KVM: inject #UD if instruction emulation fails and exit to userspace

Do not kill VM when instruction emulation fails. Inject #UD and report
failure to userspace instead. Userspace may choose to reenter guest if
vcpu is in userspace (cpl == 3) in which case guest OS will kill
offending process and continue running.

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

arch/x86/include/asm/kvm_host.h

@@ -576,7 +576,6 @@ enum emulation_result {
 #define EMULTYPE_SKIP		    (1 << 2)
 int emulate_instruction(struct kvm_vcpu *vcpu,
 			unsigned long cr2, u16 error_code, int emulation_type);
-void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 

arch/x86/kvm/mmu.c

@@ -2814,11 +2814,8 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 		return 1;
 	case EMULATE_DO_MMIO:
 		++vcpu->stat.mmio_exits;
-		return 0;
+		/* fall through */
 	case EMULATE_FAIL:
-		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-		vcpu->run->internal.ndata = 0;
 		return 0;
 	default:
 		BUG();

arch/x86/kvm/svm.c

@@ -1535,7 +1535,7 @@ static int io_interception(struct vcpu_svm *svm)
 	string = (io_info & SVM_IOIO_STR_MASK) != 0;
 	in = (io_info & SVM_IOIO_TYPE_MASK) != 0;
 	if (string || in)
-		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+		return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
 
 	port = io_info >> 16;
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
@@ -2386,16 +2386,12 @@ static int iret_interception(struct vcpu_svm *svm)
 
 static int invlpg_interception(struct vcpu_svm *svm)
 {
-	if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
+	return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE;
-		pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
-	return 1;
 }
 
 static int emulate_on_interception(struct vcpu_svm *svm)
 {
-	if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
+	return emulate_instruction(&svm->vcpu, 0, 0, 0) == EMULATE_DONE;
-		pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
-	return 1;
 }
 
 static int cr8_write_interception(struct vcpu_svm *svm)

arch/x86/kvm/vmx.c

@@ -3070,7 +3070,7 @@ static int handle_io(struct kvm_vcpu *vcpu)
 	++vcpu->stat.io_exits;
 
 	if (string || in)
-		return !(emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DO_MMIO);
+		return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
 
 	port = exit_qualification >> 16;
 	size = (exit_qualification & 7) + 1;
@@ -3327,22 +3327,7 @@ static int handle_wbinvd(struct kvm_vcpu *vcpu)
 
 static int handle_apic_access(struct kvm_vcpu *vcpu)
 {
-	unsigned long exit_qualification;
+	return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
-	enum emulation_result er;
-	unsigned long offset;
-
-	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	offset = exit_qualification & 0xffful;
-
-	er = emulate_instruction(vcpu, 0, 0, 0);
-
-	if (er !=  EMULATE_DONE) {
-		printk(KERN_ERR
-		       "Fail to handle apic access vmexit! Offset is 0x%lx\n",
-		       offset);
-		return -ENOEXEC;
-	}
-	return 1;
 }
 
 static int handle_task_switch(struct kvm_vcpu *vcpu)
@@ -3554,13 +3539,8 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 			goto out;
 		}
 
-		if (err != EMULATE_DONE) {
+		if (err != EMULATE_DONE)
-			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			return 0;
-			vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
-			vcpu->run->internal.ndata = 0;
-			ret = 0;
-			goto out;
-		}
 
 		if (signal_pending(current))
 			goto out;

arch/x86/kvm/x86.c

@@ -3639,24 +3639,6 @@ int emulator_set_dr(int dr, unsigned long value, struct kvm_vcpu *vcpu)
 	return __kvm_set_dr(vcpu, dr, value);
 }
 
-void kvm_report_emulation_failure(struct kvm_vcpu *vcpu, const char *context)
-{
-	u8 opcodes[4];
-	unsigned long rip = kvm_rip_read(vcpu);
-	unsigned long rip_linear;
-
-	if (!printk_ratelimit())
-		return;
-
-	rip_linear = rip + get_segment_base(vcpu, VCPU_SREG_CS);
-
-	kvm_read_guest_virt(rip_linear, (void *)opcodes, 4, vcpu, NULL);
-
-	printk(KERN_ERR "emulation failed (%s) rip %lx %02x %02x %02x %02x\n",
-	       context, rip, opcodes[0], opcodes[1], opcodes[2], opcodes[3]);
-}
-EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
-
 static u64 mk_cr_64(u64 curr_cr, u32 new_val)
 {
 	return (curr_cr & ~((1ULL << 32) - 1)) | new_val;
@@ -3863,6 +3845,19 @@ static void inject_emulated_exception(struct kvm_vcpu *vcpu)
 		kvm_queue_exception(vcpu, ctxt->exception);
 }
 
+static int handle_emulation_failure(struct kvm_vcpu *vcpu)
+{
+	struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
+
+	++vcpu->stat.insn_emulation_fail;
+	trace_kvm_emulate_insn_failed(vcpu);
+	vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+	vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+	vcpu->run->internal.ndata = 0;
+	kvm_queue_exception(vcpu, UD_VECTOR);
+	return EMULATE_FAIL;
+}
+
 int emulate_instruction(struct kvm_vcpu *vcpu,
 			unsigned long cr2,
 			u16 error_code,
@@ -3931,11 +3926,11 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 
 		++vcpu->stat.insn_emulation;
 		if (r)  {
-			++vcpu->stat.insn_emulation_fail;
-			trace_kvm_emulate_insn_failed(vcpu);
 			if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
 				return EMULATE_DONE;
+			if (emulation_type & EMULTYPE_SKIP)
 				return EMULATE_FAIL;
+			return handle_emulation_failure(vcpu);
 		}
 	}
 
@@ -3960,9 +3955,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
 			return EMULATE_DONE;
 
-		trace_kvm_emulate_insn_failed(vcpu);
+		return handle_emulation_failure(vcpu);
-		kvm_report_emulation_failure(vcpu, "mmio");
-		return EMULATE_FAIL;
 	}
 
 	toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility);
@@ -4798,7 +4791,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 		r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
 		srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
-		if (r == EMULATE_DO_MMIO) {
+		if (r != EMULATE_DONE) {
 			r = 0;
 			goto out;
 		}