On Tue, Jul 27, 2021 at 3:33 AM Paolo Bonzini <pbonzini@xxxxxxxxxx> wrote:
>
> KVM/ARM has an architecture-specific implementation of
> kvm_flush_remote_tlbs; however, unlike the generic one,
> it does not count the flushes in kvm->stat.remote_tlb_flush,
> so that it inexorably remained stuck to zero.
>
> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
Reviewed-by: Oliver Upton <oupton@xxxxxxxxxx>
> ---
> arch/arm64/kvm/mmu.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
> index c10207fed2f3..6cf16b43bfcc 100644
> --- a/arch/arm64/kvm/mmu.c
> +++ b/arch/arm64/kvm/mmu.c
> @@ -81,6 +81,7 @@ static bool memslot_is_logging(struct kvm_memory_slot *memslot)
> void kvm_flush_remote_tlbs(struct kvm *kvm)
> {
> kvm_call_hyp(__kvm_tlb_flush_vmid, &kvm->arch.mmu);
> + ++kvm->stat.generic.remote_tlb_flush;
> }
>
> static bool kvm_is_device_pfn(unsigned long pfn)
> --
> 2.31.1
>
> _______________________________________________
> kvmarm mailing list
> kvmarm@xxxxxxxxxxxxxxxxxxxxx
> https://lists.cs.columbia.edu/mailman/listinfo/kvmarm
