1 files changed, 132 insertions, 192 deletions

diff --git a/drivers/s390/cio/vfio_ccw_ops.c b/drivers/s390/cio/vfio_ccw_ops.c
index d8589afac272..a596f6013019 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>
 
@@ -21,176 +20,161 @@ static const struct vfio_device_ops vfio_ccw_dev_ops;
 
 static int vfio_ccw_mdev_reset(struct vfio_ccw_private *private)
 {
-	struct subchannel *sch;
-	int ret;
-
-	sch = private->sch;
 	/*
-	 * TODO:
-	 * In the cureent stage, some things like "no I/O running" and "no
-	 * interrupt pending" are clear, but we are not sure what other state
-	 * we need to care about.
-	 * There are still a lot more instructions need to be handled. We
-	 * should come back here later.
+	 * If the FSM state is seen as Not Operational after closing
+	 * and re-opening the mdev, return an error.
 	 */
-	ret = vfio_ccw_sch_quiesce(sch);
-	if (ret)
-		return ret;
-
-	ret = cio_enable_subchannel(sch, (u32)(unsigned long)sch);
-	if (!ret)
-		private->state = VFIO_CCW_STATE_IDLE;
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_OPEN);
+	if (private->state == VFIO_CCW_STATE_NOT_OPER)
+		return -EINVAL;
 
-	return ret;
+	return 0;
 }
 
-static int vfio_ccw_mdev_notifier(struct notifier_block *nb,
-				  unsigned long action,
-				  void *data)
+static void vfio_ccw_dma_unmap(struct vfio_device *vdev, u64 iova, u64 length)
 {
 	struct vfio_ccw_private *private =
-		container_of(nb, struct vfio_ccw_private, nb);
-
-	/*
-	 * Vendor drivers MUST unpin pages in response to an
-	 * invalidation.
-	 */
-	if (action == VFIO_IOMMU_NOTIFY_DMA_UNMAP) {
-		struct vfio_iommu_type1_dma_unmap *unmap = data;
-
-		if (!cp_iova_pinned(&private->cp, unmap->iova))
-			return NOTIFY_OK;
-
-		if (vfio_ccw_mdev_reset(private))
-			return NOTIFY_BAD;
-
-		cp_free(&private->cp);
-		return NOTIFY_OK;
-	}
+		container_of(vdev, struct vfio_ccw_private, vdev);
 
-	return NOTIFY_DONE;
-}
+	/* Drivers MUST unpin pages in response to an invalidation. */
+	if (!cp_iova_pinned(&private->cp, iova, length))
+		return;
 
-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");
+	vfio_ccw_mdev_reset(private);
 }
-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));
-
-	return sprintf(buf, "%d\n", atomic_read(&private->avail));
-}
-static MDEV_TYPE_ATTR_RO(available_instances);
+		container_of(vdev, struct vfio_ccw_private, vdev);
 
-static struct attribute *mdev_types_attrs[] = {
-	&mdev_type_attr_name.attr,
-	&mdev_type_attr_device_api.attr,
-	&mdev_type_attr_available_instances.attr,
-	NULL,
-};
+	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;
 
-static struct attribute_group mdev_type_group = {
-	.name  = "io",
-	.attrs = mdev_types_attrs,
-};
+	return 0;
 
-static struct attribute_group *mdev_type_groups[] = {
-	&mdev_type_group,
-	NULL,
-};
+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;
-
-	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 = vfio_alloc_device(vfio_ccw_private, vdev, &mdev->dev,
+				    &vfio_ccw_dev_ops);
+	if (IS_ERR(private))
+		return PTR_ERR(private);
 
-	private->mdev = mdev;
-	private->state = VFIO_CCW_STATE_IDLE;
+	dev_set_drvdata(&parent->dev, private);
 
-	VFIO_CCW_MSG_EVENT(2, "mdev %pUl, sch %x.%x.%04x: create\n",
-			   mdev_uuid(mdev), private->sch->schid.cssid,
-			   private->sch->schid.ssid,
-			   private->sch->schid.sch_no);
+	VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: create\n",
+			   sch->schid.cssid,
+			   sch->schid.ssid,
+			   sch->schid.sch_no);
 
 	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);
-	private->mdev = NULL;
-	private->state = VFIO_CCW_STATE_IDLE;
+err_put_vdev:
+	dev_set_drvdata(&parent->dev, NULL);
+	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);
+	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);
+}
+
 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, "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_CCW_MSG_EVENT(2, "sch %x.%x.%04x: remove\n",
+			   sch->schid.cssid,
+			   sch->schid.ssid,
+			   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))
-			private->state = VFIO_CCW_STATE_STANDBY;
-		/* 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);
+	dev_set_drvdata(&parent->dev, NULL);
+	vfio_put_device(&private->vdev);
 }
 
 static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 {
 	struct vfio_ccw_private *private =
 		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(vdev->dev, VFIO_IOMMU_NOTIFY,
-				     &events, &private->nb);
-	if (ret)
-		return ret;
+	/* Device cannot simply be opened again from this state */
+	if (private->state == VFIO_CCW_STATE_NOT_OPER)
+		return -EINVAL;
 
 	ret = vfio_ccw_register_async_dev_regions(private);
 	if (ret)
-		goto out_unregister;
+		return ret;
 
 	ret = vfio_ccw_register_schib_dev_regions(private);
 	if (ret)
@@ -200,12 +184,16 @@ static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
 	if (ret)
 		goto out_unregister;
 
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_OPEN);
+	if (private->state == VFIO_CCW_STATE_NOT_OPER) {
+		ret = -EINVAL;
+		goto out_unregister;
+	}
+
 	return ret;
 
 out_unregister:
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY,
-				 &private->nb);
 	return ret;
 }
 
@@ -214,16 +202,8 @@ static void vfio_ccw_mdev_close_device(struct vfio_device *vdev)
 	struct vfio_ccw_private *private =
 		container_of(vdev, struct vfio_ccw_private, vdev);
 
-	if ((private->state != VFIO_CCW_STATE_NOT_OPER) &&
-	    (private->state != VFIO_CCW_STATE_STANDBY)) {
-		if (!vfio_ccw_mdev_reset(private))
-			private->state = VFIO_CCW_STATE_STANDBY;
-		/* The state will be NOT_OPER on error. */
-	}
-
-	cp_free(&private->cp);
+	vfio_ccw_fsm_event(private, VFIO_CCW_EVENT_CLOSE);
 	vfio_ccw_unregister_dev_regions(private);
-	vfio_unregister_notifier(vdev->dev, VFIO_IOMMU_NOTIFY, &private->nb);
 }
 
 static ssize_t vfio_ccw_mdev_read_io_region(struct vfio_ccw_private *private,
@@ -333,10 +313,12 @@ static int vfio_ccw_mdev_get_device_info(struct vfio_ccw_private *private,
 	return 0;
 }
 
-static int vfio_ccw_mdev_get_region_info(struct vfio_ccw_private *private,
-					 struct vfio_region_info *info,
-					 unsigned long arg)
+static int vfio_ccw_mdev_ioctl_get_region_info(struct vfio_device *vdev,
+					       struct vfio_region_info *info,
+					       struct vfio_info_cap *caps)
 {
+	struct vfio_ccw_private *private =
+		container_of(vdev, struct vfio_ccw_private, vdev);
 	int i;
 
 	switch (info->index) {
@@ -348,7 +330,6 @@ static int vfio_ccw_mdev_get_region_info(struct vfio_ccw_private *private,
 		return 0;
 	default: /* all other regions are handled via capability chain */
 	{
-		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
 		struct vfio_region_info_cap_type cap_type = {
 			.header.id = VFIO_REGION_INFO_CAP_TYPE,
 			.header.version = 1 };
@@ -371,27 +352,10 @@ static int vfio_ccw_mdev_get_region_info(struct vfio_ccw_private *private,
 		cap_type.type = private->region[i].type;
 		cap_type.subtype = private->region[i].subtype;
 
-		ret = vfio_info_add_capability(&caps, &cap_type.header,
+		ret = vfio_info_add_capability(caps, &cap_type.header,
 					       sizeof(cap_type));
 		if (ret)
 			return ret;
-
-		info->flags |= VFIO_REGION_INFO_FLAG_CAPS;
-		if (info->argsz < sizeof(*info) + caps.size) {
-			info->argsz = sizeof(*info) + caps.size;
-			info->cap_offset = 0;
-		} else {
-			vfio_info_cap_shift(&caps, sizeof(*info));
-			if (copy_to_user((void __user *)arg + sizeof(*info),
-					 caps.buf, caps.size)) {
-				kfree(caps.buf);
-				return -EFAULT;
-			}
-			info->cap_offset = sizeof(*info);
-		}
-
-		kfree(caps.buf);
-
 	}
 	}
 	return 0;
@@ -441,7 +405,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private,
 	case VFIO_IRQ_SET_DATA_NONE:
 	{
 		if (*ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 		return 0;
 	}
 	case VFIO_IRQ_SET_DATA_BOOL:
@@ -452,7 +416,7 @@ static int vfio_ccw_mdev_set_irqs(struct vfio_ccw_private *private,
 			return -EFAULT;
 
 		if (trigger && *ctx)
-			eventfd_signal(*ctx, 1);
+			eventfd_signal(*ctx);
 		return 0;
 	}
 	case VFIO_IRQ_SET_DATA_EVENTFD:
@@ -552,24 +516,6 @@ static ssize_t vfio_ccw_mdev_ioctl(struct vfio_device *vdev,
 
 		return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
 	}
-	case VFIO_DEVICE_GET_REGION_INFO:
-	{
-		struct vfio_region_info info;
-
-		minsz = offsetofend(struct vfio_region_info, offset);
-
-		if (copy_from_user(&info, (void __user *)arg, minsz))
-			return -EFAULT;
-
-		if (info.argsz < minsz)
-			return -EINVAL;
-
-		ret = vfio_ccw_mdev_get_region_info(private, &info, arg);
-		if (ret)
-			return ret;
-
-		return copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
-	}
 	case VFIO_DEVICE_GET_IRQ_INFO:
 	{
 		struct vfio_irq_info info;
@@ -632,7 +578,7 @@ static void vfio_ccw_mdev_request(struct vfio_device *vdev, unsigned int count)
 					       "Relaying device request to user (#%u)\n",
 					       count);
 
-		eventfd_signal(private->req_trigger, 1);
+		eventfd_signal(private->req_trigger);
 	} else if (count == 0) {
 		dev_notice(dev,
 			   "No device request channel registered, blocked until released by user\n");
@@ -640,15 +586,25 @@ 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,
 	.write = vfio_ccw_mdev_write,
 	.ioctl = vfio_ccw_mdev_ioctl,
+	.get_region_info_caps = vfio_ccw_mdev_ioctl_get_region_info,
 	.request = vfio_ccw_mdev_request,
+	.dma_unmap = vfio_ccw_dma_unmap,
+	.bind_iommufd = vfio_iommufd_emulated_bind,
+	.unbind_iommufd = vfio_iommufd_emulated_unbind,
+	.attach_ioas = vfio_iommufd_emulated_attach_ioas,
+	.detach_ioas = vfio_iommufd_emulated_detach_ioas,
 };
 
 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,
@@ -657,19 +613,3 @@ struct mdev_driver vfio_ccw_mdev_driver = {
 	.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,
-};
-
-int vfio_ccw_mdev_reg(struct subchannel *sch)
-{
-	return mdev_register_device(&sch->dev, &vfio_ccw_mdev_ops);
-}
-
-void vfio_ccw_mdev_unreg(struct subchannel *sch)
-{
-	mdev_unregister_device(&sch->dev);
-}