KVM: x86: hyper-v: allow KVM_GET_SUPPORTED_HV_CPUID as a system ioctl

KVM_GET_SUPPORTED_HV_CPUID is a vCPU ioctl but its output is now
independent from vCPU and in some cases VMMs may want to use it as a system
ioctl instead. In particular, QEMU doesn CPU feature expansion before any
vCPU gets created so KVM_GET_SUPPORTED_HV_CPUID can't be used.

Convert KVM_GET_SUPPORTED_HV_CPUID to 'dual' system/vCPU ioctl with the
same meaning.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Message-Id: <20200929150944.1235688-2-vkuznets@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -4455,9 +4455,9 @@ that KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2 is present.
 4.118 KVM_GET_SUPPORTED_HV_CPUID
 --------------------------------
 
-:Capability: KVM_CAP_HYPERV_CPUID
+:Capability: KVM_CAP_HYPERV_CPUID (vcpu), KVM_CAP_SYS_HYPERV_CPUID (system)
 :Architectures: x86
-:Type: vcpu ioctl
+:Type: system ioctl, vcpu ioctl
 :Parameters: struct kvm_cpuid2 (in/out)
 :Returns: 0 on success, -1 on error
 
@@ -4502,9 +4502,6 @@ Currently, the following list of CPUID leaves are returned:
  - HYPERV_CPUID_SYNDBG_INTERFACE
  - HYPERV_CPUID_SYNDBG_PLATFORM_CAPABILITIES
 
-HYPERV_CPUID_NESTED_FEATURES leaf is only exposed when Enlightened VMCS was
-enabled on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
-
 Userspace invokes KVM_GET_SUPPORTED_HV_CPUID by passing a kvm_cpuid2 structure
 with the 'nent' field indicating the number of entries in the variable-size
 array 'entries'.  If the number of entries is too low to describe all Hyper-V
@@ -4515,6 +4512,15 @@ number of valid entries in the 'entries' array, which is then filled.
 'index' and 'flags' fields in 'struct kvm_cpuid_entry2' are currently reserved,
 userspace should not expect to get any particular value there.
 
+Note, vcpu version of KVM_GET_SUPPORTED_HV_CPUID is currently deprecated. Unlike
+system ioctl which exposes all supported feature bits unconditionally, vcpu
+version has the following quirks:
+- HYPERV_CPUID_NESTED_FEATURES leaf and HV_X64_ENLIGHTENED_VMCS_RECOMMENDED
+  feature bit are only exposed when Enlightened VMCS was previously enabled
+  on the corresponding vCPU (KVM_CAP_HYPERV_ENLIGHTENED_VMCS).
+- HV_STIMER_DIRECT_MODE_AVAILABLE bit is only exposed with in-kernel LAPIC.
+  (presumes KVM_CREATE_IRQCHIP has already been called).
+
 4.119 KVM_ARM_VCPU_FINALIZE
 ---------------------------
 

arch/x86/kvm/hyperv.c

@@ -1951,8 +1951,8 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args)
 	return kvm_hv_eventfd_assign(kvm, args->conn_id, args->fd);
 }
 
-int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
+int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
-				struct kvm_cpuid_entry2 __user *entries)
+		     struct kvm_cpuid_entry2 __user *entries)
 {
 	uint16_t evmcs_ver = 0;
 	struct kvm_cpuid_entry2 cpuid_entries[] = {
@@ -2037,7 +2037,7 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
 			 * Direct Synthetic timers only make sense with in-kernel
 			 * LAPIC
 			 */
-			if (lapic_in_kernel(vcpu))
+			if (!vcpu || lapic_in_kernel(vcpu))
 				ent->edx |= HV_STIMER_DIRECT_MODE_AVAILABLE;
 
 			break;

arch/x86/kvm/hyperv.h

@@ -126,7 +126,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 void kvm_hv_init_vm(struct kvm *kvm);
 void kvm_hv_destroy_vm(struct kvm *kvm);
 int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args);
-int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
+int kvm_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
-				struct kvm_cpuid_entry2 __user *entries);
+		     struct kvm_cpuid_entry2 __user *entries);
 
 #endif

arch/x86/kvm/vmx/evmcs.c

@@ -326,7 +326,6 @@ bool nested_enlightened_vmentry(struct kvm_vcpu *vcpu, u64 *evmcs_gpa)
 
 uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	/*
 	 * vmcs_version represents the range of supported Enlightened VMCS
 	 * versions: lower 8 bits is the minimal version, higher 8 bits is the
@@ -334,7 +333,7 @@ uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
 	 * KVM_EVMCS_VERSION.
 	 */
 	if (kvm_cpu_cap_get(X86_FEATURE_VMX) &&
-	    vmx->nested.enlightened_vmcs_enabled)
+	    (!vcpu || to_vmx(vcpu)->nested.enlightened_vmcs_enabled))
 		return (KVM_EVMCS_VERSION << 8) | 1;
 
 	return 0;

arch/x86/kvm/x86.c

@@ -3677,6 +3677,27 @@ static inline bool kvm_can_mwait_in_guest(void)
 		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
+static int kvm_ioctl_get_supported_hv_cpuid(struct kvm_vcpu *vcpu,
+					    struct kvm_cpuid2 __user *cpuid_arg)
+{
+	struct kvm_cpuid2 cpuid;
+	int r;
+
+	r = -EFAULT;
+	if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
+		return r;
+
+	r = kvm_get_hv_cpuid(vcpu, &cpuid, cpuid_arg->entries);
+	if (r)
+		return r;
+
+	r = -EFAULT;
+	if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
+		return r;
+
+	return 0;
+}
+
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 {
 	int r = 0;
@@ -3713,6 +3734,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_HYPERV_TLBFLUSH:
 	case KVM_CAP_HYPERV_SEND_IPI:
 	case KVM_CAP_HYPERV_CPUID:
+	case KVM_CAP_SYS_HYPERV_CPUID:
 	case KVM_CAP_PCI_SEGMENT:
 	case KVM_CAP_DEBUGREGS:
 	case KVM_CAP_X86_ROBUST_SINGLESTEP:
@@ -3898,6 +3920,9 @@ long kvm_arch_dev_ioctl(struct file *filp,
 	case KVM_GET_MSRS:
 		r = msr_io(NULL, argp, do_get_msr_feature, 1);
 		break;
+	case KVM_GET_SUPPORTED_HV_CPUID:
+		r = kvm_ioctl_get_supported_hv_cpuid(NULL, argp);
+		break;
 	default:
 		r = -EINVAL;
 		break;
@@ -4974,25 +4999,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
-	case KVM_GET_SUPPORTED_HV_CPUID: {
+	case KVM_GET_SUPPORTED_HV_CPUID:
-		struct kvm_cpuid2 __user *cpuid_arg = argp;
+		r = kvm_ioctl_get_supported_hv_cpuid(vcpu, argp);
-		struct kvm_cpuid2 cpuid;
-
-		r = -EFAULT;
-		if (copy_from_user(&cpuid, cpuid_arg, sizeof(cpuid)))
-			goto out;
-
-		r = kvm_vcpu_ioctl_get_hv_cpuid(vcpu, &cpuid,
-						cpuid_arg->entries);
-		if (r)
-			goto out;
-
-		r = -EFAULT;
-		if (copy_to_user(cpuid_arg, &cpuid, sizeof(cpuid)))
-			goto out;
-		r = 0;
 		break;
-	}
 	default:
 		r = -EINVAL;
 	}

include/uapi/linux/kvm.h

@@ -1053,6 +1053,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_X86_USER_SPACE_MSR 188
 #define KVM_CAP_X86_MSR_FILTER 189
 #define KVM_CAP_ENFORCE_PV_FEATURE_CPUID 190
+#define KVM_CAP_SYS_HYPERV_CPUID 191
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1511,7 +1512,7 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_MANUAL_DIRTY_LOG_PROTECT_2 */
 #define KVM_CLEAR_DIRTY_LOG          _IOWR(KVMIO, 0xc0, struct kvm_clear_dirty_log)
 
-/* Available with KVM_CAP_HYPERV_CPUID */
+/* Available with KVM_CAP_HYPERV_CPUID (vcpu) / KVM_CAP_SYS_HYPERV_CPUID (system) */
 #define KVM_GET_SUPPORTED_HV_CPUID _IOWR(KVMIO, 0xc1, struct kvm_cpuid2)
 
 /* Available with KVM_CAP_ARM_SVE */