linux-kernel - Re: [PATCH v5 08/24] sched: Introduce per memory space current virtual cpu id

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <Y2tyshbt+qgJXU9O@hirez.programming.kicks-ass.net>
Date:   Wed, 9 Nov 2022 10:28:18 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Cc:     linux-kernel@...r.kernel.org, Thomas Gleixner <tglx@...utronix.de>,
        "Paul E . McKenney" <paulmck@...nel.org>,
        Boqun Feng <boqun.feng@...il.com>,
        "H . Peter Anvin" <hpa@...or.com>, Paul Turner <pjt@...gle.com>,
        linux-api@...r.kernel.org, Christian Brauner <brauner@...nel.org>,
        Florian Weimer <fw@...eb.enyo.de>, David.Laight@...lab.com,
        carlos@...hat.com, Peter Oskolkov <posk@...k.io>,
        Alexander Mikhalitsyn <alexander@...alicyn.com>,
        Chris Kennelly <ckennelly@...gle.com>
Subject: Re: [PATCH v5 08/24] sched: Introduce per memory space current
 virtual cpu id

On Thu, Nov 03, 2022 at 04:03:43PM -0400, Mathieu Desnoyers wrote:

> diff --git a/kernel/fork.c b/kernel/fork.c
> index 08969f5aa38d..6a2323266942 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1047,6 +1047,10 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
>  	tsk->reported_split_lock = 0;
>  #endif
>  
> +#ifdef CONFIG_SCHED_MM_VCPU
> +	tsk->mm_vcpu = -1;
> +	tsk->mm_vcpu_active = 0;
> +#endif
>  	return tsk;
>  
>  free_stack:

Note how the above hunk does exactly the same as the below thunk, and I
think they're even on the same code-path.

How about moving all of this to __sched_fork() or something?

> @@ -1579,6 +1586,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
>  
>  	tsk->mm = mm;
>  	tsk->active_mm = mm;
> +	sched_vcpu_fork(tsk);
>  	return 0;
>  }

> +void sched_vcpu_fork(struct task_struct *t)
> +{
> +	WARN_ON_ONCE((t->flags & PF_KTHREAD) || !t->mm);
> +	t->mm_vcpu = -1;
> +	t->mm_vcpu_active = 1;
> +}