[patch 1/2] KVM: x86: do not entry guest mode if vcpu is not runnable

[Marcelo Tosatti <mtosatti@redhat.com>]

[-- Attachment #1: vcpublock-caller-handles-mpstate --]
[-- Type: text/plain, Size: 3901 bytes --]

If a vcpu has been offlined, or not initialized at all, signals
requesting userspace work to be performed will result in KVM attempting
to re-entry guest mode.

Problem is that the in-kernel irqchip emulation happily executes HALTED
state vcpu's. This breaks "savevm" on Windows SMP installation (that
only boots up a single vcpu), for example.

Fix it by blocking halted vcpu's at kvm_arch_vcpu_ioctl_run(). 

Change the promotion from halted to running to happen in the vcpu
context. Use the information available in kvm_vcpu_block(), and the
current mpstate to make the decision:

- If there's an in-kernel timer or irq event the halted->running
promotion evaluation can be performed, no need for userspace assistance.

- If there's a signal, there's either userspace work to be performed
in the vcpu's context or irqchip emulation is in userspace.

This has the nice side effect of avoiding userspace exit in case 
of irq injection to a halted vcpu from the iothread.

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

Index: kvm/arch/x86/kvm/x86.c
===================================================================
--- kvm.orig/arch/x86/kvm/x86.c
+++ kvm/arch/x86/kvm/x86.c
@@ -2505,17 +2505,25 @@ void kvm_arch_exit(void)
 	kvm_mmu_module_exit();
 }
 
+static void kvm_vcpu_promote_runnable(struct kvm_vcpu *vcpu)
+{
+	if (vcpu->arch.mp_state == KVM_MP_STATE_HALTED)
+		vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+}
+
 int kvm_emulate_halt(struct kvm_vcpu *vcpu)
 {
 	++vcpu->stat.halt_exits;
 	KVMTRACE_0D(HLT, vcpu, handler);
 	if (irqchip_in_kernel(vcpu->kvm)) {
+		int ret;
 		vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
 		up_read(&vcpu->kvm->slots_lock);
-		kvm_vcpu_block(vcpu);
+		ret = kvm_vcpu_block(vcpu);
 		down_read(&vcpu->kvm->slots_lock);
-		if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
+		if (ret)
 			return -EINTR;
+		kvm_vcpu_promote_runnable(vcpu);
 		return 1;
 	} else {
 		vcpu->run->exit_reason = KVM_EXIT_HLT;
@@ -2978,10 +2986,12 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v
 	if (vcpu->sigset_active)
 		sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
 
-	if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
-		kvm_vcpu_block(vcpu);
-		r = -EAGAIN;
-		goto out;
+	if (unlikely(!kvm_arch_vcpu_runnable(vcpu))) {
+		if (kvm_vcpu_block(vcpu)) {
+			r = -EAGAIN;
+			goto out;
+		}
+		kvm_vcpu_promote_runnable(vcpu);
 	}
 
 	/* re-sync apic's tpr */
Index: kvm/include/linux/kvm_host.h
===================================================================
--- kvm.orig/include/linux/kvm_host.h
+++ kvm/include/linux/kvm_host.h
@@ -199,7 +199,7 @@ struct kvm_memory_slot *gfn_to_memslot(s
 int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
-void kvm_vcpu_block(struct kvm_vcpu *vcpu);
+int kvm_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_resched(struct kvm_vcpu *vcpu);
 void kvm_load_guest_fpu(struct kvm_vcpu *vcpu);
 void kvm_put_guest_fpu(struct kvm_vcpu *vcpu);
Index: kvm/virt/kvm/kvm_main.c
===================================================================
--- kvm.orig/virt/kvm/kvm_main.c
+++ kvm/virt/kvm/kvm_main.c
@@ -818,9 +818,10 @@ void mark_page_dirty(struct kvm *kvm, gf
 /*
  * The vCPU has executed a HLT instruction with in-kernel mode enabled.
  */
-void kvm_vcpu_block(struct kvm_vcpu *vcpu)
+int kvm_vcpu_block(struct kvm_vcpu *vcpu)
 {
 	DEFINE_WAIT(wait);
+	int ret = 0;
 
 	for (;;) {
 		prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
@@ -831,8 +832,10 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp
 			break;
 		if (kvm_arch_vcpu_runnable(vcpu))
 			break;
-		if (signal_pending(current))
+		if (signal_pending(current)) {
+			ret = 1;
 			break;
+		}
 
 		vcpu_put(vcpu);
 		schedule();
@@ -840,6 +843,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcp
 	}
 
 	finish_wait(&vcpu->wq, &wait);
+	return ret;
 }
 
 void kvm_resched(struct kvm_vcpu *vcpu)

--