vfio/ccw: Convert to use vfio_register_emulated_iommu_dev()

This is a more complicated conversion because vfio_ccw is sharing the
vfio_device between both the mdev_device, its vfio_device and the
css_driver.

The mdev is a singleton, and the reason for this sharing is so the extra
css_driver function callbacks to be delivered to the vfio_device
implementation.

This keeps things as they are, with the css_driver allocating the
singleton, not the mdev_driver.

Embed the vfio_device in the vfio_ccw_private and instantiate it as a
vfio_device when the mdev probes. The drvdata of both the css_device and
the mdev_device point at the private, and container_of is used to get it
back from the vfio_device.

Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Link: https://lore.kernel.org/r/4-v4-cea4f5bd2c00+b52-ccw_mdev_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

3 files changed, 85 insertions, 48 deletions

diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index e32678a71644..040742777095 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -468,7 +468,7 @@ static int __init vfio_ccw_sch_init(void)
 	vfio_ccw_work_q = create_singlethread_workqueue("vfio-ccw");
 	if (!vfio_ccw_work_q) {
 		ret = -ENOMEM;
-		goto out_err;
+		goto out_regions;
 	}
 
 	vfio_ccw_io_region = kmem_cache_create_usercopy("vfio_ccw_io_region",
@@ -477,7 +477,7 @@ static int __init vfio_ccw_sch_init(void)
 					sizeof(struct ccw_io_region), NULL);
 	if (!vfio_ccw_io_region) {
 		ret = -ENOMEM;
-		goto out_err;
+		goto out_regions;
 	}
 
 	vfio_ccw_cmd_region = kmem_cache_create_usercopy("vfio_ccw_cmd_region",
@@ -486,7 +486,7 @@ static int __init vfio_ccw_sch_init(void)
 					sizeof(struct ccw_cmd_region), NULL);
 	if (!vfio_ccw_cmd_region) {
 		ret = -ENOMEM;
-		goto out_err;
+		goto out_regions;
 	}
 
 	vfio_ccw_schib_region = kmem_cache_create_usercopy("vfio_ccw_schib_region",
@@ -496,7 +496,7 @@ static int __init vfio_ccw_sch_init(void)
 
 	if (!vfio_ccw_schib_region) {
 		ret = -ENOMEM;
-		goto out_err;
+		goto out_regions;
 	}
 
 	vfio_ccw_crw_region = kmem_cache_create_usercopy("vfio_ccw_crw_region",
@@ -506,19 +506,25 @@ static int __init vfio_ccw_sch_init(void)
 
 	if (!vfio_ccw_crw_region) {
 		ret = -ENOMEM;
-		goto out_err;
+		goto out_regions;
 	}
 
+	ret = mdev_register_driver(&vfio_ccw_mdev_driver);
+	if (ret)
+		goto out_regions;
+
 	isc_register(VFIO_CCW_ISC);
 	ret = css_driver_register(&vfio_ccw_sch_driver);
 	if (ret) {
 		isc_unregister(VFIO_CCW_ISC);
-		goto out_err;
+		goto out_driver;
 	}
 
 	return ret;
 
-out_err:
+out_driver:
+	mdev_unregister_driver(&vfio_ccw_mdev_driver);
+out_regions:
 	vfio_ccw_destroy_regions();
 	destroy_workqueue(vfio_ccw_work_q);
 	vfio_ccw_debug_exit();
@@ -528,6 +534,7 @@ out_err:
 static void __exit vfio_ccw_sch_exit(void)
 {
 	css_driver_unregister(&vfio_ccw_sch_driver);
+	mdev_unregister_driver(&vfio_ccw_mdev_driver);
 	isc_unregister(VFIO_CCW_ISC);
 	vfio_ccw_destroy_regions();
 	destroy_workqueue(vfio_ccw_work_q);
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 1edbea9de0ec..d8589afac272 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -17,6 +17,8 @@
 
 #include "vfio_ccw_private.h"
 
+static const struct vfio_device_ops vfio_ccw_dev_ops;
+
 static int vfio_ccw_mdev_reset(struct vfio_ccw_private *private)
 {
 	struct subchannel *sch;
@@ -111,10 +113,10 @@ static struct attribute_group *mdev_type_groups[] = {
 	NULL,
 };
 
-static int vfio_ccw_mdev_create(struct mdev_device *mdev)
+static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 {
-	struct vfio_ccw_private *private =
-		dev_get_drvdata(mdev_parent_dev(mdev));
+	struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
+	int ret;
 
 	if (private->state == VFIO_CCW_STATE_NOT_OPER)
 		return -ENODEV;
@@ -122,6 +124,10 @@ static int vfio_ccw_mdev_create(struct mdev_device *mdev)
 	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);
+
 	private->mdev = mdev;
 	private->state = VFIO_CCW_STATE_IDLE;
 
@@ -130,19 +136,31 @@ static int vfio_ccw_mdev_create(struct mdev_device *mdev)
 			   private->sch->schid.ssid,
 			   private->sch->schid.sch_no);
 
+	ret = vfio_register_emulated_iommu_dev(&private->vdev);
+	if (ret)
+		goto err_atomic;
+	dev_set_drvdata(&mdev->dev, private);
 	return 0;
+
+err_atomic:
+	vfio_uninit_group_dev(&private->vdev);
+	atomic_inc(&private->avail);
+	private->mdev = NULL;
+	private->state = VFIO_CCW_STATE_IDLE;
+	return ret;
 }
 
-static int vfio_ccw_mdev_remove(struct mdev_device *mdev)
+static void vfio_ccw_mdev_remove(struct mdev_device *mdev)
 {
-	struct vfio_ccw_private *private =
-		dev_get_drvdata(mdev_parent_dev(mdev));
+	struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
 
 	VFIO_CCW_MSG_EVENT(2, "mdev %pUl, sch %x.%x.%04x: remove\n",
 			   mdev_uuid(mdev), private->sch->schid.cssid,
 			   private->sch->schid.ssid,
 			   private->sch->schid.sch_no);
 
+	vfio_unregister_group_dev(&private->vdev);
+
 	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
 	    (private->state != VFIO_CCW_STATE_STANDBY)) {
 		if (!vfio_ccw_sch_quiesce(private->sch))
@@ -150,23 +168,22 @@ static int vfio_ccw_mdev_remove(struct mdev_device *mdev)
 		/* The state will be NOT_OPER on error. */
 	}
 
+	vfio_uninit_group_dev(&private->vdev);
 	cp_free(&private->cp);
 	private->mdev = NULL;
 	atomic_inc(&private->avail);
-
-	return 0;
 }
 
-static int vfio_ccw_mdev_open_device(struct mdev_device *mdev)
+static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 {
 	struct vfio_ccw_private *private =
-		dev_get_drvdata(mdev_parent_dev(mdev));
+		container_of(vdev, struct vfio_ccw_private, vdev);
 	unsigned long events = VFIO_IOMMU_NOTIFY_DMA_UNMAP;
 	int ret;
 
 	private->nb.notifier_call = vfio_ccw_mdev_notifier;
 
-	ret = vfio_register_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+	ret = vfio_register_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
 				     &events, &private->nb);
 	if (ret)
 		return ret;
@@ -187,15 +204,15 @@ static int vfio_ccw_mdev_open_device(struct mdev_device *mdev)
 
 out_unregister:
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
+	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
 				 &private->nb);
 	return ret;
 }
 
-static void vfio_ccw_mdev_close_device(struct mdev_device *mdev)
+static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 {
 	struct vfio_ccw_private *private =
-		dev_get_drvdata(mdev_parent_dev(mdev));
+		container_of(vdev, struct vfio_ccw_private, vdev);
 
 	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
 	    (private->state != VFIO_CCW_STATE_STANDBY)) {
@@ -206,8 +223,7 @@ static void vfio_ccw_mdev_close_device(struct mdev_device *mdev)
 
 	cp_free(&private->cp);
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(mdev_dev(mdev), VFIO_IOMMU_NOTIFY,
-				 &private->nb);
+	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY, &private->nb);
 }
 
 static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
@@ -231,15 +247,14 @@ static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
 	return ret;
 }
 
-static ssize_t vfio_ccw_mdev_read(struct mdev_device *mdev,
+static ssize_t vfio_ccw_mdev_read(struct vfio_device *vdev,
 				  char __user *buf,
 				  size_t count,
 				  loff_t *ppos)
 {
+	struct vfio_ccw_private *private =
+		container_of(vdev, struct vfio_ccw_private, vdev);
 	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos);
-	struct vfio_ccw_private *private;
-
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
 
 	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
 		return -EINVAL;
@@ -284,15 +299,14 @@ out_unlock:
 	return ret;
 }
 
-static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
+static ssize_t vfio_ccw_mdev_write(struct vfio_device *vdev,
 				   const char __user *buf,
 				   size_t count,
 				   loff_t *ppos)
 {
+	struct vfio_ccw_private *private =
+		container_of(vdev, struct vfio_ccw_private, vdev);
 	unsigned int index = VFIO_CCW_OFFSET_TO_INDEX(*ppos);
-	struct vfio_ccw_private *private;
-
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
 
 	if (index >= VFIO_CCW_NUM_REGIONS + private->num_regions)
 		return -EINVAL;
@@ -510,12 +524,12 @@ void vfio_ccw_unregister_dev_regions(struct vfio_ccw_private *private)
 	private->region = NULL;
 }
 
-static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
+static ssize_t vfio_ccw_mdev_ioctl(struct vfio_device *vdev,
 				   unsigned int cmd,
 				   unsigned long arg)
 {
 	struct vfio_ccw_private *private =
-		dev_get_drvdata(mdev_parent_dev(mdev));
+		container_of(vdev, struct vfio_ccw_private, vdev);
 	int ret = 0;
 	unsigned long minsz;
 
@@ -606,37 +620,48 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 }
 
 /* Request removal of the device*/
-static void vfio_ccw_mdev_request(struct mdev_device *mdev, unsigned int count)
+static void vfio_ccw_mdev_request(struct vfio_device *vdev, unsigned int count)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(mdev_parent_dev(mdev));
-
-	if (!private)
-		return;
+	struct vfio_ccw_private *private =
+		container_of(vdev, struct vfio_ccw_private, vdev);
+	struct device *dev = vdev->dev;
 
 	if (private->req_trigger) {
 		if (!(count % 10))
-			dev_notice_ratelimited(mdev_dev(private->mdev),
+			dev_notice_ratelimited(dev,
 					       "Relaying device request to user (#%u)\n",
 					       count);
 
 		eventfd_signal(private->req_trigger, 1);
 	} else if (count == 0) {
-		dev_notice(mdev_dev(private->mdev),
+		dev_notice(dev,
 			   "No device request channel registered, blocked until released by user\n");
 	}
 }
 
+static const struct vfio_device_ops vfio_ccw_dev_ops = {
+	.open_device = vfio_ccw_mdev_open_device,
+	.close_device = vfio_ccw_mdev_close_device,
+	.read = vfio_ccw_mdev_read,
+	.write = vfio_ccw_mdev_write,
+	.ioctl = vfio_ccw_mdev_ioctl,
+	.request = vfio_ccw_mdev_request,
+};
+
+struct mdev_driver vfio_ccw_mdev_driver = {
+	.driver = {
+		.name = "vfio_ccw_mdev",
+		.owner = THIS_MODULE,
+		.mod_name = KBUILD_MODNAME,
+	},
+	.probe = vfio_ccw_mdev_probe,
+	.remove = vfio_ccw_mdev_remove,
+};
+
 static const struct mdev_parent_ops vfio_ccw_mdev_ops = {
 	.owner			= THIS_MODULE,
+	.device_driver		= &vfio_ccw_mdev_driver,
 	.supported_type_groups  = mdev_type_groups,
-	.create			= vfio_ccw_mdev_create,
-	.remove			= vfio_ccw_mdev_remove,
-	.open_device		= vfio_ccw_mdev_open_device,
-	.close_device		= vfio_ccw_mdev_close_device,
-	.read			= vfio_ccw_mdev_read,
-	.write			= vfio_ccw_mdev_write,
-	.ioctl			= vfio_ccw_mdev_ioctl,
-	.request		= vfio_ccw_mdev_request,
 };
 
 int vfio_ccw_mdev_reg(struct subchannel *sch)
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index b2c762eb42b9..7272eb788612 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -17,6 +17,7 @@
 #include <linux/eventfd.h>
 #include <linux/workqueue.h>
 #include <linux/vfio_ccw.h>
+#include <linux/vfio.h>
 #include <asm/crw.h>
 #include <asm/debug.h>
 
@@ -67,6 +68,7 @@ struct vfio_ccw_crw {
 
 /**
  * struct vfio_ccw_private
+ * @vdev: Embedded VFIO device
  * @sch: pointer to the subchannel
  * @state: internal state of the device
  * @completion: synchronization helper of the I/O completion
@@ -90,6 +92,7 @@ struct vfio_ccw_crw {
  * @crw_work: work for deferral process of CRW handling
  */
 struct vfio_ccw_private {
+	struct vfio_device vdev;
 	struct subchannel	*sch;
 	int			state;
 	struct completion	*completion;
@@ -121,6 +124,8 @@ extern void vfio_ccw_mdev_unreg(struct subchannel *sch);
 
 extern int vfio_ccw_sch_quiesce(struct subchannel *sch);
 
+extern struct mdev_driver vfio_ccw_mdev_driver;
+
 /*
  * States of the device statemachine.
  */