Re: [Intel-gfx] [PATCH v8 1/2] drm/i915: Refactor intel_can_enable_sagv

2019-10-25 Thread Lisovskiy, Stanislav
On Fri, 2019-10-25 at 10:44 +, Lisovskiy, Stanislav wrote: > On Fri, 2019-10-25 at 13:24 +0300, Ville Syrjälä wrote: > > On Fri, Oct 25, 2019 at 12:53:51PM +0300, Stanislav Lisovskiy > > wrote: > > > Currently intel_can_enable_sagv function contains > > > a mix of workarounds for different plat

Re: [Intel-gfx] [PATCH v8 1/2] drm/i915: Refactor intel_can_enable_sagv

2019-10-25 Thread Lisovskiy, Stanislav
On Fri, 2019-10-25 at 13:24 +0300, Ville Syrjälä wrote: > On Fri, Oct 25, 2019 at 12:53:51PM +0300, Stanislav Lisovskiy wrote: > > Currently intel_can_enable_sagv function contains > > a mix of workarounds for different platforms > > some of them are not valid for gens >= 11 already, > > so lets sp

Re: [Intel-gfx] [PATCH v8 1/2] drm/i915: Refactor intel_can_enable_sagv

2019-10-25 Thread Ville Syrjälä
On Fri, Oct 25, 2019 at 12:53:51PM +0300, Stanislav Lisovskiy wrote: > Currently intel_can_enable_sagv function contains > a mix of workarounds for different platforms > some of them are not valid for gens >= 11 already, > so lets split it into separate functions. > > v2: > - Rework watermark

[Intel-gfx] [PATCH v8 1/2] drm/i915: Refactor intel_can_enable_sagv

2019-10-25 Thread Stanislav Lisovskiy
Currently intel_can_enable_sagv function contains a mix of workarounds for different platforms some of them are not valid for gens >= 11 already, so lets split it into separate functions. v2: - Rework watermark calculation algorithm to attempt to calculate Level 0 watermark with ad