drm/i915: Minimize the huge amount of unecessary fbc sw cache clean.
authorRodrigo Vivi <rodrigo.vivi@intel.com>
Wed, 24 Sep 2014 23:50:59 +0000 (19:50 -0400)
committerDaniel Vetter <daniel.vetter@ffwll.ch>
Mon, 29 Sep 2014 12:17:31 +0000 (14:17 +0200)
commit1d73c2a8f218be3e8b6aa884740fc67110660b54
treead5adff5398fe4f3de1cae51a1c7ab0097ac915b
parent7ca5a41f4da201371e131fc0641033652f76bf30
drm/i915: Minimize the huge amount of unecessary fbc sw cache clean.

The sw cache clean on BDW is a tempoorary workaround because we cannot
set cache clean on blt ring with risk of hungs. So we are doing the cache clean on sw.
However we are doing much more than needed. Not only when using blt ring.
So, with this extra w/a we minimize the ammount of cache cleans and call it only
on same cases that it was being called on gen7.

The traditional FBC Cache clean happens over LRI on BLT ring when there is a
frontbuffer touch happening. frontbuffer tracking set fbc_dirty variable
to let BLT flush that it must clean FBC cache.

fbc.need_sw_cache_clean works in the opposite information direction
of ring->fbc_dirty telling software on frontbuffer tracking to perform
the cache clean on sw side.

v2: Clean it a little bit and fully check for Broadwell instead of gen8.

v3: Rebase after frontbuffer organization.

v4: Wiggle confused me. So fixing v3!

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
drivers/gpu/drm/i915/i915_drv.h
drivers/gpu/drm/i915/intel_frontbuffer.c
drivers/gpu/drm/i915/intel_pm.c
drivers/gpu/drm/i915/intel_ringbuffer.c
This page took 0.026602 seconds and 5 git commands to generate.