linux-kernel - Re: [RFC PATCH] arm64/fpsimd: Don't disable softirq when touching FPSIMD/SVE state

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: <0f8d6b53-6834-7363-03fc-6fd47ea49b80@arm.com>
Date:   Thu, 11 Apr 2019 15:10:28 +0100
From:   Julien Grall <julien.grall@....com>
To:     Dave Martin <Dave.Martin@....com>
Cc:     linux-arm-kernel@...ts.infradead.org, bigeasy@...utronix.de,
        linux-rt-users@...r.kernel.org, catalin.marinas@....com,
        will.deacon@....com, ard.biesheuvel@...aro.org,
        linux-kernel@...r.kernel.org
Subject: Re: [RFC PATCH] arm64/fpsimd: Don't disable softirq when touching
 FPSIMD/SVE state

Hi Dave,

On 4/4/19 11:52 AM, Dave Martin wrote:
> On Fri, Feb 08, 2019 at 04:55:13PM +0000, Julien Grall wrote:
> I'm not sure how this patch will affect context switch overhead, so it
> would be good to see hackbench numbers (or similar).

I finally have some numbers for this patch. The benchmark was ran using 
Linux 5.1-rc4 and defconfig.

On Juno2:
    * hackbench 100 process 1000 (10 times)
    * .7% quicker

On ThunderX 2:
    * hackbench 1000 process 1000 (20 times)
    * 3.4% quicker

I am happy to try other benchmark if you think it is useful.

Anyway, I will resend the series with the comments addressed.

Cheers,

-- 
Julien Grall