Received-SPF: pass (google.com: domain of linux-kernel+bounces-189021-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45d1:ec00::1 as permitted sender) client-ip=2604:1380:45d1:ec00::1;
Date: Fri, 24 May 2024 20:37:00 +0200
From: Oleg Nesterov <oleg@redhat.com>
To: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>, Ingo Molnar <mingo@redhat.com>,
	Nicholas Piggin <npiggin@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>, Phil Auld <pauld@redhat.com>,
	Chris von Recklinghausen <crecklin@redhat.com>,
	linux-kernel@vger.kernel.org
Subject: Re: sched/isolation: tick_take_do_timer_from_boot() calls
 smp_call_function_single() with irqs disabled
Message-ID: <20240524183700.GA17065@redhat.com>
References: <20240522151742.GA10400@redhat.com>
 <20240523132358.GA1965@redhat.com>
 <87h6eneeu7.ffs@tglx>
 <ZlCwKk65-eL0FrKX@pavilion.home>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <ZlCwKk65-eL0FrKX@pavilion.home>
User-Agent: Mutt/1.5.24 (2015-08-30)

Frederic. Thanks for looking at this!

I've already had a few beers today, I know I'll regret about this email
tomorrow, but I can't resist ;)

On 05/24, Frederic Weisbecker wrote:
>
> Actually... The boot CPU is nohz_full and nothing prevents it
> from stopping its tick once IRQs are enabled and before calling
> tick_nohz_idle_enter(). When that happens, tick_nohz_full_update_tick()
> doesn't go through can_stop_idle_tick() and therefore doesn't check if it
> is the timekeeper. And then it goes through tick_nohz_stop_tick() which
> can set tick_do_timer_cpu = TICK_DO_TIMER_NONE.

Heh. May be you mean, say, tick_nohz_full_update_tick() or
tick_nohz_idle_update_tick() which check tick_nohz_full_cpu(cpu).
Yes this doesn't help during the boot, and this was another source for
confusion to me.

But again, again. tick_sched_do_timer() says

	* If nohz_full is enabled, this should not happen because the
	* 'tick_do_timer_cpu' CPU never relinquishes.

so I guess it is not supposed to happen?

And. My main question was: how can smp_call_function_single() help???
Why do we actually need it?

Thanks ;)

Oleg.