On 11/06/21 14:08, Christian Borntraeger wrote:
I always interpreted it as "number of times the KVM page table
management code needed other CPUs to learn about new page tables".
Whether the broadcast is done in software or hardware shouldn't
matter; either way I suppose there is still some traffic on the bus
involved.
My point is that KVM page table management on s390x completely
piggy-backs on the qemu address space page table management from common
code for the last level.
And due to the way we handle page tables we also do not teach "other
CPUs". We always teach the whole system with things like IPTE.
But that just means that you'll have fewer KVM-exclusive and thus nicer
numbers than x86 or ARM. :) It still makes sense to count
gmap_flush_tlb calls.
Paolo
