[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAFUsyfJGxpLz14pZ-_nC-3651WaeZeb6p1yteCP2J4=aTKRsrA@mail.gmail.com>
Date: Wed, 27 Oct 2021 11:28:07 -0500
From: Noah Goldstein <goldstein.w.n@...il.com>
To: Borislav Petkov <bp@...en8.de>
Cc: tglx@...utronix.de, mingo@...hat.com, X86 ML <x86@...nel.org>,
hpa@...or.com, Andy Lutomirski <luto@...nel.org>,
open list <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v2 2/2] x86/xstate: Make AVX512 status tracking more accurate
On Wed, Oct 27, 2021 at 6:07 AM Borislav Petkov <bp@...en8.de> wrote:
>
> On Fri, Oct 15, 2021 at 03:47:17PM -0500, Noah Goldstein wrote:
> > This patch splits the timestamps for tracking the AVX512 status into
>
> For future submissions, please avoid having "This patch" or "This
> commit" in the commit message. It is tautologically useless.
Got it. Thanks.
>
> ...
>
> > @@ -1282,8 +1292,27 @@ static void avx512_status(struct seq_file *m, struct task_struct *task)
> > delta = LONG_MAX;
> > delta = jiffies_to_msecs(delta);
> > }
> > + return delta;
> > +}
> >
> > - seq_put_decimal_ll(m, "AVX512_elapsed_ms:\t", delta);
>
> Regardless of whether I think this exposing of AVX512 usage is silly
> or not, we do not break userspace by changing those strings which some
> script or tool already probably relies upon.
Fixed. Added 'delta_unified' which will report the most recent usage of
either.
>
> --
> Regards/Gruss,
> Boris.
>
> https://people.kernel.org/tglx/notes-about-netiquette
Powered by blists - more mailing lists