Adding upstream version 6.7.7.upstream/6.7.7

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

11 files changed, 1604 insertions, 277 deletions

diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile
index 8aeba8180..34b446146 100644
--- a/drivers/iommu/iommufd/Makefile
+++ b/drivers/iommu/iommufd/Makefile
@@ -11,3 +11,4 @@ iommufd-y := \
 iommufd-$(CONFIG_IOMMUFD_TEST) += selftest.o
 
 obj-$(CONFIG_IOMMUFD) += iommufd.o
+obj-$(CONFIG_IOMMUFD_DRIVER) += iova_bitmap.o
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index ce78c3671..873630c11 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -293,7 +293,7 @@ u32 iommufd_device_to_id(struct iommufd_device *idev)
 EXPORT_SYMBOL_NS_GPL(iommufd_device_to_id, IOMMUFD);
 
 static int iommufd_group_setup_msi(struct iommufd_group *igroup,
-				   struct iommufd_hw_pagetable *hwpt)
+				   struct iommufd_hwpt_paging *hwpt_paging)
 {
 	phys_addr_t sw_msi_start = igroup->sw_msi_start;
 	int rc;
@@ -311,8 +311,9 @@ static int iommufd_group_setup_msi(struct iommufd_group *igroup,
 	 * matches what the IRQ layer actually expects in a newly created
 	 * domain.
 	 */
-	if (sw_msi_start != PHYS_ADDR_MAX && !hwpt->msi_cookie) {
-		rc = iommu_get_msi_cookie(hwpt->domain, sw_msi_start);
+	if (sw_msi_start != PHYS_ADDR_MAX && !hwpt_paging->msi_cookie) {
+		rc = iommu_get_msi_cookie(hwpt_paging->common.domain,
+					  sw_msi_start);
 		if (rc)
 			return rc;
 
@@ -320,7 +321,31 @@ static int iommufd_group_setup_msi(struct iommufd_group *igroup,
 		 * iommu_get_msi_cookie() can only be called once per domain,
 		 * it returns -EBUSY on later calls.
 		 */
-		hwpt->msi_cookie = true;
+		hwpt_paging->msi_cookie = true;
+	}
+	return 0;
+}
+
+static int iommufd_hwpt_paging_attach(struct iommufd_hwpt_paging *hwpt_paging,
+				      struct iommufd_device *idev)
+{
+	int rc;
+
+	lockdep_assert_held(&idev->igroup->lock);
+
+	rc = iopt_table_enforce_dev_resv_regions(&hwpt_paging->ioas->iopt,
+						 idev->dev,
+						 &idev->igroup->sw_msi_start);
+	if (rc)
+		return rc;
+
+	if (list_empty(&idev->igroup->device_list)) {
+		rc = iommufd_group_setup_msi(idev->igroup, hwpt_paging);
+		if (rc) {
+			iopt_remove_reserved_iova(&hwpt_paging->ioas->iopt,
+						  idev->dev);
+			return rc;
+		}
 	}
 	return 0;
 }
@@ -337,18 +362,12 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 		goto err_unlock;
 	}
 
-	/* Try to upgrade the domain we have */
-	if (idev->enforce_cache_coherency) {
-		rc = iommufd_hw_pagetable_enforce_cc(hwpt);
+	if (hwpt_is_paging(hwpt)) {
+		rc = iommufd_hwpt_paging_attach(to_hwpt_paging(hwpt), idev);
 		if (rc)
 			goto err_unlock;
 	}
 
-	rc = iopt_table_enforce_dev_resv_regions(&hwpt->ioas->iopt, idev->dev,
-						 &idev->igroup->sw_msi_start);
-	if (rc)
-		goto err_unlock;
-
 	/*
 	 * Only attach to the group once for the first device that is in the
 	 * group. All the other devices will follow this attachment. The user
@@ -357,10 +376,6 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 	 * attachment.
 	 */
 	if (list_empty(&idev->igroup->device_list)) {
-		rc = iommufd_group_setup_msi(idev->igroup, hwpt);
-		if (rc)
-			goto err_unresv;
-
 		rc = iommu_attach_group(hwpt->domain, idev->igroup->group);
 		if (rc)
 			goto err_unresv;
@@ -371,7 +386,9 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 	mutex_unlock(&idev->igroup->lock);
 	return 0;
 err_unresv:
-	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
+	if (hwpt_is_paging(hwpt))
+		iopt_remove_reserved_iova(&to_hwpt_paging(hwpt)->ioas->iopt,
+					  idev->dev);
 err_unlock:
 	mutex_unlock(&idev->igroup->lock);
 	return rc;
@@ -388,7 +405,9 @@ iommufd_hw_pagetable_detach(struct iommufd_device *idev)
 		iommu_detach_group(hwpt->domain, idev->igroup->group);
 		idev->igroup->hwpt = NULL;
 	}
-	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
+	if (hwpt_is_paging(hwpt))
+		iopt_remove_reserved_iova(&to_hwpt_paging(hwpt)->ioas->iopt,
+					  idev->dev);
 	mutex_unlock(&idev->igroup->lock);
 
 	/* Caller must destroy hwpt */
@@ -407,14 +426,55 @@ iommufd_device_do_attach(struct iommufd_device *idev,
 	return NULL;
 }
 
+static void
+iommufd_group_remove_reserved_iova(struct iommufd_group *igroup,
+				   struct iommufd_hwpt_paging *hwpt_paging)
+{
+	struct iommufd_device *cur;
+
+	lockdep_assert_held(&igroup->lock);
+
+	list_for_each_entry(cur, &igroup->device_list, group_item)
+		iopt_remove_reserved_iova(&hwpt_paging->ioas->iopt, cur->dev);
+}
+
+static int
+iommufd_group_do_replace_paging(struct iommufd_group *igroup,
+				struct iommufd_hwpt_paging *hwpt_paging)
+{
+	struct iommufd_hw_pagetable *old_hwpt = igroup->hwpt;
+	struct iommufd_device *cur;
+	int rc;
+
+	lockdep_assert_held(&igroup->lock);
+
+	if (!hwpt_is_paging(old_hwpt) ||
+	    hwpt_paging->ioas != to_hwpt_paging(old_hwpt)->ioas) {
+		list_for_each_entry(cur, &igroup->device_list, group_item) {
+			rc = iopt_table_enforce_dev_resv_regions(
+				&hwpt_paging->ioas->iopt, cur->dev, NULL);
+			if (rc)
+				goto err_unresv;
+		}
+	}
+
+	rc = iommufd_group_setup_msi(igroup, hwpt_paging);
+	if (rc)
+		goto err_unresv;
+	return 0;
+
+err_unresv:
+	iommufd_group_remove_reserved_iova(igroup, hwpt_paging);
+	return rc;
+}
+
 static struct iommufd_hw_pagetable *
 iommufd_device_do_replace(struct iommufd_device *idev,
 			  struct iommufd_hw_pagetable *hwpt)
 {
 	struct iommufd_group *igroup = idev->igroup;
 	struct iommufd_hw_pagetable *old_hwpt;
-	unsigned int num_devices = 0;
-	struct iommufd_device *cur;
+	unsigned int num_devices;
 	int rc;
 
 	mutex_lock(&idev->igroup->lock);
@@ -429,42 +489,27 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 		return NULL;
 	}
 
-	/* Try to upgrade the domain we have */
-	list_for_each_entry(cur, &igroup->device_list, group_item) {
-		num_devices++;
-		if (cur->enforce_cache_coherency) {
-			rc = iommufd_hw_pagetable_enforce_cc(hwpt);
-			if (rc)
-				goto err_unlock;
-		}
-	}
-
 	old_hwpt = igroup->hwpt;
-	if (hwpt->ioas != old_hwpt->ioas) {
-		list_for_each_entry(cur, &igroup->device_list, group_item) {
-			rc = iopt_table_enforce_dev_resv_regions(
-				&hwpt->ioas->iopt, cur->dev, NULL);
-			if (rc)
-				goto err_unresv;
-		}
+	if (hwpt_is_paging(hwpt)) {
+		rc = iommufd_group_do_replace_paging(igroup,
+						     to_hwpt_paging(hwpt));
+		if (rc)
+			goto err_unlock;
 	}
 
-	rc = iommufd_group_setup_msi(idev->igroup, hwpt);
-	if (rc)
-		goto err_unresv;
-
 	rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
 	if (rc)
 		goto err_unresv;
 
-	if (hwpt->ioas != old_hwpt->ioas) {
-		list_for_each_entry(cur, &igroup->device_list, group_item)
-			iopt_remove_reserved_iova(&old_hwpt->ioas->iopt,
-						  cur->dev);
-	}
+	if (hwpt_is_paging(old_hwpt) &&
+	    (!hwpt_is_paging(hwpt) ||
+	     to_hwpt_paging(hwpt)->ioas != to_hwpt_paging(old_hwpt)->ioas))
+		iommufd_group_remove_reserved_iova(igroup,
+						   to_hwpt_paging(old_hwpt));
 
 	igroup->hwpt = hwpt;
 
+	num_devices = list_count_nodes(&igroup->device_list);
 	/*
 	 * Move the refcounts held by the device_list to the new hwpt. Retain a
 	 * refcount for this thread as the caller will free it.
@@ -478,8 +523,9 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 	/* Caller must destroy old_hwpt */
 	return old_hwpt;
 err_unresv:
-	list_for_each_entry(cur, &igroup->device_list, group_item)
-		iopt_remove_reserved_iova(&hwpt->ioas->iopt, cur->dev);
+	if (hwpt_is_paging(hwpt))
+		iommufd_group_remove_reserved_iova(igroup,
+						   to_hwpt_paging(old_hwpt));
 err_unlock:
 	mutex_unlock(&idev->igroup->lock);
 	return ERR_PTR(rc);
@@ -507,6 +553,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 	 */
 	bool immediate_attach = do_attach == iommufd_device_do_attach;
 	struct iommufd_hw_pagetable *destroy_hwpt;
+	struct iommufd_hwpt_paging *hwpt_paging;
 	struct iommufd_hw_pagetable *hwpt;
 
 	/*
@@ -515,15 +562,16 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 	 * other.
 	 */
 	mutex_lock(&ioas->mutex);
-	list_for_each_entry(hwpt, &ioas->hwpt_list, hwpt_item) {
-		if (!hwpt->auto_domain)
+	list_for_each_entry(hwpt_paging, &ioas->hwpt_list, hwpt_item) {
+		if (!hwpt_paging->auto_domain)
 			continue;
 
+		hwpt = &hwpt_paging->common;
 		if (!iommufd_lock_obj(&hwpt->obj))
 			continue;
 		destroy_hwpt = (*do_attach)(idev, hwpt);
 		if (IS_ERR(destroy_hwpt)) {
-			iommufd_put_object(&hwpt->obj);
+			iommufd_put_object(idev->ictx, &hwpt->obj);
 			/*
 			 * -EINVAL means the domain is incompatible with the
 			 * device. Other error codes should propagate to
@@ -535,16 +583,17 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 			goto out_unlock;
 		}
 		*pt_id = hwpt->obj.id;
-		iommufd_put_object(&hwpt->obj);
+		iommufd_put_object(idev->ictx, &hwpt->obj);
 		goto out_unlock;
 	}
 
-	hwpt = iommufd_hw_pagetable_alloc(idev->ictx, ioas, idev,
-					  immediate_attach);
-	if (IS_ERR(hwpt)) {
-		destroy_hwpt = ERR_CAST(hwpt);
+	hwpt_paging = iommufd_hwpt_paging_alloc(idev->ictx, ioas, idev, 0,
+						immediate_attach, NULL);
+	if (IS_ERR(hwpt_paging)) {
+		destroy_hwpt = ERR_CAST(hwpt_paging);
 		goto out_unlock;
 	}
+	hwpt = &hwpt_paging->common;
 
 	if (!immediate_attach) {
 		destroy_hwpt = (*do_attach)(idev, hwpt);
@@ -554,7 +603,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 		destroy_hwpt = NULL;
 	}
 
-	hwpt->auto_domain = true;
+	hwpt_paging->auto_domain = true;
 	*pt_id = hwpt->obj.id;
 
 	iommufd_object_finalize(idev->ictx, &hwpt->obj);
@@ -579,7 +628,8 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 		return PTR_ERR(pt_obj);
 
 	switch (pt_obj->type) {
-	case IOMMUFD_OBJ_HW_PAGETABLE: {
+	case IOMMUFD_OBJ_HWPT_NESTED:
+	case IOMMUFD_OBJ_HWPT_PAGING: {
 		struct iommufd_hw_pagetable *hwpt =
 			container_of(pt_obj, struct iommufd_hw_pagetable, obj);
 
@@ -602,7 +652,7 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 		destroy_hwpt = ERR_PTR(-EINVAL);
 		goto out_put_pt_obj;
 	}
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(idev->ictx, pt_obj);
 
 	/* This destruction has to be after we unlock everything */
 	if (destroy_hwpt)
@@ -610,15 +660,15 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 	return 0;
 
 out_put_pt_obj:
-	iommufd_put_object(pt_obj);
+	iommufd_put_object(idev->ictx, pt_obj);
 	return PTR_ERR(destroy_hwpt);
 }
 
 /**
  * iommufd_device_attach - Connect a device to an iommu_domain
  * @idev: device to attach
- * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
- *         Output the IOMMUFD_OBJ_HW_PAGETABLE ID
+ * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HWPT_PAGING
+ *         Output the IOMMUFD_OBJ_HWPT_PAGING ID
  *
  * This connects the device to an iommu_domain, either automatically or manually
  * selected. Once this completes the device could do DMA.
@@ -646,8 +696,8 @@ EXPORT_SYMBOL_NS_GPL(iommufd_device_attach, IOMMUFD);
 /**
  * iommufd_device_replace - Change the device's iommu_domain
  * @idev: device to change
- * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
- *         Output the IOMMUFD_OBJ_HW_PAGETABLE ID
+ * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HWPT_PAGING
+ *         Output the IOMMUFD_OBJ_HWPT_PAGING ID
  *
  * This is the same as::
  *
@@ -742,7 +792,7 @@ static int iommufd_access_change_ioas_id(struct iommufd_access *access, u32 id)
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 	rc = iommufd_access_change_ioas(access, ioas);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(access->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -891,7 +941,7 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
 
 		access->ops->unmap(access->data, iova, length);
 
-		iommufd_put_object(&access->obj);
+		iommufd_put_object(access->ictx, &access->obj);
 		xa_lock(&ioas->iopt.access_list);
 	}
 	xa_unlock(&ioas->iopt.access_list);
@@ -1185,10 +1235,14 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 	 */
 	cmd->data_len = data_len;
 
+	cmd->out_capabilities = 0;
+	if (device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING))
+		cmd->out_capabilities |= IOMMU_HW_CAP_DIRTY_TRACKING;
+
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_free:
 	kfree(data);
 out_put:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index cf2c1504e..6f680959b 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -5,62 +5,87 @@
 #include <linux/iommu.h>
 #include <uapi/linux/iommufd.h>
 
+#include "../iommu-priv.h"
 #include "iommufd_private.h"
 
-void iommufd_hw_pagetable_destroy(struct iommufd_object *obj)
+void iommufd_hwpt_paging_destroy(struct iommufd_object *obj)
 {
-	struct iommufd_hw_pagetable *hwpt =
-		container_of(obj, struct iommufd_hw_pagetable, obj);
+	struct iommufd_hwpt_paging *hwpt_paging =
+		container_of(obj, struct iommufd_hwpt_paging, common.obj);
 
-	if (!list_empty(&hwpt->hwpt_item)) {
-		mutex_lock(&hwpt->ioas->mutex);
-		list_del(&hwpt->hwpt_item);
-		mutex_unlock(&hwpt->ioas->mutex);
+	if (!list_empty(&hwpt_paging->hwpt_item)) {
+		mutex_lock(&hwpt_paging->ioas->mutex);
+		list_del(&hwpt_paging->hwpt_item);
+		mutex_unlock(&hwpt_paging->ioas->mutex);
 
-		iopt_table_remove_domain(&hwpt->ioas->iopt, hwpt->domain);
+		iopt_table_remove_domain(&hwpt_paging->ioas->iopt,
+					 hwpt_paging->common.domain);
 	}
 
-	if (hwpt->domain)
-		iommu_domain_free(hwpt->domain);
+	if (hwpt_paging->common.domain)
+		iommu_domain_free(hwpt_paging->common.domain);
 
-	refcount_dec(&hwpt->ioas->obj.users);
+	refcount_dec(&hwpt_paging->ioas->obj.users);
 }
 
-void iommufd_hw_pagetable_abort(struct iommufd_object *obj)
+void iommufd_hwpt_paging_abort(struct iommufd_object *obj)
 {
-	struct iommufd_hw_pagetable *hwpt =
-		container_of(obj, struct iommufd_hw_pagetable, obj);
+	struct iommufd_hwpt_paging *hwpt_paging =
+		container_of(obj, struct iommufd_hwpt_paging, common.obj);
 
 	/* The ioas->mutex must be held until finalize is called. */
-	lockdep_assert_held(&hwpt->ioas->mutex);
+	lockdep_assert_held(&hwpt_paging->ioas->mutex);
 
-	if (!list_empty(&hwpt->hwpt_item)) {
-		list_del_init(&hwpt->hwpt_item);
-		iopt_table_remove_domain(&hwpt->ioas->iopt, hwpt->domain);
+	if (!list_empty(&hwpt_paging->hwpt_item)) {
+		list_del_init(&hwpt_paging->hwpt_item);
+		iopt_table_remove_domain(&hwpt_paging->ioas->iopt,
+					 hwpt_paging->common.domain);
 	}
-	iommufd_hw_pagetable_destroy(obj);
+	iommufd_hwpt_paging_destroy(obj);
 }
 
-int iommufd_hw_pagetable_enforce_cc(struct iommufd_hw_pagetable *hwpt)
+void iommufd_hwpt_nested_destroy(struct iommufd_object *obj)
 {
-	if (hwpt->enforce_cache_coherency)
+	struct iommufd_hwpt_nested *hwpt_nested =
+		container_of(obj, struct iommufd_hwpt_nested, common.obj);
+
+	if (hwpt_nested->common.domain)
+		iommu_domain_free(hwpt_nested->common.domain);
+
+	refcount_dec(&hwpt_nested->parent->common.obj.users);
+}
+
+void iommufd_hwpt_nested_abort(struct iommufd_object *obj)
+{
+	iommufd_hwpt_nested_destroy(obj);
+}
+
+static int
+iommufd_hwpt_paging_enforce_cc(struct iommufd_hwpt_paging *hwpt_paging)
+{
+	struct iommu_domain *paging_domain = hwpt_paging->common.domain;
+
+	if (hwpt_paging->enforce_cache_coherency)
 		return 0;
 
-	if (hwpt->domain->ops->enforce_cache_coherency)
-		hwpt->enforce_cache_coherency =
-			hwpt->domain->ops->enforce_cache_coherency(
-				hwpt->domain);
-	if (!hwpt->enforce_cache_coherency)
+	if (paging_domain->ops->enforce_cache_coherency)
+		hwpt_paging->enforce_cache_coherency =
+			paging_domain->ops->enforce_cache_coherency(
+				paging_domain);
+	if (!hwpt_paging->enforce_cache_coherency)
 		return -EINVAL;
 	return 0;
 }
 
 /**
- * iommufd_hw_pagetable_alloc() - Get an iommu_domain for a device
+ * iommufd_hwpt_paging_alloc() - Get a PAGING iommu_domain for a device
  * @ictx: iommufd context
  * @ioas: IOAS to associate the domain with
  * @idev: Device to get an iommu_domain for
+ * @flags: Flags from userspace
  * @immediate_attach: True if idev should be attached to the hwpt
+ * @user_data: The user provided driver specific data describing the domain to
+ *             create
  *
  * Allocate a new iommu_domain and return it as a hw_pagetable. The HWPT
  * will be linked to the given ioas and upon return the underlying iommu_domain
@@ -70,28 +95,52 @@ int iommufd_hw_pagetable_enforce_cc(struct iommufd_hw_pagetable *hwpt)
  * iommufd_object_abort_and_destroy() or iommufd_object_finalize() is called on
  * the returned hwpt.
  */
-struct iommufd_hw_pagetable *
-iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
-			   struct iommufd_device *idev, bool immediate_attach)
+struct iommufd_hwpt_paging *
+iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
+			  struct iommufd_device *idev, u32 flags,
+			  bool immediate_attach,
+			  const struct iommu_user_data *user_data)
 {
+	const u32 valid_flags = IOMMU_HWPT_ALLOC_NEST_PARENT |
+				IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+	const struct iommu_ops *ops = dev_iommu_ops(idev->dev);
+	struct iommufd_hwpt_paging *hwpt_paging;
 	struct iommufd_hw_pagetable *hwpt;
 	int rc;
 
 	lockdep_assert_held(&ioas->mutex);
 
-	hwpt = iommufd_object_alloc(ictx, hwpt, IOMMUFD_OBJ_HW_PAGETABLE);
-	if (IS_ERR(hwpt))
-		return hwpt;
+	if ((flags || user_data) && !ops->domain_alloc_user)
+		return ERR_PTR(-EOPNOTSUPP);
+	if (flags & ~valid_flags)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	hwpt_paging = __iommufd_object_alloc(
+		ictx, hwpt_paging, IOMMUFD_OBJ_HWPT_PAGING, common.obj);
+	if (IS_ERR(hwpt_paging))
+		return ERR_CAST(hwpt_paging);
+	hwpt = &hwpt_paging->common;
 
-	INIT_LIST_HEAD(&hwpt->hwpt_item);
+	INIT_LIST_HEAD(&hwpt_paging->hwpt_item);
 	/* Pairs with iommufd_hw_pagetable_destroy() */
 	refcount_inc(&ioas->obj.users);
-	hwpt->ioas = ioas;
+	hwpt_paging->ioas = ioas;
+	hwpt_paging->nest_parent = flags & IOMMU_HWPT_ALLOC_NEST_PARENT;
 
-	hwpt->domain = iommu_domain_alloc(idev->dev->bus);
-	if (!hwpt->domain) {
-		rc = -ENOMEM;
-		goto out_abort;
+	if (ops->domain_alloc_user) {
+		hwpt->domain = ops->domain_alloc_user(idev->dev, flags, NULL,
+						      user_data);
+		if (IS_ERR(hwpt->domain)) {
+			rc = PTR_ERR(hwpt->domain);
+			hwpt->domain = NULL;
+			goto out_abort;
+		}
+	} else {
+		hwpt->domain = iommu_domain_alloc(idev->dev->bus);
+		if (!hwpt->domain) {
+			rc = -ENOMEM;
+			goto out_abort;
+		}
 	}
 
 	/*
@@ -100,9 +149,16 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 	 * doing any maps. It is an iommu driver bug to report
 	 * IOMMU_CAP_ENFORCE_CACHE_COHERENCY but fail enforce_cache_coherency on
 	 * a new domain.
+	 *
+	 * The cache coherency mode must be configured here and unchanged later.
+	 * Note that a HWPT (non-CC) created for a device (non-CC) can be later
+	 * reused by another device (either non-CC or CC). However, A HWPT (CC)
+	 * created for a device (CC) cannot be reused by another device (non-CC)
+	 * but only devices (CC). Instead user space in this case would need to
+	 * allocate a separate HWPT (non-CC).
 	 */
 	if (idev->enforce_cache_coherency) {
-		rc = iommufd_hw_pagetable_enforce_cc(hwpt);
+		rc = iommufd_hwpt_paging_enforce_cc(hwpt_paging);
 		if (WARN_ON(rc))
 			goto out_abort;
 	}
@@ -119,11 +175,11 @@ iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			goto out_abort;
 	}
 
-	rc = iopt_table_add_domain(&hwpt->ioas->iopt, hwpt->domain);
+	rc = iopt_table_add_domain(&ioas->iopt, hwpt->domain);
 	if (rc)
 		goto out_detach;
-	list_add_tail(&hwpt->hwpt_item, &hwpt->ioas->hwpt_list);
-	return hwpt;
+	list_add_tail(&hwpt_paging->hwpt_item, &ioas->hwpt_list);
+	return hwpt_paging;
 
 out_detach:
 	if (immediate_attach)
@@ -133,32 +189,121 @@ out_abort:
 	return ERR_PTR(rc);
 }
 
+/**
+ * iommufd_hwpt_nested_alloc() - Get a NESTED iommu_domain for a device
+ * @ictx: iommufd context
+ * @parent: Parent PAGING-type hwpt to associate the domain with
+ * @idev: Device to get an iommu_domain for
+ * @flags: Flags from userspace
+ * @user_data: user_data pointer. Must be valid
+ *
+ * Allocate a new iommu_domain (must be IOMMU_DOMAIN_NESTED) and return it as
+ * a NESTED hw_pagetable. The given parent PAGING-type hwpt must be capable of
+ * being a parent.
+ */
+static struct iommufd_hwpt_nested *
+iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
+			  struct iommufd_hwpt_paging *parent,
+			  struct iommufd_device *idev, u32 flags,
+			  const struct iommu_user_data *user_data)
+{
+	const struct iommu_ops *ops = dev_iommu_ops(idev->dev);
+	struct iommufd_hwpt_nested *hwpt_nested;
+	struct iommufd_hw_pagetable *hwpt;
+	int rc;
+
+	if (flags || !user_data->len || !ops->domain_alloc_user)
+		return ERR_PTR(-EOPNOTSUPP);
+	if (parent->auto_domain || !parent->nest_parent)
+		return ERR_PTR(-EINVAL);
+
+	hwpt_nested = __iommufd_object_alloc(
+		ictx, hwpt_nested, IOMMUFD_OBJ_HWPT_NESTED, common.obj);
+	if (IS_ERR(hwpt_nested))
+		return ERR_CAST(hwpt_nested);
+	hwpt = &hwpt_nested->common;
+
+	refcount_inc(&parent->common.obj.users);
+	hwpt_nested->parent = parent;
+
+	hwpt->domain = ops->domain_alloc_user(idev->dev, flags,
+					      parent->common.domain, user_data);
+	if (IS_ERR(hwpt->domain)) {
+		rc = PTR_ERR(hwpt->domain);
+		hwpt->domain = NULL;
+		goto out_abort;
+	}
+
+	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
+		rc = -EINVAL;
+		goto out_abort;
+	}
+	return hwpt_nested;
+
+out_abort:
+	iommufd_object_abort_and_destroy(ictx, &hwpt->obj);
+	return ERR_PTR(rc);
+}
+
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_hwpt_alloc *cmd = ucmd->cmd;
+	const struct iommu_user_data user_data = {
+		.type = cmd->data_type,
+		.uptr = u64_to_user_ptr(cmd->data_uptr),
+		.len = cmd->data_len,
+	};
 	struct iommufd_hw_pagetable *hwpt;
+	struct iommufd_ioas *ioas = NULL;
+	struct iommufd_object *pt_obj;
 	struct iommufd_device *idev;
-	struct iommufd_ioas *ioas;
 	int rc;
 
-	if (cmd->flags || cmd->__reserved)
+	if (cmd->__reserved)
 		return -EOPNOTSUPP;
+	if ((cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len) ||
+	    (cmd->data_type != IOMMU_HWPT_DATA_NONE && !cmd->data_len))
+		return -EINVAL;
 
 	idev = iommufd_get_device(ucmd, cmd->dev_id);
 	if (IS_ERR(idev))
 		return PTR_ERR(idev);
 
-	ioas = iommufd_get_ioas(ucmd->ictx, cmd->pt_id);
-	if (IS_ERR(ioas)) {
-		rc = PTR_ERR(ioas);
+	pt_obj = iommufd_get_object(ucmd->ictx, cmd->pt_id, IOMMUFD_OBJ_ANY);
+	if (IS_ERR(pt_obj)) {
+		rc = -EINVAL;
 		goto out_put_idev;
 	}
 
-	mutex_lock(&ioas->mutex);
-	hwpt = iommufd_hw_pagetable_alloc(ucmd->ictx, ioas, idev, false);
-	if (IS_ERR(hwpt)) {
-		rc = PTR_ERR(hwpt);
-		goto out_unlock;
+	if (pt_obj->type == IOMMUFD_OBJ_IOAS) {
+		struct iommufd_hwpt_paging *hwpt_paging;
+
+		ioas = container_of(pt_obj, struct iommufd_ioas, obj);
+		mutex_lock(&ioas->mutex);
+		hwpt_paging = iommufd_hwpt_paging_alloc(
+			ucmd->ictx, ioas, idev, cmd->flags, false,
+			user_data.len ? &user_data : NULL);
+		if (IS_ERR(hwpt_paging)) {
+			rc = PTR_ERR(hwpt_paging);
+			goto out_unlock;
+		}
+		hwpt = &hwpt_paging->common;
+	} else if (pt_obj->type == IOMMUFD_OBJ_HWPT_PAGING) {
+		struct iommufd_hwpt_nested *hwpt_nested;
+
+		hwpt_nested = iommufd_hwpt_nested_alloc(
+			ucmd->ictx,
+			container_of(pt_obj, struct iommufd_hwpt_paging,
+				     common.obj),
+			idev, cmd->flags, &user_data);
+		if (IS_ERR(hwpt_nested)) {
+			rc = PTR_ERR(hwpt_nested);
+			goto out_unlock;
+		}
+		hwpt = &hwpt_nested->common;
+	} else {
+		rc = -EINVAL;
+		goto out_put_pt;
 	}
 
 	cmd->out_hwpt_id = hwpt->obj.id;
@@ -171,9 +316,59 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 out_hwpt:
 	iommufd_object_abort_and_destroy(ucmd->ictx, &hwpt->obj);
 out_unlock:
-	mutex_unlock(&ioas->mutex);
-	iommufd_put_object(&ioas->obj);
+	if (ioas)
+		mutex_unlock(&ioas->mutex);
+out_put_pt:
+	iommufd_put_object(ucmd->ictx, pt_obj);
 out_put_idev:
-	iommufd_put_object(&idev->obj);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
+	return rc;
+}
+
+int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_set_dirty_tracking *cmd = ucmd->cmd;
+	struct iommufd_hwpt_paging *hwpt_paging;
+	struct iommufd_ioas *ioas;
+	int rc = -EOPNOTSUPP;
+	bool enable;
+
+	if (cmd->flags & ~IOMMU_HWPT_DIRTY_TRACKING_ENABLE)
+		return rc;
+
+	hwpt_paging = iommufd_get_hwpt_paging(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt_paging))
+		return PTR_ERR(hwpt_paging);
+
+	ioas = hwpt_paging->ioas;
+	enable = cmd->flags & IOMMU_HWPT_DIRTY_TRACKING_ENABLE;
+
+	rc = iopt_set_dirty_tracking(&ioas->iopt, hwpt_paging->common.domain,
+				     enable);
+
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
+	return rc;
+}
+
+int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hwpt_get_dirty_bitmap *cmd = ucmd->cmd;
+	struct iommufd_hwpt_paging *hwpt_paging;
+	struct iommufd_ioas *ioas;
+	int rc = -EOPNOTSUPP;
+
+	if ((cmd->flags & ~(IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR)) ||
+	    cmd->__reserved)
+		return -EOPNOTSUPP;
+
+	hwpt_paging = iommufd_get_hwpt_paging(ucmd, cmd->hwpt_id);
+	if (IS_ERR(hwpt_paging))
+		return PTR_ERR(hwpt_paging);
+
+	ioas = hwpt_paging->ioas;
+	rc = iopt_read_and_clear_dirty_data(
+		&ioas->iopt, hwpt_paging->common.domain, cmd->flags, cmd);
+
+	iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 117a39ae2..504ac1b01 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -15,6 +15,7 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
+#include <uapi/linux/iommufd.h>
 
 #include "io_pagetable.h"
 #include "double_span.h"
@@ -424,6 +425,177 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt,
 	return 0;
 }
 
+struct iova_bitmap_fn_arg {
+	unsigned long flags;
+	struct io_pagetable *iopt;
+	struct iommu_domain *domain;
+	struct iommu_dirty_bitmap *dirty;
+};
+
+static int __iommu_read_and_clear_dirty(struct iova_bitmap *bitmap,
+					unsigned long iova, size_t length,
+					void *opaque)
+{
+	struct iopt_area *area;
+	struct iopt_area_contig_iter iter;
+	struct iova_bitmap_fn_arg *arg = opaque;
+	struct iommu_domain *domain = arg->domain;
+	struct iommu_dirty_bitmap *dirty = arg->dirty;
+	const struct iommu_dirty_ops *ops = domain->dirty_ops;
+	unsigned long last_iova = iova + length - 1;
+	unsigned long flags = arg->flags;
+	int ret;
+
+	iopt_for_each_contig_area(&iter, area, arg->iopt, iova, last_iova) {
+		unsigned long last = min(last_iova, iopt_area_last_iova(area));
+
+		ret = ops->read_and_clear_dirty(domain, iter.cur_iova,
+						last - iter.cur_iova + 1, flags,
+						dirty);
+		if (ret)
+			return ret;
+	}
+
+	if (!iopt_area_contig_done(&iter))
+		return -EINVAL;
+	return 0;
+}
+
+static int
+iommu_read_and_clear_dirty(struct iommu_domain *domain,
+			   struct io_pagetable *iopt, unsigned long flags,
+			   struct iommu_hwpt_get_dirty_bitmap *bitmap)
+{
+	const struct iommu_dirty_ops *ops = domain->dirty_ops;
+	struct iommu_iotlb_gather gather;
+	struct iommu_dirty_bitmap dirty;
+	struct iova_bitmap_fn_arg arg;
+	struct iova_bitmap *iter;
+	int ret = 0;
+
+	if (!ops || !ops->read_and_clear_dirty)
+		return -EOPNOTSUPP;
+
+	iter = iova_bitmap_alloc(bitmap->iova, bitmap->length,
+				 bitmap->page_size,
+				 u64_to_user_ptr(bitmap->data));
+	if (IS_ERR(iter))
+		return -ENOMEM;
+
+	iommu_dirty_bitmap_init(&dirty, iter, &gather);
+
+	arg.flags = flags;
+	arg.iopt = iopt;
+	arg.domain = domain;
+	arg.dirty = &dirty;
+	iova_bitmap_for_each(iter, &arg, __iommu_read_and_clear_dirty);
+
+	if (!(flags & IOMMU_DIRTY_NO_CLEAR))
+		iommu_iotlb_sync(domain, &gather);
+
+	iova_bitmap_free(iter);
+
+	return ret;
+}
+
+int iommufd_check_iova_range(struct io_pagetable *iopt,
+			     struct iommu_hwpt_get_dirty_bitmap *bitmap)
+{
+	size_t iommu_pgsize = iopt->iova_alignment;
+	u64 last_iova;
+
+	if (check_add_overflow(bitmap->iova, bitmap->length - 1, &last_iova))
+		return -EOVERFLOW;
+
+	if (bitmap->iova > ULONG_MAX || last_iova > ULONG_MAX)
+		return -EOVERFLOW;
+
+	if ((bitmap->iova & (iommu_pgsize - 1)) ||
+	    ((last_iova + 1) & (iommu_pgsize - 1)))
+		return -EINVAL;
+
+	if (!bitmap->page_size)
+		return -EINVAL;
+
+	if ((bitmap->iova & (bitmap->page_size - 1)) ||
+	    ((last_iova + 1) & (bitmap->page_size - 1)))
+		return -EINVAL;
+
+	return 0;
+}
+
+int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt,
+				   struct iommu_domain *domain,
+				   unsigned long flags,
+				   struct iommu_hwpt_get_dirty_bitmap *bitmap)
+{
+	int ret;
+
+	ret = iommufd_check_iova_range(iopt, bitmap);
+	if (ret)
+		return ret;
+
+	down_read(&iopt->iova_rwsem);
+	ret = iommu_read_and_clear_dirty(domain, iopt, flags, bitmap);
+	up_read(&iopt->iova_rwsem);
+
+	return ret;
+}
+
+static int iopt_clear_dirty_data(struct io_pagetable *iopt,
+				 struct iommu_domain *domain)
+{
+	const struct iommu_dirty_ops *ops = domain->dirty_ops;
+	struct iommu_iotlb_gather gather;
+	struct iommu_dirty_bitmap dirty;
+	struct iopt_area *area;
+	int ret = 0;
+
+	lockdep_assert_held_read(&iopt->iova_rwsem);
+
+	iommu_dirty_bitmap_init(&dirty, NULL, &gather);
+
+	for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area;
+	     area = iopt_area_iter_next(area, 0, ULONG_MAX)) {
+		if (!area->pages)
+			continue;
+
+		ret = ops->read_and_clear_dirty(domain, iopt_area_iova(area),
+						iopt_area_length(area), 0,
+						&dirty);
+		if (ret)
+			break;
+	}
+
+	iommu_iotlb_sync(domain, &gather);
+	return ret;
+}
+
+int iopt_set_dirty_tracking(struct io_pagetable *iopt,
+			    struct iommu_domain *domain, bool enable)
+{
+	const struct iommu_dirty_ops *ops = domain->dirty_ops;
+	int ret = 0;
+
+	if (!ops)
+		return -EOPNOTSUPP;
+
+	down_read(&iopt->iova_rwsem);
+
+	/* Clear dirty bits from PTEs to ensure a clean snapshot */
+	if (enable) {
+		ret = iopt_clear_dirty_data(iopt, domain);
+		if (ret)
+			goto out_unlock;
+	}
+
+	ret = ops->set_dirty_tracking(domain, enable);
+
+out_unlock:
+	up_read(&iopt->iova_rwsem);
+	return ret;
+}
+
 int iopt_get_pages(struct io_pagetable *iopt, unsigned long iova,
 		   unsigned long length, struct list_head *pages_list)
 {
diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c
index d5624577f..742248276 100644
--- a/drivers/iommu/iommufd/ioas.c
+++ b/drivers/iommu/iommufd/ioas.c
@@ -105,7 +105,7 @@ int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd)
 		rc = -EMSGSIZE;
 out_put:
 	up_read(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -175,7 +175,7 @@ out_free:
 		interval_tree_remove(node, &allowed_iova);
 		kfree(container_of(node, struct iopt_allowed, node));
 	}
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -228,7 +228,7 @@ int iommufd_ioas_map(struct iommufd_ucmd *ucmd)
 	cmd->iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -258,7 +258,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 		return PTR_ERR(src_ioas);
 	rc = iopt_get_pages(&src_ioas->iopt, cmd->src_iova, cmd->length,
 			    &pages_list);
-	iommufd_put_object(&src_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &src_ioas->obj);
 	if (rc)
 		return rc;
 
@@ -279,7 +279,7 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
 	cmd->dst_iova = iova;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_put_dst:
-	iommufd_put_object(&dst_ioas->obj);
+	iommufd_put_object(ucmd->ictx, &dst_ioas->obj);
 out_pages:
 	iopt_free_pages_list(&pages_list);
 	return rc;
@@ -315,7 +315,7 @@ int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd)
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -393,6 +393,6 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd)
 		rc = -EOPNOTSUPP;
 	}
 
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 2c5867001..abae041e2 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -8,6 +8,9 @@
 #include <linux/xarray.h>
 #include <linux/refcount.h>
 #include <linux/uaccess.h>
+#include <linux/iommu.h>
+#include <linux/iova_bitmap.h>
+#include <uapi/linux/iommufd.h>
 
 struct iommu_domain;
 struct iommu_group;
@@ -18,6 +21,7 @@ struct iommufd_ctx {
 	struct file *file;
 	struct xarray objects;
 	struct xarray groups;
+	wait_queue_head_t destroy_wait;
 
 	u8 account_mode;
 	/* Compatibility with VFIO no iommu */
@@ -70,6 +74,13 @@ int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova,
 		    unsigned long length, unsigned long *unmapped);
 int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped);
 
+int iopt_read_and_clear_dirty_data(struct io_pagetable *iopt,
+				   struct iommu_domain *domain,
+				   unsigned long flags,
+				   struct iommu_hwpt_get_dirty_bitmap *bitmap);
+int iopt_set_dirty_tracking(struct io_pagetable *iopt,
+			    struct iommu_domain *domain, bool enable);
+
 void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
 				 unsigned long length);
 int iopt_table_add_domain(struct io_pagetable *iopt,
@@ -113,7 +124,8 @@ enum iommufd_object_type {
 	IOMMUFD_OBJ_NONE,
 	IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE,
 	IOMMUFD_OBJ_DEVICE,
-	IOMMUFD_OBJ_HW_PAGETABLE,
+	IOMMUFD_OBJ_HWPT_PAGING,
+	IOMMUFD_OBJ_HWPT_NESTED,
 	IOMMUFD_OBJ_IOAS,
 	IOMMUFD_OBJ_ACCESS,
 #ifdef CONFIG_IOMMUFD_TEST
@@ -124,7 +136,7 @@ enum iommufd_object_type {
 
 /* Base struct for all objects with a userspace ID handle. */
 struct iommufd_object {
-	struct rw_semaphore destroy_rwsem;
+	refcount_t shortterm_users;
 	refcount_t users;
 	enum iommufd_object_type type;
 	unsigned int id;
@@ -132,10 +144,15 @@ struct iommufd_object {
 
 static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 {
-	if (!down_read_trylock(&obj->destroy_rwsem))
+	if (!refcount_inc_not_zero(&obj->users))
 		return false;
-	if (!refcount_inc_not_zero(&obj->users)) {
-		up_read(&obj->destroy_rwsem);
+	if (!refcount_inc_not_zero(&obj->shortterm_users)) {
+		/*
+		 * If the caller doesn't already have a ref on obj this must be
+		 * called under the xa_lock. Otherwise the caller is holding a
+		 * ref on users. Thus it cannot be one before this decrement.
+		 */
+		refcount_dec(&obj->users);
 		return false;
 	}
 	return true;
@@ -143,10 +160,16 @@ static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 
 struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 					  enum iommufd_object_type type);
-static inline void iommufd_put_object(struct iommufd_object *obj)
+static inline void iommufd_put_object(struct iommufd_ctx *ictx,
+				      struct iommufd_object *obj)
 {
+	/*
+	 * Users first, then shortterm so that REMOVE_WAIT_SHORTTERM never sees
+	 * a spurious !0 users with a 0 shortterm_users.
+	 */
 	refcount_dec(&obj->users);
-	up_read(&obj->destroy_rwsem);
+	if (refcount_dec_and_test(&obj->shortterm_users))
+		wake_up_interruptible_all(&ictx->destroy_wait);
 }
 
 void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj);
@@ -154,24 +177,56 @@ void iommufd_object_abort_and_destroy(struct iommufd_ctx *ictx,
 				      struct iommufd_object *obj);
 void iommufd_object_finalize(struct iommufd_ctx *ictx,
 			     struct iommufd_object *obj);
-void __iommufd_object_destroy_user(struct iommufd_ctx *ictx,
-				   struct iommufd_object *obj, bool allow_fail);
+
+enum {
+	REMOVE_WAIT_SHORTTERM = 1,
+};
+int iommufd_object_remove(struct iommufd_ctx *ictx,
+			  struct iommufd_object *to_destroy, u32 id,
+			  unsigned int flags);
+
+/*
+ * The caller holds a users refcount and wants to destroy the object. At this
+ * point the caller has no shortterm_users reference and at least the xarray
+ * will be holding one.
+ */
 static inline void iommufd_object_destroy_user(struct iommufd_ctx *ictx,
 					       struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, false);
+	int ret;
+
+	ret = iommufd_object_remove(ictx, obj, obj->id, REMOVE_WAIT_SHORTTERM);
+
+	/*
+	 * If there is a bug and we couldn't destroy the object then we did put
+	 * back the caller's users refcount and will eventually try to free it
+	 * again during close.
+	 */
+	WARN_ON(ret);
 }
-static inline void iommufd_object_deref_user(struct iommufd_ctx *ictx,
-					     struct iommufd_object *obj)
+
+/*
+ * The HWPT allocated by autodomains is used in possibly many devices and
+ * is automatically destroyed when its refcount reaches zero.
+ *
+ * If userspace uses the HWPT manually, even for a short term, then it will
+ * disrupt this refcounting and the auto-free in the kernel will not work.
+ * Userspace that tries to use the automatically allocated HWPT must be careful
+ * to ensure that it is consistently destroyed, eg by not racing accesses
+ * and by not attaching an automatic HWPT to a device manually.
+ */
+static inline void
+iommufd_object_put_and_try_destroy(struct iommufd_ctx *ictx,
+				   struct iommufd_object *obj)
 {
-	__iommufd_object_destroy_user(ictx, obj, true);
+	iommufd_object_remove(ictx, obj, obj->id, 0);
 }
 
 struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     size_t size,
 					     enum iommufd_object_type type);
 
-#define iommufd_object_alloc(ictx, ptr, type)                                  \
+#define __iommufd_object_alloc(ictx, ptr, type, obj)                           \
 	container_of(_iommufd_object_alloc(                                    \
 			     ictx,                                             \
 			     sizeof(*(ptr)) + BUILD_BUG_ON_ZERO(               \
@@ -180,6 +235,9 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 			     type),                                            \
 		     typeof(*(ptr)), obj)
 
+#define iommufd_object_alloc(ictx, ptr, type) \
+	__iommufd_object_alloc(ictx, ptr, type, obj)
+
 /*
  * The IO Address Space (IOAS) pagetable is a virtual page table backed by the
  * io_pagetable object. It is a user controlled mapping of IOVA -> PFNs. The
@@ -222,6 +280,8 @@ int iommufd_option_rlimit_mode(struct iommu_option *cmd,
 			       struct iommufd_ctx *ictx);
 
 int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd);
+int iommufd_check_iova_range(struct io_pagetable *iopt,
+			     struct iommu_hwpt_get_dirty_bitmap *bitmap);
 
 /*
  * A HW pagetable is called an iommu_domain inside the kernel. This user object
@@ -231,35 +291,75 @@ int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd);
  */
 struct iommufd_hw_pagetable {
 	struct iommufd_object obj;
-	struct iommufd_ioas *ioas;
 	struct iommu_domain *domain;
+};
+
+struct iommufd_hwpt_paging {
+	struct iommufd_hw_pagetable common;
+	struct iommufd_ioas *ioas;
 	bool auto_domain : 1;
 	bool enforce_cache_coherency : 1;
 	bool msi_cookie : 1;
+	bool nest_parent : 1;
 	/* Head at iommufd_ioas::hwpt_list */
 	struct list_head hwpt_item;
 };
 
-struct iommufd_hw_pagetable *
-iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
-			   struct iommufd_device *idev, bool immediate_attach);
-int iommufd_hw_pagetable_enforce_cc(struct iommufd_hw_pagetable *hwpt);
+struct iommufd_hwpt_nested {
+	struct iommufd_hw_pagetable common;
+	struct iommufd_hwpt_paging *parent;
+};
+
+static inline bool hwpt_is_paging(struct iommufd_hw_pagetable *hwpt)
+{
+	return hwpt->obj.type == IOMMUFD_OBJ_HWPT_PAGING;
+}
+
+static inline struct iommufd_hwpt_paging *
+to_hwpt_paging(struct iommufd_hw_pagetable *hwpt)
+{
+	return container_of(hwpt, struct iommufd_hwpt_paging, common);
+}
+
+static inline struct iommufd_hwpt_paging *
+iommufd_get_hwpt_paging(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_HWPT_PAGING),
+			    struct iommufd_hwpt_paging, common.obj);
+}
+int iommufd_hwpt_set_dirty_tracking(struct iommufd_ucmd *ucmd);
+int iommufd_hwpt_get_dirty_bitmap(struct iommufd_ucmd *ucmd);
+
+struct iommufd_hwpt_paging *
+iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
+			  struct iommufd_device *idev, u32 flags,
+			  bool immediate_attach,
+			  const struct iommu_user_data *user_data);
 int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 				struct iommufd_device *idev);
 struct iommufd_hw_pagetable *
 iommufd_hw_pagetable_detach(struct iommufd_device *idev);
-void iommufd_hw_pagetable_destroy(struct iommufd_object *obj);
-void iommufd_hw_pagetable_abort(struct iommufd_object *obj);
+void iommufd_hwpt_paging_destroy(struct iommufd_object *obj);
+void iommufd_hwpt_paging_abort(struct iommufd_object *obj);
+void iommufd_hwpt_nested_destroy(struct iommufd_object *obj);
+void iommufd_hwpt_nested_abort(struct iommufd_object *obj);
 int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd);
 
 static inline void iommufd_hw_pagetable_put(struct iommufd_ctx *ictx,
 					    struct iommufd_hw_pagetable *hwpt)
 {
-	lockdep_assert_not_held(&hwpt->ioas->mutex);
-	if (hwpt->auto_domain)
-		iommufd_object_deref_user(ictx, &hwpt->obj);
-	else
-		refcount_dec(&hwpt->obj.users);
+	if (hwpt->obj.type == IOMMUFD_OBJ_HWPT_PAGING) {
+		struct iommufd_hwpt_paging *hwpt_paging = to_hwpt_paging(hwpt);
+
+		lockdep_assert_not_held(&hwpt_paging->ioas->mutex);
+
+		if (hwpt_paging->auto_domain) {
+			iommufd_object_put_and_try_destroy(ictx, &hwpt->obj);
+			return;
+		}
+	}
+	refcount_dec(&hwpt->obj.users);
 }
 
 struct iommufd_group {
diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index 3f3644375..7910fbe19 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -19,6 +19,8 @@ enum {
 	IOMMU_TEST_OP_SET_TEMP_MEMORY_LIMIT,
 	IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE,
 	IOMMU_TEST_OP_ACCESS_REPLACE_IOAS,
+	IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS,
+	IOMMU_TEST_OP_DIRTY,
 };
 
 enum {
@@ -40,6 +42,15 @@ enum {
 	MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES = 1 << 0,
 };
 
+enum {
+	MOCK_FLAGS_DEVICE_NO_DIRTY = 1 << 0,
+};
+
+enum {
+	MOCK_NESTED_DOMAIN_IOTLB_ID_MAX = 3,
+	MOCK_NESTED_DOMAIN_IOTLB_NUM = 4,
+};
+
 struct iommu_test_cmd {
 	__u32 size;
 	__u32 op;
@@ -57,6 +68,13 @@ struct iommu_test_cmd {
 			__u32 out_idev_id;
 		} mock_domain;
 		struct {
+			__u32 out_stdev_id;
+			__u32 out_hwpt_id;
+			__u32 out_idev_id;
+			/* Expand mock_domain to set mock device flags */
+			__u32 dev_flags;
+		} mock_domain_flags;
+		struct {
 			__u32 pt_id;
 		} mock_domain_replace;
 		struct {
@@ -95,6 +113,14 @@ struct iommu_test_cmd {
 		struct {
 			__u32 ioas_id;
 		} access_replace_ioas;
+		struct {
+			__u32 flags;
+			__aligned_u64 iova;
+			__aligned_u64 length;
+			__aligned_u64 page_size;
+			__aligned_u64 uptr;
+			__aligned_u64 out_nr_dirty;
+		} dirty;
 	};
 	__u32 last;
 };
@@ -109,4 +135,17 @@ struct iommu_test_hw_info {
 	__u32 test_reg;
 };
 
+/* Should not be equal to any defined value in enum iommu_hwpt_data_type */
+#define IOMMU_HWPT_DATA_SELFTEST 0xdead
+#define IOMMU_TEST_IOTLB_DEFAULT 0xbadbeef
+
+/**
+ * struct iommu_hwpt_selftest
+ *
+ * @iotlb: default mock iotlb value, IOMMU_TEST_IOTLB_DEFAULT
+ */
+struct iommu_hwpt_selftest {
+	__u32 iotlb;
+};
+
 #endif
diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
new file mode 100644
index 000000000..db8c46bee
--- /dev/null
+++ b/drivers/iommu/iommufd/iova_bitmap.c
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022, Oracle and/or its affiliates.
+ * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+#include <linux/iova_bitmap.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/highmem.h>
+
+#define BITS_PER_PAGE (PAGE_SIZE * BITS_PER_BYTE)
+
+/*
+ * struct iova_bitmap_map - A bitmap representing an IOVA range
+ *
+ * Main data structure for tracking mapped user pages of bitmap data.
+ *
+ * For example, for something recording dirty IOVAs, it will be provided a
+ * struct iova_bitmap structure, as a general structure for iterating the
+ * total IOVA range. The struct iova_bitmap_map, though, represents the
+ * subset of said IOVA space that is pinned by its parent structure (struct
+ * iova_bitmap).
+ *
+ * The user does not need to exact location of the bits in the bitmap.
+ * From user perspective the only API available is iova_bitmap_set() which
+ * records the IOVA *range* in the bitmap by setting the corresponding
+ * bits.
+ *
+ * The bitmap is an array of u64 whereas each bit represents an IOVA of
+ * range of (1 << pgshift). Thus formula for the bitmap data to be set is:
+ *
+ *   data[(iova / page_size) / 64] & (1ULL << (iova % 64))
+ */
+struct iova_bitmap_map {
+	/* base IOVA representing bit 0 of the first page */
+	unsigned long iova;
+
+	/* page size order that each bit granules to */
+	unsigned long pgshift;
+
+	/* page offset of the first user page pinned */
+	unsigned long pgoff;
+
+	/* number of pages pinned */
+	unsigned long npages;
+
+	/* pinned pages representing the bitmap data */
+	struct page **pages;
+};
+
+/*
+ * struct iova_bitmap - The IOVA bitmap object
+ *
+ * Main data structure for iterating over the bitmap data.
+ *
+ * Abstracts the pinning work and iterates in IOVA ranges.
+ * It uses a windowing scheme and pins the bitmap in relatively
+ * big ranges e.g.
+ *
+ * The bitmap object uses one base page to store all the pinned pages
+ * pointers related to the bitmap. For sizeof(struct page*) == 8 it stores
+ * 512 struct page pointers which, if the base page size is 4K, it means
+ * 2M of bitmap data is pinned at a time. If the iova_bitmap page size is
+ * also 4K then the range window to iterate is 64G.
+ *
+ * For example iterating on a total IOVA range of 4G..128G, it will walk
+ * through this set of ranges:
+ *
+ *    4G  -  68G-1 (64G)
+ *    68G - 128G-1 (64G)
+ *
+ * An example of the APIs on how to use/iterate over the IOVA bitmap:
+ *
+ *   bitmap = iova_bitmap_alloc(iova, length, page_size, data);
+ *   if (IS_ERR(bitmap))
+ *       return PTR_ERR(bitmap);
+ *
+ *   ret = iova_bitmap_for_each(bitmap, arg, dirty_reporter_fn);
+ *
+ *   iova_bitmap_free(bitmap);
+ *
+ * Each iteration of the @dirty_reporter_fn is called with a unique @iova
+ * and @length argument, indicating the current range available through the
+ * iova_bitmap. The @dirty_reporter_fn uses iova_bitmap_set() to mark dirty
+ * areas (@iova_length) within that provided range, as following:
+ *
+ *   iova_bitmap_set(bitmap, iova, iova_length);
+ *
+ * The internals of the object uses an index @mapped_base_index that indexes
+ * which u64 word of the bitmap is mapped, up to @mapped_total_index.
+ * Those keep being incremented until @mapped_total_index is reached while
+ * mapping up to PAGE_SIZE / sizeof(struct page*) maximum of pages.
+ *
+ * The IOVA bitmap is usually located on what tracks DMA mapped ranges or
+ * some form of IOVA range tracking that co-relates to the user passed
+ * bitmap.
+ */
+struct iova_bitmap {
+	/* IOVA range representing the currently mapped bitmap data */
+	struct iova_bitmap_map mapped;
+
+	/* userspace address of the bitmap */
+	u8 __user *bitmap;
+
+	/* u64 index that @mapped points to */
+	unsigned long mapped_base_index;
+
+	/* how many u64 can we walk in total */
+	unsigned long mapped_total_index;
+
+	/* base IOVA of the whole bitmap */
+	unsigned long iova;
+
+	/* length of the IOVA range for the whole bitmap */
+	size_t length;
+
+	/* length of the IOVA range set ahead the pinned pages */
+	unsigned long set_ahead_length;
+};
+
+/*
+ * Converts a relative IOVA to a bitmap index.
+ * This function provides the index into the u64 array (bitmap::bitmap)
+ * for a given IOVA offset.
+ * Relative IOVA means relative to the bitmap::mapped base IOVA
+ * (stored in mapped::iova). All computations in this file are done using
+ * relative IOVAs and thus avoid an extra subtraction against mapped::iova.
+ * The user API iova_bitmap_set() always uses a regular absolute IOVAs.
+ */
+static unsigned long iova_bitmap_offset_to_index(struct iova_bitmap *bitmap,
+						 unsigned long iova)
+{
+	unsigned long pgsize = 1 << bitmap->mapped.pgshift;
+
+	return iova / (BITS_PER_TYPE(*bitmap->bitmap) * pgsize);
+}
+
+/*
+ * Converts a bitmap index to a *relative* IOVA.
+ */
+static unsigned long iova_bitmap_index_to_offset(struct iova_bitmap *bitmap,
+						 unsigned long index)
+{
+	unsigned long pgshift = bitmap->mapped.pgshift;
+
+	return (index * BITS_PER_TYPE(*bitmap->bitmap)) << pgshift;
+}
+
+/*
+ * Returns the base IOVA of the mapped range.
+ */
+static unsigned long iova_bitmap_mapped_iova(struct iova_bitmap *bitmap)
+{
+	unsigned long skip = bitmap->mapped_base_index;
+
+	return bitmap->iova + iova_bitmap_index_to_offset(bitmap, skip);
+}
+
+/*
+ * Pins the bitmap user pages for the current range window.
+ * This is internal to IOVA bitmap and called when advancing the
+ * index (@mapped_base_index) or allocating the bitmap.
+ */
+static int iova_bitmap_get(struct iova_bitmap *bitmap)
+{
+	struct iova_bitmap_map *mapped = &bitmap->mapped;
+	unsigned long npages;
+	u8 __user *addr;
+	long ret;
+
+	/*
+	 * @mapped_base_index is the index of the currently mapped u64 words
+	 * that we have access. Anything before @mapped_base_index is not
+	 * mapped. The range @mapped_base_index .. @mapped_total_index-1 is
+	 * mapped but capped at a maximum number of pages.
+	 */
+	npages = DIV_ROUND_UP((bitmap->mapped_total_index -
+			       bitmap->mapped_base_index) *
+			       sizeof(*bitmap->bitmap), PAGE_SIZE);
+
+	/*
+	 * Bitmap address to be pinned is calculated via pointer arithmetic
+	 * with bitmap u64 word index.
+	 */
+	addr = bitmap->bitmap + bitmap->mapped_base_index;
+
+	/*
+	 * We always cap at max number of 'struct page' a base page can fit.
+	 * This is, for example, on x86 means 2M of bitmap data max.
+	 */
+	npages = min(npages + !!offset_in_page(addr),
+		     PAGE_SIZE / sizeof(struct page *));
+
+	ret = pin_user_pages_fast((unsigned long)addr, npages,
+				  FOLL_WRITE, mapped->pages);
+	if (ret <= 0)
+		return -EFAULT;
+
+	mapped->npages = (unsigned long)ret;
+	/* Base IOVA where @pages point to i.e. bit 0 of the first page */
+	mapped->iova = iova_bitmap_mapped_iova(bitmap);
+
+	/*
+	 * offset of the page where pinned pages bit 0 is located.
+	 * This handles the case where the bitmap is not PAGE_SIZE
+	 * aligned.
+	 */
+	mapped->pgoff = offset_in_page(addr);
+	return 0;
+}
+
+/*
+ * Unpins the bitmap user pages and clears @npages
+ * (un)pinning is abstracted from API user and it's done when advancing
+ * the index or freeing the bitmap.
+ */
+static void iova_bitmap_put(struct iova_bitmap *bitmap)
+{
+	struct iova_bitmap_map *mapped = &bitmap->mapped;
+
+	if (mapped->npages) {
+		unpin_user_pages(mapped->pages, mapped->npages);
+		mapped->npages = 0;
+	}
+}
+
+/**
+ * iova_bitmap_alloc() - Allocates an IOVA bitmap object
+ * @iova: Start address of the IOVA range
+ * @length: Length of the IOVA range
+ * @page_size: Page size of the IOVA bitmap. It defines what each bit
+ *             granularity represents
+ * @data: Userspace address of the bitmap
+ *
+ * Allocates an IOVA object and initializes all its fields including the
+ * first user pages of @data.
+ *
+ * Return: A pointer to a newly allocated struct iova_bitmap
+ * or ERR_PTR() on error.
+ */
+struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length,
+				      unsigned long page_size, u64 __user *data)
+{
+	struct iova_bitmap_map *mapped;
+	struct iova_bitmap *bitmap;
+	int rc;
+
+	bitmap = kzalloc(sizeof(*bitmap), GFP_KERNEL);
+	if (!bitmap)
+		return ERR_PTR(-ENOMEM);
+
+	mapped = &bitmap->mapped;
+	mapped->pgshift = __ffs(page_size);
+	bitmap->bitmap = (u8 __user *)data;
+	bitmap->mapped_total_index =
+		iova_bitmap_offset_to_index(bitmap, length - 1) + 1;
+	bitmap->iova = iova;
+	bitmap->length = length;
+	mapped->iova = iova;
+	mapped->pages = (struct page **)__get_free_page(GFP_KERNEL);
+	if (!mapped->pages) {
+		rc = -ENOMEM;
+		goto err;
+	}
+
+	rc = iova_bitmap_get(bitmap);
+	if (rc)
+		goto err;
+	return bitmap;
+
+err:
+	iova_bitmap_free(bitmap);
+	return ERR_PTR(rc);
+}
+EXPORT_SYMBOL_NS_GPL(iova_bitmap_alloc, IOMMUFD);
+
+/**
+ * iova_bitmap_free() - Frees an IOVA bitmap object
+ * @bitmap: IOVA bitmap to free
+ *
+ * It unpins and releases pages array memory and clears any leftover
+ * state.
+ */
+void iova_bitmap_free(struct iova_bitmap *bitmap)
+{
+	struct iova_bitmap_map *mapped = &bitmap->mapped;
+
+	iova_bitmap_put(bitmap);
+
+	if (mapped->pages) {
+		free_page((unsigned long)mapped->pages);
+		mapped->pages = NULL;
+	}
+
+	kfree(bitmap);
+}
+EXPORT_SYMBOL_NS_GPL(iova_bitmap_free, IOMMUFD);
+
+/*
+ * Returns the remaining bitmap indexes from mapped_total_index to process for
+ * the currently pinned bitmap pages.
+ */
+static unsigned long iova_bitmap_mapped_remaining(struct iova_bitmap *bitmap)
+{
+	unsigned long remaining, bytes;
+
+	bytes = (bitmap->mapped.npages << PAGE_SHIFT) - bitmap->mapped.pgoff;
+
+	remaining = bitmap->mapped_total_index - bitmap->mapped_base_index;
+	remaining = min_t(unsigned long, remaining,
+			  DIV_ROUND_UP(bytes, sizeof(*bitmap->bitmap)));
+
+	return remaining;
+}
+
+/*
+ * Returns the length of the mapped IOVA range.
+ */
+static unsigned long iova_bitmap_mapped_length(struct iova_bitmap *bitmap)
+{
+	unsigned long max_iova = bitmap->iova + bitmap->length - 1;
+	unsigned long iova = iova_bitmap_mapped_iova(bitmap);
+	unsigned long remaining;
+
+	/*
+	 * iova_bitmap_mapped_remaining() returns a number of indexes which
+	 * when converted to IOVA gives us a max length that the bitmap
+	 * pinned data can cover. Afterwards, that is capped to
+	 * only cover the IOVA range in @bitmap::iova .. @bitmap::length.
+	 */
+	remaining = iova_bitmap_index_to_offset(bitmap,
+			iova_bitmap_mapped_remaining(bitmap));
+
+	if (iova + remaining - 1 > max_iova)
+		remaining -= ((iova + remaining - 1) - max_iova);
+
+	return remaining;
+}
+
+/*
+ * Returns true if there's not more data to iterate.
+ */
+static bool iova_bitmap_done(struct iova_bitmap *bitmap)
+{
+	return bitmap->mapped_base_index >= bitmap->mapped_total_index;
+}
+
+static int iova_bitmap_set_ahead(struct iova_bitmap *bitmap,
+				 size_t set_ahead_length)
+{
+	int ret = 0;
+
+	while (set_ahead_length > 0 && !iova_bitmap_done(bitmap)) {
+		unsigned long length = iova_bitmap_mapped_length(bitmap);
+		unsigned long iova = iova_bitmap_mapped_iova(bitmap);
+
+		ret = iova_bitmap_get(bitmap);
+		if (ret)
+			break;
+
+		length = min(length, set_ahead_length);
+		iova_bitmap_set(bitmap, iova, length);
+
+		set_ahead_length -= length;
+		bitmap->mapped_base_index +=
+			iova_bitmap_offset_to_index(bitmap, length - 1) + 1;
+		iova_bitmap_put(bitmap);
+	}
+
+	bitmap->set_ahead_length = 0;
+	return ret;
+}
+
+/*
+ * Advances to the next range, releases the current pinned
+ * pages and pins the next set of bitmap pages.
+ * Returns 0 on success or otherwise errno.
+ */
+static int iova_bitmap_advance(struct iova_bitmap *bitmap)
+{
+	unsigned long iova = iova_bitmap_mapped_length(bitmap) - 1;
+	unsigned long count = iova_bitmap_offset_to_index(bitmap, iova) + 1;
+
+	bitmap->mapped_base_index += count;
+
+	iova_bitmap_put(bitmap);
+	if (iova_bitmap_done(bitmap))
+		return 0;
+
+	/* Iterate, set and skip any bits requested for next iteration */
+	if (bitmap->set_ahead_length) {
+		int ret;
+
+		ret = iova_bitmap_set_ahead(bitmap, bitmap->set_ahead_length);
+		if (ret)
+			return ret;
+	}
+
+	/* When advancing the index we pin the next set of bitmap pages */
+	return iova_bitmap_get(bitmap);
+}
+
+/**
+ * iova_bitmap_for_each() - Iterates over the bitmap
+ * @bitmap: IOVA bitmap to iterate
+ * @opaque: Additional argument to pass to the callback
+ * @fn: Function that gets called for each IOVA range
+ *
+ * Helper function to iterate over bitmap data representing a portion of IOVA
+ * space. It hides the complexity of iterating bitmaps and translating the
+ * mapped bitmap user pages into IOVA ranges to process.
+ *
+ * Return: 0 on success, and an error on failure either upon
+ * iteration or when the callback returns an error.
+ */
+int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque,
+			 iova_bitmap_fn_t fn)
+{
+	int ret = 0;
+
+	for (; !iova_bitmap_done(bitmap) && !ret;
+	     ret = iova_bitmap_advance(bitmap)) {
+		ret = fn(bitmap, iova_bitmap_mapped_iova(bitmap),
+			 iova_bitmap_mapped_length(bitmap), opaque);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(iova_bitmap_for_each, IOMMUFD);
+
+/**
+ * iova_bitmap_set() - Records an IOVA range in bitmap
+ * @bitmap: IOVA bitmap
+ * @iova: IOVA to start
+ * @length: IOVA range length
+ *
+ * Set the bits corresponding to the range [iova .. iova+length-1] in
+ * the user bitmap.
+ *
+ */
+void iova_bitmap_set(struct iova_bitmap *bitmap,
+		     unsigned long iova, size_t length)
+{
+	struct iova_bitmap_map *mapped = &bitmap->mapped;
+	unsigned long cur_bit = ((iova - mapped->iova) >>
+			mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
+	unsigned long last_bit = (((iova + length - 1) - mapped->iova) >>
+			mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
+	unsigned long last_page_idx = mapped->npages - 1;
+
+	do {
+		unsigned int page_idx = cur_bit / BITS_PER_PAGE;
+		unsigned int offset = cur_bit % BITS_PER_PAGE;
+		unsigned int nbits = min(BITS_PER_PAGE - offset,
+					 last_bit - cur_bit + 1);
+		void *kaddr;
+
+		if (unlikely(page_idx > last_page_idx))
+			break;
+
+		kaddr = kmap_local_page(mapped->pages[page_idx]);
+		bitmap_set(kaddr, offset, nbits);
+		kunmap_local(kaddr);
+		cur_bit += nbits;
+	} while (cur_bit <= last_bit);
+
+	if (unlikely(cur_bit <= last_bit)) {
+		bitmap->set_ahead_length =
+			((last_bit - cur_bit + 1) << bitmap->mapped.pgshift);
+	}
+}
+EXPORT_SYMBOL_NS_GPL(iova_bitmap_set, IOMMUFD);
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index e71523cbd..c9091e46d 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -33,7 +33,6 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 					     size_t size,
 					     enum iommufd_object_type type)
 {
-	static struct lock_class_key obj_keys[IOMMUFD_OBJ_MAX];
 	struct iommufd_object *obj;
 	int rc;
 
@@ -41,15 +40,8 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 	if (!obj)
 		return ERR_PTR(-ENOMEM);
 	obj->type = type;
-	/*
-	 * In most cases the destroy_rwsem is obtained with try so it doesn't
-	 * interact with lockdep, however on destroy we have to sleep. This
-	 * means if we have to destroy an object while holding a get on another
-	 * object it triggers lockdep. Using one locking class per object type
-	 * is a simple and reasonable way to avoid this.
-	 */
-	__init_rwsem(&obj->destroy_rwsem, "iommufd_object::destroy_rwsem",
-		     &obj_keys[type]);
+	/* Starts out bias'd by 1 until it is removed from the xarray */
+	refcount_set(&obj->shortterm_users, 1);
 	refcount_set(&obj->users, 1);
 
 	/*
@@ -129,92 +121,113 @@ struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 	return obj;
 }
 
+static int iommufd_object_dec_wait_shortterm(struct iommufd_ctx *ictx,
+					     struct iommufd_object *to_destroy)
+{
+	if (refcount_dec_and_test(&to_destroy->shortterm_users))
+		return 0;
+
+	if (wait_event_timeout(ictx->destroy_wait,
+				refcount_read(&to_destroy->shortterm_users) ==
+					0,
+				msecs_to_jiffies(10000)))
+		return 0;
+
+	pr_crit("Time out waiting for iommufd object to become free\n");
+	refcount_inc(&to_destroy->shortterm_users);
+	return -EBUSY;
+}
+
 /*
  * Remove the given object id from the xarray if the only reference to the
- * object is held by the xarray. The caller must call ops destroy().
+ * object is held by the xarray.
  */
-static struct iommufd_object *iommufd_object_remove(struct iommufd_ctx *ictx,
-						    u32 id, bool extra_put)
+int iommufd_object_remove(struct iommufd_ctx *ictx,
+			  struct iommufd_object *to_destroy, u32 id,
+			  unsigned int flags)
 {
 	struct iommufd_object *obj;
 	XA_STATE(xas, &ictx->objects, id);
-
-	xa_lock(&ictx->objects);
-	obj = xas_load(&xas);
-	if (xa_is_zero(obj) || !obj) {
-		obj = ERR_PTR(-ENOENT);
-		goto out_xa;
-	}
+	bool zerod_shortterm = false;
+	int ret;
 
 	/*
-	 * If the caller is holding a ref on obj we put it here under the
-	 * spinlock.
+	 * The purpose of the shortterm_users is to ensure deterministic
+	 * destruction of objects used by external drivers and destroyed by this
+	 * function. Any temporary increment of the refcount must increment
+	 * shortterm_users, such as during ioctl execution.
 	 */
-	if (extra_put)
+	if (flags & REMOVE_WAIT_SHORTTERM) {
+		ret = iommufd_object_dec_wait_shortterm(ictx, to_destroy);
+		if (ret) {
+			/*
+			 * We have a bug. Put back the callers reference and
+			 * defer cleaning this object until close.
+			 */
+			refcount_dec(&to_destroy->users);
+			return ret;
+		}
+		zerod_shortterm = true;
+	}
+
+	xa_lock(&ictx->objects);
+	obj = xas_load(&xas);
+	if (to_destroy) {
+		/*
+		 * If the caller is holding a ref on obj we put it here under
+		 * the spinlock.
+		 */
 		refcount_dec(&obj->users);
 
+		if (WARN_ON(obj != to_destroy)) {
+			ret = -ENOENT;
+			goto err_xa;
+		}
+	} else if (xa_is_zero(obj) || !obj) {
+		ret = -ENOENT;
+		goto err_xa;
+	}
+
 	if (!refcount_dec_if_one(&obj->users)) {
-		obj = ERR_PTR(-EBUSY);
-		goto out_xa;
+		ret = -EBUSY;
+		goto err_xa;
 	}
 
 	xas_store(&xas, NULL);
 	if (ictx->vfio_ioas == container_of(obj, struct iommufd_ioas, obj))
 		ictx->vfio_ioas = NULL;
-
-out_xa:
 	xa_unlock(&ictx->objects);
 
-	/* The returned object reference count is zero */
-	return obj;
-}
-
-/*
- * The caller holds a users refcount and wants to destroy the object. Returns
- * true if the object was destroyed. In all cases the caller no longer has a
- * reference on obj.
- */
-void __iommufd_object_destroy_user(struct iommufd_ctx *ictx,
-				   struct iommufd_object *obj, bool allow_fail)
-{
-	struct iommufd_object *ret;
-
-	/*
-	 * The purpose of the destroy_rwsem is to ensure deterministic
-	 * destruction of objects used by external drivers and destroyed by this
-	 * function. Any temporary increment of the refcount must hold the read
-	 * side of this, such as during ioctl execution.
-	 */
-	down_write(&obj->destroy_rwsem);
-	ret = iommufd_object_remove(ictx, obj->id, true);
-	up_write(&obj->destroy_rwsem);
-
-	if (allow_fail && IS_ERR(ret))
-		return;
-
 	/*
-	 * If there is a bug and we couldn't destroy the object then we did put
-	 * back the caller's refcount and will eventually try to free it again
-	 * during close.
+	 * Since users is zero any positive users_shortterm must be racing
+	 * iommufd_put_object(), or we have a bug.
 	 */
-	if (WARN_ON(IS_ERR(ret)))
-		return;
+	if (!zerod_shortterm) {
+		ret = iommufd_object_dec_wait_shortterm(ictx, obj);
+		if (WARN_ON(ret))
+			return ret;
+	}
 
 	iommufd_object_ops[obj->type].destroy(obj);
 	kfree(obj);
+	return 0;
+
+err_xa:
+	if (zerod_shortterm) {
+		/* Restore the xarray owned reference */
+		refcount_set(&obj->shortterm_users, 1);
+	}
+	xa_unlock(&ictx->objects);
+
+	/* The returned object reference count is zero */
+	return ret;
 }
 
 static int iommufd_destroy(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_destroy *cmd = ucmd->cmd;
-	struct iommufd_object *obj;
 
-	obj = iommufd_object_remove(ucmd->ictx, cmd->id, false);
-	if (IS_ERR(obj))
-		return PTR_ERR(obj);
-	iommufd_object_ops[obj->type].destroy(obj);
-	kfree(obj);
-	return 0;
+	return iommufd_object_remove(ucmd->ictx, NULL, cmd->id, 0);
 }
 
 static int iommufd_fops_open(struct inode *inode, struct file *filp)
@@ -238,6 +251,7 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
 	xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT);
 	xa_init(&ictx->groups);
 	ictx->file = filp;
+	init_waitqueue_head(&ictx->destroy_wait);
 	filp->private_data = ictx;
 	return 0;
 }
@@ -307,6 +321,8 @@ union ucmd_buffer {
 	struct iommu_destroy destroy;
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
+	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
+	struct iommu_hwpt_set_dirty_tracking set_dirty_tracking;
 	struct iommu_ioas_alloc alloc;
 	struct iommu_ioas_allow_iovas allow_iovas;
 	struct iommu_ioas_copy ioas_copy;
@@ -342,6 +358,10 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc,
 		 __reserved),
+	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
+		 struct iommu_hwpt_get_dirty_bitmap, data),
+	IOCTL_OP(IOMMU_HWPT_SET_DIRTY_TRACKING, iommufd_hwpt_set_dirty_tracking,
+		 struct iommu_hwpt_set_dirty_tracking, __reserved),
 	IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl,
 		 struct iommu_ioas_alloc, out_ioas_id),
 	IOCTL_OP(IOMMU_IOAS_ALLOW_IOVAS, iommufd_ioas_allow_iovas,
@@ -482,9 +502,13 @@ static const struct iommufd_object_ops iommufd_object_ops[] = {
 	[IOMMUFD_OBJ_IOAS] = {
 		.destroy = iommufd_ioas_destroy,
 	},
-	[IOMMUFD_OBJ_HW_PAGETABLE] = {
-		.destroy = iommufd_hw_pagetable_destroy,
-		.abort = iommufd_hw_pagetable_abort,
+	[IOMMUFD_OBJ_HWPT_PAGING] = {
+		.destroy = iommufd_hwpt_paging_destroy,
+		.abort = iommufd_hwpt_paging_abort,
+	},
+	[IOMMUFD_OBJ_HWPT_NESTED] = {
+		.destroy = iommufd_hwpt_nested_destroy,
+		.abort = iommufd_hwpt_nested_abort,
 	},
 #ifdef CONFIG_IOMMUFD_TEST
 	[IOMMUFD_OBJ_SELFTEST] = {
@@ -552,5 +576,6 @@ MODULE_ALIAS_MISCDEV(VFIO_MINOR);
 MODULE_ALIAS("devname:vfio/vfio");
 #endif
 MODULE_IMPORT_NS(IOMMUFD_INTERNAL);
+MODULE_IMPORT_NS(IOMMUFD);
 MODULE_DESCRIPTION("I/O Address Space Management for passthrough devices");
 MODULE_LICENSE("GPL");
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 56506d575..022ef8f55 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -20,10 +20,13 @@
 static DECLARE_FAULT_ATTR(fail_iommufd);
 static struct dentry *dbgfs_root;
 static struct platform_device *selftest_iommu_dev;
+static const struct iommu_ops mock_ops;
+static struct iommu_domain_ops domain_nested_ops;
 
 size_t iommufd_test_memory_limit = 65536;
 
 enum {
+	MOCK_DIRTY_TRACK = 1,
 	MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2,
 
 	/*
@@ -36,6 +39,7 @@ enum {
 	_MOCK_PFN_START = MOCK_PFN_MASK + 1,
 	MOCK_PFN_START_IOVA = _MOCK_PFN_START,
 	MOCK_PFN_LAST_IOVA = _MOCK_PFN_START,
+	MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1,
 };
 
 /*
@@ -82,20 +86,28 @@ void iommufd_test_syz_conv_iova_id(struct iommufd_ucmd *ucmd,
 	if (IS_ERR(ioas))
 		return;
 	*iova = iommufd_test_syz_conv_iova(&ioas->iopt, iova);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 }
 
 struct mock_iommu_domain {
+	unsigned long flags;
 	struct iommu_domain domain;
 	struct xarray pfns;
 };
 
+struct mock_iommu_domain_nested {
+	struct iommu_domain domain;
+	struct mock_iommu_domain *parent;
+	u32 iotlb[MOCK_NESTED_DOMAIN_IOTLB_NUM];
+};
+
 enum selftest_obj_type {
 	TYPE_IDEV,
 };
 
 struct mock_dev {
 	struct device dev;
+	unsigned long flags;
 };
 
 struct selftest_obj {
@@ -111,18 +123,18 @@ struct selftest_obj {
 	};
 };
 
-static void mock_domain_blocking_free(struct iommu_domain *domain)
-{
-}
-
 static int mock_domain_nop_attach(struct iommu_domain *domain,
 				  struct device *dev)
 {
+	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
+
+	if (domain->dirty_ops && (mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY))
+		return -EINVAL;
+
 	return 0;
 }
 
 static const struct iommu_domain_ops mock_blocking_ops = {
-	.free = mock_domain_blocking_free,
 	.attach_dev = mock_domain_nop_attach,
 };
 
@@ -146,15 +158,70 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type)
 	return info;
 }
 
-static struct iommu_domain *mock_domain_alloc(unsigned int iommu_domain_type)
+static int mock_domain_set_dirty_tracking(struct iommu_domain *domain,
+					  bool enable)
 {
-	struct mock_iommu_domain *mock;
+	struct mock_iommu_domain *mock =
+		container_of(domain, struct mock_iommu_domain, domain);
+	unsigned long flags = mock->flags;
 
-	if (iommu_domain_type == IOMMU_DOMAIN_BLOCKED)
-		return &mock_blocking_domain;
+	if (enable && !domain->dirty_ops)
+		return -EINVAL;
 
-	if (iommu_domain_type != IOMMU_DOMAIN_UNMANAGED)
-		return NULL;
+	/* No change? */
+	if (!(enable ^ !!(flags & MOCK_DIRTY_TRACK)))
+		return 0;
+
+	flags = (enable ? flags | MOCK_DIRTY_TRACK : flags & ~MOCK_DIRTY_TRACK);
+
+	mock->flags = flags;
+	return 0;
+}
+
+static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
+					    unsigned long iova, size_t size,
+					    unsigned long flags,
+					    struct iommu_dirty_bitmap *dirty)
+{
+	struct mock_iommu_domain *mock =
+		container_of(domain, struct mock_iommu_domain, domain);
+	unsigned long i, max = size / MOCK_IO_PAGE_SIZE;
+	void *ent, *old;
+
+	if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap)
+		return -EINVAL;
+
+	for (i = 0; i < max; i++) {
+		unsigned long cur = iova + i * MOCK_IO_PAGE_SIZE;
+
+		ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE);
+		if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) {
+			/* Clear dirty */
+			if (!(flags & IOMMU_DIRTY_NO_CLEAR)) {
+				unsigned long val;
+
+				val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA;
+				old = xa_store(&mock->pfns,
+					       cur / MOCK_IO_PAGE_SIZE,
+					       xa_mk_value(val), GFP_KERNEL);
+				WARN_ON_ONCE(ent != old);
+			}
+			iommu_dirty_bitmap_record(dirty, cur,
+						  MOCK_IO_PAGE_SIZE);
+		}
+	}
+
+	return 0;
+}
+
+const struct iommu_dirty_ops dirty_ops = {
+	.set_dirty_tracking = mock_domain_set_dirty_tracking,
+	.read_and_clear_dirty = mock_domain_read_and_clear_dirty,
+};
+
+static struct iommu_domain *mock_domain_alloc_paging(struct device *dev)
+{
+	struct mock_iommu_domain *mock;
 
 	mock = kzalloc(sizeof(*mock), GFP_KERNEL);
 	if (!mock)
@@ -162,10 +229,78 @@ static struct iommu_domain *mock_domain_alloc(unsigned int iommu_domain_type)
 	mock->domain.geometry.aperture_start = MOCK_APERTURE_START;
 	mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST;
 	mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE;
+	mock->domain.ops = mock_ops.default_domain_ops;
+	mock->domain.type = IOMMU_DOMAIN_UNMANAGED;
 	xa_init(&mock->pfns);
 	return &mock->domain;
 }
 
+static struct iommu_domain *
+__mock_domain_alloc_nested(struct mock_iommu_domain *mock_parent,
+			   const struct iommu_hwpt_selftest *user_cfg)
+{
+	struct mock_iommu_domain_nested *mock_nested;
+	int i;
+
+	mock_nested = kzalloc(sizeof(*mock_nested), GFP_KERNEL);
+	if (!mock_nested)
+		return ERR_PTR(-ENOMEM);
+	mock_nested->parent = mock_parent;
+	mock_nested->domain.ops = &domain_nested_ops;
+	mock_nested->domain.type = IOMMU_DOMAIN_NESTED;
+	for (i = 0; i < MOCK_NESTED_DOMAIN_IOTLB_NUM; i++)
+		mock_nested->iotlb[i] = user_cfg->iotlb;
+	return &mock_nested->domain;
+}
+
+static struct iommu_domain *
+mock_domain_alloc_user(struct device *dev, u32 flags,
+		       struct iommu_domain *parent,
+		       const struct iommu_user_data *user_data)
+{
+	struct mock_iommu_domain *mock_parent;
+	struct iommu_hwpt_selftest user_cfg;
+	int rc;
+
+	/* must be mock_domain */
+	if (!parent) {
+		struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
+		bool has_dirty_flag = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING;
+		bool no_dirty_ops = mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY;
+		struct iommu_domain *domain;
+
+		if (flags & (~(IOMMU_HWPT_ALLOC_NEST_PARENT |
+			       IOMMU_HWPT_ALLOC_DIRTY_TRACKING)))
+			return ERR_PTR(-EOPNOTSUPP);
+		if (user_data || (has_dirty_flag && no_dirty_ops))
+			return ERR_PTR(-EOPNOTSUPP);
+		domain = mock_domain_alloc_paging(NULL);
+		if (!domain)
+			return ERR_PTR(-ENOMEM);
+		if (has_dirty_flag)
+			container_of(domain, struct mock_iommu_domain, domain)
+				->domain.dirty_ops = &dirty_ops;
+		return domain;
+	}
+
+	/* must be mock_domain_nested */
+	if (user_data->type != IOMMU_HWPT_DATA_SELFTEST || flags)
+		return ERR_PTR(-EOPNOTSUPP);
+	if (!parent || parent->ops != mock_ops.default_domain_ops)
+		return ERR_PTR(-EINVAL);
+
+	mock_parent = container_of(parent, struct mock_iommu_domain, domain);
+	if (!mock_parent)
+		return ERR_PTR(-EINVAL);
+
+	rc = iommu_copy_struct_from_user(&user_cfg, user_data,
+					 IOMMU_HWPT_DATA_SELFTEST, iotlb);
+	if (rc)
+		return ERR_PTR(rc);
+
+	return __mock_domain_alloc_nested(mock_parent, &user_cfg);
+}
+
 static void mock_domain_free(struct iommu_domain *domain)
 {
 	struct mock_iommu_domain *mock =
@@ -243,7 +378,7 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain,
 
 		for (cur = 0; cur != pgsize; cur += MOCK_IO_PAGE_SIZE) {
 			ent = xa_erase(&mock->pfns, iova / MOCK_IO_PAGE_SIZE);
-			WARN_ON(!ent);
+
 			/*
 			 * iommufd generates unmaps that must be a strict
 			 * superset of the map's performend So every starting
@@ -253,13 +388,13 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain,
 			 * passed to map_pages
 			 */
 			if (first) {
-				WARN_ON(!(xa_to_value(ent) &
-					  MOCK_PFN_START_IOVA));
+				WARN_ON(ent && !(xa_to_value(ent) &
+						 MOCK_PFN_START_IOVA));
 				first = false;
 			}
 			if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize)
-				WARN_ON(!(xa_to_value(ent) &
-					  MOCK_PFN_LAST_IOVA));
+				WARN_ON(ent && !(xa_to_value(ent) &
+						 MOCK_PFN_LAST_IOVA));
 
 			iova += MOCK_IO_PAGE_SIZE;
 			ret += MOCK_IO_PAGE_SIZE;
@@ -283,15 +418,18 @@ static phys_addr_t mock_domain_iova_to_phys(struct iommu_domain *domain,
 
 static bool mock_domain_capable(struct device *dev, enum iommu_cap cap)
 {
-	return cap == IOMMU_CAP_CACHE_COHERENCY;
-}
+	struct mock_dev *mdev = container_of(dev, struct mock_dev, dev);
 
-static void mock_domain_set_plaform_dma_ops(struct device *dev)
-{
-	/*
-	 * mock doesn't setup default domains because we can't hook into the
-	 * normal probe path
-	 */
+	switch (cap) {
+	case IOMMU_CAP_CACHE_COHERENCY:
+		return true;
+	case IOMMU_CAP_DIRTY_TRACKING:
+		return !(mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY);
+	default:
+		break;
+	}
+
+	return false;
 }
 
 static struct iommu_device mock_iommu_device = {
@@ -303,12 +441,18 @@ static struct iommu_device *mock_probe_device(struct device *dev)
 }
 
 static const struct iommu_ops mock_ops = {
+	/*
+	 * IOMMU_DOMAIN_BLOCKED cannot be returned from def_domain_type()
+	 * because it is zero.
+	 */
+	.default_domain = &mock_blocking_domain,
+	.blocked_domain = &mock_blocking_domain,
 	.owner = THIS_MODULE,
 	.pgsize_bitmap = MOCK_IO_PAGE_SIZE,
 	.hw_info = mock_domain_hw_info,
-	.domain_alloc = mock_domain_alloc,
+	.domain_alloc_paging = mock_domain_alloc_paging,
+	.domain_alloc_user = mock_domain_alloc_user,
 	.capable = mock_domain_capable,
-	.set_platform_dma_ops = mock_domain_set_plaform_dma_ops,
 	.device_group = generic_device_group,
 	.probe_device = mock_probe_device,
 	.default_domain_ops =
@@ -321,26 +465,67 @@ static const struct iommu_ops mock_ops = {
 		},
 };
 
+static void mock_domain_free_nested(struct iommu_domain *domain)
+{
+	struct mock_iommu_domain_nested *mock_nested =
+		container_of(domain, struct mock_iommu_domain_nested, domain);
+
+	kfree(mock_nested);
+}
+
+static struct iommu_domain_ops domain_nested_ops = {
+	.free = mock_domain_free_nested,
+	.attach_dev = mock_domain_nop_attach,
+};
+
 static inline struct iommufd_hw_pagetable *
-get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id,
-		 struct mock_iommu_domain **mock)
+__get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id, u32 hwpt_type)
 {
-	struct iommufd_hw_pagetable *hwpt;
 	struct iommufd_object *obj;
 
-	obj = iommufd_get_object(ucmd->ictx, mockpt_id,
-				 IOMMUFD_OBJ_HW_PAGETABLE);
+	obj = iommufd_get_object(ucmd->ictx, mockpt_id, hwpt_type);
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
-	hwpt = container_of(obj, struct iommufd_hw_pagetable, obj);
-	if (hwpt->domain->ops != mock_ops.default_domain_ops) {
-		iommufd_put_object(&hwpt->obj);
+	return container_of(obj, struct iommufd_hw_pagetable, obj);
+}
+
+static inline struct iommufd_hw_pagetable *
+get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id,
+		 struct mock_iommu_domain **mock)
+{
+	struct iommufd_hw_pagetable *hwpt;
+
+	hwpt = __get_md_pagetable(ucmd, mockpt_id, IOMMUFD_OBJ_HWPT_PAGING);
+	if (IS_ERR(hwpt))
+		return hwpt;
+	if (hwpt->domain->type != IOMMU_DOMAIN_UNMANAGED ||
+	    hwpt->domain->ops != mock_ops.default_domain_ops) {
+		iommufd_put_object(ucmd->ictx, &hwpt->obj);
 		return ERR_PTR(-EINVAL);
 	}
 	*mock = container_of(hwpt->domain, struct mock_iommu_domain, domain);
 	return hwpt;
 }
 
+static inline struct iommufd_hw_pagetable *
+get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id,
+			struct mock_iommu_domain_nested **mock_nested)
+{
+	struct iommufd_hw_pagetable *hwpt;
+
+	hwpt = __get_md_pagetable(ucmd, mockpt_id, IOMMUFD_OBJ_HWPT_NESTED);
+	if (IS_ERR(hwpt))
+		return hwpt;
+	if (hwpt->domain->type != IOMMU_DOMAIN_NESTED ||
+	    hwpt->domain->ops != &domain_nested_ops) {
+		iommufd_put_object(ucmd->ictx, &hwpt->obj);
+		return ERR_PTR(-EINVAL);
+	}
+	*mock_nested = container_of(hwpt->domain,
+				    struct mock_iommu_domain_nested, domain);
+	return hwpt;
+}
+
 struct mock_bus_type {
 	struct bus_type bus;
 	struct notifier_block nb;
@@ -362,16 +547,20 @@ static void mock_dev_release(struct device *dev)
 	kfree(mdev);
 }
 
-static struct mock_dev *mock_dev_create(void)
+static struct mock_dev *mock_dev_create(unsigned long dev_flags)
 {
 	struct mock_dev *mdev;
 	int rc;
 
+	if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY))
+		return ERR_PTR(-EINVAL);
+
 	mdev = kzalloc(sizeof(*mdev), GFP_KERNEL);
 	if (!mdev)
 		return ERR_PTR(-ENOMEM);
 
 	device_initialize(&mdev->dev);
+	mdev->flags = dev_flags;
 	mdev->dev.release = mock_dev_release;
 	mdev->dev.bus = &iommufd_mock_bus_type.bus;
 
@@ -407,6 +596,7 @@ static int iommufd_test_mock_domain(struct iommufd_ucmd *ucmd,
 	struct iommufd_device *idev;
 	struct selftest_obj *sobj;
 	u32 pt_id = cmd->id;
+	u32 dev_flags = 0;
 	u32 idev_id;
 	int rc;
 
@@ -417,7 +607,10 @@ static int iommufd_test_mock_domain(struct iommufd_ucmd *ucmd,
 	sobj->idev.ictx = ucmd->ictx;
 	sobj->type = TYPE_IDEV;
 
-	sobj->idev.mock_dev = mock_dev_create();
+	if (cmd->op == IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS)
+		dev_flags = cmd->mock_domain_flags.dev_flags;
+
+	sobj->idev.mock_dev = mock_dev_create(dev_flags);
 	if (IS_ERR(sobj->idev.mock_dev)) {
 		rc = PTR_ERR(sobj->idev.mock_dev);
 		goto out_sobj;
@@ -488,7 +681,7 @@ static int iommufd_test_mock_domain_replace(struct iommufd_ucmd *ucmd,
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 out_dev_obj:
-	iommufd_put_object(dev_obj);
+	iommufd_put_object(ucmd->ictx, dev_obj);
 	return rc;
 }
 
@@ -506,7 +699,7 @@ static int iommufd_test_add_reserved(struct iommufd_ucmd *ucmd,
 	down_write(&ioas->iopt.iova_rwsem);
 	rc = iopt_reserve_iova(&ioas->iopt, start, start + length - 1, NULL);
 	up_write(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ucmd->ictx, &ioas->obj);
 	return rc;
 }
 
@@ -561,7 +754,7 @@ static int iommufd_test_md_check_pa(struct iommufd_ucmd *ucmd,
 	rc = 0;
 
 out_put:
-	iommufd_put_object(&hwpt->obj);
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
 	return rc;
 }
 
@@ -977,6 +1170,73 @@ static_assert((unsigned int)MOCK_ACCESS_RW_WRITE == IOMMUFD_ACCESS_RW_WRITE);
 static_assert((unsigned int)MOCK_ACCESS_RW_SLOW_PATH ==
 	      __IOMMUFD_ACCESS_RW_SLOW_PATH);
 
+static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
+			      unsigned long iova, size_t length,
+			      unsigned long page_size, void __user *uptr,
+			      u32 flags)
+{
+	unsigned long bitmap_size, i, max;
+	struct iommu_test_cmd *cmd = ucmd->cmd;
+	struct iommufd_hw_pagetable *hwpt;
+	struct mock_iommu_domain *mock;
+	int rc, count = 0;
+	void *tmp;
+
+	if (!page_size || !length || iova % page_size || length % page_size ||
+	    !uptr)
+		return -EINVAL;
+
+	hwpt = get_md_pagetable(ucmd, mockpt_id, &mock);
+	if (IS_ERR(hwpt))
+		return PTR_ERR(hwpt);
+
+	if (!(mock->flags & MOCK_DIRTY_TRACK)) {
+		rc = -EINVAL;
+		goto out_put;
+	}
+
+	max = length / page_size;
+	bitmap_size = max / BITS_PER_BYTE;
+
+	tmp = kvzalloc(bitmap_size, GFP_KERNEL_ACCOUNT);
+	if (!tmp) {
+		rc = -ENOMEM;
+		goto out_put;
+	}
+
+	if (copy_from_user(tmp, uptr, bitmap_size)) {
+		rc = -EFAULT;
+		goto out_free;
+	}
+
+	for (i = 0; i < max; i++) {
+		unsigned long cur = iova + i * page_size;
+		void *ent, *old;
+
+		if (!test_bit(i, (unsigned long *)tmp))
+			continue;
+
+		ent = xa_load(&mock->pfns, cur / page_size);
+		if (ent) {
+			unsigned long val;
+
+			val = xa_to_value(ent) | MOCK_PFN_DIRTY_IOVA;
+			old = xa_store(&mock->pfns, cur / page_size,
+				       xa_mk_value(val), GFP_KERNEL);
+			WARN_ON_ONCE(ent != old);
+			count++;
+		}
+	}
+
+	cmd->dirty.out_nr_dirty = count;
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+out_free:
+	kvfree(tmp);
+out_put:
+	iommufd_put_object(ucmd->ictx, &hwpt->obj);
+	return rc;
+}
+
 void iommufd_selftest_destroy(struct iommufd_object *obj)
 {
 	struct selftest_obj *sobj = container_of(obj, struct selftest_obj, obj);
@@ -1000,6 +1260,7 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 						 cmd->add_reserved.start,
 						 cmd->add_reserved.length);
 	case IOMMU_TEST_OP_MOCK_DOMAIN:
+	case IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS:
 		return iommufd_test_mock_domain(ucmd, cmd);
 	case IOMMU_TEST_OP_MOCK_DOMAIN_REPLACE:
 		return iommufd_test_mock_domain_replace(
@@ -1041,6 +1302,12 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 			return -EINVAL;
 		iommufd_test_memory_limit = cmd->memory_limit.limit;
 		return 0;
+	case IOMMU_TEST_OP_DIRTY:
+		return iommufd_test_dirty(ucmd, cmd->id, cmd->dirty.iova,
+					  cmd->dirty.length,
+					  cmd->dirty.page_size,
+					  u64_to_user_ptr(cmd->dirty.uptr),
+					  cmd->dirty.flags);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c
index 6c810bf80..a3ad5f0b6 100644
--- a/drivers/iommu/iommufd/vfio_compat.c
+++ b/drivers/iommu/iommufd/vfio_compat.c
@@ -41,7 +41,7 @@ int iommufd_vfio_compat_ioas_get_id(struct iommufd_ctx *ictx, u32 *out_ioas_id)
 	if (IS_ERR(ioas))
 		return PTR_ERR(ioas);
 	*out_ioas_id = ioas->obj.id;
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_get_id, IOMMUFD_VFIO);
@@ -98,7 +98,7 @@ int iommufd_vfio_compat_ioas_create(struct iommufd_ctx *ictx)
 
 	if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) {
 		ret = 0;
-		iommufd_put_object(&ictx->vfio_ioas->obj);
+		iommufd_put_object(ictx, &ictx->vfio_ioas->obj);
 		goto out_abort;
 	}
 	ictx->vfio_ioas = ioas;
@@ -133,7 +133,7 @@ int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
 		if (IS_ERR(ioas))
 			return PTR_ERR(ioas);
 		cmd->ioas_id = ioas->obj.id;
-		iommufd_put_object(&ioas->obj);
+		iommufd_put_object(ucmd->ictx, &ioas->obj);
 		return iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
 	case IOMMU_VFIO_IOAS_SET:
@@ -143,7 +143,7 @@ int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd)
 		xa_lock(&ucmd->ictx->objects);
 		ucmd->ictx->vfio_ioas = ioas;
 		xa_unlock(&ucmd->ictx->objects);
-		iommufd_put_object(&ioas->obj);
+		iommufd_put_object(ucmd->ictx, &ioas->obj);
 		return 0;
 
 	case IOMMU_VFIO_IOAS_CLEAR:
@@ -190,7 +190,7 @@ static int iommufd_vfio_map_dma(struct iommufd_ctx *ictx, unsigned int cmd,
 	iova = map.iova;
 	rc = iopt_map_user_pages(ictx, &ioas->iopt, &iova, u64_to_user_ptr(map.vaddr),
 				 map.size, iommu_prot, 0);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -249,13 +249,13 @@ static int iommufd_vfio_unmap_dma(struct iommufd_ctx *ictx, unsigned int cmd,
 		rc = -EFAULT;
 
 err_put:
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
 static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx)
 {
-	struct iommufd_hw_pagetable *hwpt;
+	struct iommufd_hwpt_paging *hwpt_paging;
 	struct iommufd_ioas *ioas;
 	int rc = 1;
 
@@ -264,15 +264,15 @@ static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx)
 		return PTR_ERR(ioas);
 
 	mutex_lock(&ioas->mutex);
-	list_for_each_entry(hwpt, &ioas->hwpt_list, hwpt_item) {
-		if (!hwpt->enforce_cache_coherency) {
+	list_for_each_entry(hwpt_paging, &ioas->hwpt_list, hwpt_item) {
+		if (!hwpt_paging->enforce_cache_coherency) {
 			rc = 0;
 			break;
 		}
 	}
 	mutex_unlock(&ioas->mutex);
 
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -349,7 +349,7 @@ static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type)
 	 */
 	if (type == VFIO_TYPE1_IOMMU)
 		rc = iopt_disable_large_pages(&ioas->iopt);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }
 
@@ -511,7 +511,7 @@ static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx,
 
 out_put:
 	up_read(&ioas->iopt.iova_rwsem);
-	iommufd_put_object(&ioas->obj);
+	iommufd_put_object(ictx, &ioas->obj);
 	return rc;
 }