[Intel-gfx] [PATCH v2 3/6] drm/i915: Use WC copies on !llc platforms for the command parser

Ville Syrjälä ville.syrjala at linux.intel.com
Tue Dec 1 09:32:43 PST 2015

On Fri, Nov 20, 2015 at 03:22:03PM +0000, Chris Wilson wrote:
> On Fri, Nov 20, 2015 at 05:05:05PM +0200, Ville Syrjälä wrote:
> > On Fri, Nov 20, 2015 at 10:55:58AM +0000, Chris Wilson wrote:
> > > Since we blow the TLB caches by using kmap/kunmap, we may as well go the
> > > whole hog and see if declaring our destination page as WC is faster than
> > > keeping it as WB and using clflush. It should be!
> > 
> > Is this description for another patch? I can't see any WC stuff in
> > there.
> No, just badly written. (Admittedly at one point I did experiment with
> remapping the pages as WC and discovered that did stop_macheine()...)
> drm/i915: Perform inline clflushes from the command parser
> On incoherent architectures, we can avoid having to clflush the
> destination shadow batch as a separate pass by inlining the call to
> clflush whilst we already have the kmap_atomic() around for the page.

With the new description:
Reviewed-by: Ville Syrjälä <ville.syrjala at linux.intel.com>

Ville Syrjälä
Intel OTC

More information about the Intel-gfx mailing list