mm: add folio_xor_flags_has_waiters()

Optimise folio_end_read() by setting the uptodate bit at the same time we
clear the unlock bit.  This saves at least one memory barrier and one
write-after-write hazard.

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]>

Author: Matthew Wilcox (Oracle)

include/linux/page-flags.h

@@ -692,6 +692,25 @@ TESTPAGEFLAG_FALSE(Ksm, ksm)
 
 u64 stable_page_flags(struct page *page);
 
+/**
+ * folio_xor_flags_has_waiters - Change some folio flags.
+ * @folio: The folio.
+ * @mask: Bits set in this word will be changed.
+ *
+ * This must only be used for flags which are changed with the folio
+ * lock held.  For example, it is unsafe to use for PG_dirty as that
+ * can be set without the folio lock held.  It can also only be used
+ * on flags which are in the range 0-6 as some of the implementations
+ * only affect those bits.
+ *
+ * Return: Whether there are tasks waiting on the folio.
+ */
+static inline bool folio_xor_flags_has_waiters(struct folio *folio,
+		unsigned long mask)
+{
+	return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0));
+}
+
 /**
  * folio_test_uptodate - Is this folio up to date?
  * @folio: The folio.

mm/filemap.c

@@ -1497,7 +1497,7 @@ void folio_unlock(struct folio *folio)
 	BUILD_BUG_ON(PG_waiters != 7);
 	BUILD_BUG_ON(PG_locked > 7);
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
-	if (xor_unlock_is_negative_byte(1 << PG_locked, folio_flags(folio, 0)))
+	if (folio_xor_flags_has_waiters(folio, 1 << PG_locked))
 		folio_wake_bit(folio, PG_locked);
 }
 EXPORT_SYMBOL(folio_unlock);
@@ -1518,9 +1518,17 @@ EXPORT_SYMBOL(folio_unlock);
  */
 void folio_end_read(struct folio *folio, bool success)
 {
+	unsigned long mask = 1 << PG_locked;
+
+	/* Must be in bottom byte for x86 to work */
+	BUILD_BUG_ON(PG_uptodate > 7);
+	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+	VM_BUG_ON_FOLIO(folio_test_uptodate(folio), folio);
+
 	if (likely(success))
-		folio_mark_uptodate(folio);
-	folio_unlock(folio);
+		mask |= 1 << PG_uptodate;
+	if (folio_xor_flags_has_waiters(folio, mask))
+		folio_wake_bit(folio, PG_locked);
 }
 EXPORT_SYMBOL(folio_end_read);