vfio: Selective dirty page tracking if IOMMU backed device pins pages

Added a check such that only singleton IOMMU groups can pin pages.
>From the point when vendor driver pins any pages, consider IOMMU group
dirty page scope to be limited to pinned pages.

To optimize to avoid walking list often, added flag
pinned_page_dirty_scope to indicate if all of the vfio_groups for each
vfio_domain in the domain_list dirty page scope is limited to pinned
pages. This flag is updated on first pinned pages request for that IOMMU
group and on attaching/detaching group.
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

drivers/vfio/vfio.c

@@ -85,6 +85,7 @@ struct vfio_group {
 	atomic_t			opened;
 	wait_queue_head_t		container_q;
 	bool				noiommu;
+	unsigned int			dev_counter;
 	struct kvm			*kvm;
 	struct blocking_notifier_head	notifier;
 };
@@ -555,6 +556,7 @@ struct vfio_device *vfio_group_create_device(struct vfio_group *group,
 
 	mutex_lock(&group->device_lock);
 	list_add(&device->group_next, &group->device_list);
+	group->dev_counter++;
 	mutex_unlock(&group->device_lock);
 
 	return device;
@@ -567,6 +569,7 @@ static void vfio_device_release(struct kref *kref)
 	struct vfio_group *group = device->group;
 
 	list_del(&device->group_next);
+	group->dev_counter--;
 	mutex_unlock(&group->device_lock);
 
 	dev_set_drvdata(device->dev, NULL);
@@ -1945,6 +1948,9 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 	if (!group)
 		return -ENODEV;
 
+	if (group->dev_counter > 1)
+		return -EINVAL;
+
 	ret = vfio_group_add_container_user(group);
 	if (ret)
 		goto err_pin_pages;
@@ -1952,7 +1958,8 @@ int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, int npage,
 	container = group->container;
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->pin_pages))
-		ret = driver->ops->pin_pages(container->iommu_data, user_pfn,
+		ret = driver->ops->pin_pages(container->iommu_data,
+					     group->iommu_group, user_pfn,
 					     npage, prot, phys_pfn);
 	else
 		ret = -ENOTTY;
@@ -2050,8 +2057,8 @@ int vfio_group_pin_pages(struct vfio_group *group,
 	driver = container->iommu_driver;
 	if (likely(driver && driver->ops->pin_pages))
 		ret = driver->ops->pin_pages(container->iommu_data,
-					     user_iova_pfn, npage,
-					     prot, phys_pfn);
+					     group->iommu_group, user_iova_pfn,
+					     npage, prot, phys_pfn);
 	else
 		ret = -ENOTTY;
 

drivers/vfio/vfio_iommu_type1.c

@@ -73,6 +73,7 @@ struct vfio_iommu {
 	bool			v2;
 	bool			nesting;
 	bool			dirty_page_tracking;
+	bool			pinned_page_dirty_scope;
 };
 
 struct vfio_domain {
@@ -100,6 +101,7 @@ struct vfio_group {
 	struct iommu_group	*iommu_group;
 	struct list_head	next;
 	bool			mdev_group;	/* An mdev group */
+	bool			pinned_page_dirty_scope;
 };
 
 struct vfio_iova {
@@ -143,6 +145,10 @@ struct vfio_regions {
 
 static int put_pfn(unsigned long pfn, int prot);
 
+static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+					       struct iommu_group *iommu_group);
+
+static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu);
 /*
  * This code handles mapping and unmapping of user data buffers
  * into DMA'ble space using the IOMMU
@@ -622,11 +628,13 @@ static int vfio_unpin_page_external(struct vfio_dma *dma, dma_addr_t iova,
 }
 
 static int vfio_iommu_type1_pin_pages(void *iommu_data,
+				      struct iommu_group *iommu_group,
 				      unsigned long *user_pfn,
 				      int npage, int prot,
 				      unsigned long *phys_pfn)
 {
 	struct vfio_iommu *iommu = iommu_data;
+	struct vfio_group *group;
 	int i, j, ret;
 	unsigned long remote_vaddr;
 	struct vfio_dma *dma;
@@ -699,8 +707,14 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
 				   (iova - dma->iova) >> pgshift, 1);
 		}
 	}
-
 	ret = i;
+
+	group = vfio_iommu_find_iommu_group(iommu, iommu_group);
+	if (!group->pinned_page_dirty_scope) {
+		group->pinned_page_dirty_scope = true;
+		update_pinned_page_dirty_scope(iommu);
+	}
+
 	goto pin_done;
 
 pin_unwind:
@@ -960,8 +974,9 @@ static void vfio_update_pgsize_bitmap(struct vfio_iommu *iommu)
 	}
 }
 
-static int update_user_bitmap(u64 __user *bitmap, struct vfio_dma *dma,
-			      dma_addr_t base_iova, size_t pgsize)
+static int update_user_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
+			      struct vfio_dma *dma, dma_addr_t base_iova,
+			      size_t pgsize)
 {
 	unsigned long pgshift = __ffs(pgsize);
 	unsigned long nbits = dma->size >> pgshift;
@@ -970,8 +985,11 @@ static int update_user_bitmap(u64 __user *bitmap, struct vfio_dma *dma,
 	unsigned long shift = bit_offset % BITS_PER_LONG;
 	unsigned long leftover;
 
-	/* mark all pages dirty if all pages are pinned and mapped. */
-	if (dma->iommu_mapped)
+	/*
+	 * mark all pages dirty if any IOMMU capable device is not able
+	 * to report dirty pages and all pages are pinned and mapped.
+	 */
+	if (!iommu->pinned_page_dirty_scope && dma->iommu_mapped)
 		bitmap_set(dma->bitmap, 0, nbits);
 
 	if (shift) {
@@ -1024,7 +1042,7 @@ static int vfio_iova_dirty_bitmap(u64 __user *bitmap, struct vfio_iommu *iommu,
 		if (dma->iova > iova + size - 1)
 			break;
 
-		ret = update_user_bitmap(bitmap, dma, iova, pgsize);
+		ret = update_user_bitmap(bitmap, iommu, dma, iova, pgsize);
 		if (ret)
 			return ret;
 
@@ -1169,7 +1187,7 @@ static int vfio_dma_do_unmap(struct vfio_iommu *iommu,
 		}
 
 		if (unmap->flags & VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP) {
-			ret = update_user_bitmap(bitmap->data, dma,
+			ret = update_user_bitmap(bitmap->data, iommu, dma,
 						 unmap->iova, pgsize);
 			if (ret)
 				break;
@@ -1521,6 +1539,51 @@ static struct vfio_group *find_iommu_group(struct vfio_domain *domain,
 	return NULL;
 }
 
+static struct vfio_group *vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
+					       struct iommu_group *iommu_group)
+{
+	struct vfio_domain *domain;
+	struct vfio_group *group = NULL;
+
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		group = find_iommu_group(domain, iommu_group);
+		if (group)
+			return group;
+	}
+
+	if (iommu->external_domain)
+		group = find_iommu_group(iommu->external_domain, iommu_group);
+
+	return group;
+}
+
+static void update_pinned_page_dirty_scope(struct vfio_iommu *iommu)
+{
+	struct vfio_domain *domain;
+	struct vfio_group *group;
+
+	list_for_each_entry(domain, &iommu->domain_list, next) {
+		list_for_each_entry(group, &domain->group_list, next) {
+			if (!group->pinned_page_dirty_scope) {
+				iommu->pinned_page_dirty_scope = false;
+				return;
+			}
+		}
+	}
+
+	if (iommu->external_domain) {
+		domain = iommu->external_domain;
+		list_for_each_entry(group, &domain->group_list, next) {
+			if (!group->pinned_page_dirty_scope) {
+				iommu->pinned_page_dirty_scope = false;
+				return;
+			}
+		}
+	}
+
+	iommu->pinned_page_dirty_scope = true;
+}
+
 static bool vfio_iommu_has_sw_msi(struct list_head *group_resv_regions,
 				  phys_addr_t *base)
 {
@@ -1928,6 +1991,16 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 
 			list_add(&group->next,
 				 &iommu->external_domain->group_list);
+			/*
+			 * Non-iommu backed group cannot dirty memory directly,
+			 * it can only use interfaces that provide dirty
+			 * tracking.
+			 * The iommu scope can only be promoted with the
+			 * addition of a dirty tracking group.
+			 */
+			group->pinned_page_dirty_scope = true;
+			if (!iommu->pinned_page_dirty_scope)
+				update_pinned_page_dirty_scope(iommu);
 			mutex_unlock(&iommu->lock);
 
 			return 0;
@@ -2051,6 +2124,13 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 done:
 	/* Delete the old one and insert new iova list */
 	vfio_iommu_iova_insert_copy(iommu, &iova_copy);
+
+	/*
+	 * An iommu backed group can dirty memory directly and therefore
+	 * demotes the iommu scope until it declares itself dirty tracking
+	 * capable via the page pinning interface.
+	 */
+	iommu->pinned_page_dirty_scope = false;
 	mutex_unlock(&iommu->lock);
 	vfio_iommu_resv_free(&group_resv_regions);
 
@@ -2203,6 +2283,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_domain *domain;
 	struct vfio_group *group;
+	bool update_dirty_scope = false;
 	LIST_HEAD(iova_copy);
 
 	mutex_lock(&iommu->lock);
@@ -2210,6 +2291,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 	if (iommu->external_domain) {
 		group = find_iommu_group(iommu->external_domain, iommu_group);
 		if (group) {
+			update_dirty_scope = !group->pinned_page_dirty_scope;
 			list_del(&group->next);
 			kfree(group);
 
@@ -2239,6 +2321,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 			continue;
 
 		vfio_iommu_detach_group(domain, group);
+		update_dirty_scope = !group->pinned_page_dirty_scope;
 		list_del(&group->next);
 		kfree(group);
 		/*
@@ -2270,6 +2353,12 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		vfio_iommu_iova_free(&iova_copy);
 
 detach_group_done:
+	/*
+	 * Removal of a group without dirty tracking may allow the iommu scope
+	 * to be promoted.
+	 */
+	if (update_dirty_scope)
+		update_pinned_page_dirty_scope(iommu);
 	mutex_unlock(&iommu->lock);
 }
 

include/linux/vfio.h

@@ -76,7 +76,9 @@ struct vfio_iommu_driver_ops {
 					struct iommu_group *group);
 	void		(*detach_group)(void *iommu_data,
 					struct iommu_group *group);
-	int		(*pin_pages)(void *iommu_data, unsigned long *user_pfn,
+	int		(*pin_pages)(void *iommu_data,
+				     struct iommu_group *group,
+				     unsigned long *user_pfn,
 				     int npage, int prot,
 				     unsigned long *phys_pfn);
 	int		(*unpin_pages)(void *iommu_data,