mm/filemap: Add folio_lock()

This is like lock_page() but for use by callers who know they have a folio.
Convert __lock_page() to be __folio_lock().  This saves one call to
compound_head() per contended call to lock_page().

Saves 455 bytes of text; mostly from improved register allocation and
inlining decisions.  __folio_lock is 59 bytes while __lock_page was 79.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: William Kucharski <william.kucharski@oracle.com>
Reviewed-by: David Howells <dhowells@redhat.com>
Acked-by: Mike Rapoport <rppt@linux.ibm.com>

include/linux/pagemap.h

@@ -652,7 +652,7 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page,
 	return true;
 }
 
-extern void __lock_page(struct page *page);
+void __folio_lock(struct folio *folio);
 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,
@@ -660,13 +660,24 @@ extern int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 void unlock_page(struct page *page);
 void folio_unlock(struct folio *folio);
 
+static inline bool folio_trylock(struct folio *folio)
+{
+	return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0)));
+}
+
 /*
  * Return true if the page was successfully locked
  */
 static inline int trylock_page(struct page *page)
 {
-	page = compound_head(page);
-	return (likely(!test_and_set_bit_lock(PG_locked, &page->flags)));
+	return folio_trylock(page_folio(page));
+}
+
+static inline void folio_lock(struct folio *folio)
+{
+	might_sleep();
+	if (!folio_trylock(folio))
+		__folio_lock(folio);
 }
 
 /*
@@ -674,9 +685,12 @@ static inline int trylock_page(struct page *page)
  */
 static inline void lock_page(struct page *page)
 {
+	struct folio *folio;
 	might_sleep();
-	if (!trylock_page(page))
-		__lock_page(page);
+
+	folio = page_folio(page);
+	if (!folio_trylock(folio))
+		__folio_lock(folio);
 }
 
 /*

mm/filemap.c

@@ -1242,7 +1242,7 @@ static void wake_up_page(struct page *page, int bit)
  */
 enum behavior {
 	EXCLUSIVE,	/* Hold ref to page and take the bit when woken, like
-			 * __lock_page() waiting on then setting PG_locked.
+			 * __folio_lock() waiting on then setting PG_locked.
 			 */
 	SHARED,		/* Hold ref to page and check the bit when woken, like
 			 * wait_on_page_writeback() waiting on PG_writeback.
@@ -1633,17 +1633,16 @@ void page_endio(struct page *page, bool is_write, int err)
 EXPORT_SYMBOL_GPL(page_endio);
 
 /**
- * __lock_page - get a lock on the page, assuming we need to sleep to get it
- * @__page: the page to lock
+ * __folio_lock - Get a lock on the folio, assuming we need to sleep to get it.
+ * @folio: The folio to lock
  */
-void __lock_page(struct page *__page)
+void __folio_lock(struct folio *folio)
 {
-	struct page *page = compound_head(__page);
-	wait_queue_head_t *q = page_waitqueue(page);
-	wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
+	wait_queue_head_t *q = page_waitqueue(&folio->page);
+	wait_on_page_bit_common(q, &folio->page, PG_locked, TASK_UNINTERRUPTIBLE,
 				EXCLUSIVE);
 }
-EXPORT_SYMBOL(__lock_page);
+EXPORT_SYMBOL(__folio_lock);
 
 int __lock_page_killable(struct page *__page)
 {
@@ -1718,10 +1717,10 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
 			return 0;
 		}
 	} else {
-		__lock_page(page);
+		__folio_lock(page_folio(page));
 	}
-	return 1;
 
+	return 1;
 }
 
 /**
@@ -2915,7 +2914,9 @@ loff_t mapping_seek_hole_data(struct address_space *mapping, loff_t start,
 static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
 				     struct file **fpin)
 {
-	if (trylock_page(page))
+	struct folio *folio = page_folio(page);
+
+	if (folio_trylock(folio))
 		return 1;
 
 	/*
@@ -2928,7 +2929,7 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
 
 	*fpin = maybe_unlock_mmap_for_io(vmf, *fpin);
 	if (vmf->flags & FAULT_FLAG_KILLABLE) {
-		if (__lock_page_killable(page)) {
+		if (__lock_page_killable(&folio->page)) {
 			/*
 			 * We didn't have the right flags to drop the mmap_lock,
 			 * but all fault_handlers only check for fatal signals
@@ -2940,11 +2941,11 @@ static int lock_page_maybe_drop_mmap(struct vm_fault *vmf, struct page *page,
 			return 0;
 		}
 	} else
-		__lock_page(page);
+		__folio_lock(folio);
+
 	return 1;
 }
 
-
 /*
  * Synchronous readahead happens when we don't even find a page in the page
  * cache at all.  We don't want to perform IO under the mmap sem, so if we have