Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm updates from Paolo Bonzini:
 "RISCV:

   - Use common KVM implementation of MMU memory caches

   - SBI v0.2 support for Guest

   - Initial KVM selftests support

   - Fix to avoid spurious virtual interrupts after clearing hideleg CSR

   - Update email address for Anup and Atish

  ARM:

   - Simplification of the 'vcpu first run' by integrating it into KVM's
     'pid change' flow

   - Refactoring of the FP and SVE state tracking, also leading to a
     simpler state and less shared data between EL1 and EL2 in the nVHE
     case

   - Tidy up the header file usage for the nvhe hyp object

   - New HYP unsharing mechanism, finally allowing pages to be unmapped
     from the Stage-1 EL2 page-tables

   - Various pKVM cleanups around refcounting and sharing

   - A couple of vgic fixes for bugs that would trigger once the vcpu
     xarray rework is merged, but not sooner

   - Add minimal support for ARMv8.7's PMU extension

   - Rework kvm_pgtable initialisation ahead of the NV work

   - New selftest for IRQ injection

   - Teach selftests about the lack of default IPA space and page sizes

   - Expand sysreg selftest to deal with Pointer Authentication

   - The usual bunch of cleanups and doc update

  s390:

   - fix sigp sense/start/stop/inconsistency

   - cleanups

  x86:

   - Clean up some function prototypes more

   - improved gfn_to_pfn_cache with proper invalidation, used by Xen
     emulation

   - add KVM_IRQ_ROUTING_XEN_EVTCHN and event channel delivery

   - completely remove potential TOC/TOU races in nested SVM consistency
     checks

   - update some PMCs on emulated instructions

   - Intel AMX support (joint work between Thomas and Intel)

   - large MMU cleanups

   - module parameter to disable PMU virtualization

   - cleanup register cache

   - first part of halt handling cleanups

   - Hyper-V enlightened MSR bitmap support for nested hypervisors

  Generic:

   - clean up Makefiles

   - introduce CONFIG_HAVE_KVM_DIRTY_RING

   - optimize memslot lookup using a tree

   - optimize vCPU array usage by converting to xarray"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (268 commits)
  x86/fpu: Fix inline prefix warnings
  selftest: kvm: Add amx selftest
  selftest: kvm: Move struct kvm_x86_state to header
  selftest: kvm: Reorder vcpu_load_state steps for AMX
  kvm: x86: Disable interception for IA32_XFD on demand
  x86/fpu: Provide fpu_sync_guest_vmexit_xfd_state()
  kvm: selftests: Add support for KVM_CAP_XSAVE2
  kvm: x86: Add support for getting/setting expanded xstate buffer
  x86/fpu: Add uabi_size to guest_fpu
  kvm: x86: Add CPUID support for Intel AMX
  kvm: x86: Add XCR0 support for Intel AMX
  kvm: x86: Disable RDMSR interception of IA32_XFD_ERR
  kvm: x86: Emulate IA32_XFD_ERR for guest
  kvm: x86: Intercept #NM for saving IA32_XFD_ERR
  x86/fpu: Prepare xfd_err in struct fpu_guest
  kvm: x86: Add emulation for IA32_XFD
  x86/fpu: Provide fpu_update_guest_xfd() for IA32_XFD emulation
  kvm: x86: Enable dynamic xfeatures at KVM_SET_CPUID2
  x86/fpu: Provide fpu_enable_guest_xfd_features() for KVM
  x86/fpu: Add guest support to xfd_enable_feature()
  ...

1 files changed, 156 insertions, 60 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 1187cd1e38aa..1b2e9d8c5cc9 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -36,6 +36,7 @@
 #include <asm/debugreg.h>
 #include <asm/desc.h>
 #include <asm/fpu/api.h>
+#include <asm/fpu/xstate.h>
 #include <asm/idtentry.h>
 #include <asm/io.h>
 #include <asm/irq_remapping.h>
@@ -161,6 +162,8 @@ static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
 	MSR_FS_BASE,
 	MSR_GS_BASE,
 	MSR_KERNEL_GS_BASE,
+	MSR_IA32_XFD,
+	MSR_IA32_XFD_ERR,
 #endif
 	MSR_IA32_SYSENTER_CS,
 	MSR_IA32_SYSENTER_ESP,
@@ -602,15 +605,13 @@ static int vmx_set_guest_uret_msr(struct vcpu_vmx *vmx,
 	unsigned int slot = msr - vmx->guest_uret_msrs;
 	int ret = 0;
 
-	u64 old_msr_data = msr->data;
-	msr->data = data;
 	if (msr->load_into_hardware) {
 		preempt_disable();
-		ret = kvm_set_user_return_msr(slot, msr->data, msr->mask);
+		ret = kvm_set_user_return_msr(slot, data, msr->mask);
 		preempt_enable();
-		if (ret)
-			msr->data = old_msr_data;
 	}
+	if (!ret)
+		msr->data = data;
 	return ret;
 }
 
@@ -763,6 +764,14 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
 		vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, match);
 	}
 
+	/*
+	 * Disabling xfd interception indicates that dynamic xfeatures
+	 * might be used in the guest. Always trap #NM in this case
+	 * to save guest xfd_err timely.
+	 */
+	if (vcpu->arch.xfd_no_write_intercept)
+		eb |= (1u << NM_VECTOR);
+
 	vmcs_write32(EXCEPTION_BITMAP, eb);
 }
 
@@ -1071,9 +1080,14 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
 		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 }
 
-void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
-			unsigned long fs_base, unsigned long gs_base)
+void vmx_set_vmcs_host_state(struct vmcs_host_state *host, unsigned long cr3,
+			     u16 fs_sel, u16 gs_sel,
+			     unsigned long fs_base, unsigned long gs_base)
 {
+	if (unlikely(cr3 != host->cr3)) {
+		vmcs_writel(HOST_CR3, cr3);
+		host->cr3 = cr3;
+	}
 	if (unlikely(fs_sel != host->fs_sel)) {
 		if (!(fs_sel & 7))
 			vmcs_write16(HOST_FS_SELECTOR, fs_sel);
@@ -1168,7 +1182,9 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	gs_base = segment_base(gs_sel);
 #endif
 
-	vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base);
+	vmx_set_vmcs_host_state(host_state, __get_current_cr3_fast(),
+				fs_sel, gs_sel, fs_base, gs_base);
+
 	vmx->guest_state_loaded = true;
 }
 
@@ -1271,7 +1287,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 
 	if (!already_loaded) {
 		void *gdt = get_current_gdt_ro();
-		unsigned long sysenter_esp;
 
 		/*
 		 * Flush all EPTP/VPID contexts, the new pCPU may have stale
@@ -1287,8 +1302,11 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
 			    (unsigned long)&get_cpu_entry_area(cpu)->tss.x86_tss);
 		vmcs_writel(HOST_GDTR_BASE, (unsigned long)gdt);   /* 22.2.4 */
 
-		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
-		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
+		if (IS_ENABLED(CONFIG_IA32_EMULATION) || IS_ENABLED(CONFIG_X86_32)) {
+			/* 22.2.3 */
+			vmcs_writel(HOST_IA32_SYSENTER_ESP,
+				    (unsigned long)(cpu_entry_stack(cpu) + 1));
+		}
 
 		vmx->loaded_vmcs->cpu = cpu;
 	}
@@ -1753,7 +1771,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
 }
 
 /*
- * Reads an msr value (of 'msr_index') into 'pdata'.
+ * Reads an msr value (of 'msr_info->index') into 'msr_info->data'.
  * Returns 0 on success, non-0 otherwise.
  * Assumes vcpu_load() was already called.
  */
@@ -1960,6 +1978,24 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_KERNEL_GS_BASE:
 		vmx_write_guest_kernel_gs_base(vmx, data);
 		break;
+	case MSR_IA32_XFD:
+		ret = kvm_set_msr_common(vcpu, msr_info);
+		/*
+		 * Always intercepting WRMSR could incur non-negligible
+		 * overhead given xfd might be changed frequently in
+		 * guest context switch. Disable write interception
+		 * upon the first write with a non-zero value (indicating
+		 * potential usage on dynamic xfeatures). Also update
+		 * exception bitmap to trap #NM for proper virtualization
+		 * of guest xfd_err.
+		 */
+		if (!ret && data) {
+			vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD,
+						      MSR_TYPE_RW);
+			vcpu->arch.xfd_no_write_intercept = true;
+			vmx_update_exception_bitmap(vcpu);
+		}
+		break;
 #endif
 	case MSR_IA32_SYSENTER_CS:
 		if (is_guest_mode(vcpu))
@@ -2100,9 +2136,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		}
 		ret = kvm_set_msr_common(vcpu, msr_info);
 		break;
-	case MSR_IA32_TSC_ADJUST:
-		ret = kvm_set_msr_common(vcpu, msr_info);
-		break;
 	case MSR_IA32_MCG_EXT_CTL:
 		if ((!msr_info->host_initiated &&
 		     !(to_vmx(vcpu)->msr_ia32_feature_control &
@@ -2985,7 +3018,7 @@ void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 	mmu->pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
 	mmu->pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 
-	kvm_register_mark_dirty(vcpu, VCPU_EXREG_PDPTR);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_PDPTR);
 }
 
 #define CR3_EXITING_BITS (CPU_BASED_CR3_LOAD_EXITING | \
@@ -3067,6 +3100,13 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 		/* Note, vmx_set_cr4() consumes the new vcpu->arch.cr0. */
 		if ((old_cr0_pg ^ cr0) & X86_CR0_PG)
 			vmx_set_cr4(vcpu, kvm_read_cr4(vcpu));
+
+		/*
+		 * When !CR0_PG -> CR0_PG, vcpu->arch.cr3 becomes active, but
+		 * GUEST_CR3 is still vmx->ept_identity_map_addr if EPT + !URG.
+		 */
+		if (!(old_cr0_pg & X86_CR0_PG) && (cr0 & X86_CR0_PG))
+			kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
 	}
 
 	/* depends on vcpu->arch.cr0 to be set to a new value */
@@ -3110,9 +3150,9 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
 
 		if (!enable_unrestricted_guest && !is_paging(vcpu))
 			guest_cr3 = to_kvm_vmx(kvm)->ept_identity_map_addr;
-		else if (test_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail))
+		else if (kvm_register_is_dirty(vcpu, VCPU_EXREG_CR3))
 			guest_cr3 = vcpu->arch.cr3;
-		else /* vmcs01.GUEST_CR3 is already up-to-date. */
+		else /* vmcs.GUEST_CR3 is already up-to-date. */
 			update_guest_cr3 = false;
 		vmx_ept_load_pdptrs(vcpu);
 	} else {
@@ -3123,6 +3163,7 @@ static void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
 		vmcs_writel(GUEST_CR3, guest_cr3);
 }
 
+
 static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	/*
@@ -3687,6 +3728,19 @@ void free_vpid(int vpid)
 	spin_unlock(&vmx_vpid_lock);
 }
 
+static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx)
+{
+	/*
+	 * When KVM is a nested hypervisor on top of Hyper-V and uses
+	 * 'Enlightened MSR Bitmap' feature L0 needs to know that MSR
+	 * bitmap has changed.
+	 */
+	if (static_branch_unlikely(&enable_evmcs))
+		evmcs_touch_msr_bitmap();
+
+	vmx->nested.force_msr_bitmap_recalc = true;
+}
+
 void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -3695,8 +3749,7 @@ void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
 
-	if (static_branch_unlikely(&enable_evmcs))
-		evmcs_touch_msr_bitmap();
+	vmx_msr_bitmap_l01_changed(vmx);
 
 	/*
 	 * Mark the desired intercept state in shadow bitmap, this is needed
@@ -3740,8 +3793,7 @@ void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
 	if (!cpu_has_vmx_msr_bitmap())
 		return;
 
-	if (static_branch_unlikely(&enable_evmcs))
-		evmcs_touch_msr_bitmap();
+	vmx_msr_bitmap_l01_changed(vmx);
 
 	/*
 	 * Mark the desired intercept state in shadow bitmap, this is needed
@@ -3931,6 +3983,19 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
 		 */
 		vmx->nested.pi_pending = true;
 		kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+		/*
+		 * This pairs with the smp_mb_*() after setting vcpu->mode in
+		 * vcpu_enter_guest() to guarantee the vCPU sees the event
+		 * request if triggering a posted interrupt "fails" because
+		 * vcpu->mode != IN_GUEST_MODE.  The extra barrier is needed as
+		 * the smb_wmb() in kvm_make_request() only ensures everything
+		 * done before making the request is visible when the request
+		 * is visible, it doesn't ensure ordering between the store to
+		 * vcpu->requests and the load from vcpu->mode.
+		 */
+		smp_mb__after_atomic();
+
 		/* the PIR and ON have been set by L1. */
 		if (!kvm_vcpu_trigger_posted_interrupt(vcpu, true))
 			kvm_vcpu_kick(vcpu);
@@ -3964,6 +4029,12 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
 	if (pi_test_and_set_on(&vmx->pi_desc))
 		return 0;
 
+	/*
+	 * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*()
+	 * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is
+	 * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a
+	 * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE.
+	 */
 	if (!kvm_vcpu_trigger_posted_interrupt(vcpu, false))
 		kvm_vcpu_kick(vcpu);
 
@@ -4021,6 +4092,12 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
 
 	rdmsr(MSR_IA32_SYSENTER_CS, low32, high32);
 	vmcs_write32(HOST_IA32_SYSENTER_CS, low32);
+
+	/*
+	 * If 32-bit syscall is enabled, vmx_vcpu_load_vcms rewrites
+	 * HOST_IA32_SYSENTER_ESP.
+	 */
+	vmcs_writel(HOST_IA32_SYSENTER_ESP, 0);
 	rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl);
 	vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl);   /* 22.2.3 */
 
@@ -4039,8 +4116,10 @@ void set_cr4_guest_host_mask(struct vcpu_vmx *vmx)
 
 	vcpu->arch.cr4_guest_owned_bits = KVM_POSSIBLE_CR4_GUEST_BITS &
 					  ~vcpu->arch.cr4_guest_rsvd_bits;
-	if (!enable_ept)
-		vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PGE;
+	if (!enable_ept) {
+		vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_TLBFLUSH_BITS;
+		vcpu->arch.cr4_guest_owned_bits &= ~X86_CR4_PDPTR_BITS;
+	}
 	if (is_guest_mode(&vmx->vcpu))
 		vcpu->arch.cr4_guest_owned_bits &=
 			~get_vmcs12(vcpu)->cr4_guest_host_mask;
@@ -4692,7 +4771,7 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 		if (kvm_emulate_instruction(vcpu, 0)) {
 			if (vcpu->arch.halt_request) {
 				vcpu->arch.halt_request = 0;
-				return kvm_vcpu_halt(vcpu);
+				return kvm_emulate_halt_noskip(vcpu);
 			}
 			return 1;
 		}
@@ -4748,6 +4827,17 @@ static int handle_exception_nmi(struct kvm_vcpu *vcpu)
 	if (is_machine_check(intr_info) || is_nmi(intr_info))
 		return 1; /* handled by handle_exception_nmi_irqoff() */
 
+	/*
+	 * Queue the exception here instead of in handle_nm_fault_irqoff().
+	 * This ensures the nested_vmx check is not skipped so vmexit can
+	 * be reflected to L1 (when it intercepts #NM) before reaching this
+	 * point.
+	 */
+	if (is_nm_fault(intr_info)) {
+		kvm_queue_exception(vcpu, NM_VECTOR);
+		return 1;
+	}
+
 	if (is_invalid_opcode(intr_info))
 		return handle_ud(vcpu);
 
@@ -5363,7 +5453,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 		if (vcpu->arch.halt_request) {
 			vcpu->arch.halt_request = 0;
-			return kvm_vcpu_halt(vcpu);
+			return kvm_emulate_halt_noskip(vcpu);
 		}
 
 		/*
@@ -6351,6 +6441,26 @@ static void handle_interrupt_nmi_irqoff(struct kvm_vcpu *vcpu,
 	kvm_after_interrupt(vcpu);
 }
 
+static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Save xfd_err to guest_fpu before interrupt is enabled, so the
+	 * MSR value is not clobbered by the host activity before the guest
+	 * has chance to consume it.
+	 *
+	 * Do not blindly read xfd_err here, since this exception might
+	 * be caused by L1 interception on a platform which doesn't
+	 * support xfd at all.
+	 *
+	 * Do it conditionally upon guest_fpu::xfd. xfd_err matters
+	 * only when xfd contains a non-zero value.
+	 *
+	 * Queuing exception is done in vmx_handle_exit. See comment there.
+	 */
+	if (vcpu->arch.guest_fpu.fpstate->xfd)
+		rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+}
+
 static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 {
 	const unsigned long nmi_entry = (unsigned long)asm_exc_nmi_noist;
@@ -6359,6 +6469,9 @@ static void handle_exception_nmi_irqoff(struct vcpu_vmx *vmx)
 	/* if exit due to PF check for async PF */
 	if (is_page_fault(intr_info))
 		vmx->vcpu.arch.apf.host_apf_flags = kvm_read_and_reset_apf_flags();
+	/* if exit due to NM, handle before interrupts are enabled */
+	else if (is_nm_fault(intr_info))
+		handle_nm_fault_irqoff(&vmx->vcpu);
 	/* Handle machine checks before interrupts are enabled */
 	else if (is_machine_check(intr_info))
 		kvm_machine_check();
@@ -6617,7 +6730,7 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
 static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr3, cr4;
+	unsigned long cr4;
 
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!enable_vnmi &&
@@ -6658,12 +6771,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 		vmcs_writel(GUEST_RSP, vcpu->arch.regs[VCPU_REGS_RSP]);
 	if (kvm_register_is_dirty(vcpu, VCPU_REGS_RIP))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
-
-	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->loaded_vmcs->host_state.cr3)) {
-		vmcs_writel(HOST_CR3, cr3);
-		vmx->loaded_vmcs->host_state.cr3 = cr3;
-	}
+	vcpu->arch.regs_dirty = 0;
 
 	cr4 = cr4_read_shadow();
 	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
@@ -6752,7 +6860,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	loadsegment(es, __USER_DS);
 #endif
 
-	vmx_register_cache_reset(vcpu);
+	vcpu->arch.regs_avail &= ~VMX_REGS_LAZY_LOAD_SET;
 
 	pt_guest_exit(vmx);
 
@@ -6971,7 +7079,6 @@ static int __init vmx_check_processor_compat(void)
 static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 {
 	u8 cache;
-	u64 ipat = 0;
 
 	/* We wanted to honor guest CD/MTRR/PAT, but doing so could result in
 	 * memory aliases with conflicting memory types and sometimes MCEs.
@@ -6991,30 +7098,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	 * EPT memory type is used to emulate guest CD/MTRR.
 	 */
 
-	if (is_mmio) {
-		cache = MTRR_TYPE_UNCACHABLE;
-		goto exit;
-	}
+	if (is_mmio)
+		return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
 
-	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
-		ipat = VMX_EPT_IPAT_BIT;
-		cache = MTRR_TYPE_WRBACK;
-		goto exit;
-	}
+	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm))
+		return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT;
 
 	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
-		ipat = VMX_EPT_IPAT_BIT;
 		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
 			cache = MTRR_TYPE_WRBACK;
 		else
 			cache = MTRR_TYPE_UNCACHABLE;
-		goto exit;
-	}
 
-	cache = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+		return (cache << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT;
+	}
 
-exit:
-	return (cache << VMX_EPT_MT_EPTE_SHIFT) | ipat;
+	return kvm_mtrr_get_guest_memory_type(vcpu, gfn) << VMX_EPT_MT_EPTE_SHIFT;
 }
 
 static void vmcs_set_secondary_exec_control(struct vcpu_vmx *vmx, u32 new_ctl)
@@ -7206,6 +7305,11 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		}
 	}
 
+	if (kvm_cpu_cap_has(X86_FEATURE_XFD))
+		vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R,
+					  !guest_cpuid_has(vcpu, X86_FEATURE_XFD));
+
+
 	set_cr4_guest_host_mask(vmx);
 
 	vmx_write_encls_bitmap(vcpu, NULL);
@@ -7741,7 +7845,7 @@ static __init int hardware_setup(void)
 {
 	unsigned long host_bndcfgs;
 	struct desc_ptr dt;
-	int r, ept_lpage_level;
+	int r;
 
 	store_idt(&dt);
 	host_idt_base = dt.address;
@@ -7838,16 +7942,8 @@ static __init int hardware_setup(void)
 		kvm_mmu_set_ept_masks(enable_ept_ad_bits,
 				      cpu_has_vmx_ept_execute_only());
 
-	if (!enable_ept)
-		ept_lpage_level = 0;
-	else if (cpu_has_vmx_ept_1g_page())
-		ept_lpage_level = PG_LEVEL_1G;
-	else if (cpu_has_vmx_ept_2m_page())
-		ept_lpage_level = PG_LEVEL_2M;
-	else
-		ept_lpage_level = PG_LEVEL_4K;
 	kvm_configure_mmu(enable_ept, 0, vmx_get_max_tdp_level(),
-			  ept_lpage_level);
+			  ept_caps_to_lpage_level(vmx_capability.ept));
 
 	/*
 	 * Only enable PML when hardware supports PML feature, and both EPT