Re: [PATCH v2 07/26] mm/fbatch: LRU_NEXT_ACTIVATE bit to optimize folio_activate()

Implement an equivalent to the old __lru_cache_activate_folio()
optimization, to activate a folio recently put in the lru_add fbatch,
without having to put it through the lru_activate fbatch too. Neither
lruvec lock nor lru bit can guard this safely and efficiently, so resort
to try_cmpxchg() on a further, LRU_NEXT_ACTIVATE bit in folio->lru_next.

Signed-off-by: Hugh Dickins <hughd@google.com>
---
 include/linux/mm_inline.h |  4 ++++
 mm/folio.c                | 23 ++++++++++++++++++++---
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 8420b1276535..8f5efadf9c7c 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h

@@ -346,6 +346,7 @@ static inline void folio_migrate_refs(struct folio *new, const struct folio *old
 enum {
 	LRU_NEXT_NEVER_TAIL = 0,	/* Used by a tail's compound_head */
 	LRU_NEXT_BATCHED = 1,		/* Not used by any aligned pointer */
+	LRU_NEXT_ACTIVATE,
 	NR_LRU_NEXT_FLAGS
 };

@@ -358,6 +359,9 @@ bool lru_add_del_folio(struct folio *folio)
 	if (!(lru_next & BIT(LRU_NEXT_BATCHED)))
 		return false;
 
+	if (lru_next & BIT(LRU_NEXT_ACTIVATE))
+		folio_set_active(folio);
+
 	WRITE_ONCE(folio->lru.next, LIST_POISON1);
 	/* BUG_ON(folio->lru_next & BIT(LRU_NEXT_BATCHED)); */
 

diff --git a/mm/folio.c b/mm/folio.c
index a18d8ef6afd5..0b75c3b69d5a 100644
--- a/mm/folio.c
+++ b/mm/folio.c

@@ -256,15 +256,32 @@ static void lru_activate(struct lruvec *lruvec, struct folio *folio)
 
 void folio_activate(struct folio *folio)
 {
+	unsigned long lru_next;
+
 	if (folio_test_active(folio) || folio_test_unevictable(folio) ||
 	    !folio_test_lru(folio))
 		return;
 
 	/*
-	 * XXX: It is curiously difficult to recreate safely the old
-	 * __lru_cache_activate_folio() optimization (folio_set_active()
-	 * directly if it's on the local lru_add fbatch): revisit later.
+	 * This optimization is intended for the common case of folio
+	 * having been recently added to this CPU's lru_add fbatch.
+	 * But since other CPUs can now take it at any instant (after
+	 * a folio_test_clear_lru()), and we may be migrated to another
+	 * CPU, it is simplest just to extend the optimization to all CPUs.
+	 *
+	 * folio_set_active() would be unsafe without the lruvec lock, and
+	 * a folio_test_clear_lru() here might cause a racing drain of the
+	 * lru_add fbatch to skip its lru_add(): so use try_cmpxchg().
 	 */
+	lru_next = READ_ONCE(folio->lru_next);
+	while (lru_next & BIT(LRU_NEXT_BATCHED)) {
+		if (lru_next & BIT(LRU_NEXT_ACTIVATE))
+			return;
+		if (try_cmpxchg(&folio->lru_next, &lru_next,
+				lru_next | BIT(LRU_NEXT_ACTIVATE)))
+			return;
+	}
+
 	folio_batch_add_and_move(folio, lru_activate);
 }