1 files changed, 186 insertions, 50 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index aa157fe5b7b3..546272a5d34d 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1344,22 +1344,35 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
 }
 
 #ifdef CONFIG_X86_64
-static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
+static u64 vmx_read_guest_host_msr(struct vcpu_vmx *vmx, u32 msr, u64 *cache)
 {
 	preempt_disable();
 	if (vmx->vt.guest_state_loaded)
-		rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+		*cache = read_msr(msr);
 	preempt_enable();
-	return vmx->msr_guest_kernel_gs_base;
+	return *cache;
 }
 
-static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
+static void vmx_write_guest_host_msr(struct vcpu_vmx *vmx, u32 msr, u64 data,
+				     u64 *cache)
 {
 	preempt_disable();
 	if (vmx->vt.guest_state_loaded)
-		wrmsrq(MSR_KERNEL_GS_BASE, data);
+		wrmsrns(msr, data);
 	preempt_enable();
-	vmx->msr_guest_kernel_gs_base = data;
+	*cache = data;
+}
+
+static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
+{
+	return vmx_read_guest_host_msr(vmx, MSR_KERNEL_GS_BASE,
+				       &vmx->msr_guest_kernel_gs_base);
+}
+
+static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
+{
+	vmx_write_guest_host_msr(vmx, MSR_KERNEL_GS_BASE, data,
+				 &vmx->msr_guest_kernel_gs_base);
 }
 #endif
 
@@ -2093,6 +2106,15 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		else
 			msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
 		break;
+	case MSR_IA32_S_CET:
+		msr_info->data = vmcs_readl(GUEST_S_CET);
+		break;
+	case MSR_KVM_INTERNAL_GUEST_SSP:
+		msr_info->data = vmcs_readl(GUEST_SSP);
+		break;
+	case MSR_IA32_INT_SSP_TAB:
+		msr_info->data = vmcs_readl(GUEST_INTR_SSP_TABLE);
+		break;
 	case MSR_IA32_DEBUGCTLMSR:
 		msr_info->data = vmx_guest_debugctl_read();
 		break;
@@ -2127,7 +2149,7 @@ u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
 	    (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)))
 		debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
 
-	if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) &&
+	if ((kvm_caps.supported_perf_cap & PERF_CAP_LBR_FMT) &&
 	    (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
 		debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 
@@ -2411,10 +2433,19 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		else
 			vmx->pt_desc.guest.addr_a[index / 2] = data;
 		break;
+	case MSR_IA32_S_CET:
+		vmcs_writel(GUEST_S_CET, data);
+		break;
+	case MSR_KVM_INTERNAL_GUEST_SSP:
+		vmcs_writel(GUEST_SSP, data);
+		break;
+	case MSR_IA32_INT_SSP_TAB:
+		vmcs_writel(GUEST_INTR_SSP_TABLE, data);
+		break;
 	case MSR_IA32_PERF_CAPABILITIES:
-		if (data & PMU_CAP_LBR_FMT) {
-			if ((data & PMU_CAP_LBR_FMT) !=
-			    (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT))
+		if (data & PERF_CAP_LBR_FMT) {
+			if ((data & PERF_CAP_LBR_FMT) !=
+			    (kvm_caps.supported_perf_cap & PERF_CAP_LBR_FMT))
 				return 1;
 			if (!cpuid_model_is_consistent(vcpu))
 				return 1;
@@ -2584,6 +2615,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
 		{ VM_ENTRY_LOAD_IA32_EFER,		VM_EXIT_LOAD_IA32_EFER },
 		{ VM_ENTRY_LOAD_BNDCFGS,		VM_EXIT_CLEAR_BNDCFGS },
 		{ VM_ENTRY_LOAD_IA32_RTIT_CTL,		VM_EXIT_CLEAR_IA32_RTIT_CTL },
+		{ VM_ENTRY_LOAD_CET_STATE,		VM_EXIT_LOAD_CET_STATE },
 	};
 
 	memset(vmcs_conf, 0, sizeof(*vmcs_conf));
@@ -4068,8 +4100,10 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
 	}
 }
 
-void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
+static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
 {
+	bool intercept;
+
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
 
@@ -4115,12 +4149,34 @@ void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
 		vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W,
 					  !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
 
+	if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) {
+		intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK);
+
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL0_SSP, MSR_TYPE_RW, intercept);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL1_SSP, MSR_TYPE_RW, intercept);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL2_SSP, MSR_TYPE_RW, intercept);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_PL3_SSP, MSR_TYPE_RW, intercept);
+	}
+
+	if (kvm_cpu_cap_has(X86_FEATURE_SHSTK) || kvm_cpu_cap_has(X86_FEATURE_IBT)) {
+		intercept = !guest_cpu_cap_has(vcpu, X86_FEATURE_IBT) &&
+			    !guest_cpu_cap_has(vcpu, X86_FEATURE_SHSTK);
+
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_U_CET, MSR_TYPE_RW, intercept);
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_S_CET, MSR_TYPE_RW, intercept);
+	}
+
 	/*
 	 * x2APIC and LBR MSR intercepts are modified on-demand and cannot be
 	 * filtered by userspace.
 	 */
 }
 
+void vmx_recalc_intercepts(struct kvm_vcpu *vcpu)
+{
+	vmx_recalc_msr_intercepts(vcpu);
+}
+
 static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 						int vector)
 {
@@ -4270,6 +4326,21 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 
 	if (cpu_has_load_ia32_efer())
 		vmcs_write64(HOST_IA32_EFER, kvm_host.efer);
+
+	/*
+	 * Supervisor shadow stack is not enabled on host side, i.e.,
+	 * host IA32_S_CET.SHSTK_EN bit is guaranteed to 0 now, per SDM
+	 * description(RDSSP instruction), SSP is not readable in CPL0,
+	 * so resetting the two registers to 0s at VM-Exit does no harm
+	 * to kernel execution. When execution flow exits to userspace,
+	 * SSP is reloaded from IA32_PL3_SSP. Check SDM Vol.2A/B Chapter
+	 * 3 and 4 for details.
+	 */
+	if (cpu_has_load_cet_ctrl()) {
+		vmcs_writel(HOST_S_CET, kvm_host.s_cet);
+		vmcs_writel(HOST_SSP, 0);
+		vmcs_writel(HOST_INTR_SSP_TABLE, 0);
+	}
 }
 
 void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
@@ -4304,7 +4375,7 @@ static u32 vmx_pin_based_exec_ctrl(struct vcpu_vmx *vmx)
 	return pin_based_exec_ctrl;
 }
 
-static u32 vmx_vmentry_ctrl(void)
+static u32 vmx_get_initial_vmentry_ctrl(void)
 {
 	u32 vmentry_ctrl = vmcs_config.vmentry_ctrl;
 
@@ -4321,7 +4392,7 @@ static u32 vmx_vmentry_ctrl(void)
 	return vmentry_ctrl;
 }
 
-static u32 vmx_vmexit_ctrl(void)
+static u32 vmx_get_initial_vmexit_ctrl(void)
 {
 	u32 vmexit_ctrl = vmcs_config.vmexit_ctrl;
 
@@ -4351,19 +4422,13 @@ void vmx_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 
 	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
 
-	if (kvm_vcpu_apicv_active(vcpu)) {
-		secondary_exec_controls_setbit(vmx,
-					       SECONDARY_EXEC_APIC_REGISTER_VIRT |
-					       SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-		if (enable_ipiv)
-			tertiary_exec_controls_setbit(vmx, TERTIARY_EXEC_IPI_VIRT);
-	} else {
-		secondary_exec_controls_clearbit(vmx,
-						 SECONDARY_EXEC_APIC_REGISTER_VIRT |
-						 SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
-		if (enable_ipiv)
-			tertiary_exec_controls_clearbit(vmx, TERTIARY_EXEC_IPI_VIRT);
-	}
+	secondary_exec_controls_changebit(vmx,
+					  SECONDARY_EXEC_APIC_REGISTER_VIRT |
+					  SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY,
+					  kvm_vcpu_apicv_active(vcpu));
+	if (enable_ipiv)
+		tertiary_exec_controls_changebit(vmx, TERTIARY_EXEC_IPI_VIRT,
+						 kvm_vcpu_apicv_active(vcpu));
 
 	vmx_update_msr_bitmap_x2apic(vcpu);
 }
@@ -4686,10 +4751,10 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 
-	vm_exit_controls_set(vmx, vmx_vmexit_ctrl());
+	vm_exit_controls_set(vmx, vmx_get_initial_vmexit_ctrl());
 
 	/* 22.2.1, 20.8.1 */
-	vm_entry_controls_set(vmx, vmx_vmentry_ctrl());
+	vm_entry_controls_set(vmx, vmx_get_initial_vmentry_ctrl());
 
 	vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits();
 	vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits);
@@ -4817,6 +4882,14 @@ void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 
 	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);  /* 22.2.1 */
 
+	if (kvm_cpu_cap_has(X86_FEATURE_SHSTK)) {
+		vmcs_writel(GUEST_SSP, 0);
+		vmcs_writel(GUEST_INTR_SSP_TABLE, 0);
+	}
+	if (kvm_cpu_cap_has(X86_FEATURE_IBT) ||
+	    kvm_cpu_cap_has(X86_FEATURE_SHSTK))
+		vmcs_writel(GUEST_S_CET, 0);
+
 	kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
 
 	vpid_sync_context(vmx->vpid);
@@ -5785,6 +5858,13 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 		if (kvm_test_request(KVM_REQ_EVENT, vcpu))
 			return 1;
 
+		/*
+		 * Ensure that any updates to kvm->buses[] observed by the
+		 * previous instruction (emulated or otherwise) are also
+		 * visible to the instruction KVM is about to emulate.
+		 */
+		smp_rmb();
+
 		if (!kvm_emulate_instruction(vcpu, 0))
 			return 0;
 
@@ -6003,6 +6083,23 @@ static int handle_notify(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static int vmx_get_msr_imm_reg(struct kvm_vcpu *vcpu)
+{
+	return vmx_get_instr_info_reg(vmcs_read32(VMX_INSTRUCTION_INFO));
+}
+
+static int handle_rdmsr_imm(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_rdmsr_imm(vcpu, vmx_get_exit_qual(vcpu),
+				     vmx_get_msr_imm_reg(vcpu));
+}
+
+static int handle_wrmsr_imm(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_wrmsr_imm(vcpu, vmx_get_exit_qual(vcpu),
+				     vmx_get_msr_imm_reg(vcpu));
+}
+
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -6061,6 +6158,8 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_ENCLS]		      = handle_encls,
 	[EXIT_REASON_BUS_LOCK]                = handle_bus_lock_vmexit,
 	[EXIT_REASON_NOTIFY]		      = handle_notify,
+	[EXIT_REASON_MSR_READ_IMM]            = handle_rdmsr_imm,
+	[EXIT_REASON_MSR_WRITE_IMM]           = handle_wrmsr_imm,
 };
 
 static const int kvm_vmx_max_exit_handlers =
@@ -6265,6 +6364,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu)
 	if (vmcs_read32(VM_EXIT_MSR_STORE_COUNT) > 0)
 		vmx_dump_msrs("guest autostore", &vmx->msr_autostore.guest);
 
+	if (vmentry_ctl & VM_ENTRY_LOAD_CET_STATE)
+		pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n",
+		       vmcs_readl(GUEST_S_CET), vmcs_readl(GUEST_SSP),
+		       vmcs_readl(GUEST_INTR_SSP_TABLE));
 	pr_err("*** Host State ***\n");
 	pr_err("RIP = 0x%016lx  RSP = 0x%016lx\n",
 	       vmcs_readl(HOST_RIP), vmcs_readl(HOST_RSP));
@@ -6295,6 +6398,10 @@ void dump_vmcs(struct kvm_vcpu *vcpu)
 		       vmcs_read64(HOST_IA32_PERF_GLOBAL_CTRL));
 	if (vmcs_read32(VM_EXIT_MSR_LOAD_COUNT) > 0)
 		vmx_dump_msrs("host autoload", &vmx->msr_autoload.host);
+	if (vmexit_ctl & VM_EXIT_LOAD_CET_STATE)
+		pr_err("S_CET = 0x%016lx, SSP = 0x%016lx, SSP TABLE = 0x%016lx\n",
+		       vmcs_readl(HOST_S_CET), vmcs_readl(HOST_SSP),
+		       vmcs_readl(HOST_INTR_SSP_TABLE));
 
 	pr_err("*** Control State ***\n");
 	pr_err("CPUBased=0x%08x SecondaryExec=0x%08x TertiaryExec=0x%016llx\n",
@@ -6495,6 +6602,8 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
 #ifdef CONFIG_MITIGATION_RETPOLINE
 	if (exit_reason.basic == EXIT_REASON_MSR_WRITE)
 		return kvm_emulate_wrmsr(vcpu);
+	else if (exit_reason.basic == EXIT_REASON_MSR_WRITE_IMM)
+		return handle_wrmsr_imm(vcpu);
 	else if (exit_reason.basic == EXIT_REASON_PREEMPTION_TIMER)
 		return handle_preemption_timer(vcpu);
 	else if (exit_reason.basic == EXIT_REASON_INTERRUPT_WINDOW)
@@ -7170,11 +7279,16 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu,
 
 	switch (vmx_get_exit_reason(vcpu).basic) {
 	case EXIT_REASON_MSR_WRITE:
-		return handle_fastpath_set_msr_irqoff(vcpu);
+		return handle_fastpath_wrmsr(vcpu);
+	case EXIT_REASON_MSR_WRITE_IMM:
+		return handle_fastpath_wrmsr_imm(vcpu, vmx_get_exit_qual(vcpu),
+						 vmx_get_msr_imm_reg(vcpu));
 	case EXIT_REASON_PREEMPTION_TIMER:
 		return handle_fastpath_preemption_timer(vcpu, force_immediate_exit);
 	case EXIT_REASON_HLT:
 		return handle_fastpath_hlt(vcpu);
+	case EXIT_REASON_INVD:
+		return handle_fastpath_invd(vcpu);
 	default:
 		return EXIT_FASTPATH_NONE;
 	}
@@ -7641,6 +7755,8 @@ static void nested_vmx_cr_fixed1_bits_update(struct kvm_vcpu *vcpu)
 	cr4_fixed1_update(X86_CR4_PKE,        ecx, feature_bit(PKU));
 	cr4_fixed1_update(X86_CR4_UMIP,       ecx, feature_bit(UMIP));
 	cr4_fixed1_update(X86_CR4_LA57,       ecx, feature_bit(LA57));
+	cr4_fixed1_update(X86_CR4_CET,	      ecx, feature_bit(SHSTK));
+	cr4_fixed1_update(X86_CR4_CET,	      edx, feature_bit(IBT));
 
 	entry = kvm_find_cpuid_entry_index(vcpu, 0x7, 1);
 	cr4_fixed1_update(X86_CR4_LAM_SUP,    eax, feature_bit(LAM));
@@ -7775,16 +7891,13 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		vmx->msr_ia32_feature_control_valid_bits &=
 			~FEAT_CTL_SGX_LC_ENABLED;
 
-	/* Recalc MSR interception to account for feature changes. */
-	vmx_recalc_msr_intercepts(vcpu);
-
 	/* Refresh #PF interception to account for MAXPHYADDR changes. */
 	vmx_update_exception_bitmap(vcpu);
 }
 
 static __init u64 vmx_get_perf_capabilities(void)
 {
-	u64 perf_cap = PMU_CAP_FW_WRITES;
+	u64 perf_cap = PERF_CAP_FW_WRITES;
 	u64 host_perf_cap = 0;
 
 	if (!enable_pmu)
@@ -7804,7 +7917,7 @@ static __init u64 vmx_get_perf_capabilities(void)
 		if (!vmx_lbr_caps.has_callstack)
 			memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps));
 		else if (vmx_lbr_caps.nr)
-			perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+			perf_cap |= host_perf_cap & PERF_CAP_LBR_FMT;
 	}
 
 	if (vmx_pebs_supported()) {
@@ -7872,7 +7985,6 @@ static __init void vmx_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_UMIP);
 
 	/* CPUID 0xD.1 */
-	kvm_caps.supported_xss = 0;
 	if (!cpu_has_vmx_xsaves())
 		kvm_cpu_cap_clear(X86_FEATURE_XSAVES);
 
@@ -7884,6 +7996,18 @@ static __init void vmx_set_cpu_caps(void)
 
 	if (cpu_has_vmx_waitpkg())
 		kvm_cpu_cap_check_and_set(X86_FEATURE_WAITPKG);
+
+	/*
+	 * Disable CET if unrestricted_guest is unsupported as KVM doesn't
+	 * enforce CET HW behaviors in emulator. On platforms with
+	 * VMX_BASIC[bit56] == 0, inject #CP at VMX entry with error code
+	 * fails, so disable CET in this case too.
+	 */
+	if (!cpu_has_load_cet_ctrl() || !enable_unrestricted_guest ||
+	    !cpu_has_vmx_basic_no_hw_errcode_cc()) {
+		kvm_cpu_cap_clear(X86_FEATURE_SHSTK);
+		kvm_cpu_cap_clear(X86_FEATURE_IBT);
+	}
 }
 
 static bool vmx_is_io_intercepted(struct kvm_vcpu *vcpu,
@@ -8333,8 +8457,6 @@ __init int vmx_hardware_setup(void)
 
 	vmx_setup_user_return_msrs();
 
-	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)
-		return -EIO;
 
 	if (boot_cpu_has(X86_FEATURE_NX))
 		kvm_enable_efer_bits(EFER_NX);
@@ -8364,6 +8486,14 @@ __init int vmx_hardware_setup(void)
 		return -EOPNOTSUPP;
 	}
 
+	/*
+	 * Shadow paging doesn't have a (further) performance penalty
+	 * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it
+	 * by default
+	 */
+	if (!enable_ept)
+		allow_smaller_maxphyaddr = true;
+
 	if (!cpu_has_vmx_ept_ad_bits() || !enable_ept)
 		enable_ept_ad_bits = 0;
 
@@ -8489,6 +8619,13 @@ __init int vmx_hardware_setup(void)
 
 	setup_default_sgx_lepubkeyhash();
 
+	vmx_set_cpu_caps();
+
+	/*
+	 * Configure nested capabilities after core CPU capabilities so that
+	 * nested support can be conditional on base support, e.g. so that KVM
+	 * can hide/show features based on kvm_cpu_cap_has().
+	 */
 	if (nested) {
 		nested_vmx_setup_ctls_msrs(&vmcs_config, vmx_capability.ept);
 
@@ -8497,8 +8634,6 @@ __init int vmx_hardware_setup(void)
 			return r;
 	}
 
-	vmx_set_cpu_caps();
-
 	r = alloc_kvm_area();
 	if (r && nested)
 		nested_vmx_hardware_unsetup();
@@ -8525,7 +8660,9 @@ __init int vmx_hardware_setup(void)
 	 */
 	if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
 		kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT;
-       kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT;
+
+	kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT;
+
 	return r;
 }
 
@@ -8558,11 +8695,18 @@ int __init vmx_init(void)
 		return -EOPNOTSUPP;
 
 	/*
-	 * Note, hv_init_evmcs() touches only VMX knobs, i.e. there's nothing
-	 * to unwind if a later step fails.
+	 * Note, VMCS and eVMCS configuration only touch VMX knobs/variables,
+	 * i.e. there's nothing to unwind if a later step fails.
 	 */
 	hv_init_evmcs();
 
+	/*
+	 * Parse the VMCS config and VMX capabilities before anything else, so
+	 * that the information is available to all setup flows.
+	 */
+	if (setup_vmcs_config(&vmcs_config, &vmx_capability) < 0)
+		return -EIO;
+
 	r = kvm_x86_vendor_init(&vt_init_ops);
 	if (r)
 		return r;
@@ -8586,14 +8730,6 @@ int __init vmx_init(void)
 
 	vmx_check_vmcs12_offsets();
 
-	/*
-	 * Shadow paging doesn't have a (further) performance penalty
-	 * from GUEST_MAXPHYADDR < HOST_MAXPHYADDR so enable it
-	 * by default
-	 */
-	if (!enable_ept)
-		allow_smaller_maxphyaddr = true;
-
 	return 0;
 
 err_l1d_flush: