mm: count the number of partially mapped anonymous THPs per size

When a THP is added to the deferred_list due to partially mapped, its
partial pages are unused, leading to wasted memory and potentially
increasing memory reclamation pressure.

Detailing the specifics of how unmapping occurs is quite difficult and not
that useful, so we adopt a simple approach: each time a THP enters the
deferred_list, we increment the count by 1; whenever it leaves for any
reason, we decrement the count by 1.

Link: https://lkml.kernel.org/r/20240824010441.21308-3-21cnbao@gmail.com
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Chuanhua Han <hanchuanhua@oppo.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuai Yuan <yuanshuai@oppo.com>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Zi Yan <ziy@nvidia.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 d6874234a09a23c66cb674c8321c56497fa8a6de..56a086900651509fe318bc106d634d4c0486e3ea 100644 (file)
--- a/Documentation/admin-guide/mm/transhuge.rst
+++ b/Documentation/admin-guide/mm/transhuge.rst
@@ -556,6 +556,13 @@ nr_anon
        might be currently entirely mapped or have partially unmapped/unused
        subpages.
 
+nr_anon_partially_mapped
+       the number of anonymous THP which are likely partially mapped, possibly
+       wasting memory, and have been queued for deferred memory reclamation.
+       Note that in corner some cases (e.g., failed migration), we might detect
+       an anonymous THP as "partially mapped" and count it here, even though it
+       is not actually partially mapped anymore.
+
 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 2ee2971e4e101bde283d9296aa0db92f79253015..4902e2f7e896f9d3c8edcf67f04c0d882ae45043 100644 (file)
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -127,6 +127,7 @@ enum mthp_stat_item {
        MTHP_STAT_SPLIT_FAILED,
        MTHP_STAT_SPLIT_DEFERRED,
        MTHP_STAT_NR_ANON,
+       MTHP_STAT_NR_ANON_PARTIALLY_MAPPED,
        __MTHP_STAT_COUNT
 };
 

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index ea57c51d478d4f8f2221a862e0c019f2906b0c69..efc625086dc7280c61e5dd2b2f78c1da5f03da0b 100644 (file)
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -598,6 +598,7 @@ 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(nr_anon, MTHP_STAT_NR_ANON);
+DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED);
 
 static struct attribute *anon_stats_attrs[] = {
        &anon_fault_alloc_attr.attr,
@@ -609,6 +610,7 @@ static struct attribute *anon_stats_attrs[] = {
 #endif
        &split_deferred_attr.attr,
        &nr_anon_attr.attr,
+       &nr_anon_partially_mapped_attr.attr,
        NULL,
 };
 
@@ -3457,6 +3459,7 @@ 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_PARTIALLY_MAPPED, -1);
                        /*
                         * Reinitialize page_deferred_list after removing the
                         * page from the split_queue, otherwise a subsequent
@@ -3523,6 +3526,7 @@ 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_PARTIALLY_MAPPED, -1);
                list_del_init(&folio->_deferred_list);
        }
        spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
@@ -3564,6 +3568,7 @@ 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_PARTIALLY_MAPPED, 1);
                list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
                ds_queue->split_queue_len++;
 #ifdef CONFIG_MEMCG
@@ -3611,6 +3616,7 @@ 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_PARTIALLY_MAPPED, -1);
                        list_del_init(&folio->_deferred_list);
                        ds_queue->split_queue_len--;
                }