[PATCH v4 0/4] Move vfio_ccw to the new mdev API

[PATCH v4 0/4] Move vfio_ccw to the new mdev API

[Jason Gunthorpe]

This is the first 4 patches of the v3 series which only change CCW to use
the new VFIO API for mdevs and leaves the lifetime model as-is.

As agreed, we will go ahead with this set and IBM can take the remaining
patches of cleanup when they want. (I won't resend them)

Alex: as Eric has now ack'd them please take them to the VFIO tree for
this upcoming merge window

This is on github: https://github.com/jgunthorpe/linux/commits/vfio_ccw

Thanks,
Jason

v4:
 - Rebase to vfio-next (9cef73918), no change
 - Add acks
v3: https://lore.kernel.org/r/0-v3-57c1502c62fd+2190-ccw_mdev_jgg@nvidia.com
 - Rebase to Christoph's group work & rc3; use
   vfio_register_emulated_iommu_dev()
 - Remove GFP_DMA
 - Order mdev_unregister_driver() symmetrically with init
 - Rework what is considered a BROKEN event in fsm_close()
 - NOP both CCW_EVENT_OPEN/CLOSE
 - Documentation updates
 - Remane goto label to err_init vfio_ccw_mdev_probe()
 - Fix NULL pointer deref in mdev_device_create()
v2: https://lore.kernel.org/r/0-v2-7d3a384024cf+2060-ccw_mdev_jgg@nvidia.com
 - Clean up the lifecycle in ccw with 7 new patches
 - Rebase
v1: https://lore.kernel.org/all/7-v2-7667f42c9bad+935-vfio3_jgg@nvidia.com

Jason Gunthorpe (4):
  vfio/ccw: Remove unneeded GFP_DMA
  vfio/ccw: Use functions for alloc/free of the vfio_ccw_private
  vfio/ccw: Pass vfio_ccw_private not mdev_device to various functions
  vfio/ccw: Convert to use vfio_register_emulated_iommu_dev()

 drivers/s390/cio/vfio_ccw_drv.c     | 158 ++++++++++++++++------------
 drivers/s390/cio/vfio_ccw_ops.c     | 142 ++++++++++++++-----------
 drivers/s390/cio/vfio_ccw_private.h |   5 +
 3 files changed, 177 insertions(+), 128 deletions(-)


base-commit: 9cef73918e15d2284e71022291a8a07901e80bad
-- 
2.33.0

[PATCH v4 1/4] vfio/ccw: Remove unneeded GFP_DMA

[Jason Gunthorpe]

Since the ccw_io_region was split out of the private the allocation no
longer needs the GFP_DMA. Remove it.

Reported-by: Christoph Hellwig <hch@infradead.org>
Fixes: c98e16b2fa12 ("s390/cio: Convert ccw_io_region to pointer")
Reviewed-by: Matthew Rosato <mjrosato@linux.ibm.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/s390/cio/vfio_ccw_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 76099bcb765b45..371558ec92045d 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -161,7 +161,7 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 		return -ENODEV;
 	}
 
-	private = kzalloc(sizeof(*private), GFP_KERNEL | GFP_DMA);
+	private = kzalloc(sizeof(*private), GFP_KERNEL);
 	if (!private)
 		return -ENOMEM;
 
-- 
2.33.0

[PATCH v4 2/4] vfio/ccw: Use functions for alloc/free of the vfio_ccw_private

[Jason Gunthorpe]

Makes the code easier to understand what is memory lifecycle and what is
other stuff.

Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/s390/cio/vfio_ccw_drv.c | 137 ++++++++++++++++++--------------
 1 file changed, 78 insertions(+), 59 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_drv.c b/drivers/s390/cio/vfio_ccw_drv.c
index 371558ec92045d..e32678a71644fb 100644
--- a/drivers/s390/cio/vfio_ccw_drv.c
+++ b/drivers/s390/cio/vfio_ccw_drv.c
@@ -137,16 +137,80 @@ static void vfio_ccw_sch_irq(struct subchannel *sch)
 	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_INTERRUPT);
 }
 
-static void vfio_ccw_free_regions(struct vfio_ccw_private *private)
+static struct vfio_ccw_private *vfio_ccw_alloc_private(struct subchannel *sch)
 {
-	if (private->crw_region)
-		kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
-	if (private->schib_region)
-		kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
-	if (private->cmd_region)
-		kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
-	if (private->io_region)
-		kmem_cache_free(vfio_ccw_io_region, private->io_region);
+	struct vfio_ccw_private *private;
+
+	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_NOT_OPER;
+	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);
+	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);
+}
+
+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)
@@ -161,53 +225,19 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 		return -ENODEV;
 	}
 
-	private = kzalloc(sizeof(*private), GFP_KERNEL);
-	if (!private)
-		return -ENOMEM;
+	private = vfio_ccw_alloc_private(sch);
+	if (IS_ERR(private))
+		return PTR_ERR(private);
 
-	private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
-				       GFP_KERNEL);
-	if (!private->cp.guest_cp)
-		goto out_free;
-
-	private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
-					       GFP_KERNEL | GFP_DMA);
-	if (!private->io_region)
-		goto out_free;
-
-	private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
-						GFP_KERNEL | GFP_DMA);
-	if (!private->cmd_region)
-		goto out_free;
-
-	private->schib_region = kmem_cache_zalloc(vfio_ccw_schib_region,
-						  GFP_KERNEL | GFP_DMA);
-
-	if (!private->schib_region)
-		goto out_free;
-
-	private->crw_region = kmem_cache_zalloc(vfio_ccw_crw_region,
-						GFP_KERNEL | GFP_DMA);
-
-	if (!private->crw_region)
-		goto out_free;
-
-	private->sch = sch;
 	dev_set_drvdata(&sch->dev, private);
-	mutex_init(&private->io_mutex);
 
 	spin_lock_irq(sch->lock);
-	private->state = VFIO_CCW_STATE_NOT_OPER;
 	sch->isc = VFIO_CCW_ISC;
 	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
 	spin_unlock_irq(sch->lock);
 	if (ret)
 		goto out_free;
 
-	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->state = VFIO_CCW_STATE_STANDBY;
 
 	ret = vfio_ccw_mdev_reg(sch);
@@ -228,31 +258,20 @@ static int vfio_ccw_sch_probe(struct subchannel *sch)
 	cio_disable_subchannel(sch);
 out_free:
 	dev_set_drvdata(&sch->dev, NULL);
-	vfio_ccw_free_regions(private);
-	kfree(private->cp.guest_cp);
-	kfree(private);
+	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_crw *crw, *temp;
 
 	vfio_ccw_sch_quiesce(sch);
-
-	list_for_each_entry_safe(crw, temp, &private->crw, next) {
-		list_del(&crw->next);
-		kfree(crw);
-	}
-
 	vfio_ccw_mdev_unreg(sch);
 
 	dev_set_drvdata(&sch->dev, NULL);
 
-	vfio_ccw_free_regions(private);
-	kfree(private->cp.guest_cp);
-	kfree(private);
+	vfio_ccw_free_private(private);
 
 	VFIO_CCW_MSG_EVENT(4, "unbound from subchannel %x.%x.%04x\n",
 			   sch->schid.cssid, sch->schid.ssid,
-- 
2.33.0

[PATCH v4 3/4] vfio/ccw: Pass vfio_ccw_private not mdev_device to various functions

[Jason Gunthorpe]

mdev_device should only be used in functions assigned to ops callbacks,
interior functions should use the struct vfio_ccw_private instead of
repeatedly trying to get it from the mdev.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: Eric Farman <farman@linux.ibm.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/s390/cio/vfio_ccw_ops.c | 37 +++++++++++++--------------------
 1 file changed, 15 insertions(+), 22 deletions(-)

diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index 7f540ad0b568bc..1edbea9de0ec42 100644
--- a/drivers/s390/cio/vfio_ccw_ops.c
+++ b/drivers/s390/cio/vfio_ccw_ops.c
@@ -17,13 +17,11 @@
 
 #include "vfio_ccw_private.h"
 
-static int vfio_ccw_mdev_reset(struct mdev_device *mdev)
+static int vfio_ccw_mdev_reset(struct vfio_ccw_private *private)
 {
-	struct vfio_ccw_private *private;
 	struct subchannel *sch;
 	int ret;
 
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	sch = private->sch;
 	/*
 	 * TODO:
@@ -61,7 +59,7 @@ static int vfio_ccw_mdev_notifier(struct notifier_block *nb,
 		if (!cp_iova_pinned(&private->cp, unmap->iova))
 			return NOTIFY_OK;
 
-		if (vfio_ccw_mdev_reset(private->mdev))
+		if (vfio_ccw_mdev_reset(private))
 			return NOTIFY_BAD;
 
 		cp_free(&private->cp);
@@ -201,7 +199,7 @@ static void vfio_ccw_mdev_close_device(struct mdev_device *mdev)
 
 	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
 	    (private->state != VFIO_CCW_STATE_STANDBY)) {
-		if (!vfio_ccw_mdev_reset(mdev))
+		if (!vfio_ccw_mdev_reset(private))
 			private->state = VFIO_CCW_STATE_STANDBY;
 		/* The state will be NOT_OPER on error. */
 	}
@@ -311,12 +309,9 @@ static ssize_t vfio_ccw_mdev_write(struct mdev_device *mdev,
 	return -EINVAL;
 }
 
-static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info,
-					 struct mdev_device *mdev)
+static int vfio_ccw_mdev_get_device_info(struct vfio_ccw_private *private,
+					 struct vfio_device_info *info)
 {
-	struct vfio_ccw_private *private;
-
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	info->flags = VFIO_DEVICE_FLAGS_CCW | VFIO_DEVICE_FLAGS_RESET;
 	info->num_regions = VFIO_CCW_NUM_REGIONS + private->num_regions;
 	info->num_irqs = VFIO_CCW_NUM_IRQS;
@@ -324,14 +319,12 @@ static int vfio_ccw_mdev_get_device_info(struct vfio_device_info *info,
 	return 0;
 }
 
-static int vfio_ccw_mdev_get_region_info(struct vfio_region_info *info,
-					 struct mdev_device *mdev,
+static int vfio_ccw_mdev_get_region_info(struct vfio_ccw_private *private,
+					 struct vfio_region_info *info,
 					 unsigned long arg)
 {
-	struct vfio_ccw_private *private;
 	int i;
 
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
 	switch (info->index) {
 	case VFIO_CCW_CONFIG_REGION_INDEX:
 		info->offset = 0;
@@ -406,19 +399,16 @@ static int vfio_ccw_mdev_get_irq_info(struct vfio_irq_info *info)
 	return 0;
 }
 
-static int vfio_ccw_mdev_set_irqs(struct mdev_device *mdev,
+static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private,
 				  uint32_t flags,
 				  uint32_t index,
 				  void __user *data)
 {
-	struct vfio_ccw_private *private;
 	struct eventfd_ctx **ctx;
 
 	if (!(flags & VFIO_IRQ_SET_ACTION_TRIGGER))
 		return -EINVAL;
 
-	private = dev_get_drvdata(mdev_parent_dev(mdev));
-
 	switch (index) {
 	case VFIO_CCW_IO_IRQ_INDEX:
 		ctx = &private->io_trigger;
@@ -524,6 +514,8 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 				   unsigned int cmd,
 				   unsigned long arg)
 {
+	struct vfio_ccw_private *private =
+		dev_get_drvdata(mdev_parent_dev(mdev));
 	int ret = 0;
 	unsigned long minsz;
 
@@ -540,7 +532,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_device_info(&info, mdev);
+		ret = vfio_ccw_mdev_get_device_info(private, &info);
 		if (ret)
 			return ret;
 
@@ -558,7 +550,7 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 		if (info.argsz < minsz)
 			return -EINVAL;
 
-		ret = vfio_ccw_mdev_get_region_info(&info, mdev, arg);
+		ret = vfio_ccw_mdev_get_region_info(private, &info, arg);
 		if (ret)
 			return ret;
 
@@ -603,10 +595,11 @@ static ssize_t vfio_ccw_mdev_ioctl(struct mdev_device *mdev,
 			return ret;
 
 		data = (void __user *)(arg + minsz);
-		return vfio_ccw_mdev_set_irqs(mdev, hdr.flags, hdr.index, data);
+		return vfio_ccw_mdev_set_irqs(private, hdr.flags, hdr.index,
+					      data);
 	}
 	case VFIO_DEVICE_RESET:
-		return vfio_ccw_mdev_reset(mdev);
+		return vfio_ccw_mdev_reset(private);
 	default:
 		return -ENOTTY;
 	}
-- 
2.33.0

[PATCH v4 4/4] vfio/ccw: Convert to use vfio_register_emulated_iommu_dev()

[Jason Gunthorpe]

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>
---
 drivers/s390/cio/vfio_ccw_drv.c     |  21 ++++--
 drivers/s390/cio/vfio_ccw_ops.c     | 107 +++++++++++++++++-----------
 drivers/s390/cio/vfio_ccw_private.h |   5 ++
 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 e32678a71644fb..0407427770955d 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 @@ static int __init vfio_ccw_sch_init(void)
 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 1edbea9de0ec42..d8589afac272f1 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 @@ static ssize_t vfio_ccw_mdev_write_io_region(struct vfio_ccw_private *private,
 	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 b2c762eb42b9bb..7272eb78861244 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.
  */
-- 
2.33.0

Re: [PATCH v4 0/4] Move vfio_ccw to the new mdev API

[Alex Williamson]

On Tue, 26 Oct 2021 14:57:29 -0300
Jason Gunthorpe <jgg@nvidia.com> wrote:

> This is the first 4 patches of the v3 series which only change CCW to use
> the new VFIO API for mdevs and leaves the lifetime model as-is.
> 
> As agreed, we will go ahead with this set and IBM can take the remaining
> patches of cleanup when they want. (I won't resend them)
> 
> Alex: as Eric has now ack'd them please take them to the VFIO tree for
> this upcoming merge window
 
Applied to vfio next branch for v5.16.  Thanks,

Alex