On 08.01.2012, at 16:24, Avi Kivity wrote: > On 01/08/2012 05:15 PM, Alexander Graf wrote: >> On 08.01.2012, at 14:29, Avi Kivity wrote: >> >>> On 01/04/2012 03:10 AM, Alexander Graf wrote: >>>> From: Paul Mackerras <paulus@xxxxxxxxx> >>>> >>>> This adds the infrastructure to enable us to page out pages underneath >>>> a Book3S HV guest, on processors that support virtualized partition >>>> memory, that is, POWER7. Instead of pinning all the guest's pages, >>>> we now look in the host userspace Linux page tables to find the >>>> mapping for a given guest page. Then, if the userspace Linux PTE >>>> gets invalidated, kvm_unmap_hva() gets called for that address, and >>>> we replace all the guest HPTEs that refer to that page with absent >>>> HPTEs, i.e. ones with the valid bit clear and the HPTE_V_ABSENT bit >>>> set, which will cause an HDSI when the guest tries to access them. >>>> Finally, the page fault handler is extended to reinstantiate the >>>> guest HPTE when the guest tries to access a page which has been paged >>>> out. >>> >>> Yay! >> >> Half-yay, yes :). It does not work on 970, so we still have a target that doesn't support it. > > It's okay not to support some features for older cpus. Is the 970 even > interesting from a virt perspective? Yes and no. It's a reasonably old CPU, but there was a machine built and distributed to open source developers back in the day that allowed you to use the virtualization extensions. This is the only machine actually available to people that you can run the code on. If you buy a POWER7 system today, it will not allow you to run HV KVM. Alex -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
