Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Date:   Thu, 8 Jul 2021 12:12:20 +0200
From:   Petr Mladek <pmladek@suse.com>
To:     Vasily Gorbik <gor@linux.ibm.com>
Cc:     Josh Poimboeuf <jpoimboe@redhat.com>,
        Jiri Kosina <jikos@kernel.org>,
        Miroslav Benes <mbenes@suse.cz>,
        Joe Lawrence <joe.lawrence@redhat.com>,
        Heiko Carstens <hca@linux.ibm.com>,
        Sven Schnelle <svens@linux.ibm.com>,
        Sumanth Korikkar <sumanthk@linux.ibm.com>,
        live-patching@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH] livepatch: Kick idle cpu's tasks to perform
 transition
Message-ID: <YObPhPkzRSqnzgK3@alley>
References: <patch.git-b76842ceb035.your-ad-here.call-01625661932-ext-1304@work.hours>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <patch.git-b76842ceb035.your-ad-here.call-01625661932-ext-1304@work.hours>
Precedence: bulk

On Wed 2021-07-07 14:49:38, Vasily Gorbik wrote:
> On an idle system with large amount of cpus it might happen that
> klp_update_patch_state() is not reached in do_idle() for a long periods
> of time. With debug messages enabled log is filled with:
> [  499.442643] livepatch: klp_try_switch_task: swapper/63:0 is running

I see. I guess that the problem is only when CONFIG_NO_HZ is enabled.
Do I get it correctly, please?

> without any signs of progress. Ending up with "failed to complete
> transition".
> 
> On s390 LPAR with 128 cpus not a single transition is able to complete
> and livepatch kselftests fail.
> 
> To deal with that, make sure we break out of do_idle() inner loop to
> reach klp_update_patch_state() by marking idle tasks as NEED_RESCHED
> as well as kick cpus out of idle state.
>
> Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
> ---
>  kernel/livepatch/transition.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
> index 3a4beb9395c4..793eba46e970 100644
> --- a/kernel/livepatch/transition.c
> +++ b/kernel/livepatch/transition.c
> @@ -415,8 +415,11 @@ void klp_try_complete_transition(void)
>  	for_each_possible_cpu(cpu) {
>  		task = idle_task(cpu);
>  		if (cpu_online(cpu)) {
> -			if (!klp_try_switch_task(task))
> +			if (!klp_try_switch_task(task)) {
>  				complete = false;
> +				set_tsk_need_resched(task);
> +				kick_process(task);

First, we should kick the idle threads in klp_send_signals().
It already solves similar problem when normal threads and kthreads
stay in the incorruptible sleep for too long.

Second, the way looks a bit hacky to me. need_resched() depends on
the currect implementation of the idle loop. kick_process() has
a completely different purpose and does checks that do not fit well
this use-case.

I wonder if wake_up_nohz_cpu() would fit better here. Please, add
scheduler people into CC, namely:

    Ingo Molnar <mingo@redhat.com>
    Peter Zijlstra <peterz@infradead.org>

and NOHZ guys:

    Frederic Weisbecker <fweisbec@gmail.com>
    Thomas Gleixner <tglx@linutronix.de>


Best Regards,
Petr