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/20231004165317.1061855-16-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

2 files changed, 30 insertions, 3 deletions

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5c02720c53a5..a88e64acebfe 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -693,6 +693,25 @@ 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.
  *
diff --git a/mm/filemap.c b/mm/filemap.c
index 458377e9a184..e9c636f57777 100644
--- a/mm/filemap.c
+++ b/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);