On Mon, Sep 09, 2019 at 02:50:20PM +0300, Joonas Lahtinen wrote: > Quoting Prathap Kumar Valsan (2019-08-26 01:48:01) > > To provide shared last-level-cache isolation to cpu workloads running > > concurrently with gpu workloads, the gpu allocation of cache lines needs > > to be restricted to certain ways. Currently GPU hardware supports four > > class-of-service(CLOS) levels and there is an associated way-mask for > > each CLOS. > > > > Hardware supports reading supported way-mask configuration for GPU using > > a bios pcode interface. The supported way-masks and the one currently > > active is communicated to userspace via a sysfs file--closctrl. Admin user > > can then select a new mask by writing the mask value to the file. > > > > Note of Caution: Restricting cache ways using this mechanism presents a > > larger attack surface for side-channel attacks. > > I wonder if this is enough to justify some further protection before > enabling? Should there be a kernel warning message on enabling this or a commit message is enough? > > > Example usage: > > The active way-mask is highlighted within square brackets. > > > cat /sys/class/drm/card0/closctrl > > [0xffff] 0xff00 0xc000 0x8000 > > How about two files for easier scripting interface? > > /sys/class/drm/card0/llc_clos > /sys/class/drm/card0/llc_clos_modes > Agreed. A single file interface was suggested by Jon. Hope he is ok with having two files :) > Regards, Joonas Thanks, Prathap _______________________________________________ Intel-gfx mailing list Intel-gfx@xxxxxxxxxxxxxxxxxxxxx https://lists.freedesktop.org/mailman/listinfo/intel-gfx
