KVM: x86: wean in-kernel PIO from vcpu->arch.pio*

Make emulator_pio_in_out operate directly on the provided buffer
as long as PIO is handled inside KVM.

For input operations, this means that, in the case of in-kernel
PIO, __emulator_pio_in() does not have to be always followed
by complete_emulator_pio_in().  This affects emulator_pio_in() and
kvm_sev_es_ins(); for the latter, that is why the call moves from
advance_sev_es_emulated_ins() to complete_sev_es_emulated_ins().

For output, it means that vcpu->pio.count is never set unnecessarily
and there is no need to clear it; but also vcpu->pio.size must not
be used in kvm_sev_es_outs(), because it will not be updated for
in-kernel OUT.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

arch/x86/kvm/x86.c

@@ -7583,19 +7583,6 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
 	int r;
 
 	WARN_ON_ONCE(vcpu->arch.pio.count);
-	vcpu->arch.pio.port = port;
-	vcpu->arch.pio.in = in;
-	vcpu->arch.pio.count = count;
-	vcpu->arch.pio.size = size;
-	if (in) {
-		/* The buffer is only used in complete_emulator_pio_in().  */
-		WARN_ON(data);
-		memset(vcpu->arch.pio_data, 0, size * count);
-	} else {
-		memcpy(vcpu->arch.pio_data, data, size * count);
-	}
-	data = vcpu->arch.pio_data;
-
 	for (i = 0; i < count; i++) {
 		if (in)
 			r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, port, size, data);
@@ -7608,9 +7595,10 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
 
 			/*
 			 * Userspace must have unregistered the device while PIO
-			 * was running.  Drop writes / read as 0 (the buffer
-			 * was zeroed in __emulator_pio_in).
+			 * was running.  Drop writes / read as 0.
 			 */
+			if (in)
+				memset(data, 0, size * (count - i));
 			break;
 		}
 
@@ -7619,6 +7607,16 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
 	return 1;
 
 userspace_io:
+	vcpu->arch.pio.port = port;
+	vcpu->arch.pio.in = in;
+	vcpu->arch.pio.count = count;
+	vcpu->arch.pio.size = size;
+
+	if (in)
+		memset(vcpu->arch.pio_data, 0, size * count);
+	else
+		memcpy(vcpu->arch.pio_data, data, size * count);
+
 	vcpu->run->exit_reason = KVM_EXIT_IO;
 	vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
 	vcpu->run->io.size = size;
@@ -7629,15 +7627,19 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
 }
 
 static int __emulator_pio_in(struct kvm_vcpu *vcpu, int size,
-			     unsigned short port, unsigned int count)
+			     unsigned short port, void *val, unsigned int count)
 {
-	return emulator_pio_in_out(vcpu, size, port, NULL, count, true);
+	int r = emulator_pio_in_out(vcpu, size, port, val, count, true);
+	if (r)
+		trace_kvm_pio(KVM_PIO_IN, port, size, count, val);
+
+	return r;
 }
 
 static void complete_emulator_pio_in(struct kvm_vcpu *vcpu, void *val)
 {
 	int size = vcpu->arch.pio.size;
-	unsigned count = vcpu->arch.pio.count;
+	unsigned int count = vcpu->arch.pio.count;
 	memcpy(val, vcpu->arch.pio_data, size * count);
 	trace_kvm_pio(KVM_PIO_IN, vcpu->arch.pio.port, size, count, vcpu->arch.pio_data);
 	vcpu->arch.pio.count = 0;
@@ -7654,16 +7656,11 @@ static int emulator_pio_in(struct kvm_vcpu *vcpu, int size,
 		 * shenanigans as KVM doesn't support modifying the rep count,
 		 * and the emulator ensures @count doesn't overflow the buffer.
 		 */
-	} else {
-		int r = __emulator_pio_in(vcpu, size, port, count);
-		if (!r)
-			return r;
-
-		/* Results already available, fall through.  */
+		complete_emulator_pio_in(vcpu, val);
+		return 1;
 	}
 
-	complete_emulator_pio_in(vcpu, val);
-	return 1;
+	return __emulator_pio_in(vcpu, size, port, val, count);
 }
 
 static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
@@ -7678,14 +7675,8 @@ static int emulator_pio_out(struct kvm_vcpu *vcpu, int size,
 			    unsigned short port, const void *val,
 			    unsigned int count)
 {
-	int ret;
-
 	trace_kvm_pio(KVM_PIO_OUT, port, size, count, val);
-	ret = emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
-	if (ret)
-                vcpu->arch.pio.count = 0;
-
-        return ret;
+	return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
 }
 
 static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
@@ -13245,7 +13236,7 @@ static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
 
 		/* memcpy done already by emulator_pio_out.  */
 		vcpu->arch.sev_pio_count -= count;
-		vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+		vcpu->arch.sev_pio_data += count * size;
 		if (!ret)
 			break;
 
@@ -13261,20 +13252,20 @@ static int kvm_sev_es_outs(struct kvm_vcpu *vcpu, unsigned int size,
 static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
 			  unsigned int port);
 
-static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
+static void advance_sev_es_emulated_ins(struct kvm_vcpu *vcpu, unsigned count, int size)
 {
-	unsigned count = vcpu->arch.pio.count;
-	complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data);
 	vcpu->arch.sev_pio_count -= count;
-	vcpu->arch.sev_pio_data += count * vcpu->arch.pio.size;
+	vcpu->arch.sev_pio_data += count * size;
 }
 
 static int complete_sev_es_emulated_ins(struct kvm_vcpu *vcpu)
 {
+	unsigned count = vcpu->arch.pio.count;
 	int size = vcpu->arch.pio.size;
 	int port = vcpu->arch.pio.port;
 
-	advance_sev_es_emulated_ins(vcpu);
+	complete_emulator_pio_in(vcpu, vcpu->arch.sev_pio_data);
+	advance_sev_es_emulated_ins(vcpu, count, size);
 	if (vcpu->arch.sev_pio_count)
 		return kvm_sev_es_ins(vcpu, size, port);
 	return 1;
@@ -13286,11 +13277,11 @@ static int kvm_sev_es_ins(struct kvm_vcpu *vcpu, unsigned int size,
 	for (;;) {
 		unsigned int count =
 			min_t(unsigned int, PAGE_SIZE / size, vcpu->arch.sev_pio_count);
-		if (!__emulator_pio_in(vcpu, size, port, count))
+		if (!__emulator_pio_in(vcpu, size, port, vcpu->arch.sev_pio_data, count))
 			break;
 
 		/* Emulation done by the kernel.  */
-		advance_sev_es_emulated_ins(vcpu);
+		advance_sev_es_emulated_ins(vcpu, count, size);
 		if (!vcpu->arch.sev_pio_count)
 			return 1;
 	}