[PATCH v4 6/6] mm: add sysfs entry to disable splitting underused THPs

[Usama Arif <usamaarif642@xxxxxxxxx>]

If disabled, THPs faulted in or collapsed will not be added to
_deferred_list, and therefore won't be considered for splitting under
memory pressure if underused.

Signed-off-by: Usama Arif <usamaarif642@xxxxxxxxx>
---
 Documentation/admin-guide/mm/transhuge.rst | 10 +++++++++
 mm/huge_memory.c                           | 26 ++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index 40741b892aff..02ae7bc9efbd 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -202,6 +202,16 @@ PMD-mappable transparent hugepage::
 
 	cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
 
+All THPs at fault and collapse time will be added to _deferred_list,
+and will therefore be split under memory presure if they are considered
+"underused". A THP is underused if the number of zero-filled pages in
+the THP is above max_ptes_none (see below). It is possible to disable
+this behaviour by writing 0 to shrink_underused, and enable it by writing
+1 to it::
+
+	echo 0 > /sys/kernel/mm/transparent_hugepage/shrink_underused
+	echo 1 > /sys/kernel/mm/transparent_hugepage/shrink_underused
+
 khugepaged will be automatically started when PMD-sized THP is enabled
 (either of the per-size anon control or the top-level control are set
 to "always" or "madvise"), and it'll be automatically shutdown when
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index f5363cf900f9..5d67d3b3c1b2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -74,6 +74,7 @@ static unsigned long deferred_split_count(struct shrinker *shrink,
 					  struct shrink_control *sc);
 static unsigned long deferred_split_scan(struct shrinker *shrink,
 					 struct shrink_control *sc);
+static bool split_underused_thp = true;
 
 static atomic_t huge_zero_refcount;
 struct folio *huge_zero_folio __read_mostly;
@@ -439,6 +440,27 @@ static ssize_t hpage_pmd_size_show(struct kobject *kobj,
 static struct kobj_attribute hpage_pmd_size_attr =
 	__ATTR_RO(hpage_pmd_size);
 
+static ssize_t split_underused_thp_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%d\n", split_underused_thp);
+}
+
+static ssize_t split_underused_thp_store(struct kobject *kobj,
+			     struct kobj_attribute *attr,
+			     const char *buf, size_t count)
+{
+	int err = kstrtobool(buf, &split_underused_thp);
+
+	if (err < 0)
+		return err;
+
+	return count;
+}
+
+static struct kobj_attribute split_underused_thp_attr = __ATTR(
+	shrink_underused, 0644, split_underused_thp_show, split_underused_thp_store);
+
 static struct attribute *hugepage_attr[] = {
 	&enabled_attr.attr,
 	&defrag_attr.attr,
@@ -447,6 +469,7 @@ static struct attribute *hugepage_attr[] = {
 #ifdef CONFIG_SHMEM
 	&shmem_enabled_attr.attr,
 #endif
+	&split_underused_thp_attr.attr,
 	NULL,
 };
 
@@ -3477,6 +3500,9 @@ void deferred_split_folio(struct folio *folio, bool partially_mapped)
 	if (folio_order(folio) <= 1)
 		return;
 
+	if (!partially_mapped && !split_underused_thp)
+		return;
+
 	/*
 	 * The try_to_unmap() in page reclaim path might reach here too,
 	 * this may cause a race condition to corrupt deferred split queue.
-- 
2.43.5