diff --git a/include/linux/swap.h b/include/linux/swap.h
index 330a420fd6de..b4b1c0a84c8b 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -298,6 +298,14 @@ void folio_add_lru(struct folio *folio);
 void folio_mark_accessed(struct folio *folio);
 void lru_add_drain_all(void);
 
+enum lru_cache_drained {
+	LRU_CACHE_NOT_DRAINED,
+	LRU_CACHE_DRAINED,
+	LRU_CACHE_DRAINED_ALL,
+};
+void lru_cache_drain_for_folio(const struct folio *folio,
+		unsigned int extra_refs, enum lru_cache_drained *drained);
+
 /* linux/mm/folio-compat.c */
 void mark_page_accessed(struct page *page);
 
diff --git a/mm/folio.c b/mm/folio.c
index a9e328c3f21b..59c477120b9a 100644
--- a/mm/folio.c
+++ b/mm/folio.c
@@ -881,6 +881,52 @@ void lru_add_drain_all(void)
 }
 #endif /* CONFIG_SMP */
 
+/**
+ * lru_cache_drain_for_folio() - drain LRU caches if the caches might hold
+ *				 folio references
+ * @folio: The folio.
+ * @extra_refs: Extra folio references held by the caller.
+ * @drained: Drain status for batch folio processing.
+ *
+ * Drain LRU caches if the caches might hold folio references. Start
+ * with a local LRU cache drain, to then drain LRU caches on all CPUs if
+ * local draining was insufficient.
+ *
+ * This function detects LRU cache references by comparing the folio refcount
+ * with the sum of the expected folio refcount + extra references held by the
+ * caller. Note that we cannot rely on PG_lru to reliably detect all LRU
+ * cache references, and there are rare scenarios (concurrent folio (un)mapping)
+ * where this function might miss detecting LRU cache references.
+ *
+ * If @drained is not NULL, the function will avoid re-draining LRU caches
+ * when processing multiple folios in a row. In that case, the variable
+ * @drained points at must be initialized to LRU_CACHE_NOT_DRAINED before
+ * the first invocation by the caller.
+ */
+void lru_cache_drain_for_folio(const struct folio *folio,
+		unsigned int extra_refs, enum lru_cache_drained *drained)
+{
+	if (!folio_may_be_lru_cached(folio))
+		return;
+
+	if (!drained || *drained == LRU_CACHE_NOT_DRAINED) {
+		if (folio_ref_count(folio) ==
+		    folio_expected_ref_count(folio) + extra_refs)
+			return;
+		lru_add_drain();
+		if (drained)
+			*drained = LRU_CACHE_DRAINED;
+	}
+	if (!drained || *drained == LRU_CACHE_DRAINED) {
+		if (folio_ref_count(folio) ==
+		    folio_expected_ref_count(folio) + extra_refs)
+			return;
+		lru_add_drain_all();
+		if (drained)
+			*drained = LRU_CACHE_DRAINED_ALL;
+	}
+}
+
 atomic_t lru_disable_count = ATOMIC_INIT(0);
 
 /*
diff --git a/mm/gup.c b/mm/gup.c
index bce275c7dbb6..eb898ea1ee22 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2266,9 +2266,9 @@ static unsigned long collect_longterm_unpinnable_folios(
 		struct list_head *movable_folio_list,
 		struct pages_or_folios *pofs)
 {
+	enum lru_cache_drained drained = LRU_CACHE_NOT_DRAINED;
 	unsigned long collected = 0;
 	struct folio *folio;
-	int drained = 0;
 	long i = 0;
 
 	for (folio = pofs_get_folio(pofs, i); folio;
@@ -2293,18 +2293,7 @@ static unsigned long collect_longterm_unpinnable_folios(
 		 * but also to remove any other folio references from LRU
 		 * caches.
 		 */
-		if (drained == 0 && folio_may_be_lru_cached(folio) &&
-				folio_ref_count(folio) !=
-				folio_expected_ref_count(folio) + pin_refs) {
-			lru_add_drain();
-			drained = 1;
-		}
-		if (drained == 1 && folio_may_be_lru_cached(folio) &&
-				folio_ref_count(folio) !=
-				folio_expected_ref_count(folio) + pin_refs) {
-			lru_add_drain_all();
-			drained = 2;
-		}
+		lru_cache_drain_for_folio(folio, pin_refs, &drained);
 
 		if (!folio_isolate_lru(folio))
 			continue;
diff --git a/mm/internal.h b/mm/internal.h
index 07f60ca0b201..38b1165212c9 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -43,7 +43,7 @@ void workingset_activation(struct folio *folio);
 /* mm/folio.c */
 void folio_add_lru_vma(struct folio *folio, struct vm_area_struct *vma);
 
-static inline bool folio_may_be_lru_cached(struct folio *folio)
+static inline bool folio_may_be_lru_cached(const struct folio *folio)
 {
 	/*
 	 * Holding PMD-sized folios in per-CPU LRU cache unbalances accounting.