KVM: x86 emulator: fix in/out emulation.

in/out emulation is broken now. The breakage is different depending
on where IO device resides. If it is in userspace emulator reports
emulation failure since it incorrectly interprets kvm_emulate_pio()
return value. If IO device is in the kernel emulation of 'in' will do
nothing since kvm_emulate_pio() stores result directly into vcpu
registers, so emulator will overwrite result of emulation during
commit of shadowed register.

Signed-off-by: Gleb Natapov <gleb@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

arch/x86/include/asm/kvm_emulate.h

@@ -119,6 +119,13 @@ struct x86_emulate_ops {
 				const void *new,
 				unsigned int bytes,
 				struct kvm_vcpu *vcpu);
+
+	int (*pio_in_emulated)(int size, unsigned short port, void *val,
+			       unsigned int count, struct kvm_vcpu *vcpu);
+
+	int (*pio_out_emulated)(int size, unsigned short port, const void *val,
+				unsigned int count, struct kvm_vcpu *vcpu);
+
 	bool (*get_cached_descriptor)(struct desc_struct *desc,
 				      int seg, struct kvm_vcpu *vcpu);
 	void (*set_cached_descriptor)(struct desc_struct *desc,

arch/x86/include/asm/kvm_host.h

@@ -590,8 +590,7 @@ int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
 
 struct x86_emulate_ctxt;
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in,
-		     int size, unsigned port);
+int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
 int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 			   int size, unsigned long count, int down,
 			    gva_t address, int rep, unsigned port);

arch/x86/kvm/emulate.c

@@ -210,13 +210,13 @@ static u32 opcode_table[256] = {
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xE0 - 0xE7 */
 	0, 0, 0, 0,
-	ByteOp | SrcImmUByte, SrcImmUByte,
-	ByteOp | SrcImmUByte, SrcImmUByte,
+	ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc,
+	ByteOp | SrcImmUByte | DstAcc, SrcImmUByte | DstAcc,
 	/* 0xE8 - 0xEF */
 	SrcImm | Stack, SrcImm | ImplicitOps,
 	SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
-	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
+	SrcNone | ByteOp | DstAcc, SrcNone | DstAcc,
+	SrcNone | ByteOp | DstAcc, SrcNone | DstAcc,
 	/* 0xF0 - 0xF7 */
 	0, 0, 0, 0,
 	ImplicitOps | Priv, ImplicitOps, Group | Group3_Byte, Group | Group3,
@@ -2426,8 +2426,6 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	u64 msr_data;
 	unsigned long saved_eip = 0;
 	struct decode_cache *c = &ctxt->decode;
-	unsigned int port;
-	int io_dir_in;
 	int rc = X86EMUL_CONTINUE;
 
 	ctxt->interruptibility = 0;
@@ -2823,14 +2821,10 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0xe4: 	/* inb */
 	case 0xe5: 	/* in */
-		port = c->src.val;
-		io_dir_in = 1;
-		goto do_io;
+		goto do_io_in;
 	case 0xe6: /* outb */
 	case 0xe7: /* out */
-		port = c->src.val;
-		io_dir_in = 0;
-		goto do_io;
+		goto do_io_out;
 	case 0xe8: /* call (near) */ {
 		long int rel = c->src.val;
 		c->src.val = (unsigned long) c->eip;
@@ -2855,25 +2849,29 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 		break;
 	case 0xec: /* in al,dx */
 	case 0xed: /* in (e/r)ax,dx */
-		port = c->regs[VCPU_REGS_RDX];
-		io_dir_in = 1;
-		goto do_io;
+		c->src.val = c->regs[VCPU_REGS_RDX];
+	do_io_in:
+		c->dst.bytes = min(c->dst.bytes, 4u);
+		if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			goto done;
+		}
+		if (!ops->pio_in_emulated(c->dst.bytes, c->src.val,
+					  &c->dst.val, 1, ctxt->vcpu))
+			goto done; /* IO is needed */
+		break;
 	case 0xee: /* out al,dx */
 	case 0xef: /* out (e/r)ax,dx */
-		port = c->regs[VCPU_REGS_RDX];
-		io_dir_in = 0;
-	do_io:
-		if (!emulator_io_permited(ctxt, ops, port,
-					  (c->d & ByteOp) ? 1 : c->op_bytes)) {
+		c->src.val = c->regs[VCPU_REGS_RDX];
+	do_io_out:
+		c->dst.bytes = min(c->dst.bytes, 4u);
+		if (!emulator_io_permited(ctxt, ops, c->src.val, c->dst.bytes)) {
 			kvm_inject_gp(ctxt->vcpu, 0);
 			goto done;
 		}
-		if (kvm_emulate_pio(ctxt->vcpu, io_dir_in,
-				   (c->d & ByteOp) ? 1 : c->op_bytes,
-				   port) != 0) {
-			c->eip = saved_eip;
-			goto cannot_emulate;
-		}
+		ops->pio_out_emulated(c->dst.bytes, c->src.val, &c->dst.val, 1,
+				      ctxt->vcpu);
+		c->dst.type = OP_NONE;	/* Disable writeback. */
 		break;
 	case 0xf4:              /* hlt */
 		ctxt->vcpu->arch.halt_request = 1;

arch/x86/kvm/svm.c

@@ -1494,29 +1494,23 @@ static int shutdown_interception(struct vcpu_svm *svm)
 
 static int io_interception(struct vcpu_svm *svm)
 {
+	struct kvm_vcpu *vcpu = &svm->vcpu;
 	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
 	int size, in, string;
 	unsigned port;
 
 	++svm->vcpu.stat.io_exits;
-
-	svm->next_rip = svm->vmcb->control.exit_info_2;
-
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
-
-	if (string) {
-		if (emulate_instruction(&svm->vcpu,
-					0, 0, 0) == EMULATE_DO_MMIO)
-			return 0;
-		return 1;
-	}
-
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
+	if (string || in)
+		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
-
+	svm->next_rip = svm->vmcb->control.exit_info_2;
 	skip_emulated_instruction(&svm->vcpu);
-	return kvm_emulate_pio(&svm->vcpu, in, size, port);
+
+	return kvm_fast_pio_out(vcpu, size, port);
 }
 
 static int nmi_interception(struct vcpu_svm *svm)

arch/x86/kvm/vmx.c

@@ -2985,22 +2985,20 @@ static int handle_io(struct kvm_vcpu *vcpu)
 	int size, in, string;
 	unsigned port;
 
-	++vcpu->stat.io_exits;
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
 	string = (exit_qualification & 16) != 0;
+	in = (exit_qualification & 8) != 0;
 
-	if (string) {
-		if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO)
-			return 0;
-		return 1;
-	}
+	++vcpu->stat.io_exits;
 
-	size = (exit_qualification & 7) + 1;
-	in = (exit_qualification & 8) != 0;
-	port = exit_qualification >> 16;
+	if (string || in)
+		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
 
+	port = exit_qualification >> 16;
+	size = (exit_qualification & 7) + 1;
 	skip_emulated_instruction(vcpu);
-	return kvm_emulate_pio(vcpu, in, size, port);
+
+	return kvm_fast_pio_out(vcpu, size, port);
 }
 
 static void