linux-kernel - Re: [PATCH v7 23/23] [DO NOT MERGE] arm64: Cope with CPUs stuck in VHE mode

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: <4d4e9a5cff65dbd8861f829089f570e5@kernel.org>
Date:   Mon, 22 Feb 2021 09:47:06 +0000
From:   Marc Zyngier <maz@...nel.org>
To:     Jonathan Neuschäfer <j.ne@...teo.net>
Cc:     linux-arm-kernel@...ts.infradead.org, kvmarm@...ts.cs.columbia.edu,
        linux-kernel@...r.kernel.org,
        Prasad Sodagudi <psodagud@...eaurora.org>,
        Srinivas Ramana <sramana@...eaurora.org>,
        Catalin Marinas <catalin.marinas@....com>,
        Hector Martin <marcan@...can.st>,
        Ajay Patil <pajay@....qualcomm.com>, kernel-team@...roid.com,
        Will Deacon <will@...nel.org>, Ard Biesheuvel <ardb@...nel.org>
Subject: Re: [PATCH v7 23/23] [DO NOT MERGE] arm64: Cope with CPUs stuck in
 VHE mode

Hi Jonathan,

On 2021-02-22 09:35, Jonathan Neuschäfer wrote:
> Hi,
> 
> On Mon, Feb 08, 2021 at 09:57:32AM +0000, Marc Zyngier wrote:
>> It seems that the CPU known as Apple M1 has the terrible habit
>> of being stuck with HCR_EL2.E2H==1, in violation of the architecture.
> 
> Minor nitpick from the sideline: The M1 SoC has two kinds of CPU in it
> (Icestorm and Firestorm), which makes "CPU known as Apple M1" a bit
> imprecise.

Fair enough. How about something along the lines of:
"At least some of the CPUs integrated in the Apple M1 SoC have
  the terrible habit..."

> In practicality it seems unlikely though, that Icestorm and Firestorm
> act differently with regards to the code in this patch.

This is my hunch as well. And if they did, it shouldn't be a big deal:
the "architecture compliant" CPUs would simply transition via EL1
as expected, and join their buggy friends running at EL2 slightly later.

Thanks,

         M.
-- 
Jazz is not dead. It just smells funny...