linux-kernel - Re: [PATCH] sched_ext: Fix missing rq lock in scx_bpf_cpuperf

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] [day] [month] [year] [list]

Message-ID: <Z-WKi_aKOMgbzU1M@gpd3>
Date: Thu, 27 Mar 2025 18:27:39 +0100
From: Andrea Righi <arighi@...dia.com>
To: Tejun Heo <tj@...nel.org>
Cc: David Vernet <void@...ifault.com>, Changwoo Min <changwoo@...lia.com>,
	Joel Fernandes <joelagnelf@...dia.com>,
	linux-kernel@...r.kernel.org
Subject: Re: [PATCH] sched_ext: Fix missing rq lock in scx_bpf_cpuperf_set()

On Thu, Mar 27, 2025 at 07:19:03AM -1000, Tejun Heo wrote:
> Hello,
> 
> On Thu, Mar 27, 2025 at 06:15:09PM +0100, Andrea Righi wrote:
> > > If we don't want to do locked rq tracking, we can always use
> > > schedule_deferred() when any rq is locked too. That's a bit more expensive
> > > tho.
> > 
> > Yeah, I'm a bit worried that locked rq tracking might introduce overhead to
> > all the scx callbacks, just to address this issue.
> 
> All operaitons are already wrapped with SCX_CALL_OP() and updating per-cpu
> state (kf flags). It's unlikely that another percpu variable update is going
> to be noticeable.

Ack, I'll explore the locked rq tracking way then.

Thanks,
-Andrea