[PATCH 4/7] mm: Revert "mm/gup: clear the LRU flag of a page before adding to LRU batch"

[Hugh Dickins <hughd@google.com>]

This reverts commit 33dfe9204f29b415bbc0abb1a50642d1ba94f5e9:
now that collect_longterm_unpinnable_folios() is checking ref_count
instead of lru, and mlock/munlock do not participate in the revised
LRU flag clearing, those changes are misleading, and enlarge the
window during which mlock/munlock may miss an mlock_count update.

It is possible (I'd hesitate to claim probable) that the greater
likelihood of missed mlock_count updates would explain the "Realtime
threads delayed due to kcompactd0" observed on 6.12 in the Link below.
If that is the case, this reversion will help; but a complete solution
needs also a further patch, beyond the scope of this series.

Included some 80-column cleanup around folio_batch_add_and_move().

The role of folio_test_clear_lru() (before taking per-memcg lru_lock)
is questionable since 6.13 removed mem_cgroup_move_account() etc; but
perhaps there are still some races which need it - not examined here.

Link: https://lore.kernel.org/linux-mm/DU0PR01MB10385345F7153F334100981888259A@DU0PR01MB10385.eurprd01.prod.exchangelabs.com/
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
---
 mm/swap.c | 50 ++++++++++++++++++++++++++------------------------
 1 file changed, 26 insertions(+), 24 deletions(-)

diff --git a/mm/swap.c b/mm/swap.c
index 3632dd061beb..6ae2d5680574 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -164,6 +164,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 	for (i = 0; i < folio_batch_count(fbatch); i++) {
 		struct folio *folio = fbatch->folios[i];
 
+		/* block memcg migration while the folio moves between lru */
+		if (move_fn != lru_add && !folio_test_clear_lru(folio))
+			continue;
+
 		folio_lruvec_relock_irqsave(folio, &lruvec, &flags);
 		move_fn(lruvec, folio);
 
@@ -176,14 +180,10 @@ static void folio_batch_move_lru(struct folio_batch *fbatch, move_fn_t move_fn)
 }
 
 static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
-		struct folio *folio, move_fn_t move_fn,
-		bool on_lru, bool disable_irq)
+		struct folio *folio, move_fn_t move_fn, bool disable_irq)
 {
 	unsigned long flags;
 
-	if (on_lru && !folio_test_clear_lru(folio))
-		return;
-
 	folio_get(folio);
 
 	if (disable_irq)
@@ -191,8 +191,8 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
 	else
 		local_lock(&cpu_fbatches.lock);
 
-	if (!folio_batch_add(this_cpu_ptr(fbatch), folio) || folio_test_large(folio) ||
-	    lru_cache_disabled())
+	if (!folio_batch_add(this_cpu_ptr(fbatch), folio) ||
+			folio_test_large(folio) || lru_cache_disabled())
 		folio_batch_move_lru(this_cpu_ptr(fbatch), move_fn);
 
 	if (disable_irq)
@@ -201,13 +201,13 @@ static void __folio_batch_add_and_move(struct folio_batch __percpu *fbatch,
 		local_unlock(&cpu_fbatches.lock);
 }
 
-#define folio_batch_add_and_move(folio, op, on_lru)						\
-	__folio_batch_add_and_move(								\
-		&cpu_fbatches.op,								\
-		folio,										\
-		op,										\
-		on_lru,										\
-		offsetof(struct cpu_fbatches, op) >= offsetof(struct cpu_fbatches, lock_irq)	\
+#define folio_batch_add_and_move(folio, op)		\
+	__folio_batch_add_and_move(			\
+		&cpu_fbatches.op,			\
+		folio,					\
+		op,					\
+		offsetof(struct cpu_fbatches, op) >=	\
+		offsetof(struct cpu_fbatches, lock_irq)	\
 	)
 
 static void lru_move_tail(struct lruvec *lruvec, struct folio *folio)
@@ -231,10 +231,10 @@ static void lru_move_tail(struct lruvec *lruvec, struct folio *folio)
 void folio_rotate_reclaimable(struct folio *folio)
 {
 	if (folio_test_locked(folio) || folio_test_dirty(folio) ||
-	    folio_test_unevictable(folio))
+	    folio_test_unevictable(folio) || !folio_test_lru(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_move_tail, true);
+	folio_batch_add_and_move(folio, lru_move_tail);
 }
 
 void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file,
@@ -328,10 +328,11 @@ static void folio_activate_drain(int cpu)
 
 void folio_activate(struct folio *folio)
 {
-	if (folio_test_active(folio) || folio_test_unevictable(folio))
+	if (folio_test_active(folio) || folio_test_unevictable(folio) ||
+	    !folio_test_lru(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_activate, true);
+	folio_batch_add_and_move(folio, lru_activate);
 }
 
 #else
@@ -507,7 +508,7 @@ void folio_add_lru(struct folio *folio)
 	    lru_gen_in_fault() && !(current->flags & PF_MEMALLOC))
 		folio_set_active(folio);
 
-	folio_batch_add_and_move(folio, lru_add, false);
+	folio_batch_add_and_move(folio, lru_add);
 }
 EXPORT_SYMBOL(folio_add_lru);
 
@@ -685,13 +686,13 @@ void lru_add_drain_cpu(int cpu)
 void deactivate_file_folio(struct folio *folio)
 {
 	/* Deactivating an unevictable folio will not accelerate reclaim */
-	if (folio_test_unevictable(folio))
+	if (folio_test_unevictable(folio) || !folio_test_lru(folio))
 		return;
 
 	if (lru_gen_enabled() && lru_gen_clear_refs(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_deactivate_file, true);
+	folio_batch_add_and_move(folio, lru_deactivate_file);
 }
 
 /*
@@ -704,13 +705,13 @@ void deactivate_file_folio(struct folio *folio)
  */
 void folio_deactivate(struct folio *folio)
 {
-	if (folio_test_unevictable(folio))
+	if (folio_test_unevictable(folio) || !folio_test_lru(folio))
 		return;
 
 	if (lru_gen_enabled() ? lru_gen_clear_refs(folio) : !folio_test_active(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_deactivate, true);
+	folio_batch_add_and_move(folio, lru_deactivate);
 }
 
 /**
@@ -723,10 +724,11 @@ void folio_deactivate(struct folio *folio)
 void folio_mark_lazyfree(struct folio *folio)
 {
 	if (!folio_test_anon(folio) || !folio_test_swapbacked(folio) ||
+	    !folio_test_lru(folio) ||
 	    folio_test_swapcache(folio) || folio_test_unevictable(folio))
 		return;
 
-	folio_batch_add_and_move(folio, lru_lazyfree, true);
+	folio_batch_add_and_move(folio, lru_lazyfree);
 }
 
 void lru_add_drain(void)
-- 
2.51.0