diff mbox series

[v2,04/10] KVM: VMX: Do Hyper-V TLB flush iff vCPU's EPTP hasn't been flushed

Message ID 20201020215613.8972-5-sean.j.christopherson@intel.com (mailing list archive)
State New, archived
Headers show
Series KVM: VMX: Clean up Hyper-V PV TLB flush | expand

Commit Message

Sean Christopherson Oct. 20, 2020, 9:56 p.m. UTC
Combine the for-loops for Hyper-V TLB EPTP checking and flushing, and in
doing so skip flushes for vCPUs whose EPTP matches the target EPTP.

Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
---
 arch/x86/kvm/vmx/vmx.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

Comments

Vitaly Kuznetsov Oct. 21, 2020, 12:23 p.m. UTC | #1
Sean Christopherson <sean.j.christopherson@intel.com> writes:

> Combine the for-loops for Hyper-V TLB EPTP checking and flushing, and in
> doing so skip flushes for vCPUs whose EPTP matches the target EPTP.
>
> Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
> ---
>  arch/x86/kvm/vmx/vmx.c | 20 ++++++--------------
>  1 file changed, 6 insertions(+), 14 deletions(-)
>
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index bba6d91f1fe1..52cb9eec1db3 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -502,31 +502,23 @@ static int hv_remote_flush_tlb_with_range(struct kvm *kvm,
>  
>  	spin_lock(&kvm_vmx->ept_pointer_lock);
>  
> -	if (kvm_vmx->ept_pointers_match == EPT_POINTERS_CHECK) {
> +	if (kvm_vmx->ept_pointers_match != EPT_POINTERS_MATCH) {
>  		kvm_vmx->ept_pointers_match = EPT_POINTERS_MATCH;
>  		kvm_vmx->hv_tlb_eptp = INVALID_PAGE;
>  
>  		kvm_for_each_vcpu(i, vcpu, kvm) {
>  			tmp_eptp = to_vmx(vcpu)->ept_pointer;
> -			if (!VALID_PAGE(tmp_eptp))
> +			if (!VALID_PAGE(tmp_eptp) ||
> +			    tmp_eptp == kvm_vmx->hv_tlb_eptp)
>  				continue;
>  
> -			if (!VALID_PAGE(kvm_vmx->hv_tlb_eptp)) {
> +			if (!VALID_PAGE(kvm_vmx->hv_tlb_eptp))
>  				kvm_vmx->hv_tlb_eptp = tmp_eptp;
> -			} else if (kvm_vmx->hv_tlb_eptp != tmp_eptp) {
> +			else
>  				kvm_vmx->ept_pointers_match
>  					= EPT_POINTERS_MISMATCH;
> -				break;
> -			}
> -		}
> -	}
>  
> -	if (kvm_vmx->ept_pointers_match != EPT_POINTERS_MATCH) {
> -		kvm_for_each_vcpu(i, vcpu, kvm) {
> -			/* If ept_pointer is invalid pointer, bypass flush request. */
> -			if (VALID_PAGE(to_vmx(vcpu)->ept_pointer))
> -				ret |= hv_remote_flush_eptp(to_vmx(vcpu)->ept_pointer,
> -							    range);
> +			ret |= hv_remote_flush_eptp(tmp_eptp, range);
>  		}
>  	} else if (VALID_PAGE(kvm_vmx->hv_tlb_eptp)) {
>  		ret = hv_remote_flush_eptp(kvm_vmx->hv_tlb_eptp, range);

Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>

I have an unrelated question though. Does it make sense to call
hv_remote_flush_eptp() in case all EPTPs matches with ept_pointer_lock
spinlock held? Like if we had a match by the time of the call, does it
make a difference if the situation will change before or right after we
do the hypercall?
diff mbox series

Patch

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index bba6d91f1fe1..52cb9eec1db3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -502,31 +502,23 @@  static int hv_remote_flush_tlb_with_range(struct kvm *kvm,
 
 	spin_lock(&kvm_vmx->ept_pointer_lock);
 
-	if (kvm_vmx->ept_pointers_match == EPT_POINTERS_CHECK) {
+	if (kvm_vmx->ept_pointers_match != EPT_POINTERS_MATCH) {
 		kvm_vmx->ept_pointers_match = EPT_POINTERS_MATCH;
 		kvm_vmx->hv_tlb_eptp = INVALID_PAGE;
 
 		kvm_for_each_vcpu(i, vcpu, kvm) {
 			tmp_eptp = to_vmx(vcpu)->ept_pointer;
-			if (!VALID_PAGE(tmp_eptp))
+			if (!VALID_PAGE(tmp_eptp) ||
+			    tmp_eptp == kvm_vmx->hv_tlb_eptp)
 				continue;
 
-			if (!VALID_PAGE(kvm_vmx->hv_tlb_eptp)) {
+			if (!VALID_PAGE(kvm_vmx->hv_tlb_eptp))
 				kvm_vmx->hv_tlb_eptp = tmp_eptp;
-			} else if (kvm_vmx->hv_tlb_eptp != tmp_eptp) {
+			else
 				kvm_vmx->ept_pointers_match
 					= EPT_POINTERS_MISMATCH;
-				break;
-			}
-		}
-	}
 
-	if (kvm_vmx->ept_pointers_match != EPT_POINTERS_MATCH) {
-		kvm_for_each_vcpu(i, vcpu, kvm) {
-			/* If ept_pointer is invalid pointer, bypass flush request. */
-			if (VALID_PAGE(to_vmx(vcpu)->ept_pointer))
-				ret |= hv_remote_flush_eptp(to_vmx(vcpu)->ept_pointer,
-							    range);
+			ret |= hv_remote_flush_eptp(tmp_eptp, range);
 		}
 	} else if (VALID_PAGE(kvm_vmx->hv_tlb_eptp)) {
 		ret = hv_remote_flush_eptp(kvm_vmx->hv_tlb_eptp, range);