[PATCH] xfs: avoid double deferrals for RWF_DONTCACHE writes

XFS already defers some writes to a workqueue when transactions are
needed to process the I/O completion. Disable the block layer bio task
completion in this case to avoid a major performance drop.

Fixes: efbde6f9f449 ("iomap: use BIO_COMPLETE_IN_TASK for dropbehind writeback")
Link: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Tal Zussman <[email protected]>
---
Follow-up fix for the RWF_DONTCACHE task-completion series. This is
targeting the block tree. [1]

[1]: https://lore.kernel.org/linux-block/[email protected]/
---
 fs/xfs/xfs_aops.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index cd8de8c82d78..74a6089abadf 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -549,10 +549,14 @@ xfs_writeback_submit(
 	}
 
 	/*
-	 * Send ioends that might require a transaction to the completion wq.
+	 * Send ioends that might require a transaction to the completion wq,
+	 * and disable the block layer task completion for them as there is no
+	 * need to defer twice.
 	 */
-	if (xfs_ioend_needs_wq_completion(ioend))
+	if (xfs_ioend_needs_wq_completion(ioend)) {
 		ioend->io_bio.bi_end_io = xfs_end_bio;
+		bio_clear_flag(&ioend->io_bio, BIO_COMPLETE_IN_TASK);
+	}
 
 	return iomap_ioend_writeback_submit(wpc, error);
 }
@@ -663,7 +667,14 @@ xfs_zoned_writeback_submit(
 {
 	struct iomap_ioend		*ioend = wpc->wb_ctx;
 
+	/*
+	 * Defer all completions to our workqueue as all zoned writes require a
+	 * transaction to be persisted. This also means we never need the block
+	 * layer in-task completion for a task context.
+	 */
 	ioend->io_bio.bi_end_io = xfs_end_bio;
+	bio_clear_flag(&ioend->io_bio, BIO_COMPLETE_IN_TASK);
+
 	if (error) {
 		ioend->io_bio.bi_status = errno_to_blk_status(error);
 		bio_endio(&ioend->io_bio);

---
base-commit: 30df3ab3c92d0e7854c54df6ae66f4aa6eb5b3d2
change-id: 20260810-xfs-dontcache-double-defer-ae3fa50ba02c

Best regards,
-- 
Tal Zussman <[email protected]>