KVM: x86: Pull the PGD's level from the MMU instead of recalculating it

Use the shadow_root_level from the current MMU as the root level for the
PGD, i.e. for VMX's EPTP.  This eliminates the weird dependency between
VMX and the MMU where both must independently calculate the same root
level for things to work correctly.  Temporarily keep VMX's calculation
of the level and use it to WARN if the incoming level diverges.

Opportunistically refactor kvm_mmu_load_pgd() to avoid indentation hell,
and rename a 'cr3' param in the load_mmu_pgd prototype that managed to
survive the cr3 purge.

No functional change intended.

Signed-off-by: Sean Christopherson <[email protected]>
Message-Id: <[email protected]>
Signed-off-by: Paolo Bonzini <[email protected]>

Author: Sean Christopherson

arch/x86/include/asm/kvm_host.h

@@ -1136,7 +1136,8 @@ struct kvm_x86_ops {
 	int (*get_tdp_level)(struct kvm_vcpu *vcpu);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 
-	void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, unsigned long cr3);
+	void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, unsigned long pgd,
+			     int pgd_level);
 
 	bool (*has_wbinvd_exit)(void);
 

arch/x86/kvm/mmu.h

@@ -90,9 +90,13 @@ static inline unsigned long kvm_get_active_pcid(struct kvm_vcpu *vcpu)
 
 static inline void kvm_mmu_load_pgd(struct kvm_vcpu *vcpu)
 {
-	if (VALID_PAGE(vcpu->arch.mmu->root_hpa))
-		kvm_x86_ops.load_mmu_pgd(vcpu, vcpu->arch.mmu->root_hpa |
-					       kvm_get_active_pcid(vcpu));
+	u64 root_hpa = vcpu->arch.mmu->root_hpa;
+
+	if (!VALID_PAGE(root_hpa))
+		return;
+
+	kvm_x86_ops.load_mmu_pgd(vcpu, root_hpa | kvm_get_active_pcid(vcpu),
+				 vcpu->arch.mmu->shadow_root_level);
 }
 
 int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,

arch/x86/kvm/svm/svm.c

@@ -3541,7 +3541,8 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu)
 	return exit_fastpath;
 }
 
-static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root)
+static void svm_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long root,
+			     int root_level)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	unsigned long cr3;

arch/x86/kvm/vmx/nested.c

@@ -2162,7 +2162,8 @@ static void prepare_vmcs02_constant_state(struct vcpu_vmx *vmx)
 	 * consistency checks.
 	 */
 	if (enable_ept && nested_early_check)
-		vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0));
+		vmcs_write64(EPT_POINTER,
+			     construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));
 
 	/* All VMFUNCs are currently emulated through L0 vmexits.  */
 	if (cpu_has_vmx_vmfunc())

arch/x86/kvm/vmx/vmx.c

@@ -2933,14 +2933,16 @@ static void vmx_flush_tlb_all(struct kvm_vcpu *vcpu)
 
 static void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 {
-	u64 root_hpa = vcpu->arch.mmu->root_hpa;
+	struct kvm_mmu *mmu = vcpu->arch.mmu;
+	u64 root_hpa = mmu->root_hpa;
 
 	/* No flush required if the current context is invalid. */
 	if (!VALID_PAGE(root_hpa))
 		return;
 
 	if (enable_ept)
-		ept_sync_context(construct_eptp(vcpu, root_hpa));
+		ept_sync_context(construct_eptp(vcpu, root_hpa,
+						mmu->shadow_root_level));
 	else if (!is_guest_mode(vcpu))
 		vpid_sync_context(to_vmx(vcpu)->vpid);
 	else
@@ -3078,11 +3080,12 @@ static int get_ept_level(struct kvm_vcpu *vcpu)
 	return vmx_get_tdp_level(vcpu);
 }
 
-u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
+u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa,
+		   int root_level)
 {
 	u64 eptp = VMX_EPTP_MT_WB;
 
-	eptp |= (get_ept_level(vcpu) == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
+	eptp |= (root_level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
 
 	if (enable_ept_ad_bits &&
 	    (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
@@ -3092,15 +3095,18 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa)
 	return eptp;
 }
 
-static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd)
+static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, unsigned long pgd,
+			     int pgd_level)
 {
 	struct kvm *kvm = vcpu->kvm;
 	bool update_guest_cr3 = true;
 	unsigned long guest_cr3;
 	u64 eptp;
 
 	if (enable_ept) {
-		eptp = construct_eptp(vcpu, pgd);
+		WARN_ON(pgd_level != get_ept_level(vcpu));
+
+		eptp = construct_eptp(vcpu, pgd, pgd_level);
 		vmcs_write64(EPT_POINTER, eptp);
 
 		if (kvm_x86_ops.tlb_remote_flush) {

arch/x86/kvm/vmx/vmx.h

@@ -341,7 +341,8 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx);
 void ept_save_pdptrs(struct kvm_vcpu *vcpu);
 void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
-u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa);
+u64 construct_eptp(struct kvm_vcpu *vcpu, unsigned long root_hpa,
+		   int root_level);
 void update_exception_bitmap(struct kvm_vcpu *vcpu);
 void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu);
 bool vmx_nmi_blocked(struct kvm_vcpu *vcpu);