From: Barry Song <v-songbaohua@xxxxxxxx>
When an mTHP is added to the deferred_list, its partial pages
are unused, leading to wasted memory and potentially increasing
memory reclamation pressure. Tracking this number indicates
the extent to which userspace is partially unmapping mTHPs.
Detailing the specifics of how unmapping occurs is quite difficult
and not that useful, so we adopt a simple approach: each time an
mTHP enters the deferred_list, we increment the count by 1; whenever
it leaves for any reason, we decrement the count by 1.
Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
---
Documentation/admin-guide/mm/transhuge.rst | 5 +++++
include/linux/huge_mm.h | 1 +
mm/huge_memory.c | 6 ++++++
3 files changed, 12 insertions(+)
diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
index 715f181543f6..5028d61cbe0c 100644
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -532,6 +532,11 @@ anon_num
These huge pages could be still entirely mapped and have partially
unmapped and unused subpages.
+anon_num_partial_unused
+ the number of anon huge pages which have been partially unmapped
+ we have in the whole system. These unmapped subpages are also
+ unused and temporarily wasting memory.
+
As the system ages, allocating huge pages may be expensive as the
system uses memory compaction to copy data around memory to free a
huge page for use. There are some counters in ``/proc/vmstat`` to help
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 294c348fe3cc..4b27a9797150 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -282,6 +282,7 @@ enum mthp_stat_item {
MTHP_STAT_SPLIT_FAILED,
MTHP_STAT_SPLIT_DEFERRED,
MTHP_STAT_NR_ANON,
+ MTHP_STAT_NR_ANON_SPLIT_DEFERRED,
__MTHP_STAT_COUNT
};
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b6bc2a3791e3..6083144f9fa0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -579,6 +579,7 @@ DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT);
DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
DEFINE_MTHP_STAT_ATTR(anon_num, MTHP_STAT_NR_ANON);
+DEFINE_MTHP_STAT_ATTR(anon_num_partial_unused, MTHP_STAT_NR_ANON_SPLIT_DEFERRED);
static struct attribute *stats_attrs[] = {
&anon_fault_alloc_attr.attr,
@@ -593,6 +594,7 @@ static struct attribute *stats_attrs[] = {
&split_failed_attr.attr,
&split_deferred_attr.attr,
&anon_num_attr.attr,
+ &anon_num_partial_unused_attr.attr,
NULL,
};
@@ -3229,6 +3231,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
if (folio_order(folio) > 1 &&
!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
+ mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_SPLIT_DEFERRED, -1);
/*
* Reinitialize page_deferred_list after removing the
* page from the split_queue, otherwise a subsequent
@@ -3291,6 +3294,7 @@ void __folio_undo_large_rmappable(struct folio *folio)
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
+ mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_SPLIT_DEFERRED, -1);
list_del_init(&folio->_deferred_list);
}
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
@@ -3332,6 +3336,7 @@ void deferred_split_folio(struct folio *folio)
if (folio_test_pmd_mappable(folio))
count_vm_event(THP_DEFERRED_SPLIT_PAGE);
count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
+ mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_SPLIT_DEFERRED, 1);
list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
ds_queue->split_queue_len++;
#ifdef CONFIG_MEMCG
@@ -3379,6 +3384,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
list_move(&folio->_deferred_list, &list);
} else {
/* We lost race with folio_put() */
+ mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_SPLIT_DEFERRED, -1);
list_del_init(&folio->_deferred_list);
ds_queue->split_queue_len--;
}
--
2.34.1
