[PATCH] mm/damon/core: eliminate hot-path integer division in damon_max_nr_accesses()

[Josh Law]

Hardware integer division is slow. The function damon_max_nr_accesses(),
which is called very frequently, performs an integer division.
However, the struct damon_attrs already caches this exact ratio in the
internal field aggr_samples. We can eliminate the hardware division in
the hot path by simply returning aggr_samples.

Signed-off-by: Josh Law <objecting@xxxxxxxxxxxxx>
---
 include/linux/damon.h       |  3 +--
 mm/damon/core.c             |  1 +
 mm/damon/tests/core-kunit.h | 16 ++++++++++++----
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 6bd71546f7b2..438fe6f3eab4 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -960,8 +960,7 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx)
 static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs)
 {
 	/* {aggr,sample}_interval are unsigned long, hence could overflow */
-	return min(attrs->aggr_interval / attrs->sample_interval,
-			(unsigned long)UINT_MAX);
+	return min_t(unsigned long, attrs->aggr_samples, UINT_MAX);
 }
 
 
diff --git a/mm/damon/core.c b/mm/damon/core.c
index b0ab0ee6eab9..59b709f04975 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -582,6 +582,7 @@ struct damon_ctx *damon_new_ctx(void)
 	ctx->attrs.sample_interval = 5 * 1000;
 	ctx->attrs.aggr_interval = 100 * 1000;
 	ctx->attrs.ops_update_interval = 60 * 1000 * 1000;
+	ctx->attrs.aggr_samples = 20;
 
 	ctx->passed_sample_intervals = 0;
 	/* These will be set from kdamond_init_ctx() */
diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h
index e86d4f4fe261..56d03ef6a5a4 100644
--- a/mm/damon/tests/core-kunit.h
+++ b/mm/damon/tests/core-kunit.h
@@ -416,6 +416,8 @@ static void damon_test_nr_accesses_to_accesses_bp(struct kunit *test)
 		.aggr_interval = ((unsigned long)UINT_MAX + 1) * 10
 	};
 
+	attrs.aggr_samples = attrs.aggr_interval / attrs.sample_interval;
+
 	/*
 	 * In some cases such as 32bit architectures where UINT_MAX is
 	 * ULONG_MAX, attrs.aggr_interval becomes zero.  Calling
@@ -434,7 +436,8 @@ static void damon_test_nr_accesses_to_accesses_bp(struct kunit *test)
 static void damon_test_update_monitoring_result(struct kunit *test)
 {
 	struct damon_attrs old_attrs = {
-		.sample_interval = 10, .aggr_interval = 1000,};
+		.sample_interval = 10, .aggr_interval = 1000,
+		.aggr_samples = 100,};
 	struct damon_attrs new_attrs;
 	struct damon_region *r = damon_new_region(3, 7);
 
@@ -446,19 +449,24 @@ static void damon_test_update_monitoring_result(struct kunit *test)
 	r->age = 20;
 
 	new_attrs = (struct damon_attrs){
-		.sample_interval = 100, .aggr_interval = 10000,};
+		.sample_interval = 100, .aggr_interval = 10000,
+		.aggr_samples = 100,};
 	damon_update_monitoring_result(r, &old_attrs, &new_attrs, false);
 	KUNIT_EXPECT_EQ(test, r->nr_accesses, 15);
 	KUNIT_EXPECT_EQ(test, r->age, 2);
 
 	new_attrs = (struct damon_attrs){
-		.sample_interval = 1, .aggr_interval = 1000};
+		.sample_interval = 1, .aggr_interval = 1000,
+		.aggr_samples = 1000,
+	};
 	damon_update_monitoring_result(r, &old_attrs, &new_attrs, false);
 	KUNIT_EXPECT_EQ(test, r->nr_accesses, 150);
 	KUNIT_EXPECT_EQ(test, r->age, 2);
 
 	new_attrs = (struct damon_attrs){
-		.sample_interval = 1, .aggr_interval = 100};
+		.sample_interval = 1, .aggr_interval = 100,
+		.aggr_samples = 100,
+	};
 	damon_update_monitoring_result(r, &old_attrs, &new_attrs, false);
 	KUNIT_EXPECT_EQ(test, r->nr_accesses, 150);
 	KUNIT_EXPECT_EQ(test, r->age, 20);
-- 
2.34.1