Re: Req: about Polaris with RKL platform

[Mario Limonciello <superm1@xxxxxxxxx>]

On Mon, Aug 9, 2021 at 9:37 AM Alex Deucher <alexdeucher@xxxxxxxxx> wrote:

On Mon, Aug 9, 2021 at 9:59 AM Koba Ko <koba.ko@xxxxxxxxxxxxx> wrote:
>
> Previously, AMD had an issue about noise  with AMD-DG on the RKL platform
> AMD provided a parameter.
> #modprobe amdgpu ppfeaturemask=0xfff7bffb
>
>  I thought it's better to check and assign values in amd gpu.
> Have a trouble determining the type of pch(RKL or else),
> search in amd drm driver and can't find any about this.
> Would someone please guide me? if there's an existing function.
>
> here's a proposal, check RKL PCH in amd driver,
> the pch definitions must be splitted off from intel_pch.h in i915
> folder to include/drm/intel_pch_definition.h

Yes, something like that would work.

Can the issue that prompted this also happen with other ASIC with the

newer SMU families?  If so, should it probably be added to all of them

or further up in the code where the mask normally gets set from module

parameters to add the extra check there.

Alex


>
> > --- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
> > +++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
> > @@ -1629,7 +1629,7 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
> >
> >         data->mclk_dpm_key_disabled = hwmgr->feature_mask & PP_MCLK_DPM_MASK ? false : true;
> >         data->sclk_dpm_key_disabled = hwmgr->feature_mask & PP_SCLK_DPM_MASK ? false : true;
> > -       data->pcie_dpm_key_disabled = hwmgr->feature_mask & PP_PCIE_DPM_MASK ? false : true;
> > +       data->pcie_dpm_key_disabled = is_rkl_pch() || !(hwmgr->feature_mask & PP_PCIE_DPM_MASK);
> >         /* need to set voltage control types before EVV patching */
> >         data->voltage_control = SMU7_VOLTAGE_CONTROL_NONE;
> >         data->vddci_control = SMU7_VOLTAGE_CONTROL_NONE;

--

Mario Limonciello
superm1@xxxxxxxxx