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: <CAGX5Wg2OOgY6d1RH514Kh9D6b+siga+jzH7qubcmE+ukq+6KKA@mail.gmail.com>
Date:   Wed, 26 Aug 2020 15:03:52 +0200
From:   Guilhem Lettron <guilhem@...pilot.io>
To:     "Rafael J. Wysocki" <rafael@...nel.org>
Cc:     Jacob Pan <jacob.jun.pan@...ux.intel.com>,
        Len Brown <lenb@...nel.org>,
        Linux PM <linux-pm@...r.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH] intel_idle: Add ICL support

On Wed, 26 Aug 2020 at 14:43, Rafael J. Wysocki <rafael@...nel.org> wrote:
>
> On Wed, Aug 26, 2020 at 2:05 PM Guilhem Lettron <guilhem@...pilot.io> wrote:
> >
> > Use the same C-states as SKL
>
> Why is this change needed?

On my laptop, a Dell XPS 13 7390 2-in-1 with i7-1065G7, ACPI only
report "C1_ACPI", "C2_ACPI" and "C3_ACPI".
After this patch I have "C1", "C1E", "C6", "C7s", "C8", "C9" and "C10".

I tested for some time on idle (without any application launched) and
battery consumption drop ~1W/2W.

But it can be a measurement problem or different context. So don't
hesitate to tell me if I look wrong or if ACPI is a better option for
this specific processor family.

> > Signed-off-by: Guilhem Lettron <guilhem@...pilot.io>
> > ---
> >  drivers/idle/intel_idle.c | 2 ++
> >  1 file changed, 2 insertions(+)
> >
> > diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
> > index 8e0fb1a5bdbd..1bb539f09a4f 100644
> > --- a/drivers/idle/intel_idle.c
> > +++ b/drivers/idle/intel_idle.c
> > @@ -1145,6 +1145,8 @@ static const struct x86_cpu_id intel_idle_ids[] __initconst = {
> >         X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE_L,          &idle_cpu_skl),
> >         X86_MATCH_INTEL_FAM6_MODEL(KABYLAKE,            &idle_cpu_skl),
> >         X86_MATCH_INTEL_FAM6_MODEL(SKYLAKE_X,           &idle_cpu_skx),
> > +       X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,             &idle_cpu_skl),
> > +       X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,           &idle_cpu_skl),
> >         X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,           &idle_cpu_icx),
> >         X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNL,        &idle_cpu_knl),
> >         X86_MATCH_INTEL_FAM6_MODEL(XEON_PHI_KNM,        &idle_cpu_knl),
> > --
> > 2.27.0
> >

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ