1 files changed, 114 insertions, 60 deletions

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index ce78c3671539..59d3a07300d9 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -293,7 +293,7 @@ u32 iommufd_device_to_id(struct iommufd_device *idev)
 EXPORT_SYMBOL_NS_GPL(iommufd_device_to_id, IOMMUFD);
 
 static int iommufd_group_setup_msi(struct iommufd_group *igroup,
-				   struct iommufd_hw_pagetable *hwpt)
+				   struct iommufd_hwpt_paging *hwpt_paging)
 {
 	phys_addr_t sw_msi_start = igroup->sw_msi_start;
 	int rc;
@@ -311,8 +311,9 @@ static int iommufd_group_setup_msi(struct iommufd_group *igroup,
 	 * matches what the IRQ layer actually expects in a newly created
 	 * domain.
 	 */
-	if (sw_msi_start != PHYS_ADDR_MAX && !hwpt->msi_cookie) {
-		rc = iommu_get_msi_cookie(hwpt->domain, sw_msi_start);
+	if (sw_msi_start != PHYS_ADDR_MAX && !hwpt_paging->msi_cookie) {
+		rc = iommu_get_msi_cookie(hwpt_paging->common.domain,
+					  sw_msi_start);
 		if (rc)
 			return rc;
 
@@ -320,7 +321,31 @@ static int iommufd_group_setup_msi(struct iommufd_group *igroup,
 		 * iommu_get_msi_cookie() can only be called once per domain,
 		 * it returns -EBUSY on later calls.
 		 */
-		hwpt->msi_cookie = true;
+		hwpt_paging->msi_cookie = true;
+	}
+	return 0;
+}
+
+static int iommufd_hwpt_paging_attach(struct iommufd_hwpt_paging *hwpt_paging,
+				      struct iommufd_device *idev)
+{
+	int rc;
+
+	lockdep_assert_held(&idev->igroup->lock);
+
+	rc = iopt_table_enforce_dev_resv_regions(&hwpt_paging->ioas->iopt,
+						 idev->dev,
+						 &idev->igroup->sw_msi_start);
+	if (rc)
+		return rc;
+
+	if (list_empty(&idev->igroup->device_list)) {
+		rc = iommufd_group_setup_msi(idev->igroup, hwpt_paging);
+		if (rc) {
+			iopt_remove_reserved_iova(&hwpt_paging->ioas->iopt,
+						  idev->dev);
+			return rc;
+		}
 	}
 	return 0;
 }
@@ -337,18 +362,12 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 		goto err_unlock;
 	}
 
-	/* Try to upgrade the domain we have */
-	if (idev->enforce_cache_coherency) {
-		rc = iommufd_hw_pagetable_enforce_cc(hwpt);
+	if (hwpt_is_paging(hwpt)) {
+		rc = iommufd_hwpt_paging_attach(to_hwpt_paging(hwpt), idev);
 		if (rc)
 			goto err_unlock;
 	}
 
-	rc = iopt_table_enforce_dev_resv_regions(&hwpt->ioas->iopt, idev->dev,
-						 &idev->igroup->sw_msi_start);
-	if (rc)
-		goto err_unlock;
-
 	/*
 	 * Only attach to the group once for the first device that is in the
 	 * group. All the other devices will follow this attachment. The user
@@ -357,10 +376,6 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 	 * attachment.
 	 */
 	if (list_empty(&idev->igroup->device_list)) {
-		rc = iommufd_group_setup_msi(idev->igroup, hwpt);
-		if (rc)
-			goto err_unresv;
-
 		rc = iommu_attach_group(hwpt->domain, idev->igroup->group);
 		if (rc)
 			goto err_unresv;
@@ -371,7 +386,9 @@ int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 	mutex_unlock(&idev->igroup->lock);
 	return 0;
 err_unresv:
-	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
+	if (hwpt_is_paging(hwpt))
+		iopt_remove_reserved_iova(&to_hwpt_paging(hwpt)->ioas->iopt,
+					  idev->dev);
 err_unlock:
 	mutex_unlock(&idev->igroup->lock);
 	return rc;
@@ -388,7 +405,9 @@ iommufd_hw_pagetable_detach(struct iommufd_device *idev)
 		iommu_detach_group(hwpt->domain, idev->igroup->group);
 		idev->igroup->hwpt = NULL;
 	}
-	iopt_remove_reserved_iova(&hwpt->ioas->iopt, idev->dev);
+	if (hwpt_is_paging(hwpt))
+		iopt_remove_reserved_iova(&to_hwpt_paging(hwpt)->ioas->iopt,
+					  idev->dev);
 	mutex_unlock(&idev->igroup->lock);
 
 	/* Caller must destroy hwpt */
@@ -407,14 +426,55 @@ iommufd_device_do_attach(struct iommufd_device *idev,
 	return NULL;
 }
 
+static void
+iommufd_group_remove_reserved_iova(struct iommufd_group *igroup,
+				   struct iommufd_hwpt_paging *hwpt_paging)
+{
+	struct iommufd_device *cur;
+
+	lockdep_assert_held(&igroup->lock);
+
+	list_for_each_entry(cur, &igroup->device_list, group_item)
+		iopt_remove_reserved_iova(&hwpt_paging->ioas->iopt, cur->dev);
+}
+
+static int
+iommufd_group_do_replace_paging(struct iommufd_group *igroup,
+				struct iommufd_hwpt_paging *hwpt_paging)
+{
+	struct iommufd_hw_pagetable *old_hwpt = igroup->hwpt;
+	struct iommufd_device *cur;
+	int rc;
+
+	lockdep_assert_held(&igroup->lock);
+
+	if (!hwpt_is_paging(old_hwpt) ||
+	    hwpt_paging->ioas != to_hwpt_paging(old_hwpt)->ioas) {
+		list_for_each_entry(cur, &igroup->device_list, group_item) {
+			rc = iopt_table_enforce_dev_resv_regions(
+				&hwpt_paging->ioas->iopt, cur->dev, NULL);
+			if (rc)
+				goto err_unresv;
+		}
+	}
+
+	rc = iommufd_group_setup_msi(igroup, hwpt_paging);
+	if (rc)
+		goto err_unresv;
+	return 0;
+
+err_unresv:
+	iommufd_group_remove_reserved_iova(igroup, hwpt_paging);
+	return rc;
+}
+
 static struct iommufd_hw_pagetable *
 iommufd_device_do_replace(struct iommufd_device *idev,
 			  struct iommufd_hw_pagetable *hwpt)
 {
 	struct iommufd_group *igroup = idev->igroup;
 	struct iommufd_hw_pagetable *old_hwpt;
-	unsigned int num_devices = 0;
-	struct iommufd_device *cur;
+	unsigned int num_devices;
 	int rc;
 
 	mutex_lock(&idev->igroup->lock);
@@ -429,42 +489,27 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 		return NULL;
 	}
 
-	/* Try to upgrade the domain we have */
-	list_for_each_entry(cur, &igroup->device_list, group_item) {
-		num_devices++;
-		if (cur->enforce_cache_coherency) {
-			rc = iommufd_hw_pagetable_enforce_cc(hwpt);
-			if (rc)
-				goto err_unlock;
-		}
-	}
-
 	old_hwpt = igroup->hwpt;
-	if (hwpt->ioas != old_hwpt->ioas) {
-		list_for_each_entry(cur, &igroup->device_list, group_item) {
-			rc = iopt_table_enforce_dev_resv_regions(
-				&hwpt->ioas->iopt, cur->dev, NULL);
-			if (rc)
-				goto err_unresv;
-		}
+	if (hwpt_is_paging(hwpt)) {
+		rc = iommufd_group_do_replace_paging(igroup,
+						     to_hwpt_paging(hwpt));
+		if (rc)
+			goto err_unlock;
 	}
 
-	rc = iommufd_group_setup_msi(idev->igroup, hwpt);
-	if (rc)
-		goto err_unresv;
-
 	rc = iommu_group_replace_domain(igroup->group, hwpt->domain);
 	if (rc)
 		goto err_unresv;
 
-	if (hwpt->ioas != old_hwpt->ioas) {
-		list_for_each_entry(cur, &igroup->device_list, group_item)
-			iopt_remove_reserved_iova(&old_hwpt->ioas->iopt,
-						  cur->dev);
-	}
+	if (hwpt_is_paging(old_hwpt) &&
+	    (!hwpt_is_paging(hwpt) ||
+	     to_hwpt_paging(hwpt)->ioas != to_hwpt_paging(old_hwpt)->ioas))
+		iommufd_group_remove_reserved_iova(igroup,
+						   to_hwpt_paging(old_hwpt));
 
 	igroup->hwpt = hwpt;
 
+	num_devices = list_count_nodes(&igroup->device_list);
 	/*
 	 * Move the refcounts held by the device_list to the new hwpt. Retain a
 	 * refcount for this thread as the caller will free it.
@@ -478,8 +523,9 @@ iommufd_device_do_replace(struct iommufd_device *idev,
 	/* Caller must destroy old_hwpt */
 	return old_hwpt;
 err_unresv:
-	list_for_each_entry(cur, &igroup->device_list, group_item)
-		iopt_remove_reserved_iova(&hwpt->ioas->iopt, cur->dev);
+	if (hwpt_is_paging(hwpt))
+		iommufd_group_remove_reserved_iova(igroup,
+						   to_hwpt_paging(old_hwpt));
 err_unlock:
 	mutex_unlock(&idev->igroup->lock);
 	return ERR_PTR(rc);
@@ -507,6 +553,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 	 */
 	bool immediate_attach = do_attach == iommufd_device_do_attach;
 	struct iommufd_hw_pagetable *destroy_hwpt;
+	struct iommufd_hwpt_paging *hwpt_paging;
 	struct iommufd_hw_pagetable *hwpt;
 
 	/*
@@ -515,10 +562,11 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 	 * other.
 	 */
 	mutex_lock(&ioas->mutex);
-	list_for_each_entry(hwpt, &ioas->hwpt_list, hwpt_item) {
-		if (!hwpt->auto_domain)
+	list_for_each_entry(hwpt_paging, &ioas->hwpt_list, hwpt_item) {
+		if (!hwpt_paging->auto_domain)
 			continue;
 
+		hwpt = &hwpt_paging->common;
 		if (!iommufd_lock_obj(&hwpt->obj))
 			continue;
 		destroy_hwpt = (*do_attach)(idev, hwpt);
@@ -539,12 +587,13 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 		goto out_unlock;
 	}
 
-	hwpt = iommufd_hw_pagetable_alloc(idev->ictx, ioas, idev,
-					  immediate_attach);
-	if (IS_ERR(hwpt)) {
-		destroy_hwpt = ERR_CAST(hwpt);
+	hwpt_paging = iommufd_hwpt_paging_alloc(idev->ictx, ioas, idev, 0,
+						immediate_attach, NULL);
+	if (IS_ERR(hwpt_paging)) {
+		destroy_hwpt = ERR_CAST(hwpt_paging);
 		goto out_unlock;
 	}
+	hwpt = &hwpt_paging->common;
 
 	if (!immediate_attach) {
 		destroy_hwpt = (*do_attach)(idev, hwpt);
@@ -554,7 +603,7 @@ iommufd_device_auto_get_domain(struct iommufd_device *idev,
 		destroy_hwpt = NULL;
 	}
 
-	hwpt->auto_domain = true;
+	hwpt_paging->auto_domain = true;
 	*pt_id = hwpt->obj.id;
 
 	iommufd_object_finalize(idev->ictx, &hwpt->obj);
@@ -579,7 +628,8 @@ static int iommufd_device_change_pt(struct iommufd_device *idev, u32 *pt_id,
 		return PTR_ERR(pt_obj);
 
 	switch (pt_obj->type) {
-	case IOMMUFD_OBJ_HW_PAGETABLE: {
+	case IOMMUFD_OBJ_HWPT_NESTED:
+	case IOMMUFD_OBJ_HWPT_PAGING: {
 		struct iommufd_hw_pagetable *hwpt =
 			container_of(pt_obj, struct iommufd_hw_pagetable, obj);
 
@@ -617,8 +667,8 @@ out_put_pt_obj:
 /**
  * iommufd_device_attach - Connect a device to an iommu_domain
  * @idev: device to attach
- * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
- *         Output the IOMMUFD_OBJ_HW_PAGETABLE ID
+ * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HWPT_PAGING
+ *         Output the IOMMUFD_OBJ_HWPT_PAGING ID
  *
  * This connects the device to an iommu_domain, either automatically or manually
  * selected. Once this completes the device could do DMA.
@@ -646,8 +696,8 @@ EXPORT_SYMBOL_NS_GPL(iommufd_device_attach, IOMMUFD);
 /**
  * iommufd_device_replace - Change the device's iommu_domain
  * @idev: device to change
- * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HW_PAGETABLE
- *         Output the IOMMUFD_OBJ_HW_PAGETABLE ID
+ * @pt_id: Input a IOMMUFD_OBJ_IOAS, or IOMMUFD_OBJ_HWPT_PAGING
+ *         Output the IOMMUFD_OBJ_HWPT_PAGING ID
  *
  * This is the same as::
  *
@@ -1185,6 +1235,10 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 	 */
 	cmd->data_len = data_len;
 
+	cmd->out_capabilities = 0;
+	if (device_iommu_capable(idev->dev, IOMMU_CAP_DIRTY_TRACKING))
+		cmd->out_capabilities |= IOMMU_HW_CAP_DIRTY_TRACKING;
+
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 out_free:
 	kfree(data);