[v2,15/17] mm: Add folio_xor_flags_has_waiters()

Commit Message

Matthew Wilcox (Oracle) Oct. 4, 2023, 4:53 p.m. UTC

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.

Signed-off-by: Matthew Wilcox (Oracle) <[e-mail]>
---
 include/linux/page-flags.h | 19 +++++++++++++++++++
 mm/filemap.c               | 14 +++++++++++---
 2 files changed, 30 insertions(+), 3 deletions(-)

Patch

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
@@ -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.
diff --git a/mm/filemap.c b/mm/filemap.c
index ab8f798eb0af..3dad2615af41 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1499,7 +1499,7 @@  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);
@@ -1520,9 +1520,17 @@  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);