Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.33 as permitted sender) client-ip=23.128.96.33;
MIME-Version: 1.0
From:   Suleiman Souhlal <suleiman@google.com>
Date:   Wed, 13 Sep 2023 21:49:07 +0900
Message-ID: <CABCjUKBXPLNaBjELHqz=Oke_JsxXLQauTWrsNmTp3KToW3-9MQ@mail.gmail.com>
Subject: NOHZ interaction between IPI-less kick_ilb() and nohz_csd_func().
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Ingo Molnar <mingo@redhat.com>, Juri Lelli <juri.lelli@redhat.com>,
        Linux Kernel <linux-kernel@vger.kernel.org>,
        Steven Rostedt <rostedt@google.com>,
        Joel Fernandes <joelaf@google.com>,
        Vineeth Pillai <vineethrp@google.com>,
        Youssef Esmat <youssefesmat@google.com>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

Hello,

I noticed that on x86 machines that have MWAIT, with NOHZ, when the
kernel decides to kick the idle load balance on another CPU in
kick_ilb(), there's an optimization that makes it avoid using an IPI
and instead exploit the fact that the remote CPU is MWAITing on the
thread_info flags, by just setting TIF_NEED_RESCHED, in
call_function_single_prep_ipi().
However, on the remote CPU, in nohz_csd_func(), we end up not raising
the sched softirq due to NEED_RESCHED being set, so the ILB doesn't
end up getting done.

Is this intended?

Thanks,
-- Suleiman