Re: [PATCH v2 14/18] KVM: x86/mmu: avoid indirect call for get_cr3

[Maxim Levitsky <mlevitsk@xxxxxxxxxx>]

On Thu, 2022-02-17 at 16:03 -0500, Paolo Bonzini wrote:
> Most of the time, calls to get_guest_pgd result in calling
> kvm_read_cr3 (the exception is only nested TDP).  Hardcode
> the default instead of using the get_cr3 function, avoiding
> a retpoline if they are enabled.
> 
> Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
> ---
>  arch/x86/kvm/mmu.h             | 13 +++++++++++++
>  arch/x86/kvm/mmu/mmu.c         | 15 +++++----------
>  arch/x86/kvm/mmu/paging_tmpl.h |  2 +-
>  arch/x86/kvm/x86.c             |  2 +-
>  4 files changed, 20 insertions(+), 12 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
> index 1d0c1904d69a..1808d6814ddb 100644
> --- a/arch/x86/kvm/mmu.h
> +++ b/arch/x86/kvm/mmu.h
> @@ -116,6 +116,19 @@ static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
>  					  vcpu->arch.mmu->shadow_root_level);
>  }
>  
> +static inline gpa_t __kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu)
> +{
> +	if (!mmu->get_guest_pgd)
> +		return kvm_read_cr3(vcpu);
> +	else
> +		return mmu->get_guest_pgd(vcpu);
> +}
> +
> +static inline gpa_t kvm_mmu_get_guest_pgd(struct kvm_vcpu *vcpu)
> +{
> +	return __kvm_mmu_get_guest_pgd(vcpu, vcpu->arch.mmu);
> +}
> +
>  struct kvm_page_fault {
>  	/* arguments to kvm_mmu_do_page_fault.  */
>  	const gpa_t addr;
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 4e8e3e9530ca..d422d0d2adf8 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3451,7 +3451,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
>  	unsigned i;
>  	int r;
>  
> -	root_pgd = mmu->get_guest_pgd(vcpu);
> +	root_pgd = kvm_mmu_get_guest_pgd(vcpu);
>  	root_gfn = root_pgd >> PAGE_SHIFT;
>  
>  	if (mmu_check_root(vcpu, root_gfn))
> @@ -3881,7 +3881,7 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
>  	arch.token = (vcpu->arch.apf.id++ << 12) | vcpu->vcpu_id;
>  	arch.gfn = gfn;
>  	arch.direct_map = vcpu->arch.mmu->direct_map;
> -	arch.cr3 = vcpu->arch.mmu->get_guest_pgd(vcpu);
> +	arch.cr3 = kvm_mmu_get_guest_pgd(vcpu);
>  
>  	return kvm_setup_async_pf(vcpu, cr2_or_gpa,
>  				  kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
> @@ -4230,11 +4230,6 @@ void kvm_mmu_new_pgd(struct kvm_vcpu *vcpu, gpa_t new_pgd)
>  }
>  EXPORT_SYMBOL_GPL(kvm_mmu_new_pgd);
>  
> -static unsigned long get_cr3(struct kvm_vcpu *vcpu)
> -{
> -	return kvm_read_cr3(vcpu);
> -}
> -
>  static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
>  			   unsigned int access)
>  {
> @@ -4789,7 +4784,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
>  	context->invlpg = NULL;
>  	context->shadow_root_level = kvm_mmu_get_tdp_level(vcpu);
>  	context->direct_map = true;
> -	context->get_guest_pgd = get_cr3;
> +	context->get_guest_pgd = NULL; /* use kvm_read_cr3 */
>  	context->get_pdptr = kvm_pdptr_read;
>  	context->inject_page_fault = kvm_inject_page_fault;
>  	context->root_level = role_regs_to_root_level(&regs);
> @@ -4964,7 +4959,7 @@ static void init_kvm_softmmu(struct kvm_vcpu *vcpu)
>  
>  	kvm_init_shadow_mmu(vcpu, &regs);
>  
> -	context->get_guest_pgd     = get_cr3;
> +	context->get_guest_pgd	   = NULL; /* use kvm_read_cr3 */
>  	context->get_pdptr         = kvm_pdptr_read;
>  	context->inject_page_fault = kvm_inject_page_fault;
>  }
> @@ -4996,7 +4991,7 @@ static void init_kvm_nested_mmu(struct kvm_vcpu *vcpu)
>  		return;
>  
>  	g_context->mmu_role.as_u64 = new_role.as_u64;
> -	g_context->get_guest_pgd     = get_cr3;
> +	g_context->get_guest_pgd     = NULL; /* use kvm_read_cr3 */
>  	g_context->get_pdptr         = kvm_pdptr_read;
>  	g_context->inject_page_fault = kvm_inject_page_fault;
>  	g_context->root_level        = new_role.base.level;
> diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
> index 346f3bad3cb9..1a85aba837b2 100644
> --- a/arch/x86/kvm/mmu/paging_tmpl.h
> +++ b/arch/x86/kvm/mmu/paging_tmpl.h
> @@ -362,7 +362,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
>  	trace_kvm_mmu_pagetable_walk(addr, access);
>  retry_walk:
>  	walker->level = mmu->root_level;
> -	pte           = mmu->get_guest_pgd(vcpu);
> +	pte           = __kvm_mmu_get_guest_pgd(vcpu, mmu);
>  	have_ad       = PT_HAVE_ACCESSED_DIRTY(mmu);
>  
>  #if PTTYPE == 64
> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
> index f10878aa5b20..adcee7c305ca 100644
> --- a/arch/x86/kvm/x86.c
> +++ b/arch/x86/kvm/x86.c
> @@ -12161,7 +12161,7 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
>  		return;
>  
>  	if (!vcpu->arch.mmu->direct_map &&
> -	      work->arch.cr3 != vcpu->arch.mmu->get_guest_pgd(vcpu))
> +	      work->arch.cr3 != kvm_mmu_get_guest_pgd(vcpu))
>  		return;
>  
>  	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);


Reviewed-by: Maxim Levitsky <mlevitsk@xxxxxxxxxx>

Not sure though if that is worth it though. IMHO it would be better to convert mmu callbacks
(and nested ops callbacks, etc) to static calls.

Best regards,
	Maxim Levitsky