[Intel-gfx] [PATCH 0/3] drm/i915: mark GEM objects as dirtied by CPU

[Dave Gordon]

This patchset covers three variations on GEM objects being dirtied by
means of CPU writes.

The first is simple: an object has been entirely filled with data via
CPU writes, and the whole object is therefore dirty (i.e. backing store
is out-of-date w.r.t. current contents). For these cases, marking the
individual pages at the point of writing would not be a win.

The second patch covers cases where only one page is actually written;
these are candidates for a future optimisation where only the specific
page is marked dirty (only applicable to objects with page-tracked
backing store).

The third deals with a couple of other apparently missed cases where
there might be an opportunity for updates to be dropped.