mm: add sysfs entry to disable splitting underused THPs

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@gmail.com
Signed-off-by: Usama Arif <usamaarif642@gmail.com>
Cc: Alexander Zhu <alexlzhu@fb.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Domenico Cerasuolo <cerasuolodomenico@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kairui Song <ryncsn@gmail.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Nico Pache <npache@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Shuang Zhai <zhais@google.com>
Cc: Shuang Zhai <szhai2@cs.rochester.edu>
Cc: Yu Zhao <yuzhao@google.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index aca0cff852b852b3b40428a29bf3d001fd1002a5..cfdd16a52e39fdff0a478b44b9ad97726029d674 100644 (file)
--- 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 cec5bce046a0d1d7fabb303036e1b889258e7f8d..691702e39f851ee1e92f5bc5300d99e78d4269be 100644 (file)
--- 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;
@@ -440,6 +441,27 @@ 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,
@@ -448,6 +470,7 @@ static struct attribute *hugepage_attr[] = {
 #ifdef CONFIG_SHMEM
        &shmem_enabled_attr.attr,
 #endif
+       &split_underused_thp_attr.attr,
        NULL,
 };
 
@@ -3557,6 +3580,9 @@ 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.