linux-kernel - Re: [PATCH v3 2/2] [WIP] tools/power turbostat: Also read package power on AMD F17h (Zen)

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: <d45d021c5546a301cf1c53d6b6d8c83ebd802a57.camel@kepstin.ca>
Date:   Wed, 20 Mar 2019 21:35:03 -0400
From:   Calvin Walton <calvin.walton@...stin.ca>
To:     Len Brown <lenb@...nel.org>
Cc:     Linux PM list <linux-pm@...r.kernel.org>,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3 2/2] [WIP] tools/power turbostat: Also read package
 power on AMD F17h (Zen)

(Whoops, resending this message. Forgot that Gmail defaulted to
HTML...)

On Wed, 2019-03-20 at 19:36 -0400, Len Brown wrote:
> Hi Calvin,
> I'm inclined to apply this -- because it will not break anything,
> and it would at least enable testing by people, who have this
> hardware.

Hi Len,

By all means go ahead and apply the package power patch as well. I've
tested it on both Summit (single-die desktop) and Raven (desktop/laptop
apu) with good results. The worst case as it stands is that if the
multi-die packages (EPYC/TR) don't aggregate the value per package,
then package power will be under-reported.

(I previously wrote that this would be easier to test with the patch
applied, because the package power is reported with the -Dump option,
but I'm not sure that's actually the case - the value might still only
be collected once per package?)

Calvin.

> 
> On Fri, Aug 17, 2018 at 12:35 PM Calvin Walton <
> calvin.walton@...stin.ca> wrote:
> > The package power can also be read from an MSR. It's not clear
> > exactly
> > what is included, and whether it's aggregated over all nodes or
> > reported separately.
> > 
> > It does look like this is reported separately per CCX (I get a
> > single
> > value on the Ryzen R7 1700), but it might be reported separately
> > per-
> > die (node?) on larger processors. If that's the case, it would have
> > to
> > be recorded per node and aggregated for the socket.
> > 
> > Note that although Zen has these MSRs reporting power, it looks
> > like
> > the actual RAPL configuration (power limits, configured TDP) is
> > done
> > through PCI configuration space. I have not yet found any public
> > documentation for this.
> > 
> > Signed-off-by: Calvin Walton <calvin.walton@...stin.ca>
> > ---
> >  tools/power/x86/turbostat/turbostat.c | 12 ++++++++++--
> >  1 file changed, 10 insertions(+), 2 deletions(-)
> > 
> > diff --git a/tools/power/x86/turbostat/turbostat.c
> > b/tools/power/x86/turbostat/turbostat.c
> > index 89d4e2e75774..675c894b8595 100644
> > --- a/tools/power/x86/turbostat/turbostat.c
> > +++ b/tools/power/x86/turbostat/turbostat.c
> > @@ -1973,6 +1973,11 @@ int get_counters(struct thread_data *t,
> > struct core_data *c, struct pkg_data *p)
> >                         return -16;
> >                 p->rapl_dram_perf_status = msr & 0xFFFFFFFF;
> >         }
> > +       if (do_rapl & RAPL_AMD_F17H) {
> > +               if (get_msr(cpu, MSR_PKG_ENERGY_STAT, &msr))
> > +                       return -13;
> > +               p->energy_pkg = msr & 0xFFFFFFFF;
> > +       }
> >         if (DO_BIC(BIC_PkgTmp)) {
> >                 if (get_msr(cpu, MSR_IA32_PACKAGE_THERM_STATUS,
> > &msr))
> >                         return -17;
> > @@ -3986,10 +3991,13 @@ void rapl_probe_amd(unsigned int family,
> > unsigned int model)
> >         switch (family) {
> >         case 0x17: /* Zen, Zen+ */
> >                 do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY;
> > -               if (rapl_joules)
> > +               if (rapl_joules) {
> > +                       BIC_PRESENT(BIC_Pkg_J);
> >                         BIC_PRESENT(BIC_Cor_J);
> > -               else
> > +               } else {
> > +                       BIC_PRESENT(BIC_PkgWatt);
> >                         BIC_PRESENT(BIC_CorWatt);
> > +               }
> >                 break;
> >         default:
> >                 return;
> > --
> > 2.18.0
> > 
> 
>