linux-kernel - Re: [RFC PATCH] pidfs: ensure consistent ENOENT/ESRCH reporting

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250409184040.GF32748@redhat.com>
Date: Wed, 9 Apr 2025 20:40:40 +0200
From: Oleg Nesterov <oleg@...hat.com>
To: Christian Brauner <brauner@...nel.org>
Cc: linux-fsdevel@...r.kernel.org, Jeff Layton <jlayton@...nel.org>,
	Lennart Poettering <lennart@...ttering.net>,
	Daan De Meyer <daan.j.demeyer@...il.com>,
	Mike Yuan <me@...dnzj.com>, linux-kernel@...r.kernel.org,
	Peter Ziljstra <peterz@...radead.org>
Subject: Re: [RFC PATCH] pidfs: ensure consistent ENOENT/ESRCH reporting

Christian,

I will actually read your patch tomorrow, but at first glance

On 04/09, Christian Brauner wrote:
>
> The seqcounter might be
> useful independent of pidfs.

Are you sure? ;) to me the new pid->pid_seq needs more justification...

Again, can't we use pid->wait_pidfd->lock if we want to avoid the
(minor) problem with the wrong ENOENT?

or even signal->siglock, although in this case we will need
pid_task() + lock_task_sighand()...

Oleg.

> Signed-off-by: Christian Brauner <brauner@...nel.org>
> ---
>  include/linux/pid.h |  1 +
>  kernel/exit.c       | 11 +++++++++++
>  kernel/fork.c       | 22 ++++++++++++----------
>  kernel/pid.c        |  1 +
>  4 files changed, 25 insertions(+), 10 deletions(-)
> 
> diff --git a/include/linux/pid.h b/include/linux/pid.h
> index 311ecebd7d56..b54a4c1ef602 100644
> --- a/include/linux/pid.h
> +++ b/include/linux/pid.h
> @@ -65,6 +65,7 @@ struct pid
>  	struct hlist_head inodes;
>  	/* wait queue for pidfd notifications */
>  	wait_queue_head_t wait_pidfd;
> +	seqcount_rwlock_t pid_seq;
>  	struct rcu_head rcu;
>  	struct upid numbers[];
>  };
> diff --git a/kernel/exit.c b/kernel/exit.c
> index 1b51dc099f1e..8050572fe682 100644
> --- a/kernel/exit.c
> +++ b/kernel/exit.c
> @@ -133,17 +133,28 @@ struct release_task_post {
>  static void __unhash_process(struct release_task_post *post, struct task_struct *p,
>  			     bool group_dead)
>  {
> +	struct pid *pid;
> +
> +	lockdep_assert_held_write(&tasklist_lock);
> +
>  	nr_threads--;
> +
> +	pid = task_pid(p);
> +	raw_write_seqcount_begin(&pid->pid_seq);
>  	detach_pid(post->pids, p, PIDTYPE_PID);
>  	if (group_dead) {
>  		detach_pid(post->pids, p, PIDTYPE_TGID);
>  		detach_pid(post->pids, p, PIDTYPE_PGID);
>  		detach_pid(post->pids, p, PIDTYPE_SID);
> +	}
> +	raw_write_seqcount_end(&pid->pid_seq);
>  
> +	if (group_dead) {
>  		list_del_rcu(&p->tasks);
>  		list_del_init(&p->sibling);
>  		__this_cpu_dec(process_counts);
>  	}
> +
>  	list_del_rcu(&p->thread_node);
>  }
>  
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 4a2080b968c8..1480bf6f5f38 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -2109,24 +2109,26 @@ 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;
> +	unsigned int seq;
>  
> -	if (!(flags & PIDFD_THREAD)) {
> +	do {
> +		seq = raw_seqcount_begin(&pid->pid_seq);
>  		/*
>  		 * 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 (!pid_has_task(pid, PIDTYPE_TGID))
> +		if (!(flags & PIDFD_THREAD) && !pid_has_task(pid, PIDTYPE_TGID))
>  			err = -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 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;
> +	} while (read_seqcount_retry(&pid->pid_seq, seq));
>  	if (err)
>  		return err;
>  
> diff --git a/kernel/pid.c b/kernel/pid.c
> index 4ac2ce46817f..bbca61f62faa 100644
> --- a/kernel/pid.c
> +++ b/kernel/pid.c
> @@ -271,6 +271,7 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
>  	upid = pid->numbers + ns->level;
>  	idr_preload(GFP_KERNEL);
>  	spin_lock(&pidmap_lock);
> +	seqcount_rwlock_init(&pid->pid_seq, &tasklist_lock);
>  	if (!(ns->pid_allocated & PIDNS_ADDING))
>  		goto out_unlock;
>  	pidfs_add_pid(pid);
> -- 
> 2.47.2
>