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
-EBUSY.
Signed-off-by: Tony Krowiak <akrowiak@xxxxxxxxxxxxx>
---
drivers/s390/crypto/vfio_ap_drv.c | 1 +
drivers/s390/crypto/vfio_ap_ops.c | 96 +++++++++++++++++++--------
drivers/s390/crypto/vfio_ap_private.h | 2 +
3 files changed, 71 insertions(+), 28 deletions(-)
diff --git a/drivers/s390/crypto/vfio_ap_drv.c b/drivers/s390/crypto/vfio_ap_drv.c
index 73bd073fd5d3..8934471b7944 100644
--- a/drivers/s390/crypto/vfio_ap_drv.c
+++ b/drivers/s390/crypto/vfio_ap_drv.c
@@ -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);
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 07caf871943c..3c2479d7e674 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -520,18 +520,40 @@ vfio_ap_mdev_verify_queues_reserved_for_apid(struct ap_matrix_mdev *matrix_mdev,
return 0;
}
+#define MDEV_SHARING_ERR "Userspace may not re-assign queue %02lx.%04lx " \
+ "already assigned to %s"
+
+static void vfio_ap_mdev_log_sharing_err(const char *mdev_name,
+ unsigned long *apm,
+ unsigned long *aqm)
+{
+ unsigned long apid, apqi;
+
+ for_each_set_bit_inv(apid, apm, AP_DEVICES)
+ for_each_set_bit_inv(apqi, aqm, AP_DOMAINS)
+ pr_warn(MDEV_SHARING_ERR, apid, apqi, mdev_name);
+}
+
/**
* vfio_ap_mdev_verify_no_sharing
*
- * Verifies that the APQNs derived from the cross product of the AP adapter IDs
- * and AP queue indexes comprising the AP matrix are not configured for another
+ * Verifies that each APQN derived from the cross product of the AP adapter IDs
+ * and AP queue indexes comprising an AP matrix is not assigned to a
* mediated device. AP queue sharing is not allowed.
*
- * @matrix_mdev: the mediated matrix device
+ * @matrix_mdev: the mediated matrix device to which the APQNs being verified
+ * are assigned. If the value is not NULL, then verification will
+ * proceed for all other matrix mediated devices; otherwise, all
+ * matrix mediated devices will be verified.
+ * @mdev_apm: mask indicating the APIDs of the APQNs to be verified
+ * @mdev_aqm: mask indicating the APQIs of the APQNs to be verified
*
- * Returns 0 if the APQNs are not shared, otherwise; returns -EADDRINUSE.
+ * Returns 0 if no APQNs are not shared, otherwise; returns -EBUSY if one
+ * or more APQNs are shared.
*/
-static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *matrix_mdev)
+static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *matrix_mdev,
+ unsigned long *mdev_apm,
+ unsigned long *mdev_aqm)
{
struct ap_matrix_mdev *lstdev;
DECLARE_BITMAP(apm, AP_DEVICES);
@@ -548,15 +570,16 @@ static int vfio_ap_mdev_verify_no_sharing(struct ap_matrix_mdev *matrix_mdev)
* We work on full longs, as we can only exclude the leftover
* bits in non-inverse order. The leftover is all zeros.
*/
- if (!bitmap_and(apm, matrix_mdev->matrix.apm,
- lstdev->matrix.apm, AP_DEVICES))
+ if (!bitmap_and(apm, mdev_apm, lstdev->matrix.apm, AP_DEVICES))
continue;
- if (!bitmap_and(aqm, matrix_mdev->matrix.aqm,
- lstdev->matrix.aqm, AP_DOMAINS))
+ if (!bitmap_and(aqm, mdev_aqm, lstdev->matrix.aqm, AP_DOMAINS))
continue;
- return -EADDRINUSE;
+ vfio_ap_mdev_log_sharing_err(dev_name(mdev_dev(lstdev->mdev)),
+ apm, aqm);
+
+ return -EBUSY;
}
return 0;
@@ -670,10 +693,10 @@ static void vfio_ap_mdev_manage_qlinks(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. -EADDRINUSE
+ * 4. -EBUSY
* 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
+ * matrix device, or the matrix_dev-> lock could not be acquired.
*/
static ssize_t assign_adapter_store(struct device *dev,
struct device_attribute *attr,
@@ -681,6 +704,7 @@ static ssize_t assign_adapter_store(struct device *dev,
{
int ret;
unsigned long apid;
+ DECLARE_BITMAP(apm, AP_DEVICES);
struct mdev_device *mdev = mdev_from_dev(dev);
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
@@ -700,24 +724,25 @@ static ssize_t assign_adapter_store(struct device *dev,
* number (APID). The bits in the mask, from most significant to least
* significant bit, correspond to APIDs 0-255.
*/
- mutex_lock(&matrix_dev->lock);
+ if (!mutex_trylock(&matrix_dev->lock))
+ return -EBUSY;
ret = vfio_ap_mdev_verify_queues_reserved_for_apid(matrix_mdev, apid);
if (ret)
goto done;
- set_bit_inv(apid, matrix_mdev->matrix.apm);
+ memset(apm, 0, sizeof(apm));
+ set_bit_inv(apid, apm);
- ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev);
+ ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev, apm,
+ matrix_mdev->matrix.aqm);
if (ret)
- goto share_err;
+ goto done;
+ set_bit_inv(apid, matrix_mdev->matrix.apm);
vfio_ap_mdev_manage_qlinks(matrix_mdev, LINK_APID, apid);
ret = count;
- goto done;
-share_err:
- clear_bit_inv(apid, matrix_mdev->matrix.apm);
done:
mutex_unlock(&matrix_dev->lock);
@@ -821,7 +846,7 @@ vfio_ap_mdev_verify_queues_reserved_for_apqi(struct ap_matrix_mdev *matrix_mdev,
* 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
+ * matrix device, or the matrix_dev-> lock could not be acquired.
*/
static ssize_t assign_domain_store(struct device *dev,
struct device_attribute *attr,
@@ -829,6 +854,7 @@ static ssize_t assign_domain_store(struct device *dev,
{
int ret;
unsigned long apqi;
+ DECLARE_BITMAP(aqm, AP_DOMAINS);
struct mdev_device *mdev = mdev_from_dev(dev);
struct ap_matrix_mdev *matrix_mdev = mdev_get_drvdata(mdev);
unsigned long max_apqi = matrix_mdev->matrix.aqm_max;
@@ -843,24 +869,25 @@ static ssize_t assign_domain_store(struct device *dev,
if (apqi > max_apqi)
return -ENODEV;
- mutex_lock(&matrix_dev->lock);
+ if (!mutex_trylock(&matrix_dev->lock))
+ return -EBUSY;
ret = vfio_ap_mdev_verify_queues_reserved_for_apqi(matrix_mdev, apqi);
if (ret)
goto done;
- set_bit_inv(apqi, matrix_mdev->matrix.aqm);
+ memset(aqm, 0, sizeof(aqm));
+ set_bit_inv(apqi, aqm);
- ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev);
+ ret = vfio_ap_mdev_verify_no_sharing(matrix_mdev,
+ matrix_mdev->matrix.apm, aqm);
if (ret)
- goto share_err;
+ goto done;
+ set_bit_inv(apqi, matrix_mdev->matrix.aqm);
vfio_ap_mdev_manage_qlinks(matrix_mdev, LINK_APQI, apqi);
ret = count;
- goto done;
-share_err:
- clear_bit_inv(apqi, matrix_mdev->matrix.aqm);
done:
mutex_unlock(&matrix_dev->lock);
@@ -956,7 +983,8 @@ static ssize_t assign_control_domain_store(struct device *dev,
* 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);
+ if (!mutex_trylock(&matrix_dev->lock))
+ return -EBUSY;
set_bit_inv(id, matrix_mdev->matrix.adm);
mutex_unlock(&matrix_dev->lock);
@@ -1457,3 +1485,15 @@ 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(NULL, apm, aqm);
+ mutex_unlock(&matrix_dev->lock);
+
+ return ret;
+}
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index 4e5cc72fc0db..8b9b5255abfe 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -105,4 +105,6 @@ struct vfio_ap_queue {
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_ */
--
2.21.1
