KVM/Hyper-V: Add new KVM capability KVM_CAP_HYPERV_DIRECT_TLBFLUSH

Hyper-V direct tlb flush function should be enabled for
guest that only uses Hyper-V hypercall. User space
hypervisor(e.g, Qemu) can disable KVM identification in
CPUID and just exposes Hyper-V identification to make
sure the precondition. Add new KVM capability KVM_CAP_
HYPERV_DIRECT_TLBFLUSH for user space to enable Hyper-V
direct tlb function and this function is default to be
disabled in KVM.

Signed-off-by: Tianyu Lan <Tianyu.Lan@microsoft.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/Documentation/virt/kvm/api.txt b/Documentation/virt/kvm/api.txt
index 136f1ee..4833904 100644
--- a/Documentation/virt/kvm/api.txt
+++ b/Documentation/virt/kvm/api.txt
@@ -5309,3 +5309,16 @@
 This capability indicates that KVM supports paravirtualized Hyper-V IPI send
 hypercalls:
 HvCallSendSyntheticClusterIpi, HvCallSendSyntheticClusterIpiEx.
+8.21 KVM_CAP_HYPERV_DIRECT_TLBFLUSH
+
+Architecture: x86
+
+This capability indicates that KVM running on top of Hyper-V hypervisor
+enables Direct TLB flush for its guests meaning that TLB flush
+hypercalls are handled by Level 0 hypervisor (Hyper-V) bypassing KVM.
+Due to the different ABI for hypercall parameters between Hyper-V and
+KVM, enabling this capability effectively disables all hypercall
+handling by KVM (as some KVM hypercall may be mistakenly treated as TLB
+flush hypercalls by Hyper-V) so userspace should disable KVM identification
+in CPUID and only exposes Hyper-V identification. In this case, guest
+thinks it's running on Hyper-V and only use Hyper-V hypercalls.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a3a3ec7..4765ae0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1213,6 +1213,7 @@ struct kvm_x86_ops {
 	bool (*need_emulation_on_page_fault)(struct kvm_vcpu *vcpu);
 
 	bool (*apic_init_signal_blocked)(struct kvm_vcpu *vcpu);
+	int (*enable_direct_tlbflush)(struct kvm_vcpu *vcpu);
 };
 
 struct kvm_arch_async_pf {
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bb93771..5becc67 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3282,6 +3282,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 		r = kvm_x86_ops->get_nested_state ?
 			kvm_x86_ops->get_nested_state(NULL, NULL, 0) : 0;
 		break;
+	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
+		r = kvm_x86_ops->enable_direct_tlbflush ? 1 : 0;
+		break;
 	default:
 		break;
 	}
@@ -4055,6 +4058,11 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 				r = -EFAULT;
 		}
 		return r;
+	case KVM_CAP_HYPERV_DIRECT_TLBFLUSH:
+		if (!kvm_x86_ops->enable_direct_tlbflush)
+			return -ENOTTY;
+
+		return kvm_x86_ops->enable_direct_tlbflush(vcpu);
 
 	default:
 		return -EINVAL;
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 233efbb..c73aead 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -999,6 +999,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_ARM_PTRAUTH_GENERIC 172
 #define KVM_CAP_PMU_EVENT_FILTER 173
 #define KVM_CAP_ARM_IRQ_LINE_LAYOUT_2 174
+#define KVM_CAP_HYPERV_DIRECT_TLBFLUSH 175
 
 #ifdef KVM_CAP_IRQ_ROUTING