Re: [PATCH 4/10] KVM MMU: Move invlpg code out of paging_tmpl.h

[Avi Kivity <avi@redhat.com>]

On 04/22/2010 09:12 AM, Xiao Guangrong wrote:
> Using '!sp->role.cr4_pae' replaces 'PTTYPE == 32' and using
> 'pte_size = sp->role.cr4_pae ? 8 : 4' replaces sizeof(pt_element_t)
>
> Then no need compile twice for this code
>
> Signed-off-by: Xiao Guangrong<xiaoguangrong@cn.fujitsu.com>
> ---
>   arch/x86/kvm/mmu.c         |   60 ++++++++++++++++++++++++++++++++++++++++++-
>   arch/x86/kvm/paging_tmpl.h |   56 -----------------------------------------
>   2 files changed, 58 insertions(+), 58 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
> index abf8bd4..fac7c09 100644
> --- a/arch/x86/kvm/mmu.c
> +++ b/arch/x86/kvm/mmu.c
> @@ -2256,6 +2256,62 @@ static bool is_rsvd_bits_set(struct kvm_vcpu *vcpu, u64 gpte, int level)
>   	return (gpte&  vcpu->arch.mmu.rsvd_bits_mask[bit7][level-1]) != 0;
>   }
>
> +static void paging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
> +{
> +	struct kvm_shadow_walk_iterator iterator;
> +	gpa_t pte_gpa = -1;
> +	int level;
> +	u64 *sptep;
> +	int need_flush = 0;
> +	unsigned pte_size = 0;
> +
> +	spin_lock(&vcpu->kvm->mmu_lock);
> +
> +	for_each_shadow_entry(vcpu, gva, iterator) {
> +		level = iterator.level;
> +		sptep = iterator.sptep;
> +
> +		if (level == PT_PAGE_TABLE_LEVEL  ||
> +		    ((level == PT_DIRECTORY_LEVEL&&  is_large_pte(*sptep))) ||
> +		    ((level == PT_PDPE_LEVEL&&  is_large_pte(*sptep)))) {
> +			struct kvm_mmu_page *sp = page_header(__pa(sptep));
> +			int offset = 0;
> +
> +			if (!sp->role.cr4_pae)
> +				offset = sp->role.quadrant<<  PT64_LEVEL_BITS;;
> +			pte_size = sp->role.cr4_pae ? 8 : 4;
> +			pte_gpa = (sp->gfn<<  PAGE_SHIFT);
> +			pte_gpa += (sptep - sp->spt + offset) * pte_size;
> +
> +			if (is_shadow_present_pte(*sptep)) {
> +				rmap_remove(vcpu->kvm, sptep);
> +				if (is_large_pte(*sptep))
> +					--vcpu->kvm->stat.lpages;
> +				need_flush = 1;
> +			}
> +			__set_spte(sptep, shadow_trap_nonpresent_pte);
> +			break;
> +		}
> +
> +		if (!is_shadow_present_pte(*sptep))
> +			break;
> +	}
> +
> +	if (need_flush)
> +		kvm_flush_remote_tlbs(vcpu->kvm);
> +
> +	atomic_inc(&vcpu->kvm->arch.invlpg_counter);
> +
> +	spin_unlock(&vcpu->kvm->mmu_lock);
> +
> +	if (pte_gpa == -1)
> +		return;
> +
> +	if (mmu_topup_memory_caches(vcpu))
> +		return;
> +	kvm_mmu_pte_write(vcpu, pte_gpa, NULL, pte_size, 0);
> +}
> +
>    

I think we should keep it in - kvm_mmu_pte_write() calls back to 
FNAME(update_pte), we could make the call directly from here speed 
things up, since we already have the spte and don't need to look it up.

-- 
Do not meddle in the internals of kernels, for they are subtle and quick to panic.