Re: [PATCH v2] cpufreq: intel_pstate: Add Icelake servers support in no-HWP mode

[Doug Smythies]

On Tue, Sep 7, 2021 at 7:04 PM Srinivas Pandruvada
<srinivas.pandruvada@xxxxxxxxxxxxxxx> wrote:
>
> On Tue, 2021-09-07 at 13:16 -0700, Doug Smythies wrote:
> > Hi Srinivas, Thank you for your reply.
> >
> > On Tue, Sep 7, 2021 at 9:01 AM Srinivas Pandruvada
> > <srinivas.pandruvada@xxxxxxxxxxxxxxx> wrote:
> > > On Tue, 2021-09-07 at 08:45 -0700, Doug Smythies wrote:
> > > >
> > > > Recent ASUS BIOS updates have changed the default system
> > > > response for this old thread, rendering "intel_pstate=no_hwp"
> > > > useless.
> > > >
> > > > It also raises a question: If BIOS has forced HWP, then how do we
> > > > prevent the acpi-cpufreq driver from being used? Read on.
> > >
> > > Does BIOS has option to enable Intel speed shift with no legacy
> > > support?
> > > Then this option will not populate ACPI _PSS table.
> >
> > The option is there no matter what.
> > I have tried every variation of legacy or no legacy that
> > I can find. Currently:
> > Current boot mode:   UEFI Firmware mode
> > SecureBoot:          disabled
> >
> > >
> > > >
> > > > On Fri, May 14, 2021 at 3:12 PM Doug Smythies <
> > > > dsmythies@xxxxxxxxx>
> > > > wrote:
> > > > >
> > > > > On Fri, May 14, 2021 at 1:33 PM Giovanni Gherdovich <
> > > > > ggherdovich@xxxxxxx> wrote:
> > > > > > On Fri, 2021-05-14 at 08:31 -0700, Doug Smythies wrote:
> > > > ...
> > > > > >
> > ...
> > > > Previous correspondence was with BIOS version 1003. There have
> > > > been 3
> > > > BIOS
> > > > releases since then (at least that I know of), 2103, 2201, 2301,
> > > > and
> > > > all of them
> > > > have changed the behaviour of the "Auto" setting for Intel Speed
> > > > Shift
> > > > Technology BIOS setting, forcing it on upon transfer of control
> > > > to
> > > > the OS.
> > > >
> > > > Where with "intel_pstate=no_hwp" one used to get 0 for
> > > > MSR_PM_ENABLE
> > > > (0x770) they now get 1.
> > >
> > > So they are forcing Out of band OOB mode.
> > > Does bit 8 or 18 in MSR 0x1aa is set?
> >
> > No.
>
> So there is no legacy path. I think you are working with their support.

Yes, for almost a month now, with very little to show for it.
We'll see what happens. I did get a message this afternoon:

"Our GTSD is debugging the issue,.
When they have the result, they will directly update you."

> In HWP mode does setting scaling min/max frequency has any impact?

No. I wouldn't have expected it to, as the system is confused as to who
is in charge. The acpi-cpufreq driver thinks it is in charge, but HWP
thinks it is.

The intel_pstate driver works fine.

... Doug

>
> Thanks,
> Srinivas
>
> >
> > Here is the output from my msr reader/decoder program.
> > Kernel 5.14 (unpatched).
> > intel_pstate=disable
> > BIOS setting "Auto" for Intel Speed Shift,
> > Driver: acpi-cpufreq
> >
> > doug@s19:~$ sudo c/msr-decoder
> > How many CPUs?: 12
> > 8.) 0x198: IA32_PERF_STATUS     : CPU 0-11 :  45 :  45 :  45 :  45 :
> > 45 :  45 :  45 :  45 :  45 :  45 :  45 :  45 :
> > B.) 0x770: IA32_PM_ENABLE: 1 : HWP enable
> > 1.) 0x19C: IA32_THERM_STATUS: 88450000
> > 2.) 0x1AA: MSR_MISC_PWR_MGMT: 401CC0 EIST enabled Coordination
> > enabled
> > OOB Bit 8 reset OOB Bit 18 reset
> > 3.) 0x1B1: IA32_PACKAGE_THERM_STATUS: 88410000
> > 4.) 0x64F: MSR_CORE_PERF_LIMIT_REASONS: 0
> > A.) 0x1FC: MSR_POWER_CTL: 3C005D : C1E disable : EEO disable : RHO
> > disable
> > 5.) 0x771: IA32_HWP_CAPABILITIES (performance): 10B2930 : high 48 :
> > guaranteed 41 : efficient 11 : lowest 1
> > 6.) 0x774: IA32_HWP_REQUEST:    CPU 0-11 :
> >     raw: 80003001 : 80003001 : 80003001 : 80003001 : 80003001 :
> > 80003001 : 80003001 : 80003001 : 80003001 : 80003001 : 80003001 :
> > 80003001 :
> >     min:        1 :        1 :        1 :        1 :        1 :
> > 1 :        1 :        1 :        1 :        1 :        1 :        1 :
> >     max:       48 :       48 :       48 :       48 :       48 :
> > 48 :       48 :       48 :       48 :       48 :       48 :       48
> > :
> >     des:        0 :        0 :        0 :        0 :        0 :
> > 0 :        0 :        0 :        0 :        0 :        0 :        0 :
> >     epp:      128 :      128 :      128 :      128 :      128 :
> > 128 :      128 :      128 :      128 :      128 :      128 :      128
> > :
> >     act:        0 :        0 :        0 :        0 :        0 :
> > 0 :        0 :        0 :        0 :        0 :        0 :        0 :
> > 7.) 0x777: IA32_HWP_STATUS: 0 : high 0 : guaranteed 0 : efficient 0 :
> > lowest 0
> >
> > ...
> >
> > ... Doug
>
>