1 files changed, 27 insertions, 15 deletions

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9a8969a6dd06..1b404e4d7dd8 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -105,6 +105,7 @@ static u64 __read_mostly cr4_reserved_bits = CR4_RESERVED_BITS;
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu);
 static void process_nmi(struct kvm_vcpu *vcpu);
+static void process_smi(struct kvm_vcpu *vcpu);
 static void enter_smm(struct kvm_vcpu *vcpu);
 static void __kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags);
 static void store_regs(struct kvm_vcpu *vcpu);
@@ -1393,16 +1394,24 @@ static u64 kvm_get_arch_capabilities(void)
 	if (!boot_cpu_has_bug(X86_BUG_MDS))
 		data |= ARCH_CAP_MDS_NO;
 
-	/*
-	 * On TAA affected systems:
-	 *      - nothing to do if TSX is disabled on the host.
-	 *      - we emulate TSX_CTRL if present on the host.
-	 *	  This lets the guest use VERW to clear CPU buffers.
-	 */
-	if (!boot_cpu_has(X86_FEATURE_RTM))
-		data &= ~(ARCH_CAP_TAA_NO | ARCH_CAP_TSX_CTRL_MSR);
-	else if (!boot_cpu_has_bug(X86_BUG_TAA))
+	if (!boot_cpu_has(X86_FEATURE_RTM)) {
+		/*
+		 * If RTM=0 because the kernel has disabled TSX, the host might
+		 * have TAA_NO or TSX_CTRL.  Clear TAA_NO (the guest sees RTM=0
+		 * and therefore knows that there cannot be TAA) but keep
+		 * TSX_CTRL: some buggy userspaces leave it set on tsx=on hosts,
+		 * and we want to allow migrating those guests to tsx=off hosts.
+		 */
+		data &= ~ARCH_CAP_TAA_NO;
+	} else if (!boot_cpu_has_bug(X86_BUG_TAA)) {
 		data |= ARCH_CAP_TAA_NO;
+	} else {
+		/*
+		 * Nothing to do here; we emulate TSX_CTRL if present on the
+		 * host so the guest can choose between disabling TSX or
+		 * using VERW to clear CPU buffers.
+		 */
+	}
 
 	return data;
 }
@@ -4230,6 +4239,9 @@ static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
 {
 	process_nmi(vcpu);
 
+	if (kvm_check_request(KVM_REQ_SMI, vcpu))
+		process_smi(vcpu);
+
 	/*
 	 * In guest mode, payload delivery should be deferred,
 	 * so that the L1 hypervisor can intercept #PF before
@@ -8802,9 +8814,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 
 	if (kvm_request_pending(vcpu)) {
 		if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
-			if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
-				;
-			else if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
+			if (unlikely(!kvm_x86_ops.nested_ops->get_nested_state_pages(vcpu))) {
 				r = 0;
 				goto out;
 			}
@@ -8988,8 +8998,6 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		kvm_x86_ops.request_immediate_exit(vcpu);
 	}
 
-	trace_kvm_entry(vcpu);
-
 	fpregs_assert_state_consistent();
 	if (test_thread_flag(TIF_NEED_FPU_LOAD))
 		switch_fpu_return();
@@ -9616,6 +9624,8 @@ static bool kvm_is_valid_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
 		 */
 		if (!(sregs->cr4 & X86_CR4_PAE) || !(sregs->efer & EFER_LMA))
 			return false;
+		if (sregs->cr3 & vcpu->arch.cr3_lm_rsvd_bits)
+			return false;
 	} else {
 		/*
 		 * Not in 64-bit mode: EFER.LMA is clear and the code
@@ -9993,6 +10003,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	fx_init(vcpu);
 
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+	vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
 
 	vcpu->arch.pat = MSR_IA32_CR_PAT_DEFAULT;
 
@@ -10494,7 +10505,7 @@ void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
 			return 0;
 
 		old_npages = slot->npages;
-		hva = 0;
+		hva = slot->userspace_addr;
 	}
 
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
@@ -11556,6 +11567,7 @@ int kvm_sev_es_string_io(struct kvm_vcpu *vcpu, unsigned int size,
 }
 EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);