[PATCH 0/9] misc patches related to powerplay

Christian König deathsimple at vodafone.de
Fri Sep 9 17:51:30 UTC 2016


Hi Rex,

exactly as I feared, please don't do this.

I for example have a system with multiple PEG slots to be able to test 
different hardware generations at the same time.

This is rather common setup for testing and will break horrible and 
quite unpredictable when the code suddenly overrides a global function 
table which is used by multiple hardware generations.

Either create one function table for each variant or make the function 
table a member of the hwmgr structure so that you can overwrite it in 
each instance without affecting others.

Regards,
Christian.

Am 09.09.2016 um 18:29 schrieb Zhu, Rex:
>
>
> Hi Christian,
>
>
>
> I used smu7_hwmgr for  all the asics of smu version 7 , CI and Vi. 
> Please see powerplay code refactoring patches.
>
>
> But some functions in the table were different between those asics. so 
> we needed to overload those functions for some asics.
>
>
> for example:
>
> from tonga. we used pptable version 1, but ci and iceland, no pptable,
>
> so needed to overload related functions:
>
>
>        hwmgr->hwmgr_func = &smu7_hwmgr_funcs;
>          hwmgr->pptable_func = &pptable_v1_0_funcs;
>          pp_smu7_thermal_initialize(hwmgr);
> +       if (hwmgr->pp_table_version == PP_TABLE_V0) {
> + hwmgr->hwmgr_func->get_pp_table_entry = &smu7_get_pp_table_entry_v0;
> + hwmgr->hwmgr_func->get_num_of_pp_table_entries = 
> smu7_get_number_of_powerplay_table_entries_v0;
> +               hwmgr->pptable_func = &pptable_funcs;
> +       }
>
>
> Best Regards
>
> Rex
>
>
>
> ------------------------------------------------------------------------
> *From:* Christian König <deathsimple at vodafone.de>
> *Sent:* Friday, September 9, 2016 10:23:26 PM
> *To:* Zhu, Rex; amd-gfx at lists.freedesktop.org
> *Subject:* Re: [PATCH 0/9] misc patches related to powerplay
> Patch #1-#7 and #9 are Acked-by: Christian König 
> <christian.koenig at amd.com>.
>
> Patch #8: That looks fishy, usually we don't want to override static
> functions tables.
>
> So what is the specific use case here?
>
> Regards,
> Christian.
>
> Am 09.09.2016 um 15:37 schrieb Rex Zhu:
> > Rex Zhu (9):
> >    drm/amd/powerplay: mark symbols static where possible on tonga.
> >    drm/amd/powerplay: add feature flags in hwmgr to enable/disable
> >      special features.
> >    drm/amd/powerplay: add module parameter for mask pp feature
> >    drm/amd/powerplay: initialize platform caps in hwmgr_init.
> >    drm/amd/powerplay: add common functiones for visiting pp table.
> >    drm/amd/powerplay: wrap get evv voltage of fiji and polaris
> >    drm/amd/powerplay: move smu related variable definitions to smumgr.
> >    drm/amd/powerplay: delete const flag of hwmgr_funcs for overload.
> >    drm/amd/powerplay: delete dupicated function and definition.
> >
> >   drivers/gpu/drm/amd/amdgpu/amdgpu.h |   1 +
> >   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c |   4 +
> >   drivers/gpu/drm/amd/powerplay/hwmgr/cz_hwmgr.c |   2 +-
> >   drivers/gpu/drm/amd/powerplay/hwmgr/fiji_hwmgr.c |   2 +-
> >   .../gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c |  34 ----
> >   drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c | 186 
> ++++++++++++++++++---
> >   .../gpu/drm/amd/powerplay/hwmgr/iceland_hwmgr.c |  10 +-
> >   .../gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.c |   7 +-
> >   .../gpu/drm/amd/powerplay/hwmgr/polaris10_hwmgr.h |   5 +-
> >   .../drm/amd/powerplay/hwmgr/polaris10_powertune.h |  13 --
> >   drivers/gpu/drm/amd/powerplay/hwmgr/tonga_hwmgr.c |  21 +--
> >   .../gpu/drm/amd/powerplay/inc/hardwaremanager.h |   1 -
> >   drivers/gpu/drm/amd/powerplay/inc/hwmgr.h |  32 +++-
> >   .../drm/amd/powerplay/smumgr/polaris10_smumgr.c |   1 -
> >   .../drm/amd/powerplay/smumgr/polaris10_smumgr.h |  20 +++
> >   drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c |   1 +
> >   16 files changed, 229 insertions(+), 111 deletions(-)
> >
>
>
>
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/amd-gfx/attachments/20160909/c1d4d587/attachment.html>


More information about the amd-gfx mailing list