maple_tree: use vacant nodes to reduce worst case allocations

In order to determine the store type for a maple tree operation, a walk of
the tree is done through mas_wr_walk().  This function descends the tree
until a spanning write is detected or we reach a leaf node.  While
descending, keep track of the height at which we encounter a node with
available space.  This is done by checking if mas->end is less than the
number of slots a given node type can fit.

Now that the height of the vacant node is tracked, we can use the
difference between the height of the tree and the height of the vacant
node to know how many levels we will have to propagate creating new nodes.
Update mas_prealloc_calc() to consider the vacant height and reduce the
number of worst-case allocations.

Rebalancing and spanning stores are not supported and fall back to using
the full height of the tree for allocations.

Update preallocation testing assertions to take into account vacant
height.

Link: https://lkml.kernel.org/r/20250410191446.2474640-4-sidhartha.kumar@oracle.com
Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 71 insertions, 8 deletions

diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c
index e0f8fabe8821..e37a3ab2e921 100644
--- a/tools/testing/radix-tree/maple.c
+++ b/tools/testing/radix-tree/maple.c
@@ -35475,15 +35475,65 @@ static void check_dfs_preorder(struct maple_tree *mt)
 }
 /* End of depth first search tests */
 
+/* get height of the lowest non-leaf node with free space */
+static unsigned char get_vacant_height(struct ma_wr_state *wr_mas, void *entry)
+{
+	struct ma_state *mas = wr_mas->mas;
+	char vacant_height = 0;
+	enum maple_type type;
+	unsigned long *pivots;
+	unsigned long min = 0;
+	unsigned long max = ULONG_MAX;
+	unsigned char offset;
+
+	/* start traversal */
+	mas_reset(mas);
+	mas_start(mas);
+	if (!xa_is_node(mas_root(mas)))
+		return 0;
+
+	type = mte_node_type(mas->node);
+	wr_mas->type = type;
+	while (!ma_is_leaf(type)) {
+		mas_node_walk(mas, mte_to_node(mas->node), type, &min, &max);
+		offset = mas->offset;
+		mas->end = mas_data_end(mas);
+		pivots = ma_pivots(mte_to_node(mas->node), type);
+
+		if (pivots) {
+			if (offset)
+				min = pivots[mas->offset - 1];
+			if (offset < mas->end)
+				max = pivots[mas->offset];
+		}
+		wr_mas->r_max = offset < mas->end ? pivots[offset] : mas->max;
+
+		/* detect spanning write */
+		if (mas_is_span_wr(wr_mas))
+			break;
+
+		if (mas->end < mt_slot_count(mas->node) - 1)
+			vacant_height = mas->depth + 1;
+
+		mas_descend(mas);
+		type = mte_node_type(mas->node);
+		mas->depth++;
+	}
+
+	return vacant_height;
+}
+
 /* Preallocation testing */
 static noinline void __init check_prealloc(struct maple_tree *mt)
 {
 	unsigned long i, max = 100;
 	unsigned long allocated;
 	unsigned char height;
+	unsigned char vacant_height;
 	struct maple_node *mn;
 	void *ptr = check_prealloc;
 	MA_STATE(mas, mt, 10, 20);
+	MA_WR_STATE(wr_mas, &mas, ptr);
 
 	mt_set_non_kernel(1000);
 	for (i = 0; i <= max; i++)
@@ -35494,8 +35544,9 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
 	MT_BUG_ON(mt, allocated == 0);
-	MT_BUG_ON(mt, allocated != 1 + height * 3);
+	MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
 	mas_destroy(&mas);
 	allocated = mas_allocated(&mas);
 	MT_BUG_ON(mt, allocated != 0);
@@ -35503,8 +35554,9 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
 	MT_BUG_ON(mt, allocated == 0);
-	MT_BUG_ON(mt, allocated != 1 + height * 3);
+	MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	mas_destroy(&mas);
 	allocated = mas_allocated(&mas);
@@ -35514,7 +35566,8 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
-	MT_BUG_ON(mt, allocated != 1 + height * 3);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
+	MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
 	mn = mas_pop_node(&mas);
 	MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1);
 	mn->parent = ma_parent_ptr(mn);
@@ -35527,7 +35580,8 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
-	MT_BUG_ON(mt, allocated != 1 + height * 3);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
+	MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
 	mn = mas_pop_node(&mas);
 	MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1);
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
@@ -35540,7 +35594,8 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
-	MT_BUG_ON(mt, allocated != 1 + height * 3);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
+	MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
 	mn = mas_pop_node(&mas);
 	MT_BUG_ON(mt, mas_allocated(&mas) != allocated - 1);
 	mas_push_node(&mas, mn);
@@ -35553,7 +35608,8 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
-	MT_BUG_ON(mt, allocated != 1 + height * 3);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
+	MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 3);
 	mas_store_prealloc(&mas, ptr);
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
 
@@ -35578,7 +35634,8 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
-	MT_BUG_ON(mt, allocated != 1 + height * 2);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
+	MT_BUG_ON(mt, allocated != 1 + (height - vacant_height) * 2);
 	mas_store_prealloc(&mas, ptr);
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
 	mt_set_non_kernel(1);
@@ -35595,8 +35652,14 @@ static noinline void __init check_prealloc(struct maple_tree *mt)
 	MT_BUG_ON(mt, mas_preallocate(&mas, ptr, GFP_KERNEL) != 0);
 	allocated = mas_allocated(&mas);
 	height = mas_mt_height(&mas);
+	vacant_height = get_vacant_height(&wr_mas, ptr);
 	MT_BUG_ON(mt, allocated == 0);
-	MT_BUG_ON(mt, allocated != 1 + height * 3);
+	/*
+	 * vacant height cannot be used to compute the number of nodes needed
+	 * as the root contains two entries which means it is on the verge of
+	 * insufficiency. The worst case full height of the tree is needed.
+	 */
+	MT_BUG_ON(mt, allocated != height * 3 + 1);
 	mas_store_prealloc(&mas, ptr);
 	MT_BUG_ON(mt, mas_allocated(&mas) != 0);
 	mas_set_range(&mas, 0, 200);