[PATCH v2 14/16] maple_tree: Refine mas_preallocate() node calculations

[Liam R. Howlett]

Calculate the number of nodes based on the pending write action instead
of assuming the worst case.

This addresses a performance regression introduced in platforms that
have longer allocation timing.

Signed-off-by: Liam R. Howlett <Liam.Howlett@xxxxxxxxxx>
---
 lib/maple_tree.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 47 insertions(+), 1 deletion(-)

diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 048d6413a114..7ac5b5457603 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -5541,9 +5541,55 @@ EXPORT_SYMBOL_GPL(mas_store_prealloc);
  */
 int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp)
 {
+	MA_WR_STATE(wr_mas, mas, entry);
+	unsigned char node_size;
+	int request = 1;
 	int ret;
 
-	mas_node_count_gfp(mas, 1 + mas_mt_height(mas) * 3, gfp);
+
+	if (unlikely(!mas->index && mas->last == ULONG_MAX))
+		goto ask_now;
+
+	mas_wr_store_setup(&wr_mas);
+	wr_mas.content = mas_start(mas);
+	/* Root expand */
+	if (unlikely(mas_is_none(mas) || mas_is_ptr(mas)))
+		goto ask_now;
+
+	if (unlikely(!mas_wr_walk(&wr_mas))) {
+		/* Spanning store, use worst case for now */
+		request = 1 + mas_mt_height(mas) * 3;
+		goto ask_now;
+	}
+
+	/* At this point, we are at the leaf node that needs to be altered. */
+	/* Exact fit, no nodes needed. */
+	if (wr_mas.r_min == mas->index && wr_mas.r_max == mas->last)
+		return 0;
+
+	mas_wr_end_piv(&wr_mas);
+	node_size = mas_wr_new_end(&wr_mas);
+	/* Slot store can avoid using any nodes */
+	if (node_size == wr_mas.node_end && wr_mas.offset_end - mas->offset == 1)
+		return 0;
+
+	if (node_size >= mt_slots[wr_mas.type]) {
+		/* Split, worst case for now. */
+		request = 1 + mas_mt_height(mas) * 2;
+		goto ask_now;
+	}
+
+	/* Appending does not need any nodes */
+	if (node_size == wr_mas.node_end + 1 && mas->offset == wr_mas.node_end)
+		return 0;
+
+	/* Potential spanning rebalance collapsing a node, use worst-case */
+	if (node_size  - 1 <= mt_min_slots[wr_mas.type])
+		request = mas_mt_height(mas) * 2 - 1;
+
+	/* node store needs one node */
+ask_now:
+	mas_node_count_gfp(mas, request, gfp);
 	mas->mas_flags |= MA_STATE_PREALLOC;
 	if (likely(!mas_is_err(mas)))
 		return 0;
-- 
2.39.2