intervals: Do not sort cached set elements over and over again

When adding element(s) to a non-empty set, code merged the two lists and
sorted the result. With many individual 'add element' commands this
causes substantial overhead. Make use of the fact that
existing_set->init is sorted already, sort only the list of new elements
and use list_splice_sorted() to merge the two sorted lists.

Add set_sort_splice() and use it for set element overlap detection and
automerge.

A test case adding ~25k elements in individual commands completes in
about 1/4th of the time with this patch applied.

Joint work with Pablo.

Fixes: 3da9643fb9ff9 ("intervals: add support to automerge with kernel elements")
Signed-off-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

3 files changed, 24 insertions, 25 deletions

diff --git a/include/expression.h b/include/expression.h
index 53194c92..cf7319b6 100644
--- a/include/expression.h
+++ b/include/expression.h
@@ -481,6 +481,7 @@ extern struct expr *compound_expr_alloc(const struct location *loc,
 extern void compound_expr_add(struct expr *compound, struct expr *expr);
 extern void compound_expr_remove(struct expr *compound, struct expr *expr);
 extern void list_expr_sort(struct list_head *head);
+extern void list_splice_sorted(struct list_head *list, struct list_head *head);
 
 extern struct expr *concat_expr_alloc(const struct location *loc);
 
diff --git a/src/intervals.c b/src/intervals.c
index e2034132..dcc06d18 100644
--- a/src/intervals.c
+++ b/src/intervals.c
@@ -118,6 +118,26 @@ static bool merge_ranges(struct set_automerge_ctx *ctx,
 	return false;
 }
 
+static void set_sort_splice(struct expr *init, struct set *set)
+{
+	struct set *existing_set = set->existing_set;
+
+	set_to_range(init);
+	list_expr_sort(&init->expressions);
+
+	if (!existing_set)
+		return;
+
+	if (existing_set->init) {
+		set_to_range(existing_set->init);
+		list_splice_sorted(&existing_set->init->expressions,
+				   &init->expressions);
+		init_list_head(&existing_set->init->expressions);
+	} else {
+		existing_set->init = set_expr_alloc(&internal_location, set);
+	}
+}
+
 static void setelem_automerge(struct set_automerge_ctx *ctx)
 {
 	struct expr *i, *next, *prev = NULL;
@@ -222,18 +242,7 @@ int set_automerge(struct list_head *msgs, struct cmd *cmd, struct set *set,
 		return 0;
 	}
 
-	if (existing_set) {
-		if (existing_set->init) {
-			list_splice_init(&existing_set->init->expressions,
-					 &init->expressions);
-		} else {
-			existing_set->init = set_expr_alloc(&internal_location,
-							    set);
-		}
-	}
-
-	set_to_range(init);
-	list_expr_sort(&init->expressions);
+	set_sort_splice(init, set);
 
 	ctx.purge = set_expr_alloc(&internal_location, set);
 
@@ -591,18 +600,7 @@ int set_overlap(struct list_head *msgs, struct set *set, struct expr *init)
 	struct expr *i, *n, *clone;
 	int err;
 
-	if (existing_set) {
-		if (existing_set->init) {
-			list_splice_init(&existing_set->init->expressions,
-					 &init->expressions);
-		} else {
-			existing_set->init = set_expr_alloc(&internal_location,
-							    set);
-		}
-	}
-
-	set_to_range(init);
-	list_expr_sort(&init->expressions);
+	set_sort_splice(init, set);
 
 	err = setelem_overlap(msgs, set, init);
 
diff --git a/src/mergesort.c b/src/mergesort.c
index 8e6aac5f..dca71422 100644
--- a/src/mergesort.c
+++ b/src/mergesort.c
@@ -70,7 +70,7 @@ static int expr_msort_cmp(const struct expr *e1, const struct expr *e2)
 	return ret;
 }
 
-static void list_splice_sorted(struct list_head *list, struct list_head *head)
+void list_splice_sorted(struct list_head *list, struct list_head *head)
 {
 	struct list_head *h = head->next;
 	struct list_head *l = list->next;