mm: use folio_xor_flags_has_waiters() in folio_end_writeback()

mainline inclusion
from mainline-v6.7-rc1
category: performance

Match how folio_unlock() works by combining the test for PG_waiters with
the clearing of PG_writeback.  This should have a small performance win,
and removes the last user of folio_wake().

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Matthew Wilcox (Oracle) <[email protected]>
Cc: Albert Ou <[email protected]>
Cc: Alexander Gordeev <[email protected]>
Cc: Andreas Dilger <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Cc: Christophe Leroy <[email protected]>
Cc: Geert Uytterhoeven <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Ivan Kokshaysky <[email protected]>
Cc: Matt Turner <[email protected]>
Cc: Michael Ellerman <[email protected]>
Cc: Nicholas Piggin <[email protected]>
Cc: Palmer Dabbelt <[email protected]>
Cc: Paul Walmsley <[email protected]>
Cc: Richard Henderson <[email protected]>
Cc: Sven Schnelle <[email protected]>
Cc: "Theodore Ts'o" <[email protected]>
Cc: Thomas Bogendoerfer <[email protected]>
Cc: Vasily Gorbik <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
(cherry picked from commit 2580d55)
Signed-off-by: Wentao Guan <[email protected]>

Author: Matthew Wilcox (Oracle)

mm/filemap.c

@@ -1205,13 +1205,6 @@ static void folio_wake_bit(struct folio *folio, int bit_nr)
 	spin_unlock_irqrestore(&q->lock, flags);
 }
 
-static void folio_wake(struct folio *folio, int bit)
-{
-	if (!folio_test_waiters(folio))
-		return;
-	folio_wake_bit(folio, bit);
-}
-
 /*
  * A choice of three behaviors for folio_wait_bit_common():
  */
@@ -1648,13 +1641,11 @@ void folio_end_writeback(struct folio *folio)
 	 * Writeback does not hold a folio reference of its own, relying
 	 * on truncation to wait for the clearing of PG_writeback.
 	 * But here we must make sure that the folio is not freed and
-	 * reused before the folio_wake().
+	 * reused before the folio_wake_bit().
 	 */
 	folio_get(folio);
-	__folio_end_writeback(folio);
-
-	smp_mb__after_atomic();
-	folio_wake(folio, PG_writeback);
+	if (__folio_end_writeback(folio))
+		folio_wake_bit(folio, PG_writeback);
 	acct_reclaim_writeback(folio);
 	folio_put(folio);
 }

mm/internal.h

@@ -150,7 +150,7 @@ static inline void wake_throttle_isolated(pg_data_t *pgdat)
 
 vm_fault_t do_swap_page(struct vm_fault *vmf);
 void folio_rotate_reclaimable(struct folio *folio);
-void __folio_end_writeback(struct folio *folio);
+bool __folio_end_writeback(struct folio *folio);
 void deactivate_file_folio(struct folio *folio);
 void folio_activate(struct folio *folio);
 

mm/page-writeback.c

@@ -2995,10 +2995,11 @@ static void wb_inode_writeback_end(struct bdi_writeback *wb)
 	spin_unlock_irqrestore(&wb->work_lock, flags);
 }
 
-void __folio_end_writeback(struct folio *folio)
+bool __folio_end_writeback(struct folio *folio)
 {
 	long nr = folio_nr_pages(folio);
 	struct address_space *mapping = folio_mapping(folio);
+	bool ret;
 
 	folio_memcg_lock(folio);
 	if (mapping && mapping_use_writeback_tags(mapping)) {
@@ -3007,7 +3008,7 @@ void __folio_end_writeback(struct folio *folio)
 		unsigned long flags;
 
 		xa_lock_irqsave(&mapping->i_pages, flags);
-		folio_test_clear_writeback(folio);
+		ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback);
 		__xa_clear_mark(&mapping->i_pages, folio_index(folio),
 					PAGECACHE_TAG_WRITEBACK);
 		if (bdi->capabilities & BDI_CAP_WRITEBACK_ACCT) {
@@ -3025,13 +3026,15 @@ void __folio_end_writeback(struct folio *folio)
 
 		xa_unlock_irqrestore(&mapping->i_pages, flags);
 	} else {
-		folio_test_clear_writeback(folio);
+		ret = folio_xor_flags_has_waiters(folio, 1 << PG_writeback);
 	}
 
 	lruvec_stat_mod_folio(folio, NR_WRITEBACK, -nr);
 	zone_stat_mod_folio(folio, NR_ZONE_WRITE_PENDING, -nr);
 	node_stat_mod_folio(folio, NR_WRITTEN, nr);
 	folio_memcg_unlock(folio);
+
+	return ret;
 }
 
 bool __folio_start_writeback(struct folio *folio, bool keep_write)