linux-kernel - Re: [RFC PATCH 07/11] sched: Add proxy execution

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sat, 15 Oct 2022 17:08:14 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Connor O'Brien <connoro@...gle.com>
Cc:     linux-kernel@...r.kernel.org, kernel-team@...roid.com,
        John Stultz <jstultz@...gle.com>,
        Joel Fernandes <joelaf@...gle.com>,
        Qais Yousef <qais.yousef@....com>,
        Ingo Molnar <mingo@...hat.com>,
        Juri Lelli <juri.lelli@...hat.com>,
        Vincent Guittot <vincent.guittot@...aro.org>,
        Dietmar Eggemann <dietmar.eggemann@....com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Ben Segall <bsegall@...gle.com>, Mel Gorman <mgorman@...e.de>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Valentin Schneider <vschneid@...hat.com>,
        Will Deacon <will@...nel.org>,
        Waiman Long <longman@...hat.com>,
        Boqun Feng <boqun.feng@...il.com>,
        "Paul E . McKenney" <paulmck@...nel.org>
Subject: Re: [RFC PATCH 07/11] sched: Add proxy execution

On Mon, Oct 03, 2022 at 09:44:57PM +0000, Connor O'Brien wrote:
> @@ -965,7 +1026,10 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
>  	if (owner & MUTEX_FLAG_HANDOFF)
>  		__mutex_handoff(lock, next);
>  
> -	preempt_disable();
> +	preempt_disable(); /* XXX connoro: why disable preemption here? */
> +#ifdef CONFIG_PROXY_EXEC
> +	raw_spin_unlock(&current->blocked_lock);
> +#endif
>  	raw_spin_unlock_irqrestore(&lock->wait_lock, flags);

Because if we wouldn't have preemption disabled it would preempt here,
before the wakeup:

>  	wake_up_q(&wake_q);

And you'd be stuck with a priority inversion.