(pid, PIDTYPE_PID))
 			return -ESRCH;
@@ -2128,7 +2094,16 @@ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret)
 			return -ENOENT;
 	}
 
-	return __pidfd_prepare(pid, flags, ret);
+	CLASS(get_unused_fd, pidfd)(O_CLOEXEC);
+	if (pidfd < 0)
+		return pidfd;
+
+	pidfs_file = pidfs_alloc_file(pid, flags | O_RDWR);
+	if (IS_ERR(pidfs_file))
+		return PTR_ERR(pidfs_file);
+
+	*ret_file = pidfs_file;
+	return take_fd(pidfd);
 }
 
 static void __delayed_free_task(struct rcu_head *rhp)
@@ -2477,7 +2452,7 @@ __latent_entropy struct task_struct *copy_process(
 		 * Note that no task has been attached to @pid yet indicate
 		 * that via CLONE_PIDFD.
 		 */
-		retval = __pidfd_prepare(pid, flags | PIDFD_CLONE, &pidfile);
+		retval = pidfd_prepare(pid, flags | PIDFD_STALE, &pidfile);
 		if (retval < 0)
 			goto bad_fork_free_pid;
 		pidfd = retval;