Merge tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd

Pull iommufd updates from Jason Gunthorpe:

 - The iova_bitmap logic for efficiently reporting dirty pages back to
   userspace has a few more tricky corner case bugs that have been
   resolved and backed with new tests.

   The revised version has simpler logic.

 - Shared branch with iommu for handle support when doing domain attach.

   Handles allow the domain owner to include additional private data on
   a per-device basis.

 - IO Page Fault Reporting to userspace via iommufd. Page faults can be
   generated on fault capable HWPTs when a translation is not present.

   Routing them to userspace would allow a VMM to be able to virtualize
   them into an emulated vIOMMU. This is the next step to fully enabling
   vSVA support.

* tag 'for-linus-iommufd' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd: (26 commits)
  iommufd: Put constants for all the uAPI enums
  iommufd: Fix error pointer checking
  iommufd: Add check on user response code
  iommufd: Remove IOMMUFD_PAGE_RESP_FAILURE
  iommufd: Require drivers to supply the cache_invalidate_user ops
  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
  iommufd/iova_bitmap: Remove iterator logic
  iommufd/iova_bitmap: Dynamic pinning on iova_bitmap_set()
  iommufd/iova_bitmap: Consolidate iova_bitmap_set exit conditionals
  iommufd/iova_bitmap: Move initial pinning to iova_bitmap_for_each()
  iommufd/iova_bitmap: Cache mapped length in iova_bitmap_map struct
  ...

13 files changed, 908 insertions, 173 deletions

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..a643d5c7c535
--- /dev/null
+++ b/drivers/iommu/iommufd/fault.c
@@ -0,0 +1,443 @@
+// 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 (IS_ERR(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;
+
+		static_assert((int)IOMMUFD_PAGE_RESP_SUCCESS ==
+			      (int)IOMMU_PAGE_RESP_SUCCESS);
+		static_assert((int)IOMMUFD_PAGE_RESP_INVALID ==
+			      (int)IOMMU_PAGE_RESP_INVALID);
+		if (response.code != IOMMUFD_PAGE_RESP_SUCCESS &&
+		    response.code != IOMMUFD_PAGE_RESP_INVALID) {
+			rc = -EINVAL;
+			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..d90f1c30cf8a 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);
@@ -236,7 +243,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 	}
 	hwpt->domain->owner = ops;
 
-	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
+	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED ||
+			 !hwpt->domain->ops->cache_invalidate_user)) {
 		rc = -EINVAL;
 		goto out_abort;
 	}
@@ -308,6 +316,21 @@ 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/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
index db8c46bee155..b9e964b1ad5c 100644
--- a/drivers/iommu/iommufd/iova_bitmap.c
+++ b/drivers/iommu/iommufd/iova_bitmap.c
@@ -35,6 +35,9 @@ struct iova_bitmap_map {
 	/* base IOVA representing bit 0 of the first page */
 	unsigned long iova;
 
+	/* mapped length */
+	unsigned long length;
+
 	/* page size order that each bit granules to */
 	unsigned long pgshift;
 
@@ -113,9 +116,6 @@ struct iova_bitmap {
 
 	/* 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;
 };
 
 /*
@@ -156,6 +156,8 @@ static unsigned long iova_bitmap_mapped_iova(struct iova_bitmap *bitmap)
 	return bitmap->iova + iova_bitmap_index_to_offset(bitmap, skip);
 }
 
+static unsigned long iova_bitmap_mapped_length(struct iova_bitmap *bitmap);
+
 /*
  * Pins the bitmap user pages for the current range window.
  * This is internal to IOVA bitmap and called when advancing the
@@ -206,6 +208,7 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap)
 	 * aligned.
 	 */
 	mapped->pgoff = offset_in_page(addr);
+	mapped->length = iova_bitmap_mapped_length(bitmap);
 	return 0;
 }
 
@@ -263,9 +266,6 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length,
 		goto err;
 	}
 
-	rc = iova_bitmap_get(bitmap);
-	if (rc)
-		goto err;
 	return bitmap;
 
 err:
@@ -338,65 +338,34 @@ static unsigned long iova_bitmap_mapped_length(struct iova_bitmap *bitmap)
 }
 
 /*
- * Returns true if there's not more data to iterate.
+ * Returns true if [@iova..@iova+@length-1] is part of the mapped IOVA range.
  */
-static bool iova_bitmap_done(struct iova_bitmap *bitmap)
+static bool iova_bitmap_mapped_range(struct iova_bitmap_map *mapped,
+				     unsigned long iova, size_t length)
 {
-	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;
+	return mapped->npages &&
+		(iova >= mapped->iova &&
+		 (iova + length - 1) <= (mapped->iova + mapped->length - 1));
 }
 
 /*
- * Advances to the next range, releases the current pinned
+ * Advances to a selected 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)
+static int iova_bitmap_advance_to(struct iova_bitmap *bitmap,
+				  unsigned long iova)
 {
-	unsigned long iova = iova_bitmap_mapped_length(bitmap) - 1;
-	unsigned long count = iova_bitmap_offset_to_index(bitmap, iova) + 1;
+	unsigned long index;
 
-	bitmap->mapped_base_index += count;
+	index = iova_bitmap_offset_to_index(bitmap, iova - bitmap->iova);
+	if (index >= bitmap->mapped_total_index)
+		return -EINVAL;
+	bitmap->mapped_base_index = index;
 
 	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 */
+	/* Pin the next set of bitmap pages */
 	return iova_bitmap_get(bitmap);
 }
 
@@ -416,17 +385,7 @@ static int iova_bitmap_advance(struct iova_bitmap *bitmap)
 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;
+	return fn(bitmap, bitmap->iova, bitmap->length, opaque);
 }
 EXPORT_SYMBOL_NS_GPL(iova_bitmap_for_each, IOMMUFD);
 
@@ -444,11 +403,25 @@ 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;
+	unsigned long cur_bit, last_bit, last_page_idx;
+
+update_indexes:
+	if (unlikely(!iova_bitmap_mapped_range(mapped, iova, length))) {
+
+		/*
+		 * The attempt to advance the base index to @iova
+		 * may fail if it's out of bounds, or pinning the pages
+		 * returns an error.
+		 */
+		if (iova_bitmap_advance_to(bitmap, iova))
+			return;
+	}
+
+	last_page_idx = mapped->npages - 1;
+	cur_bit = ((iova - mapped->iova) >>
+		mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
+	last_bit = (((iova + length - 1) - mapped->iova) >>
+		mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE;
 
 	do {
 		unsigned int page_idx = cur_bit / BITS_PER_PAGE;
@@ -457,18 +430,19 @@ void iova_bitmap_set(struct iova_bitmap *bitmap,
 					 last_bit - cur_bit + 1);
 		void *kaddr;
 
-		if (unlikely(page_idx > last_page_idx))
-			break;
+		if (unlikely(page_idx > last_page_idx)) {
+			unsigned long left =
+				((last_bit - cur_bit + 1) << mapped->pgshift);
+
+			iova += (length - left);
+			length = left;
+			goto update_indexes;
+		}
 
 		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 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 7a2199470f31..f95e32e29133 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -266,8 +266,8 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain,
 
 		/* Clear dirty */
 		if (mock_test_and_clear_dirty(mock, head, pgsize, flags))
-			iommu_dirty_bitmap_record(dirty, head, pgsize);
-		iova = head + pgsize;
+			iommu_dirty_bitmap_record(dirty, iova, pgsize);
+		iova += pgsize;
 	} while (iova < end);
 
 	return 0;
@@ -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,
@@ -1334,7 +1363,7 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
 	}
 
 	max = length / page_size;
-	bitmap_size = max / BITS_PER_BYTE;
+	bitmap_size = DIV_ROUND_UP(max, BITS_PER_BYTE);
 
 	tmp = kvzalloc(bitmap_size, GFP_KERNEL_ACCOUNT);
 	if (!tmp) {
@@ -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,