[PATCH v5 8/9] s390/vfio-ap: Fix NULL deref in status_show() during queue probe

[Anthony Krowiak]

When vfio_ap_mdev_probe_queue() creates the sysfs attribute group,
the queue's driver data has not yet been set. A concurrent read of
the 'status' attribute can therefore call dev_get_drvdata() and
get NULL, which is then passed directly to
vfio_ap_mdev_for_queue() where q->apqn is unconditionally
dereferenced, causing a NULL pointer dereference.

Fix this by acquiring the update locks before calling
sysfs_create_group(). The status_show() function acquires
guests_lock before reading the driver data, so any concurrent
read will block until after dev_set_drvdata() has been called
and the update locks are released.

As a bonus, the APQN no longer needs to be read from the queue
struct after allocation — it can be read directly from apdev
before allocation and stored in a local variable, which is then
assigned to q->apqn once the allocation succeeds.

Fixes: 260f3ea141382 ("s390/vfio-ap: move probe and remove callbacks to vfio_ap_ops.c")
Cc: stable@xxxxxxxxxxxxxxx
Signed-off-by: Anthony Krowiak <akrowiak@xxxxxxxxxxxxx>
---
 drivers/s390/crypto/vfio_ap_ops.c | 33 +++++++++++++++++++++++++++----
 1 file changed, 29 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index 16779cfc64e8..1edd0b7a3cce 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -2326,6 +2326,23 @@ static ssize_t status_show(struct device *dev,
 	mutex_lock(&matrix_dev->guests_lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
 	q = dev_get_drvdata(&apdev->device);
+
+	/*
+	 * Make sure the drvdata has been set before proceeding. There is a
+	 * possibility that the drvdata was not set if the vfio_ap_queue object
+	 * could not be allocated when the queue device was probed. In that case,
+	 * the locks used in vfio_ap_mdev_probe_queue() are released prior to
+	 * removing the sysfs status attribute to avoid a lockdep
+	 * splat. That opens a very small window where the status attribute is
+	 * still available without the vfio_ap_queue object having been
+	 * stored in the device drvdata. In that case, indicate the queue is not
+	 * assigned.
+	 */
+	if (!q) {
+		nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_UNASSIGNED);
+		goto done;
+	}
+
 	matrix_mdev = vfio_ap_mdev_for_queue(q);
 
 	/* If the queue is assigned to the matrix mediated device, then
@@ -2350,6 +2367,7 @@ static ssize_t status_show(struct device *dev,
 		nchars = sysfs_emit(buf, "%s\n", AP_QUEUE_UNASSIGNED);
 	}
 
+done:
 	mutex_unlock(&matrix_dev->mdevs_lock);
 	mutex_unlock(&matrix_dev->guests_lock);
 
@@ -2424,14 +2442,17 @@ void vfio_ap_mdev_unregister(void)
 
 int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 {
-	int ret;
+	int ret, apqn;
 	struct vfio_ap_queue *q;
 	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev;
 
+	apqn = to_ap_queue(&apdev->device)->qid;
+	matrix_mdev = get_update_locks_by_apqn(apqn);
+
 	ret = sysfs_create_group(&apdev->device.kobj, &vfio_queue_attr_group);
 	if (ret)
-		return ret;
+		goto err_release_locks;
 
 	q = kzalloc_obj(*q);
 	if (!q) {
@@ -2439,11 +2460,10 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 		goto err_remove_group;
 	}
 
-	q->apqn = to_ap_queue(&apdev->device)->qid;
+	q->apqn = apqn;
 	q->saved_isc = VFIO_AP_ISC_INVALID;
 	memset(&q->reset_status, 0, sizeof(q->reset_status));
 	INIT_WORK(&q->reset_work, apq_reset_check);
-	matrix_mdev = get_update_locks_by_apqn(q->apqn);
 
 	if (matrix_mdev) {
 		vfio_ap_mdev_link_queue(matrix_mdev, q);
@@ -2472,8 +2492,13 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 	return ret;
 
 err_remove_group:
+	release_update_locks_for_mdev(matrix_mdev);
 	sysfs_remove_group(&apdev->device.kobj, &vfio_queue_attr_group);
 	return ret;
+
+err_release_locks:
+	release_update_locks_for_mdev(matrix_mdev);
+	return ret;
 }
 
 void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
-- 
2.53.0