On Fri, Sep 26, 2014 at 04:26:20PM +0800, Zhang, Yu wrote: > Hi Chris & Daniel, > > Thanks for your comments. Following are my understandings about > the changes needed for this patch: > > 1> We do not need the guard page anymore between different VMs. For > the very last physical GTT entry, let's keep it pointing to a guard > page. > > 2> To reserve the GMs in our balloon code, drm_mm_reserve_node() is > preferred than the current drm_mm_insert_node_in_range_generic(). > > Am I correct? Please correct me if anything wrong. Thanks! :) Agreed. If you care to respin the patch, I'll see if anything else alarms me ;-) -Chris -- Chris Wilson, Intel Open Source Technology Centre _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx http://lists.freedesktop.org/mailman/listinfo/intel-gfx
