[Intel-gfx] [PATCH 19/21] drm/i915/gt: Use indices for writing into relative timelines

[Matthew Brost]

On Thu, Dec 10, 2020 at 09:05:44PM +0000, Chris Wilson wrote:
> Quoting Matthew Brost (2020-12-10 19:16:44)
> > On Thu, Dec 10, 2020 at 08:02:38AM +0000, Chris Wilson wrote:
> > > Relative timelines are relative to either the global or per-process
> > > HWSP, and so we can replace the absolute addressing with store-index
> > > variants for position invariance.
> > > 
> > 
> > Can you explain the benifit of relative addressing? Why can't we also
> > use absolute? If we can always use absolute, I don't see the point
> > complicating the breadcrumb code.
> 
> It basically allows a third party to move the contexts between hosts
> with far less patching of global state. They want us to avoid all fixed
> GGTT addressing.
> 
> The breadcrumbs themselves do not notice at all, it's just the timeline
> setup and decision to take advantage of the relative commands. The
> breadcrumb patches in this series are some outstanding fixes from ~6
> months ago.

By breadcrumbs, I meant the emit code. Relative addressing for GVT makes
sense.

With that, for this patch:
Reviewed-by: Matthew Brost <matthew.brost at intel.com>

> -Chris