[PATCH v3] x86: svm: use kvm_fast_pio_in()

[Joel Schopp <joel.schopp@amd.com>]

From: David Kaplan <David.Kaplan@amd.com>

We can make the in instruction go faster the same way the out instruction is
already.

Changes from v2[Joel]:
	* changed rax from u32 to unsigned long
	* changed a couple return 0 to BUG_ON()
	* changed 8 to sizeof(new_rax)
	* added trace hook
	* removed redundant clearing of count
Changes from v1[Joel]
	* Added kvm_fast_pio_in() implementation that was left out of v1

Signed-off-by: David Kaplan <David.Kaplan@amd.com>
[extracted from larger unlrelated patch, forward ported, addressed reviews, tested]
Signed-off-by: Joel Schopp <joel.schopp@amd.com>
---
 arch/x86/include/asm/kvm_host.h |    1 +
 arch/x86/kvm/svm.c              |    4 +++-
 arch/x86/kvm/x86.c              |   30 ++++++++++++++++++++++++++++++
 3 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a236e39..b976824 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -931,6 +931,7 @@ 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_emulate_wbinvd(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index d319e0c..f8c906b 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1899,7 +1899,7 @@ 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;
@@ -1907,6 +1907,8 @@ static int io_interception(struct vcpu_svm *svm)
 	svm->next_rip = svm->vmcb->control.exit_info_2;
 	skip_emulated_instruction(&svm->vcpu);
 
+	if (in)
+		return kvm_fast_pio_in(vcpu, size, port);
 	return kvm_fast_pio_out(vcpu, size, port);
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bd7a70b..d05efaf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5463,6 +5463,36 @@ 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(struct kvm_vcpu *vcpu)
+{
+	unsigned long new_rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
+
+	BUG_ON(!vcpu->arch.pio.count);
+	BUG_ON(vcpu->arch.pio.count * vcpu->arch.pio.size > sizeof(new_rax));
+
+	memcpy(&new_rax, vcpu, sizeof(new_rax));
+	trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, vcpu->arch.pio.size,
+		      vcpu->arch.pio.count, vcpu->arch.pio_data);
+	kvm_register_write(vcpu, VCPU_REGS_RAX, new_rax);
+	vcpu->arch.pio.count = 0;
+	return 1;
+}
+
+int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size, unsigned short port)
+{
+	unsigned long val;
+	int ret = emulator_pio_in_emulated(&vcpu->arch.emulate_ctxt, size,
+					   port, &val, 1);
+
+	if (ret)
+		kvm_register_write(vcpu, VCPU_REGS_RAX, val);
+	else
+		vcpu->arch.complete_userspace_io = complete_fast_pio;
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(kvm_fast_pio_in);
+
 static void tsc_bad(void *info)
 {
 	__this_cpu_write(cpu_tsc_khz, 0);