[LTS 8.6] imon: CVE-2025-39993, kvm: CVE-2026-23401, CVE-2023-30456, CVE-2022-45869, CVE-2022-1852

arch/x86/kvm/mmu/mmu.c

@@ -2365,6 +2365,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm,
 {
 	bool list_unstable;
 
+	lockdep_assert_held_write(&kvm->mmu_lock);
 	trace_kvm_mmu_prepare_zap_page(sp);
 	++kvm->stat.mmu_shadow_zapped;
 	*nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list);
@@ -2699,11 +2700,6 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
 		 *sptep, write_fault, gfn);
 
-	if (unlikely(is_noslot_pfn(pfn))) {
-		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
-		return RET_PF_EMULATE;
-	}
-
 	if (is_shadow_present_pte(*sptep)) {
 		/*
 		 * If we overwrite a PTE page pointer with a 2MB PMD, unlink
@@ -2725,6 +2721,14 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 			was_rmapped = 1;
 	}
 
+	if (unlikely(is_noslot_pfn(pfn))) {
+		mark_mmio_spte(vcpu, sptep, gfn, pte_access);
+		if (flush)
+			kvm_flush_remote_tlbs_with_address(vcpu->kvm, gfn,
+					KVM_PAGES_PER_HPAGE(level));
+		return RET_PF_EMULATE;
+	}
+
 	set_spte_ret = set_spte(vcpu, sptep, pte_access, level, gfn, pfn,
 				speculative, true, host_writable);
 	if (set_spte_ret & SET_SPTE_WRITE_PROTECTED_PT) {
@@ -3989,16 +3993,17 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
 
 	if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva))
 		goto out_unlock;
-	r = make_mmu_pages_available(vcpu);
-	if (r)
-		goto out_unlock;
 
-	if (is_tdp_mmu_fault)
+	if (is_tdp_mmu_fault) {
 		r = kvm_tdp_mmu_map(vcpu, gpa, error_code, map_writable, max_level,
 				    pfn, prefault);
-	else
+	} else {
+		r = make_mmu_pages_available(vcpu);
+		if (r)
+			goto out_unlock;
 		r = __direct_map(vcpu, gpa, error_code, map_writable, max_level, pfn,
 				 prefault, is_tdp);
+	}
 
 out_unlock:
 	if (is_tdp_mmu_fault)

arch/x86/kvm/vmx/nested.c

@@ -2986,7 +2986,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 					struct vmcs12 *vmcs12,
 					enum vm_entry_failure_code *entry_failure_code)
 {
-	bool ia32e;
+	bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE);
 
 	*entry_failure_code = ENTRY_FAIL_DEFAULT;
 
@@ -3012,6 +3012,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 					   vmcs12->guest_ia32_perf_global_ctrl)))
 		return -EINVAL;
 
+	if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG))
+		return -EINVAL;
+
+	if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) ||
+	    CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG)))
+		return -EINVAL;
+
 	/*
 	 * If the load IA32_EFER VM-entry control is 1, the following checks
 	 * are performed on the field for the IA32_EFER MSR:
@@ -3023,7 +3030,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	 */
 	if (to_vmx(vcpu)->nested.nested_run_pending &&
 	    (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
-		ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
 		if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) ||
 		    CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) ||
 		    CC(((vmcs12->guest_cr0 & X86_CR0_PG) &&

arch/x86/kvm/x86.c

@@ -7973,7 +7973,7 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
 
-static bool kvm_vcpu_check_breakpoint(struct kvm_vcpu *vcpu, int *r)
+static bool kvm_vcpu_check_code_breakpoint(struct kvm_vcpu *vcpu, int *r)
 {
 	if (unlikely(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) &&
 	    (vcpu->arch.guest_debug_dr7 & DR7_BP_EN_MASK)) {
@@ -8042,25 +8042,23 @@ static bool is_vmware_backdoor_opcode(struct x86_emulate_ctxt *ctxt)
 }
 
 /*
- * Decode to be emulated instruction. Return EMULATION_OK if success.
+ * Decode an instruction for emulation.  The caller is responsible for handling
+ * code breakpoints.  Note, manually detecting code breakpoints is unnecessary
+ * (and wrong) when emulating on an intercepted fault-like exception[*], as
+ * code breakpoints have higher priority and thus have already been done by
+ * hardware.
+ *
+ * [*] Except #MC, which is higher priority, but KVM should never emulate in
+ *     response to a machine check.
  */
 int x86_decode_emulated_instruction(struct kvm_vcpu *vcpu, int emulation_type,
 				    void *insn, int insn_len)
 {
-	int r = EMULATION_OK;
 	struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+	int r;
 
 	init_emulate_ctxt(vcpu);
 
-	/*
-	 * We will reenter on the same instruction since we do not set
-	 * complete_userspace_io. This does not handle watchpoints yet,
-	 * those would be handled in the emulate_ops.
-	 */
-	if (!(emulation_type & EMULTYPE_SKIP) &&
-	    kvm_vcpu_check_breakpoint(vcpu, &r))
-		return r;
-
 	r = x86_decode_insn(ctxt, insn, insn_len, emulation_type);
 
 	trace_kvm_emulate_insn_start(vcpu);
@@ -8093,6 +8091,15 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 	if (!(emulation_type & EMULTYPE_NO_DECODE)) {
 		kvm_clear_exception_queue(vcpu);
 
+		/*
+		 * Return immediately if RIP hits a code breakpoint, such #DBs
+		 * are fault-like and are higher priority than any faults on
+		 * the code fetch itself.
+		 */
+		if (!(emulation_type & EMULTYPE_SKIP) &&
+		    kvm_vcpu_check_code_breakpoint(vcpu, &r))
+			return r;
+
 		r = x86_decode_emulated_instruction(vcpu, emulation_type,
 						    insn, insn_len);
 		if (r != EMULATION_OK)  {