[PATCH v2 01/26] mm/fbatch: remove !CONFIG_SMP special case of folio_activate()

[Hugh Dickins <hughd@google.com>]

3.0 commit eb709b0d062e ("mm: batch activate_page() to reduce lock
contention") brought in an ifdef CONFIG_SMP around activate batching:
https://lore.kernel.org/linux-mm/20100805140755.501af8a7.akpm@linux-foundation.org/
shows a sensitivity to bloat that day, not any incompatibility with UP.

No other batching here has a UP alternative, and it's a bit confusing:
simplify mm/folio.c a little by removing it now.

Certainly we can reduce UP bloat (and/or 32-bit bloat) by, say, lowering
FOLIO_BATCH_SIZE from 31: traditionally 16, 14, 15, then raised to 31 by
6.9 commit 9cecde80aae0 ("mm: increase folio batch size"); or by giving
just the static per-cpu folio batches a type of their own with a smaller
array size on UP (1? or a little batching worthwhile even on UP?). But
not right now, it's orthogonal to this series.

And I suspect that the old ifdef led to lru_activate being placed last,
whereas it's usually the second most popular fbatch: move it there, to
match cpu_needs_drain() comment "Check these in order of likelihood that
they're not zero".

Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-By: Vlastimil Babka (SUSE) <vbabka@kernel.org>
---
 mm/folio.c | 40 ++++++----------------------------------
 1 file changed, 6 insertions(+), 34 deletions(-)

diff --git a/mm/folio.c b/mm/folio.c
index 50a6dbe55998..c093ca900a3e 100644
--- a/mm/folio.c
+++ b/mm/folio.c
@@ -48,12 +48,10 @@ struct cpu_fbatches {
 	 */
 	local_lock_t lock;
 	struct folio_batch lru_add;
+	struct folio_batch lru_activate;
 	struct folio_batch lru_deactivate_file;
 	struct folio_batch lru_deactivate;
 	struct folio_batch lru_lazyfree;
-#ifdef CONFIG_SMP
-	struct folio_batch lru_activate;
-#endif
 	/* Protecting the following batches which require disabling interrupts */
 	local_lock_t lock_irq;
 	struct folio_batch lru_move_tail;
@@ -283,15 +281,6 @@ static void lru_activate(struct lruvec *lruvec, struct folio *folio)
 	count_memcg_events(lruvec_memcg(lruvec), PGACTIVATE, nr_pages);
 }
 
-#ifdef CONFIG_SMP
-static void folio_activate_drain(int cpu)
-{
-	struct folio_batch *fbatch = &per_cpu(cpu_fbatches.lru_activate, cpu);
-
-	if (folio_batch_count(fbatch))
-		folio_batch_move_lru(fbatch, lru_activate);
-}
-
 void folio_activate(struct folio *folio)
 {
 	if (folio_test_active(folio) || folio_test_unevictable(folio) ||
@@ -301,25 +290,6 @@ void folio_activate(struct folio *folio)
 	folio_batch_add_and_move(folio, lru_activate);
 }
 
-#else
-static inline void folio_activate_drain(int cpu)
-{
-}
-
-void folio_activate(struct folio *folio)
-{
-	struct lruvec *lruvec;
-
-	if (!folio_test_clear_lru(folio))
-		return;
-
-	lruvec = folio_lruvec_lock_irq(folio);
-	lru_activate(lruvec, folio);
-	lruvec_unlock_irq(lruvec);
-	folio_set_lru(folio);
-}
-#endif
-
 static void __lru_cache_activate_folio(struct folio *folio)
 {
 	struct folio_batch *fbatch;
@@ -628,6 +598,10 @@ void lru_add_drain_cpu(int cpu)
 		trace_mm_lru_add_drain_tp(cpu, nr_folios);
 	}
 
+	fbatch = &fbatches->lru_activate;
+	if (folio_batch_count(fbatch))
+		folio_batch_move_lru(fbatch, lru_activate);
+
 	fbatch = &fbatches->lru_move_tail;
 	/* Disabling interrupts below acts as a compiler barrier. */
 	if (data_race(folio_batch_count(fbatch))) {
@@ -650,8 +624,6 @@ void lru_add_drain_cpu(int cpu)
 	fbatch = &fbatches->lru_lazyfree;
 	if (folio_batch_count(fbatch))
 		folio_batch_move_lru(fbatch, lru_lazyfree);
-
-	folio_activate_drain(cpu);
 }
 
 /**
@@ -759,11 +731,11 @@ static bool cpu_needs_drain(unsigned int cpu)
 
 	/* Check these in order of likelihood that they're not zero */
 	return data_race(folio_batch_count(&fbatches->lru_add) ||
+			 folio_batch_count(&fbatches->lru_activate) ||
 			 folio_batch_count(&fbatches->lru_move_tail) ||
 			 folio_batch_count(&fbatches->lru_deactivate_file) ||
 			 folio_batch_count(&fbatches->lru_deactivate) ||
 			 folio_batch_count(&fbatches->lru_lazyfree) ||
-			 folio_batch_count(&fbatches->lru_activate) ||
 			 need_mlock_drain(cpu)) ||
 		has_bh_in_lru(cpu, NULL);
 }
-- 
2.51.0