[PATCH 6/7] mm: folio_may_be_cached() unless folio_test_large()

[Hugh Dickins <hughd@google.com>]

mm/swap.c and mm/mlock.c agree to drain any per-CPU batch as soon as
a large folio is added: so collect_longterm_unpinnable_folios() just
wastes effort when calling lru_add_drain_all() on a large folio.

But although there is good reason not to batch up PMD-sized folios,
we might well benefit from batching a small number of low-order mTHPs
(though unclear how that "small number" limitation will be implemented).

So ask if folio_may_be_cached() rather than !folio_test_large(), to
insulate those particular checks from future change.  Name preferred
to "folio_is_batchable" because large folios can well be put on a batch:
it's just the per-CPU LRU caches, drained much later, which need care.

Marked for stable, to counter the increase in lru_add_drain_all()s
from "mm/gup: check ref_count instead of lru before migration".

Suggested-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
---
 include/linux/swap.h | 10 ++++++++++
 mm/gup.c             |  5 +++--
 mm/mlock.c           |  6 +++---
 mm/swap.c            |  2 +-
 4 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 2fe6ed2cc3fd..b49a61c32238 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -385,6 +385,16 @@ void folio_add_lru_vma(struct folio *, struct vm_area_struct *);
 void mark_page_accessed(struct page *);
 void folio_mark_accessed(struct folio *);
 
+static inline bool folio_may_be_cached(struct folio *folio)
+{
+	/*
+	 * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting.
+	 * Holding small numbers of low-order mTHP folios in per-CPU LRU cache
+	 * will be sensible, but nobody has implemented and tested that yet.
+	 */
+	return !folio_test_large(folio);
+}
+
 extern atomic_t lru_disable_count;
 
 static inline bool lru_cache_disabled(void)
diff --git a/mm/gup.c b/mm/gup.c
index 9f7c87f504a9..e70544c0f958 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2309,8 +2309,9 @@ static unsigned long collect_longterm_unpinnable_folios(
 			continue;
 		}
 
-		if (drain_allow && folio_ref_count(folio) !=
-				   folio_expected_ref_count(folio) + 1) {
+		if (drain_allow && folio_may_be_cached(folio) &&
+				folio_ref_count(folio) !=
+				folio_expected_ref_count(folio) + 1) {
 			lru_add_drain_all();
 			drain_allow = false;
 		}
diff --git a/mm/mlock.c b/mm/mlock.c
index a1d93ad33c6d..427339dea380 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -255,7 +255,7 @@ void mlock_folio(struct folio *folio)
 
 	folio_get(folio);
 	if (!folio_batch_add(fbatch, mlock_lru(folio)) ||
-	    folio_test_large(folio) || lru_cache_disabled())
+	    !folio_may_be_cached(folio) || lru_cache_disabled())
 		mlock_folio_batch(fbatch);
 	local_unlock(&mlock_fbatch.lock);
 }
@@ -278,7 +278,7 @@ void mlock_new_folio(struct folio *folio)
 
 	folio_get(folio);
 	if (!folio_batch_add(fbatch, mlock_new(folio)) ||
-	    folio_test_large(folio) || lru_cache_disabled())
+	    !folio_may_be_cached(folio) || lru_cache_disabled())
 		mlock_folio_batch(fbatch);
 	local_unlock(&mlock_fbatch.lock);
 }
@@ -299,7 +299,7 @@ void munlock_folio(struct folio *folio)
 	 */
 	folio_get(folio);
 	if (!folio_batch_add(fbatch, folio) ||
-	    folio_test_large(folio) || lru_cache_disabled())
+	    !folio_may_be_cached(folio) || lru_cache_disabled())
 		mlock_folio_batch(fbatch);
 	local_unlock(&mlock_fbatch.lock);
 }
diff --git a/mm/swap.c b/mm/swap.c
index 6ae2d5680574..17438fd1f51a 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -192,7 +192,7 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
 		local_lock(&cpu_fbatches.lock);
 
 	if (!folio_batch_add(this_cpu_ptr(fbatch), folio) ||
-			folio_test_large(folio) || lru_cache_disabled())
+			!folio_may_be_cached(folio) || lru_cache_disabled())
 		folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
 
 	if (disable_irq)
-- 
2.51.0