[RFC PATCH 4/6] mm/damon: introduce DAMOS_MTHP_SPLIT action and hot_threshold

[Wang Lian]

Add a new DAMOS_MTHP_SPLIT action to split a large folio to the
specified target_order, and a hot_threshold parameter to control
split decisions based on sub-page access heatmap.

target_order: For MTHP_SPLIT, valid range is 2..HPAGE_PMD_ORDER-1,
allowing splits to e.g. order-2 (16KB) or order-3 (32KB) mTHP.
An invalid value (0 or >= PMD_ORDER) defaults to order-2; 0 would
mean "split to base page" which defeats the purpose of mTHP split.

hot_threshold: Minimum percentage (0-100) of hot subpages required
to preserve a THP.  THPs with hot_fraction >= hot_threshold are
kept intact; below it, the THP is split to target_order.  Default
is 30%, based on ARM SPE profiling on Kunpeng 920 which showed:

  - 97% of THPs have <10% hot subpages (clearly cold, split)
  - 1-2% have 10-30% (borderline, tunable)
  - <1% have >30% (genuinely hot, preserve)

The 30% default catches genuinely hot THPs while splitting the vast
majority of cold THPs.  Exposed as sysfs attribute for per-scheme
tuning (e.g. lower for memory-pressure scenarios, higher for
latency-sensitive workloads).

sysfs interface:
  /sys/kernel/mm/damon/admin/kdamonds/.../schemes/0/hot_threshold

The actual split implementation follows in subsequent patches.

Co-developed-by: Kunwu Chan <kunwu.chan@xxxxxxxxx>
Signed-off-by: Kunwu Chan <kunwu.chan@xxxxxxxxx>
Signed-off-by: Wang Lian <lianux.mm@xxxxxxxxx>
---
 include/linux/damon.h    | 17 ++++++++++++--
 mm/damon/sysfs-schemes.c | 51 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 66 insertions(+), 2 deletions(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 5a0587556573..982057bbce3b 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -121,6 +121,7 @@ struct damon_target {
  * @DAMOS_HUGEPAGE:	Call ``madvise()`` for the region with MADV_HUGEPAGE.
  * @DAMOS_NOHUGEPAGE:	Call ``madvise()`` for the region with MADV_NOHUGEPAGE.
  * @DAMOS_COLLAPSE:	Call ``madvise()`` for the region with MADV_COLLAPSE.
+ * @DAMOS_MTHP_SPLIT:	Split large folios to the target mTHP order.
  * @DAMOS_LRU_PRIO:	Prioritize the region on its LRU lists.
  * @DAMOS_LRU_DEPRIO:	Deprioritize the region on its LRU lists.
  * @DAMOS_MIGRATE_HOT:  Migrate the regions prioritizing warmer regions.
@@ -141,6 +142,7 @@ enum damos_action {
 	DAMOS_HUGEPAGE,
 	DAMOS_NOHUGEPAGE,
 	DAMOS_COLLAPSE,
+	DAMOS_MTHP_SPLIT,
 	DAMOS_LRU_PRIO,
 	DAMOS_LRU_DEPRIO,
 	DAMOS_MIGRATE_HOT,
@@ -573,10 +575,21 @@ struct damos {
 	struct damos_access_pattern pattern;
 	enum damos_action action;
 	/*
-	 * @target_order: target order for mTHP actions (DAMOS_COLLAPSE).
-	 * 0 means system default (PMD order).  Valid: 0, 2..HPAGE_PMD_ORDER.
+	 * @target_order: target mTHP order for DAMOS_COLLAPSE and
+	 * DAMOS_MTHP_SPLIT.  For COLLAPSE, 0 means PMD order default,
+	 * valid values: 0, 2..HPAGE_PMD_ORDER.  For MTHP_SPLIT,
+	 * valid values: 2..HPAGE_PMD_ORDER-1; 0 and HPAGE_PMD_ORDER
+	 * are rejected at scheme creation time (defaulting to 2).
 	 */
 	unsigned int target_order;
+	/*
+	 * @hot_threshold: minimum hot subpage percentage (0-100) to
+	 * preserve a THP during DAMOS_MTHP_SPLIT.  A THP with
+	 * hot_fraction >= hot_threshold is kept intact; below it, the
+	 * THP is split to @target_order.  Default 30 based on SPE
+	 * profiling showing 97% of THPs have <10% hot subpages.
+	 */
+	unsigned int hot_threshold;
 	unsigned long apply_interval_us;
 /* private: internal use only */
 	/*
diff --git a/mm/damon/sysfs-schemes.c b/mm/damon/sysfs-schemes.c
index 735970717048..823f1ca9bd90 100644
--- a/mm/damon/sysfs-schemes.c
+++ b/mm/damon/sysfs-schemes.c
@@ -2260,6 +2260,7 @@ struct damon_sysfs_scheme {
 	struct damon_sysfs_scheme_regions *tried_regions;
 	int target_nid;
 	unsigned int target_order;
+	unsigned int hot_threshold;
 	struct damos_sysfs_dests *dests;
 };
 
@@ -2293,6 +2294,10 @@ static struct damos_sysfs_action_name damos_sysfs_action_names[] = {
 		.action = DAMOS_COLLAPSE,
 		.name = "collapse",
 	},
+	{
+		.action = DAMOS_MTHP_SPLIT,
+		.name = "mthp_split",
+	},
 	{
 		.action = DAMOS_LRU_PRIO,
 		.name = "lru_prio",
@@ -2673,6 +2678,34 @@ static ssize_t target_order_store(struct kobject *kobj,
 	return count;
 }
 
+static ssize_t hot_threshold_show(struct kobject *kobj,
+		struct kobj_attribute *attr, char *buf)
+{
+	struct damon_sysfs_scheme *scheme = container_of(kobj,
+			struct damon_sysfs_scheme, kobj);
+
+	return sysfs_emit(buf, "%u\n", scheme->hot_threshold);
+}
+
+static ssize_t hot_threshold_store(struct kobject *kobj,
+		struct kobj_attribute *attr, const char *buf, size_t count)
+{
+	struct damon_sysfs_scheme *scheme = container_of(kobj,
+			struct damon_sysfs_scheme, kobj);
+	unsigned int val;
+	int err;
+
+	err = kstrtouint(buf, 0, &val);
+	if (err)
+		return err;
+
+	if (val > 100)
+		return -EINVAL;
+
+	scheme->hot_threshold = val;
+	return count;
+}
+
 static void damon_sysfs_scheme_release(struct kobject *kobj)
 {
 	kfree(container_of(kobj, struct damon_sysfs_scheme, kobj));
@@ -2690,11 +2723,15 @@ static struct kobj_attribute damon_sysfs_scheme_target_nid_attr =
 static struct kobj_attribute damon_sysfs_scheme_target_order_attr =
 		__ATTR_RW_MODE(target_order, 0600);
 
+static struct kobj_attribute damon_sysfs_scheme_hot_threshold_attr =
+		__ATTR_RW_MODE(hot_threshold, 0600);
+
 static struct attribute *damon_sysfs_scheme_attrs[] = {
 	&damon_sysfs_scheme_action_attr.attr,
 	&damon_sysfs_scheme_apply_interval_us_attr.attr,
 	&damon_sysfs_scheme_target_nid_attr.attr,
 	&damon_sysfs_scheme_target_order_attr.attr,
+	&damon_sysfs_scheme_hot_threshold_attr.attr,
 	NULL,
 };
 ATTRIBUTE_GROUPS(damon_sysfs_scheme);
@@ -3048,8 +3085,22 @@ static struct damos *damon_sysfs_mk_scheme(
 			HPAGE_PMD_ORDER, HPAGE_PMD_ORDER);
 		sysfs_scheme->target_order = 0;
 	}
+	if (sysfs_scheme->action == DAMOS_MTHP_SPLIT &&
+	    (sysfs_scheme->target_order == 0 ||
+	     sysfs_scheme->target_order >= HPAGE_PMD_ORDER)) {
+		pr_warn("DAMON mthp_split: target_order %u invalid, need 2..%u. Defaulting to 2.\n",
+			sysfs_scheme->target_order,
+			HPAGE_PMD_ORDER - 1);
+		sysfs_scheme->target_order = 2;
+	}
 	scheme->target_order = sysfs_scheme->target_order;
 
+	if (sysfs_scheme->action == DAMOS_MTHP_SPLIT) {
+		if (sysfs_scheme->hot_threshold == 0)
+			sysfs_scheme->hot_threshold = 30;
+		scheme->hot_threshold = sysfs_scheme->hot_threshold;
+	}
+
 	err = damos_sysfs_add_quota_score(sysfs_quotas->goals, &scheme->quota);
 	if (err) {
 		damon_destroy_scheme(scheme);
-- 
2.50.1 (Apple Git-155)