Merge tag 'vfio-v6.2-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Replace deprecated git://github.com link in MAINTAINERS (Palmer
   Dabbelt)

 - Simplify vfio/mlx5 with module_pci_driver() helper (Shang XiaoJing)

 - Drop unnecessary buffer from ACPI call (Rafael Mendonca)

 - Correct latent missing include issue in iova-bitmap and fix support
   for unaligned bitmaps. Follow-up with better fix through refactor
   (Joao Martins)

 - Rework ccw mdev driver to split private data from parent structure,
   better aligning with the mdev lifecycle and allowing us to remove a
   temporary workaround (Eric Farman)

 - Add an interface to get an estimated migration data size for a
   device, allowing userspace to make informed decisions, ex. more
   accurately predicting VM downtime (Yishai Hadas)

 - Fix minor typo in vfio/mlx5 array declaration (Yishai Hadas)

 - Simplify module and Kconfig through consolidating SPAPR/EEH code and
   config options and folding virqfd module into main vfio module (Jason
   Gunthorpe)

 - Fix error path from device_register() across all vfio mdev and sample
   drivers (Alex Williamson)

 - Define migration pre-copy interface and implement for vfio/mlx5
   devices, allowing portions of the device state to be saved while the
   device continues operation, towards reducing the stop-copy state size
   (Jason Gunthorpe, Yishai Hadas, Shay Drory)

 - Implement pre-copy for hisi_acc devices (Shameer Kolothum)

 - Fixes to mdpy mdev driver remove path and error path on probe (Shang
   XiaoJing)

 - vfio/mlx5 fixes for incorrect return after copy_to_user() fault and
   incorrect buffer freeing (Dan Carpenter)

* tag 'vfio-v6.2-rc1' of https://github.com/awilliam/linux-vfio: (42 commits)
  vfio/mlx5: error pointer dereference in error handling
  vfio/mlx5: fix error code in mlx5vf_precopy_ioctl()
  samples: vfio-mdev: Fix missing pci_disable_device() in mdpy_fb_probe()
  hisi_acc_vfio_pci: Enable PRE_COPY flag
  hisi_acc_vfio_pci: Move the dev compatibility tests for early check
  hisi_acc_vfio_pci: Introduce support for PRE_COPY state transitions
  hisi_acc_vfio_pci: Add support for precopy IOCTL
  vfio/mlx5: Enable MIGRATION_PRE_COPY flag
  vfio/mlx5: Fallback to STOP_COPY upon specific PRE_COPY error
  vfio/mlx5: Introduce multiple loads
  vfio/mlx5: Consider temporary end of stream as part of PRE_COPY
  vfio/mlx5: Introduce vfio precopy ioctl implementation
  vfio/mlx5: Introduce SW headers for migration states
  vfio/mlx5: Introduce device transitions of PRE_COPY
  vfio/mlx5: Refactor to use queue based data chunks
  vfio/mlx5: Refactor migration file state
  vfio/mlx5: Refactor MKEY usage
  vfio/mlx5: Refactor PD usage
  vfio/mlx5: Enforce a single SAVE command at a time
  vfio: Extend the device migration protocol with PRE_COPY
  ...

5 files changed, 188 insertions, 162 deletions

diff --git a/drivers/s390/cio/vfio_ccw_chp.c b/drivers/s390/cio/vfio_ccw_chp.c
index 13b26a1c7988..d3f3a611f95b 100644
--- a/drivers/s390/cio/vfio_ccw_chp.c
+++ b/drivers/s390/cio/vfio_ccw_chp.c
@@ -16,6 +16,7 @@ static ssize_t vfio_ccw_schib_region_read(struct vfio_ccw_private *private,
 					  char __user *buf, size_t count,
 					  loff_t *ppos)
 {
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	unsigned int i = VFIO_CCW_OFFSET_TO_INDEX(*ppos) - VFIO_CCW_NUM_REGIONS;
 	loff_t pos = *ppos & VFIO_CCW_OFFSET_MASK;
 	struct ccw_schib_region *region;
@@ -27,12 +28,12 @@ static ssize_t vfio_ccw_schib_region_read(struct vfio_ccw_private *private,
 	mutex_lock(&private->io_mutex);
 	region = private->region[i].data;
 
-	if (cio_update_schib(private->sch)) {
+	if (cio_update_schib(sch)) {
 		ret = -ENODEV;
 		goto out;
 	}
 
-	memcpy(region, &private->sch->schib, sizeof(*region));
+	memcpy(region, &sch->schib, sizeof(*region));
 
 	if (copy_to_user(buf, (void *)region + pos, count)) {
 		ret = -EFAULT;
diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 7f5402fe857a..54aba7cceb33 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -23,10 +23,10 @@
 #include "vfio_ccw_private.h"
 
 struct workqueue_struct *vfio_ccw_work_q;
-static struct kmem_cache *vfio_ccw_io_region;
-static struct kmem_cache *vfio_ccw_cmd_region;
-static struct kmem_cache *vfio_ccw_schib_region;
-static struct kmem_cache *vfio_ccw_crw_region;
+struct kmem_cache *vfio_ccw_io_region;
+struct kmem_cache *vfio_ccw_cmd_region;
+struct kmem_cache *vfio_ccw_schib_region;
+struct kmem_cache *vfio_ccw_crw_region;
 
 debug_info_t *vfio_ccw_debug_msg_id;
 debug_info_t *vfio_ccw_debug_trace_id;
@@ -36,10 +36,19 @@ debug_info_t *vfio_ccw_debug_trace_id;
  */
 int vfio_ccw_sch_quiesce(struct subchannel *sch)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_private *private = dev_get_drvdata(&parent->dev);
 	DECLARE_COMPLETION_ONSTACK(completion);
 	int iretry, ret = 0;
 
+	/*
+	 * Probably an impossible situation, after being called through
+	 * FSM callbacks. But in the event it did, register a warning
+	 * and return as if things were fine.
+	 */
+	if (WARN_ON(!private))
+		return 0;
+
 	iretry = 255;
 	do {
 
@@ -70,7 +79,7 @@ int vfio_ccw_sch_quiesce(struct subchannel *sch)
 	return ret;
 }
 
-static void vfio_ccw_sch_io_todo(struct work_struct *work)
+void vfio_ccw_sch_io_todo(struct work_struct *work)
 {
 	struct vfio_ccw_private *private;
 	struct irb *irb;
@@ -106,7 +115,7 @@ static void vfio_ccw_sch_io_todo(struct work_struct *work)
 		eventfd_signal(private->io_trigger, 1);
 }
 
-static void vfio_ccw_crw_todo(struct work_struct *work)
+void vfio_ccw_crw_todo(struct work_struct *work)
 {
 	struct vfio_ccw_private *private;
 
@@ -121,90 +130,39 @@ static void vfio_ccw_crw_todo(struct work_struct *work)
  */
 static void vfio_ccw_sch_irq(struct subchannel *sch)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_private *private = dev_get_drvdata(&parent->dev);
+
+	/*
+	 * The subchannel should still be disabled at this point,
+	 * so an interrupt would be quite surprising. As with an
+	 * interrupt while the FSM is closed, let's attempt to
+	 * disable the subchannel again.
+	 */
+	if (!private) {
+		VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: unexpected interrupt\n",
+				   sch->schid.cssid, sch->schid.ssid,
+				   sch->schid.sch_no);
+
+		cio_disable_subchannel(sch);
+		return;
+	}
 
 	inc_irq_stat(IRQIO_CIO);
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_INTERRUPT);
 }
 
-static struct vfio_ccw_private *vfio_ccw_alloc_private(struct subchannel *sch)
+static void vfio_ccw_free_parent(struct device *dev)
 {
-	struct vfio_ccw_private *private;
+	struct vfio_ccw_parent *parent = container_of(dev, struct vfio_ccw_parent, dev);
 
-	private = kzalloc(sizeof(*private), GFP_KERNEL);
-	if (!private)
-		return ERR_PTR(-ENOMEM);
-
-	private->sch = sch;
-	mutex_init(&private->io_mutex);
-	private->state = VFIO_CCW_STATE_STANDBY;
-	INIT_LIST_HEAD(&private->crw);
-	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
-	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
-
-	private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
-				       GFP_KERNEL);
-	if (!private->cp.guest_cp)
-		goto out_free_private;
-
-	private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
-					       GFP_KERNEL | GFP_DMA);
-	if (!private->io_region)
-		goto out_free_cp;
-
-	private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
-						GFP_KERNEL | GFP_DMA);
-	if (!private->cmd_region)
-		goto out_free_io;
-
-	private->schib_region = kmem_cache_zalloc(vfio_ccw_schib_region,
-						  GFP_KERNEL | GFP_DMA);
-
-	if (!private->schib_region)
-		goto out_free_cmd;
-
-	private->crw_region = kmem_cache_zalloc(vfio_ccw_crw_region,
-						GFP_KERNEL | GFP_DMA);
-
-	if (!private->crw_region)
-		goto out_free_schib;
-	return private;
-
-out_free_schib:
-	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
-out_free_cmd:
-	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
-out_free_io:
-	kmem_cache_free(vfio_ccw_io_region, private->io_region);
-out_free_cp:
-	kfree(private->cp.guest_cp);
-out_free_private:
-	mutex_destroy(&private->io_mutex);
-	kfree(private);
-	return ERR_PTR(-ENOMEM);
+	kfree(parent);
 }
 
-static void vfio_ccw_free_private(struct vfio_ccw_private *private)
-{
-	struct vfio_ccw_crw *crw, *temp;
-
-	list_for_each_entry_safe(crw, temp, &private->crw, next) {
-		list_del(&crw->next);
-		kfree(crw);
-	}
-
-	kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
-	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
-	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
-	kmem_cache_free(vfio_ccw_io_region, private->io_region);
-	kfree(private->cp.guest_cp);
-	mutex_destroy(&private->io_mutex);
-	kfree(private);
-}
 static int vfio_ccw_sch_probe(struct subchannel *sch)
 {
 	struct pmcw *pmcw = &sch->schib.pmcw;
-	struct vfio_ccw_private *private;
+	struct vfio_ccw_parent *parent;
 	int ret = -ENOMEM;
 
 	if (pmcw->qf) {
@@ -213,42 +171,50 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 		return -ENODEV;
 	}
 
-	private = vfio_ccw_alloc_private(sch);
-	if (IS_ERR(private))
-		return PTR_ERR(private);
+	parent = kzalloc(sizeof(*parent), GFP_KERNEL);
+	if (!parent)
+		return -ENOMEM;
+
+	dev_set_name(&parent->dev, "parent");
+	parent->dev.parent = &sch->dev;
+	parent->dev.release = &vfio_ccw_free_parent;
+	ret = device_register(&parent->dev);
+	if (ret)
+		goto out_free;
 
-	dev_set_drvdata(&sch->dev, private);
+	dev_set_drvdata(&sch->dev, parent);
 
-	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,
+	parent->mdev_type.sysfs_name = "io";
+	parent->mdev_type.pretty_name = "I/O subchannel (Non-QDIO)";
+	parent->mdev_types[0] = &parent->mdev_type;
+	ret = mdev_register_parent(&parent->parent, &sch->dev,
 				   &vfio_ccw_mdev_driver,
-				   private->mdev_types, 1);
+				   parent->mdev_types, 1);
 	if (ret)
-		goto out_free;
+		goto out_unreg;
 
 	VFIO_CCW_MSG_EVENT(4, "bound to subchannel %x.%x.%04x\n",
 			   sch->schid.cssid, sch->schid.ssid,
 			   sch->schid.sch_no);
 	return 0;
 
+out_unreg:
+	device_del(&parent->dev);
 out_free:
+	put_device(&parent->dev);
 	dev_set_drvdata(&sch->dev, NULL);
-	vfio_ccw_free_private(private);
 	return ret;
 }
 
 static void vfio_ccw_sch_remove(struct subchannel *sch)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
 
-	mdev_unregister_parent(&private->parent);
+	mdev_unregister_parent(&parent->parent);
 
+	device_unregister(&parent->dev);
 	dev_set_drvdata(&sch->dev, NULL);
 
-	vfio_ccw_free_private(private);
-
 	VFIO_CCW_MSG_EVENT(4, "unbound from subchannel %x.%x.%04x\n",
 			   sch->schid.cssid, sch->schid.ssid,
 			   sch->schid.sch_no);
@@ -256,7 +222,11 @@ static void vfio_ccw_sch_remove(struct subchannel *sch)
 
 static void vfio_ccw_sch_shutdown(struct subchannel *sch)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_private *private = dev_get_drvdata(&parent->dev);
+
+	if (WARN_ON(!private))
+		return;
 
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
@@ -274,7 +244,8 @@ static void vfio_ccw_sch_shutdown(struct subchannel *sch)
  */
 static int vfio_ccw_sch_event(struct subchannel *sch, int process)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_private *private = dev_get_drvdata(&parent->dev);
 	unsigned long flags;
 	int rc = -EAGAIN;
 
@@ -287,8 +258,10 @@ static int vfio_ccw_sch_event(struct subchannel *sch, int process)
 
 	rc = 0;
 
-	if (cio_update_schib(sch))
-		vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+	if (cio_update_schib(sch)) {
+		if (private)
+			vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_NOT_OPER);
+	}
 
 out_unlock:
 	spin_unlock_irqrestore(sch->lock, flags);
@@ -326,14 +299,15 @@ static void vfio_ccw_queue_crw(struct vfio_ccw_private *private,
 static int vfio_ccw_chp_event(struct subchannel *sch,
 			      struct chp_link *link, int event)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_private *private = dev_get_drvdata(&parent->dev);
 	int mask = chp_ssd_get_mask(&sch->ssd_info, link);
 	int retry = 255;
 
 	if (!private || !mask)
 		return 0;
 
-	trace_vfio_ccw_chp_event(private->sch->schid, mask, event);
+	trace_vfio_ccw_chp_event(sch->schid, mask, event);
 	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: mask=0x%x event=%d\n",
 			   sch->schid.cssid,
 			   sch->schid.ssid, sch->schid.sch_no,
diff --git a/drivers/s390/cio/vfio_ccw_fsm.c b/drivers/s390/cio/vfio_ccw_fsm.c
index 0a5e8b4a6743..2784a4e4d2be 100644
--- a/drivers/s390/cio/vfio_ccw_fsm.c
+++ b/drivers/s390/cio/vfio_ccw_fsm.c
@@ -18,15 +18,13 @@
 
 static int fsm_io_helper(struct vfio_ccw_private *private)
 {
-	struct subchannel *sch;
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	union orb *orb;
 	int ccode;
 	__u8 lpm;
 	unsigned long flags;
 	int ret;
 
-	sch = private->sch;
-
 	spin_lock_irqsave(sch->lock, flags);
 
 	orb = cp_get_orb(&private->cp, (u32)virt_to_phys(sch), sch->lpm);
@@ -80,13 +78,11 @@ out:
 
 static int fsm_do_halt(struct vfio_ccw_private *private)
 {
-	struct subchannel *sch;
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	unsigned long flags;
 	int ccode;
 	int ret;
 
-	sch = private->sch;
-
 	spin_lock_irqsave(sch->lock, flags);
 
 	VFIO_CCW_TRACE_EVENT(2, "haltIO");
@@ -121,13 +117,11 @@ static int fsm_do_halt(struct vfio_ccw_private *private)
 
 static int fsm_do_clear(struct vfio_ccw_private *private)
 {
-	struct subchannel *sch;
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	unsigned long flags;
 	int ccode;
 	int ret;
 
-	sch = private->sch;
-
 	spin_lock_irqsave(sch->lock, flags);
 
 	VFIO_CCW_TRACE_EVENT(2, "clearIO");
@@ -160,7 +154,7 @@ static int fsm_do_clear(struct vfio_ccw_private *private)
 static void fsm_notoper(struct vfio_ccw_private *private,
 			enum vfio_ccw_event event)
 {
-	struct subchannel *sch = private->sch;
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 
 	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: notoper event %x state %x\n",
 			   sch->schid.cssid,
@@ -228,7 +222,7 @@ static void fsm_async_retry(struct vfio_ccw_private *private,
 static void fsm_disabled_irq(struct vfio_ccw_private *private,
 			     enum vfio_ccw_event event)
 {
-	struct subchannel *sch = private->sch;
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 
 	/*
 	 * An interrupt in a disabled state means a previous disable was not
@@ -238,7 +232,9 @@ static void fsm_disabled_irq(struct vfio_ccw_private *private,
 }
 inline struct subchannel_id get_schid(struct vfio_ccw_private *p)
 {
-	return p->sch->schid;
+	struct subchannel *sch = to_subchannel(p->vdev.dev->parent);
+
+	return sch->schid;
 }
 
 /*
@@ -360,10 +356,11 @@ static void fsm_async_request(struct vfio_ccw_private *private,
 static void fsm_irq(struct vfio_ccw_private *private,
 		    enum vfio_ccw_event event)
 {
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	struct irb *irb = this_cpu_ptr(&cio_irb);
 
 	VFIO_CCW_TRACE_EVENT(6, "IRQ");
-	VFIO_CCW_TRACE_EVENT(6, dev_name(&private->sch->dev));
+	VFIO_CCW_TRACE_EVENT(6, dev_name(&sch->dev));
 
 	memcpy(&private->irb, irb, sizeof(*irb));
 
@@ -376,7 +373,7 @@ static void fsm_irq(struct vfio_ccw_private *private,
 static void fsm_open(struct vfio_ccw_private *private,
 		     enum vfio_ccw_event event)
 {
-	struct subchannel *sch = private->sch;
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	int ret;
 
 	spin_lock_irq(sch->lock);
@@ -397,7 +394,7 @@ err_unlock:
 static void fsm_close(struct vfio_ccw_private *private,
 		      enum vfio_ccw_event event)
 {
-	struct subchannel *sch = private->sch;
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
 	int ret;
 
 	spin_lock_irq(sch->lock);
diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 560453d99c24..5b53b94f13c7 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -49,26 +49,70 @@ static int vfio_ccw_mdev_init_dev(struct vfio_device *vdev)
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
-	init_completion(&private->release_comp);
+	mutex_init(&private->io_mutex);
+	private->state = VFIO_CCW_STATE_STANDBY;
+	INIT_LIST_HEAD(&private->crw);
+	INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
+	INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
+
+	private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
+				       GFP_KERNEL);
+	if (!private->cp.guest_cp)
+		goto out_free_private;
+
+	private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
+					       GFP_KERNEL | GFP_DMA);
+	if (!private->io_region)
+		goto out_free_cp;
+
+	private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
+						GFP_KERNEL | GFP_DMA);
+	if (!private->cmd_region)
+		goto out_free_io;
+
+	private->schib_region = kmem_cache_zalloc(vfio_ccw_schib_region,
+						  GFP_KERNEL | GFP_DMA);
+	if (!private->schib_region)
+		goto out_free_cmd;
+
+	private->crw_region = kmem_cache_zalloc(vfio_ccw_crw_region,
+						GFP_KERNEL | GFP_DMA);
+	if (!private->crw_region)
+		goto out_free_schib;
+
 	return 0;
+
+out_free_schib:
+	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
+out_free_cmd:
+	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
+out_free_io:
+	kmem_cache_free(vfio_ccw_io_region, private->io_region);
+out_free_cp:
+	kfree(private->cp.guest_cp);
+out_free_private:
+	mutex_destroy(&private->io_mutex);
+	return -ENOMEM;
 }
 
 static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
+	struct subchannel *sch = to_subchannel(mdev->dev.parent);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_private *private;
 	int ret;
 
-	if (private->state == VFIO_CCW_STATE_NOT_OPER)
-		return -ENODEV;
+	private = vfio_alloc_device(vfio_ccw_private, vdev, &mdev->dev,
+				    &vfio_ccw_dev_ops);
+	if (IS_ERR(private))
+		return PTR_ERR(private);
 
-	ret = vfio_init_device(&private->vdev, &mdev->dev, &vfio_ccw_dev_ops);
-	if (ret)
-		return ret;
+	dev_set_drvdata(&parent->dev, private);
 
 	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: create\n",
-			   private->sch->schid.cssid,
-			   private->sch->schid.ssid,
-			   private->sch->schid.sch_no);
+			   sch->schid.cssid,
+			   sch->schid.ssid,
+			   sch->schid.sch_no);
 
 	ret = vfio_register_emulated_iommu_dev(&private->vdev);
 	if (ret)
@@ -77,6 +121,7 @@ static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
 	return 0;
 
 err_put_vdev:
+	dev_set_drvdata(&parent->dev, NULL);
 	vfio_put_device(&private->vdev);
 	return ret;
 }
@@ -85,40 +130,36 @@ static void vfio_ccw_mdev_release_dev(struct vfio_device *vdev)
 {
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
+	struct vfio_ccw_crw *crw, *temp;
 
-	/*
-	 * 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);
+	list_for_each_entry_safe(crw, temp, &private->crw, next) {
+		list_del(&crw->next);
+		kfree(crw);
+	}
+
+	kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
+	kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
+	kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
+	kmem_cache_free(vfio_ccw_io_region, private->io_region);
+	kfree(private->cp.guest_cp);
+	mutex_destroy(&private->io_mutex);
 }
 
 static void vfio_ccw_mdev_remove(struct mdev_device *mdev)
 {
-	struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
+	struct subchannel *sch = to_subchannel(mdev->dev.parent);
+	struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+	struct vfio_ccw_private *private = dev_get_drvdata(&parent->dev);
 
 	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: remove\n",
-			   private->sch->schid.cssid,
-			   private->sch->schid.ssid,
-			   private->sch->schid.sch_no);
+			   sch->schid.cssid,
+			   sch->schid.ssid,
+			   sch->schid.sch_no);
 
 	vfio_unregister_group_dev(&private->vdev);
 
+	dev_set_drvdata(&parent->dev, NULL);
 	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)
diff --git a/drivers/s390/cio/vfio_ccw_private.h b/drivers/s390/cio/vfio_ccw_private.h
index bd5fb81456af..b441ae6700fd 100644
--- a/drivers/s390/cio/vfio_ccw_private.h
+++ b/drivers/s390/cio/vfio_ccw_private.h
@@ -68,9 +68,23 @@ struct vfio_ccw_crw {
 };
 
 /**
+ * struct vfio_ccw_parent
+ *
+ * @dev: embedded device struct
+ * @parent: parent data structures for mdevs created
+ * @mdev_type(s): identifying information for mdevs created
+ */
+struct vfio_ccw_parent {
+	struct device		dev;
+
+	struct mdev_parent	parent;
+	struct mdev_type	mdev_type;
+	struct mdev_type	*mdev_types[1];
+};
+
+/**
  * 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
  * @io_region: MMIO region to input/output I/O arguments/results
@@ -88,12 +102,9 @@ 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;
 	struct ccw_io_region	*io_region;
@@ -114,15 +125,11 @@ 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);
+void vfio_ccw_sch_io_todo(struct work_struct *work);
+void vfio_ccw_crw_todo(struct work_struct *work);
 
 extern struct mdev_driver vfio_ccw_mdev_driver;
 
@@ -162,12 +169,18 @@ extern fsm_func_t *vfio_ccw_jumptable[NR_VFIO_CCW_STATES][NR_VFIO_CCW_EVENTS];
 static inline void vfio_ccw_fsm_event(struct vfio_ccw_private *private,
 				      enum vfio_ccw_event event)
 {
-	trace_vfio_ccw_fsm_event(private->sch->schid, private->state, event);
+	struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
+
+	if (sch)
+		trace_vfio_ccw_fsm_event(sch->schid, private->state, event);
 	vfio_ccw_jumptable[private->state][event](private, event);
 }
 
 extern struct workqueue_struct *vfio_ccw_work_q;
-
+extern struct kmem_cache *vfio_ccw_io_region;
+extern struct kmem_cache *vfio_ccw_cmd_region;
+extern struct kmem_cache *vfio_ccw_schib_region;
+extern struct kmem_cache *vfio_ccw_crw_region;
 
 /* s390 debug feature, similar to base cio */
 extern debug_info_t *vfio_ccw_debug_msg_id;