1 files changed, 73 insertions, 183 deletions

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 0e9217687f5c..f17490ab238f 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -36,10 +36,10 @@
 #include <linux/uaccess.h>
 #include <linux/vfio.h>
 #include <linux/workqueue.h>
-#include <linux/mdev.h>
 #include <linux/notifier.h>
 #include <linux/dma-iommu.h>
 #include <linux/irqdomain.h>
+#include "vfio.h"
 
 #define DRIVER_VERSION  "0.2"
 #define DRIVER_AUTHOR   "Alex Williamson <alex.williamson@redhat.com>"
@@ -65,7 +65,6 @@ 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;
 	struct blocking_notifier_head notifier;
@@ -78,6 +77,7 @@ struct vfio_iommu {
 	bool			nesting;
 	bool			dirty_page_tracking;
 	bool			container_open;
+	struct list_head	emulated_iommu_groups;
 };
 
 struct vfio_domain {
@@ -113,7 +113,6 @@ struct vfio_batch {
 struct vfio_iommu_group {
 	struct iommu_group	*iommu_group;
 	struct list_head	next;
-	bool			mdev_group;	/* An mdev group */
 	bool			pinned_page_dirty_scope;
 };
 
@@ -140,9 +139,6 @@ struct vfio_regions {
 	size_t len;
 };
 
-#define IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)	\
-					(!list_empty(&iommu->domain_list))
-
 #define DIRTY_BITMAP_BYTES(n)	(ALIGN(n, BITS_PER_TYPE(u64)) / BITS_PER_BYTE)
 
 /*
@@ -880,7 +876,7 @@ again:
 	 * already pinned and accounted. Accounting should be done if there is no
 	 * iommu capable domain in the container.
 	 */
-	do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu);
+	do_accounting = list_empty(&iommu->domain_list);
 
 	for (i = 0; i < npage; i++) {
 		struct vfio_pfn *vpfn;
@@ -969,7 +965,7 @@ static int vfio_iommu_type1_unpin_pages(void *iommu_data,
 
 	mutex_lock(&iommu->lock);
 
-	do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu);
+	do_accounting = list_empty(&iommu->domain_list);
 	for (i = 0; i < npage; i++) {
 		struct vfio_dma *dma;
 		dma_addr_t iova;
@@ -1090,7 +1086,7 @@ static long vfio_unmap_unpin(struct vfio_iommu *iommu, struct vfio_dma *dma,
 	if (!dma->size)
 		return 0;
 
-	if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu))
+	if (list_empty(&iommu->domain_list))
 		return 0;
 
 	/*
@@ -1667,7 +1663,7 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
 	vfio_link_dma(iommu, dma);
 
 	/* Don't pin and map if container doesn't contain IOMMU capable domain*/
-	if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu))
+	if (list_empty(&iommu->domain_list))
 		dma->size = size;
 	else
 		ret = vfio_pin_map_dma(iommu, dma, size);
@@ -1893,8 +1889,8 @@ static struct vfio_iommu_group*
 vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
 			    struct iommu_group *iommu_group)
 {
+	struct vfio_iommu_group *group;
 	struct vfio_domain *domain;
-	struct vfio_iommu_group *group = NULL;
 
 	list_for_each_entry(domain, &iommu->domain_list, next) {
 		group = find_iommu_group(domain, iommu_group);
@@ -1902,10 +1898,10 @@ vfio_iommu_find_iommu_group(struct vfio_iommu *iommu,
 			return group;
 	}
 
-	if (iommu->external_domain)
-		group = find_iommu_group(iommu->external_domain, iommu_group);
-
-	return group;
+	list_for_each_entry(group, &iommu->emulated_iommu_groups, next)
+		if (group->iommu_group == iommu_group)
+			return group;
+	return NULL;
 }
 
 static bool vfio_iommu_has_sw_msi(struct list_head *group_resv_regions,
@@ -1934,89 +1930,6 @@ static bool vfio_iommu_has_sw_msi(struct list_head *group_resv_regions,
 	return ret;
 }
 
-static int vfio_mdev_attach_domain(struct device *dev, void *data)
-{
-	struct mdev_device *mdev = to_mdev_device(dev);
-	struct iommu_domain *domain = data;
-	struct device *iommu_device;
-
-	iommu_device = mdev_get_iommu_device(mdev);
-	if (iommu_device) {
-		if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX))
-			return iommu_aux_attach_device(domain, iommu_device);
-		else
-			return iommu_attach_device(domain, iommu_device);
-	}
-
-	return -EINVAL;
-}
-
-static int vfio_mdev_detach_domain(struct device *dev, void *data)
-{
-	struct mdev_device *mdev = to_mdev_device(dev);
-	struct iommu_domain *domain = data;
-	struct device *iommu_device;
-
-	iommu_device = mdev_get_iommu_device(mdev);
-	if (iommu_device) {
-		if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX))
-			iommu_aux_detach_device(domain, iommu_device);
-		else
-			iommu_detach_device(domain, iommu_device);
-	}
-
-	return 0;
-}
-
-static int vfio_iommu_attach_group(struct vfio_domain *domain,
-				   struct vfio_iommu_group *group)
-{
-	if (group->mdev_group)
-		return iommu_group_for_each_dev(group->iommu_group,
-						domain->domain,
-						vfio_mdev_attach_domain);
-	else
-		return iommu_attach_group(domain->domain, group->iommu_group);
-}
-
-static void vfio_iommu_detach_group(struct vfio_domain *domain,
-				    struct vfio_iommu_group *group)
-{
-	if (group->mdev_group)
-		iommu_group_for_each_dev(group->iommu_group, domain->domain,
-					 vfio_mdev_detach_domain);
-	else
-		iommu_detach_group(domain->domain, group->iommu_group);
-}
-
-static bool vfio_bus_is_mdev(struct bus_type *bus)
-{
-	struct bus_type *mdev_bus;
-	bool ret = false;
-
-	mdev_bus = symbol_get(mdev_bus_type);
-	if (mdev_bus) {
-		ret = (bus == mdev_bus);
-		symbol_put(mdev_bus_type);
-	}
-
-	return ret;
-}
-
-static int vfio_mdev_iommu_device(struct device *dev, void *data)
-{
-	struct mdev_device *mdev = to_mdev_device(dev);
-	struct device **old = data, *new;
-
-	new = mdev_get_iommu_device(mdev);
-	if (!new || (*old && *old != new))
-		return -EINVAL;
-
-	*old = new;
-
-	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
@@ -2241,81 +2154,58 @@ static void vfio_iommu_iova_insert_copy(struct vfio_iommu *iommu,
 }
 
 static int vfio_iommu_type1_attach_group(void *iommu_data,
-					 struct iommu_group *iommu_group)
+		struct iommu_group *iommu_group, enum vfio_group_type type)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_iommu_group *group;
 	struct vfio_domain *domain, *d;
 	struct bus_type *bus = NULL;
-	int ret;
 	bool resv_msi, msi_remap;
 	phys_addr_t resv_msi_base = 0;
 	struct iommu_domain_geometry *geo;
 	LIST_HEAD(iova_copy);
 	LIST_HEAD(group_resv_regions);
+	int ret = -EINVAL;
 
 	mutex_lock(&iommu->lock);
 
 	/* Check for duplicates */
-	if (vfio_iommu_find_iommu_group(iommu, iommu_group)) {
-		mutex_unlock(&iommu->lock);
-		return -EINVAL;
-	}
+	if (vfio_iommu_find_iommu_group(iommu, iommu_group))
+		goto out_unlock;
 
+	ret = -ENOMEM;
 	group = kzalloc(sizeof(*group), GFP_KERNEL);
-	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
-	if (!group || !domain) {
-		ret = -ENOMEM;
-		goto out_free;
-	}
-
+	if (!group)
+		goto out_unlock;
 	group->iommu_group = iommu_group;
 
+	if (type == VFIO_EMULATED_IOMMU) {
+		list_add(&group->next, &iommu->emulated_iommu_groups);
+		/*
+		 * An emulated IOMMU 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;
+		ret = 0;
+		goto out_unlock;
+	}
+
 	/* Determine bus_type in order to allocate a domain */
 	ret = iommu_group_for_each_dev(iommu_group, &bus, vfio_bus_type);
 	if (ret)
-		goto out_free;
-
-	if (vfio_bus_is_mdev(bus)) {
-		struct device *iommu_device = NULL;
-
-		group->mdev_group = true;
-
-		/* Determine the isolation type */
-		ret = iommu_group_for_each_dev(iommu_group, &iommu_device,
-					       vfio_mdev_iommu_device);
-		if (ret || !iommu_device) {
-			if (!iommu->external_domain) {
-				INIT_LIST_HEAD(&domain->group_list);
-				iommu->external_domain = domain;
-				vfio_update_pgsize_bitmap(iommu);
-			} else {
-				kfree(domain);
-			}
-
-			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;
-			mutex_unlock(&iommu->lock);
+		goto out_free_group;
 
-			return 0;
-		}
-
-		bus = iommu_device->bus;
-	}
+	ret = -ENOMEM;
+	domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+	if (!domain)
+		goto out_free_group;
 
+	ret = -EIO;
 	domain->domain = iommu_domain_alloc(bus);
-	if (!domain->domain) {
-		ret = -EIO;
-		goto out_free;
-	}
+	if (!domain->domain)
+		goto out_free_domain;
 
 	if (iommu->nesting) {
 		ret = iommu_enable_nesting(domain->domain);
@@ -2323,7 +2213,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 			goto out_domain;
 	}
 
-	ret = vfio_iommu_attach_group(domain, group);
+	ret = iommu_attach_group(domain->domain, group->iommu_group);
 	if (ret)
 		goto out_domain;
 
@@ -2390,15 +2280,17 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
 	list_for_each_entry(d, &iommu->domain_list, next) {
 		if (d->domain->ops == domain->domain->ops &&
 		    d->prot == domain->prot) {
-			vfio_iommu_detach_group(domain, group);
-			if (!vfio_iommu_attach_group(d, group)) {
+			iommu_detach_group(domain->domain, group->iommu_group);
+			if (!iommu_attach_group(d->domain,
+						group->iommu_group)) {
 				list_add(&group->next, &d->group_list);
 				iommu_domain_free(domain->domain);
 				kfree(domain);
 				goto done;
 			}
 
-			ret = vfio_iommu_attach_group(domain, group);
+			ret = iommu_attach_group(domain->domain,
+						 group->iommu_group);
 			if (ret)
 				goto out_domain;
 		}
@@ -2435,14 +2327,16 @@ done:
 	return 0;
 
 out_detach:
-	vfio_iommu_detach_group(domain, group);
+	iommu_detach_group(domain->domain, group->iommu_group);
 out_domain:
 	iommu_domain_free(domain->domain);
 	vfio_iommu_iova_free(&iova_copy);
 	vfio_iommu_resv_free(&group_resv_regions);
-out_free:
+out_free_domain:
 	kfree(domain);
+out_free_group:
 	kfree(group);
+out_unlock:
 	mutex_unlock(&iommu->lock);
 	return ret;
 }
@@ -2567,25 +2461,19 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 	LIST_HEAD(iova_copy);
 
 	mutex_lock(&iommu->lock);
+	list_for_each_entry(group, &iommu->emulated_iommu_groups, next) {
+		if (group->iommu_group != iommu_group)
+			continue;
+		update_dirty_scope = !group->pinned_page_dirty_scope;
+		list_del(&group->next);
+		kfree(group);
 
-	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);
-
-			if (list_empty(&iommu->external_domain->group_list)) {
-				if (!IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu)) {
-					WARN_ON(iommu->notifier.head);
-					vfio_iommu_unmap_unpin_all(iommu);
-				}
-
-				kfree(iommu->external_domain);
-				iommu->external_domain = NULL;
-			}
-			goto detach_group_done;
+		if (list_empty(&iommu->emulated_iommu_groups) &&
+		    list_empty(&iommu->domain_list)) {
+			WARN_ON(iommu->notifier.head);
+			vfio_iommu_unmap_unpin_all(iommu);
 		}
+		goto detach_group_done;
 	}
 
 	/*
@@ -2600,7 +2488,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		if (!group)
 			continue;
 
-		vfio_iommu_detach_group(domain, group);
+		iommu_detach_group(domain->domain, group->iommu_group);
 		update_dirty_scope = !group->pinned_page_dirty_scope;
 		list_del(&group->next);
 		kfree(group);
@@ -2613,7 +2501,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
 		 */
 		if (list_empty(&domain->group_list)) {
 			if (list_is_singular(&iommu->domain_list)) {
-				if (!iommu->external_domain) {
+				if (list_empty(&iommu->emulated_iommu_groups)) {
 					WARN_ON(iommu->notifier.head);
 					vfio_iommu_unmap_unpin_all(iommu);
 				} else {
@@ -2677,41 +2565,43 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 	mutex_init(&iommu->lock);
 	BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
 	init_waitqueue_head(&iommu->vaddr_wait);
+	iommu->pgsize_bitmap = PAGE_MASK;
+	INIT_LIST_HEAD(&iommu->emulated_iommu_groups);
 
 	return iommu;
 }
 
-static void vfio_release_domain(struct vfio_domain *domain, bool external)
+static void vfio_release_domain(struct vfio_domain *domain)
 {
 	struct vfio_iommu_group *group, *group_tmp;
 
 	list_for_each_entry_safe(group, group_tmp,
 				 &domain->group_list, next) {
-		if (!external)
-			vfio_iommu_detach_group(domain, group);
+		iommu_detach_group(domain->domain, group->iommu_group);
 		list_del(&group->next);
 		kfree(group);
 	}
 
-	if (!external)
-		iommu_domain_free(domain->domain);
+	iommu_domain_free(domain->domain);
 }
 
 static void vfio_iommu_type1_release(void *iommu_data)
 {
 	struct vfio_iommu *iommu = iommu_data;
 	struct vfio_domain *domain, *domain_tmp;
+	struct vfio_iommu_group *group, *next_group;
 
-	if (iommu->external_domain) {
-		vfio_release_domain(iommu->external_domain, true);
-		kfree(iommu->external_domain);
+	list_for_each_entry_safe(group, next_group,
+			&iommu->emulated_iommu_groups, next) {
+		list_del(&group->next);
+		kfree(group);
 	}
 
 	vfio_iommu_unmap_unpin_all(iommu);
 
 	list_for_each_entry_safe(domain, domain_tmp,
 				 &iommu->domain_list, next) {
-		vfio_release_domain(domain, false);
+		vfio_release_domain(domain);
 		list_del(&domain->next);
 		kfree(domain);
 	}