Merge tag 'kvm-x86-vmx-6.19' of https://github.com/kvm-x86/linux into HEAD

KVM VMX changes for 6.19:

- Use the root role from kvm_mmu_page to construct EPTPs instead of the
current vCPU state, partly as worthwhile cleanup, but mostly to pave the
way for tracking per-root TLB flushes so that KVM can elide EPT flushes on
pCPU migration if KVM has flushed the root at least once.

- Add a few missing nested consistency checks.

- Rip out support for doing "early" consistency checks via hardware as the
functionality hasn't been used in years and is no longer useful in general,
and replace it with an off-by-default module param to detected missed
consistency checks (i.e. WARN if hardware finds a check that KVM does not).

- Fix a currently-benign bug where KVM would drop the guest's SPEC_CTRL[63:32]
on VM-Enter.

- Misc cleanups.

arch/x86/kvm/mmu/mmu_internal.h

···
 #define INVALID_PAE_ROOT	0
 #define IS_VALID_PAE_ROOT(x)	(!!(x))
 
-static inline hpa_t kvm_mmu_get_dummy_root(void)
-{
-	return my_zero_pfn(0) << PAGE_SHIFT;
-}
-
-static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page)
-{
-	return is_zero_pfn(shadow_page >> PAGE_SHIFT);
-}
-
 typedef u64 __rcu *tdp_ptep_t;
 
 struct kvm_mmu_page {

arch/x86/kvm/mmu/spte.h

···
  */
 extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;
 
+static inline hpa_t kvm_mmu_get_dummy_root(void)
+{
+	return my_zero_pfn(0) << PAGE_SHIFT;
+}
+
+static inline bool kvm_mmu_is_dummy_root(hpa_t shadow_page)
+{
+	return is_zero_pfn(shadow_page >> PAGE_SHIFT);
+}
+
 static inline struct kvm_mmu_page *to_shadow_page(hpa_t shadow_page)
 {
 	struct page *page = pfn_to_page((shadow_page) >> PAGE_SHIFT);

arch/x86/kvm/vmx/nested.c

···
 static bool __read_mostly enable_shadow_vmcs = 1;
 module_param_named(enable_shadow_vmcs, enable_shadow_vmcs, bool, S_IRUGO);
 
-static bool __read_mostly nested_early_check = 0;
-module_param(nested_early_check, bool, S_IRUGO);
+static bool __ro_after_init warn_on_missed_cc;
+module_param(warn_on_missed_cc, bool, 0444);
 
 #define CC KVM_NESTED_VMENTER_CONSISTENCY_CHECK
 
···
 	if (CC(!page_address_valid(vcpu, vmcs12->virtual_apic_page_addr)))
 		return -EINVAL;
 
+	if (CC(!nested_cpu_has_vid(vmcs12) && vmcs12->tpr_threshold >> 4))
+		return -EINVAL;
+
 	return 0;
 }
 
···
 				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
 		return;
 
-	kvm_read_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+	kvm_read_guest_cached(vcpu->kvm, ghc, get_shadow_vmcs12(vcpu),
 			      VMCS12_SIZE);
 }
 
···
 				      vmcs12->vmcs_link_pointer, VMCS12_SIZE))
 		return;
 
-	kvm_write_guest_cached(vmx->vcpu.kvm, ghc, get_shadow_vmcs12(vcpu),
+	kvm_write_guest_cached(vcpu->kvm, ghc, get_shadow_vmcs12(vcpu),
 			       VMCS12_SIZE);
 }
 
···
 		return;
 	vmx->nested.vmcs02_initialized = true;
 
-	/*
-	 * We don't care what the EPTP value is we just need to guarantee
-	 * it's valid so we don't get a false positive when doing early
-	 * consistency checks.
-	 */
-	if (enable_ept && nested_early_check)
-		vmcs_write64(EPT_POINTER,
-			     construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));
-
 	if (vmx->ve_info)
 		vmcs_write64(VE_INFORMATION_ADDRESS, __pa(vmx->ve_info));
 
···
 		vmcs_write64(GUEST_IA32_PAT, vmcs12->guest_ia32_pat);
 		vcpu->arch.pat = vmcs12->guest_ia32_pat;
 	} else if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
-		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
+		vmcs_write64(GUEST_IA32_PAT, vcpu->arch.pat);
 	}
 
 	vcpu->arch.tsc_offset = kvm_calc_nested_tsc_offset(
···
 		}
 	}
 
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_TSC_SCALING) &&
+	    CC(!vmcs12->tsc_multiplier))
+		return -EINVAL;
+
 	return 0;
 }
 
···
 	if (guest_cpu_cap_has_evmcs(vcpu))
 		return nested_evmcs_check_controls(vmcs12);
 #endif
+
+	return 0;
+}
+
+static int nested_vmx_check_controls_late(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	void *vapic = to_vmx(vcpu)->nested.virtual_apic_map.hva;
+	u32 vtpr = vapic ? (*(u32 *)(vapic + APIC_TASKPRI)) >> 4 : 0;
+
+	/*
+	 * Don't bother with the consistency checks if KVM isn't configured to
+	 * WARN on missed consistency checks, as KVM needs to rely on hardware
+	 * to fully detect an illegal vTPR vs. TRP Threshold combination due to
+	 * the vTPR being writable by L1 at all times (it's an in-memory value,
+	 * not a VMCS field).  I.e. even if the check passes now, it might fail
+	 * at the actual VM-Enter.
+	 *
+	 * Keying off the module param also allows treating an invalid vAPIC
+	 * mapping as a consistency check failure without increasing the risk
+	 * of breaking a "real" VM.
+	 */
+	if (!warn_on_missed_cc)
+		return 0;
+
+	if ((exec_controls_get(to_vmx(vcpu)) & CPU_BASED_TPR_SHADOW) &&
+	    nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW) &&
+	    !nested_cpu_has_vid(vmcs12) &&
+	    !nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    (CC(!vapic) ||
+	     CC((vmcs12->tpr_threshold & GENMASK(3, 0)) > (vtpr & GENMASK(3, 0)))))
+		return -EINVAL;
 
 	return 0;
 }
···
 
 	if (nested_check_guest_non_reg_state(vmcs12))
 		return -EINVAL;
-
-	return 0;
-}
-
-static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	unsigned long cr3, cr4;
-	bool vm_fail;
-
-	if (!nested_early_check)
-		return 0;
-
-	if (vmx->msr_autoload.host.nr)
-		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
-	if (vmx->msr_autoload.guest.nr)
-		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
-
-	preempt_disable();
-
-	vmx_prepare_switch_to_guest(vcpu);
-
-	/*
-	 * Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
-	 * which is reserved to '1' by hardware.  GUEST_RFLAGS is guaranteed to
-	 * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e.
-	 * there is no need to preserve other bits or save/restore the field.
-	 */
-	vmcs_writel(GUEST_RFLAGS, 0);
-
-	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;
-	}
-
-	cr4 = cr4_read_shadow();
-	if (unlikely(cr4 != vmx->loaded_vmcs->host_state.cr4)) {
-		vmcs_writel(HOST_CR4, cr4);
-		vmx->loaded_vmcs->host_state.cr4 = cr4;
-	}
-
-	vm_fail = __vmx_vcpu_run(vmx, (unsigned long *)&vcpu->arch.regs,
-				 __vmx_vcpu_run_flags(vmx));
-
-	if (vmx->msr_autoload.host.nr)
-		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
-	if (vmx->msr_autoload.guest.nr)
-		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
-
-	if (vm_fail) {
-		u32 error = vmcs_read32(VM_INSTRUCTION_ERROR);
-
-		preempt_enable();
-
-		trace_kvm_nested_vmenter_failed(
-			"early hardware check VM-instruction error: ", error);
-		WARN_ON_ONCE(error != VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		return 1;
-	}
-
-	/*
-	 * VMExit clears RFLAGS.IF and DR7, even on a consistency check.
-	 */
-	if (hw_breakpoint_active())
-		set_debugreg(__this_cpu_read(cpu_dr7), 7);
-	local_irq_enable();
-	preempt_enable();
-
-	/*
-	 * A non-failing VMEntry means we somehow entered guest mode with
-	 * an illegal RIP, and that's just the tip of the iceberg.  There
-	 * is no telling what memory has been modified or what state has
-	 * been exposed to unknown code.  Hitting this all but guarantees
-	 * a (very critical) hardware issue.
-	 */
-	WARN_ON(!(vmcs_read32(VM_EXIT_REASON) &
-		VMX_EXIT_REASONS_FAILED_VMENTRY));
 
 	return 0;
 }
···
 				    &vmx->nested.pre_vmenter_ssp_tbl);
 
 	/*
-	 * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled *and*
-	 * nested early checks are disabled.  In the event of a "late" VM-Fail,
-	 * i.e. a VM-Fail detected by hardware but not KVM, KVM must unwind its
-	 * software model to the pre-VMEntry host state.  When EPT is disabled,
-	 * GUEST_CR3 holds KVM's shadow CR3, not L1's "real" CR3, which causes
-	 * nested_vmx_restore_host_state() to corrupt vcpu->arch.cr3.  Stuffing
-	 * vmcs01.GUEST_CR3 results in the unwind naturally setting arch.cr3 to
-	 * the correct value.  Smashing vmcs01.GUEST_CR3 is safe because nested
-	 * VM-Exits, and the unwind, reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is
-	 * guaranteed to be overwritten with a shadow CR3 prior to re-entering
-	 * L1.  Don't stuff vmcs01.GUEST_CR3 when using nested early checks as
-	 * KVM modifies vcpu->arch.cr3 if and only if the early hardware checks
-	 * pass, and early VM-Fails do not reset KVM's MMU, i.e. the VM-Fail
-	 * path would need to manually save/restore vmcs01.GUEST_CR3.
+	 * Overwrite vmcs01.GUEST_CR3 with L1's CR3 if EPT is disabled.  In the
+	 * event of a "late" VM-Fail, i.e. a VM-Fail detected by hardware but
+	 * not KVM, KVM must unwind its software model to the pre-VM-Entry host
+	 * state.  When EPT is disabled, GUEST_CR3 holds KVM's shadow CR3, not
+	 * L1's "real" CR3, which causes nested_vmx_restore_host_state() to
+	 * corrupt vcpu->arch.cr3.  Stuffing vmcs01.GUEST_CR3 results in the
+	 * unwind naturally setting arch.cr3 to the correct value.  Smashing
+	 * vmcs01.GUEST_CR3 is safe because nested VM-Exits, and the unwind,
+	 * reset KVM's MMU, i.e. vmcs01.GUEST_CR3 is guaranteed to be
+	 * overwritten with a shadow CR3 prior to re-entering L1.
 	 */
-	if (!enable_ept && !nested_early_check)
+	if (!enable_ept)
 		vmcs_writel(GUEST_CR3, vcpu->arch.cr3);
 
 	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
···
 			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
 		}
 
-		if (nested_vmx_check_vmentry_hw(vcpu)) {
+		if (nested_vmx_check_controls_late(vcpu, vmcs12)) {
 			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 			return NVMX_VMENTRY_VMFAIL;
 		}
···
 		/*
 		 * The only expected VM-instruction error is "VM entry with
 		 * invalid control field(s)." Anything else indicates a
-		 * problem with L0.  And we should never get here with a
-		 * VMFail of any type if early consistency checks are enabled.
+		 * problem with L0.
 		 */
 		WARN_ON_ONCE(vmcs_read32(VM_INSTRUCTION_ERROR) !=
 			     VMXERR_ENTRY_INVALID_CONTROL_FIELD);
-		WARN_ON_ONCE(nested_early_check);
+
+		/* VM-Fail at VM-Entry means KVM missed a consistency check. */
+		WARN_ON_ONCE(warn_on_missed_cc);
 	}
 
 	/*

arch/x86/kvm/vmx/tdx.c

···
 
 static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
 {
+	struct kvm_tdx_init_vm __user *user_data = u64_to_user_ptr(cmd->data);
 	struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
 	struct kvm_tdx_init_vm *init_vm;
 	struct td_params *td_params = NULL;
+	u32 nr_user_entries;
 	int ret;
 
 	BUILD_BUG_ON(sizeof(*init_vm) != 256 + sizeof_field(struct kvm_tdx_init_vm, cpuid));
···
 	if (cmd->flags)
 		return -EINVAL;
 
-	init_vm = kmalloc(sizeof(*init_vm) +
-			  sizeof(init_vm->cpuid.entries[0]) * KVM_MAX_CPUID_ENTRIES,
-			  GFP_KERNEL);
-	if (!init_vm)
-		return -ENOMEM;
+	if (get_user(nr_user_entries, &user_data->cpuid.nent))
+		return -EFAULT;
 
-	if (copy_from_user(init_vm, u64_to_user_ptr(cmd->data), sizeof(*init_vm))) {
-		ret = -EFAULT;
-		goto out;
-	}
+	if (nr_user_entries > KVM_MAX_CPUID_ENTRIES)
+		return -E2BIG;
 
-	if (init_vm->cpuid.nent > KVM_MAX_CPUID_ENTRIES) {
-		ret = -E2BIG;
-		goto out;
-	}
-
-	if (copy_from_user(init_vm->cpuid.entries,
-			   u64_to_user_ptr(cmd->data) + sizeof(*init_vm),
-			   flex_array_size(init_vm, cpuid.entries, init_vm->cpuid.nent))) {
-		ret = -EFAULT;
-		goto out;
-	}
+	init_vm = memdup_user(user_data,
+			      struct_size(user_data, cpuid.entries, nr_user_entries));
+	if (IS_ERR(init_vm))
+		return PTR_ERR(init_vm);
 
 	if (memchr_inv(init_vm->reserved, 0, sizeof(init_vm->reserved))) {
 		ret = -EINVAL;

arch/x86/kvm/vmx/vmenter.S

···
 	 * and vmentry.
 	 */
 	mov 2*WORD_SIZE(%_ASM_SP), %_ASM_DI
-	movl VMX_spec_ctrl(%_ASM_DI), %edi
-	movl PER_CPU_VAR(x86_spec_ctrl_current), %esi
-	cmp %edi, %esi
+#ifdef CONFIG_X86_64
+	mov VMX_spec_ctrl(%rdi), %rdx
+	cmp PER_CPU_VAR(x86_spec_ctrl_current), %rdx
 	je .Lspec_ctrl_done
+	movl %edx, %eax
+	shr $32, %rdx
+#else
+	mov VMX_spec_ctrl(%edi), %eax
+	mov PER_CPU_VAR(x86_spec_ctrl_current), %ecx
+	xor %eax, %ecx
+	mov VMX_spec_ctrl + 4(%edi), %edx
+	mov PER_CPU_VAR(x86_spec_ctrl_current + 4), %edi
+	xor %edx, %edi
+	or %edi, %ecx
+	je .Lspec_ctrl_done
+#endif
 	mov $MSR_IA32_SPEC_CTRL, %ecx
-	xor %edx, %edx
-	mov %edi, %eax
 	wrmsr
 
 .Lspec_ctrl_done:

arch/x86/kvm/vmx/vmx.c

···
 	loaded_vmcs->launched = 0;
 }
 
-void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
+static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
 {
 	int cpu = loaded_vmcs->cpu;
 
···
 	return to_vmx(vcpu)->vpid;
 }
 
+static u64 construct_eptp(hpa_t root_hpa)
+{
+	u64 eptp = root_hpa | VMX_EPTP_MT_WB;
+	struct kvm_mmu_page *root;
+
+	if (kvm_mmu_is_dummy_root(root_hpa))
+		return eptp | VMX_EPTP_PWL_4;
+
+	/*
+	 * EPT roots should always have an associated MMU page.  Return a "bad"
+	 * EPTP to induce VM-Fail instead of continuing on in a unknown state.
+	 */
+	root = root_to_sp(root_hpa);
+	if (WARN_ON_ONCE(!root))
+		return INVALID_PAGE;
+
+	eptp |= (root->role.level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
+
+	if (enable_ept_ad_bits && !root->role.ad_disabled)
+		eptp |= VMX_EPTP_AD_ENABLE_BIT;
+
+	return eptp;
+}
+
+static void vmx_flush_tlb_ept_root(hpa_t root_hpa)
+{
+	u64 eptp = construct_eptp(root_hpa);
+
+	if (VALID_PAGE(eptp))
+		ept_sync_context(eptp);
+	else
+		ept_sync_global();
+}
+
 void vmx_flush_tlb_current(struct kvm_vcpu *vcpu)
 {
 	struct kvm_mmu *mmu = vcpu->arch.mmu;
···
 		return;
 
 	if (enable_ept)
-		ept_sync_context(construct_eptp(vcpu, root_hpa,
-						mmu->root_role.level));
+		vmx_flush_tlb_ept_root(root_hpa);
 	else
 		vpid_sync_context(vmx_get_current_vpid(vcpu));
 }
···
 	return 4;
 }
 
-u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level)
-{
-	u64 eptp = VMX_EPTP_MT_WB;
-
-	eptp |= (root_level == 5) ? VMX_EPTP_PWL_5 : VMX_EPTP_PWL_4;
-
-	if (enable_ept_ad_bits &&
-	    (!is_guest_mode(vcpu) || nested_ept_ad_enabled(vcpu)))
-		eptp |= VMX_EPTP_AD_ENABLE_BIT;
-	eptp |= root_hpa;
-
-	return eptp;
-}
-
 void vmx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level)
 {
 	struct kvm *kvm = vcpu->kvm;
 	bool update_guest_cr3 = true;
 	unsigned long guest_cr3;
-	u64 eptp;
 
 	if (enable_ept) {
-		eptp = construct_eptp(vcpu, root_hpa, root_level);
-		vmcs_write64(EPT_POINTER, eptp);
+		KVM_MMU_WARN_ON(root_to_sp(root_hpa) &&
+				root_level != root_to_sp(root_hpa)->role.level);
+		vmcs_write64(EPT_POINTER, construct_eptp(root_hpa));
 
 		hv_track_root_tdp(vcpu, root_hpa);
 

arch/x86/kvm/vmx/vmx.h

···
 void ept_save_pdptrs(struct kvm_vcpu *vcpu);
 void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 void __vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
-u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
 
 bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu);
 void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
···
 void free_vmcs(struct vmcs *vmcs);
 int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
 void free_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
-void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs);
 
 static inline struct vmcs *alloc_vmcs(bool shadow)
 {

arch/x86/kvm/vmx/x86_ops.h

···
 void vmx_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 void vmx_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
 void vmx_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
-void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val);
 void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val);
 void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu);
 void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg);