KVM: Protect device ops->create and list_add with kvm->lock

KVM devices were manipulating list data structures without any form of
synchronization, and some implementations of the create operations also
suffered from a lack of synchronization.

Now when we've split the xics create operation into create and init, we
can hold the kvm->lock mutex while calling the create operation and when
manipulating the devices list.

The error path in the generic code gets slightly ugly because we have to
take the mutex again and delete the device from the list, but holding
the mutex during anon_inode_getfd or releasing/locking the mutex in the
common non-error path seemed wrong.

Signed-off-by: Christoffer Dall <[e-mail]>
Reviewed-by: Paolo Bonzini <[e-mail]>
Acked-by: Christian Borntraeger <[e-mail]>
Signed-off-by: Radim Krčmář <[e-mail]>

arch/arm/kvm/arm.c

···
 
 	switch (ioctl) {
 	case KVM_CREATE_IRQCHIP: {
+		int ret;
 		if (!vgic_present)
 			return -ENXIO;
-		return kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+		mutex_lock(&kvm->lock);
+		ret = kvm_vgic_create(kvm, KVM_DEV_TYPE_ARM_VGIC_V2);
+		mutex_unlock(&kvm->lock);
+		return ret;
 	}
 	case KVM_ARM_SET_DEVICE_ADDR: {
 		struct kvm_arm_device_addr dev_addr;

arch/powerpc/kvm/book3s_xics.c

···
 	xics->kvm = kvm;
 
 	/* Already there ? */
-	mutex_lock(&kvm->lock);
 	if (kvm->arch.xics)
 		ret = -EEXIST;
 	else
 		kvm->arch.xics = xics;
-	mutex_unlock(&kvm->lock);
 
 	if (ret) {
 		kfree(xics);

include/linux/kvm_host.h

···
 /* create, destroy, and name are mandatory */
 struct kvm_device_ops {
 	const char *name;
+
+	/*
+	 * create is called holding kvm->lock and any operations not suitable
+	 * to do while holding the lock should be deferred to init (see
+	 * below).
+	 */
 	int (*create)(struct kvm_device *dev, u32 type);
 
 	/*

virt/kvm/arm/vgic/vgic-init.c

···
 	int i, vcpu_lock_idx = -1, ret;
 	struct kvm_vcpu *vcpu;
 
-	mutex_lock(&kvm->lock);
-
-	if (irqchip_in_kernel(kvm)) {
-		ret = -EEXIST;
-		goto out;
-	}
+	if (irqchip_in_kernel(kvm))
+		return -EEXIST;
 
 	/*
 	 * This function is also called by the KVM_CREATE_IRQCHIP handler,
···
 	 * the proper checks already.
 	 */
 	if (type == KVM_DEV_TYPE_ARM_VGIC_V2 &&
-		!kvm_vgic_global_state.can_emulate_gicv2) {
-		ret = -ENODEV;
-		goto out;
-	}
+		!kvm_vgic_global_state.can_emulate_gicv2)
+		return -ENODEV;
 
 	/*
 	 * Any time a vcpu is run, vcpu_load is called which tries to grab the
···
 		vcpu = kvm_get_vcpu(kvm, vcpu_lock_idx);
 		mutex_unlock(&vcpu->mutex);
 	}
-
-out:
-	mutex_unlock(&kvm->lock);
 	return ret;
 }
 

virt/kvm/kvm_main.c

···
 {
 	struct kvm_device *dev, *tmp;
 
+	/*
+	 * We do not need to take the kvm->lock here, because nobody else
+	 * has a reference to the struct kvm at this point and therefore
+	 * cannot access the devices list anyhow.
+	 */
 	list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
 		list_del(&dev->vm_node);
 		dev->ops->destroy(dev);
···
 	dev->ops = ops;
 	dev->kvm = kvm;
 
+	mutex_lock(&kvm->lock);
 	ret = ops->create(dev, cd->type);
 	if (ret < 0) {
+		mutex_unlock(&kvm->lock);
 		kfree(dev);
 		return ret;
 	}
+	list_add(&dev->vm_node, &kvm->devices);
+	mutex_unlock(&kvm->lock);
 
 	if (ops->init)
 		ops->init(dev);
···
 	ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC);
 	if (ret < 0) {
 		ops->destroy(dev);
+		mutex_lock(&kvm->lock);
+		list_del(&dev->vm_node);
+		mutex_unlock(&kvm->lock);
 		return ret;
 	}
 
-	list_add(&dev->vm_node, &kvm->devices);
 	kvm_get_kvm(kvm);
 	cd->fd = ret;
 	return 0;