Manuel Bouyer <[email protected]> wrote: > > I have a preliminary patch to support up to 255 CPUs on amd64 (not worth > > on i386), however there is still some bug in the early initialisation > > code, when TLBs are not being flushed. I have not had time yet to > > debug it out. > > > > http://www.netbsd.org/~rmind/x86_256_cpus_v4.diff > > > > Apart from that bug, it should be mostly complete. > > It looks like the patch need to be updated for the latest Xen pmap :)
Right. Patch synced with HEAD changes, if somebody enjoys debugging: http://www.netbsd.org/~rmind/x86_256_cpus_v5.diff > Please make as little assumption as possible about the number of > CPUs Xen supports. I need to do a bit more reverse-ingeenering on > the interface, but I guess hypercalls like MMUEXT_INVLPG_MULTI takes > an array of uint32_t, so we can use more than 32 cpus here as well. I just did mechanical update for Xen to use kcpuset(9) interface. Xen can be updated to support more CPUs later (if hypercalls allow suport that). -- Mindaugas
