linux-kernel - Re: Question about interrupt prioriyt of ARM GICv3/4

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: <86frmrslx0.wl-maz@kernel.org>
Date: Fri, 13 Dec 2024 14:22:03 +0000
From: Marc Zyngier <maz@...nel.org>
To: Mark Kettenis <mark.kettenis@...all.nl>
Cc: richard.xnu.clark@...il.com,
	linux-arm-kernel@...ts.infradead.org,
	linux-kernel@...r.kernel.org,
	will@...nel.org,
	linux@...linux.org.uk,
	mark.rutland@....com,
	torvalds@...ux-foundation.org
Subject: Re: Question about interrupt prioriyt of ARM GICv3/4

On Thu, 12 Dec 2024 13:02:45 +0000,
Mark Kettenis <mark.kettenis@...all.nl> wrote:
> 
> Based on my experience with OpenBSD, I'm not even sure there is much
> benefit even if you have preemtion.
> 
> And regarding anything wrong happening: there is an interesting bug in
> the RK3399 GIC integration where it gets the priorities wrong:
> 
> https://github.com/openbsd/src/blob/feb3ea439d8f49b3c0e33f54c34631a611b98e21/sys/arch/arm64/dev/agintc.c#L395
> 
> (that comment is my interpretation of what's happening; I might be
> misinterpreting what's really going on)
> 
> As far as I can tell the Linux code doesn't handle that quirk.
> Probably it doesn't matter because Linux only uses the priority
> mechanisms to implement pseudo-NMI functionality and/or doesn't do
> preemption of interrupts.

Ah, beautiful! We actually do preemption with pseudo-NMI, and as it
turns out, I just had a report of 6.11 being broken on that SoC when
pNMIs are enabled.

My "solution" for this is to just disable security at the distributor
level, and let things rip, see [1].

Thanks for the heads up!

	M.

[1] https://lore.kernel.org/r/20241213141037.3995049-1-maz@kernel.org

-- 
Without deviation from the norm, progress is not possible.