On 25.11.20 10:06, Christian Borntraeger wrote:
> Right now we do count pfault (pseudo page faults aka async page faults
> start and completion events). What we do not count is, if an async page
> fault would have been possible by the host, but it was disabled by the
> guest (e.g. interrupts off, pfault disabled, secure execution....). Let
> us count those as well in the pfault_sync counter.
>
> Signed-off-by: Christian Borntraeger <borntraeger@xxxxxxxxxx>
> ---
> arch/s390/include/asm/kvm_host.h | 1 +
> arch/s390/kvm/kvm-s390.c | 2 ++
> 2 files changed, 3 insertions(+)
>
> diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
> index 463c24e26000..74f9a036bab2 100644
> --- a/arch/s390/include/asm/kvm_host.h
> +++ b/arch/s390/include/asm/kvm_host.h
> @@ -459,6 +459,7 @@ struct kvm_vcpu_stat {
> u64 diagnose_308;
> u64 diagnose_500;
> u64 diagnose_other;
> + u64 pfault_sync;
> };
>
> #define PGM_OPERATION 0x01
> diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
> index 282a13ece554..dbafd057ca6a 100644
> --- a/arch/s390/kvm/kvm-s390.c
> +++ b/arch/s390/kvm/kvm-s390.c
> @@ -60,6 +60,7 @@
> struct kvm_stats_debugfs_item debugfs_entries[] = {
> VCPU_STAT("userspace_handled", exit_userspace),
> VCPU_STAT("exit_null", exit_null),
> + VCPU_STAT("pfault_sync", pfault_sync),
> VCPU_STAT("exit_validity", exit_validity),
> VCPU_STAT("exit_stop_request", exit_stop_request),
> VCPU_STAT("exit_external_request", exit_external_request),
> @@ -4109,6 +4110,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
> current->thread.gmap_pfault = 0;
> if (kvm_arch_setup_async_pf(vcpu))
> return 0;
> + vcpu->stat.pfault_sync++;
> return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
> }
> return vcpu_post_run_fault_in_sie(vcpu);
>
Reviewed-by: David Hildenbrand <david@xxxxxxxxxx>
--
Thanks,
David / dhildenb
