Merge: KVM: kvm fixes for 2026-07-21

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/8407

KVM: kvm fixes for 2026-07-21

JIRA: https://redhat.atlassian.net/browse/RHEL-211279

JIRA: https://redhat.atlassian.net/browse/RHEL-213339

CVE: CVE-2025-40026

CVE: CVE-2026-63807

Commits:

```
KVM: x86/mmu: Ensure hugepage is in by slot before checking max mapping level
KVM: nVMX: Hide shadow VMCS right after VMCLEAR
KVM: x86: Check for invalid/obsolete root *after* making MMU pages available
KVM: nVMX: Add helper to put (unmap) vmcs12 pages
KVM: nVMX: Put vmcs12 pages if nested VM-Enter fails due to invalid guest state
KVM: x86: Don't (re)check L1 intercepts when completing userspace I/O
```

Signed-off-by: Aidan Wallace <awallace@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Approved-by: Peter Xu <peterx@redhat.com>
Approved-by: Jay Shin <jaeshin@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: CKI GitLab Kmaint Pipeline Bot <26919896-cki-kmaint-pipeline-bot@users.noreply.gitlab.com>

arch/x86/kvm/emulate.c

@@ -5107,12 +5107,11 @@ void init_decode_cache(struct x86_emulate_ctxt *ctxt)
 	ctxt->mem_read.end = 0;
 }
 
-int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
+int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, bool check_intercepts)
 {
 	const struct x86_emulate_ops *ops = ctxt->ops;
 	int rc = X86EMUL_CONTINUE;
 	int saved_dst_type = ctxt->dst.type;
-	bool is_guest_mode = ctxt->ops->is_guest_mode(ctxt);
 
 	ctxt->mem_read.pos = 0;
 
@@ -5160,7 +5159,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				fetch_possible_mmx_operand(&ctxt->dst);
 		}
 
-		if (unlikely(is_guest_mode) && ctxt->intercept) {
+		if (unlikely(check_intercepts) && ctxt->intercept) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_PRE_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5189,7 +5188,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 				goto done;
 		}
 
-		if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) {
+		if (unlikely(check_intercepts) && (ctxt->d & Intercept)) {
 			rc = emulator_check_intercept(ctxt, ctxt->intercept,
 						      X86_ICPT_POST_EXCEPT);
 			if (rc != X86EMUL_CONTINUE)
@@ -5243,7 +5242,7 @@ int x86_emulate_insn(struct x86_emulate_ctxt *ctxt)
 
 special_insn:
 
-	if (unlikely(is_guest_mode) && (ctxt->d & Intercept)) {
+	if (unlikely(check_intercepts) && (ctxt->d & Intercept)) {
 		rc = emulator_check_intercept(ctxt, ctxt->intercept,
 					      X86_ICPT_POST_MEMACCESS);
 		if (rc != X86EMUL_CONTINUE)

arch/x86/kvm/kvm_emulate.h

@@ -233,7 +233,6 @@ struct x86_emulate_ops {
 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
 
 	bool (*is_smm)(struct x86_emulate_ctxt *ctxt);
-	bool (*is_guest_mode)(struct x86_emulate_ctxt *ctxt);
 	int (*leave_smm)(struct x86_emulate_ctxt *ctxt);
 	void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
 	int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
@@ -519,7 +518,7 @@ bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_RESTART 1
 #define EMULATION_INTERCEPTED 2
 void init_decode_cache(struct x86_emulate_ctxt *ctxt);
-int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
+int x86_emulate_insn(struct x86_emulate_ctxt *ctxt, bool check_intercepts);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 			 u16 tss_selector, int idt_index, int reason,
 			 bool has_error_code, u32 error_code);

arch/x86/kvm/mmu/mmu.c

@@ -4573,16 +4573,17 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 	if (r != RET_PF_CONTINUE)
 		return r;
 
-	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
 
-	if (is_page_fault_stale(vcpu, fault))
-		goto out_unlock;
-
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
 
+	if (is_page_fault_stale(vcpu, fault)) {
+		r = RET_PF_RETRY;
+		goto out_unlock;
+	}
+
 	r = direct_map(vcpu, fault);
 
 out_unlock:
@@ -6916,13 +6917,19 @@ restart:
 		sp = sptep_to_sp(sptep);
 
 		/*
-		 * We cannot do huge page mapping for indirect shadow pages,
-		 * which are found on the last rmap (level = 1) when not using
-		 * tdp; such shadow pages are synced with the page table in
-		 * the guest, and the guest page table is using 4K page size
-		 * mapping if the indirect sp has level = 1.
+		 * Direct shadow page can be replaced by a hugepage if the host
+		 * mapping level allows it and the memslot maps all of the host
+		 * hugepage.  Note!  If the memslot maps only part of the
+		 * hugepage, sp->gfn may be below slot->base_gfn, and querying
+		 * the max mapping level would cause an out-of-bounds lpage_info
+		 * access.  So the gfn bounds check *must* be done first.
+		 *
+		 * Indirect shadow pages are created when the guest page tables
+		 * are using 4K pages.  Since the host mapping is always
+		 * constrained by the page size in the guest, indirect shadow
+		 * pages are never collapsible.
 		 */
-		if (sp->role.direct &&
+		if (sp->role.direct && is_gfn_in_memslot(slot, sp->gfn) &&
 		    sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
 							       PG_LEVEL_NUM)) {
 			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);

arch/x86/kvm/mmu/paging_tmpl.h

@@ -835,15 +835,17 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
 			walker.pte_access &= ~ACC_EXEC_MASK;
 	}
 
-	r = RET_PF_RETRY;
 	write_lock(&vcpu->kvm->mmu_lock);
 
-	if (is_page_fault_stale(vcpu, fault))
-		goto out_unlock;
-
 	r = make_mmu_pages_available(vcpu);
 	if (r)
 		goto out_unlock;
+
+	if (is_page_fault_stale(vcpu, fault)) {
+		r = RET_PF_RETRY;
+		goto out_unlock;
+	}
+
 	r = FNAME(fetch)(vcpu, fault, &walker);
 
 out_unlock:

arch/x86/kvm/vmx/nested.c

@@ -317,6 +317,21 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 	vcpu->arch.regs_dirty = 0;
 }
 
+static void nested_put_vmcs12_pages(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	/*
+	 * Unpin physical memory we referred to in the vmcs02.  The APIC access
+	 * page's backing page (yeah, confusing) shouldn't actually be accessed,
+	 * and if it is written, the contents are irrelevant.
+	 */
+	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
+	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
+	vmx->nested.pi_desc = NULL;
+}
+
 /*
  * Free whatever needs to be freed from vmx->nested when L1 goes down, or
  * just stops using VMX.
@@ -324,6 +339,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
 static void free_nested(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct vmcs *shadow_vmcs;
 
 	if (WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01))
 		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
@@ -341,23 +357,22 @@ static void free_nested(struct kvm_vcpu *vcpu)
 	vmx->nested.current_vmptr = INVALID_GPA;
 	if (enable_shadow_vmcs) {
 		vmx_disable_shadow_vmcs(vmx);
-		vmcs_clear(vmx->vmcs01.shadow_vmcs);
-		free_vmcs(vmx->vmcs01.shadow_vmcs);
+
+		/*
+		 * Keep the pointer visible until after VMCLEAR, so migration
+		 * can clear an active shadow VMCS on the old CPU.
+		 */
+		shadow_vmcs = vmx->vmcs01.shadow_vmcs;
+		vmcs_clear(shadow_vmcs);
 		vmx->vmcs01.shadow_vmcs = NULL;
+		free_vmcs(shadow_vmcs);
 	}
 	kfree(vmx->nested.cached_vmcs12);
 	vmx->nested.cached_vmcs12 = NULL;
 	kfree(vmx->nested.cached_shadow_vmcs12);
 	vmx->nested.cached_shadow_vmcs12 = NULL;
-	/*
-	 * Unpin physical memory we referred to in the vmcs02.  The APIC access
-	 * page's backing page (yeah, confusing) shouldn't actually be accessed,
-	 * and if it is written, the contents are irrelevant.
-	 */
-	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
-	vmx->nested.pi_desc = NULL;
+
+	nested_put_vmcs12_pages(vcpu);
 
 	kvm_mmu_free_roots(vcpu->kvm, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
 
@@ -3607,6 +3622,8 @@ vmentry_fail_vmexit:
 	if (!from_vmentry)
 		return NVMX_VMENTRY_VMEXIT;
 
+	nested_put_vmcs12_pages(vcpu);
+
 	load_vmcs12_host_state(vcpu, vmcs12);
 	vmcs12->vm_exit_reason = exit_reason.full;
 	if (enable_shadow_vmcs || nested_vmx_is_evmptr12_valid(vmx))
@@ -4959,11 +4976,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 		vmx_update_cpu_dirty_logging(vcpu);
 	}
 
-	/* Unpin physical memory we referred to in vmcs02 */
-	kvm_vcpu_unmap(vcpu, &vmx->nested.apic_access_page_map, false);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
-	kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
-	vmx->nested.pi_desc = NULL;
+	nested_put_vmcs12_pages(vcpu);
 
 	if (vmx->nested.reload_vmcs01_apic_access_page) {
 		vmx->nested.reload_vmcs01_apic_access_page = false;

arch/x86/kvm/x86.c

@@ -8621,11 +8621,6 @@ static bool emulator_is_smm(struct x86_emulate_ctxt *ctxt)
 	return is_smm(emul_to_vcpu(ctxt));
 }
 
-static bool emulator_is_guest_mode(struct x86_emulate_ctxt *ctxt)
-{
-	return is_guest_mode(emul_to_vcpu(ctxt));
-}
-
 #ifndef CONFIG_KVM_SMM
 static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt)
 {
@@ -8709,7 +8704,6 @@ static const struct x86_emulate_ops emulate_ops = {
 	.guest_cpuid_is_intel_compatible = emulator_guest_cpuid_is_intel_compatible,
 	.set_nmi_mask        = emulator_set_nmi_mask,
 	.is_smm              = emulator_is_smm,
-	.is_guest_mode       = emulator_is_guest_mode,
 	.leave_smm           = emulator_leave_smm,
 	.triple_fault        = emulator_triple_fault,
 	.set_xcr             = emulator_set_xcr,
@@ -9327,7 +9321,14 @@ restart:
 		ctxt->exception.address = 0;
 	}
 
-	r = x86_emulate_insn(ctxt);
+	/*
+	 * Check L1's instruction intercepts when emulating instructions for
+	 * L2, unless KVM is re-emulating a previously decoded instruction,
+	 * e.g. to complete userspace I/O, in which case KVM has already
+	 * checked the intercepts.
+	 */
+	r = x86_emulate_insn(ctxt, is_guest_mode(vcpu) &&
+				   !(emulation_type & EMULTYPE_NO_DECODE));
 
 	if (r == EMULATION_INTERCEPTED)
 		return 1;

include/linux/kvm_host.h

@@ -1735,6 +1735,11 @@ int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
 
+static inline bool is_gfn_in_memslot(const struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages;
+}
+
 /*
  * Returns a pointer to the memslot if it contains gfn.
  * Otherwise returns NULL.
@@ -1745,7 +1750,7 @@ try_get_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
 	if (!slot)
 		return NULL;
 
-	if (gfn >= slot->base_gfn && gfn < slot->base_gfn + slot->npages)
+	if (is_gfn_in_memslot(slot, gfn))
 		return slot;
 	else
 		return NULL;