1 files changed, 73 insertions, 170 deletions

diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 81401f386c9c..4fc83e3f5ad3 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -55,15 +55,12 @@ MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
 	      "Gerd Hoffmann <kraxel@redhat.com>");
 MODULE_DESCRIPTION("User-space granted page access driver");
 
-static int limit = 1024*1024;
-module_param(limit, int, 0644);
-MODULE_PARM_DESC(limit, "Maximum number of grants that may be mapped by "
-		"the gntdev device");
-
-static atomic_t pages_mapped = ATOMIC_INIT(0);
+static unsigned int limit = 64*1024;
+module_param(limit, uint, 0644);
+MODULE_PARM_DESC(limit,
+	"Maximum number of grants that may be mapped by one mapping request");
 
 static int use_ptemod;
-#define populate_freeable_maps use_ptemod
 
 static int unmap_grant_pages(struct gntdev_grant_map *map,
 			     int offset, int pages);
@@ -72,9 +69,9 @@ static struct miscdevice gntdev_miscdev;
 
 /* ------------------------------------------------------------------ */
 
-bool gntdev_account_mapped_pages(int count)
+bool gntdev_test_page_count(unsigned int count)
 {
-	return atomic_add_return(count, &pages_mapped) > limit;
+	return !count || count > limit;
 }
 
 static void gntdev_print_maps(struct gntdev_priv *priv,
@@ -115,14 +112,14 @@ static void gntdev_free_map(struct gntdev_grant_map *map)
 		gnttab_free_pages(map->count, map->pages);
 
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
-	kfree(map->frames);
+	kvfree(map->frames);
 #endif
-	kfree(map->pages);
-	kfree(map->grants);
-	kfree(map->map_ops);
-	kfree(map->unmap_ops);
-	kfree(map->kmap_ops);
-	kfree(map->kunmap_ops);
+	kvfree(map->pages);
+	kvfree(map->grants);
+	kvfree(map->map_ops);
+	kvfree(map->unmap_ops);
+	kvfree(map->kmap_ops);
+	kvfree(map->kunmap_ops);
 	kfree(map);
 }
 
@@ -136,12 +133,13 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	if (NULL == add)
 		return NULL;
 
-	add->grants    = kcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
-	add->map_ops   = kcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
-	add->unmap_ops = kcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
-	add->kmap_ops  = kcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
-	add->kunmap_ops = kcalloc(count, sizeof(add->kunmap_ops[0]), GFP_KERNEL);
-	add->pages     = kcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
+	add->grants    = kvcalloc(count, sizeof(add->grants[0]), GFP_KERNEL);
+	add->map_ops   = kvcalloc(count, sizeof(add->map_ops[0]), GFP_KERNEL);
+	add->unmap_ops = kvcalloc(count, sizeof(add->unmap_ops[0]), GFP_KERNEL);
+	add->kmap_ops  = kvcalloc(count, sizeof(add->kmap_ops[0]), GFP_KERNEL);
+	add->kunmap_ops = kvcalloc(count,
+				   sizeof(add->kunmap_ops[0]), GFP_KERNEL);
+	add->pages     = kvcalloc(count, sizeof(add->pages[0]), GFP_KERNEL);
 	if (NULL == add->grants    ||
 	    NULL == add->map_ops   ||
 	    NULL == add->unmap_ops ||
@@ -160,8 +158,8 @@ struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 	if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) {
 		struct gnttab_dma_alloc_args args;
 
-		add->frames = kcalloc(count, sizeof(add->frames[0]),
-				      GFP_KERNEL);
+		add->frames = kvcalloc(count, sizeof(add->frames[0]),
+				       GFP_KERNEL);
 		if (!add->frames)
 			goto err;
 
@@ -242,19 +240,11 @@ void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 	if (!refcount_dec_and_test(&map->users))
 		return;
 
-	atomic_sub(map->count, &pages_mapped);
-
 	if (map->notify.flags & UNMAP_NOTIFY_SEND_EVENT) {
 		notify_remote_via_evtchn(map->notify.event);
 		evtchn_put(map->notify.event);
 	}
 
-	if (populate_freeable_maps && priv) {
-		mutex_lock(&priv->lock);
-		list_del(&map->next);
-		mutex_unlock(&priv->lock);
-	}
-
 	if (map->pages && !use_ptemod)
 		unmap_grant_pages(map, 0, map->count);
 	gntdev_free_map(map);
@@ -444,16 +434,9 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 
 	pr_debug("gntdev_vma_close %p\n", vma);
 	if (use_ptemod) {
-		/* It is possible that an mmu notifier could be running
-		 * concurrently, so take priv->lock to ensure that the vma won't
-		 * vanishing during the unmap_grant_pages call, since we will
-		 * spin here until that completes. Such a concurrent call will
-		 * not do any unmapping, since that has been done prior to
-		 * closing the vma, but it may still iterate the unmap_ops list.
-		 */
-		mutex_lock(&priv->lock);
+		WARN_ON(map->vma != vma);
+		mmu_interval_notifier_remove(&map->notifier);
 		map->vma = NULL;
-		mutex_unlock(&priv->lock);
 	}
 	vma->vm_private_data = NULL;
 	gntdev_put_map(priv, map);
@@ -475,109 +458,44 @@ static const struct vm_operations_struct gntdev_vmops = {
 
 /* ------------------------------------------------------------------ */
 
-static bool in_range(struct gntdev_grant_map *map,
-			      unsigned long start, unsigned long end)
-{
-	if (!map->vma)
-		return false;
-	if (map->vma->vm_start >= end)
-		return false;
-	if (map->vma->vm_end <= start)
-		return false;
-
-	return true;
-}
-
-static int unmap_if_in_range(struct gntdev_grant_map *map,
-			      unsigned long start, unsigned long end,
-			      bool blockable)
+static bool gntdev_invalidate(struct mmu_interval_notifier *mn,
+			      const struct mmu_notifier_range *range,
+			      unsigned long cur_seq)
 {
+	struct gntdev_grant_map *map =
+		container_of(mn, struct gntdev_grant_map, notifier);
 	unsigned long mstart, mend;
 	int err;
 
-	if (!in_range(map, start, end))
-		return 0;
+	if (!mmu_notifier_range_blockable(range))
+		return false;
 
-	if (!blockable)
-		return -EAGAIN;
+	/*
+	 * If the VMA is split or otherwise changed the notifier is not
+	 * updated, but we don't want to process VA's outside the modified
+	 * VMA. FIXME: It would be much more understandable to just prevent
+	 * modifying the VMA in the first place.
+	 */
+	if (map->vma->vm_start >= range->end ||
+	    map->vma->vm_end <= range->start)
+		return true;
 
-	mstart = max(start, map->vma->vm_start);
-	mend   = min(end,   map->vma->vm_end);
+	mstart = max(range->start, map->vma->vm_start);
+	mend = min(range->end, map->vma->vm_end);
 	pr_debug("map %d+%d (%lx %lx), range %lx %lx, mrange %lx %lx\n",
 			map->index, map->count,
 			map->vma->vm_start, map->vma->vm_end,
-			start, end, mstart, mend);
+			range->start, range->end, mstart, mend);
 	err = unmap_grant_pages(map,
 				(mstart - map->vma->vm_start) >> PAGE_SHIFT,
 				(mend - mstart) >> PAGE_SHIFT);
 	WARN_ON(err);
 
-	return 0;
-}
-
-static int mn_invl_range_start(struct mmu_notifier *mn,
-			       const struct mmu_notifier_range *range)
-{
-	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct gntdev_grant_map *map;
-	int ret = 0;
-
-	if (mmu_notifier_range_blockable(range))
-		mutex_lock(&priv->lock);
-	else if (!mutex_trylock(&priv->lock))
-		return -EAGAIN;
-
-	list_for_each_entry(map, &priv->maps, next) {
-		ret = unmap_if_in_range(map, range->start, range->end,
-					mmu_notifier_range_blockable(range));
-		if (ret)
-			goto out_unlock;
-	}
-	list_for_each_entry(map, &priv->freeable_maps, next) {
-		ret = unmap_if_in_range(map, range->start, range->end,
-					mmu_notifier_range_blockable(range));
-		if (ret)
-			goto out_unlock;
-	}
-
-out_unlock:
-	mutex_unlock(&priv->lock);
-
-	return ret;
-}
-
-static void mn_release(struct mmu_notifier *mn,
-		       struct mm_struct *mm)
-{
-	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct gntdev_grant_map *map;
-	int err;
-
-	mutex_lock(&priv->lock);
-	list_for_each_entry(map, &priv->maps, next) {
-		if (!map->vma)
-			continue;
-		pr_debug("map %d+%d (%lx %lx)\n",
-				map->index, map->count,
-				map->vma->vm_start, map->vma->vm_end);
-		err = unmap_grant_pages(map, /* offset */ 0, map->count);
-		WARN_ON(err);
-	}
-	list_for_each_entry(map, &priv->freeable_maps, next) {
-		if (!map->vma)
-			continue;
-		pr_debug("map %d+%d (%lx %lx)\n",
-				map->index, map->count,
-				map->vma->vm_start, map->vma->vm_end);
-		err = unmap_grant_pages(map, /* offset */ 0, map->count);
-		WARN_ON(err);
-	}
-	mutex_unlock(&priv->lock);
+	return true;
 }
 
-static const struct mmu_notifier_ops gntdev_mmu_ops = {
-	.release                = mn_release,
-	.invalidate_range_start = mn_invl_range_start,
+static const struct mmu_interval_notifier_ops gntdev_mmu_ops = {
+	.invalidate = gntdev_invalidate,
 };
 
 /* ------------------------------------------------------------------ */
@@ -585,40 +503,23 @@ static const struct mmu_notifier_ops gntdev_mmu_ops = {
 static int gntdev_open(struct inode *inode, struct file *flip)
 {
 	struct gntdev_priv *priv;
-	int ret = 0;
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	INIT_LIST_HEAD(&priv->maps);
-	INIT_LIST_HEAD(&priv->freeable_maps);
 	mutex_init(&priv->lock);
 
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
 	priv->dmabuf_priv = gntdev_dmabuf_init(flip);
 	if (IS_ERR(priv->dmabuf_priv)) {
-		ret = PTR_ERR(priv->dmabuf_priv);
-		kfree(priv);
-		return ret;
-	}
-#endif
-
-	if (use_ptemod) {
-		priv->mm = get_task_mm(current);
-		if (!priv->mm) {
-			kfree(priv);
-			return -ENOMEM;
-		}
-		priv->mn.ops = &gntdev_mmu_ops;
-		ret = mmu_notifier_register(&priv->mn, priv->mm);
-		mmput(priv->mm);
-	}
+		int ret = PTR_ERR(priv->dmabuf_priv);
 
-	if (ret) {
 		kfree(priv);
 		return ret;
 	}
+#endif
 
 	flip->private_data = priv;
 #ifdef CONFIG_XEN_GRANT_DMA_ALLOC
@@ -644,16 +545,12 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
-	WARN_ON(!list_empty(&priv->freeable_maps));
 	mutex_unlock(&priv->lock);
 
 #ifdef CONFIG_XEN_GNTDEV_DMABUF
 	gntdev_dmabuf_fini(priv->dmabuf_priv);
 #endif
 
-	if (use_ptemod)
-		mmu_notifier_unregister(&priv->mn, priv->mm);
-
 	kfree(priv);
 	return 0;
 }
@@ -668,7 +565,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
 		return -EFAULT;
 	pr_debug("priv %p, add %d\n", priv, op.count);
-	if (unlikely(op.count <= 0))
+	if (unlikely(gntdev_test_page_count(op.count)))
 		return -EINVAL;
 
 	err = -ENOMEM;
@@ -676,12 +573,6 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 	if (!map)
 		return err;
 
-	if (unlikely(gntdev_account_mapped_pages(op.count))) {
-		pr_debug("can't map: over limit\n");
-		gntdev_put_map(NULL, map);
-		return err;
-	}
-
 	if (copy_from_user(map->grants, &u->refs,
 			   sizeof(map->grants[0]) * op.count) != 0) {
 		gntdev_put_map(NULL, map);
@@ -714,8 +605,6 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 	map = gntdev_find_map_index(priv, op.index >> PAGE_SHIFT, op.count);
 	if (map) {
 		list_del(&map->next);
-		if (populate_freeable_maps)
-			list_add_tail(&map->next, &priv->freeable_maps);
 		err = 0;
 	}
 	mutex_unlock(&priv->lock);
@@ -1087,11 +976,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		goto unlock_out;
 	if (use_ptemod && map->vma)
 		goto unlock_out;
-	if (use_ptemod && priv->mm != vma->vm_mm) {
-		pr_warn("Huh? Other mm?\n");
-		goto unlock_out;
-	}
-
 	refcount_inc(&map->users);
 
 	vma->vm_ops = &gntdev_vmops;
@@ -1102,10 +986,6 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		vma->vm_flags |= VM_DONTCOPY;
 
 	vma->vm_private_data = map;
-
-	if (use_ptemod)
-		map->vma = vma;
-
 	if (map->flags) {
 		if ((vma->vm_flags & VM_WRITE) &&
 				(map->flags & GNTMAP_readonly))
@@ -1116,8 +996,28 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 			map->flags |= GNTMAP_readonly;
 	}
 
+	if (use_ptemod) {
+		map->vma = vma;
+		err = mmu_interval_notifier_insert_locked(
+			&map->notifier, vma->vm_mm, vma->vm_start,
+			vma->vm_end - vma->vm_start, &gntdev_mmu_ops);
+		if (err)
+			goto out_unlock_put;
+	}
 	mutex_unlock(&priv->lock);
 
+	/*
+	 * gntdev takes the address of the PTE in find_grant_ptes() and passes
+	 * it to the hypervisor in gntdev_map_grant_pages(). The purpose of
+	 * the notifier is to prevent the hypervisor pointer to the PTE from
+	 * going stale.
+	 *
+	 * Since this vma's mappings can't be touched without the mmap_sem,
+	 * and we are holding it now, there is no need for the notifier_range
+	 * locking pattern.
+	 */
+	mmu_interval_read_begin(&map->notifier);
+
 	if (use_ptemod) {
 		map->pages_vm_start = vma->vm_start;
 		err = apply_to_page_range(vma->vm_mm, vma->vm_start,
@@ -1166,8 +1066,11 @@ out_unlock_put:
 	mutex_unlock(&priv->lock);
 out_put_map:
 	if (use_ptemod) {
-		map->vma = NULL;
 		unmap_grant_pages(map, 0, map->count);
+		if (map->vma) {
+			mmu_interval_notifier_remove(&map->notifier);
+			map->vma = NULL;
+		}
 	}
 	gntdev_put_map(priv, map);
 	return err;