1 files changed, 34 insertions, 4 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index a91d5ad27984..90ad3006ef3a 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -902,7 +902,30 @@ static void submit_extent_page(struct btrfs_bio_ctrl *bio_ctrl,
 		size -= len;
 		pg_offset += len;
 		disk_bytenr += len;
-		bio_ctrl->len_to_oe_boundary -= len;
+
+		/*
+		 * len_to_oe_boundary defaults to U32_MAX, which isn't page or
+		 * sector aligned.  alloc_new_bio() then sets it to the end of
+		 * our ordered extent for writes into zoned devices.
+		 *
+		 * When len_to_oe_boundary is tracking an ordered extent, we
+		 * trust the ordered extent code to align things properly, and
+		 * the check above to cap our write to the ordered extent
+		 * boundary is correct.
+		 *
+		 * When len_to_oe_boundary is U32_MAX, the cap above would
+		 * result in a 4095 byte IO for the last page right before
+		 * we hit the bio limit of UINT_MAX.  bio_add_page() has all
+		 * the checks required to make sure we don't overflow the bio,
+		 * and we should just ignore len_to_oe_boundary completely
+		 * unless we're using it to track an ordered extent.
+		 *
+		 * It's pretty hard to make a bio sized U32_MAX, but it can
+		 * happen when the page cache is able to feed us contiguous
+		 * pages for large extents.
+		 */
+		if (bio_ctrl->len_to_oe_boundary != U32_MAX)
+			bio_ctrl->len_to_oe_boundary -= len;
 
 		/* Ordered extent boundary: move on to a new bio. */
 		if (bio_ctrl->len_to_oe_boundary == 0)
@@ -2145,6 +2168,12 @@ retry:
 				continue;
 			}
 
+			if (!folio_test_dirty(folio)) {
+				/* Someone wrote it for us. */
+				folio_unlock(folio);
+				continue;
+			}
+
 			if (wbc->sync_mode != WB_SYNC_NONE) {
 				if (folio_test_writeback(folio))
 					submit_write_bio(bio_ctrl, 0);
@@ -2164,11 +2193,12 @@ retry:
 			}
 
 			/*
-			 * the filesystem may choose to bump up nr_to_write.
+			 * The filesystem may choose to bump up nr_to_write.
 			 * We have to make sure to honor the new nr_to_write
-			 * at any time
+			 * at any time.
 			 */
-			nr_to_write_done = wbc->nr_to_write <= 0;
+			nr_to_write_done = (wbc->sync_mode == WB_SYNC_NONE &&
+					    wbc->nr_to_write <= 0);
 		}
 		folio_batch_release(&fbatch);
 		cond_resched();