linux-kernel - Re: [PATCH v2 2/7] arm64: fpsimd: Make sure SVE setup is complete before SIMD is used

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: <aa5a4242-7684-4212-f03e-fdf3a5784dfb@arm.com>
Date:   Fri, 10 Jan 2020 18:41:49 +0000
From:   Suzuki Kuruppassery Poulose <suzuki.poulose@....com>
To:     Catalin Marinas <catalin.marinas@....com>
Cc:     linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
        will@...nel.org, maz@...nel.org, mark.rutland@....com,
        dave.martin@....com, ard.biesheuvel@...aro.org,
        christoffer.dall@....com, Will Deacon <will.deacon@....com>
Subject: Re: [PATCH v2 2/7] arm64: fpsimd: Make sure SVE setup is complete
 before SIMD is used

On 10/01/2020 11:51, Catalin Marinas wrote:
> On Tue, Dec 17, 2019 at 06:33:57PM +0000, Suzuki K Poulose wrote:
>> In-kernel users of NEON rely on may_use_simd() to check if the SIMD
>> can be used. However, we must initialize the SVE before SIMD can
>> be used. Add a sanity check to make sure that we have completed the
>> SVE setup before anyone uses the SIMD.
>>
>> Cc: Ard Biesheuvel <ard.biesheuvel@...aro.org>
>> Cc: Mark Rutland <mark.rutland@....com>
>> Cc: Will Deacon <will.deacon@....com>
>> Cc: Catalin Marinas <catalin.marinas@....com>
>> Signed-off-by: Suzuki K Poulose <suzuki.poulose@....com>
>> ---
>> Discussion here : https://lkml.kernel.org/r/20191014145204.GS27757@arm.com
> 
> Re-reading this thread, I think the conclusion was more towards having a
> WARN_ON in system_supports_fpsimd() (or may_use_simd()). We don't expect
> code to start using neon before the SMP is initialised (other than
> early_initcall(), the rest run after the secondary CPUs are brought up).

Thanks for pointing out. I missed this from the Dave's last email.
I have added a WARN_ON(!system_capabilities_finalized()) to
may_use_simd() for the next version.

Thanks for the review !

Suzuki