btrfs: rework page locking in __extent_writepage()

Pages passed to __extent_writepage() are always locked, but they may be
locked by different functions.

There are two types of locked page for __extent_writepage():

- Page locked by plain lock_page()
  It should not have any subpage::writers count.
  Can be unlocked by unlock_page().
  This is the most common locked page for __extent_writepage() called
  inside extent_write_cache_pages() or extent_write_full_page().
  Rarer cases include the @locked_page from extent_write_locked_range().

- Page locked by lock_delalloc_pages()
  There is only one caller, all pages except @locked_page for
  extent_write_locked_range().
  In this case, we have to call subpage helper to handle the case.

So here we introduce a helper, btrfs_page_unlock_writer(), to allow
__extent_writepage() to unlock different locked pages.

And since for all other callers of __extent_writepage() their pages are
ensured to be locked by lock_page(), also add an extra check for
epd::extent_locked to unlock such pages directly.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/extent_io.c

@@ -4051,6 +4051,7 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 			      struct extent_page_data *epd)
 {
 	struct inode *inode = page->mapping->host;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	const u64 page_start = page_offset(page);
 	const u64 page_end = page_start + PAGE_SIZE - 1;
 	int ret;
@@ -4138,7 +4139,19 @@ static int __extent_writepage(struct page *page, struct writeback_control *wbc,
 	 */
 	if (PageError(page))
 		end_extent_writepage(page, ret, page_start, page_end);
-	unlock_page(page);
+	if (epd->extent_locked) {
+		/*
+		 * If epd->extent_locked, it's from extent_write_locked_range(),
+		 * the page can either be locked by lock_page() or
+		 * process_one_page().
+		 * Let btrfs_page_unlock_writer() handle both cases.
+		 */
+		ASSERT(wbc);
+		btrfs_page_unlock_writer(fs_info, page, wbc->range_start,
+					 wbc->range_end + 1 - wbc->range_start);
+	} else {
+		unlock_page(page);
+	}
 	ASSERT(ret <= 0);
 	return ret;
 }

fs/btrfs/subpage.c

@@ -690,3 +690,46 @@ void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
 	ASSERT(PagePrivate(page) && page->private);
 	ASSERT(subpage_test_bitmap_all_zero(fs_info, subpage, dirty));
 }
+
+/*
+ * Handle different locked pages with different page sizes:
+ *
+ * - Page locked by plain lock_page()
+ *   It should not have any subpage::writers count.
+ *   Can be unlocked by unlock_page().
+ *   This is the most common locked page for __extent_writepage() called
+ *   inside extent_write_cache_pages() or extent_write_full_page().
+ *   Rarer cases include the @locked_page from extent_write_locked_range().
+ *
+ * - Page locked by lock_delalloc_pages()
+ *   There is only one caller, all pages except @locked_page for
+ *   extent_write_locked_range().
+ *   In this case, we have to call subpage helper to handle the case.
+ */
+void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page,
+			      u64 start, u32 len)
+{
+	struct btrfs_subpage *subpage;
+
+	ASSERT(PageLocked(page));
+	/* For regular page size case, we just unlock the page */
+	if (fs_info->sectorsize == PAGE_SIZE)
+		return unlock_page(page);
+
+	ASSERT(PagePrivate(page) && page->private);
+	subpage = (struct btrfs_subpage *)page->private;
+
+	/*
+	 * For subpage case, there are two types of locked page.  With or
+	 * without writers number.
+	 *
+	 * Since we own the page lock, no one else could touch subpage::writers
+	 * and we are safe to do several atomic operations without spinlock.
+	 */
+	if (atomic_read(&subpage->writers))
+		/* No writers, locked by plain lock_page() */
+		return unlock_page(page);
+
+	/* Have writers, use proper subpage helper to end it */
+	btrfs_page_end_writer_lock(fs_info, page, start, len);
+}

fs/btrfs/subpage.h

@@ -150,5 +150,7 @@ bool btrfs_subpage_clear_and_test_dirty(const struct btrfs_fs_info *fs_info,
 
 void btrfs_page_assert_not_dirty(const struct btrfs_fs_info *fs_info,
 				 struct page *page);
+void btrfs_page_unlock_writer(struct btrfs_fs_info *fs_info, struct page *page,
+			      u64 start, u32 len);
 
 #endif