From 17f1b08acf50c0bfb02e21623e53e7e575612b67 Mon Sep 17 00:00:00 2001 From: Christian Brauner Date: Fri, 11 Apr 2025 15:22:45 +0200 Subject: [PATCH] pidfs: ensure consistent ENOENT/ESRCH reporting In a prior patch series we tried to cleanly differentiate between: (1) The task has already been reaped. (2) The caller requested a pidfd for a thread-group leader but the pid actually references a struct pid that isn't used as a thread-group leader. as this was causing issues for non-threaded workloads. But there's cases where the current simple logic is wrong. Specifically, if the pid was a leader pid and the check races with __unhash_process(). Stabilize this by using the pidfd waitqueue lock. Link: https://lore.kernel.org/20250411-work-pidfs-enoent-v2-2-60b2d3bb545f@kernel.org Reviewed-by: Oleg Nesterov Signed-off-by: Christian Brauner --- kernel/fork.c | 34 ++++++++++++++++------------------ 1 file changed, 16 insertions(+), 18 deletions(-) diff --git a/kernel/fork.c b/kernel/fork.c index 4a2080b968c8..f7403e1fb0d4 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -2108,28 +2108,26 @@ static int __pidfd_prepare(struct pid *pid, unsigned int flags, struct file **re */ int pidfd_prepare(struct pid *pid, unsigned int flags, struct file **ret) { - int err = 0; - - if (!(flags & PIDFD_THREAD)) { + /* + * 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. + */ + scoped_guard(spinlock_irq, &pid->wait_pidfd.lock) { + /* Task has already been reaped. */ + if (!pid_has_task(pid, PIDTYPE_PID)) + return -ESRCH; /* - * If this is struct pid isn't used as a thread-group - * leader pid but the caller requested to create a - * thread-group leader pidfd then report ENOENT to the - * caller as a hint. + * If this struct pid isn't used as a thread-group + * leader but the caller requested to create a + * thread-group leader pidfd then report ENOENT. */ - if (!pid_has_task(pid, PIDTYPE_TGID)) - err = -ENOENT; + if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID)) + return -ENOENT; } - /* - * If this wasn't a thread-group leader struct pid or the task - * got reaped in the meantime report -ESRCH to userspace. - */ - if (!pid_has_task(pid, PIDTYPE_PID)) - err = -ESRCH; - if (err) - return err; - return __pidfd_prepare(pid, flags, ret); } -- 2.25.1