[PATCH 23/25] fs,mm/fbatch: use invalidate_bh_lrus() not invalidate_bh_lrus_cpu()

Whilst there can be a case for including an invalidate_bh_lrus_cpu() in
lru_add_drain_all()'s workqueued visits to remote CPUs, wouldn't it now
be a preferable cleanup to remove that alternative, and stick with the
smp_call_function_many_cond()-based invalidate_bh_lrus() throughout?

And fix the UP lru_add_drain_all() to include an invalidate_bh_lrus(),
which went missing when 5.15 commit 243418e3925d ("mm: fs: invalidate
bh_lrus for only cold path") took that out of lru_add_drain().

Signed-off-by: Hugh Dickins <[email protected]>
---
 fs/buffer.c                 | 16 +---------------
 include/linux/buffer_head.h |  4 ----
 mm/folio.c                  | 25 ++++++-------------------
 3 files changed, 7 insertions(+), 38 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index ed966fa73b1b..7d114e5b9c62 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1427,7 +1427,7 @@ static void invalidate_bh_lru(void *arg)
 	put_cpu_var(bh_lrus);
 }
 
-bool has_bh_in_lru(int cpu, void *dummy)
+static bool has_bh_in_lru(int cpu, void *dummy)
 {
 	struct bh_lru *b = per_cpu_ptr(&bh_lrus, cpu);
 	int i;
@@ -1446,20 +1446,6 @@ void invalidate_bh_lrus(void)
 }
 EXPORT_SYMBOL_GPL(invalidate_bh_lrus);
 
-/*
- * It's called from workqueue context so we need a bh_lru_lock to close
- * the race with preemption/irq.
- */
-void invalidate_bh_lrus_cpu(void)
-{
-	struct bh_lru *b;
-
-	bh_lru_lock();
-	b = this_cpu_ptr(&bh_lrus);
-	__invalidate_bh_lrus(b);
-	bh_lru_unlock();
-}
-
 void folio_set_bh(struct buffer_head *bh, struct folio *folio,
 		  unsigned long offset)
 {
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index fd2c7115c054..f19f9e80be8f 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -518,8 +518,6 @@ bool mmb_has_buffers(struct mapping_metadata_bhs *mmb);
 void mmb_invalidate(struct mapping_metadata_bhs *mmb);
 int mmb_sync(struct mapping_metadata_bhs *mmb);
 void invalidate_bh_lrus(void);
-void invalidate_bh_lrus_cpu(void);
-bool has_bh_in_lru(int cpu, void *dummy);
 extern int buffer_heads_over_limit;
 
 #else /* CONFIG_BUFFER_HEAD */
@@ -528,8 +526,6 @@ static inline void buffer_init(void) {}
 static inline bool try_to_free_buffers(struct folio *folio) { return true; }
 static inline int mmb_sync(struct mapping_metadata_bhs *mmb) { return 0; }
 static inline void invalidate_bh_lrus(void) {}
-static inline void invalidate_bh_lrus_cpu(void) {}
-static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
 #define buffer_heads_over_limit 0
 
 #endif /* CONFIG_BUFFER_HEAD */
diff --git a/mm/folio.c b/mm/folio.c
index 782b8245d213..3212c7a58623 100644
--- a/mm/folio.c
+++ b/mm/folio.c
@@ -748,21 +748,6 @@ void lru_add_drain(void)
 	mlock_drain_local();
 }
 
-/*
- * It's called from per-cpu workqueue context in SMP case so
- * lru_add_drain_cpu and invalidate_bh_lrus_cpu should run on
- * the same cpu. It shouldn't be a problem in !SMP case since
- * the core is only one and the locks will disable preemption.
- */
-static void lru_add_and_bh_lrus_drain(void)
-{
-	local_lock(&cpu_fbatches.lock);
-	lru_add_drain_cpu(smp_processor_id());
-	local_unlock(&cpu_fbatches.lock);
-	invalidate_bh_lrus_cpu();
-	mlock_drain_local();
-}
-
 void lru_add_drain_cpu_zone(struct zone *zone)
 {
 	local_lock(&cpu_fbatches.lock);
@@ -778,7 +763,7 @@ static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work);
 
 static void lru_add_drain_per_cpu(struct work_struct *dummy)
 {
-	lru_add_and_bh_lrus_drain();
+	lru_add_drain();
 }
 
 static bool cpu_needs_drain(unsigned int cpu)
@@ -791,8 +776,7 @@ static bool cpu_needs_drain(unsigned int cpu)
 			 folio_batch_count(&fbatches->lru_move_tail) ||
 			 folio_batch_count(&fbatches->lru_deactivate_file) ||
 			 folio_batch_count(&fbatches->lru_deactivate) ||
-			 need_mlock_drain(cpu)) ||
-		has_bh_in_lru(cpu, NULL);
+			 need_mlock_drain(cpu));
 }
 
 /*
@@ -891,6 +875,8 @@ static inline void __lru_add_drain_all(bool force_all_cpus)
 		}
 	}
 
+	invalidate_bh_lrus();
+
 	for_each_cpu(cpu, &has_work)
 		flush_work(&per_cpu(lru_add_drain_work, cpu));
 
@@ -906,6 +892,7 @@ void lru_add_drain_all(void)
 void lru_add_drain_all(void)
 {
 	lru_add_drain();
+	invalidate_bh_lrus();
 }
 #endif /* CONFIG_SMP */
 
@@ -939,7 +926,7 @@ void lru_cache_disable(void)
 #ifdef CONFIG_SMP
 	__lru_add_drain_all(true);
 #else
-	lru_add_and_bh_lrus_drain();
+	lru_add_drain_all();
 #endif
 }
 
-- 
2.51.0