KVM: x86: Add a quirk for KVM's "MONITOR/MWAIT are NOPs!" behavior

Add a quirk for KVM's behavior of emulating intercepted MONITOR/MWAIT
instructions a NOPs regardless of whether or not they are supported in
guest CPUID.  KVM's current behavior was likely motiviated by a certain
fruity operating system that expects MONITOR/MWAIT to be supported
unconditionally and blindly executes MONITOR/MWAIT without first checking
CPUID.  And because KVM does NOT advertise MONITOR/MWAIT to userspace,
that's effectively the default setup for any VMM that regurgitates
KVM_GET_SUPPORTED_CPUID to KVM_SET_CPUID2.

Note, this quirk interacts with KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT.  The
behavior is actually desirable, as userspace VMMs that want to
unconditionally hide MONITOR/MWAIT from the guest can leave the
MISC_ENABLE quirk enabled.
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20220608224516.3788274-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -7522,6 +7522,19 @@ The valid bits in cap.args[0] are:
                                     hypercall instructions. Executing the
                                     incorrect hypercall instruction will
                                     generate a #UD within the guest.
+
+KVM_X86_QUIRK_MWAIT_NEVER_FAULTS    By default, KVM emulates MONITOR/MWAIT (if
+                                    they are intercepted) as NOPs regardless of
+                                    whether or not MONITOR/MWAIT are supported
+                                    according to guest CPUID.  When this quirk
+                                    is disabled and KVM_X86_DISABLE_EXITS_MWAIT
+                                    is not set (MONITOR/MWAIT are intercepted),
+                                    KVM will inject a #UD on MONITOR/MWAIT if
+                                    they're unsupported per guest CPUID.  Note,
+                                    KVM will modify MONITOR/MWAIT support in
+                                    guest CPUID on writes to MISC_ENABLE if
+                                    KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT is
+                                    disabled.
 =================================== ============================================
 
 7.32 KVM_CAP_MAX_VCPU_ID

arch/x86/include/asm/kvm_host.h

@@ -2076,6 +2076,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
 	 KVM_X86_QUIRK_LAPIC_MMIO_HOLE |	\
 	 KVM_X86_QUIRK_OUT_7E_INC_RIP |		\
 	 KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT |	\
-	 KVM_X86_QUIRK_FIX_HYPERCALL_INSN)
+	 KVM_X86_QUIRK_FIX_HYPERCALL_INSN |	\
+	 KVM_X86_QUIRK_MWAIT_NEVER_FAULTS)
 
 #endif /* _ASM_X86_KVM_HOST_H */

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

@@ -439,6 +439,7 @@ struct kvm_sync_regs {
 #define KVM_X86_QUIRK_OUT_7E_INC_RIP		(1 << 3)
 #define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT	(1 << 4)
 #define KVM_X86_QUIRK_FIX_HYPERCALL_INSN	(1 << 5)
+#define KVM_X86_QUIRK_MWAIT_NEVER_FAULTS	(1 << 6)
 
 #define KVM_STATE_NESTED_FORMAT_VMX	0
 #define KVM_STATE_NESTED_FORMAT_SVM	1

arch/x86/kvm/x86.c

@@ -2036,13 +2036,6 @@ int kvm_emulate_invd(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_invd);
 
-int kvm_emulate_mwait(struct kvm_vcpu *vcpu)
-{
-	pr_warn_once("kvm: MWAIT instruction emulated as NOP!\n");
-	return kvm_emulate_as_nop(vcpu);
-}
-EXPORT_SYMBOL_GPL(kvm_emulate_mwait);
-
 int kvm_handle_invalid_op(struct kvm_vcpu *vcpu)
 {
 	kvm_queue_exception(vcpu, UD_VECTOR);
@@ -2050,11 +2043,26 @@ int kvm_handle_invalid_op(struct kvm_vcpu *vcpu)
 }
 EXPORT_SYMBOL_GPL(kvm_handle_invalid_op);
 
-int kvm_emulate_monitor(struct kvm_vcpu *vcpu)
+
+static int kvm_emulate_monitor_mwait(struct kvm_vcpu *vcpu, const char *insn)
 {
-	pr_warn_once("kvm: MONITOR instruction emulated as NOP!\n");
+	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MWAIT_NEVER_FAULTS) &&
+	    !guest_cpuid_has(vcpu, X86_FEATURE_MWAIT))
+		return kvm_handle_invalid_op(vcpu);
+
+	pr_warn_once("kvm: %s instruction emulated as NOP!\n", insn);
 	return kvm_emulate_as_nop(vcpu);
 }
+int kvm_emulate_mwait(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_monitor_mwait(vcpu, "MWAIT");
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_mwait);
+
+int kvm_emulate_monitor(struct kvm_vcpu *vcpu)
+{
+	return kvm_emulate_monitor_mwait(vcpu, "MONITOR");
+}
 EXPORT_SYMBOL_GPL(kvm_emulate_monitor);
 
 static inline bool kvm_vcpu_exit_request(struct kvm_vcpu *vcpu)
@@ -3884,8 +3892,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
 			return kvm_pmu_get_msr(vcpu, msr_info);
 		/*
-		 * Userspace is allowed to read MSRs that KVM reports in
-		 * KVM_GET_MSR_INDEX_LIST, even if an MSR isn't fully supported.
+		 * Userspace is allowed to read MSRs that KVM reports as
+		 * to-be-saved, even if an MSR isn't fully supported.
 		 */
 		if (!msr_info->host_initiated)
 			return 1;