1 files changed, 212 insertions, 102 deletions

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 1ffdd411201c..122c85c22469 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -294,6 +294,19 @@ static int handle_pqap(struct kvm_vcpu *vcpu)
 	matrix_mdev = container_of(vcpu->kvm->arch.crypto.pqap_hook,
 				   struct ap_matrix_mdev, pqap_hook);
 
+	/*
+	 * If the KVM pointer is in the process of being set, wait until the
+	 * process has completed.
+	 */
+	wait_event_cmd(matrix_mdev->wait_for_kvm,
+		       !matrix_mdev->kvm_busy,
+		       mutex_unlock(&matrix_dev->lock),
+		       mutex_lock(&matrix_dev->lock));
+
+	/* If the there is no guest using the mdev, there is nothing to do */
+	if (!matrix_mdev->kvm)
+		goto out_unlock;
+
 	q = vfio_ap_get_queue(matrix_mdev, apqn);
 	if (!q)
 		goto out_unlock;
@@ -322,7 +335,7 @@ static void vfio_ap_matrix_init(struct ap_config_info *info,
 	matrix->adm_max = info->apxa ? info->Nd : 15;
 }
 
-static int vfio_ap_mdev_create(struct kobject *kobj, struct mdev_device *mdev)
+static int vfio_ap_mdev_create(struct mdev_device *mdev)
 {
 	struct ap_matrix_mdev *matrix_mdev;
 
@@ -337,6 +350,7 @@ static int vfio_ap_mdev_create(struct kobject *kobj, struct mdev_device *mdev)
 
 	matrix_mdev->mdev = mdev;
 	vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->matrix);
+	init_waitqueue_head(&matrix_mdev->wait_for_kvm);
 	mdev_set_drvdata(mdev, matrix_mdev);
 	matrix_mdev->pqap_hook.hook = handle_pqap;
 	matrix_mdev->pqap_hook.owner = THIS_MODULE;
@@ -351,30 +365,28 @@ static int vfio_ap_mdev_remove(struct mdev_device *mdev)
 {
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 
-	if (matrix_mdev->kvm)
-		return -EBUSY;
-
 	mutex_lock(&matrix_dev->lock);
 	vfio_ap_mdev_reset_queues(mdev);
 	list_del(&matrix_mdev->node);
-	mutex_unlock(&matrix_dev->lock);
-
 	kfree(matrix_mdev);
 	mdev_set_drvdata(mdev, NULL);
 	atomic_inc(&matrix_dev->available_instances);
+	mutex_unlock(&matrix_dev->lock);
 
 	return 0;
 }
 
-static ssize_t name_show(struct kobject *kobj, struct device *dev, char *buf)
+static ssize_t name_show(struct mdev_type *mtype,
+			 struct mdev_type_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", VFIO_AP_MDEV_NAME_HWVIRT);
 }
 
 static MDEV_TYPE_ATTR_RO(name);
 
-static ssize_t available_instances_show(struct kobject *kobj,
-					struct device *dev, char *buf)
+static ssize_t available_instances_show(struct mdev_type *mtype,
+					struct mdev_type_attribute *attr,
+					char *buf)
 {
 	return sprintf(buf, "%d\n",
 		       atomic_read(&matrix_dev->available_instances));
@@ -382,8 +394,8 @@ static ssize_t available_instances_show(struct kobject *kobj,
 
 static MDEV_TYPE_ATTR_RO(available_instances);
 
-static ssize_t device_api_show(struct kobject *kobj, struct device *dev,
-			       char *buf)
+static ssize_t device_api_show(struct mdev_type *mtype,
+			       struct mdev_type_attribute *attr, char *buf)
 {
 	return sprintf(buf, "%s\n", VFIO_DEVICE_API_AP_STRING);
 }
@@ -606,24 +618,31 @@ static ssize_t assign_adapter_store(struct device *dev,
 	struct mdev_device *mdev = mdev_from_dev(dev);
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 
-	/* If the guest is running, disallow assignment of adapter */
-	if (matrix_mdev->kvm)
-		return -EBUSY;
+	mutex_lock(&matrix_dev->lock);
+
+	/*
+	 * If the KVM pointer is in flux or the guest is running, disallow
+	 * un-assignment of adapter
+	 */
+	if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+		ret = -EBUSY;
+		goto done;
+	}
 
 	ret = kstrtoul(buf, 0, &apid);
 	if (ret)
-		return ret;
+		goto done;
 
-	if (apid > matrix_mdev->matrix.apm_max)
-		return -ENODEV;
+	if (apid > matrix_mdev->matrix.apm_max) {
+		ret = -ENODEV;
+		goto done;
+	}
 
 	/*
 	 * Set the bit in the AP mask (APM) corresponding to the AP adapter
 	 * number (APID). The bits in the mask, from most significant to least
 	 * significant bit, correspond to APIDs 0-255.
 	 */
-	mutex_lock(&matrix_dev->lock);
-
 	ret = vfio_ap_mdev_verify_queues_reserved_for_apid(matrix_mdev, apid);
 	if (ret)
 		goto done;
@@ -672,22 +691,31 @@ static ssize_t unassign_adapter_store(struct device *dev,
 	struct mdev_device *mdev = mdev_from_dev(dev);
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 
-	/* If the guest is running, disallow un-assignment of adapter */
-	if (matrix_mdev->kvm)
-		return -EBUSY;
+	mutex_lock(&matrix_dev->lock);
+
+	/*
+	 * If the KVM pointer is in flux or the guest is running, disallow
+	 * un-assignment of adapter
+	 */
+	if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+		ret = -EBUSY;
+		goto done;
+	}
 
 	ret = kstrtoul(buf, 0, &apid);
 	if (ret)
-		return ret;
+		goto done;
 
-	if (apid > matrix_mdev->matrix.apm_max)
-		return -ENODEV;
+	if (apid > matrix_mdev->matrix.apm_max) {
+		ret = -ENODEV;
+		goto done;
+	}
 
-	mutex_lock(&matrix_dev->lock);
 	clear_bit_inv((unsigned long)apid, matrix_mdev->matrix.apm);
+	ret = count;
+done:
 	mutex_unlock(&matrix_dev->lock);
-
-	return count;
+	return ret;
 }
 static DEVICE_ATTR_WO(unassign_adapter);
 
@@ -753,17 +781,24 @@ static ssize_t assign_domain_store(struct device *dev,
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 	unsigned long max_apqi = matrix_mdev->matrix.aqm_max;
 
-	/* If the guest is running, disallow assignment of domain */
-	if (matrix_mdev->kvm)
-		return -EBUSY;
+	mutex_lock(&matrix_dev->lock);
+
+	/*
+	 * If the KVM pointer is in flux or the guest is running, disallow
+	 * assignment of domain
+	 */
+	if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+		ret = -EBUSY;
+		goto done;
+	}
 
 	ret = kstrtoul(buf, 0, &apqi);
 	if (ret)
-		return ret;
-	if (apqi > max_apqi)
-		return -ENODEV;
-
-	mutex_lock(&matrix_dev->lock);
+		goto done;
+	if (apqi > max_apqi) {
+		ret = -ENODEV;
+		goto done;
+	}
 
 	ret = vfio_ap_mdev_verify_queues_reserved_for_apqi(matrix_mdev, apqi);
 	if (ret)
@@ -814,22 +849,32 @@ static ssize_t unassign_domain_store(struct device *dev,
 	struct mdev_device *mdev = mdev_from_dev(dev);
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 
-	/* If the guest is running, disallow un-assignment of domain */
-	if (matrix_mdev->kvm)
-		return -EBUSY;
+	mutex_lock(&matrix_dev->lock);
+
+	/*
+	 * If the KVM pointer is in flux or the guest is running, disallow
+	 * un-assignment of domain
+	 */
+	if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+		ret = -EBUSY;
+		goto done;
+	}
 
 	ret = kstrtoul(buf, 0, &apqi);
 	if (ret)
-		return ret;
+		goto done;
 
-	if (apqi > matrix_mdev->matrix.aqm_max)
-		return -ENODEV;
+	if (apqi > matrix_mdev->matrix.aqm_max) {
+		ret = -ENODEV;
+		goto done;
+	}
 
-	mutex_lock(&matrix_dev->lock);
 	clear_bit_inv((unsigned long)apqi, matrix_mdev->matrix.aqm);
-	mutex_unlock(&matrix_dev->lock);
+	ret = count;
 
-	return count;
+done:
+	mutex_unlock(&matrix_dev->lock);
+	return ret;
 }
 static DEVICE_ATTR_WO(unassign_domain);
 
@@ -858,27 +903,36 @@ static ssize_t assign_control_domain_store(struct device *dev,
 	struct mdev_device *mdev = mdev_from_dev(dev);
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 
-	/* If the guest is running, disallow assignment of control domain */
-	if (matrix_mdev->kvm)
-		return -EBUSY;
+	mutex_lock(&matrix_dev->lock);
+
+	/*
+	 * If the KVM pointer is in flux or the guest is running, disallow
+	 * assignment of control domain.
+	 */
+	if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+		ret = -EBUSY;
+		goto done;
+	}
 
 	ret = kstrtoul(buf, 0, &id);
 	if (ret)
-		return ret;
+		goto done;
 
-	if (id > matrix_mdev->matrix.adm_max)
-		return -ENODEV;
+	if (id > matrix_mdev->matrix.adm_max) {
+		ret = -ENODEV;
+		goto done;
+	}
 
 	/* Set the bit in the ADM (bitmask) corresponding to the AP control
 	 * domain number (id). The bits in the mask, from most significant to
 	 * least significant, correspond to IDs 0 up to the one less than the
 	 * number of control domains that can be assigned.
 	 */
-	mutex_lock(&matrix_dev->lock);
 	set_bit_inv(id, matrix_mdev->matrix.adm);
+	ret = count;
+done:
 	mutex_unlock(&matrix_dev->lock);
-
-	return count;
+	return ret;
 }
 static DEVICE_ATTR_WO(assign_control_domain);
 
@@ -908,21 +962,30 @@ static ssize_t unassign_control_domain_store(struct device *dev,
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 	unsigned long max_domid =  matrix_mdev->matrix.adm_max;
 
-	/* If the guest is running, disallow un-assignment of control domain */
-	if (matrix_mdev->kvm)
-		return -EBUSY;
+	mutex_lock(&matrix_dev->lock);
+
+	/*
+	 * If the KVM pointer is in flux or the guest is running, disallow
+	 * un-assignment of control domain.
+	 */
+	if (matrix_mdev->kvm_busy || matrix_mdev->kvm) {
+		ret = -EBUSY;
+		goto done;
+	}
 
 	ret = kstrtoul(buf, 0, &domid);
 	if (ret)
-		return ret;
-	if (domid > max_domid)
-		return -ENODEV;
+		goto done;
+	if (domid > max_domid) {
+		ret = -ENODEV;
+		goto done;
+	}
 
-	mutex_lock(&matrix_dev->lock);
 	clear_bit_inv(domid, matrix_mdev->matrix.adm);
+	ret = count;
+done:
 	mutex_unlock(&matrix_dev->lock);
-
-	return count;
+	return ret;
 }
 static DEVICE_ATTR_WO(unassign_control_domain);
 
@@ -1027,8 +1090,15 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = {
  * @matrix_mdev: a mediated matrix device
  * @kvm: reference to KVM instance
  *
- * Verifies no other mediated matrix device has @kvm and sets a reference to
- * it in @matrix_mdev->kvm.
+ * Sets all data for @matrix_mdev that are needed to manage AP resources
+ * for the guest whose state is represented by @kvm.
+ *
+ * Note: The matrix_dev->lock must be taken prior to calling
+ * this function; however, the lock will be temporarily released while the
+ * guest's AP configuration is set to avoid a potential lockdep splat.
+ * The kvm->lock is taken to set the guest's AP configuration which, under
+ * certain circumstances, will result in a circular lock dependency if this is
+ * done under the @matrix_mdev->lock.
  *
  * Return 0 if no other mediated matrix device has a reference to @kvm;
  * otherwise, returns an -EPERM.
@@ -1038,14 +1108,25 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
 {
 	struct ap_matrix_mdev *m;
 
-	list_for_each_entry(m, &matrix_dev->mdev_list, node) {
-		if ((m != matrix_mdev) && (m->kvm == kvm))
-			return -EPERM;
-	}
+	if (kvm->arch.crypto.crycbd) {
+		list_for_each_entry(m, &matrix_dev->mdev_list, node) {
+			if (m != matrix_mdev && m->kvm == kvm)
+				return -EPERM;
+		}
 
-	matrix_mdev->kvm = kvm;
-	kvm_get_kvm(kvm);
-	kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
+		kvm_get_kvm(kvm);
+		matrix_mdev->kvm_busy = true;
+		mutex_unlock(&matrix_dev->lock);
+		kvm_arch_crypto_set_masks(kvm,
+					  matrix_mdev->matrix.apm,
+					  matrix_mdev->matrix.aqm,
+					  matrix_mdev->matrix.adm);
+		mutex_lock(&matrix_dev->lock);
+		kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
+		matrix_mdev->kvm = kvm;
+		matrix_mdev->kvm_busy = false;
+		wake_up_all(&matrix_mdev->wait_for_kvm);
+	}
 
 	return 0;
 }
@@ -1079,51 +1160,65 @@ static int vfio_ap_mdev_iommu_notifier(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
+/**
+ * vfio_ap_mdev_unset_kvm
+ *
+ * @matrix_mdev: a matrix mediated device
+ *
+ * Performs clean-up of resources no longer needed by @matrix_mdev.
+ *
+ * Note: The matrix_dev->lock must be taken prior to calling
+ * this function; however, the lock will be temporarily released while the
+ * guest's AP configuration is cleared to avoid a potential lockdep splat.
+ * The kvm->lock is taken to clear the guest's AP configuration which, under
+ * certain circumstances, will result in a circular lock dependency if this is
+ * done under the @matrix_mdev->lock.
+ *
+ */
 static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 {
-	kvm_arch_crypto_clear_masks(matrix_mdev->kvm);
-	matrix_mdev->kvm->arch.crypto.pqap_hook = NULL;
-	vfio_ap_mdev_reset_queues(matrix_mdev->mdev);
-	kvm_put_kvm(matrix_mdev->kvm);
-	matrix_mdev->kvm = NULL;
+	/*
+	 * If the KVM pointer is in the process of being set, wait until the
+	 * process has completed.
+	 */
+	wait_event_cmd(matrix_mdev->wait_for_kvm,
+		       !matrix_mdev->kvm_busy,
+		       mutex_unlock(&matrix_dev->lock),
+		       mutex_lock(&matrix_dev->lock));
+
+	if (matrix_mdev->kvm) {
+		matrix_mdev->kvm_busy = true;
+		mutex_unlock(&matrix_dev->lock);
+		kvm_arch_crypto_clear_masks(matrix_mdev->kvm);
+		mutex_lock(&matrix_dev->lock);
+		vfio_ap_mdev_reset_queues(matrix_mdev->mdev);
+		matrix_mdev->kvm->arch.crypto.pqap_hook = NULL;
+		kvm_put_kvm(matrix_mdev->kvm);
+		matrix_mdev->kvm = NULL;
+		matrix_mdev->kvm_busy = false;
+		wake_up_all(&matrix_mdev->wait_for_kvm);
+	}
 }
 
 static int vfio_ap_mdev_group_notifier(struct notifier_block *nb,
 				       unsigned long action, void *data)
 {
-	int ret, notify_rc = NOTIFY_OK;
+	int notify_rc = NOTIFY_OK;
 	struct ap_matrix_mdev *matrix_mdev;
 
 	if (action != VFIO_GROUP_NOTIFY_SET_KVM)
 		return NOTIFY_OK;
 
-	matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);
 	mutex_lock(&matrix_dev->lock);
+	matrix_mdev = container_of(nb, struct ap_matrix_mdev, group_notifier);
 
-	if (!data) {
-		if (matrix_mdev->kvm)
-			vfio_ap_mdev_unset_kvm(matrix_mdev);
-		goto notify_done;
-	}
-
-	ret = vfio_ap_mdev_set_kvm(matrix_mdev, data);
-	if (ret) {
-		notify_rc = NOTIFY_DONE;
-		goto notify_done;
-	}
-
-	/* If there is no CRYCB pointer, then we can't copy the masks */
-	if (!matrix_mdev->kvm->arch.crypto.crycbd) {
+	if (!data)
+		vfio_ap_mdev_unset_kvm(matrix_mdev);
+	else if (vfio_ap_mdev_set_kvm(matrix_mdev, data))
 		notify_rc = NOTIFY_DONE;
-		goto notify_done;
-	}
 
-	kvm_arch_crypto_set_masks(matrix_mdev->kvm, matrix_mdev->matrix.apm,
-				  matrix_mdev->matrix.aqm,
-				  matrix_mdev->matrix.adm);
-
-notify_done:
 	mutex_unlock(&matrix_dev->lock);
+
 	return notify_rc;
 }
 
@@ -1258,8 +1353,7 @@ static void vfio_ap_mdev_release(struct mdev_device *mdev)
 	struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
 
 	mutex_lock(&matrix_dev->lock);
-	if (matrix_mdev->kvm)
-		vfio_ap_mdev_unset_kvm(matrix_mdev);
+	vfio_ap_mdev_unset_kvm(matrix_mdev);
 	mutex_unlock(&matrix_dev->lock);
 
 	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
@@ -1293,6 +1387,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev,
 				    unsigned int cmd, unsigned long arg)
 {
 	int ret;
+	struct ap_matrix_mdev *matrix_mdev;
 
 	mutex_lock(&matrix_dev->lock);
 	switch (cmd) {
@@ -1300,6 +1395,21 @@ static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev,
 		ret = vfio_ap_mdev_get_device_info(arg);
 		break;
 	case VFIO_DEVICE_RESET:
+		matrix_mdev = mdev_get_drvdata(mdev);
+		if (WARN(!matrix_mdev, "Driver data missing from mdev!!")) {
+			ret = -EINVAL;
+			break;
+		}
+
+		/*
+		 * If the KVM pointer is in the process of being set, wait until
+		 * the process has completed.
+		 */
+		wait_event_cmd(matrix_mdev->wait_for_kvm,
+			       !matrix_mdev->kvm_busy,
+			       mutex_unlock(&matrix_dev->lock),
+			       mutex_lock(&matrix_dev->lock));
+
 		ret = vfio_ap_mdev_reset_queues(mdev);
 		break;
 	default: