linux-kernel - Re: [PATCH] arm64: Trap WFI executed in userspace

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: <86lg7vx0i7.wl-marc.zyngier@arm.com>
Date:   Thu, 20 Sep 2018 23:33:20 +0100
From:   Marc Zyngier <marc.zyngier@....com>
To:     Pavel Machek <pavel@....cz>
Cc:     <linux-arm-kernel@...ts.infradead.org>,
        <linux-kernel@...r.kernel.org>,
        Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will.deacon@....com>
Subject: Re: [PATCH] arm64: Trap WFI executed in userspace

On Thu, 20 Sep 2018 23:04:30 +0100,
Pavel Machek <pavel@....cz> wrote:
> 
> On Tue 2018-08-07 10:33:26, Marc Zyngier wrote:
> > It recently came to light that userspace can execute WFI, and that
> > the arm64 kernel doesn trap this event. This sounds rather benign,
> > but the kernel should decide when it wants to wait for an interrupt,
> > and not userspace.
> > 
> > Let's trap WFI and treat it as a way to yield the CPU to another
> > process.
> 
> I don't think that's reasonable. Userspace should not be doing that,
> and we do not want to encourage it. SIGILL would be reasonable, I'd
> say.

This ship has already sailed. Sending SIGILL changes the ABI in an
incompatible way. Immediately returning to userspace without doing
anything else (see v2 [1]) is the best we can do without changing the
behaviour of userspace.

Thanks,

	M.

[1] https://patchwork.kernel.org/patch/10562517/

-- 
Jazz is not dead, it just smell funny.