Merge branch 'iommufd_pri' into iommufd for-next

Lu Baolu says:

====================
This series implements the functionality of delivering IO page faults to
user space through the IOMMUFD framework. One feasible use case is the
nested translation. Nested translation is a hardware feature that supports
two-stage translation tables for IOMMU. The second-stage translation table
is managed by the host VMM, while the first-stage translation table is
owned by user space. This allows user space to control the IOMMU mappings
for its devices.

When an IO page fault occurs on the first-stage translation table, the
IOMMU hardware can deliver the page fault to user space through the
IOMMUFD framework. User space can then handle the page fault and respond
to the device top-down through the IOMMUFD. This allows user space to
implement its own IO page fault handling policies.

User space application that is capable of handling IO page faults should
allocate a fault object, and bind the fault object to any domain that it
is willing to handle the fault generatd for them. On a successful return
of fault object allocation, the user can retrieve and respond to page
faults by reading or writing to the file descriptor (FD) returned.

The iommu selftest framework has been updated to test the IO page fault
delivery and response functionality.
====================

* iommufd_pri:
  iommufd/selftest: Add coverage for IOPF test
  iommufd/selftest: Add IOPF support for mock device
  iommufd: Associate fault object with iommufd_hw_pgtable
  iommufd: Fault-capable hwpt attach/detach/replace
  iommufd: Add iommufd fault object
  iommufd: Add fault and response message definitions
  iommu: Extend domain attach group with handle support
  iommu: Add attach handle to struct iopf_group
  iommu: Remove sva handle list
  iommu: Introduce domain attachment handle

Link: https://lore.kernel.org/all/20240702063444.105814-1-baolu.lu@linux.intel.com
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

18 files changed, 1083 insertions, 117 deletions

diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c
index a7295943fa22..385c488c9cd1 100644
--- a/drivers/dma/idxd/init.c
+++ b/drivers/dma/idxd/init.c
@@ -584,7 +584,7 @@ static int idxd_enable_system_pasid(struct idxd_device *idxd)
 	 * DMA domain is owned by the driver, it should support all valid
 	 * types such as DMA-FQ, identity, etc.
 	 */
-	ret = iommu_attach_device_pasid(domain, dev, pasid);
+	ret = iommu_attach_device_pasid(domain, dev, pasid, NULL);
 	if (ret) {
 		dev_err(dev, "failed to attach device pasid %d, domain type %d",
 			pasid, domain->type);
diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
index 06d78fcc79fd..cd679c13752e 100644
--- a/drivers/iommu/io-pgfault.c
+++ b/drivers/iommu/io-pgfault.c
@@ -59,30 +59,6 @@ void iopf_free_group(struct iopf_group *group)
 }
 EXPORT_SYMBOL_GPL(iopf_free_group);
 
-static struct iommu_domain *get_domain_for_iopf(struct device *dev,
-						struct iommu_fault *fault)
-{
-	struct iommu_domain *domain;
-
-	if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) {
-		domain = iommu_get_domain_for_dev_pasid(dev, fault->prm.pasid, 0);
-		if (IS_ERR(domain))
-			domain = NULL;
-	} else {
-		domain = iommu_get_domain_for_dev(dev);
-	}
-
-	if (!domain || !domain->iopf_handler) {
-		dev_warn_ratelimited(dev,
-			"iopf (pasid %d) without domain attached or handler installed\n",
-			 fault->prm.pasid);
-
-		return NULL;
-	}
-
-	return domain;
-}
-
 /* Non-last request of a group. Postpone until the last one. */
 static int report_partial_fault(struct iommu_fault_param *fault_param,
 				struct iommu_fault *fault)
@@ -134,6 +110,8 @@ static struct iopf_group *iopf_group_alloc(struct iommu_fault_param *iopf_param,
 	list_add(&group->pending_node, &iopf_param->faults);
 	mutex_unlock(&iopf_param->lock);
 
+	group->fault_count = list_count_nodes(&group->faults);
+
 	return group;
 }
 
@@ -206,20 +184,51 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
 	if (group == &abort_group)
 		goto err_abort;
 
-	group->domain = get_domain_for_iopf(dev, fault);
-	if (!group->domain)
+	if (fault->prm.flags & IOMMU_FAULT_PAGE_REQUEST_PASID_VALID) {
+		group->attach_handle = iommu_attach_handle_get(dev->iommu_group,
+							       fault->prm.pasid,
+							       0);
+		if (IS_ERR(group->attach_handle)) {
+			const struct iommu_ops *ops = dev_iommu_ops(dev);
+
+			if (!ops->user_pasid_table)
+				goto err_abort;
+
+			/*
+			 * The iommu driver for this device supports user-
+			 * managed PASID table. Therefore page faults for
+			 * any PASID should go through the NESTING domain
+			 * attached to the device RID.
+			 */
+			group->attach_handle =
+				iommu_attach_handle_get(dev->iommu_group,
+							IOMMU_NO_PASID,
+							IOMMU_DOMAIN_NESTED);
+			if (IS_ERR(group->attach_handle))
+				goto err_abort;
+		}
+	} else {
+		group->attach_handle =
+			iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0);
+		if (IS_ERR(group->attach_handle))
+			goto err_abort;
+	}
+
+	if (!group->attach_handle->domain->iopf_handler)
 		goto err_abort;
 
 	/*
 	 * On success iopf_handler must call iopf_group_response() and
 	 * iopf_free_group()
 	 */
-	if (group->domain->iopf_handler(group))
+	if (group->attach_handle->domain->iopf_handler(group))
 		goto err_abort;
 
 	return;
 
 err_abort:
+	dev_warn_ratelimited(dev, "iopf with pasid %d aborted\n",
+			     fault->prm.pasid);
 	iopf_group_response(group, IOMMU_PAGE_RESP_FAILURE);
 	if (group == &abort_group)
 		__iopf_free_group(group);
diff --git a/drivers/iommu/iommu-priv.h b/drivers/iommu/iommu-priv.h
index 5f731d994803..c37801c32f33 100644
--- a/drivers/iommu/iommu-priv.h
+++ b/drivers/iommu/iommu-priv.h
@@ -28,4 +28,15 @@ void iommu_device_unregister_bus(struct iommu_device *iommu,
 				 const struct bus_type *bus,
 				 struct notifier_block *nb);
 
+struct iommu_attach_handle *iommu_attach_handle_get(struct iommu_group *group,
+						    ioasid_t pasid,
+						    unsigned int type);
+int iommu_attach_group_handle(struct iommu_domain *domain,
+			      struct iommu_group *group,
+			      struct iommu_attach_handle *handle);
+void iommu_detach_group_handle(struct iommu_domain *domain,
+			       struct iommu_group *group);
+int iommu_replace_group_handle(struct iommu_group *group,
+			       struct iommu_domain *new_domain,
+			       struct iommu_attach_handle *handle);
 #endif /* __LINUX_IOMMU_PRIV_H */
diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c
index 18a35e798b72..69cde094440e 100644
--- a/drivers/iommu/iommu-sva.c
+++ b/drivers/iommu/iommu-sva.c
@@ -41,7 +41,6 @@ static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct de
 	}
 	iommu_mm->pasid = pasid;
 	INIT_LIST_HEAD(&iommu_mm->sva_domains);
-	INIT_LIST_HEAD(&iommu_mm->sva_handles);
 	/*
 	 * Make sure the write to mm->iommu_mm is not reordered in front of
 	 * initialization to iommu_mm fields. If it does, readers may see a
@@ -69,11 +68,16 @@ static struct iommu_mm_data *iommu_alloc_mm_data(struct mm_struct *mm, struct de
  */
 struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
+	struct iommu_group *group = dev->iommu_group;
+	struct iommu_attach_handle *attach_handle;
 	struct iommu_mm_data *iommu_mm;
 	struct iommu_domain *domain;
 	struct iommu_sva *handle;
 	int ret;
 
+	if (!group)
+		return ERR_PTR(-ENODEV);
+
 	mutex_lock(&iommu_sva_lock);
 
 	/* Allocate mm->pasid if necessary. */
@@ -83,12 +87,22 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 		goto out_unlock;
 	}
 
-	list_for_each_entry(handle, &mm->iommu_mm->sva_handles, handle_item) {
-		if (handle->dev == dev) {
-			refcount_inc(&handle->users);
-			mutex_unlock(&iommu_sva_lock);
-			return handle;
+	/* A bond already exists, just take a reference`. */
+	attach_handle = iommu_attach_handle_get(group, iommu_mm->pasid, IOMMU_DOMAIN_SVA);
+	if (!IS_ERR(attach_handle)) {
+		handle = container_of(attach_handle, struct iommu_sva, handle);
+		if (attach_handle->domain->mm != mm) {
+			ret = -EBUSY;
+			goto out_unlock;
 		}
+		refcount_inc(&handle->users);
+		mutex_unlock(&iommu_sva_lock);
+		return handle;
+	}
+
+	if (PTR_ERR(attach_handle) != -ENOENT) {
+		ret = PTR_ERR(attach_handle);
+		goto out_unlock;
 	}
 
 	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
@@ -99,7 +113,8 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 
 	/* Search for an existing domain. */
 	list_for_each_entry(domain, &mm->iommu_mm->sva_domains, next) {
-		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
+		ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid,
+						&handle->handle);
 		if (!ret) {
 			domain->users++;
 			goto out;
@@ -113,7 +128,8 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 		goto out_free_handle;
 	}
 
-	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid);
+	ret = iommu_attach_device_pasid(domain, dev, iommu_mm->pasid,
+					&handle->handle);
 	if (ret)
 		goto out_free_domain;
 	domain->users = 1;
@@ -121,10 +137,8 @@ struct iommu_sva *iommu_sva_bind_device(struct device *dev, struct mm_struct *mm
 
 out:
 	refcount_set(&handle->users, 1);
-	list_add(&handle->handle_item, &mm->iommu_mm->sva_handles);
 	mutex_unlock(&iommu_sva_lock);
 	handle->dev = dev;
-	handle->domain = domain;
 	return handle;
 
 out_free_domain:
@@ -147,7 +161,7 @@ EXPORT_SYMBOL_GPL(iommu_sva_bind_device);
  */
 void iommu_sva_unbind_device(struct iommu_sva *handle)
 {
-	struct iommu_domain *domain = handle->domain;
+	struct iommu_domain *domain = handle->handle.domain;
 	struct iommu_mm_data *iommu_mm = domain->mm->iommu_mm;
 	struct device *dev = handle->dev;
 
@@ -156,7 +170,6 @@ void iommu_sva_unbind_device(struct iommu_sva *handle)
 		mutex_unlock(&iommu_sva_lock);
 		return;
 	}
-	list_del(&handle->handle_item);
 
 	iommu_detach_device_pasid(domain, dev, iommu_mm->pasid);
 	if (--domain->users == 0) {
@@ -170,7 +183,7 @@ EXPORT_SYMBOL_GPL(iommu_sva_unbind_device);
 
 u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 {
-	struct iommu_domain *domain = handle->domain;
+	struct iommu_domain *domain = handle->handle.domain;
 
 	return mm_get_enqcmd_pasid(domain->mm);
 }
@@ -259,7 +272,8 @@ static void iommu_sva_handle_iopf(struct work_struct *work)
 		if (status != IOMMU_PAGE_RESP_SUCCESS)
 			break;
 
-		status = iommu_sva_handle_mm(&iopf->fault, group->domain->mm);
+		status = iommu_sva_handle_mm(&iopf->fault,
+					     group->attach_handle->domain->mm);
 	}
 
 	iopf_group_response(group, status);
diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 9df7cc75c1bc..8484285fbaa8 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -3352,16 +3352,17 @@ static void __iommu_remove_group_pasid(struct iommu_group *group,
  * @domain: the iommu domain.
  * @dev: the attached device.
  * @pasid: the pasid of the device.
+ * @handle: the attach handle.
  *
  * Return: 0 on success, or an error.
  */
 int iommu_attach_device_pasid(struct iommu_domain *domain,
-			      struct device *dev, ioasid_t pasid)
+			      struct device *dev, ioasid_t pasid,
+			      struct iommu_attach_handle *handle)
 {
 	/* Caller must be a probed driver on dev */
 	struct iommu_group *group = dev->iommu_group;
 	struct group_device *device;
-	void *curr;
 	int ret;
 
 	if (!domain->ops->set_dev_pasid)
@@ -3382,11 +3383,12 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 		}
 	}
 
-	curr = xa_cmpxchg(&group->pasid_array, pasid, NULL, domain, GFP_KERNEL);
-	if (curr) {
-		ret = xa_err(curr) ? : -EBUSY;
+	if (handle)
+		handle->domain = domain;
+
+	ret = xa_insert(&group->pasid_array, pasid, handle, GFP_KERNEL);
+	if (ret)
 		goto out_unlock;
-	}
 
 	ret = __iommu_set_group_pasid(domain, group, pasid);
 	if (ret)
@@ -3414,46 +3416,11 @@ void iommu_detach_device_pasid(struct iommu_domain *domain, struct device *dev,
 
 	mutex_lock(&group->mutex);
 	__iommu_remove_group_pasid(group, pasid, domain);
-	WARN_ON(xa_erase(&group->pasid_array, pasid) != domain);
+	xa_erase(&group->pasid_array, pasid);
 	mutex_unlock(&group->mutex);
 }
 EXPORT_SYMBOL_GPL(iommu_detach_device_pasid);
 
-/*
- * iommu_get_domain_for_dev_pasid() - Retrieve domain for @pasid of @dev
- * @dev: the queried device
- * @pasid: the pasid of the device
- * @type: matched domain type, 0 for any match
- *
- * This is a variant of iommu_get_domain_for_dev(). It returns the existing
- * domain attached to pasid of a device. Callers must hold a lock around this
- * function, and both iommu_attach/detach_dev_pasid() whenever a domain of
- * type is being manipulated. This API does not internally resolve races with
- * attach/detach.
- *
- * Return: attached domain on success, NULL otherwise.
- */
-struct iommu_domain *iommu_get_domain_for_dev_pasid(struct device *dev,
-						    ioasid_t pasid,
-						    unsigned int type)
-{
-	/* Caller must be a probed driver on dev */
-	struct iommu_group *group = dev->iommu_group;
-	struct iommu_domain *domain;
-
-	if (!group)
-		return NULL;
-
-	xa_lock(&group->pasid_array);
-	domain = xa_load(&group->pasid_array, pasid);
-	if (type && domain && domain->type != type)
-		domain = ERR_PTR(-EBUSY);
-	xa_unlock(&group->pasid_array);
-
-	return domain;
-}
-EXPORT_SYMBOL_GPL(iommu_get_domain_for_dev_pasid);
-
 ioasid_t iommu_alloc_global_pasid(struct device *dev)
 {
 	int ret;
@@ -3480,3 +3447,137 @@ void iommu_free_global_pasid(ioasid_t pasid)
 	ida_free(&iommu_global_pasid_ida, pasid);
 }
 EXPORT_SYMBOL_GPL(iommu_free_global_pasid);
+
+/**
+ * iommu_attach_handle_get - Return the attach handle
+ * @group: the iommu group that domain was attached to
+ * @pasid: the pasid within the group
+ * @type: matched domain type, 0 for any match
+ *
+ * Return handle or ERR_PTR(-ENOENT) on none, ERR_PTR(-EBUSY) on mismatch.
+ *
+ * Return the attach handle to the caller. The life cycle of an iommu attach
+ * handle is from the time when the domain is attached to the time when the
+ * domain is detached. Callers are required to synchronize the call of
+ * iommu_attach_handle_get() with domain attachment and detachment. The attach
+ * handle can only be used during its life cycle.
+ */
+struct iommu_attach_handle *
+iommu_attach_handle_get(struct iommu_group *group, ioasid_t pasid, unsigned int type)
+{
+	struct iommu_attach_handle *handle;
+
+	xa_lock(&group->pasid_array);
+	handle = xa_load(&group->pasid_array, pasid);
+	if (!handle)
+		handle = ERR_PTR(-ENOENT);
+	else if (type && handle->domain->type != type)
+		handle = ERR_PTR(-EBUSY);
+	xa_unlock(&group->pasid_array);
+
+	return handle;
+}
+EXPORT_SYMBOL_NS_GPL(iommu_attach_handle_get, IOMMUFD_INTERNAL);
+
+/**
+ * iommu_attach_group_handle - Attach an IOMMU domain to an IOMMU group
+ * @domain: IOMMU domain to attach
+ * @group: IOMMU group that will be attached
+ * @handle: attach handle
+ *
+ * Returns 0 on success and error code on failure.
+ *
+ * This is a variant of iommu_attach_group(). It allows the caller to provide
+ * an attach handle and use it when the domain is attached. This is currently
+ * used by IOMMUFD to deliver the I/O page faults.
+ */
+int iommu_attach_group_handle(struct iommu_domain *domain,
+			      struct iommu_group *group,
+			      struct iommu_attach_handle *handle)
+{
+	int ret;
+
+	if (handle)
+		handle->domain = domain;
+
+	mutex_lock(&group->mutex);
+	ret = xa_insert(&group->pasid_array, IOMMU_NO_PASID, handle, GFP_KERNEL);
+	if (ret)
+		goto err_unlock;
+
+	ret = __iommu_attach_group(domain, group);
+	if (ret)
+		goto err_erase;
+	mutex_unlock(&group->mutex);
+
+	return 0;
+err_erase:
+	xa_erase(&group->pasid_array, IOMMU_NO_PASID);
+err_unlock:
+	mutex_unlock(&group->mutex);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(iommu_attach_group_handle, IOMMUFD_INTERNAL);
+
+/**
+ * iommu_detach_group_handle - Detach an IOMMU domain from an IOMMU group
+ * @domain: IOMMU domain to attach
+ * @group: IOMMU group that will be attached
+ *
+ * Detach the specified IOMMU domain from the specified IOMMU group.
+ * It must be used in conjunction with iommu_attach_group_handle().
+ */
+void iommu_detach_group_handle(struct iommu_domain *domain,
+			       struct iommu_group *group)
+{
+	mutex_lock(&group->mutex);
+	__iommu_group_set_core_domain(group);
+	xa_erase(&group->pasid_array, IOMMU_NO_PASID);
+	mutex_unlock(&group->mutex);
+}
+EXPORT_SYMBOL_NS_GPL(iommu_detach_group_handle, IOMMUFD_INTERNAL);
+
+/**
+ * iommu_replace_group_handle - replace the domain that a group is attached to
+ * @group: IOMMU group that will be attached to the new domain
+ * @new_domain: new IOMMU domain to replace with
+ * @handle: attach handle
+ *
+ * This is a variant of iommu_group_replace_domain(). It allows the caller to
+ * provide an attach handle for the new domain and use it when the domain is
+ * attached.
+ */
+int iommu_replace_group_handle(struct iommu_group *group,
+			       struct iommu_domain *new_domain,
+			       struct iommu_attach_handle *handle)
+{
+	void *curr;
+	int ret;
+
+	if (!new_domain)
+		return -EINVAL;
+
+	mutex_lock(&group->mutex);
+	if (handle) {
+		ret = xa_reserve(&group->pasid_array, IOMMU_NO_PASID, GFP_KERNEL);
+		if (ret)
+			goto err_unlock;
+	}
+
+	ret = __iommu_group_set_domain(group, new_domain);
+	if (ret)
+		goto err_release;
+
+	curr = xa_store(&group->pasid_array, IOMMU_NO_PASID, handle, GFP_KERNEL);
+	WARN_ON(xa_is_err(curr));
+
+	mutex_unlock(&group->mutex);
+
+	return 0;
+err_release:
+	xa_release(&group->pasid_array, IOMMU_NO_PASID);
+err_unlock:
+	mutex_unlock(&group->mutex);
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, IOMMUFD_INTERNAL);
diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile
index 34b446146961..cf4605962bea 100644
--- a/drivers/iommu/iommufd/Makefile
+++ b/drivers/iommu/iommufd/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 iommufd-y := \
 	device.o \
+	fault.o \
 	hw_pagetable.o \
 	io_pagetable.o \
 	ioas.o \
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 873630c111c1..9a7ec5997c61 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -215,6 +215,7 @@ struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 	refcount_inc(&idev->obj.users);
 	/* igroup refcount moves into iommufd_device */
 	idev->igroup = igroup;
+	mutex_init(&idev->iopf_lock);
 
 	/*
 	 * If the caller fails after this success it must call
@@ -376,7 +377,7 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 	 * attachment.
 	 */
 	if (list_empty(&idev->igroup->device_list)) {
-		rc = iommu_attach_group(hwpt->domain, idev->igroup->group);
+		rc = iommufd_hwpt_attach_device(hwpt, idev);
 		if (rc)
 			goto err_unresv;
 		idev->igroup->hwpt = hwpt;
@@ -402,7 +403,7 @@ iommufd_hw_pagetable_detach(struct iommufd_device *idev)
 	mutex_lock(&idev->igroup->lock);
 	list_del(&idev->group_item);
 	if (list_empty(&idev->igroup->device_list)) {
-		iommu_detach_group(hwpt->domain, idev->igroup->group);
+		iommufd_hwpt_detach_device(hwpt, idev);
 		idev->igroup->hwpt = NULL;
 	}
 	if (hwpt_is_paging(hwpt))
@@ -497,7 +498,7 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 			goto err_unlock;
 	}
 
-	rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
+	rc = iommufd_hwpt_replace_device(idev, hwpt, old_hwpt);
 	if (rc)
 		goto err_unresv;
 
diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c
new file mode 100644
index 000000000000..54d6cd20a673
--- /dev/null
+++ b/drivers/iommu/iommufd/fault.c
@@ -0,0 +1,433 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation
+ */
+#define pr_fmt(fmt) "iommufd: " fmt
+
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/iommufd.h>
+#include <linux/pci.h>
+#include <linux/poll.h>
+#include <linux/anon_inodes.h>
+#include <uapi/linux/iommufd.h>
+
+#include "../iommu-priv.h"
+#include "iommufd_private.h"
+
+static int iommufd_fault_iopf_enable(struct iommufd_device *idev)
+{
+	struct device *dev = idev->dev;
+	int ret;
+
+	/*
+	 * Once we turn on PCI/PRI support for VF, the response failure code
+	 * should not be forwarded to the hardware due to PRI being a shared
+	 * resource between PF and VFs. There is no coordination for this
+	 * shared capability. This waits for a vPRI reset to recover.
+	 */
+	if (dev_is_pci(dev) && to_pci_dev(dev)->is_virtfn)
+		return -EINVAL;
+
+	mutex_lock(&idev->iopf_lock);
+	/* Device iopf has already been on. */
+	if (++idev->iopf_enabled > 1) {
+		mutex_unlock(&idev->iopf_lock);
+		return 0;
+	}
+
+	ret = iommu_dev_enable_feature(dev, IOMMU_DEV_FEAT_IOPF);
+	if (ret)
+		--idev->iopf_enabled;
+	mutex_unlock(&idev->iopf_lock);
+
+	return ret;
+}
+
+static void iommufd_fault_iopf_disable(struct iommufd_device *idev)
+{
+	mutex_lock(&idev->iopf_lock);
+	if (!WARN_ON(idev->iopf_enabled == 0)) {
+		if (--idev->iopf_enabled == 0)
+			iommu_dev_disable_feature(idev->dev, IOMMU_DEV_FEAT_IOPF);
+	}
+	mutex_unlock(&idev->iopf_lock);
+}
+
+static int __fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+	int ret;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	handle->idev = idev;
+	ret = iommu_attach_group_handle(hwpt->domain, idev->igroup->group,
+					&handle->handle);
+	if (ret)
+		kfree(handle);
+
+	return ret;
+}
+
+int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
+				    struct iommufd_device *idev)
+{
+	int ret;
+
+	if (!hwpt->fault)
+		return -EINVAL;
+
+	ret = iommufd_fault_iopf_enable(idev);
+	if (ret)
+		return ret;
+
+	ret = __fault_domain_attach_dev(hwpt, idev);
+	if (ret)
+		iommufd_fault_iopf_disable(idev);
+
+	return ret;
+}
+
+static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
+					 struct iommufd_attach_handle *handle)
+{
+	struct iommufd_fault *fault = hwpt->fault;
+	struct iopf_group *group, *next;
+	unsigned long index;
+
+	if (!fault)
+		return;
+
+	mutex_lock(&fault->mutex);
+	list_for_each_entry_safe(group, next, &fault->deliver, node) {
+		if (group->attach_handle != &handle->handle)
+			continue;
+		list_del(&group->node);
+		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
+		iopf_free_group(group);
+	}
+
+	xa_for_each(&fault->response, index, group) {
+		if (group->attach_handle != &handle->handle)
+			continue;
+		xa_erase(&fault->response, index);
+		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
+		iopf_free_group(group);
+	}
+	mutex_unlock(&fault->mutex);
+}
+
+static struct iommufd_attach_handle *
+iommufd_device_get_attach_handle(struct iommufd_device *idev)
+{
+	struct iommu_attach_handle *handle;
+
+	handle = iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID, 0);
+	if (!handle)
+		return NULL;
+
+	return to_iommufd_handle(handle);
+}
+
+void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+
+	handle = iommufd_device_get_attach_handle(idev);
+	iommu_detach_group_handle(hwpt->domain, idev->igroup->group);
+	iommufd_auto_response_faults(hwpt, handle);
+	iommufd_fault_iopf_disable(idev);
+	kfree(handle);
+}
+
+static int __fault_domain_replace_dev(struct iommufd_device *idev,
+				      struct iommufd_hw_pagetable *hwpt,
+				      struct iommufd_hw_pagetable *old)
+{
+	struct iommufd_attach_handle *handle, *curr = NULL;
+	int ret;
+
+	if (old->fault)
+		curr = iommufd_device_get_attach_handle(idev);
+
+	if (hwpt->fault) {
+		handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+		if (!handle)
+			return -ENOMEM;
+
+		handle->handle.domain = hwpt->domain;
+		handle->idev = idev;
+		ret = iommu_replace_group_handle(idev->igroup->group,
+						 hwpt->domain, &handle->handle);
+	} else {
+		ret = iommu_replace_group_handle(idev->igroup->group,
+						 hwpt->domain, NULL);
+	}
+
+	if (!ret && curr) {
+		iommufd_auto_response_faults(old, curr);
+		kfree(curr);
+	}
+
+	return ret;
+}
+
+int iommufd_fault_domain_replace_dev(struct iommufd_device *idev,
+				     struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_hw_pagetable *old)
+{
+	bool iopf_off = !hwpt->fault && old->fault;
+	bool iopf_on = hwpt->fault && !old->fault;
+	int ret;
+
+	if (iopf_on) {
+		ret = iommufd_fault_iopf_enable(idev);
+		if (ret)
+			return ret;
+	}
+
+	ret = __fault_domain_replace_dev(idev, hwpt, old);
+	if (ret) {
+		if (iopf_on)
+			iommufd_fault_iopf_disable(idev);
+		return ret;
+	}
+
+	if (iopf_off)
+		iommufd_fault_iopf_disable(idev);
+
+	return 0;
+}
+
+void iommufd_fault_destroy(struct iommufd_object *obj)
+{
+	struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj);
+	struct iopf_group *group, *next;
+
+	/*
+	 * The iommufd object's reference count is zero at this point.
+	 * We can be confident that no other threads are currently
+	 * accessing this pointer. Therefore, acquiring the mutex here
+	 * is unnecessary.
+	 */
+	list_for_each_entry_safe(group, next, &fault->deliver, node) {
+		list_del(&group->node);
+		iopf_group_response(group, IOMMU_PAGE_RESP_INVALID);
+		iopf_free_group(group);
+	}
+}
+
+static void iommufd_compose_fault_message(struct iommu_fault *fault,
+					  struct iommu_hwpt_pgfault *hwpt_fault,
+					  struct iommufd_device *idev,
+					  u32 cookie)
+{
+	hwpt_fault->flags = fault->prm.flags;
+	hwpt_fault->dev_id = idev->obj.id;
+	hwpt_fault->pasid = fault->prm.pasid;
+	hwpt_fault->grpid = fault->prm.grpid;
+	hwpt_fault->perm = fault->prm.perm;
+	hwpt_fault->addr = fault->prm.addr;
+	hwpt_fault->length = 0;
+	hwpt_fault->cookie = cookie;
+}
+
+static ssize_t iommufd_fault_fops_read(struct file *filep, char __user *buf,
+				       size_t count, loff_t *ppos)
+{
+	size_t fault_size = sizeof(struct iommu_hwpt_pgfault);
+	struct iommufd_fault *fault = filep->private_data;
+	struct iommu_hwpt_pgfault data;
+	struct iommufd_device *idev;
+	struct iopf_group *group;
+	struct iopf_fault *iopf;
+	size_t done = 0;
+	int rc = 0;
+
+	if (*ppos || count % fault_size)
+		return -ESPIPE;
+
+	mutex_lock(&fault->mutex);
+	while (!list_empty(&fault->deliver) && count > done) {
+		group = list_first_entry(&fault->deliver,
+					 struct iopf_group, node);
+
+		if (group->fault_count * fault_size > count - done)
+			break;
+
+		rc = xa_alloc(&fault->response, &group->cookie, group,
+			      xa_limit_32b, GFP_KERNEL);
+		if (rc)
+			break;
+
+		idev = to_iommufd_handle(group->attach_handle)->idev;
+		list_for_each_entry(iopf, &group->faults, list) {
+			iommufd_compose_fault_message(&iopf->fault,
+						      &data, idev,
+						      group->cookie);
+			if (copy_to_user(buf + done, &data, fault_size)) {
+				xa_erase(&fault->response, group->cookie);
+				rc = -EFAULT;
+				break;
+			}
+			done += fault_size;
+		}
+
+		list_del(&group->node);
+	}
+	mutex_unlock(&fault->mutex);
+
+	return done == 0 ? rc : done;
+}
+
+static ssize_t iommufd_fault_fops_write(struct file *filep, const char __user *buf,
+					size_t count, loff_t *ppos)
+{
+	size_t response_size = sizeof(struct iommu_hwpt_page_response);
+	struct iommufd_fault *fault = filep->private_data;
+	struct iommu_hwpt_page_response response;
+	struct iopf_group *group;
+	size_t done = 0;
+	int rc = 0;
+
+	if (*ppos || count % response_size)
+		return -ESPIPE;
+
+	mutex_lock(&fault->mutex);
+	while (count > done) {
+		rc = copy_from_user(&response, buf + done, response_size);
+		if (rc)
+			break;
+
+		group = xa_erase(&fault->response, response.cookie);
+		if (!group) {
+			rc = -EINVAL;
+			break;
+		}
+
+		iopf_group_response(group, response.code);
+		iopf_free_group(group);
+		done += response_size;
+	}
+	mutex_unlock(&fault->mutex);
+
+	return done == 0 ? rc : done;
+}
+
+static __poll_t iommufd_fault_fops_poll(struct file *filep,
+					struct poll_table_struct *wait)
+{
+	struct iommufd_fault *fault = filep->private_data;
+	__poll_t pollflags = EPOLLOUT;
+
+	poll_wait(filep, &fault->wait_queue, wait);
+	mutex_lock(&fault->mutex);
+	if (!list_empty(&fault->deliver))
+		pollflags |= EPOLLIN | EPOLLRDNORM;
+	mutex_unlock(&fault->mutex);
+
+	return pollflags;
+}
+
+static int iommufd_fault_fops_release(struct inode *inode, struct file *filep)
+{
+	struct iommufd_fault *fault = filep->private_data;
+
+	refcount_dec(&fault->obj.users);
+	iommufd_ctx_put(fault->ictx);
+	return 0;
+}
+
+static const struct file_operations iommufd_fault_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nonseekable_open,
+	.read		= iommufd_fault_fops_read,
+	.write		= iommufd_fault_fops_write,
+	.poll		= iommufd_fault_fops_poll,
+	.release	= iommufd_fault_fops_release,
+	.llseek		= no_llseek,
+};
+
+int iommufd_fault_alloc(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_fault_alloc *cmd = ucmd->cmd;
+	struct iommufd_fault *fault;
+	struct file *filep;
+	int fdno;
+	int rc;
+
+	if (cmd->flags)
+		return -EOPNOTSUPP;
+
+	fault = iommufd_object_alloc(ucmd->ictx, fault, IOMMUFD_OBJ_FAULT);
+	if (IS_ERR(fault))
+		return PTR_ERR(fault);
+
+	fault->ictx = ucmd->ictx;
+	INIT_LIST_HEAD(&fault->deliver);
+	xa_init_flags(&fault->response, XA_FLAGS_ALLOC1);
+	mutex_init(&fault->mutex);
+	init_waitqueue_head(&fault->wait_queue);
+
+	filep = anon_inode_getfile("[iommufd-pgfault]", &iommufd_fault_fops,
+				   fault, O_RDWR);
+	if (IS_ERR(filep)) {
+		rc = PTR_ERR(filep);
+		goto out_abort;
+	}
+
+	refcount_inc(&fault->obj.users);
+	iommufd_ctx_get(fault->ictx);
+	fault->filep = filep;
+
+	fdno = get_unused_fd_flags(O_CLOEXEC);
+	if (fdno < 0) {
+		rc = fdno;
+		goto out_fput;
+	}
+
+	cmd->out_fault_id = fault->obj.id;
+	cmd->out_fault_fd = fdno;
+
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+	if (rc)
+		goto out_put_fdno;
+	iommufd_object_finalize(ucmd->ictx, &fault->obj);
+
+	fd_install(fdno, fault->filep);
+
+	return 0;
+out_put_fdno:
+	put_unused_fd(fdno);
+out_fput:
+	fput(filep);
+	refcount_dec(&fault->obj.users);
+	iommufd_ctx_put(fault->ictx);
+out_abort:
+	iommufd_object_abort_and_destroy(ucmd->ictx, &fault->obj);
+
+	return rc;
+}
+
+int iommufd_fault_iopf_handler(struct iopf_group *group)
+{
+	struct iommufd_hw_pagetable *hwpt;
+	struct iommufd_fault *fault;
+
+	hwpt = group->attach_handle->domain->fault_data;
+	fault = hwpt->fault;
+
+	mutex_lock(&fault->mutex);
+	list_add_tail(&group->node, &fault->deliver);
+	mutex_unlock(&fault->mutex);
+
+	wake_up_interruptible(&fault->wait_queue);
+
+	return 0;
+}
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 33d142f8057d..e63f80f087d1 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -8,6 +8,15 @@
 #include "../iommu-priv.h"
 #include "iommufd_private.h"
 
+static void __iommufd_hwpt_destroy(struct iommufd_hw_pagetable *hwpt)
+{
+	if (hwpt->domain)
+		iommu_domain_free(hwpt->domain);
+
+	if (hwpt->fault)
+		refcount_dec(&hwpt->fault->obj.users);
+}
+
 void iommufd_hwpt_paging_destroy(struct iommufd_object *obj)
 {
 	struct iommufd_hwpt_paging *hwpt_paging =
@@ -22,9 +31,7 @@ void iommufd_hwpt_paging_destroy(struct iommufd_object *obj)
 					 hwpt_paging->common.domain);
 	}
 
-	if (hwpt_paging->common.domain)
-		iommu_domain_free(hwpt_paging->common.domain);
-
+	__iommufd_hwpt_destroy(&hwpt_paging->common);
 	refcount_dec(&hwpt_paging->ioas->obj.users);
 }
 
@@ -49,9 +56,7 @@ void iommufd_hwpt_nested_destroy(struct iommufd_object *obj)
 	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);
-
+	__iommufd_hwpt_destroy(&hwpt_nested->common);
 	refcount_dec(&hwpt_nested->parent->common.obj.users);
 }
 
@@ -213,7 +218,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 	struct iommufd_hw_pagetable *hwpt;
 	int rc;
 
-	if (flags || !user_data->len || !ops->domain_alloc_user)
+	if ((flags & ~IOMMU_HWPT_FAULT_ID_VALID) ||
+	    !user_data->len || !ops->domain_alloc_user)
 		return ERR_PTR(-EOPNOTSUPP);
 	if (parent->auto_domain || !parent->nest_parent)
 		return ERR_PTR(-EINVAL);
@@ -227,7 +233,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 	refcount_inc(&parent->common.obj.users);
 	hwpt_nested->parent = parent;
 
-	hwpt->domain = ops->domain_alloc_user(idev->dev, flags,
+	hwpt->domain = ops->domain_alloc_user(idev->dev,
+					      flags & ~IOMMU_HWPT_FAULT_ID_VALID,
 					      parent->common.domain, user_data);
 	if (IS_ERR(hwpt->domain)) {
 		rc = PTR_ERR(hwpt->domain);
@@ -308,6 +315,21 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 		goto out_put_pt;
 	}
 
+	if (cmd->flags & IOMMU_HWPT_FAULT_ID_VALID) {
+		struct iommufd_fault *fault;
+
+		fault = iommufd_get_fault(ucmd, cmd->fault_id);
+		if (IS_ERR(fault)) {
+			rc = PTR_ERR(fault);
+			goto out_hwpt;
+		}
+		hwpt->fault = fault;
+		hwpt->domain->iopf_handler = iommufd_fault_iopf_handler;
+		hwpt->domain->fault_data = hwpt;
+		refcount_inc(&fault->obj.users);
+		iommufd_put_object(ucmd->ictx, &fault->obj);
+	}
+
 	cmd->out_hwpt_id = hwpt->obj.id;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 	if (rc)
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 991f864d1f9b..92efe30a8f0d 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -11,6 +11,7 @@
 #include <linux/iommu.h>
 #include <linux/iova_bitmap.h>
 #include <uapi/linux/iommufd.h>
+#include "../iommu-priv.h"
 
 struct iommu_domain;
 struct iommu_group;
@@ -128,6 +129,7 @@ enum iommufd_object_type {
 	IOMMUFD_OBJ_HWPT_NESTED,
 	IOMMUFD_OBJ_IOAS,
 	IOMMUFD_OBJ_ACCESS,
+	IOMMUFD_OBJ_FAULT,
 #ifdef CONFIG_IOMMUFD_TEST
 	IOMMUFD_OBJ_SELFTEST,
 #endif
@@ -292,6 +294,7 @@ int iommufd_check_iova_range(struct io_pagetable *iopt,
 struct iommufd_hw_pagetable {
 	struct iommufd_object obj;
 	struct iommu_domain *domain;
+	struct iommufd_fault *fault;
 };
 
 struct iommufd_hwpt_paging {
@@ -395,6 +398,9 @@ struct iommufd_device {
 	/* always the physical device */
 	struct device *dev;
 	bool enforce_cache_coherency;
+	/* protect iopf_enabled counter */
+	struct mutex iopf_lock;
+	unsigned int iopf_enabled;
 };
 
 static inline struct iommufd_device *
@@ -426,6 +432,80 @@ void iopt_remove_access(struct io_pagetable *iopt,
 			u32 iopt_access_list_id);
 void iommufd_access_destroy_object(struct iommufd_object *obj);
 
+/*
+ * An iommufd_fault object represents an interface to deliver I/O page faults
+ * to the user space. These objects are created/destroyed by the user space and
+ * associated with hardware page table objects during page-table allocation.
+ */
+struct iommufd_fault {
+	struct iommufd_object obj;
+	struct iommufd_ctx *ictx;
+	struct file *filep;
+
+	/* The lists of outstanding faults protected by below mutex. */
+	struct mutex mutex;
+	struct list_head deliver;
+	struct xarray response;
+
+	struct wait_queue_head wait_queue;
+};
+
+struct iommufd_attach_handle {
+	struct iommu_attach_handle handle;
+	struct iommufd_device *idev;
+};
+
+/* Convert an iommu attach handle to iommufd handle. */
+#define to_iommufd_handle(hdl)	container_of(hdl, struct iommufd_attach_handle, handle)
+
+static inline struct iommufd_fault *
+iommufd_get_fault(struct iommufd_ucmd *ucmd, u32 id)
+{
+	return container_of(iommufd_get_object(ucmd->ictx, id,
+					       IOMMUFD_OBJ_FAULT),
+			    struct iommufd_fault, obj);
+}
+
+int iommufd_fault_alloc(struct iommufd_ucmd *ucmd);
+void iommufd_fault_destroy(struct iommufd_object *obj);
+int iommufd_fault_iopf_handler(struct iopf_group *group);
+
+int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
+				    struct iommufd_device *idev);
+void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_device *idev);
+int iommufd_fault_domain_replace_dev(struct iommufd_device *idev,
+				     struct iommufd_hw_pagetable *hwpt,
+				     struct iommufd_hw_pagetable *old);
+
+static inline int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt,
+					     struct iommufd_device *idev)
+{
+	if (hwpt->fault)
+		return iommufd_fault_domain_attach_dev(hwpt, idev);
+
+	return iommu_attach_group(hwpt->domain, idev->igroup->group);
+}
+
+static inline void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt,
+					      struct iommufd_device *idev)
+{
+	if (hwpt->fault)
+		iommufd_fault_domain_detach_dev(hwpt, idev);
+
+	iommu_detach_group(hwpt->domain, idev->igroup->group);
+}
+
+static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev,
+					      struct iommufd_hw_pagetable *hwpt,
+					      struct iommufd_hw_pagetable *old)
+{
+	if (old->fault || hwpt->fault)
+		return iommufd_fault_domain_replace_dev(idev, hwpt, old);
+
+	return iommu_group_replace_domain(idev->igroup->group, hwpt->domain);
+}
+
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
 void iommufd_selftest_destroy(struct iommufd_object *obj);
diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h
index e854d3f67205..acbbba1c6671 100644
--- a/drivers/iommu/iommufd/iommufd_test.h
+++ b/drivers/iommu/iommufd/iommufd_test.h
@@ -22,6 +22,7 @@ enum {
 	IOMMU_TEST_OP_MOCK_DOMAIN_FLAGS,
 	IOMMU_TEST_OP_DIRTY,
 	IOMMU_TEST_OP_MD_CHECK_IOTLB,
+	IOMMU_TEST_OP_TRIGGER_IOPF,
 };
 
 enum {
@@ -127,6 +128,13 @@ struct iommu_test_cmd {
 			__u32 id;
 			__u32 iotlb;
 		} check_iotlb;
+		struct {
+			__u32 dev_id;
+			__u32 pasid;
+			__u32 grpid;
+			__u32 perm;
+			__u64 addr;
+		} trigger_iopf;
 	};
 	__u32 last;
 };
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 39b32932c61e..83bbd7c5d160 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -319,6 +319,7 @@ static int iommufd_option(struct iommufd_ucmd *ucmd)
 
 union ucmd_buffer {
 	struct iommu_destroy destroy;
+	struct iommu_fault_alloc fault;
 	struct iommu_hw_info info;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
@@ -355,6 +356,8 @@ struct iommufd_ioctl_op {
 	}
 static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 	IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id),
+	IOCTL_OP(IOMMU_FAULT_QUEUE_ALLOC, iommufd_fault_alloc, struct iommu_fault_alloc,
+		 out_fault_fd),
 	IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info,
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc,
@@ -513,6 +516,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = {
 		.destroy = iommufd_hwpt_nested_destroy,
 		.abort = iommufd_hwpt_nested_abort,
 	},
+	[IOMMUFD_OBJ_FAULT] = {
+		.destroy = iommufd_fault_destroy,
+	},
 #ifdef CONFIG_IOMMUFD_TEST
 	[IOMMUFD_OBJ_SELFTEST] = {
 		.destroy = iommufd_selftest_destroy,
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 7a70a3e0fee6..f95e32e29133 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -504,6 +504,8 @@ static bool mock_domain_capable(struct device *dev, enum iommu_cap cap)
 	return false;
 }
 
+static struct iopf_queue *mock_iommu_iopf_queue;
+
 static struct iommu_device mock_iommu_device = {
 };
 
@@ -514,6 +516,29 @@ static struct iommu_device *mock_probe_device(struct device *dev)
 	return &mock_iommu_device;
 }
 
+static void mock_domain_page_response(struct device *dev, struct iopf_fault *evt,
+				      struct iommu_page_response *msg)
+{
+}
+
+static int mock_dev_enable_feat(struct device *dev, enum iommu_dev_features feat)
+{
+	if (feat != IOMMU_DEV_FEAT_IOPF || !mock_iommu_iopf_queue)
+		return -ENODEV;
+
+	return iopf_queue_add_device(mock_iommu_iopf_queue, dev);
+}
+
+static int mock_dev_disable_feat(struct device *dev, enum iommu_dev_features feat)
+{
+	if (feat != IOMMU_DEV_FEAT_IOPF || !mock_iommu_iopf_queue)
+		return -ENODEV;
+
+	iopf_queue_remove_device(mock_iommu_iopf_queue, dev);
+
+	return 0;
+}
+
 static const struct iommu_ops mock_ops = {
 	/*
 	 * IOMMU_DOMAIN_BLOCKED cannot be returned from def_domain_type()
@@ -529,6 +554,10 @@ static const struct iommu_ops mock_ops = {
 	.capable = mock_domain_capable,
 	.device_group = generic_device_group,
 	.probe_device = mock_probe_device,
+	.page_response = mock_domain_page_response,
+	.dev_enable_feat = mock_dev_enable_feat,
+	.dev_disable_feat = mock_dev_disable_feat,
+	.user_pasid_table = true,
 	.default_domain_ops =
 		&(struct iommu_domain_ops){
 			.free = mock_domain_free,
@@ -1375,6 +1404,31 @@ out_put:
 	return rc;
 }
 
+static int iommufd_test_trigger_iopf(struct iommufd_ucmd *ucmd,
+				     struct iommu_test_cmd *cmd)
+{
+	struct iopf_fault event = { };
+	struct iommufd_device *idev;
+
+	idev = iommufd_get_device(ucmd, cmd->trigger_iopf.dev_id);
+	if (IS_ERR(idev))
+		return PTR_ERR(idev);
+
+	event.fault.prm.flags = IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE;
+	if (cmd->trigger_iopf.pasid != IOMMU_NO_PASID)
+		event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PASID_VALID;
+	event.fault.type = IOMMU_FAULT_PAGE_REQ;
+	event.fault.prm.addr = cmd->trigger_iopf.addr;
+	event.fault.prm.pasid = cmd->trigger_iopf.pasid;
+	event.fault.prm.grpid = cmd->trigger_iopf.grpid;
+	event.fault.prm.perm = cmd->trigger_iopf.perm;
+
+	iommu_report_device_fault(idev->dev, &event);
+	iommufd_put_object(ucmd->ictx, &idev->obj);
+
+	return 0;
+}
+
 void iommufd_selftest_destroy(struct iommufd_object *obj)
 {
 	struct selftest_obj *sobj = container_of(obj, struct selftest_obj, obj);
@@ -1450,6 +1504,8 @@ int iommufd_test(struct iommufd_ucmd *ucmd)
 					  cmd->dirty.page_size,
 					  u64_to_user_ptr(cmd->dirty.uptr),
 					  cmd->dirty.flags);
+	case IOMMU_TEST_OP_TRIGGER_IOPF:
+		return iommufd_test_trigger_iopf(ucmd, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -1491,6 +1547,9 @@ int __init iommufd_test_init(void)
 				  &iommufd_mock_bus_type.nb);
 	if (rc)
 		goto err_sysfs;
+
+	mock_iommu_iopf_queue = iopf_queue_alloc("mock-iopfq");
+
 	return 0;
 
 err_sysfs:
@@ -1506,6 +1565,11 @@ err_dbgfs:
 
 void iommufd_test_exit(void)
 {
+	if (mock_iommu_iopf_queue) {
+		iopf_queue_free(mock_iommu_iopf_queue);
+		mock_iommu_iopf_queue = NULL;
+	}
+
 	iommu_device_sysfs_remove(&mock_iommu_device);
 	iommu_device_unregister_bus(&mock_iommu_device,
 				    &iommufd_mock_bus_type.bus,
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 17b3f36ad843..73bc3aee95a1 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -124,12 +124,16 @@ struct iopf_fault {
 struct iopf_group {
 	struct iopf_fault last_fault;
 	struct list_head faults;
+	size_t fault_count;
 	/* list node for iommu_fault_param::faults */
 	struct list_head pending_node;
 	struct work_struct work;
-	struct iommu_domain *domain;
+	struct iommu_attach_handle *attach_handle;
 	/* The device's fault data parameter. */
 	struct iommu_fault_param *fault_param;
+	/* Used by handler provider to hook the group on its own lists. */
+	struct list_head node;
+	u32 cookie;
 };
 
 /**
@@ -547,6 +551,10 @@ static inline int __iommu_copy_struct_from_user_array(
  * @default_domain: If not NULL this will always be set as the default domain.
  *                  This should be an IDENTITY/BLOCKED/PLATFORM domain.
  *                  Do not use in new drivers.
+ * @user_pasid_table: IOMMU driver supports user-managed PASID table. There is
+ *                    no user domain for each PASID and the I/O page faults are
+ *                    forwarded through the user domain attached to the device
+ *                    RID.
  */
 struct iommu_ops {
 	bool (*capable)(struct device *dev, enum iommu_cap);
@@ -590,6 +598,7 @@ struct iommu_ops {
 	struct iommu_domain *blocked_domain;
 	struct iommu_domain *release_domain;
 	struct iommu_domain *default_domain;
+	u8 user_pasid_table:1;
 };
 
 /**
@@ -989,20 +998,28 @@ struct iommu_fwspec {
 /* ATS is supported */
 #define IOMMU_FWSPEC_PCI_RC_ATS			(1 << 0)
 
+/*
+ * An iommu attach handle represents a relationship between an iommu domain
+ * and a PASID or RID of a device. It is allocated and managed by the component
+ * that manages the domain and is stored in the iommu group during the time the
+ * domain is attached.
+ */
+struct iommu_attach_handle {
+	struct iommu_domain		*domain;
+};
+
 /**
  * struct iommu_sva - handle to a device-mm bond
  */
 struct iommu_sva {
+	struct iommu_attach_handle	handle;
 	struct device			*dev;
-	struct iommu_domain		*domain;
-	struct list_head		handle_item;
 	refcount_t			users;
 };
 
 struct iommu_mm_data {
 	u32			pasid;
 	struct list_head	sva_domains;
-	struct list_head	sva_handles;
 };
 
 int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
@@ -1052,12 +1069,10 @@ int iommu_device_claim_dma_owner(struct device *dev, void *owner);
 void iommu_device_release_dma_owner(struct device *dev);
 
 int iommu_attach_device_pasid(struct iommu_domain *domain,
-			      struct device *dev, ioasid_t pasid);
+			      struct device *dev, ioasid_t pasid,
+			      struct iommu_attach_handle *handle);
 void iommu_detach_device_pasid(struct iommu_domain *domain,
 			       struct device *dev, ioasid_t pasid);
-struct iommu_domain *
-iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
-			       unsigned int type);
 ioasid_t iommu_alloc_global_pasid(struct device *dev);
 void iommu_free_global_pasid(ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
@@ -1388,7 +1403,8 @@ static inline int iommu_device_claim_dma_owner(struct device *dev, void *owner)
 }
 
 static inline int iommu_attach_device_pasid(struct iommu_domain *domain,
-					    struct device *dev, ioasid_t pasid)
+					    struct device *dev, ioasid_t pasid,
+					    struct iommu_attach_handle *handle)
 {
 	return -ENODEV;
 }
@@ -1398,13 +1414,6 @@ static inline void iommu_detach_device_pasid(struct iommu_domain *domain,
 {
 }
 
-static inline struct iommu_domain *
-iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
-			       unsigned int type)
-{
-	return NULL;
-}
-
 static inline ioasid_t iommu_alloc_global_pasid(struct device *dev)
 {
 	return IOMMU_PASID_INVALID;
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 1dfeaa2e649e..ede2b464a761 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -50,6 +50,7 @@ enum {
 	IOMMUFD_CMD_HWPT_SET_DIRTY_TRACKING,
 	IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP,
 	IOMMUFD_CMD_HWPT_INVALIDATE,
+	IOMMUFD_CMD_FAULT_QUEUE_ALLOC,
 };
 
 /**
@@ -356,10 +357,13 @@ struct iommu_vfio_ioas {
  *                                the parent HWPT in a nesting configuration.
  * @IOMMU_HWPT_ALLOC_DIRTY_TRACKING: Dirty tracking support for device IOMMU is
  *                                   enforced on device attachment
+ * @IOMMU_HWPT_FAULT_ID_VALID: The fault_id field of hwpt allocation data is
+ *                             valid.
  */
 enum iommufd_hwpt_alloc_flags {
 	IOMMU_HWPT_ALLOC_NEST_PARENT = 1 << 0,
 	IOMMU_HWPT_ALLOC_DIRTY_TRACKING = 1 << 1,
+	IOMMU_HWPT_FAULT_ID_VALID = 1 << 2,
 };
 
 /**
@@ -411,6 +415,9 @@ enum iommu_hwpt_data_type {
  * @data_type: One of enum iommu_hwpt_data_type
  * @data_len: Length of the type specific data
  * @data_uptr: User pointer to the type specific data
+ * @fault_id: The ID of IOMMUFD_FAULT object. Valid only if flags field of
+ *            IOMMU_HWPT_FAULT_ID_VALID is set.
+ * @__reserved2: Padding to 64-bit alignment. Must be 0.
  *
  * Explicitly allocate a hardware page table object. This is the same object
  * type that is returned by iommufd_device_attach() and represents the
@@ -441,6 +448,8 @@ struct iommu_hwpt_alloc {
 	__u32 data_type;
 	__u32 data_len;
 	__aligned_u64 data_uptr;
+	__u32 fault_id;
+	__u32 __reserved2;
 };
 #define IOMMU_HWPT_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_ALLOC)
 
@@ -692,4 +701,104 @@ struct iommu_hwpt_invalidate {
 	__u32 __reserved;
 };
 #define IOMMU_HWPT_INVALIDATE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HWPT_INVALIDATE)
+
+/**
+ * enum iommu_hwpt_pgfault_flags - flags for struct iommu_hwpt_pgfault
+ * @IOMMU_PGFAULT_FLAGS_PASID_VALID: The pasid field of the fault data is
+ *                                   valid.
+ * @IOMMU_PGFAULT_FLAGS_LAST_PAGE: It's the last fault of a fault group.
+ */
+enum iommu_hwpt_pgfault_flags {
+	IOMMU_PGFAULT_FLAGS_PASID_VALID		= (1 << 0),
+	IOMMU_PGFAULT_FLAGS_LAST_PAGE		= (1 << 1),
+};
+
+/**
+ * enum iommu_hwpt_pgfault_perm - perm bits for struct iommu_hwpt_pgfault
+ * @IOMMU_PGFAULT_PERM_READ: request for read permission
+ * @IOMMU_PGFAULT_PERM_WRITE: request for write permission
+ * @IOMMU_PGFAULT_PERM_EXEC: (PCIE 10.4.1) request with a PASID that has the
+ *                           Execute Requested bit set in PASID TLP Prefix.
+ * @IOMMU_PGFAULT_PERM_PRIV: (PCIE 10.4.1) request with a PASID that has the
+ *                           Privileged Mode Requested bit set in PASID TLP
+ *                           Prefix.
+ */
+enum iommu_hwpt_pgfault_perm {
+	IOMMU_PGFAULT_PERM_READ			= (1 << 0),
+	IOMMU_PGFAULT_PERM_WRITE		= (1 << 1),
+	IOMMU_PGFAULT_PERM_EXEC			= (1 << 2),
+	IOMMU_PGFAULT_PERM_PRIV			= (1 << 3),
+};
+
+/**
+ * struct iommu_hwpt_pgfault - iommu page fault data
+ * @flags: Combination of enum iommu_hwpt_pgfault_flags
+ * @dev_id: id of the originated device
+ * @pasid: Process Address Space ID
+ * @grpid: Page Request Group Index
+ * @perm: Combination of enum iommu_hwpt_pgfault_perm
+ * @addr: Fault address
+ * @length: a hint of how much data the requestor is expecting to fetch. For
+ *          example, if the PRI initiator knows it is going to do a 10MB
+ *          transfer, it could fill in 10MB and the OS could pre-fault in
+ *          10MB of IOVA. It's default to 0 if there's no such hint.
+ * @cookie: kernel-managed cookie identifying a group of fault messages. The
+ *          cookie number encoded in the last page fault of the group should
+ *          be echoed back in the response message.
+ */
+struct iommu_hwpt_pgfault {
+	__u32 flags;
+	__u32 dev_id;
+	__u32 pasid;
+	__u32 grpid;
+	__u32 perm;
+	__u64 addr;
+	__u32 length;
+	__u32 cookie;
+};
+
+/**
+ * enum iommufd_page_response_code - Return status of fault handlers
+ * @IOMMUFD_PAGE_RESP_SUCCESS: Fault has been handled and the page tables
+ *                             populated, retry the access. This is the
+ *                             "Success" defined in PCI 10.4.2.1.
+ * @IOMMUFD_PAGE_RESP_INVALID: Could not handle this fault, don't retry the
+ *                             access. This is the "Invalid Request" in PCI
+ *                             10.4.2.1.
+ * @IOMMUFD_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from
+ *                             this device if possible. This is the "Response
+ *                             Failure" in PCI 10.4.2.1.
+ */
+enum iommufd_page_response_code {
+	IOMMUFD_PAGE_RESP_SUCCESS = 0,
+	IOMMUFD_PAGE_RESP_INVALID,
+	IOMMUFD_PAGE_RESP_FAILURE,
+};
+
+/**
+ * struct iommu_hwpt_page_response - IOMMU page fault response
+ * @cookie: The kernel-managed cookie reported in the fault message.
+ * @code: One of response code in enum iommufd_page_response_code.
+ */
+struct iommu_hwpt_page_response {
+	__u32 cookie;
+	__u32 code;
+};
+
+/**
+ * struct iommu_fault_alloc - ioctl(IOMMU_FAULT_QUEUE_ALLOC)
+ * @size: sizeof(struct iommu_fault_alloc)
+ * @flags: Must be 0
+ * @out_fault_id: The ID of the new FAULT
+ * @out_fault_fd: The fd of the new FAULT
+ *
+ * Explicitly allocate a fault handling object.
+ */
+struct iommu_fault_alloc {
+	__u32 size;
+	__u32 flags;
+	__u32 out_fault_id;
+	__u32 out_fault_fd;
+};
+#define IOMMU_FAULT_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_FAULT_QUEUE_ALLOC)
 #endif
diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
index 5f7d5a5ba89b..6343f4053bd4 100644
--- a/tools/testing/selftests/iommu/iommufd.c
+++ b/tools/testing/selftests/iommu/iommufd.c
@@ -279,6 +279,9 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 	uint32_t parent_hwpt_id = 0;
 	uint32_t parent_hwpt_id_not_work = 0;
 	uint32_t test_hwpt_id = 0;
+	uint32_t iopf_hwpt_id;
+	uint32_t fault_id;
+	uint32_t fault_fd;
 
 	if (self->device_id) {
 		/* Negative tests */
@@ -326,6 +329,7 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 					   sizeof(data));
 
 		/* Allocate two nested hwpts sharing one common parent hwpt */
+		test_ioctl_fault_alloc(&fault_id, &fault_fd);
 		test_cmd_hwpt_alloc_nested(self->device_id, parent_hwpt_id, 0,
 					   &nested_hwpt_id[0],
 					   IOMMU_HWPT_DATA_SELFTEST, &data,
@@ -334,6 +338,14 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 					   &nested_hwpt_id[1],
 					   IOMMU_HWPT_DATA_SELFTEST, &data,
 					   sizeof(data));
+		test_err_hwpt_alloc_iopf(ENOENT, self->device_id, parent_hwpt_id,
+					 UINT32_MAX, IOMMU_HWPT_FAULT_ID_VALID,
+					 &iopf_hwpt_id, IOMMU_HWPT_DATA_SELFTEST,
+					 &data, sizeof(data));
+		test_cmd_hwpt_alloc_iopf(self->device_id, parent_hwpt_id, fault_id,
+					 IOMMU_HWPT_FAULT_ID_VALID, &iopf_hwpt_id,
+					 IOMMU_HWPT_DATA_SELFTEST, &data,
+					 sizeof(data));
 		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[0],
 					      IOMMU_TEST_IOTLB_DEFAULT);
 		test_cmd_hwpt_check_iotlb_all(nested_hwpt_id[1],
@@ -504,14 +516,24 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested)
 			     _test_ioctl_destroy(self->fd, nested_hwpt_id[1]));
 		test_ioctl_destroy(nested_hwpt_id[0]);
 
+		/* Switch from nested_hwpt_id[1] to iopf_hwpt_id */
+		test_cmd_mock_domain_replace(self->stdev_id, iopf_hwpt_id);
+		EXPECT_ERRNO(EBUSY,
+			     _test_ioctl_destroy(self->fd, iopf_hwpt_id));
+		/* Trigger an IOPF on the device */
+		test_cmd_trigger_iopf(self->device_id, fault_fd);
+
 		/* Detach from nested_hwpt_id[1] and destroy it */
 		test_cmd_mock_domain_replace(self->stdev_id, parent_hwpt_id);
 		test_ioctl_destroy(nested_hwpt_id[1]);
+		test_ioctl_destroy(iopf_hwpt_id);
 
 		/* Detach from the parent hw_pagetable and destroy it */
 		test_cmd_mock_domain_replace(self->stdev_id, self->ioas_id);
 		test_ioctl_destroy(parent_hwpt_id);
 		test_ioctl_destroy(parent_hwpt_id_not_work);
+		close(fault_fd);
+		test_ioctl_destroy(fault_id);
 	} else {
 		test_err_hwpt_alloc(ENOENT, self->device_id, self->ioas_id, 0,
 				    &parent_hwpt_id);
diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c
index f590417cd67a..c5d5e69452b0 100644
--- a/tools/testing/selftests/iommu/iommufd_fail_nth.c
+++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c
@@ -615,7 +615,7 @@ TEST_FAIL_NTH(basic_fail_nth, device)
 	if (_test_cmd_get_hw_info(self->fd, idev_id, &info, sizeof(info), NULL))
 		return -1;
 
-	if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, &hwpt_id,
+	if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, 0, &hwpt_id,
 				 IOMMU_HWPT_DATA_NONE, 0, 0))
 		return -1;
 
diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
index c612fbf0195b..40f6f14ce136 100644
--- a/tools/testing/selftests/iommu/iommufd_utils.h
+++ b/tools/testing/selftests/iommu/iommufd_utils.h
@@ -155,7 +155,7 @@ static int _test_cmd_mock_domain_replace(int fd, __u32 stdev_id, __u32 pt_id,
 	EXPECT_ERRNO(_errno, _test_cmd_mock_domain_replace(self->fd, stdev_id, \
 							   pt_id, NULL))
 
-static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id,
+static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, __u32 ft_id,
 				__u32 flags, __u32 *hwpt_id, __u32 data_type,
 				void *data, size_t data_len)
 {
@@ -167,6 +167,7 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id,
 		.data_type = data_type,
 		.data_len = data_len,
 		.data_uptr = (uint64_t)data,
+		.fault_id = ft_id,
 	};
 	int ret;
 
@@ -179,24 +180,36 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id,
 }
 
 #define test_cmd_hwpt_alloc(device_id, pt_id, flags, hwpt_id)                  \
-	ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, flags,   \
+	ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, 0, flags,   \
 					  hwpt_id, IOMMU_HWPT_DATA_NONE, NULL, \
 					  0))
 #define test_err_hwpt_alloc(_errno, device_id, pt_id, flags, hwpt_id)   \
 	EXPECT_ERRNO(_errno, _test_cmd_hwpt_alloc(                      \
-				     self->fd, device_id, pt_id, flags, \
+				     self->fd, device_id, pt_id, 0, flags, \
 				     hwpt_id, IOMMU_HWPT_DATA_NONE, NULL, 0))
 
 #define test_cmd_hwpt_alloc_nested(device_id, pt_id, flags, hwpt_id,         \
 				   data_type, data, data_len)                \
-	ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, flags, \
+	ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, 0, flags, \
 					  hwpt_id, data_type, data, data_len))
 #define test_err_hwpt_alloc_nested(_errno, device_id, pt_id, flags, hwpt_id, \
 				   data_type, data, data_len)                \
 	EXPECT_ERRNO(_errno,                                                 \
-		     _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, flags, \
+		     _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, 0, flags, \
 					  hwpt_id, data_type, data, data_len))
 
+#define test_cmd_hwpt_alloc_iopf(device_id, pt_id, fault_id, flags, hwpt_id,    \
+				   data_type, data, data_len)                   \
+	ASSERT_EQ(0, _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, fault_id, \
+					  flags, hwpt_id, data_type, data,      \
+					  data_len))
+#define test_err_hwpt_alloc_iopf(_errno, device_id, pt_id, fault_id, flags,     \
+				 hwpt_id, data_type, data, data_len)            \
+	EXPECT_ERRNO(_errno,                                                    \
+		     _test_cmd_hwpt_alloc(self->fd, device_id, pt_id, fault_id, \
+					  flags, hwpt_id, data_type, data,      \
+					  data_len))
+
 #define test_cmd_hwpt_check_iotlb(hwpt_id, iotlb_id, expected)                 \
 	({                                                                     \
 		struct iommu_test_cmd test_cmd = {                             \
@@ -686,3 +699,66 @@ static int _test_cmd_get_hw_info(int fd, __u32 device_id, void *data,
 
 #define test_cmd_get_hw_capabilities(device_id, caps, mask) \
 	ASSERT_EQ(0, _test_cmd_get_hw_info(self->fd, device_id, NULL, 0, &caps))
+
+static int _test_ioctl_fault_alloc(int fd, __u32 *fault_id, __u32 *fault_fd)
+{
+	struct iommu_fault_alloc cmd = {
+		.size = sizeof(cmd),
+	};
+	int ret;
+
+	ret = ioctl(fd, IOMMU_FAULT_QUEUE_ALLOC, &cmd);
+	if (ret)
+		return ret;
+	*fault_id = cmd.out_fault_id;
+	*fault_fd = cmd.out_fault_fd;
+	return 0;
+}
+
+#define test_ioctl_fault_alloc(fault_id, fault_fd)                       \
+	({                                                               \
+		ASSERT_EQ(0, _test_ioctl_fault_alloc(self->fd, fault_id, \
+						     fault_fd));         \
+		ASSERT_NE(0, *(fault_id));                               \
+		ASSERT_NE(0, *(fault_fd));                               \
+	})
+
+static int _test_cmd_trigger_iopf(int fd, __u32 device_id, __u32 fault_fd)
+{
+	struct iommu_test_cmd trigger_iopf_cmd = {
+		.size = sizeof(trigger_iopf_cmd),
+		.op = IOMMU_TEST_OP_TRIGGER_IOPF,
+		.trigger_iopf = {
+			.dev_id = device_id,
+			.pasid = 0x1,
+			.grpid = 0x2,
+			.perm = IOMMU_PGFAULT_PERM_READ | IOMMU_PGFAULT_PERM_WRITE,
+			.addr = 0xdeadbeaf,
+		},
+	};
+	struct iommu_hwpt_page_response response = {
+		.code = IOMMUFD_PAGE_RESP_SUCCESS,
+	};
+	struct iommu_hwpt_pgfault fault = {};
+	ssize_t bytes;
+	int ret;
+
+	ret = ioctl(fd, _IOMMU_TEST_CMD(IOMMU_TEST_OP_TRIGGER_IOPF), &trigger_iopf_cmd);
+	if (ret)
+		return ret;
+
+	bytes = read(fault_fd, &fault, sizeof(fault));
+	if (bytes <= 0)
+		return -EIO;
+
+	response.cookie = fault.cookie;
+
+	bytes = write(fault_fd, &response, sizeof(response));
+	if (bytes <= 0)
+		return -EIO;
+
+	return 0;
+}
+
+#define test_cmd_trigger_iopf(device_id, fault_fd) \
+	ASSERT_EQ(0, _test_cmd_trigger_iopf(self->fd, device_id, fault_fd))