KVM: x86: Avoid guest page table walk when gpa_available is set

When a guest causes a page fault which requires emulation, the
vcpu->arch.gpa_available flag is set to indicate that cr2 contains a
valid GPA.

Currently, emulator_read_write_onepage() makes use of gpa_available flag
to avoid a guest page walk for a known MMIO regions. Lets not limit
the gpa_available optimization to just MMIO region. The patch extends
the check to avoid page walk whenever gpa_available flag is set.

Signed-off-by: Brijesh Singh <[email protected]>
[Fix EPT=0 according to Wanpeng Li's fix, plus ensure VMX also uses the
 new code. - Paolo]
Signed-off-by: Paolo Bonzini <[email protected]>
Reviewed-by: David Hildenbrand <[email protected]>
[Moved "ret < 0" to the else brach, as per David's review. - Radim]
Signed-off-by: Radim Krčmář <[email protected]>

arch/x86/include/asm/kvm_host.h

@@ -685,8 +685,9 @@ struct kvm_vcpu_arch {
 	int pending_ioapic_eoi;
 	int pending_external_vector;
 
-	/* GPA available (AMD only) */
+	/* GPA available */
 	bool gpa_available;
+	gpa_t gpa_val;
 
 	/* be preempted when it's in kernel-mode(cpl=0) */
 	bool preempted_in_kernel;

arch/x86/kvm/mmu.c

@@ -4843,6 +4843,12 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u64 error_code,
 	enum emulation_result er;
 	bool direct = vcpu->arch.mmu.direct_map || mmu_is_nested(vcpu);
 
+	/* With shadow page tables, fault_address contains a GVA or nGPA.  */
+	if (vcpu->arch.mmu.direct_map) {
+		vcpu->arch.gpa_available = true;
+		vcpu->arch.gpa_val = cr2;
+	}
+
 	if (unlikely(error_code & PFERR_RSVD_MASK)) {
 		r = handle_mmio_page_fault(vcpu, cr2, direct);
 		if (r == RET_MMIO_PF_EMULATE) {

arch/x86/kvm/svm.c

@@ -4236,8 +4236,6 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 
 	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
 
-	vcpu->arch.gpa_available = (exit_code == SVM_EXIT_NPF);
-
 	if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
 	if (npt_enabled)

arch/x86/kvm/vmx.c

@@ -6393,9 +6393,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
 	error_code |= (exit_qualification & 0x100) != 0 ?
 	       PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
 
-	vcpu->arch.gpa_available = true;
 	vcpu->arch.exit_qualification = exit_qualification;
-
 	return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
 }
 
@@ -6410,7 +6408,6 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
 		return kvm_skip_emulated_instruction(vcpu);
 	}
 
-	vcpu->arch.gpa_available = true;
 	ret = kvm_mmu_page_fault(vcpu, gpa, PFERR_RSVD_MASK, NULL, 0);
 	if (ret >= 0)
 		return ret;
@@ -8644,7 +8641,6 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	u32 vectoring_info = vmx->idt_vectoring_info;
 
 	trace_kvm_exit(exit_reason, vcpu, KVM_ISA_VMX);
-	vcpu->arch.gpa_available = false;
 
 	/*
 	 * Flush logged GPAs PML buffer, this will make dirty_bitmap more

arch/x86/kvm/x86.c

@@ -4657,25 +4657,18 @@ static int emulator_read_write_onepage(unsigned long addr, void *val,
 	 */
 	if (vcpu->arch.gpa_available &&
 	    emulator_can_use_gpa(ctxt) &&
-	    vcpu_is_mmio_gpa(vcpu, addr, exception->address, write) &&
-	    (addr & ~PAGE_MASK) == (exception->address & ~PAGE_MASK)) {
-		gpa = exception->address;
-		goto mmio;
+	    (addr & ~PAGE_MASK) == (vcpu->arch.gpa_val & ~PAGE_MASK)) {
+		gpa = vcpu->arch.gpa_val;
+		ret = vcpu_is_mmio_gpa(vcpu, addr, gpa, write);
+	} else {
+		ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
+		if (ret < 0)
+			return X86EMUL_PROPAGATE_FAULT;
 	}
 
-	ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
-
-	if (ret < 0)
-		return X86EMUL_PROPAGATE_FAULT;
-
-	/* For APIC access vmexit */
-	if (ret)
-		goto mmio;
-
-	if (ops->read_write_emulate(vcpu, gpa, val, bytes))
+	if (!ret && ops->read_write_emulate(vcpu, gpa, val, bytes))
 		return X86EMUL_CONTINUE;
 
-mmio:
 	/*
 	 * Is this MMIO handled locally?
 	 */
@@ -7002,6 +6995,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	if (vcpu->arch.apic_attention)
 		kvm_lapic_sync_from_vapic(vcpu);
 
+	vcpu->arch.gpa_available = false;
 	r = kvm_x86_ops->handle_exit(vcpu);
 	return r;