1 files changed, 63 insertions, 22 deletions

diff --git a/kernel/arch/x86/kvm/vmx.c b/kernel/arch/x86/kvm/vmx.c
index a722f724c..8d744a82f 100644
--- a/kernel/arch/x86/kvm/vmx.c
+++ b/kernel/arch/x86/kvm/vmx.c
@@ -415,6 +415,7 @@ struct nested_vmx {
 	struct list_head vmcs02_pool;
 	int vmcs02_num;
 	u64 vmcs01_tsc_offset;
+	bool change_vmcs01_virtual_x2apic_mode;
 	/* L2 must run next, and mustn't decide to exit to L1. */
 	bool nested_run_pending;
 	/*
@@ -1308,10 +1309,10 @@ static inline bool nested_cpu_has_posted_intr(struct vmcs12 *vmcs12)
 	return vmcs12->pin_based_vm_exec_control & PIN_BASED_POSTED_INTR;
 }
 
-static inline bool is_exception(u32 intr_info)
+static inline bool is_nmi(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VALID_MASK))
-		== (INTR_TYPE_HARD_EXCEPTION | INTR_INFO_VALID_MASK);
+		== (INTR_TYPE_NMI_INTR | INTR_INFO_VALID_MASK);
 }
 
 static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
@@ -2699,8 +2700,15 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 	} else
 		vmx->nested.nested_vmx_ept_caps = 0;
 
+	/*
+	 * Old versions of KVM use the single-context version without
+	 * checking for support, so declare that it is supported even
+	 * though it is treated as global context.  The alternative is
+	 * not failing the single-context invvpid, and it is worse.
+	 */
 	if (enable_vpid)
 		vmx->nested.nested_vmx_vpid_caps = VMX_VPID_INVVPID_BIT |
+				VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT |
 				VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT;
 	else
 		vmx->nested.nested_vmx_vpid_caps = 0;
@@ -5016,8 +5024,8 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
 
 	cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
-	vmx_set_cr0(vcpu, cr0); /* enter rmode */
 	vmx->vcpu.arch.cr0 = cr0;
+	vmx_set_cr0(vcpu, cr0); /* enter rmode */
 	vmx_set_cr4(vcpu, 0);
 	vmx_set_efer(vcpu, 0);
 	vmx_fpu_activate(vcpu);
@@ -5295,7 +5303,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 	if (is_machine_check(intr_info))
 		return handle_machine_check(vcpu);
 
-	if ((intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR)
+	if (is_nmi(intr_info))
 		return 1;  /* already handled by vmx_vcpu_run() */
 
 	if (is_no_device(intr_info)) {
@@ -6652,7 +6660,13 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 
 	/* Checks for #GP/#SS exceptions. */
 	exn = false;
-	if (is_protmode(vcpu)) {
+	if (is_long_mode(vcpu)) {
+		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
+		 * non-canonical form. This is the only check on the memory
+		 * destination for long mode!
+		 */
+		exn = is_noncanonical_address(*ret);
+	} else if (is_protmode(vcpu)) {
 		/* Protected mode: apply checks for segment validity in the
 		 * following order:
 		 * - segment type check (#GP(0) may be thrown)
@@ -6669,17 +6683,10 @@ static int get_vmx_mem_address(struct kvm_vcpu *vcpu,
 			 * execute-only code segment
 			 */
 			exn = ((s.type & 0xa) == 8);
-	}
-	if (exn) {
-		kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
-		return 1;
-	}
-	if (is_long_mode(vcpu)) {
-		/* Long mode: #GP(0)/#SS(0) if the memory address is in a
-		 * non-canonical form. This is an only check for long mode.
-		 */
-		exn = is_noncanonical_address(*ret);
-	} else if (is_protmode(vcpu)) {
+		if (exn) {
+			kvm_queue_exception_e(vcpu, GP_VECTOR, 0);
+			return 1;
+		}
 		/* Protected mode: #GP(0)/#SS(0) if the segment is unusable.
 		 */
 		exn = (s.unusable != 0);
@@ -7420,6 +7427,7 @@ static int handle_invept(struct kvm_vcpu *vcpu)
 	if (!(types & (1UL << type))) {
 		nested_vmx_failValid(vcpu,
 				VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		skip_emulated_instruction(vcpu);
 		return 1;
 	}
 
@@ -7478,6 +7486,7 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	if (!(types & (1UL << type))) {
 		nested_vmx_failValid(vcpu,
 			VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+		skip_emulated_instruction(vcpu);
 		return 1;
 	}
 
@@ -7494,12 +7503,17 @@ static int handle_invvpid(struct kvm_vcpu *vcpu)
 	}
 
 	switch (type) {
+	case VMX_VPID_EXTENT_SINGLE_CONTEXT:
+		/*
+		 * Old versions of KVM use the single-context version so we
+		 * have to support it; just treat it the same as all-context.
+		 */
 	case VMX_VPID_EXTENT_ALL_CONTEXT:
 		__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02);
 		nested_vmx_succeed(vcpu);
 		break;
 	default:
-		/* Trap single context invalidation invvpid calls */
+		/* Trap individual address invalidation invvpid calls */
 		BUG_ON(1);
 		break;
 	}
@@ -7795,7 +7809,7 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 
 	switch (exit_reason) {
 	case EXIT_REASON_EXCEPTION_NMI:
-		if (!is_exception(intr_info))
+		if (is_nmi(intr_info))
 			return false;
 		else if (is_page_fault(intr_info))
 			return enable_ept;
@@ -8200,6 +8214,7 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	if ((vectoring_info & VECTORING_INFO_VALID_MASK) &&
 			(exit_reason != EXIT_REASON_EXCEPTION_NMI &&
 			exit_reason != EXIT_REASON_EPT_VIOLATION &&
+			exit_reason != EXIT_REASON_PML_FULL &&
 			exit_reason != EXIT_REASON_TASK_SWITCH)) {
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_DELIVERY_EV;
@@ -8259,6 +8274,12 @@ static void vmx_set_virtual_x2apic_mode(struct kvm_vcpu *vcpu, bool set)
 {
 	u32 sec_exec_control;
 
+	/* Postpone execution until vmcs01 is the current VMCS. */
+	if (is_guest_mode(vcpu)) {
+		to_vmx(vcpu)->nested.change_vmcs01_virtual_x2apic_mode = true;
+		return;
+	}
+
 	/*
 	 * There is not point to enable virtualize x2apic without enable
 	 * apicv
@@ -8397,8 +8418,7 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 		kvm_machine_check();
 
 	/* We need to handle NMIs before interrupts are enabled */
-	if ((exit_intr_info & INTR_INFO_INTR_TYPE_MASK) == INTR_TYPE_NMI_INTR &&
-	    (exit_intr_info & INTR_INFO_VALID_MASK)) {
+	if (is_nmi(exit_intr_info)) {
 		kvm_before_handle_nmi(&vmx->vcpu);
 		asm("int $2");
 		kvm_after_handle_nmi(&vmx->vcpu);
@@ -8834,6 +8854,22 @@ static void vmx_load_vmcs01(struct kvm_vcpu *vcpu)
 	put_cpu();
 }
 
+/*
+ * Ensure that the current vmcs of the logical processor is the
+ * vmcs01 of the vcpu before calling free_nested().
+ */
+static void vmx_free_vcpu_nested(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+       int r;
+
+       r = vcpu_load(vcpu);
+       BUG_ON(r);
+       vmx_load_vmcs01(vcpu);
+       free_nested(vmx);
+       vcpu_put(vcpu);
+}
+
 static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -8842,8 +8878,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
 		vmx_destroy_pml_buffer(vmx);
 	free_vpid(vmx->vpid);
 	leave_guest_mode(vcpu);
-	vmx_load_vmcs01(vcpu);
-	free_nested(vmx);
+	vmx_free_vcpu_nested(vcpu);
 	free_loaded_vmcs(vmx->loaded_vmcs);
 	kfree(vmx->guest_msrs);
 	kvm_vcpu_uninit(vcpu);
@@ -10576,6 +10611,12 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
 			      PIN_BASED_VMX_PREEMPTION_TIMER);
 
+	if (vmx->nested.change_vmcs01_virtual_x2apic_mode) {
+		vmx->nested.change_vmcs01_virtual_x2apic_mode = false;
+		vmx_set_virtual_x2apic_mode(vcpu,
+				vcpu->arch.apic_base & X2APIC_ENABLE);
+	}
+
 	/* This is needed for same reason as it was needed in prepare_vmcs02 */
 	vmx->host_rsp = 0;