Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
MIME-Version: 1.0
References: <20221117005418.3499691-1-joshdon@google.com> <Y3d+1a9AEnWaxFwq@hirez.programming.kicks-ass.net>
 <CABk29NtSmXVCvkdpymeam7AYmXhZy2JLYLPFTdKpk5g6AN1-zg@mail.gmail.com>
 <094299a3-f039-04c1-d749-2bea0bc14246@linux.dev> <Y3tn5wz6TjsqfGTA@hirez.programming.kicks-ass.net>
 <CABk29Nuyp=Ba=qiJAospx-SR2ZQM9GrKW0pDUeJ3sfgNB4uLFg@mail.gmail.com>
 <Y3ymBOfRikUci/PD@hirez.programming.kicks-ass.net> <Y4CDZXZJpPB0J1BV@hirez.programming.kicks-ass.net>
In-Reply-To: <Y4CDZXZJpPB0J1BV@hirez.programming.kicks-ass.net>
From:   Josh Don <joshdon@google.com>
Date:   Mon, 28 Nov 2022 17:32:15 -0800
Message-ID: <CABk29NsyhxiOnE7ssJpPEvgFV2_em1k2=9Yy3nMG9z9TssbBNA@mail.gmail.com>
Subject: Re: [PATCH v3] sched: async unthrottling for cfs bandwidth
To:     Peter Zijlstra <peterz@infradead.org>
Cc:     Chengming Zhou <zhouchengming@bytedance.com>,
        Ingo Molnar <mingo@redhat.com>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        linux-kernel@vger.kernel.org, Tejun Heo <tj@kernel.org>,
        =?UTF-8?Q?Michal_Koutn=C3=BD?= <mkoutny@suse.com>,
        Christian Brauner <brauner@kernel.org>,
        Zefan Li <lizefan.x@bytedance.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Frederic Weisbecker <fweisbec@gmail.com>,
        anna-maria@linutronix.de
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

> @@ -1686,7 +1698,17 @@ static void __run_hrtimer(struct hrtimer_cpu_base *cpu_base,
>
>         lockdep_hrtimer_exit(expires_in_hardirq);
>         trace_hrtimer_expire_exit(timer);
> -       raw_spin_lock_irq(&cpu_base->lock);
> +
> +       local_irq_disable();
> +
> +       if (restart >= HRTIMER_RESTART_MIGRATE) {
> +               int cpu = restart - HRTIMER_RESTART_MIGRATE;

I know this is just a rough draft, but just noting that this wants a
check against MIGRATE_MAX :)

> +               if (new_cpu_base != cpu_base) {
> +                       timer->base = new_base;
> +                       enqueue_hrtimer(timer, new_base, HRTIMER_MODE_ABS);
> +                       raw_spin_unlock(&new_cpu_base->lock);

unlock the old base->lock right?