[PATCH v4 12/25] mm/filemap: Add unlock_folio

["Matthew Wilcox (Oracle)" <willy@infradead.org>]

Convert unlock_page() to call unlock_folio().  By using a folio we
avoid a call to compound_head().  This shortens the function from 39
bytes to 25 and removes 4 instructions on x86-64.  Because we still
have unlock_page(), it's a net increase of 24 bytes of text.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
 include/linux/pagemap.h |  3 ++-
 mm/filemap.c            | 27 ++++++++++-----------------
 mm/folio-compat.c       |  6 ++++++
 3 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 5a2c0764d7c0..a34cf531c100 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -640,7 +640,8 @@ extern int __lock_page_killable(struct page *page);
 extern int __lock_page_async(struct page *page, struct wait_page_queue *wait);
 extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 				unsigned int flags);
-extern void unlock_page(struct page *page);
+void unlock_page(struct page *page);
+void unlock_folio(struct folio *folio);
 
 /*
  * Return true if the page was successfully locked
diff --git a/mm/filemap.c b/mm/filemap.c
index 3d1635d3be3e..9960ef1b2758 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1408,29 +1408,22 @@ static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile void *mem
 #endif
 
 /**
- * unlock_page - unlock a locked page
- * @page: the page
+ * unlock_folio - Unlock a locked folio.
+ * @folio: The folio.
  *
- * Unlocks the page and wakes up sleepers in wait_on_page_locked().
- * Also wakes sleepers in wait_on_page_writeback() because the wakeup
- * mechanism between PageLocked pages and PageWriteback pages is shared.
- * But that's OK - sleepers in wait_on_page_writeback() just go back to sleep.
+ * Unlocks the folio and wakes up any thread sleeping on the page lock.
  *
- * Note that this depends on PG_waiters being the sign bit in the byte
- * that contains PG_locked - thus the BUILD_BUG_ON(). That allows us to
- * clear the PG_locked bit and test PG_waiters at the same time fairly
- * portably (architectures that do LL/SC can test any bit, while x86 can
- * test the sign bit).
+ * Context: May be called from interrupt or process context.  May not be
+ * called from NMI context.
  */
-void unlock_page(struct page *page)
+void unlock_folio(struct folio *folio)
 {
 	BUILD_BUG_ON(PG_waiters != 7);
-	page = compound_head(page);
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	if (clear_bit_unlock_is_negative_byte(PG_locked, &page->flags))
-		wake_up_page_bit(page, PG_locked);
+	VM_BUG_ON_FOLIO(!FolioLocked(folio), folio);
+	if (clear_bit_unlock_is_negative_byte(PG_locked, folio_flags(folio)))
+		wake_up_page_bit(&folio->page, PG_locked);
 }
-EXPORT_SYMBOL(unlock_page);
+EXPORT_SYMBOL(unlock_folio);
 
 /**
  * end_page_writeback - end writeback against a page
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 5e107aa30a62..02798abf19a1 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -11,3 +11,9 @@ struct address_space *page_mapping(struct page *page)
 	return folio_mapping(page_folio(page));
 }
 EXPORT_SYMBOL(page_mapping);
+
+void unlock_page(struct page *page)
+{
+	return unlock_folio(page_folio(page));
+}
+EXPORT_SYMBOL(unlock_page);
-- 
2.30.0