On Mon, Nov 01, 2010 at 04:58:43PM +0800, Xiao Guangrong wrote:
> Tracing 'async' and *pfn is useless, since 'async' is always true,
> and '*pfn' is always "fault_pfn'
>
> We can trace 'gva' and 'gfn' instead, it can help us to see the
> life-cycle of an async_pf
>
> Signed-off-by: Xiao Guangrong <xiaoguangrong@xxxxxxxxxxxxxx>
Acked-by: Gleb Natapov <gleb@xxxxxxxxxx>
> ---
> arch/x86/kvm/mmu.c | 2 +-
> include/trace/events/kvm.h | 12 +++++++-----
> 2 files changed, 8 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
> index 39cc0c6..5275c50 100644
> --- a/arch/x86/kvm/mmu.c
> +++ b/arch/x86/kvm/mmu.c
> @@ -2627,7 +2627,7 @@ static bool try_async_pf(struct kvm_vcpu *vcpu, bool no_apf, gfn_t gfn,
> put_page(pfn_to_page(*pfn));
>
> if (!no_apf && can_do_async_pf(vcpu)) {
> - trace_kvm_try_async_get_page(async, *pfn);
> + trace_kvm_try_async_get_page(gva, gfn);
> if (kvm_find_async_pf_gfn(vcpu, gfn)) {
> trace_kvm_async_pf_doublefault(gva, gfn);
> kvm_make_request(KVM_REQ_APF_HALT, vcpu);
> diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
> index 9c2cc6a..30063c6 100644
> --- a/include/trace/events/kvm.h
> +++ b/include/trace/events/kvm.h
> @@ -188,18 +188,20 @@ TRACE_EVENT(kvm_age_page,
> #ifdef CONFIG_KVM_ASYNC_PF
> TRACE_EVENT(
> kvm_try_async_get_page,
> - TP_PROTO(bool async, u64 pfn),
> - TP_ARGS(async, pfn),
> + TP_PROTO(u64 gva, u64 gfn),
> + TP_ARGS(gva, gfn),
>
> TP_STRUCT__entry(
> - __field(__u64, pfn)
> + __field(u64, gva)
> + __field(u64, gfn)
> ),
>
> TP_fast_assign(
> - __entry->pfn = (!async) ? pfn : (u64)-1;
> + __entry->gva = gva;
> + __entry->gfn = gfn;
> ),
>
> - TP_printk("pfn %#llx", __entry->pfn)
> + TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn)
> );
>
> TRACE_EVENT(
> --
> 1.7.0.4
--
Gleb.
--
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
