Re: [PATCH v3 7/9] x86/kvm/nVMX: introduce source data cache for kvm_init_shadow_ept_mmu()

[Sean Christopherson]

On Mon, Oct 01, 2018 at 04:20:08PM +0200, Vitaly Kuznetsov wrote:
> MMU re-initialization is expensive, in particular,
> update_permission_bitmask() and update_pkru_bitmask() are.
> 
> Cache the data used to setup shadow EPT MMU and avoid full re-init when
> it is unchanged.
> 
> Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>

Nit below, otherwise:

Reviewed-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>

> ---
> Changes since v2:
> - Preserve mmu_role.base in kvm_calc_shadow_ept_root_page_role()
>   [Sean Christopherson]
> - Rename kvm_calc_mmu_role_common() -> kvm_calc_mmu_role_ext() to
>   support the change.
> ---
>  arch/x86/include/asm/kvm_host.h | 14 +++++++++
>  arch/x86/kvm/mmu.c              | 53 +++++++++++++++++++++++----------
>  2 files changed, 52 insertions(+), 15 deletions(-)
> 
> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
> index 1821b0215230..87ddaa1579e7 100644
> --- a/arch/x86/include/asm/kvm_host.h
> +++ b/arch/x86/include/asm/kvm_host.h
> @@ -274,7 +274,21 @@ union kvm_mmu_page_role {
>  };
>  
>  union kvm_mmu_extended_role {
> +/*
> + * This structure complements kvm_mmu_page_role caching everything needed for
> + * MMU configuration. If nothing in both these structures changed, MMU
> + * re-configuration can be skipped. @valid bit is set on first usage so we don't
> + * treat all-zero structure as valid data.
> + */
>  	u32 word;
> +	struct {
> +		unsigned int valid:1;
> +		unsigned int execonly:1;
> +		unsigned int cr4_pse:1;
> +		unsigned int cr4_pke:1;
> +		unsigned int cr4_smap:1;
> +		unsigned int cr4_smep:1;
> +	};
>  };
>  
>  union kvm_mmu_role {
> diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
> index 60c916286bf4..d303f722d671 100644
> --- a/arch/x86/kvm/mmu.c
> +++ b/arch/x86/kvm/mmu.c
> @@ -4708,6 +4708,20 @@ static void paging32E_init_context(struct kvm_vcpu *vcpu,
>  	paging64_init_context_common(vcpu, context, PT32E_ROOT_LEVEL);
>  }
>  
> +static union kvm_mmu_extended_role kvm_calc_mmu_role_ext(struct kvm_vcpu *vcpu)
> +{
> +	union kvm_mmu_extended_role ext = {0};
> +
> +	ext.cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP) != 0;
> +	ext.cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP) != 0;
> +	ext.cr4_pse = !!is_pse(vcpu);
> +	ext.cr4_pke = kvm_read_cr4_bits(vcpu, X86_CR4_PKE) != 0;

These can all be !!kvm_read_cr4_bits(), a la the is_pse() line, which
coincidentally is a wrapper to kvm_read_cr4_bits(vcpu, X86_CR4_PSE).
And I think technically even the "!!" can be omitted, though bitwise
unions are definitely not my area of expertise.

> +
> +	ext.valid = 1;
> +
> +	return ext;
> +}
> +
>  static union kvm_mmu_page_role
>  kvm_calc_tdp_mmu_root_page_role(struct kvm_vcpu *vcpu)
>  {
> @@ -4814,19 +4828,23 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
>  }
>  EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
>  
> -static union kvm_mmu_page_role
> -kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty)
> +static union kvm_mmu_role
> +kvm_calc_shadow_ept_root_page_role(struct kvm_vcpu *vcpu, bool accessed_dirty,
> +				   bool execonly)
>  {
> -	union kvm_mmu_page_role role = vcpu->arch.mmu->mmu_role.base;
> +	union kvm_mmu_role role;
>  
> -	/* Role is inherited from root_mmu */
> -	role.word = vcpu->arch.root_mmu.base_role.word;
> +	/* Base role is inherited from root_mmu */
> +	role.base.word = vcpu->arch.root_mmu.mmu_role.base.word;
> +	role.ext = kvm_calc_mmu_role_ext(vcpu);
>  
> -	role.level = PT64_ROOT_4LEVEL;
> -	role.direct = false;
> -	role.ad_disabled = !accessed_dirty;
> -	role.guest_mode = true;
> -	role.access = ACC_ALL;
> +	role.base.level = PT64_ROOT_4LEVEL;
> +	role.base.direct = false;
> +	role.base.ad_disabled = !accessed_dirty;
> +	role.base.guest_mode = true;
> +	role.base.access = ACC_ALL;
> +
> +	role.ext.execonly = execonly;
>  
>  	return role;
>  }
> @@ -4835,10 +4853,16 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
>  			     bool accessed_dirty, gpa_t new_eptp)
>  {
>  	struct kvm_mmu *context = vcpu->arch.mmu;
> -	union kvm_mmu_page_role root_page_role =
> -		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty);
> +	union kvm_mmu_role new_role =
> +		kvm_calc_shadow_ept_root_page_role(vcpu, accessed_dirty,
> +						   execonly);
> +
> +	__kvm_mmu_new_cr3(vcpu, new_eptp, new_role.base, false);
> +
> +	new_role.base.word &= mmu_base_role_mask.word;
> +	if (new_role.as_u64 == context->mmu_role.as_u64)
> +		return;
>  
> -	__kvm_mmu_new_cr3(vcpu, new_eptp, root_page_role, false);
>  	context->shadow_root_level = PT64_ROOT_4LEVEL;
>  
>  	context->nx = true;
> @@ -4850,8 +4874,7 @@ void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
>  	context->update_pte = ept_update_pte;
>  	context->root_level = PT64_ROOT_4LEVEL;
>  	context->direct_map = false;
> -	context->mmu_role.base.word =
> -		root_page_role.word & mmu_base_role_mask.word;
> +	context->mmu_role.as_u64 = new_role.as_u64;
>  
>  	update_permission_bitmask(vcpu, context, true);
>  	update_pkru_bitmask(vcpu, context, true);
> -- 
> 2.17.1
>