KVM: x86: Introduce KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM

Add KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM to allow L1 to set
FREEZE_IN_SMM in vmcs12's GUEST_IA32_DEBUGCTL field, as permitted
prior to commit 6b1dd26 ("KVM: VMX: Preserve host's
DEBUGCTLMSR_FREEZE_IN_SMM while running the guest").  Enable the quirk
by default for backwards compatibility (like all quirks); userspace
can disable it via KVM_CAP_DISABLE_QUIRKS2 for consistency with the
constraints on WRMSR(IA32_DEBUGCTL).

Note that the quirk only bypasses the consistency check.  The vmcs02 bit is
still owned by the host, and PMCs are not frozen during virtualized SMM.
In particular, if a host administrator decides that PMCs should not be
frozen during physical SMM, then L1 has no say in the matter.

Fixes: 095686e ("KVM: nVMX: Check vmcs12->guest_ia32_debugctl on nested VM-Enter")
Cc: stable@vger.kernel.org
Signed-off-by: Jim Mattson <jmattson@google.com>
Link: https://patch.msgid.link/20260205231537.1278753-1-jmattson@google.com
[sean: tag for stable@, clean-up and fix goofs in the comment and docs]
Signed-off-by: Sean Christopherson <seanjc@google.com>
[Rename quirk. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Author: jsmattsonjr

Documentation/virt/kvm/api.rst

@@ -8543,6 +8543,14 @@ KVM_X86_QUIRK_IGNORE_GUEST_PAT      By default, on Intel platforms, KVM ignores
                                     guest software, for example if it does not
                                     expose a bochs graphics device (which is
                                     known to have had a buggy driver).
+
+KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM   By default, KVM relaxes the consistency
+                                      check for GUEST_IA32_DEBUGCTL in vmcs12
+                                      to allow FREEZE_IN_SMM to be set.  When
+                                      this quirk is disabled, KVM requires this
+                                      bit to be cleared.  Note that the vmcs02
+                                      bit is still completely controlled by the
+                                      host, regardless of the quirk setting.
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID

arch/x86/include/asm/kvm_host.h

@@ -2485,7 +2485,8 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS |	\
 	 KVM_X86_QUIRK_SLOT_ZAP_ALL |		\
 	 KVM_X86_QUIRK_STUFF_FEATURE_MSRS |	\
-	 KVM_X86_QUIRK_IGNORE_GUEST_PAT)
+	 KVM_X86_QUIRK_IGNORE_GUEST_PAT |	\
+	 KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM)
 
 #define KVM_X86_CONDITIONAL_QUIRKS		\
 	(KVM_X86_QUIRK_CD_NW_CLEARED |		\

arch/x86/include/uapi/asm/kvm.h

@@ -476,6 +476,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_SLOT_ZAP_ALL		(1 << 7)
 #define KVM_X86_QUIRK_STUFF_FEATURE_MSRS	(1 << 8)
 #define KVM_X86_QUIRK_IGNORE_GUEST_PAT		(1 << 9)
+#define KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM (1 << 10)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1

arch/x86/kvm/vmx/nested.c

@@ -3300,10 +3300,24 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
 	if (CC(vmcs12->guest_cr4 & X86_CR4_CET && !(vmcs12->guest_cr0 & X86_CR0_WP)))
 		return -EINVAL;
 
-	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
-	    (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
-	     CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
-		return -EINVAL;
+	if (vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) {
+		u64 debugctl = vmcs12->guest_ia32_debugctl;
+
+		/*
+		 * FREEZE_IN_SMM is not virtualized, but allow L1 to set it in
+		 * vmcs12's DEBUGCTL under a quirk for backwards compatibility.
+		 * Note that the quirk only relaxes the consistency check.  The
+		 * vmcc02 bit is still under the control of the host.  In
+		 * particular, if a host administrator decides to clear the bit,
+		 * then L1 has no say in the matter.
+		 */
+		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_VMCS12_ALLOW_FREEZE_IN_SMM))
+			debugctl &= ~DEBUGCTLMSR_FREEZE_IN_SMM;
+
+		if (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+		    CC(!vmx_is_valid_debugctl(vcpu, debugctl, false)))
+			return -EINVAL;
+	}
 
 	if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
 	    CC(!kvm_pat_valid(vmcs12->guest_ia32_pat)))