mm: folio_may_be_lru_cached() unless folio_test_large()

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_lru_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".

Link: https://lkml.kernel.org/r/[email protected]
Fixes: 9a4e9f3 ("mm: update get_user_pages_longterm to migrate pages allocated from CMA region")
Signed-off-by: Hugh Dickins <[email protected]>
Suggested-by: David Hildenbrand <[email protected]>
Acked-by: David Hildenbrand <[email protected]>
Cc: "Aneesh Kumar K.V" <[email protected]>
Cc: Axel Rasmussen <[email protected]>
Cc: Chris Li <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Jason Gunthorpe <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: John Hubbard <[email protected]>
Cc: Keir Fraser <[email protected]>
Cc: Konstantin Khlebnikov <[email protected]>
Cc: Li Zhe <[email protected]>
Cc: Matthew Wilcox (Oracle) <[email protected]>
Cc: Peter Xu <[email protected]>
Cc: Rik van Riel <[email protected]>
Cc: Shivank Garg <[email protected]>
Cc: Vlastimil Babka <[email protected]>
Cc: Wei Xu <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: yangge <[email protected]>
Cc: Yuanchu Xie <[email protected]>
Cc: Yu Zhao <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: Hugh Dickins

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_lru_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)

mm/gup.c

@@ -2307,13 +2307,13 @@ static unsigned long collect_longterm_unpinnable_folios(
 			continue;
 		}
 
-		if (drained == 0 &&
+		if (drained == 0 && folio_may_be_lru_cached(folio) &&
 				folio_ref_count(folio) !=
 				folio_expected_ref_count(folio) + 1) {
 			lru_add_drain();
 			drained = 1;
 		}
-		if (drained == 1 &&
+		if (drained == 1 && folio_may_be_lru_cached(folio) &&
 				folio_ref_count(folio) !=
 				folio_expected_ref_count(folio) + 1) {
 			lru_add_drain_all();

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_lru_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_lru_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_lru_cached(folio) || lru_cache_disabled())
 		mlock_folio_batch(fbatch);
 	local_unlock(&mlock_fbatch.lock);
 }

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_lru_cached(folio) || lru_cache_disabled())
 		folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
 
 	if (disable_irq)