Quoting Mika Kuoppala (2020-02-06 16:32:22) > Chris Wilson <chris@xxxxxxxxxxxxxxxxxx> writes: > > > Trust that the HW does the right thing after simply updating the > > PD_DIR_BASE? > > Bspec offers an invalidate before writing the base. > > So, lets assume the DCLV write is superfluous as it will be > the same. > > Then the sequence would be TLB_INVLIDATE followed by > PP_DIR_BASE (which will all pds) I can recommend not doing the *cs++ = _MASKED_BIT_ENABLE(INSTPM_TLB_INVALIDATE); first. -Chris _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
