There are two sites are not subpage compatible yet for
extent_write_locked_range():

- How @nr_pages are calculated
  For subpage we can have the following range with 64K page size:

  0   32K  64K   96K 128K
  |   |////|/////|   |

  In that case, although 96K - 32K == 64K, thus it looks like one page
  is enough, but the range spans across two pages, not one.

  Fix it by doing proper round_up() and round_down() to calculate
  @nr_pages.

  Also add some extra ASSERT()s to ensure the range passed in is already
  aligned.

- How the page end is calculated
  Currently we just use cur + PAGE_SIZE - 1 to calculate the page end.

  Which can't handle above range layout, and will trigger ASSERT() in
  btrfs_writepage_endio_finish_ordered(), as the range is no longer
  covered by the page range.

  Fix it by take page end into consideration.

Signed-off-by: Qu Wenruo <redacted>
---
 fs/btrfs/extent_io.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 825917f1b623..f05d8896d1ad 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c

@@ -5087,15 +5087,14 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)
 	struct address_space *mapping = inode->i_mapping;
 	struct page *page;
 	u64 cur = start;
-	unsigned long nr_pages = (end - start + PAGE_SIZE) >>
-		PAGE_SHIFT;
+	unsigned long nr_pages;
+	const u32 sectorsize = btrfs_sb(inode->i_sb)->sectorsize;
 	struct extent_page_data epd = {
 		.bio_ctrl = { 0 },
 		.extent_locked = 1,
 		.sync_io = 1,
 	};
 	struct writeback_control wbc_writepages = {
-		.nr_to_write	= nr_pages * 2,
 		.sync_mode	= WB_SYNC_ALL,
 		.range_start	= start,
 		.range_end	= end + 1,

@@ -5104,14 +5103,24 @@ int extent_write_locked_range(struct inode *inode, u64 start, u64 end)
 		.no_cgroup_owner = 1,
 	};
 
+	ASSERT(IS_ALIGNED(start, sectorsize) &&
+	       IS_ALIGNED(end + 1, sectorsize));
+	nr_pages = (round_up(end, PAGE_SIZE) - round_down(start, PAGE_SIZE)) >>
+		   PAGE_SHIFT;
+	wbc_writepages.nr_to_write = nr_pages * 2;
+
 	wbc_attach_fdatawrite_inode(&wbc_writepages, inode);
 	while (cur <= end) {
+		u64 cur_end = min(round_down(cur, PAGE_SIZE) + PAGE_SIZE - 1,
+				  end);
+
 		page = find_get_page(mapping, cur >> PAGE_SHIFT);
 		/*
 		 * All pages in the range are locked since
 		 * btrfs_run_delalloc_range(), thus there is no way to clear
 		 * the page dirty flag.
 		 */
+		ASSERT(PageLocked(page));