btrfs: make set/clear_extent_buffer_dirty() subpage compatible

For set_extent_buffer_dirty() to support subpage sized metadata, just
call btrfs_page_set_dirty() to handle both cases.

For clear_extent_buffer_dirty(), it needs to clear the page dirty if and
only if all extent buffers in the page range are no longer dirty.
Also do the same for page error.

This is pretty different from the existing clear_extent_buffer_dirty()
routine, so add a new helper function,
clear_subpage_extent_buffer_dirty() to do this for subpage metadata.

Also since the main part of clearing page dirty code is still the same,
extract that into btree_clear_page_dirty() so that it can be utilized
for both cases.

But there is a special race between set_extent_buffer_dirty() and
clear_extent_buffer_dirty(), where we can clear the page dirty.

[POSSIBLE RACE WINDOW]
For the race window between clear_subpage_extent_buffer_dirty() and
set_extent_buffer_dirty(), due to the fact that we can't call
clear_page_dirty_for_io() under subpage spin lock, we can race like
below:

   T1 (eb1 in the same page)	|  T2 (eb2 in the same page)
 -------------------------------+------------------------------
 set_extent_buffer_dirty()	| clear_extent_buffer_dirty()
 |- was_dirty = false;		| |- clear_subpagE_extent_buffer_dirty()
 |				|    |- btrfs_clear_and_test_dirty()
 |				|    |  Since eb2 is the last dirty page
 |				|    |  we got:
 |				|    |  last == true;
 |				|    |
 |- btrfs_page_set_dirty()	|    |
 |  We set the page dirty and   |    |
 |  subpage dirty bitmap	|    |
 |				|    |- if (last)
 |				|    |  Since we don't have subpage lock
 |				|    |  held, now @last is no longer
 |				|    |  correct
 |				|    |- btree_clear_page_dirty()
 |				|	Now PageDirty == false, even if
 |				|       we have dirty_bitmap not zero.
 |- ASSERT(PageDirty());	|
    ^^^^ CRASH

The solution here is to also lock the eb->pages[0] for subpage case of
set_extent_buffer_dirty(), to prevent racing with
clear_extent_buffer_dirty().
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/extent_io.c

@@ -5814,28 +5814,51 @@ void free_extent_buffer_stale(struct extent_buffer *eb)
 	release_extent_buffer(eb);
 }
 
+static void btree_clear_page_dirty(struct page *page)
+{
+	ASSERT(PageDirty(page));
+	ASSERT(PageLocked(page));
+	clear_page_dirty_for_io(page);
+	xa_lock_irq(&page->mapping->i_pages);
+	if (!PageDirty(page))
+		__xa_clear_mark(&page->mapping->i_pages,
+				page_index(page), PAGECACHE_TAG_DIRTY);
+	xa_unlock_irq(&page->mapping->i_pages);
+}
+
+static void clear_subpage_extent_buffer_dirty(const struct extent_buffer *eb)
+{
+	struct btrfs_fs_info *fs_info = eb->fs_info;
+	struct page *page = eb->pages[0];
+	bool last;
+
+	/* btree_clear_page_dirty() needs page locked */
+	lock_page(page);
+	last = btrfs_subpage_clear_and_test_dirty(fs_info, page, eb->start,
+						  eb->len);
+	if (last)
+		btree_clear_page_dirty(page);
+	unlock_page(page);
+	WARN_ON(atomic_read(&eb->refs) == 0);
+}
+
 void clear_extent_buffer_dirty(const struct extent_buffer *eb)
 {
 	int i;
 	int num_pages;
 	struct page *page;
 
+	if (eb->fs_info->sectorsize < PAGE_SIZE)
+		return clear_subpage_extent_buffer_dirty(eb);
+
 	num_pages = num_extent_pages(eb);
 
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (!PageDirty(page))
 			continue;
-
 		lock_page(page);
-		WARN_ON(!PagePrivate(page));
-
-		clear_page_dirty_for_io(page);
-		xa_lock_irq(&page->mapping->i_pages);
-		if (!PageDirty(page))
-			__xa_clear_mark(&page->mapping->i_pages,
-					page_index(page), PAGECACHE_TAG_DIRTY);
-		xa_unlock_irq(&page->mapping->i_pages);
+		btree_clear_page_dirty(page);
 		ClearPageError(page);
 		unlock_page(page);
 	}
@@ -5856,10 +5879,28 @@ bool set_extent_buffer_dirty(struct extent_buffer *eb)
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
 
-	if (!was_dirty)
-		for (i = 0; i < num_pages; i++)
-			set_page_dirty(eb->pages[i]);
+	if (!was_dirty) {
+		bool subpage = eb->fs_info->sectorsize < PAGE_SIZE;
 
+		/*
+		 * For subpage case, we can have other extent buffers in the
+		 * same page, and in clear_subpage_extent_buffer_dirty() we
+		 * have to clear page dirty without subpage lock held.
+		 * This can cause race where our page gets dirty cleared after
+		 * we just set it.
+		 *
+		 * Thankfully, clear_subpage_extent_buffer_dirty() has locked
+		 * its page for other reasons, we can use page lock to prevent
+		 * the above race.
+		 */
+		if (subpage)
+			lock_page(eb->pages[0]);
+		for (i = 0; i < num_pages; i++)
+			btrfs_page_set_dirty(eb->fs_info, eb->pages[i],
+					     eb->start, eb->len);
+		if (subpage)
+			unlock_page(eb->pages[0]);
+	}
 #ifdef CONFIG_BTRFS_DEBUG
 	for (i = 0; i < num_pages; i++)
 		ASSERT(PageDirty(eb->pages[i]));