Date:   Thu, 16 Feb 2023 09:04:59 +0100
From:   Oleg Nesterov <oleg@redhat.com>
To:     David Vernet <void@manifault.com>
Cc:     mingo@redhat.com, peterz@infradead.org, juri.lelli@redhat.com,
        vincent.guittot@linaro.org, rostedt@goodmis.org,
        bsegall@google.com, mgorman@suse.de, bristot@redhat.com,
        vschneid@redhat.com, kernel-team@meta.com,
        torvalds@linux-foundation.org, ebiederm@xmission.com,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH] tasks: Extract rcu_users out of union
Message-ID: <20230216080459.GA5200@redhat.com>
References: <20230215233033.889644-1-void@manifault.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20230215233033.889644-1-void@manifault.com>
User-Agent: Mutt/1.5.24 (2015-08-30)
Precedence: bulk

I won't argue with this patch, but I can't understand the changelog...

On 02/15, David Vernet wrote:
>
> Similarly, in sched_ext, schedulers are using integer pids to remember
> tasks, and then looking them up with find_task_by_pid_ns(). This is
> slow, error prone, and adds complexity. It would be more convenient and
> performant if BPF schedulers could instead store tasks directly in maps,
> and then leverage RCU to ensure they can be safely accessed with low
> overhead.

To simplify, suppose we have

	int global_pid;

	void func(void)
	{
		rcu_read_lock();
		task = find_task_by_pid(global_pid);
		do_something(task);
		rcu_read_unlock();
	}

Could you explain how exactly can this patch help to turn global_pid into
"task_struct *" ? Why do you need to increment task->rcu_users ?

>    a task that's successfully looked
>    up in e.g. the pid_list with find_task_by_pid_ns(), can always have a
>    'usage' reference acquired on them, as it's guaranteed to be >
>    0 until after the next gp.

Yes. So it seems you need another key-to-task_struct map with rcu-safe
lookup/get and thus the add() method needs inc_not_zero(task->rcu_users) ?

I am just curious,

Oleg.