27 files changed, 493 insertions, 424 deletions

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index c59515ba7e69..add1737dae0d 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -64,8 +64,8 @@ static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, int atomic)
 		else {
 			child =
 			    list_entry(mm->unused_nodes.next,
-				       struct drm_mm_node, free_stack);
-			list_del(&child->free_stack);
+				       struct drm_mm_node, node_list);
+			list_del(&child->node_list);
 			--mm->num_unused;
 		}
 		spin_unlock(&mm->unused_lock);
@@ -94,195 +94,242 @@ int drm_mm_pre_get(struct drm_mm *mm)
 			return ret;
 		}
 		++mm->num_unused;
-		list_add_tail(&node->free_stack, &mm->unused_nodes);
+		list_add_tail(&node->node_list, &mm->unused_nodes);
 	}
 	spin_unlock(&mm->unused_lock);
 	return 0;
 }
 EXPORT_SYMBOL(drm_mm_pre_get);
 
-static int drm_mm_create_tail_node(struct drm_mm *mm,
-				   unsigned long start,
-				   unsigned long size, int atomic)
+static inline unsigned long drm_mm_hole_node_start(struct drm_mm_node *hole_node)
 {
-	struct drm_mm_node *child;
-
-	child = drm_mm_kmalloc(mm, atomic);
-	if (unlikely(child == NULL))
-		return -ENOMEM;
-
-	child->free = 1;
-	child->size = size;
-	child->start = start;
-	child->mm = mm;
+	return hole_node->start + hole_node->size;
+}
 
-	list_add_tail(&child->node_list, &mm->node_list);
-	list_add_tail(&child->free_stack, &mm->free_stack);
+static inline unsigned long drm_mm_hole_node_end(struct drm_mm_node *hole_node)
+{
+	struct drm_mm_node *next_node =
+		list_entry(hole_node->node_list.next, struct drm_mm_node,
+			   node_list);
 
-	return 0;
+	return next_node->start;
 }
 
-static struct drm_mm_node *drm_mm_split_at_start(struct drm_mm_node *parent,
-						 unsigned long size,
-						 int atomic)
+static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
+				 struct drm_mm_node *node,
+				 unsigned long size, unsigned alignment)
 {
-	struct drm_mm_node *child;
+	struct drm_mm *mm = hole_node->mm;
+	unsigned long tmp = 0, wasted = 0;
+	unsigned long hole_start = drm_mm_hole_node_start(hole_node);
+	unsigned long hole_end = drm_mm_hole_node_end(hole_node);
 
-	child = drm_mm_kmalloc(parent->mm, atomic);
-	if (unlikely(child == NULL))
-		return NULL;
+	BUG_ON(!hole_node->hole_follows || node->allocated);
 
-	INIT_LIST_HEAD(&child->free_stack);
+	if (alignment)
+		tmp = hole_start % alignment;
 
-	child->size = size;
-	child->start = parent->start;
-	child->mm = parent->mm;
+	if (!tmp) {
+		hole_node->hole_follows = 0;
+		list_del_init(&hole_node->hole_stack);
+	} else
+		wasted = alignment - tmp;
 
-	list_add_tail(&child->node_list, &parent->node_list);
-	INIT_LIST_HEAD(&child->free_stack);
+	node->start = hole_start + wasted;
+	node->size = size;
+	node->mm = mm;
+	node->allocated = 1;
 
-	parent->size -= size;
-	parent->start += size;
-	return child;
-}
+	INIT_LIST_HEAD(&node->hole_stack);
+	list_add(&node->node_list, &hole_node->node_list);
+
+	BUG_ON(node->start + node->size > hole_end);
 
+	if (node->start + node->size < hole_end) {
+		list_add(&node->hole_stack, &mm->hole_stack);
+		node->hole_follows = 1;
+	} else {
+		node->hole_follows = 0;
+	}
+}
 
-struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *node,
+struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *hole_node,
 					     unsigned long size,
 					     unsigned alignment,
 					     int atomic)
 {
+	struct drm_mm_node *node;
 
-	struct drm_mm_node *align_splitoff = NULL;
-	unsigned tmp = 0;
+	node = drm_mm_kmalloc(hole_node->mm, atomic);
+	if (unlikely(node == NULL))
+		return NULL;
 
-	if (alignment)
-		tmp = node->start % alignment;
+	drm_mm_insert_helper(hole_node, node, size, alignment);
 
-	if (tmp) {
-		align_splitoff =
-		    drm_mm_split_at_start(node, alignment - tmp, atomic);
-		if (unlikely(align_splitoff == NULL))
-			return NULL;
-	}
+	return node;
+}
+EXPORT_SYMBOL(drm_mm_get_block_generic);
 
-	if (node->size == size) {
-		list_del_init(&node->free_stack);
-		node->free = 0;
-	} else {
-		node = drm_mm_split_at_start(node, size, atomic);
-	}
+/**
+ * Search for free space and insert a preallocated memory node. Returns
+ * -ENOSPC if no suitable free area is available. The preallocated memory node
+ * must be cleared.
+ */
+int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
+		       unsigned long size, unsigned alignment)
+{
+	struct drm_mm_node *hole_node;
 
-	if (align_splitoff)
-		drm_mm_put_block(align_splitoff);
+	hole_node = drm_mm_search_free(mm, size, alignment, 0);
+	if (!hole_node)
+		return -ENOSPC;
 
-	return node;
+	drm_mm_insert_helper(hole_node, node, size, alignment);
+
+	return 0;
 }
-EXPORT_SYMBOL(drm_mm_get_block_generic);
+EXPORT_SYMBOL(drm_mm_insert_node);
 
-struct drm_mm_node *drm_mm_get_block_range_generic(struct drm_mm_node *node,
-						unsigned long size,
-						unsigned alignment,
-						unsigned long start,
-						unsigned long end,
-						int atomic)
+static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
+				       struct drm_mm_node *node,
+				       unsigned long size, unsigned alignment,
+				       unsigned long start, unsigned long end)
 {
-	struct drm_mm_node *align_splitoff = NULL;
-	unsigned tmp = 0;
-	unsigned wasted = 0;
+	struct drm_mm *mm = hole_node->mm;
+	unsigned long tmp = 0, wasted = 0;
+	unsigned long hole_start = drm_mm_hole_node_start(hole_node);
+	unsigned long hole_end = drm_mm_hole_node_end(hole_node);
+
+	BUG_ON(!hole_node->hole_follows || node->allocated);
 
-	if (node->start < start)
-		wasted += start - node->start;
+	if (hole_start < start)
+		wasted += start - hole_start;
 	if (alignment)
-		tmp = ((node->start + wasted) % alignment);
+		tmp = (hole_start + wasted) % alignment;
 
 	if (tmp)
 		wasted += alignment - tmp;
-	if (wasted) {
-		align_splitoff = drm_mm_split_at_start(node, wasted, atomic);
-		if (unlikely(align_splitoff == NULL))
-			return NULL;
+
+	if (!wasted) {
+		hole_node->hole_follows = 0;
+		list_del_init(&hole_node->hole_stack);
 	}
 
-	if (node->size == size) {
-		list_del_init(&node->free_stack);
-		node->free = 0;
+	node->start = hole_start + wasted;
+	node->size = size;
+	node->mm = mm;
+	node->allocated = 1;
+
+	INIT_LIST_HEAD(&node->hole_stack);
+	list_add(&node->node_list, &hole_node->node_list);
+
+	BUG_ON(node->start + node->size > hole_end);
+	BUG_ON(node->start + node->size > end);
+
+	if (node->start + node->size < hole_end) {
+		list_add(&node->hole_stack, &mm->hole_stack);
+		node->hole_follows = 1;
 	} else {
-		node = drm_mm_split_at_start(node, size, atomic);
+		node->hole_follows = 0;
 	}
+}
 
-	if (align_splitoff)
-		drm_mm_put_block(align_splitoff);
+struct drm_mm_node *drm_mm_get_block_range_generic(struct drm_mm_node *hole_node,
+						unsigned long size,
+						unsigned alignment,
+						unsigned long start,
+						unsigned long end,
+						int atomic)
+{
+	struct drm_mm_node *node;
+
+	node = drm_mm_kmalloc(hole_node->mm, atomic);
+	if (unlikely(node == NULL))
+		return NULL;
+
+	drm_mm_insert_helper_range(hole_node, node, size, alignment,
+				   start, end);
 
 	return node;
 }
 EXPORT_SYMBOL(drm_mm_get_block_range_generic);
 
-/*
- * Put a block. Merge with the previous and / or next block if they are free.
- * Otherwise add to the free stack.
+/**
+ * Search for free space and insert a preallocated memory node. Returns
+ * -ENOSPC if no suitable free area is available. This is for range
+ * restricted allocations. The preallocated memory node must be cleared.
  */
-
-void drm_mm_put_block(struct drm_mm_node *cur)
+int drm_mm_insert_node_in_range(struct drm_mm *mm, struct drm_mm_node *node,
+				unsigned long size, unsigned alignment,
+				unsigned long start, unsigned long end)
 {
+	struct drm_mm_node *hole_node;
 
-	struct drm_mm *mm = cur->mm;
-	struct list_head *cur_head = &cur->node_list;
-	struct list_head *root_head = &mm->node_list;
-	struct drm_mm_node *prev_node = NULL;
-	struct drm_mm_node *next_node;
+	hole_node = drm_mm_search_free_in_range(mm, size, alignment,
+						start, end, 0);
+	if (!hole_node)
+		return -ENOSPC;
 
-	int merged = 0;
+	drm_mm_insert_helper_range(hole_node, node, size, alignment,
+				   start, end);
 
-	BUG_ON(cur->scanned_block || cur->scanned_prev_free
-				  || cur->scanned_next_free);
+	return 0;
+}
+EXPORT_SYMBOL(drm_mm_insert_node_in_range);
 
-	if (cur_head->prev != root_head) {
-		prev_node =
-		    list_entry(cur_head->prev, struct drm_mm_node, node_list);
-		if (prev_node->free) {
-			prev_node->size += cur->size;
-			merged = 1;
-		}
-	}
-	if (cur_head->next != root_head) {
-		next_node =
-		    list_entry(cur_head->next, struct drm_mm_node, node_list);
-		if (next_node->free) {
-			if (merged) {
-				prev_node->size += next_node->size;
-				list_del(&next_node->node_list);
-				list_del(&next_node->free_stack);
-				spin_lock(&mm->unused_lock);
-				if (mm->num_unused < MM_UNUSED_TARGET) {
-					list_add(&next_node->free_stack,
-						 &mm->unused_nodes);
-					++mm->num_unused;
-				} else
-					kfree(next_node);
-				spin_unlock(&mm->unused_lock);
-			} else {
-				next_node->size += cur->size;
-				next_node->start = cur->start;
-				merged = 1;
-			}
-		}
-	}
-	if (!merged) {
-		cur->free = 1;
-		list_add(&cur->free_stack, &mm->free_stack);
-	} else {
-		list_del(&cur->node_list);
-		spin_lock(&mm->unused_lock);
-		if (mm->num_unused < MM_UNUSED_TARGET) {
-			list_add(&cur->free_stack, &mm->unused_nodes);
-			++mm->num_unused;
-		} else
-			kfree(cur);
-		spin_unlock(&mm->unused_lock);
-	}
+/**
+ * Remove a memory node from the allocator.
+ */
+void drm_mm_remove_node(struct drm_mm_node *node)
+{
+	struct drm_mm *mm = node->mm;
+	struct drm_mm_node *prev_node;
+
+	BUG_ON(node->scanned_block || node->scanned_prev_free
+				   || node->scanned_next_free);
+
+	prev_node =
+	    list_entry(node->node_list.prev, struct drm_mm_node, node_list);
+
+	if (node->hole_follows) {
+		BUG_ON(drm_mm_hole_node_start(node)
+				== drm_mm_hole_node_end(node));
+		list_del(&node->hole_stack);
+	} else
+		BUG_ON(drm_mm_hole_node_start(node)
+				!= drm_mm_hole_node_end(node));
+
+	if (!prev_node->hole_follows) {
+		prev_node->hole_follows = 1;
+		list_add(&prev_node->hole_stack, &mm->hole_stack);
+	} else
+		list_move(&prev_node->hole_stack, &mm->hole_stack);
+
+	list_del(&node->node_list);
+	node->allocated = 0;
 }
+EXPORT_SYMBOL(drm_mm_remove_node);
+
+/*
+ * Remove a memory node from the allocator and free the allocated struct
+ * drm_mm_node. Only to be used on a struct drm_mm_node obtained by one of the
+ * drm_mm_get_block functions.
+ */
+void drm_mm_put_block(struct drm_mm_node *node)
+{
 
+	struct drm_mm *mm = node->mm;
+
+	drm_mm_remove_node(node);
+
+	spin_lock(&mm->unused_lock);
+	if (mm->num_unused < MM_UNUSED_TARGET) {
+		list_add(&node->node_list, &mm->unused_nodes);
+		++mm->num_unused;
+	} else
+		kfree(node);
+	spin_unlock(&mm->unused_lock);
+}
 EXPORT_SYMBOL(drm_mm_put_block);
 
 static int check_free_hole(unsigned long start, unsigned long end,
@@ -319,8 +366,10 @@ struct drm_mm_node *drm_mm_search_free(const struct drm_mm *mm,
 	best = NULL;
 	best_size = ~0UL;
 
-	list_for_each_entry(entry, &mm->free_stack, free_stack) {
-		if (!check_free_hole(entry->start, entry->start + entry->size,
+	list_for_each_entry(entry, &mm->hole_stack, hole_stack) {
+		BUG_ON(!entry->hole_follows);
+		if (!check_free_hole(drm_mm_hole_node_start(entry),
+				     drm_mm_hole_node_end(entry),
 				     size, alignment))
 			continue;
 
@@ -353,12 +402,13 @@ struct drm_mm_node *drm_mm_search_free_in_range(const struct drm_mm *mm,
 	best = NULL;
 	best_size = ~0UL;
 
-	list_for_each_entry(entry, &mm->free_stack, free_stack) {
-		unsigned long adj_start = entry->start < start ?
-			start : entry->start;
-		unsigned long adj_end = entry->start + entry->size > end ?
-			end : entry->start + entry->size;
+	list_for_each_entry(entry, &mm->hole_stack, hole_stack) {
+		unsigned long adj_start = drm_mm_hole_node_start(entry) < start ?
+			start : drm_mm_hole_node_start(entry);
+		unsigned long adj_end = drm_mm_hole_node_end(entry) > end ?
+			end : drm_mm_hole_node_end(entry);
 
+		BUG_ON(!entry->hole_follows);
 		if (!check_free_hole(adj_start, adj_end, size, alignment))
 			continue;
 
@@ -376,6 +426,23 @@ struct drm_mm_node *drm_mm_search_free_in_range(const struct drm_mm *mm,
 EXPORT_SYMBOL(drm_mm_search_free_in_range);
 
 /**
+ * Moves an allocation. To be used with embedded struct drm_mm_node.
+ */
+void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new)
+{
+	list_replace(&old->node_list, &new->node_list);
+	list_replace(&old->node_list, &new->hole_stack);
+	new->hole_follows = old->hole_follows;
+	new->mm = old->mm;
+	new->start = old->start;
+	new->size = old->size;
+
+	old->allocated = 0;
+	new->allocated = 1;
+}
+EXPORT_SYMBOL(drm_mm_replace_node);
+
+/**
  * Initializa lru scanning.
  *
  * This simply sets up the scanning routines with the parameters for the desired
@@ -393,6 +460,7 @@ void drm_mm_init_scan(struct drm_mm *mm, unsigned long size,
 	mm->scan_hit_start = 0;
 	mm->scan_hit_size = 0;
 	mm->scan_check_range = 0;
+	mm->prev_scanned_node = NULL;
 }
 EXPORT_SYMBOL(drm_mm_init_scan);
 
@@ -418,6 +486,7 @@ void drm_mm_init_scan_with_range(struct drm_mm *mm, unsigned long size,
 	mm->scan_start = start;
 	mm->scan_end = end;
 	mm->scan_check_range = 1;
+	mm->prev_scanned_node = NULL;
 }
 EXPORT_SYMBOL(drm_mm_init_scan_with_range);
 
@@ -430,70 +499,42 @@ EXPORT_SYMBOL(drm_mm_init_scan_with_range);
 int drm_mm_scan_add_block(struct drm_mm_node *node)
 {
 	struct drm_mm *mm = node->mm;
-	struct list_head *prev_free, *next_free;
-	struct drm_mm_node *prev_node, *next_node;
+	struct drm_mm_node *prev_node;
+	unsigned long hole_start, hole_end;
 	unsigned long adj_start;
 	unsigned long adj_end;
 
 	mm->scanned_blocks++;
 
-	prev_free = next_free = NULL;
-
-	BUG_ON(node->free);
+	BUG_ON(node->scanned_block);
 	node->scanned_block = 1;
-	node->free = 1;
-
-	if (node->node_list.prev != &mm->node_list) {
-		prev_node = list_entry(node->node_list.prev, struct drm_mm_node,
-				       node_list);
-
-		if (prev_node->free) {
-			list_del(&prev_node->node_list);
 
-			node->start = prev_node->start;
-			node->size += prev_node->size;
+	prev_node = list_entry(node->node_list.prev, struct drm_mm_node,
+			       node_list);
 
-			prev_node->scanned_prev_free = 1;
-
-			prev_free = &prev_node->free_stack;
-		}
-	}
-
-	if (node->node_list.next != &mm->node_list) {
-		next_node = list_entry(node->node_list.next, struct drm_mm_node,
-				       node_list);
-
-		if (next_node->free) {
-			list_del(&next_node->node_list);
-
-			node->size += next_node->size;
-
-			next_node->scanned_next_free = 1;
-
-			next_free = &next_node->free_stack;
-		}
-	}
-
-	/* The free_stack list is not used for allocated objects, so these two
-	 * pointers can be abused (as long as no allocations in this memory
-	 * manager happens). */
-	node->free_stack.prev = prev_free;
-	node->free_stack.next = next_free;
+	node->scanned_preceeds_hole = prev_node->hole_follows;
+	prev_node->hole_follows = 1;
+	list_del(&node->node_list);
+	node->node_list.prev = &prev_node->node_list;
+	node->node_list.next = &mm->prev_scanned_node->node_list;
+	mm->prev_scanned_node = node;
 
+	hole_start = drm_mm_hole_node_start(prev_node);
+	hole_end = drm_mm_hole_node_end(prev_node);
 	if (mm->scan_check_range) {
-		adj_start = node->start < mm->scan_start ?
-			mm->scan_start : node->start;
-		adj_end = node->start + node->size > mm->scan_end ?
-			mm->scan_end : node->start + node->size;
+		adj_start = hole_start < mm->scan_start ?
+			mm->scan_start : hole_start;
+		adj_end = hole_end > mm->scan_end ?
+			mm->scan_end : hole_end;
 	} else {
-		adj_start = node->start;
-		adj_end = node->start + node->size;
+		adj_start = hole_start;
+		adj_end = hole_end;
 	}
 
 	if (check_free_hole(adj_start , adj_end,
 			    mm->scan_size, mm->scan_alignment)) {
-		mm->scan_hit_start = node->start;
-		mm->scan_hit_size = node->size;
+		mm->scan_hit_start = hole_start;
+		mm->scan_hit_size = hole_end;
 
 		return 1;
 	}
@@ -519,39 +560,19 @@ EXPORT_SYMBOL(drm_mm_scan_add_block);
 int drm_mm_scan_remove_block(struct drm_mm_node *node)
 {
 	struct drm_mm *mm = node->mm;
-	struct drm_mm_node *prev_node, *next_node;
+	struct drm_mm_node *prev_node;
 
 	mm->scanned_blocks--;
 
 	BUG_ON(!node->scanned_block);
 	node->scanned_block = 0;
-	node->free = 0;
-
-	prev_node = list_entry(node->free_stack.prev, struct drm_mm_node,
-			       free_stack);
-	next_node = list_entry(node->free_stack.next, struct drm_mm_node,
-			       free_stack);
 
-	if (prev_node) {
-		BUG_ON(!prev_node->scanned_prev_free);
-		prev_node->scanned_prev_free = 0;
-
-		list_add_tail(&prev_node->node_list, &node->node_list);
-
-		node->start = prev_node->start + prev_node->size;
-		node->size -= prev_node->size;
-	}
+	prev_node = list_entry(node->node_list.prev, struct drm_mm_node,
+			       node_list);
 
-	if (next_node) {
-		BUG_ON(!next_node->scanned_next_free);
-		next_node->scanned_next_free = 0;
-
-		list_add(&next_node->node_list, &node->node_list);
-
-		node->size -= next_node->size;
-	}
-
-	INIT_LIST_HEAD(&node->free_stack);
+	prev_node->hole_follows = node->scanned_preceeds_hole;
+	INIT_LIST_HEAD(&node->node_list);
+	list_add(&node->node_list, &prev_node->node_list);
 
 	/* Only need to check for containement because start&size for the
 	 * complete resulting free block (not just the desired part) is
@@ -568,7 +589,7 @@ EXPORT_SYMBOL(drm_mm_scan_remove_block);
 
 int drm_mm_clean(struct drm_mm * mm)
 {
-	struct list_head *head = &mm->node_list;
+	struct list_head *head = &mm->head_node.node_list;
 
 	return (head->next->next == head);
 }
@@ -576,38 +597,40 @@ EXPORT_SYMBOL(drm_mm_clean);
 
 int drm_mm_init(struct drm_mm * mm, unsigned long start, unsigned long size)
 {
-	INIT_LIST_HEAD(&mm->node_list);
-	INIT_LIST_HEAD(&mm->free_stack);
+	INIT_LIST_HEAD(&mm->hole_stack);
 	INIT_LIST_HEAD(&mm->unused_nodes);
 	mm->num_unused = 0;
 	mm->scanned_blocks = 0;
 	spin_lock_init(&mm->unused_lock);
 
-	return drm_mm_create_tail_node(mm, start, size, 0);
+	/* Clever trick to avoid a special case in the free hole tracking. */
+	INIT_LIST_HEAD(&mm->head_node.node_list);
+	INIT_LIST_HEAD(&mm->head_node.hole_stack);
+	mm->head_node.hole_follows = 1;
+	mm->head_node.scanned_block = 0;
+	mm->head_node.scanned_prev_free = 0;
+	mm->head_node.scanned_next_free = 0;
+	mm->head_node.mm = mm;
+	mm->head_node.start = start + size;
+	mm->head_node.size = start - mm->head_node.start;
+	list_add_tail(&mm->head_node.hole_stack, &mm->hole_stack);
+
+	return 0;
 }
 EXPORT_SYMBOL(drm_mm_init);
 
 void drm_mm_takedown(struct drm_mm * mm)
 {
-	struct list_head *bnode = mm->free_stack.next;
-	struct drm_mm_node *entry;
-	struct drm_mm_node *next;
+	struct drm_mm_node *entry, *next;
 
-	entry = list_entry(bnode, struct drm_mm_node, free_stack);
-
-	if (entry->node_list.next != &mm->node_list ||
-	    entry->free_stack.next != &mm->free_stack) {
+	if (!list_empty(&mm->head_node.node_list)) {
 		DRM_ERROR("Memory manager not clean. Delaying takedown\n");
 		return;
 	}
 
-	list_del(&entry->free_stack);
-	list_del(&entry->node_list);
-	kfree(entry);
-
 	spin_lock(&mm->unused_lock);
-	list_for_each_entry_safe(entry, next, &mm->unused_nodes, free_stack) {
-		list_del(&entry->free_stack);
+	list_for_each_entry_safe(entry, next, &mm->unused_nodes, node_list) {
+		list_del(&entry->node_list);
 		kfree(entry);
 		--mm->num_unused;
 	}
@@ -620,19 +643,37 @@ EXPORT_SYMBOL(drm_mm_takedown);
 void drm_mm_debug_table(struct drm_mm *mm, const char *prefix)
 {
 	struct drm_mm_node *entry;
-	int total_used = 0, total_free = 0, total = 0;
-
-	list_for_each_entry(entry, &mm->node_list, node_list) {
-		printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8ld: %s\n",
+	unsigned long total_used = 0, total_free = 0, total = 0;
+	unsigned long hole_start, hole_end, hole_size;
+
+	hole_start = drm_mm_hole_node_start(&mm->head_node);
+	hole_end = drm_mm_hole_node_end(&mm->head_node);
+	hole_size = hole_end - hole_start;
+	if (hole_size)
+		printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8lu: free\n",
+			prefix, hole_start, hole_end,
+			hole_size);
+	total_free += hole_size;
+
+	drm_mm_for_each_node(entry, mm) {
+		printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8lu: used\n",
 			prefix, entry->start, entry->start + entry->size,
-			entry->size, entry->free ? "free" : "used");
-		total += entry->size;
-		if (entry->free)
-			total_free += entry->size;
-		else
-			total_used += entry->size;
+			entry->size);
+		total_used += entry->size;
+
+		if (entry->hole_follows) {
+			hole_start = drm_mm_hole_node_start(entry);
+			hole_end = drm_mm_hole_node_end(entry);
+			hole_size = hole_end - hole_start;
+			printk(KERN_DEBUG "%s 0x%08lx-0x%08lx: %8lu: free\n",
+				prefix, hole_start, hole_end,
+				hole_size);
+			total_free += hole_size;
+		}
 	}
-	printk(KERN_DEBUG "%s total: %d, used %d free %d\n", prefix, total,
+	total = total_free + total_used;
+
+	printk(KERN_DEBUG "%s total: %lu, used %lu free %lu\n", prefix, total,
 		total_used, total_free);
 }
 EXPORT_SYMBOL(drm_mm_debug_table);
@@ -641,17 +682,34 @@ EXPORT_SYMBOL(drm_mm_debug_table);
 int drm_mm_dump_table(struct seq_file *m, struct drm_mm *mm)
 {
 	struct drm_mm_node *entry;
-	int total_used = 0, total_free = 0, total = 0;
-
-	list_for_each_entry(entry, &mm->node_list, node_list) {
-		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: %s\n", entry->start, entry->start + entry->size, entry->size, entry->free ? "free" : "used");
-		total += entry->size;
-		if (entry->free)
-			total_free += entry->size;
-		else
-			total_used += entry->size;
+	unsigned long total_used = 0, total_free = 0, total = 0;
+	unsigned long hole_start, hole_end, hole_size;
+
+	hole_start = drm_mm_hole_node_start(&mm->head_node);
+	hole_end = drm_mm_hole_node_end(&mm->head_node);
+	hole_size = hole_end - hole_start;
+	if (hole_size)
+		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
+				hole_start, hole_end, hole_size);
+	total_free += hole_size;
+
+	drm_mm_for_each_node(entry, mm) {
+		seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: used\n",
+				entry->start, entry->start + entry->size,
+				entry->size);
+		total_used += entry->size;
+		if (entry->hole_follows) {
+			hole_start = drm_mm_hole_node_start(&mm->head_node);
+			hole_end = drm_mm_hole_node_end(&mm->head_node);
+			hole_size = hole_end - hole_start;
+			seq_printf(m, "0x%08lx-0x%08lx: 0x%08lx: free\n",
+					hole_start, hole_end, hole_size);
+			total_free += hole_size;
+		}
 	}
-	seq_printf(m, "total: %d, used %d free %d\n", total, total_used, total_free);
+	total = total_free + total_used;
+
+	seq_printf(m, "total: %lu, used %lu free %lu\n", total, total_used, total_free);
 	return 0;
 }
 EXPORT_SYMBOL(drm_mm_dump_table);
diff --git a/drivers/gpu/drm/nouveau/nouveau_object.c b/drivers/gpu/drm/nouveau/nouveau_object.c
index 30b6544467ca..03adfe4c7665 100644
--- a/drivers/gpu/drm/nouveau/nouveau_object.c
+++ b/drivers/gpu/drm/nouveau/nouveau_object.c
@@ -909,7 +909,7 @@ nouveau_gpuobj_channel_takedown(struct nouveau_channel *chan)
 	nouveau_vm_ref(NULL, &chan->vm, chan->vm_pd);
 	nouveau_gpuobj_ref(NULL, &chan->vm_pd);
 
-	if (chan->ramin_heap.free_stack.next)
+	if (drm_mm_initialized(&chan->ramin_heap))
 		drm_mm_takedown(&chan->ramin_heap);
 	nouveau_gpuobj_ref(NULL, &chan->ramin);
 }
diff --git a/drivers/gpu/drm/nouveau/nv50_instmem.c b/drivers/gpu/drm/nouveau/nv50_instmem.c
index ea0041810ae3..300285ae8e9e 100644
--- a/drivers/gpu/drm/nouveau/nv50_instmem.c
+++ b/drivers/gpu/drm/nouveau/nv50_instmem.c
@@ -56,7 +56,7 @@ nv50_channel_del(struct nouveau_channel **pchan)
 	nouveau_gpuobj_ref(NULL, &chan->ramfc);
 	nouveau_vm_ref(NULL, &chan->vm, chan->vm_pd);
 	nouveau_gpuobj_ref(NULL, &chan->vm_pd);
-	if (chan->ramin_heap.free_stack.next)
+	if (drm_mm_initialized(&chan->ramin_heap))
 		drm_mm_takedown(&chan->ramin_heap);
 	nouveau_gpuobj_ref(NULL, &chan->ramin);
 	kfree(chan);
@@ -259,7 +259,7 @@ nv50_instmem_takedown(struct drm_device *dev)
 	nouveau_gpuobj_ref(NULL, &dev_priv->bar3_vm->pgt[0].obj[0]);
 	nouveau_vm_ref(NULL, &dev_priv->bar3_vm, NULL);
 
-	if (dev_priv->ramin_heap.free_stack.next)
+	if (drm_mm_initialized(&dev_priv->ramin_heap))
 		drm_mm_takedown(&dev_priv->ramin_heap);
 
 	dev_priv->engine.instmem.priv = NULL;
diff --git a/drivers/gpu/drm/nouveau/nvc0_instmem.c b/drivers/gpu/drm/nouveau/nvc0_instmem.c
index c09091749054..82357d2df1f4 100644
--- a/drivers/gpu/drm/nouveau/nvc0_instmem.c
+++ b/drivers/gpu/drm/nouveau/nvc0_instmem.c
@@ -67,7 +67,7 @@ nvc0_channel_del(struct nouveau_channel **pchan)
 		return;
 
 	nouveau_vm_ref(NULL, &chan->vm, NULL);
-	if (chan->ramin_heap.free_stack.next)
+	if (drm_mm_initialized(&chan->ramin_heap))
 		drm_mm_takedown(&chan->ramin_heap);
 	nouveau_gpuobj_ref(NULL, &chan->ramin);
 	kfree(chan);
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index b1537000a104..d56f08d3cbdc 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1030,7 +1030,7 @@ static int evergreen_crtc_do_set_base(struct drm_crtc *crtc,
 	 * just update base pointers
 	 */
 	obj = radeon_fb->obj;
-	rbo = obj->driver_private;
+	rbo = gem_to_radeon_bo(obj);
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
 		return r;
@@ -1145,7 +1145,7 @@ static int evergreen_crtc_do_set_base(struct drm_crtc *crtc,
 
 	if (!atomic && fb && fb != crtc->fb) {
 		radeon_fb = to_radeon_framebuffer(fb);
-		rbo = radeon_fb->obj->driver_private;
+		rbo = gem_to_radeon_bo(radeon_fb->obj);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r != 0))
 			return r;
@@ -1191,7 +1191,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	}
 
 	obj = radeon_fb->obj;
-	rbo = obj->driver_private;
+	rbo = gem_to_radeon_bo(obj);
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
 		return r;
@@ -1308,7 +1308,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 
 	if (!atomic && fb && fb != crtc->fb) {
 		radeon_fb = to_radeon_framebuffer(fb);
-		rbo = radeon_fb->obj->driver_private;
+		rbo = gem_to_radeon_bo(radeon_fb->obj);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r != 0))
 			return r;
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index a1ba4b3053d0..2ed930e02f3a 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -572,7 +572,7 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	obj_size += evergreen_ps_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
-	r = radeon_bo_create(rdev, NULL, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
+	r = radeon_bo_create(rdev, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				&rdev->r600_blit.shader_obj);
 	if (r) {
 		DRM_ERROR("evergreen failed to allocate shader\n");
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 650672a0f5ad..be780a6b9b1d 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2728,7 +2728,7 @@ static int r600_ih_ring_alloc(struct radeon_device *rdev)
 
 	/* Allocate ring buffer */
 	if (rdev->ih.ring_obj == NULL) {
-		r = radeon_bo_create(rdev, NULL, rdev->ih.ring_size,
+		r = radeon_bo_create(rdev, rdev->ih.ring_size,
 				     PAGE_SIZE, true,
 				     RADEON_GEM_DOMAIN_GTT,
 				     &rdev->ih.ring_obj);
diff --git a/drivers/gpu/drm/radeon/r600_audio.c b/drivers/gpu/drm/radeon/r600_audio.c
index b5443fe1c1d1..846fae576399 100644
--- a/drivers/gpu/drm/radeon/r600_audio.c
+++ b/drivers/gpu/drm/radeon/r600_audio.c
@@ -26,6 +26,7 @@
 #include "drmP.h"
 #include "radeon.h"
 #include "radeon_reg.h"
+#include "radeon_asic.h"
 #include "atom.h"
 
 #define AUDIO_TIMER_INTERVALL 100 /* 1/10 sekund should be enough */
diff --git a/drivers/gpu/drm/radeon/r600_blit_kms.c b/drivers/gpu/drm/radeon/r600_blit_kms.c
index 86e5aa07f0db..16e211a614d7 100644
--- a/drivers/gpu/drm/radeon/r600_blit_kms.c
+++ b/drivers/gpu/drm/radeon/r600_blit_kms.c
@@ -501,7 +501,7 @@ int r600_blit_init(struct radeon_device *rdev)
 	obj_size += r6xx_ps_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
-	r = radeon_bo_create(rdev, NULL, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
+	r = radeon_bo_create(rdev, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				&rdev->r600_blit.shader_obj);
 	if (r) {
 		DRM_ERROR("r600 failed to allocate shader\n");
diff --git a/drivers/gpu/drm/radeon/r600_hdmi.c b/drivers/gpu/drm/radeon/r600_hdmi.c
index e6a58ed48dcf..50db6d62eec2 100644
--- a/drivers/gpu/drm/radeon/r600_hdmi.c
+++ b/drivers/gpu/drm/radeon/r600_hdmi.c
@@ -26,6 +26,7 @@
 #include "drmP.h"
 #include "radeon_drm.h"
 #include "radeon.h"
+#include "radeon_asic.h"
 #include "atom.h"
 
 /*
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 82aa59941aa1..55fefe763965 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -258,8 +258,9 @@ struct radeon_bo {
 	int				surface_reg;
 	/* Constant after initialization */
 	struct radeon_device		*rdev;
-	struct drm_gem_object		*gobj;
+	struct drm_gem_object		gem_base;
 };
+#define gem_to_radeon_bo(gobj) container_of((gobj), struct radeon_bo, gem_base)
 
 struct radeon_bo_list {
 	struct ttm_validate_buffer tv;
@@ -1197,19 +1198,6 @@ int radeon_device_init(struct radeon_device *rdev,
 void radeon_device_fini(struct radeon_device *rdev);
 int radeon_gpu_wait_for_idle(struct radeon_device *rdev);
 
-/* r600 blit */
-int r600_blit_prepare_copy(struct radeon_device *rdev, int size_bytes);
-void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence);
-void r600_kms_blit_copy(struct radeon_device *rdev,
-			u64 src_gpu_addr, u64 dst_gpu_addr,
-			int size_bytes);
-/* evergreen blit */
-int evergreen_blit_prepare_copy(struct radeon_device *rdev, int size_bytes);
-void evergreen_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence);
-void evergreen_kms_blit_copy(struct radeon_device *rdev,
-			     u64 src_gpu_addr, u64 dst_gpu_addr,
-			     int size_bytes);
-
 static inline uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg)
 {
 	if (reg < rdev->rmmio_size)
@@ -1460,59 +1448,12 @@ extern void radeon_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc
 extern int radeon_resume_kms(struct drm_device *dev);
 extern int radeon_suspend_kms(struct drm_device *dev, pm_message_t state);
 
-/* r600, rv610, rv630, rv620, rv635, rv670, rs780, rs880 */
-extern bool r600_card_posted(struct radeon_device *rdev);
-extern void r600_cp_stop(struct radeon_device *rdev);
-extern int r600_cp_start(struct radeon_device *rdev);
-extern void r600_ring_init(struct radeon_device *rdev, unsigned ring_size);
-extern int r600_cp_resume(struct radeon_device *rdev);
-extern void r600_cp_fini(struct radeon_device *rdev);
-extern int r600_count_pipe_bits(uint32_t val);
-extern int r600_mc_wait_for_idle(struct radeon_device *rdev);
-extern int r600_pcie_gart_init(struct radeon_device *rdev);
-extern void r600_pcie_gart_tlb_flush(struct radeon_device *rdev);
-extern int r600_ib_test(struct radeon_device *rdev);
-extern int r600_ring_test(struct radeon_device *rdev);
-extern void r600_scratch_init(struct radeon_device *rdev);
-extern int r600_blit_init(struct radeon_device *rdev);
-extern void r600_blit_fini(struct radeon_device *rdev);
-extern int r600_init_microcode(struct radeon_device *rdev);
-extern int r600_asic_reset(struct radeon_device *rdev);
-/* r600 irq */
-extern int r600_irq_init(struct radeon_device *rdev);
-extern void r600_irq_fini(struct radeon_device *rdev);
-extern void r600_ih_ring_init(struct radeon_device *rdev, unsigned ring_size);
-extern int r600_irq_set(struct radeon_device *rdev);
-extern void r600_irq_suspend(struct radeon_device *rdev);
-extern void r600_disable_interrupts(struct radeon_device *rdev);
-extern void r600_rlc_stop(struct radeon_device *rdev);
-/* r600 audio */
-extern int r600_audio_init(struct radeon_device *rdev);
-extern int r600_audio_tmds_index(struct drm_encoder *encoder);
-extern void r600_audio_set_clock(struct drm_encoder *encoder, int clock);
-extern int r600_audio_channels(struct radeon_device *rdev);
-extern int r600_audio_bits_per_sample(struct radeon_device *rdev);
-extern int r600_audio_rate(struct radeon_device *rdev);
-extern uint8_t r600_audio_status_bits(struct radeon_device *rdev);
-extern uint8_t r600_audio_category_code(struct radeon_device *rdev);
-extern void r600_audio_schedule_polling(struct radeon_device *rdev);
-extern void r600_audio_enable_polling(struct drm_encoder *encoder);
-extern void r600_audio_disable_polling(struct drm_encoder *encoder);
-extern void r600_audio_fini(struct radeon_device *rdev);
-extern void r600_hdmi_init(struct drm_encoder *encoder);
+/*
+ * r600 functions used by radeon_encoder.c
+ */
 extern void r600_hdmi_enable(struct drm_encoder *encoder);
 extern void r600_hdmi_disable(struct drm_encoder *encoder);
 extern void r600_hdmi_setmode(struct drm_encoder *encoder, struct drm_display_mode *mode);
-extern int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder);
-extern void r600_hdmi_update_audio_settings(struct drm_encoder *encoder);
-
-extern void r700_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
-extern void r700_cp_stop(struct radeon_device *rdev);
-extern void r700_cp_fini(struct radeon_device *rdev);
-extern void evergreen_disable_interrupt_state(struct radeon_device *rdev);
-extern int evergreen_irq_set(struct radeon_device *rdev);
-extern int evergreen_blit_init(struct radeon_device *rdev);
-extern void evergreen_blit_fini(struct radeon_device *rdev);
 
 extern int ni_init_microcode(struct radeon_device *rdev);
 extern int btc_mc_load_microcode(struct radeon_device *rdev);
@@ -1524,14 +1465,6 @@ extern int radeon_acpi_init(struct radeon_device *rdev);
 static inline int radeon_acpi_init(struct radeon_device *rdev) { return 0; } 
 #endif 
 
-/* evergreen */
-struct evergreen_mc_save {
-	u32 vga_control[6];
-	u32 vga_render_control;
-	u32 vga_hdp_control;
-	u32 crtc_control[6];
-};
-
 #include "radeon_object.h"
 
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index c59bd98a2029..1c7317e3aa8c 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -57,8 +57,6 @@ int r100_init(struct radeon_device *rdev);
 void r100_fini(struct radeon_device *rdev);
 int r100_suspend(struct radeon_device *rdev);
 int r100_resume(struct radeon_device *rdev);
-uint32_t r100_mm_rreg(struct radeon_device *rdev, uint32_t reg);
-void r100_mm_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void r100_vga_set_state(struct radeon_device *rdev, bool state);
 bool r100_gpu_is_lockup(struct radeon_device *rdev);
 int r100_asic_reset(struct radeon_device *rdev);
@@ -164,8 +162,6 @@ extern void r300_fence_ring_emit(struct radeon_device *rdev,
 extern int r300_cs_parse(struct radeon_cs_parser *p);
 extern void rv370_pcie_gart_tlb_flush(struct radeon_device *rdev);
 extern int rv370_pcie_gart_set_page(struct radeon_device *rdev, int i, uint64_t addr);
-extern uint32_t rv370_pcie_rreg(struct radeon_device *rdev, uint32_t reg);
-extern void rv370_pcie_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 extern void rv370_set_pcie_lanes(struct radeon_device *rdev, int lanes);
 extern int rv370_get_pcie_lanes(struct radeon_device *rdev);
 extern void r300_set_reg_safe(struct radeon_device *rdev);
@@ -208,7 +204,6 @@ void rs400_gart_adjust_size(struct radeon_device *rdev);
 void rs400_gart_disable(struct radeon_device *rdev);
 void rs400_gart_fini(struct radeon_device *rdev);
 
-
 /*
  * rs600.
  */
@@ -270,8 +265,6 @@ void rv515_fini(struct radeon_device *rdev);
 uint32_t rv515_mc_rreg(struct radeon_device *rdev, uint32_t reg);
 void rv515_mc_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void rv515_ring_start(struct radeon_device *rdev);
-uint32_t rv515_pcie_rreg(struct radeon_device *rdev, uint32_t reg);
-void rv515_pcie_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 void rv515_bandwidth_update(struct radeon_device *rdev);
 int rv515_resume(struct radeon_device *rdev);
 int rv515_suspend(struct radeon_device *rdev);
@@ -307,14 +300,13 @@ void r600_pciep_wreg(struct radeon_device *rdev, uint32_t reg, uint32_t v);
 int r600_cs_parse(struct radeon_cs_parser *p);
 void r600_fence_ring_emit(struct radeon_device *rdev,
 			  struct radeon_fence *fence);
-int r600_irq_process(struct radeon_device *rdev);
-int r600_irq_set(struct radeon_device *rdev);
 bool r600_gpu_is_lockup(struct radeon_device *rdev);
 int r600_asic_reset(struct radeon_device *rdev);
 int r600_set_surface_reg(struct radeon_device *rdev, int reg,
 			 uint32_t tiling_flags, uint32_t pitch,
 			 uint32_t offset, uint32_t obj_size);
 void r600_clear_surface_reg(struct radeon_device *rdev, int reg);
+int r600_ib_test(struct radeon_device *rdev);
 void r600_ring_ib_execute(struct radeon_device *rdev, struct radeon_ib *ib);
 int r600_ring_test(struct radeon_device *rdev);
 int r600_copy_blit(struct radeon_device *rdev,
@@ -333,6 +325,50 @@ extern void rs780_pm_init_profile(struct radeon_device *rdev);
 extern void r600_pm_get_dynpm_state(struct radeon_device *rdev);
 extern void r600_set_pcie_lanes(struct radeon_device *rdev, int lanes);
 extern int r600_get_pcie_lanes(struct radeon_device *rdev);
+bool r600_card_posted(struct radeon_device *rdev);
+void r600_cp_stop(struct radeon_device *rdev);
+int r600_cp_start(struct radeon_device *rdev);
+void r600_ring_init(struct radeon_device *rdev, unsigned ring_size);
+int r600_cp_resume(struct radeon_device *rdev);
+void r600_cp_fini(struct radeon_device *rdev);
+int r600_count_pipe_bits(uint32_t val);
+int r600_mc_wait_for_idle(struct radeon_device *rdev);
+int r600_pcie_gart_init(struct radeon_device *rdev);
+void r600_scratch_init(struct radeon_device *rdev);
+int r600_blit_init(struct radeon_device *rdev);
+void r600_blit_fini(struct radeon_device *rdev);
+int r600_init_microcode(struct radeon_device *rdev);
+/* r600 irq */
+int r600_irq_process(struct radeon_device *rdev);
+int r600_irq_init(struct radeon_device *rdev);
+void r600_irq_fini(struct radeon_device *rdev);
+void r600_ih_ring_init(struct radeon_device *rdev, unsigned ring_size);
+int r600_irq_set(struct radeon_device *rdev);
+void r600_irq_suspend(struct radeon_device *rdev);
+void r600_disable_interrupts(struct radeon_device *rdev);
+void r600_rlc_stop(struct radeon_device *rdev);
+/* r600 audio */
+int r600_audio_init(struct radeon_device *rdev);
+int r600_audio_tmds_index(struct drm_encoder *encoder);
+void r600_audio_set_clock(struct drm_encoder *encoder, int clock);
+int r600_audio_channels(struct radeon_device *rdev);
+int r600_audio_bits_per_sample(struct radeon_device *rdev);
+int r600_audio_rate(struct radeon_device *rdev);
+uint8_t r600_audio_status_bits(struct radeon_device *rdev);
+uint8_t r600_audio_category_code(struct radeon_device *rdev);
+void r600_audio_schedule_polling(struct radeon_device *rdev);
+void r600_audio_enable_polling(struct drm_encoder *encoder);
+void r600_audio_disable_polling(struct drm_encoder *encoder);
+void r600_audio_fini(struct radeon_device *rdev);
+void r600_hdmi_init(struct drm_encoder *encoder);
+int r600_hdmi_buffer_status_changed(struct drm_encoder *encoder);
+void r600_hdmi_update_audio_settings(struct drm_encoder *encoder);
+/* r600 blit */
+int r600_blit_prepare_copy(struct radeon_device *rdev, int size_bytes);
+void r600_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence);
+void r600_kms_blit_copy(struct radeon_device *rdev,
+			u64 src_gpu_addr, u64 dst_gpu_addr,
+			int size_bytes);
 
 /*
  * rv770,rv730,rv710,rv740
@@ -341,12 +377,21 @@ int rv770_init(struct radeon_device *rdev);
 void rv770_fini(struct radeon_device *rdev);
 int rv770_suspend(struct radeon_device *rdev);
 int rv770_resume(struct radeon_device *rdev);
-extern void rv770_pm_misc(struct radeon_device *rdev);
-extern u32 rv770_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
+void rv770_pm_misc(struct radeon_device *rdev);
+u32 rv770_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
+void r700_vram_gtt_location(struct radeon_device *rdev, struct radeon_mc *mc);
+void r700_cp_stop(struct radeon_device *rdev);
+void r700_cp_fini(struct radeon_device *rdev);
 
 /*
  * evergreen
  */
+struct evergreen_mc_save {
+	u32 vga_control[6];
+	u32 vga_render_control;
+	u32 vga_hdp_control;
+	u32 crtc_control[6];
+};
 void evergreen_pcie_gart_tlb_flush(struct radeon_device *rdev);
 int evergreen_init(struct radeon_device *rdev);
 void evergreen_fini(struct radeon_device *rdev);
@@ -374,5 +419,15 @@ extern void evergreen_pm_finish(struct radeon_device *rdev);
 extern void evergreen_pre_page_flip(struct radeon_device *rdev, int crtc);
 extern u32 evergreen_page_flip(struct radeon_device *rdev, int crtc, u64 crtc_base);
 extern void evergreen_post_page_flip(struct radeon_device *rdev, int crtc);
+void evergreen_disable_interrupt_state(struct radeon_device *rdev);
+int evergreen_blit_init(struct radeon_device *rdev);
+void evergreen_blit_fini(struct radeon_device *rdev);
+/* evergreen blit */
+int evergreen_blit_prepare_copy(struct radeon_device *rdev, int size_bytes);
+void evergreen_blit_done_copy(struct radeon_device *rdev, struct radeon_fence *fence);
+void evergreen_kms_blit_copy(struct radeon_device *rdev,
+			     u64 src_gpu_addr, u64 dst_gpu_addr,
+			     int size_bytes);
+
 
 #endif
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index c558685cc637..10191d9372d8 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -41,7 +41,7 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
 
 	size = bsize;
 	n = 1024;
-	r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, sdomain, &sobj);
+	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, sdomain, &sobj);
 	if (r) {
 		goto out_cleanup;
 	}
@@ -53,7 +53,7 @@ void radeon_benchmark_move(struct radeon_device *rdev, unsigned bsize,
 	if (r) {
 		goto out_cleanup;
 	}
-	r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, ddomain, &dobj);
+	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, ddomain, &dobj);
 	if (r) {
 		goto out_cleanup;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 35b5eb8fbe2a..8c1916941871 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -75,7 +75,7 @@ int radeon_cs_parser_relocs(struct radeon_cs_parser *p)
 				return -ENOENT;
 			}
 			p->relocs_ptr[i] = &p->relocs[i];
-			p->relocs[i].robj = p->relocs[i].gobj->driver_private;
+			p->relocs[i].robj = gem_to_radeon_bo(p->relocs[i].gobj);
 			p->relocs[i].lobj.bo = p->relocs[i].robj;
 			p->relocs[i].lobj.wdomain = r->write_domain;
 			p->relocs[i].lobj.rdomain = r->read_domains;
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 0d478932b1a9..7c0a3f26ab5e 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -184,7 +184,7 @@ int radeon_wb_init(struct radeon_device *rdev)
 	int r;
 
 	if (rdev->wb.wb_obj == NULL) {
-		r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE, PAGE_SIZE, true,
+		r = radeon_bo_create(rdev, RADEON_GPU_PAGE_SIZE, PAGE_SIZE, true,
 				RADEON_GEM_DOMAIN_GTT, &rdev->wb.wb_obj);
 		if (r) {
 			dev_warn(rdev->dev, "(%d) create WB bo failed\n", r);
@@ -860,7 +860,7 @@ int radeon_suspend_kms(struct drm_device *dev, pm_message_t state)
 		if (rfb == NULL || rfb->obj == NULL) {
 			continue;
 		}
-		robj = rfb->obj->driver_private;
+		robj = gem_to_radeon_bo(rfb->obj);
 		/* don't unpin kernel fb objects */
 		if (!radeon_fbdev_robj_is_fb(rdev, robj)) {
 			r = radeon_bo_reserve(robj, false);
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 2eff98cfd728..4409975a363c 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -371,7 +371,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	new_radeon_fb = to_radeon_framebuffer(fb);
 	/* schedule unpin of the old buffer */
 	obj = old_radeon_fb->obj;
-	rbo = obj->driver_private;
+	rbo = gem_to_radeon_bo(obj);
 	work->old_rbo = rbo;
 	INIT_WORK(&work->work, radeon_unpin_work_func);
 
@@ -391,7 +391,7 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 
 	/* pin the new buffer */
 	obj = new_radeon_fb->obj;
-	rbo = obj->driver_private;
+	rbo = gem_to_radeon_bo(obj);
 
 	DRM_DEBUG_DRIVER("flip-ioctl() cur_fbo = %p, cur_bbo = %p\n",
 			 work->old_rbo, rbo);
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index cb968f997ce7..28431e78ab56 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -90,7 +90,7 @@ int radeon_align_pitch(struct radeon_device *rdev, int width, int bpp, bool tile
 
 static void radeonfb_destroy_pinned_object(struct drm_gem_object *gobj)
 {
-	struct radeon_bo *rbo = gobj->driver_private;
+	struct radeon_bo *rbo = gem_to_radeon_bo(gobj);
 	int ret;
 
 	ret = radeon_bo_reserve(rbo, false);
@@ -128,7 +128,7 @@ static int radeonfb_create_pinned_object(struct radeon_fbdev *rfbdev,
 		       aligned_size);
 		return -ENOMEM;
 	}
-	rbo = gobj->driver_private;
+	rbo = gem_to_radeon_bo(gobj);
 
 	if (fb_tiled)
 		tiling_flags = RADEON_TILING_MACRO;
@@ -202,7 +202,7 @@ static int radeonfb_create(struct radeon_fbdev *rfbdev,
 	mode_cmd.depth = sizes->surface_depth;
 
 	ret = radeonfb_create_pinned_object(rfbdev, &mode_cmd, &gobj);
-	rbo = gobj->driver_private;
+	rbo = gem_to_radeon_bo(gobj);
 
 	/* okay we have an object now allocate the framebuffer */
 	info = framebuffer_alloc(0, device);
@@ -403,14 +403,14 @@ int radeon_fbdev_total_size(struct radeon_device *rdev)
 	struct radeon_bo *robj;
 	int size = 0;
 
-	robj = rdev->mode_info.rfbdev->rfb.obj->driver_private;
+	robj = gem_to_radeon_bo(rdev->mode_info.rfbdev->rfb.obj);
 	size += radeon_bo_size(robj);
 	return size;
 }
 
 bool radeon_fbdev_robj_is_fb(struct radeon_device *rdev, struct radeon_bo *robj)
 {
-	if (robj == rdev->mode_info.rfbdev->rfb.obj->driver_private)
+	if (robj == gem_to_radeon_bo(rdev->mode_info.rfbdev->rfb.obj))
 		return true;
 	return false;
 }
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index a6b0fed7bae9..f0534ef2f331 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -78,7 +78,7 @@ int radeon_gart_table_vram_alloc(struct radeon_device *rdev)
 	int r;
 
 	if (rdev->gart.table.vram.robj == NULL) {
-		r = radeon_bo_create(rdev, NULL, rdev->gart.table_size,
+		r = radeon_bo_create(rdev, rdev->gart.table_size,
 				     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				     &rdev->gart.table.vram.robj);
 		if (r) {
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index ede5dccdf79f..a419b67d8401 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -32,21 +32,18 @@
 
 int radeon_gem_object_init(struct drm_gem_object *obj)
 {
-	/* we do nothings here */
+	BUG();
+
 	return 0;
 }
 
 void radeon_gem_object_free(struct drm_gem_object *gobj)
 {
-	struct radeon_bo *robj = gobj->driver_private;
+	struct radeon_bo *robj = gem_to_radeon_bo(gobj);
 
-	gobj->driver_private = NULL;
 	if (robj) {
 		radeon_bo_unref(&robj);
 	}
-
-	drm_gem_object_release(gobj);
-	kfree(gobj);
 }
 
 int radeon_gem_object_create(struct radeon_device *rdev, int size,
@@ -54,36 +51,34 @@ int radeon_gem_object_create(struct radeon_device *rdev, int size,
 				bool discardable, bool kernel,
 				struct drm_gem_object **obj)
 {
-	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
 	int r;
 
 	*obj = NULL;
-	gobj = drm_gem_object_alloc(rdev->ddev, size);
-	if (!gobj) {
-		return -ENOMEM;
-	}
 	/* At least align on page size */
 	if (alignment < PAGE_SIZE) {
 		alignment = PAGE_SIZE;
 	}
-	r = radeon_bo_create(rdev, gobj, size, alignment, kernel, initial_domain, &robj);
+	r = radeon_bo_create(rdev, size, alignment, kernel, initial_domain, &robj);
 	if (r) {
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("Failed to allocate GEM object (%d, %d, %u, %d)\n",
 				  size, initial_domain, alignment, r);
-		drm_gem_object_unreference_unlocked(gobj);
 		return r;
 	}
-	gobj->driver_private = robj;
-	*obj = gobj;
+	*obj = &robj->gem_base;
+
+	mutex_lock(&rdev->gem.mutex);
+	list_add_tail(&robj->list, &rdev->gem.objects);
+	mutex_unlock(&rdev->gem.mutex);
+
 	return 0;
 }
 
 int radeon_gem_object_pin(struct drm_gem_object *obj, uint32_t pin_domain,
 			  uint64_t *gpu_addr)
 {
-	struct radeon_bo *robj = obj->driver_private;
+	struct radeon_bo *robj = gem_to_radeon_bo(obj);
 	int r;
 
 	r = radeon_bo_reserve(robj, false);
@@ -96,7 +91,7 @@ int radeon_gem_object_pin(struct drm_gem_object *obj, uint32_t pin_domain,
 
 void radeon_gem_object_unpin(struct drm_gem_object *obj)
 {
-	struct radeon_bo *robj = obj->driver_private;
+	struct radeon_bo *robj = gem_to_radeon_bo(obj);
 	int r;
 
 	r = radeon_bo_reserve(robj, false);
@@ -114,7 +109,7 @@ int radeon_gem_set_domain(struct drm_gem_object *gobj,
 	int r;
 
 	/* FIXME: reeimplement */
-	robj = gobj->driver_private;
+	robj = gem_to_radeon_bo(gobj);
 	/* work out where to validate the buffer to */
 	domain = wdomain;
 	if (!domain) {
@@ -228,7 +223,7 @@ int radeon_gem_set_domain_ioctl(struct drm_device *dev, void *data,
 	if (gobj == NULL) {
 		return -ENOENT;
 	}
-	robj = gobj->driver_private;
+	robj = gem_to_radeon_bo(gobj);
 
 	r = radeon_gem_set_domain(gobj, args->read_domains, args->write_domain);
 
@@ -247,7 +242,7 @@ int radeon_mode_dumb_mmap(struct drm_file *filp,
 	if (gobj == NULL) {
 		return -ENOENT;
 	}
-	robj = gobj->driver_private;
+	robj = gem_to_radeon_bo(gobj);
 	*offset_p = radeon_bo_mmap_offset(robj);
 	drm_gem_object_unreference_unlocked(gobj);
 	return 0;
@@ -274,7 +269,7 @@ int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 	if (gobj == NULL) {
 		return -ENOENT;
 	}
-	robj = gobj->driver_private;
+	robj = gem_to_radeon_bo(gobj);
 	r = radeon_bo_wait(robj, &cur_placement, true);
 	switch (cur_placement) {
 	case TTM_PL_VRAM:
@@ -304,7 +299,7 @@ int radeon_gem_wait_idle_ioctl(struct drm_device *dev, void *data,
 	if (gobj == NULL) {
 		return -ENOENT;
 	}
-	robj = gobj->driver_private;
+	robj = gem_to_radeon_bo(gobj);
 	r = radeon_bo_wait(robj, NULL, false);
 	/* callback hw specific functions if any */
 	if (robj->rdev->asic->ioctl_wait_idle)
@@ -325,7 +320,7 @@ int radeon_gem_set_tiling_ioctl(struct drm_device *dev, void *data,
 	gobj = drm_gem_object_lookup(dev, filp, args->handle);
 	if (gobj == NULL)
 		return -ENOENT;
-	robj = gobj->driver_private;
+	robj = gem_to_radeon_bo(gobj);
 	r = radeon_bo_set_tiling_flags(robj, args->tiling_flags, args->pitch);
 	drm_gem_object_unreference_unlocked(gobj);
 	return r;
@@ -343,7 +338,7 @@ int radeon_gem_get_tiling_ioctl(struct drm_device *dev, void *data,
 	gobj = drm_gem_object_lookup(dev, filp, args->handle);
 	if (gobj == NULL)
 		return -ENOENT;
-	rbo = gobj->driver_private;
+	rbo = gem_to_radeon_bo(gobj);
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
 		goto out;
diff --git a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
index cf0638c3b7c7..9ae599eb2e6d 100644
--- a/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
+++ b/drivers/gpu/drm/radeon/radeon_legacy_crtc.c
@@ -415,7 +415,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 
 	/* Pin framebuffer & get tilling informations */
 	obj = radeon_fb->obj;
-	rbo = obj->driver_private;
+	rbo = gem_to_radeon_bo(obj);
 	r = radeon_bo_reserve(rbo, false);
 	if (unlikely(r != 0))
 		return r;
@@ -520,7 +520,7 @@ int radeon_crtc_do_set_base(struct drm_crtc *crtc,
 
 	if (!atomic && fb && fb != crtc->fb) {
 		radeon_fb = to_radeon_framebuffer(fb);
-		rbo = radeon_fb->obj->driver_private;
+		rbo = gem_to_radeon_bo(radeon_fb->obj);
 		r = radeon_bo_reserve(rbo, false);
 		if (unlikely(r != 0))
 			return r;
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 7d6b8e88f746..8758d02cca1a 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -55,6 +55,7 @@ static void radeon_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	list_del_init(&bo->list);
 	mutex_unlock(&bo->rdev->gem.mutex);
 	radeon_bo_clear_surface_reg(bo);
+	drm_gem_object_release(&bo->gem_base);
 	kfree(bo);
 }
 
@@ -86,7 +87,7 @@ void radeon_ttm_placement_from_domain(struct radeon_bo *rbo, u32 domain)
 	rbo->placement.num_busy_placement = c;
 }
 
-int radeon_bo_create(struct radeon_device *rdev, struct drm_gem_object *gobj,
+int radeon_bo_create(struct radeon_device *rdev,
 		     unsigned long size, int byte_align, bool kernel, u32 domain,
 		     struct radeon_bo **bo_ptr)
 {
@@ -96,6 +97,8 @@ int radeon_bo_create(struct radeon_device *rdev, struct drm_gem_object *gobj,
 	unsigned long max_size = 0;
 	int r;
 
+	size = ALIGN(size, PAGE_SIZE);
+
 	if (unlikely(rdev->mman.bdev.dev_mapping == NULL)) {
 		rdev->mman.bdev.dev_mapping = rdev->ddev->dev_mapping;
 	}
@@ -118,8 +121,13 @@ retry:
 	bo = kzalloc(sizeof(struct radeon_bo), GFP_KERNEL);
 	if (bo == NULL)
 		return -ENOMEM;
+	r = drm_gem_object_init(rdev->ddev, &bo->gem_base, size);
+	if (unlikely(r)) {
+		kfree(bo);
+		return r;
+	}
 	bo->rdev = rdev;
-	bo->gobj = gobj;
+	bo->gem_base.driver_private = NULL;
 	bo->surface_reg = -1;
 	INIT_LIST_HEAD(&bo->list);
 	radeon_ttm_placement_from_domain(bo, domain);
@@ -142,12 +150,9 @@ retry:
 		return r;
 	}
 	*bo_ptr = bo;
-	if (gobj) {
-		mutex_lock(&bo->rdev->gem.mutex);
-		list_add_tail(&bo->list, &rdev->gem.objects);
-		mutex_unlock(&bo->rdev->gem.mutex);
-	}
+
 	trace_radeon_bo_create(bo);
+
 	return 0;
 }
 
@@ -260,7 +265,6 @@ int radeon_bo_evict_vram(struct radeon_device *rdev)
 void radeon_bo_force_delete(struct radeon_device *rdev)
 {
 	struct radeon_bo *bo, *n;
-	struct drm_gem_object *gobj;
 
 	if (list_empty(&rdev->gem.objects)) {
 		return;
@@ -268,16 +272,14 @@ void radeon_bo_force_delete(struct radeon_device *rdev)
 	dev_err(rdev->dev, "Userspace still has active objects !\n");
 	list_for_each_entry_safe(bo, n, &rdev->gem.objects, list) {
 		mutex_lock(&rdev->ddev->struct_mutex);
-		gobj = bo->gobj;
 		dev_err(rdev->dev, "%p %p %lu %lu force free\n",
-			gobj, bo, (unsigned long)gobj->size,
-			*((unsigned long *)&gobj->refcount));
+			&bo->gem_base, bo, (unsigned long)bo->gem_base.size,
+			*((unsigned long *)&bo->gem_base.refcount));
 		mutex_lock(&bo->rdev->gem.mutex);
 		list_del_init(&bo->list);
 		mutex_unlock(&bo->rdev->gem.mutex);
 		radeon_bo_unref(&bo);
-		gobj->driver_private = NULL;
-		drm_gem_object_unreference(gobj);
+		drm_gem_object_unreference(&bo->gem_base);
 		mutex_unlock(&rdev->ddev->struct_mutex);
 	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_object.h b/drivers/gpu/drm/radeon/radeon_object.h
index 22d4c237dea5..7f8e778dba46 100644
--- a/drivers/gpu/drm/radeon/radeon_object.h
+++ b/drivers/gpu/drm/radeon/radeon_object.h
@@ -137,10 +137,9 @@ static inline int radeon_bo_wait(struct radeon_bo *bo, u32 *mem_type,
 }
 
 extern int radeon_bo_create(struct radeon_device *rdev,
-			    struct drm_gem_object *gobj, unsigned long size,
-			    int byte_align,
-			    bool kernel, u32 domain,
-			    struct radeon_bo **bo_ptr);
+				unsigned long size, int byte_align,
+				bool kernel, u32 domain,
+				struct radeon_bo **bo_ptr);
 extern int radeon_bo_kmap(struct radeon_bo *bo, void **ptr);
 extern void radeon_bo_kunmap(struct radeon_bo *bo);
 extern void radeon_bo_unref(struct radeon_bo **bo);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index 06e79822a2bf..992d99d13fc5 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -175,7 +175,7 @@ int radeon_ib_pool_init(struct radeon_device *rdev)
 		return 0;
 	INIT_LIST_HEAD(&rdev->ib_pool.bogus_ib);
 	/* Allocate 1M object buffer */
-	r = radeon_bo_create(rdev, NULL,  RADEON_IB_POOL_SIZE*64*1024,
+	r = radeon_bo_create(rdev, RADEON_IB_POOL_SIZE*64*1024,
 			     PAGE_SIZE, true, RADEON_GEM_DOMAIN_GTT,
 			     &rdev->ib_pool.robj);
 	if (r) {
@@ -332,7 +332,7 @@ int radeon_ring_init(struct radeon_device *rdev, unsigned ring_size)
 	rdev->cp.ring_size = ring_size;
 	/* Allocate ring buffer */
 	if (rdev->cp.ring_obj == NULL) {
-		r = radeon_bo_create(rdev, NULL, rdev->cp.ring_size, PAGE_SIZE, true,
+		r = radeon_bo_create(rdev, rdev->cp.ring_size, PAGE_SIZE, true,
 					RADEON_GEM_DOMAIN_GTT,
 					&rdev->cp.ring_obj);
 		if (r) {
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 5b44f652145c..dee4a0c1b4b2 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -52,7 +52,7 @@ void radeon_test_moves(struct radeon_device *rdev)
 		goto out_cleanup;
 	}
 
-	r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
+	r = radeon_bo_create(rdev, size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				&vram_obj);
 	if (r) {
 		DRM_ERROR("Failed to create VRAM object\n");
@@ -71,7 +71,7 @@ void radeon_test_moves(struct radeon_device *rdev)
 		void **gtt_start, **gtt_end;
 		void **vram_start, **vram_end;
 
-		r = radeon_bo_create(rdev, NULL, size, PAGE_SIZE, true,
+		r = radeon_bo_create(rdev, size, PAGE_SIZE, true,
 					 RADEON_GEM_DOMAIN_GTT, gtt_obj + i);
 		if (r) {
 			DRM_ERROR("Failed to create GTT object %d\n", i);
diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index c345e899e881..177adc884b74 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -530,7 +530,7 @@ int radeon_ttm_init(struct radeon_device *rdev)
 		DRM_ERROR("Failed initializing VRAM heap.\n");
 		return r;
 	}
-	r = radeon_bo_create(rdev, NULL, 256 * 1024, PAGE_SIZE, true,
+	r = radeon_bo_create(rdev, 256 * 1024, PAGE_SIZE, true,
 				RADEON_GEM_DOMAIN_VRAM,
 				&rdev->stollen_vga_memory);
 	if (r) {
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 2211a323db41..3a95999d2fef 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -999,7 +999,7 @@ static int rv770_vram_scratch_init(struct radeon_device *rdev)
 	u64 gpu_addr;
 
 	if (rdev->vram_scratch.robj == NULL) {
-		r = radeon_bo_create(rdev, NULL, RADEON_GPU_PAGE_SIZE,
+		r = radeon_bo_create(rdev, RADEON_GPU_PAGE_SIZE,
 				     PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
 				     &rdev->vram_scratch.robj);
 		if (r) {
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index e39177778601..b1e7809e5e15 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -42,23 +42,25 @@
 #endif
 
 struct drm_mm_node {
-	struct list_head free_stack;
 	struct list_head node_list;
-	unsigned free : 1;
+	struct list_head hole_stack;
+	unsigned hole_follows : 1;
 	unsigned scanned_block : 1;
 	unsigned scanned_prev_free : 1;
 	unsigned scanned_next_free : 1;
+	unsigned scanned_preceeds_hole : 1;
+	unsigned allocated : 1;
 	unsigned long start;
 	unsigned long size;
 	struct drm_mm *mm;
 };
 
 struct drm_mm {
-	/* List of free memory blocks, most recently freed ordered. */
-	struct list_head free_stack;
-	/* List of all memory nodes, ordered according to the (increasing) start
-	 * address of the memory node. */
-	struct list_head node_list;
+	/* List of all memory nodes that immediatly preceed a free hole. */
+	struct list_head hole_stack;
+	/* head_node.node_list is the list of all memory nodes, ordered
+	 * according to the (increasing) start address of the memory node. */
+	struct drm_mm_node head_node;
 	struct list_head unused_nodes;
 	int num_unused;
 	spinlock_t unused_lock;
@@ -70,8 +72,28 @@ struct drm_mm {
 	unsigned scanned_blocks;
 	unsigned long scan_start;
 	unsigned long scan_end;
+	struct drm_mm_node *prev_scanned_node;
 };
 
+static inline bool drm_mm_node_allocated(struct drm_mm_node *node)
+{
+	return node->allocated;
+}
+
+static inline bool drm_mm_initialized(struct drm_mm *mm)
+{
+	return mm->hole_stack.next;
+}
+#define drm_mm_for_each_node(entry, mm) list_for_each_entry(entry, \
+						&(mm)->head_node.node_list, \
+						node_list);
+#define drm_mm_for_each_scanned_node_reverse(entry, n, mm) \
+	for (entry = (mm)->prev_scanned_node, \
+		next = entry ? list_entry(entry->node_list.next, \
+			struct drm_mm_node, node_list) : NULL; \
+	     entry != NULL; entry = next, \
+		next = entry ? list_entry(entry->node_list.next, \
+			struct drm_mm_node, node_list) : NULL) \
 /*
  * Basic range manager support (drm_mm.c)
  */
@@ -118,7 +140,15 @@ static inline struct drm_mm_node *drm_mm_get_block_atomic_range(
 	return drm_mm_get_block_range_generic(parent, size, alignment,
 						start, end, 1);
 }
+extern int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
+			      unsigned long size, unsigned alignment);
+extern int drm_mm_insert_node_in_range(struct drm_mm *mm,
+				       struct drm_mm_node *node,
+				       unsigned long size, unsigned alignment,
+				       unsigned long start, unsigned long end);
 extern void drm_mm_put_block(struct drm_mm_node *cur);
+extern void drm_mm_remove_node(struct drm_mm_node *node);
+extern void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new);
 extern struct drm_mm_node *drm_mm_search_free(const struct drm_mm *mm,
 					      unsigned long size,
 					      unsigned alignment,
@@ -134,11 +164,6 @@ extern int drm_mm_init(struct drm_mm *mm, unsigned long start,
 		       unsigned long size);
 extern void drm_mm_takedown(struct drm_mm *mm);
 extern int drm_mm_clean(struct drm_mm *mm);
-extern unsigned long drm_mm_tail_space(struct drm_mm *mm);
-extern int drm_mm_remove_space_from_tail(struct drm_mm *mm,
-					 unsigned long size);
-extern int drm_mm_add_space_to_tail(struct drm_mm *mm,
-				    unsigned long size, int atomic);
 extern int drm_mm_pre_get(struct drm_mm *mm);
 
 static inline struct drm_mm *drm_get_mm(struct drm_mm_node *block)