@@ -147,6 +147,7 @@ static int __init vfio_ap_init(void)
memset(&vfio_ap_drv, 0, sizeof(vfio_ap_drv));
vfio_ap_drv.probe = vfio_ap_mdev_probe_queue;
vfio_ap_drv.remove = vfio_ap_mdev_remove_queue;
+ vfio_ap_drv.in_use = vfio_ap_mdev_resource_in_use;
vfio_ap_drv.ids = ap_queue_ids;
ret = ap_driver_register(&vfio_ap_drv, THIS_MODULE, VFIO_AP_DRV_NAME);
@@ -650,10 +650,14 @@ static void vfio_ap_mdev_link_adapter(struct ap_matrix_mdev *matrix_mdev,
* driver; or, if no APQIs have yet been assigned, the APID is not
* contained in an APQN bound to the vfio_ap device driver.
*
- * 4. -EBUSY
+ * 4. -EADDRINUSE
* An APQN derived from the cross product of the APID being assigned
* and the APQIs previously assigned is being used by another mediated
- * matrix device or the mdev lock could not be acquired.
+ * matrix device.
+ *
+ * 5. -EAGAIN
+ * The mdev lock could not be acquired which is required in order to
+ * change the AP configuration for the mdev
*/
static ssize_t assign_adapter_store(struct device *dev,
struct device_attribute *attr,
@@ -664,7 +668,8 @@ 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);
- mutex_lock(&matrix_dev->lock);
+ if (!mutex_trylock(&matrix_dev->lock))
+ return -EAGAIN;
/*
* If the KVM pointer is in flux or the guest is running, disallow
@@ -803,10 +808,14 @@ static void vfio_ap_mdev_link_domain(struct ap_matrix_mdev *matrix_mdev,
* driver; or, if no APIDs have yet been assigned, the APQI is not
* contained in an APQN bound to the vfio_ap device driver.
*
- * 4. -BUSY
+ * 4. -EADDRINUSE
* An APQN derived from the cross product of the APQI being assigned
* and the APIDs previously assigned is being used by another mediated
- * matrix device or the mdev lock could not be acquired.
+ * matrix device.
+ *
+ * 5. -EAGAIN
+ * The mdev lock could not be acquired which is required in order to
+ * change the AP configuration for the mdev
*/
static ssize_t assign_domain_store(struct device *dev,
struct device_attribute *attr,
@@ -818,7 +827,8 @@ 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;
- mutex_lock(&matrix_dev->lock);
+ if (!mutex_trylock(&matrix_dev->lock))
+ return -EAGAIN;
/*
* If the KVM pointer is in flux or the guest is running, disallow
@@ -946,6 +956,7 @@ static void vfio_ap_mdev_hot_plug_cdom(struct ap_matrix_mdev *matrix_mdev,
* returns one of the following errors:
* -EINVAL if the ID is not a number
* -ENODEV if the ID exceeds the maximum value configured for the system
+ * -EAGAIN if the mdev lock could not be acquired
*/
static ssize_t assign_control_domain_store(struct device *dev,
struct device_attribute *attr,
@@ -956,7 +967,8 @@ 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);
- mutex_lock(&matrix_dev->lock);
+ if (!mutex_trylock(&matrix_dev->lock))
+ return -EAGAIN;
/*
* If the KVM pointer is in flux or the guest is running, disallow
@@ -1587,3 +1599,15 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
kfree(q);
mutex_unlock(&matrix_dev->lock);
}
+
+int vfio_ap_mdev_resource_in_use(unsigned long *apm, unsigned long *aqm)
+{
+ int ret;
+
+ if (!mutex_trylock(&matrix_dev->lock))
+ return -EBUSY;
+ ret = vfio_ap_mdev_verify_no_sharing(apm, aqm);
+ mutex_unlock(&matrix_dev->lock);
+
+ return ret;
+}
@@ -109,4 +109,6 @@ void vfio_ap_mdev_unregister(void);
int vfio_ap_mdev_probe_queue(struct ap_device *queue);
void vfio_ap_mdev_remove_queue(struct ap_device *queue);
+int vfio_ap_mdev_resource_in_use(unsigned long *apm, unsigned long *aqm);
+
#endif /* _VFIO_AP_PRIVATE_H_ */
Let's implement the callback to indicate when an APQN is in use by the vfio_ap device driver. The callback is invoked whenever a change to the apmask or aqmask would result in one or more queue devices being removed from the driver. The vfio_ap device driver will indicate a resource is in use if the APQN of any of the queue devices to be removed are assigned to any of the matrix mdevs under the driver's control. There is potential for a deadlock condition between the matrix_dev->lock used to lock the matrix device during assignment of adapters and domains and the ap_perms_mutex locked by the AP bus when changes are made to the sysfs apmask/aqmask attributes. Consider following scenario (courtesy of Halil Pasic): 1) apmask_store() takes ap_perms_mutex 2) assign_adapter_store() takes matrix_dev->lock 3) apmask_store() calls vfio_ap_mdev_resource_in_use() which tries to take matrix_dev->lock 4) assign_adapter_store() calls ap_apqn_in_matrix_owned_by_def_drv which tries to take ap_perms_mutex BANG! To resolve this issue, instead of using the mutex_lock(&matrix_dev->lock) function to lock the matrix device during assignment of an adapter or domain to a matrix_mdev as well as during the in_use callback, the mutex_trylock(&matrix_dev->lock) function will be used. If the lock is not obtained, then the assignment and in_use functions will terminate with -EAGAIN. Signed-off-by: Tony Krowiak <akrowiak@linux.ibm.com> --- drivers/s390/crypto/vfio_ap_drv.c | 1 + drivers/s390/crypto/vfio_ap_ops.c | 38 ++++++++++++++++++++++----- drivers/s390/crypto/vfio_ap_private.h | 2 ++ 3 files changed, 34 insertions(+), 7 deletions(-)