It doesn't seem necessary to have the redundant layer of splitting.
The request size will even be more consistent / aligned to the cap.

Signed-off-by: Tom Yan <redacted>
---
  block/blk-lib.c   | 5 ++++-
  block/blk-merge.c | 2 +-
  block/blk.h       | 8 ++++++--
  3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index e90614fd8d6a..f606184a9050 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c

@@ -85,9 +85,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
  		 *   is split in device drive, the split ones are very probably
  		 *   to be aligned to discard_granularity of the device's queue.
  		 */
-		if (granularity_aligned_lba == sector_mapped)
+		if (granularity_aligned_lba == sector_mapped) {
  			req_sects = min_t(sector_t, nr_sects,
  					  bio_aligned_discard_max_sectors(q));
+			if (!req_sects)
+				return -EOPNOTSUPP;
+		}
  		else