Merge tag 'vfio-v5.4-rc1' of git://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Fix spapr iommu error case case (Alexey Kardashevskiy)

 - Consolidate region type definitions (Cornelia Huck)

 - Restore saved original PCI state on release (hexin)

 - Simplify mtty sample driver interrupt path (Parav Pandit)

 - Support for reporting valid IOVA regions to user (Shameer Kolothum)

* tag 'vfio-v5.4-rc1' of git://github.com/awilliam/linux-vfio:
  vfio_pci: Restore original state on release
  vfio/type1: remove duplicate retrieval of reserved regions
  vfio/type1: Add IOVA range capability support
  vfio/type1: check dma map request is within a valid iova range
  vfio/spapr_tce: Fix incorrect tce_iommu_group memory free
  vfio-mdev/mtty: Simplify interrupt generation
  vfio: re-arrange vfio region definitions
  vfio/type1: Update iova list on detach
  vfio/type1: Check reserved region conflict and update iova list
  vfio/type1: Introduce iova list and add iommu aperture validity check

drivers/vfio/pci/vfio_pci.c

@@ -438,11 +438,20 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
 	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
 
 	/*
-	 * Try to reset the device.  The success of this is dependent on
-	 * being able to lock the device, which is not always possible.
+	 * Try to get the locks ourselves to prevent a deadlock. The
+	 * success of this is dependent on being able to lock the device,
+	 * which is not always possible.
+	 * We can not use the "try" reset interface here, which will
+	 * overwrite the previously restored configuration information.
 	 */
-	if (vdev->reset_works && !pci_try_reset_function(pdev))
+	if (vdev->reset_works && pci_cfg_access_trylock(pdev)) {
+		if (device_trylock(&pdev->dev)) {
+			if (!__pci_reset_function_locked(pdev))
 				vdev->needs_reset = false;
+			device_unlock(&pdev->dev);
+		}
+		pci_cfg_access_unlock(pdev);
+	}
 
 	pci_restore_state(pdev);
 out:

drivers/vfio/vfio_iommu_spapr_tce.c

@@ -1240,7 +1240,7 @@ static long tce_iommu_take_ownership_ddw(struct tce_container *container,
 static int tce_iommu_attach_group(void *iommu_data,
 		struct iommu_group *iommu_group)
 {
-	int ret;
+	int ret = 0;
 	struct tce_container *container = iommu_data;
 	struct iommu_table_group *table_group;
 	struct tce_iommu_group *tcegrp = NULL;
@@ -1293,13 +1293,13 @@ static int tce_iommu_attach_group(void *iommu_data,
 			!table_group->ops->release_ownership) {
 		if (container->v2) {
 			ret = -EPERM;
-			goto unlock_exit;
+			goto free_exit;
 		}
 		ret = tce_iommu_take_ownership(container, table_group);
 	} else {
 		if (!container->v2) {
 			ret = -EPERM;
-			goto unlock_exit;
+			goto free_exit;
 		}
 		ret = tce_iommu_take_ownership_ddw(container, table_group);
 		if (!tce_groups_attached(container) && !container->tables[0])
@@ -1311,10 +1311,11 @@ static int tce_iommu_attach_group(void *iommu_data,
 		list_add(&tcegrp->next, &container->group_list);
 	}
 
-unlock_exit:
+free_exit:
 	if (ret && tcegrp)
 		kfree(tcegrp);
 
+unlock_exit:
 	mutex_unlock(&container->lock);
 
 	return ret;

drivers/vfio/vfio_iommu_type1.c

@@ -62,6 +62,7 @@ MODULE_PARM_DESC(dma_entry_limit,
 
 struct vfio_iommu {
 	struct list_head	domain_list;
+	struct list_head	iova_list;
 	struct vfio_domain	*external_domain; /* domain for external user */
 	struct mutex		lock;
 	struct rb_root		dma_list;
@@ -97,6 +98,12 @@ struct vfio_group {
 	bool			mdev_group;	/* An mdev group */
 };
 
+struct vfio_iova {
+	struct list_head	list;
+	dma_addr_t		start;
+	dma_addr_t		end;
+};
+
 /*
  * Guest RAM pinning working set or DMA target
  */
@@ -1038,6 +1045,27 @@ static int vfio_pin_map_dma(struct vfio_iommu *iommu, struct vfio_dma *dma,
 	return ret;
 }
 
+/*
+ * Check dma map request is within a valid iova range
+ */
+static bool vfio_iommu_iova_dma_valid(struct vfio_iommu *iommu,
+				      dma_addr_t start, dma_addr_t end)
+{
+	struct list_head *iova = &iommu->iova_list;
+	struct vfio_iova *node;
+
+	list_for_each_entry(node, iova, list) {
+		if (start >= node->start && end <= node->end)
+			return true;
+	}
+
+	/*
+	 * Check for list_empty() as well since a container with
+	 * a single mdev device will have an empty list.
+	 */
+	return list_empty(iova);
+}
+
 static int vfio_dma_do_map(struct vfio_iommu *iommu,
 			   struct vfio_iommu_type1_dma_map *map)
 {
@@ -1081,6 +1109,11 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 		goto out_unlock;
 	}
 
+	if (!vfio_iommu_iova_dma_valid(iommu, iova, iova + size - 1)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
 	dma = kzalloc(sizeof(*dma), GFP_KERNEL);
 	if (!dma) {
 		ret = -ENOMEM;
@@ -1270,15 +1303,13 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
 	return NULL;
 }
 
-static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base)
+static bool vfio_iommu_has_sw_msi(struct list_head *group_resv_regions,
+				  phys_addr_t *base)
 {
-	struct list_head group_resv_regions;
-	struct iommu_resv_region *region, *next;
+	struct iommu_resv_region *region;
 	bool ret = false;
 
-	INIT_LIST_HEAD(&group_resv_regions);
-	iommu_get_group_resv_regions(group, &group_resv_regions);
-	list_for_each_entry(region, &group_resv_regions, list) {
+	list_for_each_entry(region, group_resv_regions, list) {
 		/*
 		 * The presence of any 'real' MSI regions should take
 		 * precedence over the software-managed one if the
@@ -1294,8 +1325,7 @@ static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base)
 			ret = true;
 		}
 	}
-	list_for_each_entry_safe(region, next, &group_resv_regions, list)
-		kfree(region);
+
 	return ret;
 }
 
@@ -1395,6 +1425,228 @@ static int vfio_mdev_iommu_device(struct device *dev, void *data)
 	return 0;
 }
 
+/*
+ * This is a helper function to insert an address range to iova list.
+ * The list is initially created with a single entry corresponding to
+ * the IOMMU domain geometry to which the device group is attached.
+ * The list aperture gets modified when a new domain is added to the
+ * container if the new aperture doesn't conflict with the current one
+ * or with any existing dma mappings. The list is also modified to
+ * exclude any reserved regions associated with the device group.
+ */
+static int vfio_iommu_iova_insert(struct list_head *head,
+				  dma_addr_t start, dma_addr_t end)
+{
+	struct vfio_iova *region;
+
+	region = kmalloc(sizeof(*region), GFP_KERNEL);
+	if (!region)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&region->list);
+	region->start = start;
+	region->end = end;
+
+	list_add_tail(&region->list, head);
+	return 0;
+}
+
+/*
+ * Check the new iommu aperture conflicts with existing aper or with any
+ * existing dma mappings.
+ */
+static bool vfio_iommu_aper_conflict(struct vfio_iommu *iommu,
+				     dma_addr_t start, dma_addr_t end)
+{
+	struct vfio_iova *first, *last;
+	struct list_head *iova = &iommu->iova_list;
+
+	if (list_empty(iova))
+		return false;
+
+	/* Disjoint sets, return conflict */
+	first = list_first_entry(iova, struct vfio_iova, list);
+	last = list_last_entry(iova, struct vfio_iova, list);
+	if (start > last->end || end < first->start)
+		return true;
+
+	/* Check for any existing dma mappings below the new start */
+	if (start > first->start) {
+		if (vfio_find_dma(iommu, first->start, start - first->start))
+			return true;
+	}
+
+	/* Check for any existing dma mappings beyond the new end */
+	if (end < last->end) {
+		if (vfio_find_dma(iommu, end + 1, last->end - end))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Resize iommu iova aperture window. This is called only if the new
+ * aperture has no conflict with existing aperture and dma mappings.
+ */
+static int vfio_iommu_aper_resize(struct list_head *iova,
+				  dma_addr_t start, dma_addr_t end)
+{
+	struct vfio_iova *node, *next;
+
+	if (list_empty(iova))
+		return vfio_iommu_iova_insert(iova, start, end);
+
+	/* Adjust iova list start */
+	list_for_each_entry_safe(node, next, iova, list) {
+		if (start < node->start)
+			break;
+		if (start >= node->start && start < node->end) {
+			node->start = start;
+			break;
+		}
+		/* Delete nodes before new start */
+		list_del(&node->list);
+		kfree(node);
+	}
+
+	/* Adjust iova list end */
+	list_for_each_entry_safe(node, next, iova, list) {
+		if (end > node->end)
+			continue;
+		if (end > node->start && end <= node->end) {
+			node->end = end;
+			continue;
+		}
+		/* Delete nodes after new end */
+		list_del(&node->list);
+		kfree(node);
+	}
+
+	return 0;
+}
+
+/*
+ * Check reserved region conflicts with existing dma mappings
+ */
+static bool vfio_iommu_resv_conflict(struct vfio_iommu *iommu,
+				     struct list_head *resv_regions)
+{
+	struct iommu_resv_region *region;
+
+	/* Check for conflict with existing dma mappings */
+	list_for_each_entry(region, resv_regions, list) {
+		if (region->type == IOMMU_RESV_DIRECT_RELAXABLE)
+			continue;
+
+		if (vfio_find_dma(iommu, region->start, region->length))
+			return true;
+	}
+
+	return false;
+}
+
+/*
+ * Check iova region overlap with  reserved regions and
+ * exclude them from the iommu iova range
+ */
+static int vfio_iommu_resv_exclude(struct list_head *iova,
+				   struct list_head *resv_regions)
+{
+	struct iommu_resv_region *resv;
+	struct vfio_iova *n, *next;
+
+	list_for_each_entry(resv, resv_regions, list) {
+		phys_addr_t start, end;
+
+		if (resv->type == IOMMU_RESV_DIRECT_RELAXABLE)
+			continue;
+
+		start = resv->start;
+		end = resv->start + resv->length - 1;
+
+		list_for_each_entry_safe(n, next, iova, list) {
+			int ret = 0;
+
+			/* No overlap */
+			if (start > n->end || end < n->start)
+				continue;
+			/*
+			 * Insert a new node if current node overlaps with the
+			 * reserve region to exlude that from valid iova range.
+			 * Note that, new node is inserted before the current
+			 * node and finally the current node is deleted keeping
+			 * the list updated and sorted.
+			 */
+			if (start > n->start)
+				ret = vfio_iommu_iova_insert(&n->list, n->start,
+							     start - 1);
+			if (!ret && end < n->end)
+				ret = vfio_iommu_iova_insert(&n->list, end + 1,
+							     n->end);
+			if (ret)
+				return ret;
+
+			list_del(&n->list);
+			kfree(n);
+		}
+	}
+
+	if (list_empty(iova))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void vfio_iommu_resv_free(struct list_head *resv_regions)
+{
+	struct iommu_resv_region *n, *next;
+
+	list_for_each_entry_safe(n, next, resv_regions, list) {
+		list_del(&n->list);
+		kfree(n);
+	}
+}
+
+static void vfio_iommu_iova_free(struct list_head *iova)
+{
+	struct vfio_iova *n, *next;
+
+	list_for_each_entry_safe(n, next, iova, list) {
+		list_del(&n->list);
+		kfree(n);
+	}
+}
+
+static int vfio_iommu_iova_get_copy(struct vfio_iommu *iommu,
+				    struct list_head *iova_copy)
+{
+	struct list_head *iova = &iommu->iova_list;
+	struct vfio_iova *n;
+	int ret;
+
+	list_for_each_entry(n, iova, list) {
+		ret = vfio_iommu_iova_insert(iova_copy, n->start, n->end);
+		if (ret)
+			goto out_free;
+	}
+
+	return 0;
+
+out_free:
+	vfio_iommu_iova_free(iova_copy);
+	return ret;
+}
+
+static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
+					struct list_head *iova_copy)
+{
+	struct list_head *iova = &iommu->iova_list;
+
+	vfio_iommu_iova_free(iova);
+
+	list_splice_tail(iova_copy, iova);
+}
 static int vfio_iommu_type1_attach_group(void *iommu_data,
 					 struct iommu_group *iommu_group)
 {
@@ -1405,6 +1657,9 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	int ret;
 	bool resv_msi, msi_remap;
 	phys_addr_t resv_msi_base;
+	struct iommu_domain_geometry geo;
+	LIST_HEAD(iova_copy);
+	LIST_HEAD(group_resv_regions);
 
 	mutex_lock(&iommu->lock);
 
@@ -1481,7 +1736,43 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	if (ret)
 		goto out_domain;
 
-	resv_msi = vfio_iommu_has_sw_msi(iommu_group, &resv_msi_base);
+	/* Get aperture info */
+	iommu_domain_get_attr(domain->domain, DOMAIN_ATTR_GEOMETRY, &geo);
+
+	if (vfio_iommu_aper_conflict(iommu, geo.aperture_start,
+				     geo.aperture_end)) {
+		ret = -EINVAL;
+		goto out_detach;
+	}
+
+	ret = iommu_get_group_resv_regions(iommu_group, &group_resv_regions);
+	if (ret)
+		goto out_detach;
+
+	if (vfio_iommu_resv_conflict(iommu, &group_resv_regions)) {
+		ret = -EINVAL;
+		goto out_detach;
+	}
+
+	/*
+	 * We don't want to work on the original iova list as the list
+	 * gets modified and in case of failure we have to retain the
+	 * original list. Get a copy here.
+	 */
+	ret = vfio_iommu_iova_get_copy(iommu, &iova_copy);
+	if (ret)
+		goto out_detach;
+
+	ret = vfio_iommu_aper_resize(&iova_copy, geo.aperture_start,
+				     geo.aperture_end);
+	if (ret)
+		goto out_detach;
+
+	ret = vfio_iommu_resv_exclude(&iova_copy, &group_resv_regions);
+	if (ret)
+		goto out_detach;
+
+	resv_msi = vfio_iommu_has_sw_msi(&group_resv_regions, &resv_msi_base);
 
 	INIT_LIST_HEAD(&domain->group_list);
 	list_add(&group->next, &domain->group_list);
@@ -1514,8 +1805,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 				list_add(&group->next, &d->group_list);
 				iommu_domain_free(domain->domain);
 				kfree(domain);
-				mutex_unlock(&iommu->lock);
-				return 0;
+				goto done;
 			}
 
 			ret = vfio_iommu_attach_group(domain, group);
@@ -1538,8 +1828,11 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	}
 
 	list_add(&domain->next, &iommu->domain_list);
-
+done:
+	/* Delete the old one and insert new iova list */
+	vfio_iommu_iova_insert_copy(iommu, &iova_copy);
 	mutex_unlock(&iommu->lock);
+	vfio_iommu_resv_free(&group_resv_regions);
 
 	return 0;
 
@@ -1547,6 +1840,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	vfio_iommu_detach_group(domain, group);
 out_domain:
 	iommu_domain_free(domain->domain);
+	vfio_iommu_iova_free(&iova_copy);
+	vfio_iommu_resv_free(&group_resv_regions);
 out_free:
 	kfree(domain);
 	kfree(group);
@@ -1602,12 +1897,93 @@ static void vfio_sanity_check_pfn_list(struct vfio_iommu *iommu)
 	WARN_ON(iommu->notifier.head);
 }
 
+/*
+ * Called when a domain is removed in detach. It is possible that
+ * the removed domain decided the iova aperture window. Modify the
+ * iova aperture with the smallest window among existing domains.
+ */
+static void vfio_iommu_aper_expand(struct vfio_iommu *iommu,
+				   struct list_head *iova_copy)
+{
+	struct vfio_domain *domain;
+	struct iommu_domain_geometry geo;
+	struct vfio_iova *node;
+	dma_addr_t start = 0;
+	dma_addr_t end = (dma_addr_t)~0;
+
+	if (list_empty(iova_copy))
+		return;
+
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		iommu_domain_get_attr(domain->domain, DOMAIN_ATTR_GEOMETRY,
+				      &geo);
+		if (geo.aperture_start > start)
+			start = geo.aperture_start;
+		if (geo.aperture_end < end)
+			end = geo.aperture_end;
+	}
+
+	/* Modify aperture limits. The new aper is either same or bigger */
+	node = list_first_entry(iova_copy, struct vfio_iova, list);
+	node->start = start;
+	node = list_last_entry(iova_copy, struct vfio_iova, list);
+	node->end = end;
+}
+
+/*
+ * Called when a group is detached. The reserved regions for that
+ * group can be part of valid iova now. But since reserved regions
+ * may be duplicated among groups, populate the iova valid regions
+ * list again.
+ */
+static int vfio_iommu_resv_refresh(struct vfio_iommu *iommu,
+				   struct list_head *iova_copy)
+{
+	struct vfio_domain *d;
+	struct vfio_group *g;
+	struct vfio_iova *node;
+	dma_addr_t start, end;
+	LIST_HEAD(resv_regions);
+	int ret;
+
+	if (list_empty(iova_copy))
+		return -EINVAL;
+
+	list_for_each_entry(d, &iommu->domain_list, next) {
+		list_for_each_entry(g, &d->group_list, next) {
+			ret = iommu_get_group_resv_regions(g->iommu_group,
+							   &resv_regions);
+			if (ret)
+				goto done;
+		}
+	}
+
+	node = list_first_entry(iova_copy, struct vfio_iova, list);
+	start = node->start;
+	node = list_last_entry(iova_copy, struct vfio_iova, list);
+	end = node->end;
+
+	/* purge the iova list and create new one */
+	vfio_iommu_iova_free(iova_copy);
+
+	ret = vfio_iommu_aper_resize(iova_copy, start, end);
+	if (ret)
+		goto done;
+
+	/* Exclude current reserved regions from iova ranges */
+	ret = vfio_iommu_resv_exclude(iova_copy, &resv_regions);
+done:
+	vfio_iommu_resv_free(&resv_regions);
+	return ret;
+}
+
 static void vfio_iommu_type1_detach_group(void *iommu_data,
 					  struct iommu_group *iommu_group)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_domain *domain;
 	struct vfio_group *group;
+	LIST_HEAD(iova_copy);
 
 	mutex_lock(&iommu->lock);
 
@@ -1630,6 +2006,13 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		}
 	}
 
+	/*
+	 * Get a copy of iova list. This will be used to update
+	 * and to replace the current one later. Please note that
+	 * we will leave the original list as it is if update fails.
+	 */
+	vfio_iommu_iova_get_copy(iommu, &iova_copy);
+
 	list_for_each_entry(domain, &iommu->domain_list, next) {
 		group = find_iommu_group(domain, iommu_group);
 		if (!group)
@@ -1655,10 +2038,16 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 			iommu_domain_free(domain->domain);
 			list_del(&domain->next);
 			kfree(domain);
+			vfio_iommu_aper_expand(iommu, &iova_copy);
 		}
 		break;
 	}
 
+	if (!vfio_iommu_resv_refresh(iommu, &iova_copy))
+		vfio_iommu_iova_insert_copy(iommu, &iova_copy);
+	else
+		vfio_iommu_iova_free(&iova_copy);
+
 detach_group_done:
 	mutex_unlock(&iommu->lock);
 }
@@ -1686,6 +2075,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 	}
 
 	INIT_LIST_HEAD(&iommu->domain_list);
+	INIT_LIST_HEAD(&iommu->iova_list);
 	iommu->dma_list = RB_ROOT;
 	iommu->dma_avail = dma_entry_limit;
 	mutex_init(&iommu->lock);
@@ -1729,6 +2119,9 @@ static void vfio_iommu_type1_release(void *iommu_data)
 		list_del(&domain->next);
 		kfree(domain);
 	}
+
+	vfio_iommu_iova_free(&iommu->iova_list);
+
 	kfree(iommu);
 }
 
@@ -1749,6 +2142,73 @@ static int vfio_domains_have_iommu_cache(struct vfio_iommu *iommu)
 	return ret;
 }
 
+static int vfio_iommu_iova_add_cap(struct vfio_info_cap *caps,
+		 struct vfio_iommu_type1_info_cap_iova_range *cap_iovas,
+		 size_t size)
+{
+	struct vfio_info_cap_header *header;
+	struct vfio_iommu_type1_info_cap_iova_range *iova_cap;
+
+	header = vfio_info_cap_add(caps, size,
+				   VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE, 1);
+	if (IS_ERR(header))
+		return PTR_ERR(header);
+
+	iova_cap = container_of(header,
+				struct vfio_iommu_type1_info_cap_iova_range,
+				header);
+	iova_cap->nr_iovas = cap_iovas->nr_iovas;
+	memcpy(iova_cap->iova_ranges, cap_iovas->iova_ranges,
+	       cap_iovas->nr_iovas * sizeof(*cap_iovas->iova_ranges));
+	return 0;
+}
+
+static int vfio_iommu_iova_build_caps(struct vfio_iommu *iommu,
+				      struct vfio_info_cap *caps)
+{
+	struct vfio_iommu_type1_info_cap_iova_range *cap_iovas;
+	struct vfio_iova *iova;
+	size_t size;
+	int iovas = 0, i = 0, ret;
+
+	mutex_lock(&iommu->lock);
+
+	list_for_each_entry(iova, &iommu->iova_list, list)
+		iovas++;
+
+	if (!iovas) {
+		/*
+		 * Return 0 as a container with a single mdev device
+		 * will have an empty list
+		 */
+		ret = 0;
+		goto out_unlock;
+	}
+
+	size = sizeof(*cap_iovas) + (iovas * sizeof(*cap_iovas->iova_ranges));
+
+	cap_iovas = kzalloc(size, GFP_KERNEL);
+	if (!cap_iovas) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	cap_iovas->nr_iovas = iovas;
+
+	list_for_each_entry(iova, &iommu->iova_list, list) {
+		cap_iovas->iova_ranges[i].start = iova->start;
+		cap_iovas->iova_ranges[i].end = iova->end;
+		i++;
+	}
+
+	ret = vfio_iommu_iova_add_cap(caps, cap_iovas, size);
+
+	kfree(cap_iovas);
+out_unlock:
+	mutex_unlock(&iommu->lock);
+	return ret;
+}
+
 static long vfio_iommu_type1_ioctl(void *iommu_data,
 				   unsigned int cmd, unsigned long arg)
 {
@@ -1770,19 +2230,53 @@ static long vfio_iommu_type1_ioctl(void *iommu_data,
 		}
 	} else if (cmd == VFIO_IOMMU_GET_INFO) {
 		struct vfio_iommu_type1_info info;
+		struct vfio_info_cap caps = { .buf = NULL, .size = 0 };
+		unsigned long capsz;
+		int ret;
 
 		minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes);
 
+		/* For backward compatibility, cannot require this */
+		capsz = offsetofend(struct vfio_iommu_type1_info, cap_offset);
+
 		if (copy_from_user(&info, (void __user *)arg, minsz))
 			return -EFAULT;
 
 		if (info.argsz < minsz)
 			return -EINVAL;
 
+		if (info.argsz >= capsz) {
+			minsz = capsz;
+			info.cap_offset = 0; /* output, no-recopy necessary */
+		}
+
 		info.flags = VFIO_IOMMU_INFO_PGSIZES;
 
 		info.iova_pgsizes = vfio_pgsize_bitmap(iommu);
 
+		ret = vfio_iommu_iova_build_caps(iommu, &caps);
+		if (ret)
+			return ret;
+
+		if (caps.size) {
+			info.flags |= VFIO_IOMMU_INFO_CAPS;
+
+			if (info.argsz < sizeof(info) + caps.size) {
+				info.argsz = sizeof(info) + caps.size;
+			} else {
+				vfio_info_cap_shift(&caps, sizeof(info));
+				if (copy_to_user((void __user *)arg +
+						sizeof(info), caps.buf,
+						caps.size)) {
+					kfree(caps.buf);
+					return -EFAULT;
+				}
+				info.cap_offset = sizeof(info);
+			}
+
+			kfree(caps.buf);
+		}
+
 		return copy_to_user((void __user *)arg, &info, minsz) ?
 			-EFAULT : 0;
 

include/uapi/linux/vfio.h

@@ -295,15 +295,38 @@ struct vfio_region_info_cap_type {
 	__u32 subtype;	/* type specific */
 };
 
+/*
+ * List of region types, global per bus driver.
+ * If you introduce a new type, please add it here.
+ */
+
+/* PCI region type containing a PCI vendor part */
 #define VFIO_REGION_TYPE_PCI_VENDOR_TYPE	(1 << 31)
 #define VFIO_REGION_TYPE_PCI_VENDOR_MASK	(0xffff)
+#define VFIO_REGION_TYPE_GFX                    (1)
+#define VFIO_REGION_TYPE_CCW			(2)
+
+/* sub-types for VFIO_REGION_TYPE_PCI_* */
 
-/* 8086 Vendor sub-types */
+/* 8086 vendor PCI sub-types */
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION	(1)
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_HOST_CFG	(2)
 #define VFIO_REGION_SUBTYPE_INTEL_IGD_LPC_CFG	(3)
 
-#define VFIO_REGION_TYPE_GFX                    (1)
+/* 10de vendor PCI sub-types */
+/*
+ * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
+ */
+#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM	(1)
+
+/* 1014 vendor PCI sub-types */
+/*
+ * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
+ * to do TLB invalidation on a GPU.
+ */
+#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD	(1)
+
+/* sub-types for VFIO_REGION_TYPE_GFX */
 #define VFIO_REGION_SUBTYPE_GFX_EDID            (1)
 
 /**
@@ -353,25 +376,9 @@ struct vfio_region_gfx_edid {
 #define VFIO_DEVICE_GFX_LINK_STATE_DOWN  2
 };
 
-#define VFIO_REGION_TYPE_CCW			(2)
-/* ccw sub-types */
+/* sub-types for VFIO_REGION_TYPE_CCW */
 #define VFIO_REGION_SUBTYPE_CCW_ASYNC_CMD	(1)
 
-/*
- * 10de vendor sub-type
- *
- * NVIDIA GPU NVlink2 RAM is coherent RAM mapped onto the host address space.
- */
-#define VFIO_REGION_SUBTYPE_NVIDIA_NVLINK2_RAM	(1)
-
-/*
- * 1014 vendor sub-type
- *
- * IBM NPU NVlink2 ATSD (Address Translation Shootdown) register of NPU
- * to do TLB invalidation on a GPU.
- */
-#define VFIO_REGION_SUBTYPE_IBM_NVLINK2_ATSD	(1)
-
 /*
  * The MSIX mappable capability informs that MSIX data of a BAR can be mmapped
  * which allows direct access to non-MSIX registers which happened to be within
@@ -714,7 +721,31 @@ struct vfio_iommu_type1_info {
 	__u32	argsz;
 	__u32	flags;
 #define VFIO_IOMMU_INFO_PGSIZES (1 << 0)	/* supported page sizes info */
+#define VFIO_IOMMU_INFO_CAPS	(1 << 1)	/* Info supports caps */
 	__u64	iova_pgsizes;	/* Bitmap of supported page sizes */
+	__u32   cap_offset;	/* Offset within info struct of first cap */
+};
+
+/*
+ * The IOVA capability allows to report the valid IOVA range(s)
+ * excluding any non-relaxable reserved regions exposed by
+ * devices attached to the container. Any DMA map attempt
+ * outside the valid iova range will return error.
+ *
+ * The structures below define version 1 of this capability.
+ */
+#define VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE  1
+
+struct vfio_iova_range {
+	__u64	start;
+	__u64	end;
+};
+
+struct vfio_iommu_type1_info_cap_iova_range {
+	struct	vfio_info_cap_header header;
+	__u32	nr_iovas;
+	__u32	reserved;
+	struct	vfio_iova_range iova_ranges[];
 };
 
 #define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12)

samples/vfio-mdev/mtty.c

@@ -152,20 +152,9 @@ static const struct file_operations vd_fops = {
 
 /* function prototypes */
 
-static int mtty_trigger_interrupt(const guid_t *uuid);
+static int mtty_trigger_interrupt(struct mdev_state *mdev_state);
 
 /* Helper functions */
-static struct mdev_state *find_mdev_state_by_uuid(const guid_t *uuid)
-{
-	struct mdev_state *mds;
-
-	list_for_each_entry(mds, &mdev_devices_list, next) {
-		if (guid_equal(mdev_uuid(mds->mdev), uuid))
-			return mds;
-	}
-
-	return NULL;
-}
 
 static void dump_buffer(u8 *buf, uint32_t count)
 {
@@ -337,8 +326,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 				pr_err("Serial port %d: Fifo level trigger\n",
 					index);
 #endif
-				mtty_trigger_interrupt(
-						mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 			}
 		} else {
 #if defined(DEBUG_INTR)
@@ -352,8 +340,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 			 */
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 								UART_IER_RLSI)
-				mtty_trigger_interrupt(
-						mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 		break;
@@ -372,8 +359,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 				pr_err("Serial port %d: IER_THRI write\n",
 					index);
 #endif
-				mtty_trigger_interrupt(
-						mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 			}
 
 			mutex_unlock(&mdev_state->rxtx_lock);
@@ -444,7 +430,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR_OUT2 write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
+			mtty_trigger_interrupt(mdev_state);
 		}
 
 		if ((mdev_state->s[index].uart_reg[UART_IER] & UART_IER_MSI) &&
@@ -452,7 +438,7 @@ static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
 #if defined(DEBUG_INTR)
 			pr_err("Serial port %d: MCR RTS/DTR write\n", index);
 #endif
-			mtty_trigger_interrupt(mdev_uuid(mdev_state->mdev));
+			mtty_trigger_interrupt(mdev_state);
 		}
 		break;
 
@@ -503,8 +489,7 @@ static void handle_bar_read(unsigned int index, struct mdev_state *mdev_state,
 #endif
 			if (mdev_state->s[index].uart_reg[UART_IER] &
 							 UART_IER_THRI)
-				mtty_trigger_interrupt(
-					mdev_uuid(mdev_state->mdev));
+				mtty_trigger_interrupt(mdev_state);
 		}
 		mutex_unlock(&mdev_state->rxtx_lock);
 
@@ -1028,17 +1013,9 @@ static int mtty_set_irqs(struct mdev_device *mdev, uint32_t flags,
 	return ret;
 }
 
-static int mtty_trigger_interrupt(const guid_t *uuid)
+static int mtty_trigger_interrupt(struct mdev_state *mdev_state)
 {
 	int ret = -1;
-	struct mdev_state *mdev_state;
-
-	mdev_state = find_mdev_state_by_uuid(uuid);
-
-	if (!mdev_state) {
-		pr_info("%s: mdev not found\n", __func__);
-		return -EINVAL;
-	}
 
 	if ((mdev_state->irq_index == VFIO_PCI_MSI_IRQ_INDEX) &&
 	    (!mdev_state->msi_evtfd))