1 files changed, 177 insertions, 91 deletions

diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index acb710d3d7bc..983b3b16196c 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -32,7 +32,8 @@
 
 #define AP_RESET_INTERVAL		20	/* Reset sleep interval (20ms)		*/
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable);
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev);
+static int vfio_ap_mdev_reset_qlist(struct list_head *qlist);
 static struct vfio_ap_queue *vfio_ap_find_queue(int apqn);
 static const struct vfio_device_ops vfio_ap_matrix_dev_ops;
 static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q);
@@ -665,17 +666,23 @@ static bool vfio_ap_mdev_filter_cdoms(struct ap_matrix_mdev *matrix_mdev)
  *				device driver.
  *
  * @matrix_mdev: the matrix mdev whose matrix is to be filtered.
+ * @apm_filtered: a 256-bit bitmap for storing the APIDs filtered from the
+ *		  guest's AP configuration that are still in the host's AP
+ *		  configuration.
  *
  * Note: If an APQN referencing a queue device that is not bound to the vfio_ap
  *	 driver, its APID will be filtered from the guest's APCB. The matrix
  *	 structure precludes filtering an individual APQN, so its APID will be
- *	 filtered.
+ *	 filtered. Consequently, all queues associated with the adapter that
+ *	 are in the host's AP configuration must be reset. If queues are
+ *	 subsequently made available again to the guest, they should re-appear
+ *	 in a reset state
  *
  * Return: a boolean value indicating whether the KVM guest's APCB was changed
  *	   by the filtering or not.
  */
-static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
-				       struct ap_matrix_mdev *matrix_mdev)
+static bool vfio_ap_mdev_filter_matrix(struct ap_matrix_mdev *matrix_mdev,
+				       unsigned long *apm_filtered)
 {
 	unsigned long apid, apqi, apqn;
 	DECLARE_BITMAP(prev_shadow_apm, AP_DEVICES);
@@ -685,6 +692,7 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 	bitmap_copy(prev_shadow_apm, matrix_mdev->shadow_apcb.apm, AP_DEVICES);
 	bitmap_copy(prev_shadow_aqm, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS);
 	vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->shadow_apcb);
+	bitmap_clear(apm_filtered, 0, AP_DEVICES);
 
 	/*
 	 * Copy the adapters, domains and control domains to the shadow_apcb
@@ -696,8 +704,9 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 	bitmap_and(matrix_mdev->shadow_apcb.aqm, matrix_mdev->matrix.aqm,
 		   (unsigned long *)matrix_dev->info.aqm, AP_DOMAINS);
 
-	for_each_set_bit_inv(apid, apm, AP_DEVICES) {
-		for_each_set_bit_inv(apqi, aqm, AP_DOMAINS) {
+	for_each_set_bit_inv(apid, matrix_mdev->shadow_apcb.apm, AP_DEVICES) {
+		for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm,
+				     AP_DOMAINS) {
 			/*
 			 * If the APQN is not bound to the vfio_ap device
 			 * driver, then we can't assign it to the guest's
@@ -709,8 +718,16 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 			apqn = AP_MKQID(apid, apqi);
 			q = vfio_ap_mdev_get_queue(matrix_mdev, apqn);
 			if (!q || q->reset_status.response_code) {
-				clear_bit_inv(apid,
-					      matrix_mdev->shadow_apcb.apm);
+				clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
+
+				/*
+				 * If the adapter was previously plugged into
+				 * the guest, let's let the caller know that
+				 * the APID was filtered.
+				 */
+				if (test_bit_inv(apid, prev_shadow_apm))
+					set_bit_inv(apid, apm_filtered);
+
 				break;
 			}
 		}
@@ -812,7 +829,7 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev)
 
 	mutex_lock(&matrix_dev->guests_lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
-	vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+	vfio_ap_mdev_reset_queues(matrix_mdev);
 	vfio_ap_mdev_unlink_fr_queues(matrix_mdev);
 	list_del(&matrix_mdev->node);
 	mutex_unlock(&matrix_dev->mdevs_lock);
@@ -922,6 +939,47 @@ static void vfio_ap_mdev_link_adapter(struct ap_matrix_mdev *matrix_mdev,
 				       AP_MKQID(apid, apqi));
 }
 
+static void collect_queues_to_reset(struct ap_matrix_mdev *matrix_mdev,
+				    unsigned long apid,
+				    struct list_head *qlist)
+{
+	struct vfio_ap_queue *q;
+	unsigned long  apqi;
+
+	for_each_set_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm, AP_DOMAINS) {
+		q = vfio_ap_mdev_get_queue(matrix_mdev, AP_MKQID(apid, apqi));
+		if (q)
+			list_add_tail(&q->reset_qnode, qlist);
+	}
+}
+
+static void reset_queues_for_apid(struct ap_matrix_mdev *matrix_mdev,
+				  unsigned long apid)
+{
+	struct list_head qlist;
+
+	INIT_LIST_HEAD(&qlist);
+	collect_queues_to_reset(matrix_mdev, apid, &qlist);
+	vfio_ap_mdev_reset_qlist(&qlist);
+}
+
+static int reset_queues_for_apids(struct ap_matrix_mdev *matrix_mdev,
+				  unsigned long *apm_reset)
+{
+	struct list_head qlist;
+	unsigned long apid;
+
+	if (bitmap_empty(apm_reset, AP_DEVICES))
+		return 0;
+
+	INIT_LIST_HEAD(&qlist);
+
+	for_each_set_bit_inv(apid, apm_reset, AP_DEVICES)
+		collect_queues_to_reset(matrix_mdev, apid, &qlist);
+
+	return vfio_ap_mdev_reset_qlist(&qlist);
+}
+
 /**
  * assign_adapter_store - parses the APID from @buf and sets the
  * corresponding bit in the mediated matrix device's APM
@@ -962,7 +1020,7 @@ static ssize_t assign_adapter_store(struct device *dev,
 {
 	int ret;
 	unsigned long apid;
-	DECLARE_BITMAP(apm_delta, AP_DEVICES);
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -991,12 +1049,11 @@ static ssize_t assign_adapter_store(struct device *dev,
 	}
 
 	vfio_ap_mdev_link_adapter(matrix_mdev, apid);
-	memset(apm_delta, 0, sizeof(apm_delta));
-	set_bit_inv(apid, apm_delta);
 
-	if (vfio_ap_mdev_filter_matrix(apm_delta,
-				       matrix_mdev->matrix.aqm, matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+		reset_queues_for_apids(matrix_mdev, apm_filtered);
+	}
 
 	ret = count;
 done:
@@ -1027,11 +1084,12 @@ static struct vfio_ap_queue
  *				 adapter was assigned.
  * @matrix_mdev: the matrix mediated device to which the adapter was assigned.
  * @apid: the APID of the unassigned adapter.
- * @qtable: table for storing queues associated with unassigned adapter.
+ * @qlist: list for storing queues associated with unassigned adapter that
+ *	   need to be reset.
  */
 static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 					unsigned long apid,
-					struct ap_queue_table *qtable)
+					struct list_head *qlist)
 {
 	unsigned long apqi;
 	struct vfio_ap_queue *q;
@@ -1039,11 +1097,10 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 	for_each_set_bit_inv(apqi, matrix_mdev->matrix.aqm, AP_DOMAINS) {
 		q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi);
 
-		if (q && qtable) {
+		if (q && qlist) {
 			if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 			    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
-				hash_add(qtable->queues, &q->mdev_qnode,
-					 q->apqn);
+				list_add_tail(&q->reset_qnode, qlist);
 		}
 	}
 }
@@ -1051,26 +1108,23 @@ static void vfio_ap_mdev_unlink_adapter(struct ap_matrix_mdev *matrix_mdev,
 static void vfio_ap_mdev_hot_unplug_adapter(struct ap_matrix_mdev *matrix_mdev,
 					    unsigned long apid)
 {
-	int loop_cursor;
-	struct vfio_ap_queue *q;
-	struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL);
+	struct vfio_ap_queue *q, *tmpq;
+	struct list_head qlist;
 
-	hash_init(qtable->queues);
-	vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, qtable);
+	INIT_LIST_HEAD(&qlist);
+	vfio_ap_mdev_unlink_adapter(matrix_mdev, apid, &qlist);
 
 	if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm)) {
 		clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	vfio_ap_mdev_reset_qlist(&qlist);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
-		hash_del(&q->mdev_qnode);
+		list_del(&q->reset_qnode);
 	}
-
-	kfree(qtable);
 }
 
 /**
@@ -1171,7 +1225,7 @@ static ssize_t assign_domain_store(struct device *dev,
 {
 	int ret;
 	unsigned long apqi;
-	DECLARE_BITMAP(aqm_delta, AP_DOMAINS);
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(dev);
 
 	mutex_lock(&ap_perms_mutex);
@@ -1200,12 +1254,11 @@ static ssize_t assign_domain_store(struct device *dev,
 	}
 
 	vfio_ap_mdev_link_domain(matrix_mdev, apqi);
-	memset(aqm_delta, 0, sizeof(aqm_delta));
-	set_bit_inv(apqi, aqm_delta);
 
-	if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm, aqm_delta,
-				       matrix_mdev))
+	if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+		reset_queues_for_apids(matrix_mdev, apm_filtered);
+	}
 
 	ret = count;
 done:
@@ -1218,7 +1271,7 @@ static DEVICE_ATTR_WO(assign_domain);
 
 static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 				       unsigned long apqi,
-				       struct ap_queue_table *qtable)
+				       struct list_head *qlist)
 {
 	unsigned long apid;
 	struct vfio_ap_queue *q;
@@ -1226,11 +1279,10 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 	for_each_set_bit_inv(apid, matrix_mdev->matrix.apm, AP_DEVICES) {
 		q = vfio_ap_unlink_apqn_fr_mdev(matrix_mdev, apid, apqi);
 
-		if (q && qtable) {
+		if (q && qlist) {
 			if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 			    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm))
-				hash_add(qtable->queues, &q->mdev_qnode,
-					 q->apqn);
+				list_add_tail(&q->reset_qnode, qlist);
 		}
 	}
 }
@@ -1238,26 +1290,23 @@ static void vfio_ap_mdev_unlink_domain(struct ap_matrix_mdev *matrix_mdev,
 static void vfio_ap_mdev_hot_unplug_domain(struct ap_matrix_mdev *matrix_mdev,
 					   unsigned long apqi)
 {
-	int loop_cursor;
-	struct vfio_ap_queue *q;
-	struct ap_queue_table *qtable = kzalloc(sizeof(*qtable), GFP_KERNEL);
+	struct vfio_ap_queue *q, *tmpq;
+	struct list_head qlist;
 
-	hash_init(qtable->queues);
-	vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, qtable);
+	INIT_LIST_HEAD(&qlist);
+	vfio_ap_mdev_unlink_domain(matrix_mdev, apqi, &qlist);
 
 	if (test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
 		clear_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm);
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 	}
 
-	vfio_ap_mdev_reset_queues(qtable);
+	vfio_ap_mdev_reset_qlist(&qlist);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	list_for_each_entry_safe(q, tmpq, &qlist, reset_qnode) {
 		vfio_ap_unlink_mdev_fr_queue(q);
-		hash_del(&q->mdev_qnode);
+		list_del(&q->reset_qnode);
 	}
-
-	kfree(qtable);
 }
 
 /**
@@ -1612,7 +1661,7 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev)
 		get_update_locks_for_kvm(kvm);
 
 		kvm_arch_crypto_clear_masks(kvm);
-		vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		vfio_ap_mdev_reset_queues(matrix_mdev);
 		kvm_put_kvm(kvm);
 		matrix_mdev->kvm = NULL;
 
@@ -1748,15 +1797,33 @@ static void vfio_ap_mdev_reset_queue(struct vfio_ap_queue *q)
 	}
 }
 
-static int vfio_ap_mdev_reset_queues(struct ap_queue_table *qtable)
+static int vfio_ap_mdev_reset_queues(struct ap_matrix_mdev *matrix_mdev)
 {
 	int ret = 0, loop_cursor;
 	struct vfio_ap_queue *q;
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode)
+	hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode)
 		vfio_ap_mdev_reset_queue(q);
 
-	hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+	hash_for_each(matrix_mdev->qtable.queues, loop_cursor, q, mdev_qnode) {
+		flush_work(&q->reset_work);
+
+		if (q->reset_status.response_code)
+			ret = -EIO;
+	}
+
+	return ret;
+}
+
+static int vfio_ap_mdev_reset_qlist(struct list_head *qlist)
+{
+	int ret = 0;
+	struct vfio_ap_queue *q;
+
+	list_for_each_entry(q, qlist, reset_qnode)
+		vfio_ap_mdev_reset_queue(q);
+
+	list_for_each_entry(q, qlist, reset_qnode) {
 		flush_work(&q->reset_work);
 
 		if (q->reset_status.response_code)
@@ -1942,7 +2009,7 @@ static ssize_t vfio_ap_mdev_ioctl(struct vfio_device *vdev,
 		ret = vfio_ap_mdev_get_device_info(arg);
 		break;
 	case VFIO_DEVICE_RESET:
-		ret = vfio_ap_mdev_reset_queues(&matrix_mdev->qtable);
+		ret = vfio_ap_mdev_reset_queues(matrix_mdev);
 		break;
 	case VFIO_DEVICE_GET_IRQ_INFO:
 			ret = vfio_ap_get_irq_info(arg);
@@ -2088,6 +2155,7 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 {
 	int ret;
 	struct vfio_ap_queue *q;
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
 	struct ap_matrix_mdev *matrix_mdev;
 
 	ret = sysfs_create_group(&apdev->device.kobj, &vfio_queue_attr_group);
@@ -2109,15 +2177,28 @@ int vfio_ap_mdev_probe_queue(struct ap_device *apdev)
 	if (matrix_mdev) {
 		vfio_ap_mdev_link_queue(matrix_mdev, q);
 
-		if (vfio_ap_mdev_filter_matrix(matrix_mdev->matrix.apm,
-					       matrix_mdev->matrix.aqm,
-					       matrix_mdev))
+		/*
+		 * If we're in the process of handling the adding of adapters or
+		 * domains to the host's AP configuration, then let the
+		 * vfio_ap device driver's on_scan_complete callback filter the
+		 * matrix and update the guest's AP configuration after all of
+		 * the new queue devices are probed.
+		 */
+		if (!bitmap_empty(matrix_mdev->apm_add, AP_DEVICES) ||
+		    !bitmap_empty(matrix_mdev->aqm_add, AP_DOMAINS))
+			goto done;
+
+		if (vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered)) {
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+			reset_queues_for_apids(matrix_mdev, apm_filtered);
+		}
 	}
+
+done:
 	dev_set_drvdata(&apdev->device, q);
 	release_update_locks_for_mdev(matrix_mdev);
 
-	return 0;
+	return ret;
 
 err_remove_group:
 	sysfs_remove_group(&apdev->device.kobj, &vfio_queue_attr_group);
@@ -2134,26 +2215,40 @@ void vfio_ap_mdev_remove_queue(struct ap_device *apdev)
 	q = dev_get_drvdata(&apdev->device);
 	get_update_locks_for_queue(q);
 	matrix_mdev = q->matrix_mdev;
+	apid = AP_QID_CARD(q->apqn);
+	apqi = AP_QID_QUEUE(q->apqn);
 
 	if (matrix_mdev) {
-		vfio_ap_unlink_queue_fr_mdev(q);
-
-		apid = AP_QID_CARD(q->apqn);
-		apqi = AP_QID_QUEUE(q->apqn);
-
-		/*
-		 * If the queue is assigned to the guest's APCB, then remove
-		 * the adapter's APID from the APCB and hot it into the guest.
-		 */
+		/* If the queue is assigned to the guest's AP configuration */
 		if (test_bit_inv(apid, matrix_mdev->shadow_apcb.apm) &&
 		    test_bit_inv(apqi, matrix_mdev->shadow_apcb.aqm)) {
+			/*
+			 * Since the queues are defined via a matrix of adapters
+			 * and domains, it is not possible to hot unplug a
+			 * single queue; so, let's unplug the adapter.
+			 */
 			clear_bit_inv(apid, matrix_mdev->shadow_apcb.apm);
 			vfio_ap_mdev_update_guest_apcb(matrix_mdev);
+			reset_queues_for_apid(matrix_mdev, apid);
+			goto done;
 		}
 	}
 
-	vfio_ap_mdev_reset_queue(q);
-	flush_work(&q->reset_work);
+	/*
+	 * If the queue is not in the host's AP configuration, then resetting
+	 * it will fail with response code 01, (APQN not valid); so, let's make
+	 * sure it is in the host's config.
+	 */
+	if (test_bit_inv(apid, (unsigned long *)matrix_dev->info.apm) &&
+	    test_bit_inv(apqi, (unsigned long *)matrix_dev->info.aqm)) {
+		vfio_ap_mdev_reset_queue(q);
+		flush_work(&q->reset_work);
+	}
+
+done:
+	if (matrix_mdev)
+		vfio_ap_unlink_queue_fr_mdev(q);
+
 	dev_set_drvdata(&apdev->device, NULL);
 	kfree(q);
 	release_update_locks_for_mdev(matrix_mdev);
@@ -2461,39 +2556,30 @@ void vfio_ap_on_cfg_changed(struct ap_config_info *cur_cfg_info,
 
 static void vfio_ap_mdev_hot_plug_cfg(struct ap_matrix_mdev *matrix_mdev)
 {
-	bool do_hotplug = false;
-	int filter_domains = 0;
-	int filter_adapters = 0;
-	DECLARE_BITMAP(apm, AP_DEVICES);
-	DECLARE_BITMAP(aqm, AP_DOMAINS);
+	DECLARE_BITMAP(apm_filtered, AP_DEVICES);
+	bool filter_domains, filter_adapters, filter_cdoms, do_hotplug = false;
 
 	mutex_lock(&matrix_mdev->kvm->lock);
 	mutex_lock(&matrix_dev->mdevs_lock);
 
-	filter_adapters = bitmap_and(apm, matrix_mdev->matrix.apm,
-				     matrix_mdev->apm_add, AP_DEVICES);
-	filter_domains = bitmap_and(aqm, matrix_mdev->matrix.aqm,
-				    matrix_mdev->aqm_add, AP_DOMAINS);
-
-	if (filter_adapters && filter_domains)
-		do_hotplug |= vfio_ap_mdev_filter_matrix(apm, aqm, matrix_mdev);
-	else if (filter_adapters)
-		do_hotplug |=
-			vfio_ap_mdev_filter_matrix(apm,
-						   matrix_mdev->shadow_apcb.aqm,
-						   matrix_mdev);
-	else
-		do_hotplug |=
-			vfio_ap_mdev_filter_matrix(matrix_mdev->shadow_apcb.apm,
-						   aqm, matrix_mdev);
+	filter_adapters = bitmap_intersects(matrix_mdev->matrix.apm,
+					    matrix_mdev->apm_add, AP_DEVICES);
+	filter_domains = bitmap_intersects(matrix_mdev->matrix.aqm,
+					   matrix_mdev->aqm_add, AP_DOMAINS);
+	filter_cdoms = bitmap_intersects(matrix_mdev->matrix.adm,
+					 matrix_mdev->adm_add, AP_DOMAINS);
 
-	if (bitmap_intersects(matrix_mdev->matrix.adm, matrix_mdev->adm_add,
-			      AP_DOMAINS))
+	if (filter_adapters || filter_domains)
+		do_hotplug = vfio_ap_mdev_filter_matrix(matrix_mdev, apm_filtered);
+
+	if (filter_cdoms)
 		do_hotplug |= vfio_ap_mdev_filter_cdoms(matrix_mdev);
 
 	if (do_hotplug)
 		vfio_ap_mdev_update_guest_apcb(matrix_mdev);
 
+	reset_queues_for_apids(matrix_mdev, apm_filtered);
+
 	mutex_unlock(&matrix_dev->mdevs_lock);
 	mutex_unlock(&matrix_mdev->kvm->lock);
 }