The patch titled
Subject: mm: add sysfs entry to disable splitting underused THPs
has been added to the -mm mm-unstable branch. Its filename is
mm-add-sysfs-entry-to-disable-splitting-underused-thps.patch
This patch will shortly appear at
https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-add-sysfs-entry-to-disable-splitting-underused-thps.patch
This patch will later appear in the mm-unstable branch at
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next via the mm-everything
branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there every 2-3 working days
------------------------------------------------------
From: Usama Arif <usamaarif642@xxxxxxxxx>
Subject: mm: add sysfs entry to disable splitting underused THPs
Date: Fri, 30 Aug 2024 11:03:40 +0100
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.
Link: https://lkml.kernel.org/r/20240830100438.3623486-7-usamaarif642@xxxxxxxxx
Signed-off-by: Usama Arif <usamaarif642@xxxxxxxxx>
Cc: Alexander Zhu <alexlzhu@xxxxxx>
Cc: Barry Song <baohua@xxxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Domenico Cerasuolo <cerasuolodomenico@xxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Kairui Song <ryncsn@xxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxx>
Cc: Nico Pache <npache@xxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Cc: Roman Gushchin <roman.gushchin@xxxxxxxxx>
Cc: Ryan Roberts <ryan.roberts@xxxxxxx>
Cc: Shakeel Butt <shakeel.butt@xxxxxxxxx>
Cc: Shuang Zhai <zhais@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/admin-guide/mm/transhuge.rst | 10 +++++++
mm/huge_memory.c | 26 +++++++++++++++++++
2 files changed, 36 insertions(+)
--- a/Documentation/admin-guide/mm/transhuge.rst~mm-add-sysfs-entry-to-disable-splitting-underused-thps
+++ a/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
--- a/mm/huge_memory.c~mm-add-sysfs-entry-to-disable-splitting-underused-thps
+++ a/mm/huge_memory.c
@@ -74,6 +74,7 @@ static unsigned long deferred_split_coun
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;
@@ -440,6 +441,27 @@ static ssize_t hpage_pmd_size_show(struc
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,
@@ -448,6 +470,7 @@ static struct attribute *hugepage_attr[]
#ifdef CONFIG_SHMEM
&shmem_enabled_attr.attr,
#endif
+ &split_underused_thp_attr.attr,
NULL,
};
@@ -3601,6 +3624,9 @@ void deferred_split_folio(struct folio *
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.
_
Patches currently in -mm which might be from usamaarif642@xxxxxxxxx are
revert-mm-skip-cma-pages-when-they-are-not-available.patch
revert-mm-skip-cma-pages-when-they-are-not-available-update.patch
mm-store-zero-pages-to-be-swapped-out-in-a-bitmap.patch
mm-remove-code-to-handle-same-filled-pages.patch
mm-introduce-a-pageflag-for-partially-mapped-folios.patch
mm-split-underused-thps.patch
mm-add-sysfs-entry-to-disable-splitting-underused-thps.patch
