diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index da07e175dac8..77cb3f93de2b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1133,6 +1133,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
 struct x86_emulate_ctxt;
 
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port);
 void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int kvm_vcpu_halt(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 4e462bb85723..5e64e656103c 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -2270,7 +2270,7 @@ static int io_interception(struct vcpu_svm *svm)
 	++svm->vcpu.stat.io_exits;
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
-	if (string || in)
+	if (string)
 		return emulate_instruction(vcpu, 0) == EMULATE_DONE;
 
 	port = io_info >> 16;
@@ -2278,7 +2278,8 @@ static int io_interception(struct vcpu_svm *svm)
 	svm->next_rip = svm->vmcb->control.exit_info_2;
 	skip_emulated_instruction(&svm->vcpu);
 
-	return kvm_fast_pio_out(vcpu, size, port);
+	return in ? kvm_fast_pio_in(vcpu, size, port)
+		  : kvm_fast_pio_out(vcpu, size, port);
 }
 
 static int nmi_interception(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6f9c9ad13f88..ec59301f5192 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5615,6 +5615,49 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
+static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
+{
+	unsigned long val;
+
+	/* We should only ever be called with arch.pio.count equal to 1 */
+	BUG_ON(vcpu->arch.pio.count != 1);
+
+	/* For size less than 4 we merge, else we zero extend */
+	val = (vcpu->arch.pio.size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX)
+					: 0;
+
+	/*
+	 * Since vcpu->arch.pio.count == 1 let emulator_pio_in_emulated perform
+	 * the copy and tracing
+	 */
+	emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, vcpu->arch.pio.size,
+				 vcpu->arch.pio.port, &val, 1);
+	kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+
+	return 1;
+}
+
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port)
+{
+	unsigned long val;
+	int ret;
+
+	/* For size less than 4 we merge, else we zero extend */
+	val = (size < 4) ? kvm_register_read(vcpu, VCPU_REGS_RAX) : 0;
+
+	ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size, port,
+				       &val, 1);
+	if (ret) {
+		kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+		return ret;
+	}
+
+	vcpu->arch.complete_userspace_io = complete_fast_pio_in;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(kvm_fast_pio_in);
+
 static int kvmclock_cpu_down_prep(unsigned int cpu)
 {
 	__this_cpu_write(cpu_tsc_khz, 0);