@@ -294,6 +294,21 @@ 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. Unlock the matrix_dev->lock while waiting to
+ * allow the value of the KVM pointer to be set.
+ */
+ while (matrix_mdev->kvm_busy) {
+ mutex_unlock(&matrix_dev->lock);
+ msleep(100);
+ 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;
@@ -350,8 +365,11 @@ static int vfio_ap_mdev_create(struct kobject *kobj, struct mdev_device *mdev)
static int vfio_ap_mdev_remove(struct mdev_device *mdev)
{
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
-
- if (matrix_mdev->kvm)
+ /*
+ * If the KVM pointer is in flux or the guest is running, disallow
+ * removal of the mdev
+ */
+ if (matrix_mdev->kvm_busy || matrix_mdev->kvm)
return -EBUSY;
mutex_lock(&matrix_dev->lock);
@@ -606,8 +624,11 @@ 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)
+ /*
+ * 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)
return -EBUSY;
ret = kstrtoul(buf, 0, &apid);
@@ -672,8 +693,11 @@ 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)
+ /*
+ * 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)
return -EBUSY;
ret = kstrtoul(buf, 0, &apid);
@@ -753,8 +777,11 @@ 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)
+ /*
+ * 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)
return -EBUSY;
ret = kstrtoul(buf, 0, &apqi);
@@ -814,8 +841,11 @@ 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)
+ /*
+ * 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)
return -EBUSY;
ret = kstrtoul(buf, 0, &apqi);
@@ -858,8 +888,11 @@ 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)
+ /*
+ * 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)
return -EBUSY;
ret = kstrtoul(buf, 0, &id);
@@ -908,8 +941,11 @@ 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)
+ /*
+ * 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)
return -EBUSY;
ret = kstrtoul(buf, 0, &domid);
@@ -1027,8 +1063,15 @@ 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.
@@ -1043,9 +1086,18 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev,
return -EPERM;
}
- matrix_mdev->kvm = kvm;
- kvm_get_kvm(kvm);
- kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook;
+ if (kvm->arch.crypto.crycbd) {
+ matrix_mdev->kvm_busy = true;
+ kvm_get_kvm(kvm);
+ 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);
+ matrix_mdev->kvm = kvm;
+ matrix_mdev->kvm_busy = false;
+ }
return 0;
}
@@ -1079,51 +1131,54 @@ 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 (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);
+ kvm_put_kvm(matrix_mdev->kvm);
+ matrix_mdev->kvm = NULL;
+ matrix_mdev->kvm_busy = false;
+ }
}
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 +1313,20 @@ 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 the KVM pointer is in the process of being set, wait until the
+ * process has completed. Unlock the matrix_dev->lock while waiting to
+ * allow the value of the KVM pointer to be set.
+ */
+ while (matrix_mdev->kvm_busy) {
+ mutex_unlock(&matrix_dev->lock);
+ msleep(100);
+ mutex_lock(&matrix_dev->lock);
+ }
+
if (matrix_mdev->kvm)
vfio_ap_mdev_unset_kvm(matrix_mdev);
+
mutex_unlock(&matrix_dev->lock);
vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
@@ -1293,6 +1360,7 @@ 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) {
@@ -1300,7 +1368,12 @@ static ssize_t vfio_ap_mdev_ioctl(struct mdev_device *mdev,
ret = vfio_ap_mdev_get_device_info(arg);
break;
case VFIO_DEVICE_RESET:
- ret = vfio_ap_mdev_reset_queues(mdev);
+ matrix_mdev = mdev_get_drvdata(mdev);
+
+ if (matrix_mdev->kvm_busy)
+ ret = -EBUSY;
+ else
+ ret = vfio_ap_mdev_reset_queues(mdev);
break;
default:
ret = -EOPNOTSUPP;
@@ -83,6 +83,7 @@ struct ap_matrix_mdev {
struct ap_matrix matrix;
struct notifier_block group_notifier;
struct notifier_block iommu_notifier;
+ bool kvm_busy;
struct kvm *kvm;
struct kvm_s390_module_hook pqap_hook;
struct mdev_device *mdev;
This patch fixes a circular locking dependency in the CI introduced by commit f21916ec4826 ("s390/vfio-ap: clean up vfio_ap resources when KVM pointer invalidated"). The lockdep only occurs when starting a Secure Execution guest. Crypto virtualization (vfio_ap) is not yet supported for SE guests; however, in order to avoid CI errors, this fix is being provided. The circular lockdep was introduced when the masks in the guest's APCB were taken under the matrix_dev->lock. While the lock is definitely needed to protect the setting/unsetting of the KVM pointer, it is not necessarily critical for setting the masks, so this will not be done under protection of the matrix_dev->lock. Fixes: f21916ec4826 ("s390/vfio-ap: clean up vfio_ap resources when KVM pointer invalidated") Cc: stable@vger.kernel.org Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com> Acked-by: Cornelia Huck <cohuck@redhat.com> --- drivers/s390/crypto/vfio_ap_ops.c | 169 ++++++++++++++++++-------- drivers/s390/crypto/vfio_ap_private.h | 1 + 2 files changed, 122 insertions(+), 48 deletions(-)