linux-kernel - Re: [PATCH v2 08/10] um: Add initial SMP support

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: <20250912004501.2565976-1-tiwei.bie@linux.dev>
Date: Fri, 12 Sep 2025 08:45:01 +0800
From: Tiwei Bie <tiwei.bie@...ux.dev>
To: johannes@...solutions.net
Cc: richard@....at,
	anton.ivanov@...bridgegreys.com,
	benjamin@...solutions.net,
	arnd@...db.de,
	linux-um@...ts.infradead.org,
	linux-kernel@...r.kernel.org,
	tiwei.btw@...group.com,
	tiwei.bie@...ux.dev
Subject: Re: [PATCH v2 08/10] um: Add initial SMP support

On Thu, 11 Sep 2025 11:32:56 +0200, Johannes Berg wrote:
> On Sun, 2025-08-10 at 13:51 +0800, Tiwei Bie wrote:
> > From: Tiwei Bie <tiwei.btw@...group.com>
> > 
> > Add initial symmetric multi-processing (SMP) support to UML. With
> > this support enabled, users can tell UML to start multiple virtual
> > processors, each represented as a separate host thread.
> > 
> > In UML, kthreads and normal threads (when running in kernel mode)
> > can be scheduled and executed simultaneously on different virtual
> > processors. However, the userspace code of normal threads still
> > runs within their respective single-threaded stubs.
> > 
> > That is, SMP support is currently available both within the kernel
> > and across different processes, but still remains limited within
> > threads of the same process in userspace.
> 
> Another thing that isn't covered is anything relating to interrupt
> affinity, I guess? Is that automatically not working, or will it look
> like you can change things but that not do anything?
> 
> I don't think it's important now (though eventually I would actually
> like to have it for our simulations), but was just thinking about it.

Currently, our irq_chips haven't implemented the irq_set_affinity
method, so setting IRQ affinity is not supported at the moment, e.g.,
attempting to set affinity through /proc/irq/IRQ#/smp_affinity will
fail with EPERM. And yeah, we should support it eventually. :)

Regards,
Tiwei