maple_tree: add mas_wr_new_end() to calculate new_end accurately

The previous new_end calculation is inaccurate, because it assumes that
two new pivots must be added (this is inaccurate), and sometimes it will
miss the fast path and enter the slow path.  Add mas_wr_new_end() to
accurately calculate new_end to make the conditions for entering the fast
path more accurate.

Link: https://lkml.kernel.org/r/20230524031247.65949-7-zhangpeng.00@bytedance.com
Signed-off-by: Peng Zhang <zhangpeng.00@bytedance.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index e6e42e1ba44cfea95e37606d7fd1a57c16b13606..07c5c7afd4156b6570f314174ab597b7ed9a8ccd 100644 (file)
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -4296,6 +4296,21 @@ static inline void mas_wr_extend_null(struct ma_wr_state *wr_mas)
        }
 }
 
+static inline unsigned char mas_wr_new_end(struct ma_wr_state *wr_mas)
+{
+       struct ma_state *mas = wr_mas->mas;
+       unsigned char new_end = wr_mas->node_end + 2;
+
+       new_end -= wr_mas->offset_end - mas->offset;
+       if (wr_mas->r_min == mas->index)
+               new_end--;
+
+       if (wr_mas->end_piv == mas->last)
+               new_end--;
+
+       return new_end;
+}
+
 static inline bool mas_wr_append(struct ma_wr_state *wr_mas)
 {
        unsigned char end = wr_mas->node_end;
@@ -4351,9 +4366,8 @@ static void mas_wr_bnode(struct ma_wr_state *wr_mas)
 
 static inline void mas_wr_modify(struct ma_wr_state *wr_mas)
 {
-       unsigned char node_slots;
-       unsigned char node_size;
        struct ma_state *mas = wr_mas->mas;
+       unsigned char new_end;
 
        /* Direct replacement */
        if (wr_mas->r_min == mas->index && wr_mas->r_max == mas->last) {
@@ -4363,17 +4377,15 @@ static inline void mas_wr_modify(struct ma_wr_state *wr_mas)
                return;
        }
 
-       /* Attempt to append */
-       node_slots = mt_slots[wr_mas->type];
-       node_size = wr_mas->node_end - wr_mas->offset_end + mas->offset + 2;
-       if (mas->max == ULONG_MAX)
-               node_size++;
-
-       /* slot and node store will not fit, go to the slow path */
-       if (unlikely(node_size >= node_slots))
+       /*
+        * new_end exceeds the size of the maple node and cannot enter the fast
+        * path.
+        */
+       new_end = mas_wr_new_end(wr_mas);
+       if (new_end >= mt_slots[wr_mas->type])
                goto slow_path;
 
-       if (wr_mas->entry && (wr_mas->node_end < node_slots - 1) &&
+       if (wr_mas->entry && (wr_mas->node_end < mt_slots[wr_mas->type] - 1) &&
            (mas->offset == wr_mas->node_end) && mas_wr_append(wr_mas)) {
                if (!wr_mas->content || !wr_mas->entry)
                        mas_update_gap(mas);