1 files changed, 32 insertions, 16 deletions

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 0e21ccc46792..101f53ccf571 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1446,7 +1446,7 @@ static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 	return vcpu->arch.tsc_offset;
 }
 
-static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
+static u64 svm_write_l1_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 g_tsc_offset = 0;
@@ -1464,6 +1464,7 @@ static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 	svm->vmcb->control.tsc_offset = offset + g_tsc_offset;
 
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
+	return svm->vmcb->control.tsc_offset;
 }
 
 static void avic_init_vmcb(struct vcpu_svm *svm)
@@ -1664,20 +1665,23 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
 static int avic_init_access_page(struct kvm_vcpu *vcpu)
 {
 	struct kvm *kvm = vcpu->kvm;
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&kvm->slots_lock);
 	if (kvm->arch.apic_access_page_done)
-		return 0;
+		goto out;
 
-	ret = x86_set_memory_region(kvm,
-				    APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
-				    APIC_DEFAULT_PHYS_BASE,
-				    PAGE_SIZE);
+	ret = __x86_set_memory_region(kvm,
+				      APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+				      APIC_DEFAULT_PHYS_BASE,
+				      PAGE_SIZE);
 	if (ret)
-		return ret;
+		goto out;
 
 	kvm->arch.apic_access_page_done = true;
-	return 0;
+out:
+	mutex_unlock(&kvm->slots_lock);
+	return ret;
 }
 
 static int avic_init_backing_page(struct kvm_vcpu *vcpu)
@@ -2189,21 +2193,31 @@ out:
 	return ERR_PTR(err);
 }
 
+static void svm_clear_current_vmcb(struct vmcb *vmcb)
+{
+	int i;
+
+	for_each_online_cpu(i)
+		cmpxchg(&per_cpu(svm_data, i)->current_vmcb, vmcb, NULL);
+}
+
 static void svm_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	/*
+	 * The vmcb page can be recycled, causing a false negative in
+	 * svm_vcpu_load(). So, ensure that no logical CPU has this
+	 * vmcb page recorded as its current vmcb.
+	 */
+	svm_clear_current_vmcb(svm->vmcb);
+
 	__free_page(pfn_to_page(__sme_clr(svm->vmcb_pa) >> PAGE_SHIFT));
 	__free_pages(virt_to_page(svm->msrpm), MSRPM_ALLOC_ORDER);
 	__free_page(virt_to_page(svm->nested.hsave));
 	__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
 	kvm_vcpu_uninit(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, svm);
-	/*
-	 * The vmcb page can be recycled, causing a false negative in
-	 * svm_vcpu_load(). So do a full IBPB now.
-	 */
-	indirect_branch_prediction_barrier();
 }
 
 static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
@@ -2923,6 +2937,8 @@ static void nested_svm_inject_npf_exit(struct kvm_vcpu *vcpu,
 static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 {
 	WARN_ON(mmu_is_nested(vcpu));
+
+	vcpu->arch.mmu = &vcpu->arch.guest_mmu;
 	kvm_init_shadow_mmu(vcpu);
 	vcpu->arch.mmu->set_cr3           = nested_svm_set_tdp_cr3;
 	vcpu->arch.mmu->get_cr3           = nested_svm_get_tdp_cr3;
@@ -2935,6 +2951,7 @@ static void nested_svm_init_mmu_context(struct kvm_vcpu *vcpu)
 
 static void nested_svm_uninit_mmu_context(struct kvm_vcpu *vcpu)
 {
+	vcpu->arch.mmu = &vcpu->arch.root_mmu;
 	vcpu->arch.walk_mmu = &vcpu->arch.root_mmu;
 }
 
@@ -3444,7 +3461,6 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 		svm->vcpu.arch.hflags &= ~HF_HIF_MASK;
 
 	if (nested_vmcb->control.nested_ctl & SVM_NESTED_CTL_NP_ENABLE) {
-		kvm_mmu_unload(&svm->vcpu);
 		svm->nested.nested_cr3 = nested_vmcb->control.nested_cr3;
 		nested_svm_init_mmu_context(&svm->vcpu);
 	}
@@ -7149,7 +7165,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
 	.read_l1_tsc_offset = svm_read_l1_tsc_offset,
-	.write_tsc_offset = svm_write_tsc_offset,
+	.write_l1_tsc_offset = svm_write_l1_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,