Merge tag 'vfio-v6.1-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Prune private items from vfio_pci_core.h to a new internal header,
   fix missed function rename, and refactor vfio-pci interrupt defines
   (Jason Gunthorpe)

 - Create consistent naming and handling of ioctls with a function per
   ioctl for vfio-pci and vfio group handling, use proper type args
   where available (Jason Gunthorpe)

 - Implement a set of low power device feature ioctls allowing userspace
   to make use of power states such as D3cold where supported (Abhishek
   Sahu)

 - Remove device counter on vfio groups, which had restricted the page
   pinning interface to singleton groups to account for limitations in
   the type1 IOMMU backend. Document usage as limited to emulated IOMMU
   devices, ie. traditional mdev devices where this restriction is
   consistent (Jason Gunthorpe)

 - Correct function prefix in hisi_acc driver incurred during previous
   refactoring (Shameer Kolothum)

 - Correct typo and remove redundant warning triggers in vfio-fsl driver
   (Christophe JAILLET)

 - Introduce device level DMA dirty tracking uAPI and implementation in
   the mlx5 variant driver (Yishai Hadas & Joao Martins)

 - Move much of the vfio_device life cycle management into vfio core,
   simplifying and avoiding duplication across drivers. This also
   facilitates adding a struct device to vfio_device which begins the
   introduction of device rather than group level user support and fills
   a gap allowing userspace identify devices as vfio capable without
   implicit knowledge of the driver (Kevin Tian & Yi Liu)

 - Split vfio container handling to a separate file, creating a more
   well defined API between the core and container code, masking IOMMU
   backend implementation from the core, allowing for an easier future
   transition to an iommufd based implementation of the same (Jason
   Gunthorpe)

 - Attempt to resolve race accessing the iommu_group for a device
   between vfio releasing DMA ownership and removal of the device from
   the IOMMU driver. Follow-up with support to allow vfio_group to exist
   with NULL iommu_group pointer to support existing userspace use cases
   of holding the group file open (Jason Gunthorpe)

 - Fix error code and hi/lo register manipulation issues in the hisi_acc
   variant driver, along with various code cleanups (Longfang Liu)

 - Fix a prior regression in GVT-g group teardown, resulting in
   unreleased resources (Jason Gunthorpe)

 - A significant cleanup and simplification of the mdev interface,
   consolidating much of the open coded per driver sysfs interface
   support into the mdev core (Christoph Hellwig)

 - Simplification of tracking and locking around vfio_groups that fall
   out from previous refactoring (Jason Gunthorpe)

 - Replace trivial open coded f_ops tests with new helper (Alex
   Williamson)

* tag 'vfio-v6.1-rc1' of https://github.com/awilliam/linux-vfio: (77 commits)
  vfio: More vfio_file_is_group() use cases
  vfio: Make the group FD disassociate from the iommu_group
  vfio: Hold a reference to the iommu_group in kvm for SPAPR
  vfio: Add vfio_file_is_group()
  vfio: Change vfio_group->group_rwsem to a mutex
  vfio: Remove the vfio_group->users and users_comp
  vfio/mdev: add mdev available instance checking to the core
  vfio/mdev: consolidate all the description sysfs into the core code
  vfio/mdev: consolidate all the available_instance sysfs into the core code
  vfio/mdev: consolidate all the name sysfs into the core code
  vfio/mdev: consolidate all the device_api sysfs into the core code
  vfio/mdev: remove mtype_get_parent_dev
  vfio/mdev: remove mdev_parent_dev
  vfio/mdev: unexport mdev_bus_type
  vfio/mdev: remove mdev_from_dev
  vfio/mdev: simplify mdev_type handling
  vfio/mdev: embedd struct mdev_parent in the parent data structure
  vfio/mdev: make mdev.h standalone includable
  drm/i915/gvt: simplify vgpu configuration management
  drm/i915/gvt: fix a memory leak in intel_gvt_init_vgpu_types
  ...

5 files changed, 97 insertions, 133 deletions

diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 86d9e428357b..7f5402fe857a 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -12,7 +12,6 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/device.h>
 #include <linux/slab.h>
 #include <linux/mdev.h>
 
@@ -142,7 +141,6 @@ static struct vfio_ccw_private *vfio_ccw_alloc_private(struct subchannel *sch)
 	INIT_LIST_HEAD(&private->crw);
 	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
 	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
-	atomic_set(&private->avail, 1);
 
 	private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
 				       GFP_KERNEL);
@@ -203,7 +201,6 @@ static void vfio_ccw_free_private(struct vfio_ccw_private *private)
 	mutex_destroy(&private->io_mutex);
 	kfree(private);
 }
-
 static int vfio_ccw_sch_probe(struct subchannel *sch)
 {
 	struct pmcw *pmcw = &sch->schib.pmcw;
@@ -222,7 +219,12 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 
 	dev_set_drvdata(&sch->dev, private);
 
-	ret = mdev_register_device(&sch->dev, &vfio_ccw_mdev_driver);
+	private->mdev_type.sysfs_name = "io";
+	private->mdev_type.pretty_name = "I/O subchannel (Non-QDIO)";
+	private->mdev_types[0] = &private->mdev_type;
+	ret = mdev_register_parent(&private->parent, &sch->dev,
+				   &vfio_ccw_mdev_driver,
+				   private->mdev_types, 1);
 	if (ret)
 		goto out_free;
 
@@ -241,7 +243,7 @@ static void vfio_ccw_sch_remove(struct subchannel *sch)
 {
 	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
 
-	mdev_unregister_device(&sch->dev);
+	mdev_unregister_parent(&private->parent);
 
 	dev_set_drvdata(&sch->dev, NULL);
 
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 4a806a2273b5..6ae4d012d800 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -11,7 +11,6 @@
  */
 
 #include <linux/vfio.h>
-#include <linux/mdev.h>
 #include <linux/nospec.h>
 #include <linux/slab.h>
 
@@ -45,47 +44,14 @@ static void vfio_ccw_dma_unmap(struct vfio_device *vdev, u64 iova, u64 length)
 	vfio_ccw_mdev_reset(private);
 }
 
-static ssize_t name_show(struct mdev_type *mtype,
-			 struct mdev_type_attribute *attr, char *buf)
-{
-	return sprintf(buf, "I/O subchannel (Non-QDIO)\n");
-}
-static MDEV_TYPE_ATTR_RO(name);
-
-static ssize_t device_api_show(struct mdev_type *mtype,
-			       struct mdev_type_attribute *attr, char *buf)
-{
-	return sprintf(buf, "%s\n", VFIO_DEVICE_API_CCW_STRING);
-}
-static MDEV_TYPE_ATTR_RO(device_api);
-
-static ssize_t available_instances_show(struct mdev_type *mtype,
-					struct mdev_type_attribute *attr,
-					char *buf)
+static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 {
 	struct vfio_ccw_private *private =
-		dev_get_drvdata(mtype_get_parent_dev(mtype));
+		container_of(vdev, struct vfio_ccw_private, vdev);
 
-	return sprintf(buf, "%d\n", atomic_read(&private->avail));
+	init_completion(&private->release_comp);
+	return 0;
 }
-static MDEV_TYPE_ATTR_RO(available_instances);
-
-static struct attribute *mdev_types_attrs[] = {
-	&mdev_type_attr_name.attr,
-	&mdev_type_attr_device_api.attr,
-	&mdev_type_attr_available_instances.attr,
-	NULL,
-};
-
-static struct attribute_group mdev_type_group = {
-	.name  = "io",
-	.attrs = mdev_types_attrs,
-};
-
-static struct attribute_group *mdev_type_groups[] = {
-	&mdev_type_group,
-	NULL,
-};
 
 static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 {
@@ -95,12 +61,9 @@ static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 	if (private->state == VFIO_CCW_STATE_NOT_OPER)
 		return -ENODEV;
 
-	if (atomic_dec_if_positive(&private->avail) < 0)
-		return -EPERM;
-
-	memset(&private->vdev, 0, sizeof(private->vdev));
-	vfio_init_group_dev(&private->vdev, &mdev->dev,
-			    &vfio_ccw_dev_ops);
+	ret = vfio_init_device(&private->vdev, &mdev->dev, &vfio_ccw_dev_ops);
+	if (ret)
+		return ret;
 
 	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: create\n",
 			   private->sch->schid.cssid,
@@ -109,16 +72,32 @@ static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 
 	ret = vfio_register_emulated_iommu_dev(&private->vdev);
 	if (ret)
-		goto err_atomic;
+		goto err_put_vdev;
 	dev_set_drvdata(&mdev->dev, private);
 	return 0;
 
-err_atomic:
-	vfio_uninit_group_dev(&private->vdev);
-	atomic_inc(&private->avail);
+err_put_vdev:
+	vfio_put_device(&private->vdev);
 	return ret;
 }
 
+static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
+{
+	struct vfio_ccw_private *private =
+		container_of(vdev, struct vfio_ccw_private, vdev);
+
+	/*
+	 * We cannot free vfio_ccw_private here because it includes
+	 * parent info which must be free'ed by css driver.
+	 *
+	 * Use a workaround by memset'ing the core device part and
+	 * then notifying the remove path that all active references
+	 * to this device have been released.
+	 */
+	memset(vdev, 0, sizeof(*vdev));
+	complete(&private->release_comp);
+}
+
 static void vfio_ccw_mdev_remove(struct mdev_device *mdev)
 {
 	struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
@@ -130,8 +109,16 @@ static void vfio_ccw_mdev_remove(struct mdev_device *mdev)
 
 	vfio_unregister_group_dev(&private->vdev);
 
-	vfio_uninit_group_dev(&private->vdev);
-	atomic_inc(&private->avail);
+	vfio_put_device(&private->vdev);
+	/*
+	 * Wait for all active references on mdev are released so it
+	 * is safe to defer kfree() to a later point.
+	 *
+	 * TODO: the clean fix is to split parent/mdev info from ccw
+	 * private structure so each can be managed in its own life
+	 * cycle.
+	 */
+	wait_for_completion(&private->release_comp);
 }
 
 static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
@@ -592,6 +579,8 @@ static void vfio_ccw_mdev_request(struct vfio_device *vdev, unsigned int count)
 }
 
 static const struct vfio_device_ops vfio_ccw_dev_ops = {
+	.init = vfio_ccw_mdev_init_dev,
+	.release = vfio_ccw_mdev_release_dev,
 	.open_device = vfio_ccw_mdev_open_device,
 	.close_device = vfio_ccw_mdev_close_device,
 	.read = vfio_ccw_mdev_read,
@@ -602,6 +591,8 @@ static const struct vfio_device_ops vfio_ccw_dev_ops = {
 };
 
 struct mdev_driver vfio_ccw_mdev_driver = {
+	.device_api = VFIO_DEVICE_API_CCW_STRING,
+	.max_instances = 1,
 	.driver = {
 		.name = "vfio_ccw_mdev",
 		.owner = THIS_MODULE,
@@ -609,5 +600,4 @@ struct mdev_driver vfio_ccw_mdev_driver = {
 	},
 	.probe = vfio_ccw_mdev_probe,
 	.remove = vfio_ccw_mdev_remove,
-	.supported_type_groups  = mdev_type_groups,
 };
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index cd24b7fada91..bd5fb81456af 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -18,6 +18,7 @@
 #include <linux/workqueue.h>
 #include <linux/vfio_ccw.h>
 #include <linux/vfio.h>
+#include <linux/mdev.h>
 #include <asm/crw.h>
 #include <asm/debug.h>
 
@@ -72,7 +73,6 @@ struct vfio_ccw_crw {
  * @sch: pointer to the subchannel
  * @state: internal state of the device
  * @completion: synchronization helper of the I/O completion
- * @avail: available for creating a mediated device
  * @io_region: MMIO region to input/output I/O arguments/results
  * @io_mutex: protect against concurrent update of I/O regions
  * @region: additional regions for other subchannel operations
@@ -88,13 +88,14 @@ struct vfio_ccw_crw {
  * @req_trigger: eventfd ctx for signaling userspace to return device
  * @io_work: work for deferral process of I/O handling
  * @crw_work: work for deferral process of CRW handling
+ * @release_comp: synchronization helper for vfio device release
+ * @parent: parent data structures for mdevs created
  */
 struct vfio_ccw_private {
 	struct vfio_device vdev;
 	struct subchannel	*sch;
 	int			state;
 	struct completion	*completion;
-	atomic_t		avail;
 	struct ccw_io_region	*io_region;
 	struct mutex		io_mutex;
 	struct vfio_ccw_region *region;
@@ -113,6 +114,12 @@ struct vfio_ccw_private {
 	struct eventfd_ctx	*req_trigger;
 	struct work_struct	io_work;
 	struct work_struct	crw_work;
+
+	struct completion	release_comp;
+
+	struct mdev_parent	parent;
+	struct mdev_type	mdev_type;
+	struct mdev_type	*mdev_types[1];
 } __aligned(8);
 
 int vfio_ccw_sch_quiesce(struct subchannel *sch);
diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c
index ee82207b4e60..0b4cc8c597ae 100644
--- a/drivers/s390/crypto/vfio_ap_ops.c
+++ b/drivers/s390/crypto/vfio_ap_ops.c
@@ -684,42 +684,41 @@ static bool vfio_ap_mdev_filter_matrix(unsigned long *apm, unsigned long *aqm,
 			     AP_DOMAINS);
 }
 
-static int vfio_ap_mdev_probe(struct mdev_device *mdev)
+static int vfio_ap_mdev_init_dev(struct vfio_device *vdev)
 {
-	struct ap_matrix_mdev *matrix_mdev;
-	int ret;
-
-	if ((atomic_dec_if_positive(&matrix_dev->available_instances) < 0))
-		return -EPERM;
-
-	matrix_mdev = kzalloc(sizeof(*matrix_mdev), GFP_KERNEL);
-	if (!matrix_mdev) {
-		ret = -ENOMEM;
-		goto err_dec_available;
-	}
-	vfio_init_group_dev(&matrix_mdev->vdev, &mdev->dev,
-			    &vfio_ap_matrix_dev_ops);
+	struct ap_matrix_mdev *matrix_mdev =
+		container_of(vdev, struct ap_matrix_mdev, vdev);
 
-	matrix_mdev->mdev = mdev;
+	matrix_mdev->mdev = to_mdev_device(vdev->dev);
 	vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->matrix);
 	matrix_mdev->pqap_hook = handle_pqap;
 	vfio_ap_matrix_init(&matrix_dev->info, &matrix_mdev->shadow_apcb);
 	hash_init(matrix_mdev->qtable.queues);
 
+	return 0;
+}
+
+static int vfio_ap_mdev_probe(struct mdev_device *mdev)
+{
+	struct ap_matrix_mdev *matrix_mdev;
+	int ret;
+
+	matrix_mdev = vfio_alloc_device(ap_matrix_mdev, vdev, &mdev->dev,
+					&vfio_ap_matrix_dev_ops);
+	if (IS_ERR(matrix_mdev))
+		return PTR_ERR(matrix_mdev);
+
 	ret = vfio_register_emulated_iommu_dev(&matrix_mdev->vdev);
 	if (ret)
-		goto err_list;
+		goto err_put_vdev;
 	dev_set_drvdata(&mdev->dev, matrix_mdev);
 	mutex_lock(&matrix_dev->mdevs_lock);
 	list_add(&matrix_mdev->node, &matrix_dev->mdev_list);
 	mutex_unlock(&matrix_dev->mdevs_lock);
 	return 0;
 
-err_list:
-	vfio_uninit_group_dev(&matrix_mdev->vdev);
-	kfree(matrix_mdev);
-err_dec_available:
-	atomic_inc(&matrix_dev->available_instances);
+err_put_vdev:
+	vfio_put_device(&matrix_mdev->vdev);
 	return ret;
 }
 
@@ -766,6 +765,11 @@ static void vfio_ap_mdev_unlink_fr_queues(struct ap_matrix_mdev *matrix_mdev)
 	}
 }
 
+static void vfio_ap_mdev_release_dev(struct vfio_device *vdev)
+{
+	vfio_free_device(vdev);
+}
+
 static void vfio_ap_mdev_remove(struct mdev_device *mdev)
 {
 	struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(&mdev->dev);
@@ -779,54 +783,9 @@ static void vfio_ap_mdev_remove(struct mdev_device *mdev)
 	list_del(&matrix_mdev->node);
 	mutex_unlock(&matrix_dev->mdevs_lock);
 	mutex_unlock(&matrix_dev->guests_lock);
-	vfio_uninit_group_dev(&matrix_mdev->vdev);
-	kfree(matrix_mdev);
-	atomic_inc(&matrix_dev->available_instances);
+	vfio_put_device(&matrix_mdev->vdev);
 }
 
-static ssize_t name_show(struct mdev_type *mtype,
-			 struct mdev_type_attribute *attr, char *buf)
-{
-	return sprintf(buf, "%s\n", VFIO_AP_MDEV_NAME_HWVIRT);
-}
-
-static MDEV_TYPE_ATTR_RO(name);
-
-static ssize_t available_instances_show(struct mdev_type *mtype,
-					struct mdev_type_attribute *attr,
-					char *buf)
-{
-	return sprintf(buf, "%d\n",
-		       atomic_read(&matrix_dev->available_instances));
-}
-
-static MDEV_TYPE_ATTR_RO(available_instances);
-
-static ssize_t device_api_show(struct mdev_type *mtype,
-			       struct mdev_type_attribute *attr, char *buf)
-{
-	return sprintf(buf, "%s\n", VFIO_DEVICE_API_AP_STRING);
-}
-
-static MDEV_TYPE_ATTR_RO(device_api);
-
-static struct attribute *vfio_ap_mdev_type_attrs[] = {
-	&mdev_type_attr_name.attr,
-	&mdev_type_attr_device_api.attr,
-	&mdev_type_attr_available_instances.attr,
-	NULL,
-};
-
-static struct attribute_group vfio_ap_mdev_hwvirt_type_group = {
-	.name = VFIO_AP_MDEV_TYPE_HWVIRT,
-	.attrs = vfio_ap_mdev_type_attrs,
-};
-
-static struct attribute_group *vfio_ap_mdev_type_groups[] = {
-	&vfio_ap_mdev_hwvirt_type_group,
-	NULL,
-};
-
 #define MDEV_SHARING_ERR "Userspace may not re-assign queue %02lx.%04lx " \
 			 "already assigned to %s"
 
@@ -1824,6 +1783,8 @@ static const struct attribute_group vfio_queue_attr_group = {
 };
 
 static const struct vfio_device_ops vfio_ap_matrix_dev_ops = {
+	.init = vfio_ap_mdev_init_dev,
+	.release = vfio_ap_mdev_release_dev,
 	.open_device = vfio_ap_mdev_open_device,
 	.close_device = vfio_ap_mdev_close_device,
 	.ioctl = vfio_ap_mdev_ioctl,
@@ -1831,6 +1792,8 @@ static const struct vfio_device_ops vfio_ap_matrix_dev_ops = {
 };
 
 static struct mdev_driver vfio_ap_matrix_driver = {
+	.device_api = VFIO_DEVICE_API_AP_STRING,
+	.max_instances = MAX_ZDEV_ENTRIES_EXT,
 	.driver = {
 		.name = "vfio_ap_mdev",
 		.owner = THIS_MODULE,
@@ -1839,20 +1802,22 @@ static struct mdev_driver vfio_ap_matrix_driver = {
 	},
 	.probe = vfio_ap_mdev_probe,
 	.remove = vfio_ap_mdev_remove,
-	.supported_type_groups = vfio_ap_mdev_type_groups,
 };
 
 int vfio_ap_mdev_register(void)
 {
 	int ret;
 
-	atomic_set(&matrix_dev->available_instances, MAX_ZDEV_ENTRIES_EXT);
-
 	ret = mdev_register_driver(&vfio_ap_matrix_driver);
 	if (ret)
 		return ret;
 
-	ret = mdev_register_device(&matrix_dev->device, &vfio_ap_matrix_driver);
+	matrix_dev->mdev_type.sysfs_name = VFIO_AP_MDEV_TYPE_HWVIRT;
+	matrix_dev->mdev_type.pretty_name = VFIO_AP_MDEV_NAME_HWVIRT;
+	matrix_dev->mdev_types[0] = &matrix_dev->mdev_type;
+	ret = mdev_register_parent(&matrix_dev->parent, &matrix_dev->device,
+				   &vfio_ap_matrix_driver,
+				   matrix_dev->mdev_types, 1);
 	if (ret)
 		goto err_driver;
 	return 0;
@@ -1864,7 +1829,7 @@ err_driver:
 
 void vfio_ap_mdev_unregister(void)
 {
-	mdev_unregister_device(&matrix_dev->device);
+	mdev_unregister_parent(&matrix_dev->parent);
 	mdev_unregister_driver(&vfio_ap_matrix_driver);
 }
 
diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h
index d782cf463eab..2eddd5f34ed3 100644
--- a/drivers/s390/crypto/vfio_ap_private.h
+++ b/drivers/s390/crypto/vfio_ap_private.h
@@ -13,7 +13,6 @@
 #define _VFIO_AP_PRIVATE_H_
 
 #include <linux/types.h>
-#include <linux/device.h>
 #include <linux/mdev.h>
 #include <linux/delay.h>
 #include <linux/mutex.h>
@@ -30,7 +29,6 @@
  * struct ap_matrix_dev - Contains the data for the matrix device.
  *
  * @device:	generic device structure associated with the AP matrix device
- * @available_instances: number of mediated matrix devices that can be created
  * @info:	the struct containing the output from the PQAP(QCI) instruction
  * @mdev_list:	the list of mediated matrix devices created
  * @mdevs_lock: mutex for locking the AP matrix device. This lock will be
@@ -47,12 +45,14 @@
  */
 struct ap_matrix_dev {
 	struct device device;
-	atomic_t available_instances;
 	struct ap_config_info info;
 	struct list_head mdev_list;
 	struct mutex mdevs_lock; /* serializes access to each ap_matrix_mdev */
 	struct ap_driver  *vfio_ap_drv;
 	struct mutex guests_lock; /* serializes access to each KVM guest */
+	struct mdev_parent parent;
+	struct mdev_type mdev_type;
+	struct mdev_type *mdev_types[];
 };
 
 extern struct ap_matrix_dev *matrix_dev;